Blood Information Prediction Device

Abstract

The purpose of the present invention is to provide a blood information estimating apparatus for determining the condition of a user's blood, such as blood pressure.　A blood information estimating apparatus 100 is provided with a data acquiring function 41 which functions as a log acquiring unit for acquiring a terminal utilization log of a user terminal, such as a mobile terminal, and a high blood pressure detecting function 45 which functions as an estimating unit for estimating, on the basis of the terminal utilization log, blood information relating to variations in blood condition. The blood information estimating apparatus 100 is provided with a high blood pressure detecting model that outputs blood information corresponding to the terminal utilization log. The high blood pressure detecting function 45 utilizes the high blood pressure detecting model to estimate the blood information. This configuration makes it possible to estimate the blood condition without burdening the user with an examination. This also makes it possible to easily estimate the condition of masked hypertension, for example.

Description

Technical Field

[0001] The present invention relates to a blood information estimation device for estimating a user's blood state.

Background Art

[0002] Patent Document 1 describes a method for detecting changes in a patient's health status, particularly for predicting the risk of changes in a patient's medical symptoms based on the usage log of a native communication application and a health risk model.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Among health risks, hypertension may have no symptoms. In general blood pressure measurements in a clinic, only one point in time during the examination is focused on. Since blood pressure changes depending on the environment where the measurer is placed and the measurement timing, it is possible to miss the existence of health risks such as hypertension. That is, when continuously measuring blood pressure at home, it is possible to measure blood pressure that can be judged as hypertension, while when measuring blood pressure in a clinic or the like, it may not be possible to measure blood pressure that can be judged as hypertension. Such a blood pressure state is called masked hypertension. On the other hand, in the technique described in Patent Document 1, although there is a description of predicting health risks, it does not grasp states such as blood pressure, and it is difficult to judge masked hypertension or the like.

[0005] Therefore, in order to solve the above problems, an object of the present invention is to provide a blood information estimation device that determines the state of blood, such as a user's blood pressure. [Means for solving the problem]

[0006] The blood information estimation device of the present invention comprises a log acquisition unit that acquires usage logs of a user terminal such as a smartphone, and a blood information estimation unit that estimates blood information related to changes in the blood condition based on the usage logs.

[0007] According to this invention, blood information such as blood pressure can be estimated without the user having to actively undergo testing. [Effects of the Invention]

[0008] According to the present invention, blood information can be estimated without the user having to actively undergo testing. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows the functional configuration of the blood information estimation device 100 in this disclosure. [Figure 2] This diagram shows the functional configuration of the terminal usage log acquisition unit 20. [Figure 3] This diagram shows the functional configuration of the weather information acquisition unit 30. [Figure 4] This diagram shows the functional configuration of the hypertension detection unit 40. [Figure 5] This diagram shows the relationship between device usage logs and lifestyle habits. [Figure 6] This figure shows the training data stored in the training data storage database 40a. [Figure 7] This is a flowchart showing the operation of the hypertension detection unit 40. [Figure 8] This is a flowchart showing the process for building the hypertension detection model 44a. [Figure 9] This is a flowchart showing the hypertension detection process using hypertension detection model 44a. [Figure 10] This figure shows an example of the hardware configuration of a blood information estimation device 100 according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0010] Embodiments of this disclosure will be described with reference to the attached drawings. Where possible, the same parts will be denoted by the same reference numerals, and redundant descriptions will be omitted.

[0011] Figure 1 shows the functional configuration of the blood information estimation device 100 in this disclosure. This blood information estimation device 100 includes a terminal usage log acquisition unit 20, a weather information acquisition unit 30, and a hypertension detection unit 40.

[0012] The terminal usage log acquisition unit 20 is responsible for acquiring terminal usage logs of user terminals operated by user 10, as well as user attribute information of the user of said user terminal.

[0013] The weather information acquisition unit 30 is responsible for acquiring weather information for the area where user 10 is located.

[0014] The hypertension detection unit 40 is the part that detects the blood pressure status of user 10 based on the terminal usage log acquisition unit 20 and the weather information acquisition unit 30, respectively, which acquire the terminal usage log, user attribute information, and weather information. In this disclosure, hypertension is assumed as the blood pressure status, but it is not limited to that. In addition to blood pressure, other blood conditions such as blood glucose levels, triglycerides, and cholesterol levels may also be detected.

[0015] Next, the configuration of the terminal usage log acquisition unit 20 will be described. Figure 2 is a diagram showing the functional configuration of the terminal usage log acquisition unit 20. The terminal usage log acquisition unit 20 is composed of a user authentication function 21, a user attribute information acquisition function 22, an application usage information acquisition function 23, a purchase history information acquisition function 24, a location information acquisition function 25, a terminal operation information acquisition function 26, and a data transfer function 27.

[0016] The user authentication function 21 is a function that authenticates whether the user of the user terminal is a properly registered user when obtaining user attribute information or terminal usage logs from the user terminal. The user terminal is a wearable terminal (such as a watch type, glasses type, etc.), in addition to a mobile terminal, a smartphone, etc.

[0017] The user attribute information acquisition function 22 is a function that directly acquires user attribute information from the user terminal or user 10. The user attribute information is user attribute information such as the user's age, gender, etc., which can affect the state of the blood.

[0018] The app usage information acquisition function 23 is a function that acquires the number of steps, sleep time, weight, etc. of the user obtained in a healthcare-related application (hereinafter abbreviated as a healthcare-related app) as terminal usage logs. The healthcare-related app can measure the number of steps by using the gyro function provided in the user terminal and / or the declared value input by the user to the app. Also, by using the operation history of the user terminal or the above gyro, the behavior of the user terminal is measured, and the time period during which the behavior cannot be measured is measured as the sleep time. Alternatively, the sleep time may be obtained based on the declared value input by the user to the app. The weight may be estimated from an image of the user's face, etc., or may be obtained based on the declared value input by the user to the app or the measured value of the measuring device linked to the user terminal. The app usage information acquisition function 23 can measure body temperature and pulse by using a healthcare-related app or obtain them from the user's input. Also, the app usage information acquisition function 23 can acquire the camera image taken by the camera provided in the terminal as a usage log.

[0019] The purchase history information acquisition function 24 acquires the purchase history information for which a purchase has been made using the payment function of the user terminal as terminal usage logs. The payment function is payment using a QR code, or payment using a contactless IC card, etc. The purchase history information includes purchase store information, purchase amount, purchased goods, and date, etc.

[0020] The location information acquisition function 25 is a function that acquires the user's current location as a terminal usage log, and acquires location based on GPS information or base station location information measured on the user's terminal, or WiFi access point.

[0021] The terminal operation information acquisition function 26 is a function that acquires terminal operation information as a terminal usage log. Terminal operation information includes information such as screen on / off, acceleration, brightness, viewed URLs, and applications used. Terminal operation information is stored as history on the user's terminal, and the terminal operation information acquisition function 26 acquires this history.

[0022] The data transfer function 27 is a function that transfers user attribute information and terminal usage logs acquired by each acquisition function to the hypertension detection unit 40.

[0023] Next, the functional configuration of the weather information acquisition unit 30 will be described. Figure 3 is a diagram showing the functional configuration of the weather information acquisition unit 30. The weather information acquisition unit 30 includes a user authentication function 31, a user location information acquisition function 32, a weather information acquisition function 33, and a data transfer function 34.

[0024] The user authentication function 31 is a function that authenticates the user. When acquiring weather information, it is necessary to know the user's location, and user authentication is performed at that time.

[0025] The user location information acquisition function 32 is a function that acquires the user's location information. The location information is acquired from a mobile communication network server that manages the location of the user terminal, or from the user terminal.

[0026] The weather information acquisition function 33 is a function that acquires weather information corresponding to the user's location information from the weather information database 30a.

[0027] The data transfer function 34 is a function that transfers acquired weather information to the hypertension detection unit 40.

[0028] Next, the hypertension detection unit 40 will be described. Figure 4 is a diagram showing the functional configuration of the hypertension detection unit 40. The hypertension detection unit 40 consists of a data acquisition function 41 (log information acquisition unit), a data cleansing function 42, a lifestyle estimation function 43, a hypertension detection model construction function 44 (learning unit), a hypertension detection function 45 (blood information estimation unit), and a result notification function 46.

[0029] The data acquisition function 41 is a function that acquires terminal usage logs, user attribute information, and weather information from the terminal usage log acquisition unit 20 and the weather information acquisition unit 30, respectively. The data acquisition function 41 acquires terminal usage logs, etc., acquired by the terminal usage log acquisition unit 20 and the weather information acquisition unit 30 for a predetermined period of time at any time or periodically. User attribute information does not need to be collected if it is stored in advance. Alternatively, it may be collected once and then stored.

[0030] The data cleansing function 42 is a function that performs cleansing on missing values, abnormal values, etc., in terminal usage logs and weather information acquired over a predetermined period.

[0031] The lifestyle habit estimation function 43 is a function that estimates lifestyle habits such as exercise volume, commuting / schooling method / time / pattern, stress, fatigue level, regularity of lifestyle / sleep, frequency of eating out, salt intake, and calorie intake, based on terminal usage logs and user attribute information. In addition, the lifestyle habit estimation function 43 may also estimate happiness level based on terminal usage logs and user attribute information. Happiness level is calculated by comprehensively considering factors such as exercise volume, commuting / schooling method, stress, and fatigue level.

[0032] This section explains the relationship between user attribute information and device usage logs when deriving lifestyle habits. Figure 5 shows the relationship between device usage logs and lifestyle habits. The lifestyle habit estimation function 43 estimates lifestyle habits based on the relationship shown in Figure 5. Exercise as a lifestyle habit is indicated by, for example, calories burned, and is estimated based on user attributes and device usage logs, specifically age, gender, steps, GPS information, base station location information, and acceleration. Commuting / schooling method / time / pattern indicates commuting time, etc., and is estimated based on GPS information and base station location information. For example, the distance between home and work / school, the travel time, and the travel route are determined based on travel time, travel speed, and location, and from there the commuting / schooling method is estimated. Stress indicates the degree of stress, for example, indicated on a 10-point scale. Stress is estimated based on a stress estimation algorithm, using purchase store information, purchase amount, purchased items, screen on / off information, illumination, viewed URLs, and used application information. Fatigue level indicates the degree of fatigue and is estimated based on age, gender, and sleep duration. Shorter sleep duration is estimated to indicate a higher level of fatigue. Regularity of lifestyle / sleep indicates the degree of regularity and is estimated based on step count, sleep duration, GPS information, base station location information, and screen on / off status. Frequency of eating out indicates the number of times meals are eaten out and is estimated based on store information, purchased items, GPS information, and base station location information. Salt intake indicates a specific numerical value or its extent and is estimated based on store information and purchased items. Calorie intake indicates a specific numerical value or its extent and is estimated based on weight, store information, purchase amount, and purchased items. Note that the above is an example and can be modified as needed.

[0033] The lifestyle habit estimation function 43 estimates lifestyle habits based on the usage logs of each device. The lifestyle habit estimation function 43 determines lifestyle habits based on a predetermined algorithm. For example, the lifestyle habit estimation function 43 calculates the amount of exercise based on the number of steps taken.

[0034] The hypertension detection model construction function 44 is a function that constructs a hypertension detection model (hypertension prediction model) based on training data stored in the training data storage database 40a. The training data is compiled in advance by a healthcare application installed on each user terminal.

[0035] Figure 6 shows the training data stored in the training data storage database 40a. As shown in the figure, user attribute information, terminal usage logs, lifestyle information, weather information, and blood pressure information are stored for each user and date and time. This training data is data provided in advance by the users, and each user provides information for a predetermined period (e.g., several months). The hypertension detection model construction function 44 constructs a hypertension detection model by performing machine learning with user attribute information, terminal usage logs, lifestyle information, and weather information as explanatory variables and blood pressure information (either the average value for the predetermined period or a binary value indicating whether or not the person has hypertension based on that average value) as the objective variable. In addition to, or instead of, blood pressure information, blood glucose level information, triglyceride information, or cholesterol information may be stored and used as the objective variable to construct an estimation model.

[0036] The hypertension detection model building function 44 may build a hypertension detection model 44a for each user attribute information. For example, the hypertension detection model building function 44 may learn the hypertension detection model 44a by separating terminal usage logs and blood information by age and / or gender.

[0037] The hypertension detection function 45 inputs terminal usage logs, weather information, and user attribute information acquired by the data acquisition function 41, as well as lifestyle information estimated by the lifestyle estimation function 43, into a hypertension detection model. It then estimates blood pressure information as its output and detects hypertension. While inputting terminal usage logs is important, considering lifestyle information, weather information, and user attribute information in addition to terminal usage logs will further improve accuracy.

[0038] The result notification function 46 is a function that notifies the user of blood pressure information. For example, the result notification function 46 notifies the user of blood pressure information on the user's terminal. In addition to blood pressure information, if the result notification function 46 estimates blood glucose level information, triglyceride information, and cholesterol information, it also notifies the user of that blood glucose level information, triglyceride information, and cholesterol information. Furthermore, the result notification function 46 may notify the user of lifestyle habits that may increase their risk of hypertension, among the lifestyle habits estimated by the lifestyle habit estimation function 43.

[0039] Next, the operation of the hypertension detection unit 40 in this disclosure will be described. Figure 7 is a flowchart of its operation. The data acquisition function 41 acquires from the user terminal terminal the terminal usage log for a predetermined period of time for which hypertension is to be estimated, which has been acquired by the terminal usage log acquisition unit 20, and weather information for the user's location, which has been acquired by the weather information acquisition unit 30 (S100).

[0040] The data cleansing function 42 performs cleansing on the terminal usage logs and weather information acquired in processing S100, such as removing outliers and interpolating missing values ​​(S101).

[0041] The hypertension detection model construction function 44 constructs a hypertension detection model 44a from training data for any predetermined period stored in the training data storage database 40a (S102).

[0042] The lifestyle habit estimation function 43 estimates lifestyle habits based on terminal usage logs (S103). For example, the lifestyle habit estimation function 43 estimates lifestyle habits based on the relationship shown in Figure 5.

[0043] The hypertension detection function 45 inputs the terminal usage log, lifestyle habits, and weather information of the user's location to the hypertension detection model 44a, and the hypertension detection model 44a outputs blood pressure information, which is the result of hypertension detection (S104).

[0044] The result notification function 46 notifies the user terminal of the hypertension detection result (S105). In the above process, the hypertension detection model 44a is constructed in process 102, but this process is not necessarily required. The hypertension detection model 44a may be constructed in advance, and process S103 may be executed after process S101.

[0045] Next, the process of constructing the hypertension detection model 44a in the above process S102 will be explained in more detail. Figure 8 is a flowchart showing the detailed process of the hypertension detection model construction function 44. The hypertension detection model construction function 44 acquires training data (including training usage logs, training lifestyle information, training blood information, etc.) from the training data stored in the training data storage database 40a for an arbitrary period, such as user attributes, terminal usage logs, lifestyle information, weather information, and blood information (in this case, blood pressure values) (S103-1).

[0046] Next, the hypertension detection model building function 44 averages the blood pressure values, which are multiple for each user, for the acquired data (S103-2). The training data includes multiple data (blood information) over time for the same user, and by calculating the average value, temporary outliers are eliminated. Alternatively, the median or a moving average over an arbitrary point in time may be used instead of the average value.

[0047] The hypertension detection model construction function 44 labels each user as having hypertension (and may also include the degree of hypertension) based on the averaged blood pressure value (S103-3). The hypertension detection model construction function 44 constructs a hypertension detection model 44a that estimates the averaged blood pressure value or hypertension label from each user's terminal usage log, lifestyle habits, and weather information of their location in the training data (S103-4). For example, the hypertension detection model construction function 44 performs machine learning with each user's terminal usage log, lifestyle habits, and weather information of their location as explanatory variables and the blood pressure value or hypertension label as the dependent variable. In this disclosure, the machine learning method used is not limited. For example, it may be a classical linear model, or it may be a method such as SVM, XGBoost, or LightGBM, or it may be a deep learning method such as DNN.

[0048] In this way, the hypertension detection model building function 44 can learn the hypertension detection model 44a based on the terminal usage logs of the user terminal.

[0049] Next, we will explain process S104, which is a hypertension detection process using this hypertension detection model 44a. Figure 9 is a flowchart of this process. The hypertension detection function 45 inputs the terminal usage log, lifestyle habits, and weather information of the user's location to the hypertension detection model 44a (S104-1). The lifestyle habits here are the information estimated in S103.

[0050] The hypertension detection function 45 receives the user's blood pressure value or a label indicating whether or not they have hypertension (or the probability of having hypertension or the blood pressure value) from the hypertension detection model 44a (S104-2).

[0051] Furthermore, the hypertension detection function 45 identifies lifestyle habits that may cause hypertension or increase the risk of hypertension for the user (S104-3). The hypertension detection model construction function 44 may identify lifestyle habits that increase the risk of hypertension from the magnitude of coefficients related to each feature of the hypertension detection model 44a (for example, the weight coefficients of the intermediate layer in machine learning), or it may identify such lifestyle habits from an index that evaluates the importance of features using an interpretation method of a machine learning prediction model such as LIME or SHAP. For example, if the user has hypertension (or has a high probability of having hypertension), the hypertension detection function 45 estimates which lifestyle habits, such as the user's low exercise level or high stress level, influenced or did not influence the output of the hypertension detection model construction function 44, i.e., the label indicating whether or not the user has hypertension (or the probability of having hypertension or blood pressure value).

[0052] Next, the effects of the blood information estimation device 100 in this disclosure will be explained. The blood information estimation device 100 in this disclosure includes a data acquisition function 41 that functions as a log acquisition unit that acquires terminal usage logs of a user terminal such as a mobile terminal, and a hypertension detection function 45 that functions as an estimation unit that estimates blood information related to changes in blood condition based on the terminal usage logs.

[0053] This configuration allows for the estimation of blood conditions (blood pressure, blood glucose levels, triglycerides, or cholesterol) without imposing any testing burden on the user. Therefore, conditions such as masked hypertension can also be easily estimated.

[0054] In the explanation above, blood status was estimated by considering user attribute information, weather information, and lifestyle information, but at the very least, terminal usage logs should be used.

[0055] The blood information estimation device 100 of this disclosure includes at least one of blood pressure, blood glucose level, triglycerides, and cholesterol as blood information.

[0056] Furthermore, the blood information estimation device 100 of this disclosure estimates blood information using at least one of the following as terminal usage logs: step count, sleep time, location information, screen on / off information, acceleration, illuminance, viewed URLs, purchase history, or application usage information.

[0057] In the blood information estimation device 100 of this disclosure, the lifestyle estimation function 43 estimates lifestyle information including at least one of the user's exercise amount, exercise time, calories burned, sleep time, sleep quality, regularity, and stress based on terminal usage logs, and the hypertension detection function 45 estimates blood information based on said lifestyle information.

[0058] This configuration allows for the estimation of blood information while taking lifestyle habits into account, enabling more accurate estimation of blood information.

[0059] The blood information estimation device 100 of this disclosure includes a hypertension detection model that outputs blood information according to the terminal usage log. The hypertension detection function 45 estimates blood information using the hypertension detection model.

[0060] In the blood information estimation device 100 of this disclosure, the hypertension detection model construction function 44 constructs a hypertension detection model by learning based on the average value of blood information over a predetermined period as the blood information during learning.

[0061] Blood information, particularly blood pressure, blood glucose levels, triglyceride levels, and cholesterol levels, fluctuates. Therefore, building a hypertension detection model based on only one point in time will not allow for accurate estimation. For example, training a model based solely on blood pressure data collected in a doctor's office will not yield accurate estimation results. In this disclosure, the estimation accuracy can be improved by training the model based on the average value of blood pressure data.

[0062] The hypertension detection model building function 44 of this disclosure may learn a hypertension detection model based on terminal usage logs and blood information for a predetermined age and / or gender, and the hypertension detection function 45 may apply the hypertension detection model according to the user's age and / or gender to estimate blood information.

[0063] This configuration allows for the application of age- and gender-specific models, enabling highly accurate estimations.

[0064] The hypertension detection function 45 of this disclosure identifies the lifestyle habits that formed the basis of the estimated blood information. For example, if hypertension is detected, it identifies the lifestyle habits that contributed to that determination. The hypertension detection function 45 can identify lifestyle habits by using an interpretation method (LIME or SHAP) to determine how the hypertension detection model 44a interpreted the information.

[0065] This allows us to identify the reasons for a diagnosis of high blood pressure in the user's lifestyle and encourage them to make improvements.

[0066] The block diagram used in the description of the above embodiment shows functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining the above one device or the above multiple devices with software.

[0067] Functions include, but are not limited to, judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. As mentioned above, the method of implementation is not particularly limited.

[0068] For example, the blood information estimation device 100 in one embodiment of the present disclosure may function as a computer that processes the blood information estimation method of the present disclosure. Figure 10 is a diagram showing an example of the hardware configuration of the blood information estimation device 100 according to one embodiment of the present disclosure. The blood information estimation device 100 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0069] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the blood information estimation device 100 may include one or more of the devices shown in the figure, or it may be configured without some of the devices.

[0070] Each function in the blood information estimation device 100 is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.

[0071] The processor 1001 controls the entire computer, for example, by running the operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. For example, the terminal usage log acquisition unit 20 and the hypertension detection unit 40 mentioned above may be implemented by the processor 1001.

[0072] Furthermore, the processor 1001 reads programs (program code), software modules, data, etc., from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the hypertension detection unit 40 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described processes have been explained as being executed by one processor 1001, but they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may also be transmitted from a network via a telecommunications line.

[0073] Memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 1002 may also be called a register, cache, main memory, etc. Memory 1002 can store executable programs (program code), software modules, etc., for carrying out the blood information estimation method according to one embodiment of the present disclosure.

[0074] Storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0075] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, duplexer, filter, frequency synthesizer, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the terminal usage log acquisition unit 20 described above may be implemented by the communication device 1004.

[0076] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0077] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0078] Furthermore, the blood information estimation device 100 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0079] Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0080] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described herein may be reordered, provided they are consistent with each other. For example, the methods described herein present various step elements in an exemplary order and are not limited to that specific order.

[0081] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0082] The determination may be made by a value represented by 1 bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0083] Each aspect / embodiment described herein may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0084] Although the present disclosure has been described in detail above, it will be clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0085] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0086] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technology (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technology (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0087] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0088] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of the channel and symbol may be a signal (signaling). Also, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, cell, frequency carrier, etc.

[0089] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index.

[0090] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiry (e.g., searching in a table, database, or other data structure), and ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0091] The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0092] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0093] In the configuration of each of the above devices, "means" may be replaced with "part," "circuit," "device," etc.

[0094] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0095] In this disclosure, if articles are added through translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0096] In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combine" may be interpreted similarly to "different." [Explanation of Symbols]

[0097] 100...Blood information estimation device, 20...Terminal usage log acquisition unit, 30...Weather information acquisition unit, 40...Hypertension detection unit, 21...User authentication function, 22...User attribute information acquisition function, 23...App usage information acquisition function, 24...Purchase history information acquisition function, 25...Location information acquisition function, 26...Terminal operation information acquisition function, 27...Data transfer function, 31...User authentication function, 32...User location information acquisition function, 33...Weather information acquisition function, 34...Data transfer function, 30a...Weather information database, 41...Data acquisition function, 42...Data cleansing function, 43...Lifestyle estimation function, 44...Hypertension detection model construction function, 45...Hypertension detection function, 46...Notification function, 40a...Training data storage database, 44a...Hypertension detection model.

Claims

1. A log acquisition unit that acquires usage logs of user terminals, Based on the aforementioned usage log, a blood information estimation unit estimates blood information related to changes in blood condition, The system includes a predictive model that outputs blood information corresponding to the usage log, The aforementioned usage log includes the purchase amount and the purchased items, The blood information estimation unit uses the prediction model to estimate lifestyle information, including at least one of stress, frequency of eating out, salt intake, and calorie intake, based on the usage log, and estimates blood information based on said lifestyle information. Blood information estimation device.

2. The aforementioned blood information includes at least one of blood pressure, blood glucose level, triglycerides, and cholesterol. The blood information estimation device according to claim 1.

3. The blood information estimation unit, In addition to the aforementioned usage logs, blood information is estimated by considering at least one of the following: user attribute information, weather information, or lifestyle information. A blood information estimation device according to claim 1 or 2.

4. The system further includes a learning unit that learns the predictive model based on learning usage logs and learning blood information stored as training data, The blood information used for learning by the learning unit is based on the average value over a predetermined period. A blood information estimation device according to any one of claims 1 to 3.

5. The blood information estimation unit identifies lifestyle habits that have an influence on the blood information estimated by the prediction model. A blood information estimation device according to any one of claims 1 to 4.

6. The aforementioned predictive model is trained based on usage logs and blood information for a predetermined age and / or gender. The blood information estimation unit estimates blood information by applying a predictive model that corresponds to the user's age and / or gender. A blood information estimation device according to any one of claims 1 to 5.

Images