Classification system, classification method, and program
The classification system addresses the limitations of existing pulse measuring devices by classifying pulses using pulse rate, variation, pressure, and waveform characteristics, enabling accurate pulse diagnosis in Oriental medicine through a computerized approach.
Patent Information
- Application Number
- JP2021145621
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2021-09-07
- Publication Date
- 2024-12-04
- Estimated Expiration
- 2041-09-07
AI Technical Summary
Existing pulse measuring devices, such as those in wearable devices and blood pressure monitors, are cumbersome or limited in their functionality, failing to accurately classify pulses based on the principles of Oriental medicine, making it difficult for inexperienced individuals to perform effective pulse diagnosis.
A classification system and method that utilizes a general-purpose pulse measuring device in wearable devices to classify pulses based on pulse rate, degree of variation, pressure, and waveform characteristics, employing a computerized approach to determine pulse patterns using a classification system comprising an acquisition, classification, and determination process.
Enables accurate classification of pulses based on Oriental medicine principles using a general-purpose pulse measuring device, facilitating effective pulse diagnosis even for inexperienced users.
Smart Images

Figure 0007594514000001 
Figure 0007594514000002 
Figure 0007594514000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a classification system, a classification method, and a program. [Background technology]
[0002] Pulse diagnosis has been practiced in traditional Chinese medicine. In pulse diagnosis, a specialist doctor touches the patient's pulse to grasp the strength, speed, hardness, thickness, ups and downs of the pulse, and examines the state of the disease. For example, in pulse diagnosis, a specialist doctor judges which of multiple types (e.g., 28 types) of pulse patterns (pulse types) the patient's pulse corresponds to, and performs an examination based on the judgment result. Such pulse diagnosis is handed down by human senses, and it takes a long time to master it, so that it is difficult for inexperienced people to judge the pulse pattern. Patent Document 1 discloses a technology for quantitatively judging the pulse pattern using signal processing technology so that even inexperienced people can judge the pulse pattern.
[0003] Meanwhile, Patent Document 2 discloses a photoelectric pulse measuring device. The photoelectric pulse measuring device measures the pulse by irradiating the human body with light and utilizing the difference in absorbance caused by blood pulsation. Currently, such photoelectric pulse measuring devices are widely used in wearable devices such as smart watches. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] JP 2015-16268 A [Patent Document 2] Japanese Patent Application Publication No. 9-122090 Summary of the Invention [Problem to be solved by the invention]
[0005] However, in Patent Document 1, the measurement is performed by wrapping a blood pressure cuff around the arm. This causes a problem that the measurement is more cumbersome than with wearable devices such as smart watches. In addition, although the pulse measurement device in Patent Document 2 is compact, it is only built into a wearable device and is used to measure heart rate (pulse rate) and blood oxygen saturation (SpO2), and has hardly been used as a pulse measurement device to judge the state of physical condition based on the concept of pulse diagnosis.
[0006] The present invention has been made in consideration of the above-mentioned situation, and provides a classification system, classification method, and program that can classify pulses based on the concept of pulse diagnosis in traditional Chinese medicine using a general-purpose pulse measuring device used in wearable devices such as smart watches. [Means for solving the problem]
[0007] In order to solve the above-mentioned problems of the present invention, the present invention provides a classification system comprising an acquisition unit that acquires pulse wave data measured in measurement states corresponding to each of floating, middle and sinking, a classification unit that performs each of the following classifications on the pulse wave data acquired by the acquisition unit: a first classification that classifies the pulse wave data based on the pulse rate, a second classification that classifies the pulse wave data based on the degree of variation in pulse time, a third classification that classifies the pulse wave data based on differences in the pulse wave data in each of the measurement states of floating, middle and sinking, and a fourth classification that classifies the pulse wave data based on waveform features, and a determination unit that determines the type of the pulse wave data based on the classification results obtained by the classification unit.
[0008] The present invention is a classification method performed by a computer, in which an acquisition unit acquires pulse wave data measured in measurement states corresponding to floating, middle and sinking, and a classification unit performs each of the following classifications on the pulse wave data acquired by the acquisition unit: a first classification that classifies the pulse wave data based on the pulse rate; a second classification that classifies the pulse wave data based on the degree of variation in pulse time; a third classification that classifies the pulse wave data based on differences in the pulse wave data in each of the measurement states of floating, middle and sinking; and a fourth classification that classifies the pulse wave data based on waveform features; and a determination unit determines the type of the pulse wave data based on the classification results obtained by the classification unit.
[0009] The present invention is a program which causes a computer to acquire pulse wave data measured in measurement states corresponding to each of floating, middle and sinking, and to perform a first classification on the acquired pulse wave data which classifies the pulse wave data based on the pulse rate, a second classification which classifies the pulse wave data based on the degree of variation in pulse time, a third classification which classifies the pulse wave data based on differences in the pulse wave data in each of the measurement states of floating, middle and sinking, and a fourth classification which classifies the pulse wave data based on waveform features, and to determine the type of the pulse wave data based on the classification results. Effect of the Invention
[0010] According to the present invention, a general-purpose pulse measuring device used in wearable devices such as smart watches can be used to classify pulses based on the concept of pulse diagnosis in traditional Chinese medicine. [Brief description of the drawings]
[0011] [Figure 1] 1 is a block diagram showing an example of the configuration of a classification system 1 according to an embodiment. [Diagram 2] 1 is a block diagram showing an example of a configuration of a measurement terminal 10 according to an embodiment. [Diagram 3] 2 is a block diagram showing an example of the configuration of a classification server 20 according to the embodiment. FIG. [Figure 4]FIG. 2 is a diagram showing an example of pulse wave information 220 according to an embodiment. [Diagram 5] FIG. 1 is a diagram illustrating a pulse phenomenon according to an embodiment. [Figure 6] FIG. 1 is a diagram illustrating a pulse phenomenon according to an embodiment. [Figure 7] FIG. 1 is a diagram illustrating a pulse phenomenon according to an embodiment. [Figure 8] FIG. 1 is a diagram illustrating a pulse phenomenon according to an embodiment. [Figure 9] FIG. 4 is a diagram showing an example of pulse wave data according to the embodiment. [Figure 10] FIG. 1 is a diagram illustrating a pulse phenomenon according to an embodiment. [Figure 11] 4 is a flowchart showing a flow of processing performed by the classification server 20 according to the embodiment. [Figure 12] 1 is a block diagram showing an example of the configuration of a classification system 1 according to a first modified example of an embodiment. [Figure 13] FIG. 2 is a block diagram showing an example of the configuration of a learning server 30 according to a first modified example of the embodiment. [Figure 14] 11 is a sequence diagram showing the flow of processing performed by the classification system 1 according to the first modified example of the embodiment. FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[0013] [Overview of Classification System 1] An overview of the classification system 1 will be described. In this embodiment, a service (hereinafter, referred to as a health support service) that supports the health of a user based on the concept of pulse diagnosis in traditional Chinese medicine is provided by the classification system 1. In the health support service, the pulse pattern (pulse type) of the user is determined based on the concept of pulse diagnosis, and the determination result and health management advice based on the determination result are provided to the user.
[0014] [Structure of Classification System 1] The following describes the configuration of the classification system 1. Fig. 1 is a block diagram showing an example of the configuration of the classification system 1 according to the embodiment. The classification system 1 includes, for example, a measurement terminal 10 and a classification server 20. The measurement terminal 10 and the classification server 20 are communicatively connected via a communication network NW.
[0015] The measurement terminal 10 is a computer. For example, the measurement terminal 10 is a wearable terminal, a smartphone, a personal computer, a mobile phone, a tablet terminal, etc. For example, application software that provides a health support service (hereinafter, referred to as a health support application) is installed in the measurement terminal 10. The measurement terminal 10 measures the pulse wave of the user via the health support application, and transmits information (pulse wave data) indicating the measured pulse wave to the classification server 20.
[0016] For example, as shown in FIG. 1, the measurement terminal 10 is communicably connected to the pulse wave sensor 100 via wireless communication such as Bluetooth (registered trademark) or via a Universal Serial Bus (USB) or the like.
[0017] The pulse wave sensor 100 measures the pulse of a user. The pulse wave sensor 100 may be any sensor capable of measuring at least the pulse, and may be, for example, an optical photoelectric pulse measuring device. The pulse wave sensor 100 is attached to a measurement position where the pulse is measured, and irradiates light to the measurement position. The measurement position here is the wrist, and more specifically, the pulsating part of the radial artery that is touched on the inside of the radial styloid process of the left and right forearms. The pulse wave sensor 100 receives the irradiated light that has passed through the measurement position, or the light that has been reflected at the measurement position. The pulse wave sensor 100 utilizes the property that a part of the irradiated light is absorbed according to the blood flow rate at the measurement position, and measures the pulse based on the relationship between the amount of light received and the blood flow rate. The pulse wave sensor 100 transmits information indicating the measured pulse as pulse wave data to the measurement terminal 10. The measurement terminal 10 receives the pulse wave data from the pulse wave sensor 100. As a result, the measurement terminal 10 measures the pulse wave of the user.
[0018] The measurement terminal 10 may incorporate a pulse wave sensor 100 and acquire pulse wave data measured by the pulse wave sensor 100 via the pulse wave sensor 100 to measure the user's pulse wave.
[0019] The classification server 20 is a computer. For example, the classification server 20 is a cloud device, a server device, a personal computer, etc. The classification server 20 provides, for example, a health support service. For example, the classification server 20 receives pulse wave data of a user from the measurement terminal 10 and determines a pulse pattern in the received pulse wave data. The classification server 20 transmits the determination result of the pulse pattern to the measurement terminal 10.
[0020] The classification server 20 determines the pulse pattern (type of pulse wave data) based on the classification result of the pulse wave data, and transmits the result to the measurement terminal 10. In the example of this figure, an example of the display of the measurement terminal 10 when the user's pulse pattern is determined to be a "Hong Pulse" is shown.
[0021] [Configuration of the measuring terminal 10] The following describes the configuration of the measurement terminal 10. Fig. 2 is a block diagram showing an example of the configuration of the measurement terminal 10 according to the embodiment. The measurement terminal 10 includes, for example, a communication unit 11, a storage unit 12, a control unit 13, a display unit 14, and an input unit 15.
[0022] The communication unit 11 communicates with the classification server 20 via the communication network NW. The communication unit 11 also receives pulse wave data measured by the pulse wave sensor 100.
[0023] The storage unit 12 is configured by a storage medium such as a hard disk drive (HDD), a flash memory, an electrically erasable programmable read only memory (EEPROM), a random access read / write memory (RAM), a read only memory (ROM), or a combination of these. The storage unit 12 stores programs for executing various processes of the measurement terminal 10 and temporary data used when performing various processes.
[0024] The control unit 13 is realized by causing a CPU (Central Processing Unit) provided as hardware in the measurement terminal 10 to execute a program. The control unit 13 comprehensively controls the measurement terminal 10. The control unit 13 controls the display unit 14 and the input unit 15 according to a program related to a health support application, for example.
[0025] The control unit 13 executes processing according to the program of the health support app. For example, when the icon of the health support app is tapped, the control unit 13 starts the health support app. This causes login to the health support app. When login is successful, for example, a startup image of the health support app is displayed on the display unit 14.
[0026] The control unit 13 includes, for example, an acquisition unit 130, a measurement support unit 131, and a device control unit 132. The acquisition unit 130 acquires various types of information. The acquisition unit 130 acquires pulse wave data measured by the pulse wave sensor 100 via the communication unit 11. In addition, for example, the acquisition unit 130 acquires information input by the user operating an app via the input unit 15.
[0027] The measurement support unit 131 supports the user who measures the pulse. Generally, there are various methods for pulse diagnosis. For example, in the six-part localized pulse diagnosis, the pulse is examined at each of the three measurement positions (called cun, kwan, and shaku) along the pulsating part of the radial artery of both arms, a total of six measurement positions. In the six-part localized pulse diagnosis, the pulse is examined in each of the three measurement states of floating, middle, and sinking. In the floating state, the pulse is examined by lightly placing the finger on the measurement position. In the sinking state, the pulse is examined by sinking the finger with force. In the middle state, the pulse is examined by placing the finger on the measurement position with a force that is exactly halfway between the floating state and the sinking state. Then, the pulse condition is judged comprehensively based on the floating, middle, and sinking pulses at the cun, kwan, and shaku of both arms.
[0028] In this embodiment, the measurement support unit 131 supports the user so that the measurement is performed according to such a measurement position and measurement state. For example, the measurement support unit 131 causes the display unit 14 to display a guidance image.
[0029] Specifically, when measuring the float at the measurement position of the "sun" of the left hand, for example, the measurement support unit 131 displays an image showing the measurement position with a mark at the "sun" position of the left hand on the display unit 14. Then, the measurement support unit 131 displays a message such as "The float of the "sun" of the left hand will be measured. Please refer to the image and wear the pulse wave sensor 100 so that it lightly touches the "sun" position of the left hand." If a stable waveform is acquired by the pulse wave sensor 100, the measurement support unit 131 displays a measurement start message such as "Measurement will begin," and after a predetermined time (e.g., one minute) has elapsed since the measurement start message was displayed, a measurement end message such as "Measurement has ended."
[0030] Alternatively, when measuring the sinking at the measurement position of the right hand, for example, the measurement support unit 131 displays an image showing the measurement position with a mark at the position of the right hand on the display unit 14. Then, the measurement support unit 131 displays a message such as "The sinking of the right hand at the "shaku" will be measured. Please refer to the image, wear the pulse wave sensor 100 so that it touches the "shaku" position of your right hand, and press down on the pulse wave sensor 100." If a stable waveform is acquired by the pulse wave sensor 100, the measurement support unit 131 displays a measurement start message such as "Measurement will start," and after a predetermined time (for example, one minute) has elapsed since the measurement start message was displayed, displays a measurement end message such as "Measurement has ended."
[0031] The measurement support unit 131 transmits the pulse wave data thus acquired together with its attribute information to the measurement terminal 10. The attribute information here is information related to the pulse wave data, and is information indicating the measurement position (indicating size, length, length, etc.), the measurement state (indicating whether the measurement was taken floating, middle, or sinking, etc.), etc. The attribute information may also include information indicating the measurement time, the measurement date and time, etc.
[0032] In pulse diagnosis, some measurement positions and some measurement states may be omitted. For example, only the pulse of the left hand may be measured, and the right hand may be omitted. Even if the measurement position or measurement state is omitted in this way, the number of pulse patterns that can be determined may decrease, but it is possible to determine the pulse pattern. Based on this viewpoint, in this embodiment, the measurement position and measurement state may be selected according to the user's wishes. In this case, the pulse pattern is determined based on the measured pulse wave data and its attribute information.
[0033] The measurement support unit 131 may also notify the user of the timing of measurement. For example, the measurement support unit 131 notifies the user of the timing of measurement by sounding an alarm or displaying a message such as "Let's take a measurement." The measurement support unit 131 measures the pulse at different times multiple times a day, for example, when the user is resting immediately after waking up, during the day, and before going to bed.
[0034] The device control unit 132 performs overall control of the measurement terminal 10. For example, the device control unit 132 outputs the pulse wave data received by the communication unit 11 to the acquisition unit 130. The device control unit 132 outputs the pulse wave data output by the measurement assistance unit 131 and its attribute information to the communication unit 11, thereby transmitting the data to the classification server 20.
[0035] The display unit 14 includes, for example, a display device such as a liquid crystal display, and displays an image according to the control of the control unit 13. The input unit 15 includes, for example, an input device such as a mouse, a keyboard, or a touch panel, and outputs information input by a user operating an app to the control unit 13.
[0036] [Configuration of classification server 20] The following describes the configuration of the classification server 20. Fig. 3 is a block diagram showing an example of the configuration of the classification server 20 according to the embodiment. The classification server 20 includes, for example, a communication unit 21, a storage unit 22, and a control unit 23.
[0037] The communication unit 21 communicates with the measurement terminal 10 via the communication network NW.
[0038] The storage unit 22 is configured by a storage medium such as a HDD, a flash memory, an EEPROM, a RAM, a ROM, or a combination of these. The storage unit 22 stores programs for executing various processes of the classification server 20 and temporary data used when performing various processes.
[0039] The control unit 23 is realized by causing a CPU provided as hardware in the classification server 20 to execute a program. The control unit 23 controls the classification server 20 in an overall manner.
[0040] Control unit 23 executes processing in response to the provision of a health support service. Control unit 23 includes, for example, an acquisition unit 230, a classification unit 231, a determination unit 232, and a device control unit 233. Acquisition unit 230 acquires pulse wave data transmitted from measurement terminal 10 via communication unit 21, and outputs the acquired pulse wave data to classification unit 231.
[0041] The classification unit 231 classifies the pulse wave data. The classification unit 231 classifies the pulse wave data based on the viewpoints of pulse rate, regularity, pressure, and waveform. The pulse rate here is the number of times the pulse wave data pulsates in a predetermined unit time (for example, one minute). The regularity is the rhythm of the pulse, and the degree of variation in the time required for one pulse (called the pulse time). The pressure is whether or not the pulse wave data differs between floating, middle, and sinking pulses. The waveform is the time-series change in pulse strength. The classification unit 231 stores the classification results in the pulse wave information 220. A specific method by which the classification unit 231 classifies the pulse wave data will be described in detail later.
[0042] The determining section 232 determines the pulse phenomenon based on the classification result obtained by the classifying section 231. The determining section 232 stores the determined pulse phenomenon in the pulse wave information 220. A specific method by which the determining section 232 determines the pulse phenomenon will be described in detail later.
[0043] The device control unit 233 performs overall control of the classification server 20. For example, the device control unit 233 outputs the pulse wave data received by the communication unit 21 to the acquisition unit 230. The device control unit 233 transmits to the measurement terminal 10 the judgment result (pulse phenomenon) judged by the judgment unit 232, and advice on health management based on the judgment result.
[0044] [Configuration of Pulse Wave Information 220] The configuration of pulse wave information 220 will be described. Fig. 4 is a diagram showing an example of pulse wave information 220 according to an embodiment. Pulse wave information 220 stores information corresponding to each item, such as a pulse ID, measurement date and time, measurement position, measurement state, user ID, classification result, and pulse phenomenon. The pulse ID is identification information that uniquely identifies the pulse wave data. The measurement date and time is information indicating the date and time when the pulse wave data identified by the pulse ID was measured.
[0045] The measurement position is information indicating the measurement position (inches, squares, feet, etc.) at which the pulse wave data identified by the pulse ID was measured. The measurement state is information indicating the measurement state (floating, medium, sinking, etc.) at which the pulse wave data identified by the pulse ID was measured. The user ID is information identifying the user at which the pulse wave data identified by the pulse ID was measured.
[0046] The classification result is information indicating the classification result by the classification unit 231. The classification result is indicated in association with items such as pulse rate, regularity, pressure, waveform, etc. The pulse phenomenon is information indicating the pulse phenomenon as the judgment result by the judgment unit 232.
[0047] [Method by which classification unit 231 classifies pulse wave data] The method by which classification unit 231 classifies pulse wave data will be described with reference to Figures 5 to 9. Figures 5 to 9 are diagrams for explaining pulse patterns in pulse diagnosis.
[0048] FIG. 5 shows an example of classification by pulse rate. As shown in FIG. 5, in pulse diagnosis, pulses are classified into four pulse types based on the pulse rate: "slow pulse", "moderate pulse", "rapid pulse", and "fast pulse". For example, a pulse with a pulse rate of 60 beats / min or less is classified as "slow pulse". A pulse with a pulse rate of about 65 beats / min is classified as "slow pulse". A pulse with a pulse rate of 90 beats / min or more is classified as "rapid pulse". A pulse with a pulse rate of 110 beats / min or more is classified as "fast pulse". A pulse with a pulse rate of about 65 to less than 90 beats / min is classified as "medium pulse". The medium pulse is a reference pulse, and the user's health condition is determined based on the state of the medium pulse.
[0049] Classification unit 231 calculates the pulse rate from the pulse wave data (see FIG. 9). For example, classification unit 231 determines the number of peaks (point P2 in FIG. 9) of the pulse wave data contained in a predetermined unit time (for example, one minute) as the pulse rate. Then, classification unit 231 classifies the pulse wave data according to the categories shown in FIG. 5 based on the calculated pulse rate. The classification performed by classification unit 231 here is an example of the "first classification".
[0050] Figure 6 shows an example of classification by regularity. As shown in Figure 6, in pulse diagnosis, pulses are classified into three types of pulses based on regularity: a "prompted pulse," a "joint pulse," and a "substitute pulse." For example, a pulse that is irregularly missed when the pulse rate is 90 beats per minute or more is classified as a "prompted pulse." A pulse that is irregularly missed when the pulse rate is 60 beats per minute or less is classified as a "joint pulse." Moreover, a pulse that is regularly missed, regardless of pulse rate, is classified as a "substitute pulse."
[0051] The classification unit 231 calculates the variation in pulse time from the pulse wave data as an index of regularity. For example, the classification unit 231 calculates the frequency characteristics of the pulse by frequency analysis of the pulse wave data. The classification unit 231 calculates the S / N ratio of the frequency characteristics of the pulse. Here, S (signal) is the magnitude of the main component of the pulse rhythm, specifically, the intensity of the frequency with the largest frequency component in the frequency characteristics. Here, N (noise) is the magnitude of the components other than the main component in the pulse rhythm, specifically, the intensity of the frequency with the smallest frequency component in the frequency characteristics. Then, the classification unit 231 calculates the variation in the pulse time based on the calculated S / N ratio. For example, when the S / N ratio is equal to or greater than a predetermined threshold, the classification unit 231 determines that there is little variation, that is, there is no loss. On the other hand, when the S / N ratio is less than a predetermined threshold, the classification unit 231 determines that there is a large variation, that is, there is a loss.
[0052] If the classification unit 231 determines that the variation in the pulse wave data is large, it determines whether the gaps are irregular or regular. For example, the classification unit 231 calculates an S2 / N ratio based on the frequency characteristics of the pulse wave data. Here, S2 (second signal) is the intensity of the frequency with the second largest frequency component. For example, if the S2 / N ratio is equal to or greater than a predetermined threshold, the classification unit 231 determines that the gaps are regular. On the other hand, if the S2 / N ratio is less than the predetermined threshold, the classification unit 231 determines that the gaps are irregular. Then, the classification unit 231 classifies the pulse wave data according to the categories shown in FIG. 6. The classification performed by the classification unit 231 here is an example of the "second classification".
[0053] An example of classification by pressure is shown in Figure 7. As shown in Figure 7, in pulse diagnosis, pulses are classified into five types: "floating pulse," "sinking pulse," "submerged pulse," "weak pulse," and "solid pulse," based on whether the pulse is different in the floating and sinking states. For example, a pulse that is strongest in the floating state and weaker in the middle and sinking states is classified as a "floating pulse."
[0054] Classification unit 231 acquires pulse wave data measured in each of the measurement states of floating, middle, and sinking from the attribute information of the pulse wave data. Classification unit 231 compares the intensities of the acquired pulse wave data, for example, the amplitudes of the pulse wave data (the difference between intensities VM and VS in FIG. 9). Classification unit 231 performs classification according to the categories shown in FIG. 7 based on the comparison results. The classification performed by classification unit 231 here is an example of the "third classification".
[0055] Examples of classification by waveform are shown in Fig. 8 and Fig. 9. As shown in Fig. 8, in pulse diagnosis, pulses are classified into nine types, such as "thin pulse", "big pulse", "Hong pulse", and "Xian pulse", based on the thickness, tension, length, and blood flow state of the pulse. Fig. 9 shows pulse wave data in a schematic manner. The horizontal axis of Fig. 9 shows time, and the vertical axis shows pulse strength. For example, the pulse wave data shows repeated time series changes consisting of point P1 corresponding to the start point of the pulse, point P2 corresponding to the peak of the pulse, and point P3 corresponding to the end point of the pulse.
[0056] The thickness of the pulse shown in FIG. 8 is the magnitude of the amplitude in the pulse wave data. Tension is the steepness of the rising edge in the pulse wave data (the rate of change in intensity from point P1 to point P2 in FIG. 9). The length here is the difference in pulse wave data depending on the measurement position. The state of blood flow is the time series change in the rising and falling edges (from point P2 to point P3 in FIG. 9) in the pulse wave data. The state of blood flow shown in FIG. 8 is whether or not there is a second rising edge (from point P4 to point P5 of the dashed waveform data in FIG. 9) in the process of the fall from point P2 to point P3, and the time series change if there is a second rising edge.
[0057] Classification unit 231 extracts the waveform of the pulse wave data. For example, classification unit 231 extracts the waveform of the pulse wave data by normalizing the pulse wave data by a time corresponding to the pulse period (from time TS to TE in FIG. 9). Alternatively, classification unit 231 extracts the waveform of the pulse wave data by normalizing the pulse wave data by a time corresponding to the pulse amplitude. Normalizing the pulse wave data can simplify classification by waveform.
[0058] For example, classification unit 231 performs classification according to the pulse thickness classification in Fig. 7 based on the magnitude of the amplitude. Classification unit 231 performs classification according to the pulse tension classification in Fig. 7 based on the steepness of the rising edge in the normalized pulse wave data. Classification unit 231 performs classification according to the pulse length classification in Fig. 7 by acquiring pulse wave data corresponding to each measurement position such as inches, inches, and inches, and comparing the waveforms of the acquired pulse wave data. Classification unit 231 performs classification according to the pulse blood flow state classification in Fig. 7 based on time series changes such as the rate of change of the rising and falling edges in the normalized pulse wave data. The classification performed by classification unit 231 here is an example of the "fourth classification".
[0059] [Method by which the determination unit 232 determines a pulse pattern] A method for determining the pulse phenomenon by the determination unit 232 will be described. The determination unit 232 determines the pulse phenomenon based on the classification result of the classification unit 231. When one pulse wave data is classified into one or more pulse phenomena as a result of classification by the classification unit 231 for each of the pulse rate, regularity, pressure, and waveform, the determination unit 232 determines the one or more pulse phenomena as the pulse phenomenon of the pulse wave data. Alternatively, when the pulse phenomenon is determined in a composite manner based on the classification results of each of the pulse rate, regularity, pressure, and waveform, the determination unit 232 determines the pulse phenomenon according to the classification.
[0060] An example of a composite classification is shown in Fig. 10. As shown in Fig. 10, in pulse diagnosis, for example, a pulse that is classified as a rapid pulse based on the pulse rate and a smooth pulse or a short pulse based on the waveform is classified as "arterial". The determination unit 232 determines the pulse pattern according to the classification results by the classification unit 231 and in accordance with the divisions shown in Fig. 10.
[0061] [Flow of processing performed by classification server 20] The flow of processing performed by classification server 20 will be described with reference to FIG. 11. First, classification server 20 acquires pulse wave data (step S10). Classification server 20 classifies the acquired pulse wave data based on its pulse rate (step S11). Classification server 20 classifies the acquired pulse wave data based on its regularity (step S12). Classification server 20 classifies the acquired pulse wave data based on its pressure (step S13). Classification server 20 classifies the acquired pulse wave data based on its waveform (step S14). Then, classification server 20 determines the pulse pattern of the pulse wave data based on the results of the classification performed in steps S11 to S14 (step S15).
[0062] As described above, the classification system 1 according to the embodiment includes an acquisition unit 230, a classification unit 231, and a determination unit 232. The acquisition unit 230 acquires pulse wave data measured in a measurement state corresponding to each of floating, middle, and sinking. The classification unit 231 classifies the pulse wave data acquired by the acquisition unit 230. The classification unit 231 performs a first classification to classify the pulse wave data based on a representative value of the pulse rate. The classification unit 231 performs a second classification to classify the pulse wave data based on the degree of variation in the pulse rate. The classification unit 231 performs a third classification to classify the pulse wave data based on the difference between the pulse wave data in each of the floating, middle, and sinking states. The classification unit 231 performs a fourth classification to classify the pulse wave data based on the feature amount of the waveform. The determination unit 232 determines the pulse pattern (type of pulse wave data) based on the classification result obtained by the classification unit 231. As a result, the classification system 1 according to the embodiment can classify pulses based on the concept of pulse diagnosis in traditional Chinese medicine using a general-purpose pulse measuring device that is used in wearable devices such as smart watches.
[0063] [First Modification of the Embodiment] A first modified example of the embodiment will be described. This modified example differs from the above-mentioned embodiment in that classification by waveform is performed using a trained model. The trained model is a model that has learned the correspondence between waveform and pulse phenomenon. By performing classification by waveform using the trained model, it is possible to omit signal processing related to the waveform and reduce the processing load of the classification server 20.
[0064] FIG. 12 is a block diagram showing an example of the configuration of a classification system 1 according to a first modified example of the embodiment. In this modified example, the classification system 1 further includes a learning server 30. The learning server 30 is a computer. For example, the learning server 30 is a cloud device, a server device, a personal computer, or the like. The learning server 30 generates a trained model. The learning server 30 receives pulse wave data to be classified from the classification server 20. The learning server 30 uses the trained model to estimate a pulse phenomenon to which the pulse wave data to be classified corresponds, and notifies the classification server 20 of the estimation result.
[0065] 13 is a block diagram showing an example of the configuration of the learning server 30 according to the first modification of the embodiment. The learning server 30 includes a communication unit 31, a storage unit 32, and a control unit 33, for example.
[0066] The communication unit 31 communicates with the classification server 20 via the communication network NW. The storage unit 32 is configured with a storage medium such as a HDD, a flash memory, an EEPROM, a RAM, a ROM, or a combination of these. The storage unit 32 stores programs for executing various processes of the learning server 30, and temporary data used when performing various processes.
[0067] The control unit 33 is realized by executing a program on a CPU provided as hardware in the learning server 30. The control unit 33 comprehensively controls the learning server 30. The control unit 33 includes, for example, an acquisition unit 330, a learning unit 331, an estimation unit 332, and a device control unit 333.
[0068] The acquiring unit 330 acquires various information. The acquiring unit 330 acquires a learning data set for learning via the communication unit 31. The learning data set for learning is data used to generate a trained model. The acquiring unit 330 also acquires, via the communication unit 31, pulse wave data to be classified that is transmitted from the classification server 20.
[0069] The learning unit 331 generates a trained model. The learning unit 331 acquires a training data set for training via the acquisition unit 330. The training data set for training is information in which training pulse wave data (input data) is associated with training pulse wave data (output data) to form a set. For example, the training data set for training is created in advance by using the results of a diagnosis made by a specialist who can perform pulse diagnosis and setting the pulse phenomenon in the training pulse wave data.
[0070] The learning unit 331 generates a trained model by performing machine learning using a training data set on a training model such as a Convolutional Neural Network (CNN). The machine learning method here is, for example, supervised learning.
[0071] The learning unit 331 inputs input data of a data set for learning to the learning model. The learning unit 331 adjusts the parameters of the learning model (weight W, bias component b, etc.) so that data output from the learning model when the input data is inputted approaches the output data of the learning data set. In this way, the learning unit 331 makes the learning model learn the correspondence between the pulse wave data and the pulse phenomenon based on the classification by the waveform.
[0072] The learning unit 331 repeatedly trains the learning model until a predetermined termination condition is satisfied. The termination condition here is, for example, a condition that an error between data output from the learning model and (output data) of a data set for learning falls within a predetermined range. The learning unit 331 regards the learning model trained until the predetermined termination condition is satisfied as a trained model, and stores information indicating the trained model in the storage unit 32 as the trained model 320.
[0073] The learning model is not limited to CNN. For example, a decision tree, a hierarchical Bayesian model, or a support vector machine (SVM) may be used as the learning model.
[0074] The estimation unit 332 performs estimation using the trained model 320. The estimation unit 332 acquires the pulse wave data to be classified via the acquisition unit 330. The estimation unit 332 inputs the acquired pulse wave data to the trained model 320. As a result, the trained model 320 outputs an estimation result that estimates the pulse phenomenon when the input pulse wave data is classified based on the waveform. The estimation unit 332 acquires the estimation result output from the trained model 320. As a result, the estimation unit 332 performs estimation using the trained model 320.
[0075] The device control unit 333 comprehensively controls the learning server 30. For example, the device control unit 333 outputs the pulse wave data received by the communication unit 31 to the acquisition unit 330. The device control unit 333 transmits the estimation result estimated by the estimation unit 332 to the classification server 20.
[0076] Fig. 14 is a sequence diagram showing the flow of processing performed by the classification system 1 according to the first modified example of the embodiment. Steps S20 to S23 and S28 in Fig. 14 are similar to steps S10 to S13 and S15 in Fig. 11, and therefore description thereof will be omitted.
[0077] The classification server 20 transmits the pulse wave data to the learning server 30 and requests the learning server 30 to perform classification based on the waveform (step S24). The learning server 30 acquires the pulse wave data transmitted from the classification server 20 (step S25) and estimates the classification result (pulse phenomenon) of the classification based on the waveform using the trained model (step S26). The learning server 30 transmits the estimation result to the classification server 20. As a result, the classification server 20 regards the estimation result notified by the learning server 30 as the classification result of classifying the pulse wave data based on the waveform.
[0078] In the above description, the learned model 320 is stored in the learning server 30, but the present invention is not limited to this. The learned model 320 may be stored in the classification server 20. In this case, the classification server 20 can estimate a pulse using the learned model 320 stored in the classification server 20 without accessing the learning server 30.
[0079] As described above, the classification system 1 according to the first modification of the embodiment further includes a learning unit 331. The learning unit 331 generates a trained model 320. The trained model 320 is a model that predicts a classification result of classification by waveform in pulse wave data. The learning unit 331 generates a trained model by having the trained model learn a correspondence relationship between the training pulse wave data and the classification result of classification by waveform in the training pulse wave data. The classification unit 231 performs classification by waveform in the pulse wave data using the trained model 320. As a result, the classification system 1 according to the first modification of the embodiment can perform classification by waveform using the trained model, and the classification server 20 does not need to perform signal processing related to the waveform. This makes it possible to reduce the processing load.
[0080] In the above, the pulse wave data is inputted into the trained model to classify the pulse wave data according to the waveform, but the present invention is not limited to this. The pulse wave data may be classified according to the waveform by inputting the feature extracted from the pulse wave data into the trained model. The feature in this case is, for example, information indicating normalized data of the pulse wave data, the maximum value, the minimum value, the maximum value and the minimum value of the slope in the pulse wave data. In this case, the trained model is a model that has learned the correspondence between the feature extracted from the training pulse wave data and the pulse pattern in the training pulse wave data. In this way, by using the feature extracted from the pulse wave data, it is possible to reduce the amount of data inputted into the trained model compared to the pulse wave data itself.
[0081] In addition, a program for realizing all or part of the functions of the classification system 1, the measurement terminal 10, the classification server 20, and the learning server 30 may be recorded in a computer-readable recording medium, and the program recorded in the recording medium may be read into a computer system and executed to perform processing. Here, "reading a program recorded in a recording medium into a computer system and executing it" includes installing the program into a computer system. The "computer system" here includes hardware such as an OS and peripheral devices. The "computer system" may also include a plurality of computer devices connected via a network including the Internet, a WAN, a LAN, a dedicated line, and other communication lines. The "computer-readable recording medium" refers to a portable medium such as a flexible disk, an optical magnetic disk, a ROM, a CD-ROM, and a storage device such as a hard disk built into a computer system. In this way, the recording medium storing the program may be a non-transient recording medium such as a CD-ROM. The recording medium also includes a recording medium provided inside or outside the computer system that can be accessed from the distribution server in order to distribute the program. The code of the program stored in the recording medium of the distribution server may be different from the code of the program in a format executable by the terminal device. That is, the format in which the program is stored in the distribution server does not matter as long as the program can be downloaded from the distribution server and installed in a form executable by the terminal device. The program may be divided into multiple parts, downloaded at different times, and then combined on the terminal device, or each of the divided programs may be distributed by a different distribution server. Furthermore, the "computer-readable recording medium" includes a program that holds a program for a certain period of time, such as a volatile memory (RAM) inside a computer system that becomes a server or a client when a program is transmitted via a network. The program may also be a program for realizing part of the above-mentioned functions. Furthermore, the program may be a so-called difference file (difference program) that can realize the above-mentioned functions in combination with a program already recorded in the computer system. [Explanation of symbols]
[0082] 1. Classification system 10…Measuring terminal 131…Measurement Support Department 20…Classification server 230…Acquisition Department 231...Classification section 232...Judgment section 233...Device control section 30…Learning server 320…Trained model
Claims
1. a measurement support unit that displays different pressure magnitudes on a wearable device having a built-in pulse wave sensor and displays a message encouraging the user to perform measurement while applying different pressure magnitudes to a measurement position by pressing down on the wearable device; an acquisition unit that acquires pulse wave data measured under measurement conditions in which pressures of different magnitudes are applied in accordance with the message displayed by the measurement support unit; a classification unit that performs a first classification on the pulse wave data acquired by the acquisition unit, the first classification being a classification of the pulse wave data based on a pulse rate, a second classification being a classification of the pulse wave data based on a degree of variation in pulse time, a third classification being a classification of the pulse wave data based on a difference between the pulse wave data in each of the measurement states in which the pressures of the different magnitudes are applied, and a fourth classification being a classification of the pulse wave data based on a feature amount of a waveform; a determination unit that determines a type of the pulse wave data based on a classification result obtained by the classification unit; A classification system comprising:
2. The measurement support unit displays the message with pressures corresponding to the floating, middle and sinking as the magnitudes of the different pressures, The acquisition unit acquires the pulse wave data measured in a measurement state corresponding to each of floating, middle, and sinking according to the display by the measurement support unit. The classification system of claim 1 .
3. the measurement support unit displays the message encouraging the user to wear the wearable device so that the pulse wave sensor touches a measurement position corresponding to each of the inches, lengths, and feet, and to perform measurement; The acquisition unit acquires the pulse wave data measured at measurement positions corresponding to each of the inches, lengths, and feet according to the display by the measurement support unit, The classification unit classifies the pulse wave data in the fourth classification based on waveform features in the pulse wave data measured at parts corresponding to each of inches, inches, and inches. A classification system according to claim 1 or claim 2.
4. The classification unit classifies the pulse wave data in the fourth classification based on a waveform feature amount of the normalized pulse wave data. A classification system according to any one of claims 1 to 3.
5. a learning unit that generates a trained model that predicts the classification result of the fourth classification from the feature amount of the pulse waveform in the pulse wave data by having a learning model learn a correspondence relationship between a feature amount extracted from a pulse waveform in the pulse wave data for training and a classification result of the fourth classification in the pulse wave data for training; Further comprising: The classification unit performs the fourth classification using the trained model. A classification system according to any one of claims 1 to 4.
6. 1. A computer-implemented classification method comprising: The measurement support unit causes a wearable device having a built-in pulse wave sensor to display the different pressure magnitudes and displays a message encouraging the wearer to perform measurement while applying different pressure magnitudes to a measurement position by pressing down on the wearable device; an acquisition unit acquires pulse wave data measured in a measurement state in which pressures of different magnitudes are applied in accordance with the display of the message by the measurement support unit; a classification unit performs a first classification on the pulse wave data acquired by the acquisition unit, the first classification being a classification of the pulse wave data based on a pulse rate; a second classification being a classification of the pulse wave data based on a degree of variation in pulse time; a third classification being a classification of the pulse wave data based on a difference between the pulse wave data in each of the measurement states in which the pressures of the different magnitudes are applied; and a fourth classification being a classification of the pulse wave data based on a feature amount of a waveform. a determination unit that determines a type of the pulse wave data based on a result of classification by the classification unit; Classification method.
7. On the computer, Displaying different pressure magnitudes on a wearable device having a built-in pulse wave sensor, and displaying a message encouraging the user to perform measurement while applying different pressure magnitudes to a measurement position by pressing down on the wearable device; According to the display of the message, obtain pulse wave data measured under measurement conditions in which pressures of different magnitudes are applied; the acquired pulse wave data is subjected to a first classification, which classifies the pulse wave data based on a pulse rate; a second classification, which classifies the pulse wave data based on a degree of variation in pulse time; a third classification, which classifies the pulse wave data based on a difference between the pulse wave data in each measurement state in which the pressures of the mutually different magnitudes are applied; and a fourth classification, which classifies the pulse wave data based on a feature amount of a waveform; determining a type of the pulse wave data based on the classification result; program.
Citation Information
Patent Citations
Mobile terminal and processing method for remotely obtaining analysis result on basis of pulse data by mobile terminal
CN105411542A
Non-restrictive pulsimeter
JP1997122090A
Health condition determination-supporting system using self-organizing map, and generating system of self-organizing map
JP2009183608A
Measuring analytical method for pulse diagnosis in oriental medicine, measuring analytical system for the same, and simple and portable measuring analytical device for pulse diagnosis using artificial-intelligence
JP2015016268A
Health state evaluation system by measuring pulse and actuation method thereof
JP2020074940A
