WO2024027482A1 - 糖尿病风险检测方法、电子设备及系统 - Google Patents

糖尿病风险检测方法、电子设备及系统 Download PDF

Info

Publication number
WO2024027482A1
WO2024027482A1 PCT/CN2023/107318 CN2023107318W WO2024027482A1 WO 2024027482 A1 WO2024027482 A1 WO 2024027482A1 CN 2023107318 W CN2023107318 W CN 2023107318W WO 2024027482 A1 WO2024027482 A1 WO 2024027482A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
diabetes
user
diabetes risk
risk detection
Prior art date
Application number
PCT/CN2023/107318
Other languages
English (en)
French (fr)
Inventor
贾子谦
李露平
陈茂林
Original Assignee
华为技术有限公司
中国医学科学院北京协和医院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司, 中国医学科学院北京协和医院 filed Critical 华为技术有限公司
Publication of WO2024027482A1 publication Critical patent/WO2024027482A1/zh

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
    • A61B5/0015—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4806—Sleep evaluation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • Embodiments of the present application relate to the field of terminal technology, and in particular to a diabetes risk detection method, electronic device and system.
  • diabetes risk testing is of great significance.
  • Traditional diabetes risk testing mainly relies on invasive and minimally invasive devices to collect blood and tissue fluid samples for blood glucose concentration analysis. This invasive or minimally invasive detection method will cause pain to the user, requires professional equipment, and is inconvenient.
  • wearable devices can be used to collect users' physiological data to achieve non-invasive diabetes risk detection.
  • the existing methods for non-invasive diabetes risk detection using wearable devices provide relatively short detection results when collecting physiological data (such as photoplethysmography (PPG) signals) for a short period of time. Inaccurate.
  • physiological data such as photoplethysmography (PPG) signals
  • embodiments of the present application provide a diabetes risk detection method, electronic device and system.
  • the technical solution provided by the embodiment of the present application can improve the accuracy of the detection results when the time for collecting PPG signals is short.
  • a diabetes risk detection method includes: obtaining first data and second data, and determining a diabetes risk detection result based on the first data and the second data. Afterwards, the diabetes risk detection results are output.
  • the first data includes various data that can reflect diabetes characteristics and is used for diabetes risk detection.
  • the first data is a PPG signal obtained through a PPG sensor.
  • the second data includes one or more of the following: diet data, exercise data, physical symptom data, drug usage data, sleep data, and emotion data.
  • dietary data includes one or more of the following: eating time, food taste or ingredients, and satiety level.
  • Exercise data includes one or more of the following: exercise time, duration, exercise intensity, exercise frequency.
  • Sleep data includes one or more of the following: sleep time period, sleep duration, whether in deep sleep, deep sleep time period, and deep sleep duration.
  • Drug use data includes one or more of the following: whether medication is used, type of medication, and frequency of medication.
  • Emotional data includes one or more of the following: mental stress index, mood index.
  • the first data can be obtained in the following ways: the electronic device obtains it through a built-in sensor; or the electronic device obtains it through other electronic devices.
  • the second data can be obtained through the following methods: the electronic device interacts with the user to obtain it; for example: displaying one or more interfaces, the one or more interfaces display the second data that needs to be provided by the user; Receive second data input by the user in the one or more interfaces. and/or, an electronic device obtains it from other electronic devices; and/or, obtains it from installed applications and/or services.
  • obtaining the first data and the second data may be implemented by: detecting a triggering operation of the user's diabetes risk detection; and obtaining the first data and the second data in response to the triggering operation.
  • diabetes risk detection is performed after the user triggers it.
  • determining the diabetes risk detection result based on the first data and the second data may be implemented as: determining the first risk value based on the first data. According to the second data and the first risk value, a second risk value is obtained, and the second risk value can be used to represent the diabetes risk detection result.
  • an implementation method for obtaining the second risk value based on the second data and the first risk value, that is, obtaining the second risk value based on the second data and the first risk value, It can be implemented by: obtaining the second risk value according to the weight corresponding to different second data and the first risk value.
  • the weight of one or an item of second data is used to indicate the degree of influence of the second data on the detection result; the greater the influence of a certain type or item of second data on the detection result, the greater the corresponding weight, and the corresponding , the greater the adjustment to the first risk value.
  • the weight can be preset. That is, the first risk value is increased or decreased according to the impact of different second data on diabetes. Among them, if a certain type of second data has a greater impact on diabetes, the corresponding adjustment will be larger. Correspondingly, if a certain or a certain second data has a smaller impact on diabetes, the corresponding adjustment range will be smaller.
  • the method further includes: outputting the confidence of the diabetes risk detection result.
  • the confidence level is used to represent the accuracy of the diabetes risk detection result.
  • the confidence level is determined based on at least one or more of the following: the duration of the acquired first data, whether the acquired first data is missing within a preset time period, the quality of the acquired first data, the acquired The type of the second data, the detail level of the acquired second data, etc.
  • the method further includes prompting the user the confidence level of the diabetes risk detection result and the second data corresponding to the confidence level.
  • the user when the confidence level is lower than a preset threshold, the user is prompted to edit the acquired second data or input more second data (in this application, it can also be described as the third Three data).
  • obtaining the second data includes: obtaining the second data for a preset time period.
  • the preset time period includes one or more of the following time periods: a first data missing time period, a nap time period, a eating time period, and a night sleep time period.
  • the second data includes multiple types of second data. Then, obtaining the first data and the second data and determining the diabetes risk detection result based on the first data and the second data includes:
  • the confidence of the obtained diabetes risk detection result is determined to be lower than the preset threshold based on the acquired second data and the first data, then continue to obtain the second data until the confidence of the diabetes risk detection result is equal to or higher than the preset threshold.
  • the priorities of different items or types of second data corresponding to different users are different or the same.
  • this method can reduce the amount of second data filled in by the user and reduce the user's interaction burden. For example: If physical symptom data, drug usage data, diet data, and exercise data are located on different pages, it is better for the user to flip between these three pages and fill in all the data on these three pages.
  • users may only need to fill in one type of content (that is, the content of one page), such as physical symptom data and drug usage data, without filling in other second data, reducing the user's interaction burden.
  • an electronic device in a second aspect, includes: a processor and a memory.
  • the memory is coupled to the processor.
  • the memory is used to store computer-readable instructions.
  • the processor reads the computer-readable instructions from the memory, the electronic device performs the following operations: obtains the first data and The second data determines the diabetes risk detection result based on the first data and the second data. Afterwards, the diabetes risk detection results are output.
  • obtaining the first data and the second data may be implemented by: detecting a triggering operation of the user's diabetes risk detection; and obtaining the first data and the second data in response to the triggering operation.
  • determining the diabetes risk detection result based on the first data and the second data can be implemented as: The first risk value is determined based on the first data. The first risk value is adjusted according to the second data to obtain a second risk value, which can be used to represent the diabetes risk detection result.
  • adjusting the first risk value according to the second data to obtain the second risk value can be implemented as: adjusting the first risk value according to the weight of different second data to obtain the second risk value .
  • the processor when the processor reads the computer instructions from the memory, it also causes the electronic device to perform the following operations: output the confidence level of the diabetes risk detection result.
  • the confidence level is used to represent the accuracy of the diabetes risk detection result.
  • the confidence level is determined based on at least one or more of the following: the duration of the acquired first data, whether the acquired first data is missing within a preset time period, the acquired first data The quality, the type of the second data obtained, and the detail level of the second data obtained.
  • the processor when the processor reads the computer instructions from the memory, it also causes the electronic device to perform the following operations: prompting the user for the confidence level of the diabetes risk detection result and the second data corresponding to the confidence level.
  • the processor when the processor reads the computer instructions from the memory, it also causes the electronic device to perform the following operations: when the confidence level is lower than a preset threshold, prompt the user to edit the acquired second data or enter third data.
  • obtaining the second data includes: obtaining the second data for a preset time period.
  • the preset time period includes one or more of the following time periods: a first data missing time period, a nap time period, a eating time period, and a night sleep time period.
  • the second data includes multiple types of second data. Then, obtaining the first data and the second data and determining the diabetes risk detection result based on the first data and the second data includes:
  • the first data obtain high-priority second data according to the priorities of different second data; if it is determined based on the high-priority second data and the first data that the confidence of the obtained diabetes risk detection result is equal to or higher than If the threshold is preset, acquisition of the second data will be stopped.
  • the low-priority second data is obtained and based on the obtained second data and the first data.
  • a piece of data determines the diabetes test result until the confidence level of the diabetes risk test result is equal to or higher than a preset threshold.
  • embodiments of the present application provide an electronic device that has the function of implementing the diabetes risk detection method as described in the first aspect and any possible implementation manner.
  • This function can be implemented by hardware, or can be implemented by hardware and corresponding software.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • a computer-readable storage medium stores a computer program (which may also be referred to as instructions or codes).
  • the computer program When the computer program is executed by an electronic device, it causes the electronic device to perform the method of the first aspect or any one of the embodiments of the first aspect.
  • embodiments of the present application provide a computer program product, which when the computer program product is run on an electronic device, causes the electronic device to execute the method of the first aspect or any one of the implementation modes of the first aspect.
  • inventions of the present application provide a circuit system.
  • the circuit system includes a processing circuit, and the processing circuit is configured to execute the method of the first aspect or any one of the implementation modes of the first aspect.
  • embodiments of the present application provide a chip system, including at least one processor and at least one interface circuit.
  • the at least one interface circuit is used to perform transceiver functions and send instructions to at least one processor.
  • At least one processor When at least one processor When executing instructions, At least one processor executes the method of the first aspect or any one of the implementation modes of the first aspect.
  • inventions of the present application provide a diabetes risk detection system.
  • the system includes a first electronic device and a second electronic device.
  • the first electronic device is used to perform the first aspect or any one of the implementation methods in the first aspect.
  • a method in which the second electronic device obtains the first data and/or the second data and sends them to the first electronic device.
  • Figure 1 is a schematic structural diagram of a system provided by an embodiment of the present application.
  • Figure 2 is a schematic structural diagram of a wearable device provided by an embodiment of the present application.
  • Figure 3 is a schematic structural diagram of another wearable device provided by an embodiment of the present application.
  • Figure 4A is a schematic diagram of the interface provided by an embodiment of the present application.
  • Figure 4B is the second schematic diagram of the interface provided by the embodiment of the present application.
  • Figure 4C is the third schematic diagram of the interface provided by the embodiment of the present application.
  • Figure 4D is a schematic diagram 4 of the interface provided by the embodiment of the present application.
  • Figure 5 is a schematic diagram of the preheating period provided by the embodiment of the present application.
  • Figure 6A is a schematic diagram 5 of the interface provided by the embodiment of the present application.
  • Figure 6B is a schematic diagram 6 of the interface provided by the embodiment of the present application.
  • Figure 7 is a schematic seventh interface diagram provided by the embodiment of the present application.
  • Figure 8 is a schematic diagram 8 of the interface provided by the embodiment of the present application.
  • Figure 9 is a schematic structural diagram 2 of the system provided by the embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • wearable devices can be used to achieve non-invasive diabetes risk detection.
  • PPG photoplethysmography
  • a wearable device such as a wearable watch or bracelet
  • the PPG signal is collected through the sensor.
  • features related to diabetes are extracted based on the PPG signal, and then the user's risk of diabetes is detected.
  • the user wears a wearable device with a built-in PPG sensor.
  • the wearable device captures the pulse signal through the PPG sensor, preprocesses the pulse signal, and obtains the waveform corresponding to the pulse signal. Multiple peaks in the waveform are detected and a first set of characteristic parameters are extracted from them.
  • a second set of characteristic parameters are extracted from the waveforms of the pulse signals corresponding to each control group. Compare the first set of characteristic parameters with the second set of characteristic parameters. Finally, based on the comparison result, it is determined whether the user is in a normal state, a pre-diabetic state, or a diabetic state.
  • the user wears a wearable device with a built-in PPG sensor.
  • the wearable device obtains the pulse signal through the PPG sensor, performs frequency domain analysis, linear analysis, nonlinear analysis, etc. on the pulse signal to obtain the pulse rate (pulse rate, PR) sequence and other information in the pulse signal, and further analyzes to obtain the required Pulse signal characteristic indicators.
  • the diabetes condition assessment results are obtained based on the analyzed pulse signal characteristic indicators and the pre-established model function of the corresponding relationship between the pulse signal characteristic indicators and the diabetes condition.
  • the above-mentioned related solutions detect diabetes risk based on pulse signals.
  • the pulse signal quality is poor and the collection time is short, the accuracy of the diabetes risk detection results obtained is low.
  • embodiments of the present application provide a non-invasive method for detecting diabetes risk, which can improve the accuracy of the detection results of diabetes risk obtained after collecting the user's physiological data (such as PPG signal) in a short period of time. sex.
  • the diabetes risk detection method provided by the embodiment of the present application can be applied in a system composed of multiple electronic devices.
  • the multiple electronic devices include wearable devices and other electronic devices, multiple wearable devices, multiple other electronic devices, etc.
  • the embodiments of the present application do not limit the number of electronic devices included in the system.
  • the system is a system composed of a wearable device 100 and other electronic devices 200.
  • the wearable device 100 may be a terminal device such as a smart watch, a smart bracelet, a smart anklet, a wireless headset, smart glasses, a smart helmet, or the like.
  • Operating systems installed on wearable devices include but are not limited to or other operating systems.
  • the wearable device may be a fixed device or a portable device. This application does not place any restrictions on the specific type of wearable devices or the operating systems installed.
  • other electronic devices 200 may be, for example, a mobile phone (mobile phone), a personal computer (PC), a tablet computer (Pad), a notebook computer, a desktop computer, a notebook computer, a computer with transceiver functions, or a wearable device. , vehicle-mounted equipment, artificial intelligence (AI) equipment and other terminal equipment.
  • the operating systems installed on other electronic devices include but are not limited to or other operating systems.
  • the other electronic device may be a fixed device or a portable device. This application does not limit the specific types of other electronic devices or the operating systems installed.
  • Figure 1 takes a wearable device and other electronic devices as an example for illustration. In actual applications, the number of wearable devices and/or other electronic devices may be multiple.
  • wireless communication technology includes but is not limited to at least one of the following: near field communication (NFC), Bluetooth (bluetooth, BT) (for example, traditional Bluetooth or low power (bluetooth low energy, BLE) Bluetooth) ), wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) network), Zigbee, frequency modulation (FM), infrared (IR), etc.
  • NFC near field communication
  • Bluetooth bluetooth, BT
  • BLE Bluetooth low power
  • WLAN wireless local area networks
  • WiFi wireless fidelity
  • Zigbee Zigbee
  • FM frequency modulation
  • IR infrared
  • both the wearable device 100 and other electronic devices 200 support the proximity discovery function. For example, after the wearable device is close to the other electronic device, the wearable device and the other electronic device can discover each other, and then establish wireless communications such as Wi-Fi peer to peer (P2P) connection, Bluetooth connection, etc. connect. After establishing a wireless communication connection, the wearable device and the other electronic device can realize signal interaction through the wireless communication connection.
  • P2P Wi-Fi peer to peer
  • Bluetooth connection Bluetooth connection
  • the wearable device 100 establishes a wireless communication connection with other electronic devices 200 through a local area network.
  • the wearable device 100 and other electronic devices 200 are both connected to the same router.
  • the wearable device 100 establishes a wireless communication connection with other electronic devices 200 through a cellular network, the Internet, etc.
  • other electronic devices 200 access the Internet through a router, and the wearable device 100 accesses the Internet through a cellular network; further, the wearable device 100 establishes a wireless communication connection with other electronic devices 200 .
  • the wearable device 100 and other electronic devices 200 collaborate to obtain the first data and the second data for diabetes risk detection, and then conduct a comprehensive analysis based on the first data and the second data to obtain the user's diabetes risk profile. Risk detection results.
  • the embodiments of this application do not limit which device obtains which data, nor does it limit which device performs comprehensive analysis on the obtained data.
  • the wearable device 100 obtains first data for diabetes risk detection; other electronic devices 200 obtain second data, and the second data includes at least one of the following: the user's basic information, such as age, gender, height, and weight. Etc., exercise data, sleep data, emotional data, physical symptom data, drug use data, etc. The specific explanation of the second data is detailed below.
  • the wearable device 100 sends the acquired first data to other electronic devices 200, and the other electronic devices 200 perform comprehensive analysis based on the first data and the second data to obtain detection results of the user's diabetes risk.
  • the wearable device 100 obtains first data for diabetes risk detection; other electronic devices 200 obtain second data, and the second data is as described above.
  • the other electronic device 200 sends the second data it acquires to the wearable device 100, and the wearable device 100 performs comprehensive analysis based on the first data and the second data to obtain the detection result of the user's diabetes risk.
  • the wearable device 100 obtains first data for diabetes risk detection, and other electronic devices 200 obtain part of the second data, such as the user's basic information, physical symptom data, drug usage data, etc. Wearable devices obtain some secondary data, such as exercise data, sleep data, etc. The wearable device then sends the acquired first data and second data to other electronic devices 200 , and the other electronic devices 200 perform comprehensive analysis on the first data and second data acquired from the wearable device and the second data acquired by itself. , to obtain the test results of the user's diabetes risk.
  • first data for diabetes risk detection and other electronic devices 200 obtain part of the second data, such as the user's basic information, physical symptom data, drug usage data, etc. Wearable devices obtain some secondary data, such as exercise data, sleep data, etc.
  • the wearable device then sends the acquired first data and second data to other electronic devices 200 , and the other electronic devices 200 perform comprehensive analysis on the first data and second data acquired from the wearable device and the second data acquired by itself. , to obtain the test results of the user's diabetes
  • the wearable device 100 obtains first data for diabetes risk detection, and other electronic devices 200 obtain part of the second data, such as the user's basic information, physical symptom data, drug usage data, etc. Wearable devices obtain some secondary data, such as exercise data, sleep data, etc. Then other electronic devices 200 send the acquired second data to the wearable device 100, and the wearable device 100 comprehensively analyzes the first data and second data acquired by itself and the second data acquired from other electronic devices 200, and obtains Test results of the user's diabetes risk.
  • first data for diabetes risk detection such as the user's basic information, physical symptom data, drug usage data, etc.
  • Wearable devices obtain some secondary data, such as exercise data, sleep data, etc.
  • other electronic devices 200 send the acquired second data to the wearable device 100, and the wearable device 100 comprehensively analyzes the first data and second data acquired by itself and the second data acquired from other electronic devices 200, and obtains Test results of the user's diabetes risk.
  • FIG. 2 shows a schematic structural diagram of the wearable device 100.
  • the wearable device 100 may include a processor 110, a memory 120, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, and a mobile communication module 150 , wireless communication module 160, audio module 170, sensor module 180, button 190, motor 191, indicator 192, camera 193, display screen 194, etc.
  • the sensor module 180 may include a photoplethysmographic sensor 180A, an acceleration (ACC) sensor 180B, a temperature sensor 180C, a touch sensor 180D, and the like.
  • the processor 110 may include one or more processing units.
  • the processor 110 may include an application processor (application processor, AP), a modem processor, a graphics processing unit (GPU), and an image signal processor. (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural network processor (neural-network processing unit, NPU), etc.
  • application processor application processor, AP
  • modem processor graphics processing unit
  • GPU graphics processing unit
  • image signal processor image signal processor
  • ISP image signal processor
  • controller video codec
  • digital signal processor digital signal processor
  • DSP digital signal processor
  • baseband processor baseband processor
  • neural network processor neural-network processing unit
  • the controller can generate operation control signals based on the instruction operation code and timing signals to complete the control of fetching and executing instructions.
  • the processor 110 may also be provided with a memory for storing instructions and data.
  • the memory in processor 110 is cache memory. This memory may hold instructions or data that have been recently used or recycled by processor 110 . If the processor 110 needs to use the instructions or data again, it can be called directly from the memory. Repeated access is avoided and the waiting time of the processor 110 is reduced, thus improving the efficiency of the system.
  • the processor 110 may include one or more interfaces, such as a USB interface 130 or the like.
  • the USB interface 130 may be an interface that complies with USB standard specifications, and specifically may be a Mini USB interface, a Micro USB interface, a USB type C interface, etc.
  • the USB interface 130 can be used to connect a charger to charge the wearable device 100, and can also be used to transmit data between the wearable device 100 and peripheral devices. It can also be used to connect headphones to play audio through them. This interface can also be used to connect other devices, such as Augmented reality (AR) equipment, etc.
  • AR Augmented reality
  • the charging management module 140 is used to receive charging input from the charger.
  • the charger can be a wireless charger or a wired charger.
  • the power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110.
  • the power management module 141 receives input from the battery 142 and/or the charging management module 140, and supplies power to the processor 110, the memory 120, the display screen 194, the camera 193, the wireless communication module 160, and the like.
  • the wireless communication function of the wearable device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, and so on.
  • Antenna 1 and Antenna 2 are used to transmit and receive electromagnetic wave signals.
  • Each antenna in wearable device 100 may be used to cover a single or multiple communication bands. Different antennas can also be reused to improve antenna utilization.
  • Antenna 1 can be reused as a diversity antenna for a wireless LAN. In other embodiments, antennas may be used in conjunction with tuning switches.
  • the mobile communication module 150 can provide solutions for wireless communication including 2G/3G/4G/5G applied on the wearable device 100 .
  • the mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc.
  • the wireless communication module 160 can provide applications on the wearable device 100 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) network), Bluetooth (bluetooth, BT), and global navigation.
  • WLAN wireless local area networks
  • WiFi wireless fidelity
  • Bluetooth bluetooth, BT
  • global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions.
  • the antenna 1 of the wearable device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the wearable device 100 can communicate with the network and other devices through wireless communication technology.
  • the wearable device 100 implements display functions through a GPU, a display screen 194, an application processor, and the like.
  • the GPU is an image processing microprocessor and is connected to the display screen 194 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering.
  • Processor 110 may include one or more GPUs that execute program instructions to generate or alter display information.
  • the display screen 194 is used to display images, videos, etc.
  • Display 194 includes a display panel.
  • the display panel can use a liquid crystal display (LCD), such as an organic light-emitting diode (OLED), an active matrix organic light emitting diode or an active matrix organic light emitting diode (active-matrix).
  • LCD liquid crystal display
  • OLED organic light-emitting diode
  • active-matrix active matrix organic light emitting diode
  • AMOLED organic light emitting diodes
  • FLED flexible light-emitting diodes
  • Mini-led Micro-led, Micro-oled
  • quantum dot light emitting diodes QLED
  • the wearable device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.
  • Camera 193 is used to capture still images or video.
  • the wearable device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.
  • Memory 120 may be used to store computer executable program code, which includes instructions.
  • the memory 120 may include a program storage area and a data storage area.
  • the stored program area can store an operating system, at least one application program required for a function (such as a sound playback function, an image playback function, etc.).
  • the storage data area may store data created during use of the wearable device 100 (such as first data, second data), etc.
  • the memory 120 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.
  • the processor 110 executes various functional applications and data processing of the wearable device 100 by executing instructions stored in the memory 120 and/or instructions stored in a memory provided in the processor.
  • the wearable device 100 can implement audio functions through the audio module 170 and an application processor. Such as music playback, recording, etc.
  • the audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. Audio module 170 may also be used to encode and decode audio signals. In some embodiments, the audio module 170 may be provided in the processor 110 , or some functional modules of the audio module 170 may be provided in the processor 110 . The wearable device 100 can perform music playback, recording, etc. through the audio module 170 .
  • the audio module 170 may include a speaker, a receiver, a microphone, an application processor, etc. to implement audio functions.
  • Photoplethysmography sensor 180A can use photoplethysmography (PPG), Based on light emitting diode (LED) light sources and detectors, the PPG signal is obtained by measuring the attenuated light reflected and absorbed by human blood vessels and tissues.
  • PPG photoplethysmography
  • LED light emitting diode
  • the principle of photoplethysmography is that when light passes through skin tissue and then reflects to the photosensitive sensor, there will be a certain attenuation of the light.
  • the absorption of light by muscles, bones, veins and other connecting tissues is basically unchanged, but blood is different. Since there is blood flow in the arteries, the absorption of light will naturally also vary. changed.
  • the wearable device 100 collects PPG signals through the photoplethysm sensor 180A for analysis, and can obtain the user's physiological data, such as heart rate, respiratory rate, blood oxygen, etc.
  • features related to diabetes are extracted by analyzing PPG signals to detect the user's diabetes risk.
  • the acceleration sensor 180B can detect the acceleration of the wearable device 100 in various directions (generally three axes). When the wearable device 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of wearable devices and be used in horizontal and vertical screen switching, pedometer and other applications. In some embodiments of the present application, the acceleration sensor 180B measures an acceleration signal, where the acceleration signal can be used to determine the user's state, such as a stationary state, a moving state, etc. Because users are in different states, physiological data (such as breathing rate, heart rate, blood oxygen, blood sugar, etc.) may be different. Therefore, in order to improve the accuracy of the obtained user's physiological data, the wearable device 100 can also determine the user's state through the acceleration signal collected by the acceleration sensor 180B.
  • physiological data such as breathing rate, heart rate, blood oxygen, blood sugar, etc.
  • Temperature sensor 180C is used to detect temperature.
  • the wearable device 100 utilizes the temperature detected by the temperature sensor 180C to execute the temperature processing strategy. For example, when the temperature reported by the temperature sensor 180C exceeds a threshold, the wearable device 100 reduces the performance of a processor located near the temperature sensor 180C to reduce power consumption and implement thermal protection. In other embodiments, when the temperature is lower than another threshold, the wearable device 100 heats the battery 142 to avoid the low temperature causing the wearable device 100 to shut down abnormally. In some other embodiments, when the temperature is lower than another threshold, the wearable device 100 performs boosting on the output voltage of the battery 142 to avoid abnormal shutdown caused by low temperature.
  • Touch sensor 180D is also called a "touch device”.
  • the touch sensor 180D can be disposed on the display screen 194.
  • the touch sensor 180D and the display screen 194 form a touch screen, which is also called a "touch screen”.
  • the touch sensor 180D is used to detect a touch operation acting on or near the touch sensor 180D.
  • the touch sensor can pass the detected touch operation to the application processor to determine the touch event type.
  • Visual output related to the touch operation may be provided through display screen 194 .
  • the touch sensor 180D may also be disposed on the surface of the wearable device 100 at a location different from that of the display screen 194 .
  • the sensor module 180 may also include a pressure sensor, an air pressure sensor, a magnetic sensor, a distance sensor, a proximity light sensor, a gyroscope sensor, a fingerprint sensor, an ambient light sensor, a bone conduction sensor, etc.
  • the buttons 190 include a power button, a volume button, etc.
  • Key 190 may be a mechanical key. It can also be a touch button.
  • the wearable device 100 may receive key inputs and generate key signal inputs related to user settings and function control of the wearable device 100 .
  • the motor 191 can generate vibration prompts.
  • the motor 191 can be used for vibration prompts for incoming calls and can also be used for touch vibration feedback.
  • the indicator 192 may be an indicator light, which may be used to indicate charging status, power changes, or may be used to indicate messages, missed calls, notifications, etc.
  • FIG. 3 shows another exemplary structure of a wearable device.
  • the wearable device includes: a processor 201, a memory 202, and a transceiver 203.
  • the processor 201 and the memory 202 please refer to the implementation of the processor and the memory mentioned above.
  • Transceiver 203 is used for the wearable device to interact with other devices (such as mobile phones).
  • Transceiver 203 may be a device based on a communication protocol such as Wi-Fi, Bluetooth, or other communication protocols.
  • the wearable device may include more or fewer components than those shown in Figures 2 and 3, or some components may be combined, some components may be separated, or some components may be replaced, Or a different component arrangement.
  • the components illustrated may be implemented in hardware, software, or a combination of software and hardware.
  • the structure of the electronic device 200 reference may be made to the structure of the wearable device 100.
  • the electronic device 200 may have more or less structures than the wearable device 100, and this application does not specifically limit this.
  • the diabetes risk detection method provided by the embodiment of the present application can also be applied to any other electronic device that can obtain the first data and the second data for diabetes risk detection, such as any device with the structure shown in Figure 2 or Figure 3 , such as: mobile phones, wearable devices, etc.
  • Embodiments of the present application provide a non-invasive method for detecting diabetes risk.
  • the method obtains first data and second data for detecting diabetes risk, such as the user's basic information (such as age, gender, height, weight, etc.) , diet, exercise, health, sleep and other data.
  • the diabetes risk detection result can be obtained in a short time.
  • the detection result is a result obtained by using the second data to calibrate the first data used for diabetes risk detection, which can improve the accuracy of short-term detection results.
  • the first data includes various data that can reflect the characteristics of diabetes and is further used for diabetes risk detection.
  • some wearable devices have built-in PPG sensors, and the PPG signal is acquired through the PPG sensor (the PPG signal can be analyzed based on pulse signals, signals obtained by pressing fingers, etc.) and the PPG signal is analyzed to extract features related to diabetes to detect diabetes risk. . Therefore, the first data may be a PPG signal.
  • some wearable devices can be built into the eye to monitor the wearer's blood sugar levels by analyzing the glucose content in their tears. Therefore, the first data may be a blood glucose value.
  • some wearable devices can be worn on the fingers.
  • the first data can also be the optical signal.
  • the embodiments of the present application do not limit the type of the first data.
  • the second data is used to reflect the user's life information and can cover all aspects of the user's life.
  • the second data includes at least one of the following: basic information, diet, exercise, physical symptoms, drug usage, sleep and other data.
  • the user's basic information includes the user's age, gender, height, weight, etc.
  • the user's dietary data includes the user's eating time, food taste or ingredients, and degree of satiety.
  • the user's exercise data includes the user's exercise time, duration, exercise intensity, exercise frequency, etc.
  • the user's sleep data includes the user's sleep time period, sleep duration, whether in deep sleep, deep sleep time period, deep sleep duration, etc.
  • Physical symptom data includes whether the user has physical symptoms related to diabetes, such as three highs and one low.
  • User's drug usage data includes whether medication is used, type of medication, frequency of medication, etc. In some descriptions of the embodiments of this application and the accompanying drawings, physical symptom data and drug usage data are described as health data.
  • the second data may also include a mental stress index, a mood index, etc., used to indicate the user's recent mental stress, whether the user is in a good mood, etc.
  • the following description takes the method provided by the embodiment of the present application applied in a system composed of a wearable device and a mobile phone as an example.
  • the mobile phone receives the user's triggering operation for diabetes risk detection.
  • the mobile phone obtains the second data, and the mobile phone obtains the first data through the wearable device.
  • the mobile phone detects the user's risk of diabetes based on the first data and the second data, and obtains the diabetes risk detection result.
  • the first data includes any data that can reflect the characteristics of diabetes and is used for diabetes risk detection.
  • the second data includes at least one of the following: user's basic information, diet, exercise, health, sleep and other data.
  • the user's triggering operation for diabetes risk detection is used to trigger the mobile phone to turn on the diabetes risk detection function.
  • the mobile phone provides the user with an entrance to enable the diabetes risk detection function through an application, such as the "Sports Health" application.
  • mobile phones provide users with access to this function through "mini programs”.
  • the mobile phone provides users with the entrance to this function through the recommendation service of the service card.
  • the user's triggering operation for diabetes risk detection can be a series of operations such as clicking and sliding in the application or applet or service card.
  • the trigger operation can also be some shortcut operations of the user, such as shortcut operations through gestures or key combinations.
  • the trigger operation can also be a voice command input by the user, such as calling the voice assistant to turn on the diabetes risk detection function, etc.
  • the embodiments of this application do not limit the specific implementation form of the triggering operation.
  • the "Sports and Health” application 401 is installed in the homepage interface 400 of the mobile phone.
  • the mobile phone displays interface 402 as shown in Figure 4A.
  • the interface 402 displays icons of all functional modules that the application can provide, such as icons of functional modules such as health management, intelligent fat reduction, heart rate measurement, sleep monitoring, and diabetes risk detection.
  • long-term detection and short-term detection are distinguished based on the length of the first data collected during diabetes risk detection.
  • Long-term detection collects the first data for a longer period of time, usually 5 to 7 days;
  • Short-term detection collects the first data for a shorter period of time, usually 1-2 days.
  • the detection results corresponding to "long-term detection” are more accurate than the detection results corresponding to "short-term detection", and the user has to wait longer for the results.
  • the above-mentioned 5-7 days and 1-2 days are only exemplary descriptions and are intended to distinguish the length of time of the first data that needs to be collected for long-term detection and short-term detection.
  • the specific length of time is determined according to the actual function of the electronic device.
  • the detection function required. Regardless of whether the user chooses the "short-term detection” or “long-term detection” function, it is equivalent to the user performing a triggering operation for diabetes risk detection.
  • the function provided by the "diabetes risk detection" function module does not distinguish between "short-term detection” and "long-term detection” functions, that is, the module may only provide a default detection function. As long as the mobile phone detects that the user triggers the function, the mobile phone obtains the first data and the second data for diabetes risk detection.
  • the method of the embodiment of the present application can be applied in both short-term detection and long-term detection scenarios to improve the accuracy of detection results.
  • the following description takes the user's selection of the "short-term detection" function as an example.
  • the mobile phone After the mobile phone detects the user's operation 405 of selecting the "short-term detection” function, it obtains the first data and the second data for diabetes risk detection.
  • the mobile phone can obtain the second data by interacting with the user.
  • the mobile phone displays the prompt interface 406 as shown in Figure 4B.
  • the mobile phone displays prompt information for collecting the second data.
  • the following prompt is displayed: "A short-term diabetes risk test will be conducted for you soon. The test results will be provided to you within 1-2 days; in order to improve the accuracy of the test results, you are required to provide relevant user data. Do you provide user data?" ?” and the corresponding selection controls "Yes" and "No" for the user to choose whether to provide user data.
  • the mobile phone displays the interface 407 in Figure 4B.
  • the second data can reflect the user's daily habits.
  • the content of the second data can cover all aspects of the user's daily life habits. The more types of second data the user can provide and the more detailed the content, the more helpful it is to improve the accuracy of the detection results.
  • the interface 407 displays personal information, exercise, health, diet and other related second data that the user needs to provide.
  • personal information specifically includes the user's gender, age, height, weight, etc.
  • Exercise data includes the user's exercise time period, exercise duration, exercise items, and exercise frequency (such as the number of exercises in a preset time period, such as three times a week, twice a month, etc.).
  • Diet data includes the user's recent diet type (such as light, greasy, sweet) and the degree of satiety (the degree of satiety refers to whether the user feels hungry or full after eating, such as five points full, eight points full , very full).
  • the interface 407 only provides some second data that needs to be provided by the user as an example. In actual design, more or less second data that needs to be provided by the user may be included.
  • all the second data that the user needs to fill in are displayed on the same page. However, because there is a lot of second data that the user needs to fill in, the current page cannot fully display all the second data. Then the user The page can be scrolled to display the complete secondary data.
  • all the second data that the user needs to fill in are displayed on different pages, for example: the user's personal information, exercise, health, and diet data are displayed on four different pages. Users can jump to the next page by turning the page or clicking on the prompt information at the bottom of the page, such as "Next". If the user does not want to provide certain secondary data, he may not fill in the corresponding data or click "Skip".
  • the second data is obtained through voice interaction between the mobile phone and the user.
  • the embodiments of the present application do not limit the interaction method between the mobile phone and the user when acquiring the second data.
  • the mobile phone can also obtain the second data through other methods, such as obtaining the second data through wearable devices or data that the user has entered in other applications under the premise of obtaining the user's authorization.
  • the mobile phone displays a prompt interface, which may include the following content: "Your exercise data will be obtained through a wearable device” and the corresponding controls “Agree” and “ disagree”. and/or, "Your sleep data will be obtained through the sleep detection module in the Sports Health application” and the corresponding controls "Agree” and “Disagree”.
  • the mobile phone can obtain different second data respectively through one or more wearable devices.
  • the method of establishing a connection between the mobile phone and the wearable device and obtaining data such as exercise data and heart rate data through the wearable device can refer to the existing technology. This application No longer.
  • the user can also input other supplementary second data that he or she wants to input according to the actual situation, and the mobile phone can obtain the user's supplementary second data by identifying keywords or other methods.
  • the specific implementation method for the mobile phone to obtain the second data is not limited.
  • the user After the mobile phone obtains the second data, as shown in the interface 408 in Figure 4C, the user is prompted that the mobile phone will further obtain the first data (a PPG signal is taken as an example in the figure) from the wearable device (a smart watch is taken as an example in the figure).
  • a PPG signal is taken as an example in the figure
  • a smart watch is taken as an example in the figure
  • the user is prompted for relevant information about the wearable device, and the user can instruct the mobile phone to obtain the PPG signal through the smart watch by clicking "Start Obtaining PPG Signal".
  • the example in the above figure is explained by taking the mobile phone to first obtain the second data and then obtain the first data.
  • the mobile phone can also obtain the first data first and then the second data, or obtain the first data and the second data at the same time.
  • user interfaces corresponding to this data acquisition method are designed for wearable devices and mobile phones. For example: in other possible implementations, after the user clicks "Short-term Detection" in interface 404, on the one hand, the mobile phone obtains the first data through the wearable device (this process can be operated internally on the mobile phone, that is, invisible to the user), On the one hand, an interface shown as interface 406 is displayed.
  • the embodiment of the present application does not limit the order in which the mobile phone obtains the second data and the first data.
  • the mobile phone analyzes the second data obtained and the first data obtained through the wearable device to obtain the user's diabetes risk detection result.
  • the wearable device as a smart watch as an example, the smart watch can have a built-in PPG sensor, which can acquire the pulse signal and analyze the pulse signal to obtain the PPG signal.
  • the smart watch sends this PPG signal to the mobile phone.
  • the mobile phone obtains the diabetes risk detection result based on the PPG signal and the acquired second data.
  • the mobile phone first obtains the preliminary diabetes risk value based on the first data (PPG signal) (for the convenience of description, this application describes the preliminary diabetes risk value as the first risk value), and then obtains the preliminary diabetes risk value based on the obtained second data. and the first risk value to obtain the final diabetes risk value (for convenience of description, this application describes the final diabetes risk value as the second risk value), and the second risk value is used as the final diabetes risk detection result.
  • PPG signal for the convenience of description, this application describes the preliminary diabetes risk value as the first risk value
  • the preliminary diabetes risk value based on the obtained second data
  • the first risk value for convenience of description, this application describes the final diabetes risk value as the second risk value
  • the second risk value is used as the final diabetes risk detection result.
  • the second risk value is obtained according to the weight corresponding to different second data and the first risk value. For example: adjust the first risk value according to the weight corresponding to different second data to obtain the second risk value.
  • the weight corresponding to an item or a type of second data is used to indicate the degree of influence of the item of second data on the detection result; the greater the influence of a certain item or type of second data on the detection result, the greater the corresponding weight. , correspondingly, the greater the adjustment range for the first risk value.
  • the weight can be preset. That is, the first risk value is increased or decreased according to the impact of different second data on diabetes.
  • first risk values corresponding to different risks of diabetes are set. The greater the risk of the user suffering from diabetes, the greater the corresponding first risk value. For example: if you do not have diabetes (healthy user), the corresponding first risk value is below 60 points; for pre-diabetes, the corresponding first risk value is 60-80 points; for diabetes, the corresponding first risk value For 80-100 points.
  • the mobile phone analyzes the user's basic information and determines that the user's weight is 65kg and 158cm, the user is overweight. Since weight has a slight impact on diabetes, the value can be slightly increased.
  • the first risk value for example, is increased by 3 points to 68 points; further, the mobile phone analyzes the user's dietary data and determines that the user has frequently eaten sweet foods recently. Since eating habits have a greater impact on diabetes than weight, Then further fine-tune the first risk value, for example, increase it by 5 points to 73 points. Furthermore, the mobile phone analyzes the user's exercise data and determines that the user exercises regularly.
  • the mobile phone analyzes the user's physical symptom data and drug usage data to determine the user's medication and current physical symptoms. If there are symptoms related to diabetes, the physical symptom data and drug usage data will have an impact on diabetes. If it is larger, it will be increased by 8 points to 78 points. Furthermore, the mobile phone can also analyze other secondary data that can be obtained, such as sleep, whether there is greater mental stress, whether the mood is good, etc., and adjust the scores in sequence to obtain the second risk value. The second risk value is used as the final diabetes risk detection result.
  • the adjustment ranges corresponding to different first data are the same, that is, no weight may be set for the first data.
  • different first data have corresponding preset adjustment values, which can be adjusted according to the preset adjustment values.
  • the preset adjustment values corresponding to different first data may be the same or different.
  • the mobile phone only obtains the diabetes risk detection result based on the first data obtained from the wearable device, that is, the first risk value is Diabetes risk test results.
  • the mobile phone outputs the diabetes risk test results.
  • mobile phones display diabetes risk test results in the display interface.
  • the mobile phone can also output the test results in other ways such as voice broadcast.
  • the mobile phone displaying diabetes risk detection results in the display interface as an example, in one possible implementation, if the mobile phone can obtain the second data, the detection result is obtained based on a comprehensive analysis of the second data and the first data, Then the mobile phone directly displays the second risk value as the diabetes risk test result. If the second data cannot be obtained, the test result is obtained based on the analysis of the first data, and the mobile phone directly displays the first risk value as the diabetes risk test result. In another possible implementation, a rough diabetes risk assessment result is obtained based on the diabetes risk value.
  • the corresponding evaluation result is "the evaluation result is good and the risk of diabetes is low”; if the diabetes risk value is 60 to 80 points, the corresponding evaluation result is "the evaluation result is average, you may currently If you are in the pre-diabetes stage and have a risk of developing diabetes”; if the diabetes risk value is 80-100 points, the corresponding assessment result is "the assessment result is poor and you have an extremely severe risk of developing diabetes".
  • the phone displays this rough diabetes risk assessment. For example, as shown in the interface 410 in FIG. 4D , the evaluation result "the evaluation result is good and the risk of diabetes is low" is displayed in the interface.
  • the mobile phone can also output instructions and health advice corresponding to the test result.
  • the corresponding description can be "Based on the PPG signal obtained by the wearable device and user data, the evaluation result is divided into good and average.” and worse, your current assessment result is good, indicating that blood glucose concentration is maintained at a good level.”
  • the health advice corresponding to the evaluation result may be: the recent blood sugar health status is good, it is recommended to maintain a low-sugar and low-fat diet, moderately increase exercise, etc.
  • the "diabetes risk detection” module provides two functions: “short-term detection” and “long-term detection”, it can output both short-term detection results and long-term detection results.
  • both short-term and long-term detection results can be displayed on the same interface. Since long-term detection results require the collection of more time-consuming second data, the situation that may occur in the display interface is: short-term detection results appear, but long-term detection results are still in the warm-up period, and no results have been output yet. For example, as shown in the interface 410 in Figure 4D, the interface displays "short-term test results: good evaluation results, low risk of diabetes" and "long-term test results: currently in the warm-up period” , there are no test results yet.”
  • the warm-up period can be understood as the time period for waiting for long-term detection results, or the time period from starting to collect the first data to obtaining the long-term detection results.
  • the display interface may appear as follows: there are both short-term detection results and long-term detection results.
  • the short-term detection results are displayed in this interface: the evaluation result is good, the risk of diabetes is low, and the long-term detection results expressed in images are displayed.
  • the first data collected during "short-term detection” is insufficient, and the accuracy of the detection results obtained based only on the first data is low.
  • by collecting the second data and comprehensively analyzing the second data and the first data it is equivalent to using the second data to calibrate the diabetes risk detection results obtained based on the first data, and obtain the calibrated diabetes risk test results.
  • Risk detection results improve the accuracy of detection results.
  • the solution provided by the embodiment of the present application can quickly provide the detection results of diabetes risk in a shorter time, alleviating the user's anxiety during the waiting process.
  • the detection results can reflect the user's short-term detection. Diabetes risk conditions that exist within a certain period of time to meet user needs and improve user experience.
  • T 1 is the time when the first data collection starts
  • T 2 is the time when the long-term risk detection result is obtained by collecting the first data for a longer period of time.
  • the period between T 1 and T 2 is the preheating period. If “long-term detection” is used, the user needs to wait until time T 2 to get the result of the long-term detection. If “short-term detection” is used, the user can get the short-term detection result at a certain time between T 1 and T 2 .
  • the detection result is higher in accuracy because it is calibrated based on the second data.
  • the mobile phone can also determine the confidence level of the detection result based on the collected second data and the first data, that is, the credibility or accuracy of the detection result.
  • the duration of the first data collected, the quality of the first data collected, the type of the second data collected, the level of detail of the second data collected, etc. affect the confidence of the detection results.
  • the quality of the collected first data can be obtained by determining whether the first data is missing, the status of the user, etc. For example: if the first data of important times such as three meals and naps of the user is not collected, the quality of the first data will be poor. Another example: the first data may be affected by the user's motion status. If If the first data is collected when the user is performing strenuous activities, the quality of the first data will be poor.
  • the test result obtained is the first test result. If the first data that can be obtained includes its PPG signal in the past three days, and the second data that can be obtained includes the user's basic information, dietary data, physical symptom data, drug usage data, and exercise data, the detection result obtained is the second test result. Then, the confidence level of the second detection result is higher than the confidence level of the first detection result.
  • the mobile phone not only outputs the detection result, but also outputs the confidence level of the detection result.
  • the interface 601 shown in FIG. 6A and the interface 602 shown in FIG. 6B display the diabetes risk detection result and the confidence level corresponding to the detection result. Confidence is generally expressed by probability.
  • the probability value is calculated, the interval range in which it is located is obtained according to the value of the probability value. Different interval ranges correspond to a rough high and low situation, and then the confidence level is displayed as Rough high and low situation.
  • the probability value is lower than 60%, the corresponding confidence level is low, the probability value is between 60% and 75%, the probability value is between 75% and 90%, the probability value is high, and the probability value is above 90%. high.
  • the confidence level can also be displayed in the interface in the form of a probability value.
  • the mobile phone can also prompt the user about the influence relationship between the confidence level and the second data, that is, prompt the user about the confidence level of the diabetes risk detection result and the second data corresponding to the confidence level.
  • the obtainable second data corresponding to the confidence level can be further displayed, including diet data, exercise data, physical symptom data, and drug usage data (wherein physical symptom data, Drug use data also includes drug use data and physical symptom data), sleep data, and emotional data (such as high mental stress).
  • the acquired second data corresponding to the confidence level is displayed, including only motion data and excluding other data. It can be seen that the reason why the confidence level shown in the interface 602 is lower than the confidence level shown in the interface 601 is that it acquires less second data.
  • the mobile phone can further prompt the user to improve the acquired second data or input more second data to improve the confidence of the detection results.
  • the mobile phone can voice broadcast or display the following words: "The confidence of the current test results is low. In order to improve the accuracy of the test results, please provide further user data. After you provide more user data, we will Output the detection results again.” In this way, by continuously guiding the user to input more second data, the confidence of the detection results is improved.
  • the second data obtained by the mobile phone is all possible second data of the user within a period of time.
  • the process of obtaining the second data requires interaction with the user, which will bring a certain "interaction burden" to the user.
  • the mobile phone determines the detection result based on a large amount of second data, which requires a large amount of collection and calculation.
  • the user's interaction burden and the mobile phone's processing burden are reduced.
  • only the second data of certain specific time periods can be collected for the specific time period.
  • a period of poor quality or missing data of the collected first data is determined, and only the second data of this period is collected.
  • statistical analysis is performed on the first data for the period of time, and a time period in which the quality of the first data is poor or the data is missing is identified.
  • the time period when the pulse signal quality is poor or the data is missing is detected based on the waveform, peak value and other characteristics of the pulse signal. For example, this time period is usually the user's nap time period.
  • the mobile phone When acquiring the second data, the mobile phone only obtains the second data of the user during this nap time period.
  • the obtained second data of the user during the nap time period includes the user's lunch satiety level (such as no eating, three points full, five points full, eight points full, very full, Twelve minutes full, etc.), lunch type (such as light, greasy, sweet, etc.) and exercise data (such as exercise intensity: low intensity, medium intensity, extreme intensity, etc.).
  • lunch satiety level such as no eating, three points full, five points full, eight points full, very full, Twelve minutes full, etc.
  • lunch type such as light, greasy, sweet, etc.
  • exercise data such as exercise intensity: low intensity, medium intensity, extreme intensity, etc.
  • the second data of the nap time period shown in FIG. 7 is only an exemplary illustration, and the second data of the nap time period is not limited to the data shown in FIG. 7 .
  • the first data is missing or of poor quality, it will have a greater impact on the accuracy of the detection results. big. So, for these important times Intervals, collect users’ secondary data during these important time periods. For example: for the night sleep period, obtain the user's sleep time, sleep duration, deep sleep status (such as whether deep sleep, deep sleep period and deep sleep duration), etc. For the periods before and after three meals, the user's satiety level, diet type, and exercise data of the three meals are obtained respectively. For the nap period, obtain the user's nap time, nap duration, etc.
  • the first data of these important time periods are counted, and it is determined which time periods among these important time periods have poor first data quality or missing data.
  • the obtained first data of the nighttime sleep period, the period before and after three meals, and the nap period are collected to identify whether the user has a time period in which the first data quality is poor or the data is missing during these important time periods. If only the second data of the user's sleep period at night is missing, then the second data of the user's sleep period at night is separately collected.
  • the mobile phone further eliminates the interference of the user's various behaviors before going to bed on the test results by collecting secondary data of the sleep period, including: sleep time, food before bed, whether to exercise before bed, and other information, and improves the accuracy of the test results.
  • the mobile phone determines the user's activities during usual sleep time based on the data collected by the wearable device, such as ACC data and heart rate, and then determines whether there is the possibility of staying up late, eating, exercising, etc. . If the user engages in activities such as staying up late, eating, exercising, etc., the mobile phone interacts with the user to collect targeted information about the user's diet, exercise, etc. before going to bed.
  • the data collected by the wearable device such as ACC data and heart rate
  • the second data of the sleep time period is collected in a targeted manner.
  • important data segments (such as: night sleep period, period before and after three meals, nap period, etc.) will have a greater impact on the detection results when the signal quality is poor or missing. Confidence.
  • the above method provided by the embodiments of the present application can improve the accuracy of the detection results by separately collecting targeted information on important data segments with poor signal quality or missing information while minimizing the user interaction burden.
  • differences in the second data obtained by the mobile phone will lead to differences in the confidence of the detection results.
  • Some data have a greater impact on the confidence of the detection results.
  • the mobile phone may only obtain these data, and the confidence of the detection results obtained based on the second data and the first data can meet the requirements.
  • Some data have a small impact on the confidence of the detection results, so the mobile phone needs to obtain more second data before the confidence of the detection results can meet the requirements.
  • the priorities of different second data are obtained according to the degree of influence of the second data on the confidence of the detection result. Then the mobile phone can collect the second data according to the priority. After collecting the high-priority second data, it determines the detection result and the confidence of the detection result based on the high-priority second data and the first data. If the confidence meets the requirements , there is no need to further collect the second data; if the confidence does not meet the requirements, further collect the second data of the next priority level.
  • the second data includes multiple types of second data. Then, obtain the first data; obtain the second data in order from high to low according to the priority of different second data; each time the second data is obtained, if it is determined based on the obtained second data and the first data If the confidence level of the diabetes risk detection result is equal to or higher than the preset threshold, acquisition of the second data is stopped. Otherwise, if the confidence of the diabetes risk detection result is determined to be lower than the preset threshold based on the acquired second data and the first data, the second data will continue to be acquired until the confidence of the diabetes risk detection result is equal to or higher than the preset threshold. Set threshold.
  • the first data can be obtained; high-priority second data can be obtained according to the priorities of different second data; if the confidence of the obtained diabetes risk detection result is determined based on the high-priority second data and the first data degree is equal to or higher than the preset threshold, stop acquiring the second data. If the confidence of the diabetes risk detection result is determined to be lower than the preset threshold based on the high-priority second data and the first data, the low-priority second data is obtained and the result is obtained based on the obtained second data and the first data. The diabetes test result is determined until the confidence level of the diabetes risk test result is equal to or higher than a preset threshold.
  • the mobile phone can use a neural network model for training to obtain the priorities of different second data.
  • a common priority of the second data is obtained or set through training, and the common priority is applicable to all users.
  • different second data may have different priorities for different users or different groups.
  • the priority order of the second data is physical symptom data, drug usage data>diet data>exercise data>sleep data; while for other users, the priority order of the second data is physical symptom data, Medication usage data > Exercise data > Sleep data > Diet data.
  • the priorities of the corresponding second data can be determined respectively for different or different types of users.
  • the priority order of different second data corresponding to it is as follows: body Symptom data, drug usage data>diet data>exercise data>sleep data, then the mobile phone can first interact with the user to obtain physical symptom data, drug usage data, and determine the risk of diabetes based on the obtained physical symptom data, drug usage data and first data The detection result and the confidence of the detection result. If the confidence is higher than the preset threshold, there is no need to further obtain other second data; on the contrary, if the confidence is lower than the preset threshold, further dietary data is obtained in order of priority.
  • this method can reduce the amount of second data filled in by the user and reduce the user's interaction burden. For example: If physical symptom data, drug usage data, diet data, and exercise data are located on different pages, it is better for the user to flip between these three pages and fill in all the data on these three pages.
  • users may only need to fill in one type of content (that is, the content of one page), such as physical symptom data and drug usage data, without filling in other second data, reducing the user's interaction burden.
  • the method provided by the embodiment of the present application collects second data with different priorities in sequence according to the priority of the second data, and calculates the detection result and the confidence of the detection result after each collection of the second data; when the confidence reaches the standard You can then stop collecting the second data, thereby reducing the user’s “interaction burden”.
  • multiple embodiments of the present application can be combined and the combined solution can be implemented.
  • some operations in the processes of each method embodiment are optionally combined, and/or the order of some operations is optionally changed.
  • the execution order between the steps of each process is only exemplary and does not constitute a limitation on the execution order between the steps. Other execution orders are possible between the steps. It is not intended that the order of execution described is the only order in which these operations may be performed.
  • One of ordinary skill in the art will recognize various ways to reorder the operations described herein.
  • the process details involved in a certain embodiment herein are also applicable to other embodiments in a similar manner, or different embodiments can be used in combination.
  • each method embodiment can be implemented individually or in combination.
  • the diabetes risk detection system 900 includes:
  • the data collection module 901 is used to collect first data and second data.
  • the data collection module can be divided into a sensor collection module 9011 and a user interaction collection module 9012.
  • the sensor collection module 9011 is used to collect data collected by sensors, such as the user's first data such as PPG and ACC and part of the second data (the part of the second data includes sleep data, motion data, etc.).
  • the user interaction collection module 9012 is used to collect data through interaction with the user, including user basic information, such as user age, gender, height, weight and other information, drug usage data, emotional data and other second data.
  • the feature extraction module 902 is used to preprocess the first data (eg, PPG signal), analyze whether the first data is missing, determine the quality of the first data, extract diabetes-related features from the first data, etc.
  • first data eg, PPG signal
  • the user performs diabetes risk detection based on the first data and the second data and obtains the detection results.
  • the detection module 903 may also specifically include a short-term detection module and a long-term detection module.
  • the short-term detection module is used to quickly provide diabetes detection results by analyzing the data collected in a short period of time, relieve the user's anxiety during the waiting process, and reflect the user's short-term health status.
  • the long-term detection module is used to analyze the data collected over a long period of time to provide more accurate diabetes detection results after a period of data accumulation.
  • the output module 904 is used to output diabetes risk detection results.
  • short-term detection and long-term detection are included, output the short-term detection results and long-term detection results.
  • the system provided by the embodiment of the present application also includes a health intervention module (not shown in the figure), which is used to draw a diabetes risk curve based on the detection results and the improvement of multiple monitoring results, and give health intervention suggestions, reflecting User health status.
  • a health intervention module (not shown in the figure), which is used to draw a diabetes risk curve based on the detection results and the improvement of multiple monitoring results, and give health intervention suggestions, reflecting User health status.
  • All modules in the above system can be located in the same electronic device, such as mobile phones, wearable devices, etc.
  • the modules in the above system are located in multiple different devices.
  • the data acquisition module and feature extraction module are located in the computer with PPG detection module.
  • the detection module, output module and health intervention module are located in the mobile phone.
  • the data collection modules can be located in wearable devices and mobile phones, and can collect different data.
  • the diabetes risk detection device provided by the embodiment of the present application will be described in detail below with reference to FIG. 10 .
  • FIG. 10 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the electronic device 1000 may include: a transceiver unit 1001 and a processing unit 1002.
  • the electronic device 1000 can be used to implement the functions of the electronic device involved in the above method embodiments (taking the mobile phone in the above embodiments as an example).
  • the transceiver unit 1001 is used to support the interaction between the electronic device and other electronic devices, for example: receiving the first data and/or the second data from other electronic devices (taking the wearable device in the previous embodiment as an example).
  • the processing unit 1002 is configured to support the electronic device to perform the following steps: determining a diabetes risk detection result based on the first data and the second data.
  • the electronic device also includes an input unit 1003 and an output unit 1004, where the input unit 1003 is used to support the electronic device in obtaining the second data.
  • the output unit 1004 is used to support the electronic device to perform the following steps: outputting the diabetes risk detection result, outputting the confidence level of the diabetes risk detection result, prompting the user the confidence level of the diabetes risk detection result and the second value corresponding to the confidence level. data, and when the confidence level is lower than the preset threshold, the user is prompted to edit the acquired second data or input more second data.
  • the transceiver unit may include a receiving unit and a transmitting unit, may be implemented by a transceiver or a transceiver-related circuit component, and may be a transceiver or a transceiver module.
  • the operation and/or function of each unit in the first electronic device 1000 is to implement the corresponding process of the diabetes risk detection method described in the above method embodiment. All relevant content of each step involved in the above method embodiment can be quoted. The function description of the corresponding functional unit will not be repeated here for the sake of brevity.
  • the electronic device 1000 shown in Fig. 10 may also include a storage unit (not shown in Fig. 10), in which programs or instructions are stored.
  • a storage unit not shown in Fig. 10
  • the transceiver unit 1001 and the processing unit 1002 execute the program or instruction
  • the electronic device 1000 shown in FIG. 10 can perform the diabetes risk detection method described in the above method embodiment.
  • the technical solution provided by this application can also be a functional unit or chip in the electronic device, or a device used in conjunction with the electronic device.
  • An embodiment of the present application also provides a chip system, including: a processor, the processor is coupled to a memory, and the memory is used to store programs or instructions. When the program or instructions are executed by the processor, the The chip system implements the method in any of the above method embodiments.
  • processors in the chip system there may be one or more processors in the chip system.
  • the processor can be implemented in hardware or software.
  • the processor may be a logic circuit, an integrated circuit, or the like.
  • the processor may be a general-purpose processor implemented by reading software code stored in memory.
  • the memory may be integrated with the processor or may be provided separately from the processor, which is not limited by the embodiments of the present application.
  • the memory may be a non-transient processor, such as a read-only memory ROM, which may be integrated with the processor on the same chip, or may be separately provided on different chips.
  • the embodiments of this application vary on the type of memory, and The arrangement of the memory and processor is not specifically limited.
  • the chip system can be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or a system on chip (SoC). ), it can also be a central processor (central processor unit, CPU), a network processor (network processor, NP), a digital signal processing circuit (digital signal processor, DSP), or a microcontroller (micro controller unit, MCU), it can also be a programmable logic device (PLD) or other integrated chip.
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • SoC system on chip
  • CPU central processor unit, CPU
  • NP network processor
  • DSP digital signal processing circuit
  • microcontroller micro controller unit, MCU
  • PLD programmable logic device
  • each step in the above method embodiment can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software.
  • the method steps disclosed in conjunction with the embodiments of this application can be directly implemented by a hardware processor, or executed by a combination of hardware and software modules in the processor.
  • Embodiments of the present application also provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, When the computer program is run on the computer, the computer is caused to perform the above related steps to implement the diabetes risk detection method in the above embodiment.
  • An embodiment of the present application also provides a computer program product.
  • the computer program product When the computer program product is run on a computer, it causes the computer to perform the above related steps to implement the diabetes risk detection method in the above embodiment.
  • the embodiment of the present application also provides a device.
  • the device may specifically be a component or module, and the device may include one or more connected processors and memories. Among them, memory is used to store computer programs. When the computer program is executed by one or more processors, the device is caused to execute the diabetes risk detection method in each of the above method embodiments.
  • the devices, computer-readable storage media, computer program products or chips provided by the embodiments of the present application are all used to execute the corresponding methods provided above. Therefore, the beneficial effects it can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be described again here.
  • the steps of the methods or algorithms described in connection with the disclosure of the embodiments of this application can be implemented in hardware or by a processor executing software instructions.
  • Software instructions can be composed of corresponding software modules, and software modules can be stored in random access memory (RAM), flash memory, read only memory (read only memory, ROM), erasable programmable read-only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable read-only memory (EPROM, EEPROM), register, hard disk, removable hard disk, compact disc (CD-ROM) or any other form of storage media well known in the art.
  • An exemplary storage medium is coupled to the processor such that the processor can read information from the storage medium and write information to the storage medium.
  • the storage medium can also be an integral part of the processor.
  • the processor and storage medium may be located in an application specific integrated circuit (ASIC).
  • ASIC application specific integrated circuit
  • the disclosed method can be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of modules or units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored. or not executed.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, indirect coupling or communication connection of modules or units, and may be in electrical, mechanical or other forms.
  • each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit.
  • the above integrated units can be implemented in the form of hardware or software functional units.
  • Computer-readable storage media includes but is not limited to any of the following: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.
  • ROM read-only memory
  • RAM random access memory
  • magnetic disk or optical disk etc.
  • Various media that can store program code include but is not limited to any of the following: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Physics & Mathematics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Veterinary Medicine (AREA)
  • Psychiatry (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Dentistry (AREA)
  • Social Psychology (AREA)
  • Developmental Disabilities (AREA)
  • Educational Technology (AREA)
  • Hospice & Palliative Care (AREA)
  • Databases & Information Systems (AREA)
  • Psychology (AREA)
  • Child & Adolescent Psychology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physiology (AREA)
  • Data Mining & Analysis (AREA)
  • Optics & Photonics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种糖尿病风险检测方法、电子设备及系统，应用在终端技术领域，以解决现有技术中在采集PPG信号时间短的情况下，得到的糖尿病风险检测结果不准确的问题。其中，方法包括：获取第一数据和第二数据。其中，第一数据包括通过光电容积脉搏波描记法PPG传感器获取的PPG信号，第二数据包括以下一项或多项：饮食数据、运动数据、身体症状数据、药物使用数据、睡眠数据、情绪数据。根据第一数据和第二数据确定糖尿病风险检测结果，最后输出糖尿病风险检测结果，向用户提示健康状况。

Description

糖尿病风险检测方法、电子设备及系统
本申请要求于2022年7月30日提交国家知识产权局、申请号为202210911487.3、申请名称为“糖尿病风险检测方法、电子设备及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及终端技术领域，尤其涉及一种糖尿病风险检测方法、电子设备及系统。
背景技术
糖尿病的患病率呈快速升高趋势，糖尿病及其并发症的危害愈发严重，由此带来的医疗开支快速增长。因此，糖尿病风险检测的意义重大。传统的糖尿病风险检测主要依靠有创与微创设备采集血液和组织液样本进行血糖浓度分析。这种有创或微创的检测方式会给用户带来疼痛感，且需要专业的设备，较不方便。随着科学技术的进步，可采用可穿戴设备采集用户的生理数据实现无创糖尿病风险检测。现有技术提供的利用可穿戴设备进行无创糖尿病风险检测的方法，在采集生理数据(例如：光电容积脉搏波描记法(photoplethysmography，PPG)信号)的时间较短的情况下，得到的检测结果较不准确。
发明内容
为了解决上述的技术问题，本申请实施例提供了一种糖尿病风险检测方法、电子设备及系统。本申请实施例提供的技术方案，能够在采集PPG信号的时间较短的情况下，提高检测结果的准确性。
为了实现上述的技术目的，本申请实施例提供了如下技术方案：
第一方面，提供一种糖尿病风险检测方法，该方法包括：获取第一数据和第二数据，根据第一数据和第二数据确定糖尿病风险检测结果。之后，输出糖尿病风险检测结果。
其中，第一数据包括各种能够反映糖尿病特征，进而用于进行糖尿病风险检测的数据，例如：第一数据为通过PPG传感器获取的PPG信号。所述第二数据包括以下一项或多项：饮食数据、运动数据、身体症状数据、药物使用数据、睡眠数据、情绪数据。
示例性的，饮食数据包括以下一项或多项：进食时间、食物口味或成分以及饱腹感程度。运动数据包括以下一项或多项：运动时间、时长、运动强度、运动频率。睡眠数据包括以下一项或多项：睡眠时间段、睡眠时长、是否深度睡眠、深度睡眠时间段、深度睡眠时长。药物使用数据包括以下一项或多项：是否用药、药物类型、用药频率。情绪数据包括以下一项或多项：精神压力指数、情绪指数。
示例性的，所述第一数据可通过以下方式获取得到：电子设备通过内置传感器获取得到；或者，电子设备通过其他电子设备获取得到。
示例性的，所述第二数据可通过以下方式获取得到：电子设备与用户交互获取；例如：显示一个或多个界面，所述一个或多个界面中显示有需要用户提供的第二数据；接收用户在所述一个或多个界面中输入的第二数据。和/或，一个电子设备从其他电子设备获取得到；和/或，从已安装的应用程序和/或服务中获取得到。
可见，本申请实施例中，通过采集第二数据，根据该第二数据和第一数据综合分析，相当于利用第二数据对根据第一数据得到的糖尿病风险检测结果进行校准，得到校准后的糖尿病风险检测结果，提高了检测结果的准确性。
在一种可能的实现方式中，获取第一数据和第二数据可实现为：检测到用户的糖尿病风险检测的触发操作；响应于该触发操作，获取第一数据和第二数据。
也即，在该实现方式中，用户触发后再进行糖尿病风险检测。
在一种可能的实现方式中，所述根据第一数据和第二数据确定糖尿病风险检测结果，可实现为：根据第一数据确定第一风险值。根据第二数据和该第一风险值，得到第二风险值，该第二风险值可用于表示糖尿病风险检测结果。
可选的，根据第二数据调整第一风险值，得到第二风险值。
在一种可能的实现方式中，提供了一种根据第二数据和第一风险值，得到第二风险值的实现方式，也即根据第二数据和第一风险值，得到第二风险值，可实现为：根据不同的第二数据对应的权重和第一风险值，得到所述第二风险值。
可选的，根据不同的第二数据对应的权重，调整第一风险值，得到第二风险值。其中，一种或一项第二数据的权重用于表示该第二数据对检测结果的影响程度；某种或某项第二数据对检测结果的影响程度越大，对应的权重越大，相应的，对第一风险值的调整幅度越大。其中，该权重可预先设定。也即，根据不同第二数据对糖尿病的影响程度，调高或调低第一风险值。其中，某种或某项第二数据对糖尿病的影响程度较大，则对应的调整幅度较大。相应的，某种或某项第二数据对糖尿病的影响程度较小，则对应的调整幅度较小。
在一种可能的实现方式中，所述方法还包括：输出糖尿病风险检测结果的置信度。其中，该置信度用于表示所述糖尿病风险检测结果的准确度。
可选的，所述置信度根据以下至少一项或多项确定：获取的第一数据的时长、获取的第一数据在预设时间段内是否缺失、获取的第一数据的质量、获取的第二数据的种类、获取的第二数据的详细程度等。
采集的第一数据的时长越长、质量越高、采集的第二数据的种类越多、采集的第二数据越详细，则检测结果的置信度越高。
在一种可能的实现方式中，在得到置信度后，由于置信度和第二数据相关，因此还可提示用户该置信度与第二数据的关联关系，也即该置信度是在获取了哪些第二数据得到的。因此，所述方法还包括：提示用户糖尿病风险检测结果的置信度以及该置信度对应的第二数据。
在一种可能的实现方式中，在所述置信度低于预设阈值的情况下，提示用户编辑已获取的第二数据或输入更多的第二数据(本申请中，也可描述为第三数据)。
这样，通过不断的引导用户输入更多的第二数据，能够提高糖尿病风险检测结果的置信度。
在一种可能的实现方式中，获取第二数据，包括：获取预设时间段的第二数据。其中，所述预设时间段包括以下一个或多个时间段：第一数据缺失的时间段、午睡时间段、饮食时间段、夜间睡眠时间段。
这样，针对某些特定时间段，仅采集该特定时间段的第二数据，能够减少获取的第二数据的数据量，减轻用户的交互负担以及电子设备的处理负担。
在一种可能的实现方式中，第二数据包括多种第二数据。那么，所述获取第一数据和第二数据，根据所述第一数据和第二数据确定糖尿病风险检测结果，包括：
获取第一数据；按照不同第二数据的优先级的从高到低的顺序，获取第二数据；若根据已获取的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度等于或高于预设阈值，则停止获取第二数据。
若根据已获取的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度低于预设阈值，则继续获取第二数据，直至糖尿病风险检测结果的置信度等于或高于预设阈值。
其中，不同用户对应的不同项或种的第二数据的优先级不同或相同。
相比于用户需要一次性填写所有的第二数据而言，该方式能够减少用户填写的第二数据的数据量，减轻用户的交互负担。比如：假如身体症状数据、药物使用数据、饮食数据、运动数据分别位于不同的页面，相比于用户在这三种页面之间翻页，并且填写这三种页面的所有数据。采用这种按照优先级填写的方式，用户可能仅需填写身体症状数据、药物使用数据这一种类型的内容(也即一个页面的内容)，无需填写其他第二数据，减少用户的交互负担。
第二方面，提供一种电子设备。该电子设备包括：处理器和存储器，存储器与处理器耦合，存储器用于存储计算机可读指令，当处理器从存储器中读取计算机可读指令，使得电子设备执行如下操作：获取第一数据和第二数据，根据第一数据和第二数据确定糖尿病风险检测结果。之后，输出糖尿病风险检测结果。
在一种可能的实现方式中，获取第一数据和第二数据可实现为：检测到用户的糖尿病风险检测的触发操作；响应于该触发操作，获取第一数据和第二数据。
在一种可能的实现方式中，根据第一数据和第二数据确定糖尿病风险检测结果，可实现为：根 据第一数据确定第一风险值。根据第二数据调整该第一风险值，得到第二风险值，该第二风险值可用于表示糖尿病风险检测结果。
在一种可能的实现方式中，根据第二数据调整第一风险值，得到第二风险值，可实现为：根据不同的第二数据的权重调整第一风险值，得到所述第二风险值。
在一种可能的实现方式中，当处理器从存储器中读取计算机指令，还使得电子设备执行如下操作：输出糖尿病风险检测结果的置信度。其中，该置信度用于表示所述糖尿病风险检测结果的准确度。
在一种可能的实现方式中，所述置信度根据以下至少一项或多项确定：获取的第一数据的时长、获取的第一数据在预设时间段内是否缺失、获取的第一数据的质量、获取的第二数据的种类、获取的第二数据的详细程度。
在一种可能的实现方式中，当处理器从存储器中读取计算机指令，还使得电子设备执行如下操作：提示用户糖尿病风险检测结果的置信度以及该置信度对应的第二数据。
在一种可能的实现方式中，当处理器从存储器中读取计算机指令，还使得电子设备执行如下操作：在所述置信度低于预设阈值的情况下，提示用户编辑已获取的第二数据或输入第三数据。
在一种可能的实现方式中，获取第二数据，包括：获取预设时间段的第二数据。其中，所述预设时间段包括以下一个或多个时间段：第一数据缺失的时间段、午睡时间段、饮食时间段、夜间睡眠时间段。
在一种可能的实现方式中，第二数据包括多种第二数据。那么，所述获取第一数据和第二数据，根据所述第一数据和第二数据确定糖尿病风险检测结果，包括：
获取第一数据；按照不同第二数据的优先级，获取高优先级的第二数据；若根据高优先级的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度等于或高于预设阈值，则停止获取第二数据。
否则，若根据高优先级的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度低于预设阈值，则获取低优先级的第二数据并根据已获取的第二数据和第一数据确定糖尿病检测结果，直至糖尿病风险检测结果的置信度等于或高于预设阈值。
第二方面以及第二方面中任意一种实现方式所对应的技术效果，可参见上述第一方面及第一方面中任意一种实现方式所对应的技术效果，此处不再赘述。
第三方面，本申请实施例提供一种电子设备，该电子设备具有实现如上述第一方面及其中任一种可能的实现方式中所述的糖尿病风险检测方法的功能。该功能可以通过硬件实现，也可以通过硬件执行相应地软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。
第三方面以及第三方面中任意一种实现方式所对应的技术效果，可参见上述第一方面及第一方面中任意一种实现方式所对应的技术效果，此处不再赘述。
第四方面，提供一种计算机可读存储介质。计算机可读存储介质存储有计算机程序(也可称为指令或代码)，当该计算机程序被电子设备执行时，使得电子设备执行第一方面或第一方面中任意一种实施方式的方法。
第四方面以及第四方面中任意一种实现方式所对应的技术效果，可参见上述第一方面及第一方面中任意一种实现方式所对应的技术效果，此处不再赘述。
第五方面，本申请实施例提供一种计算机程序产品，当计算机程序产品在电子设备上运行时，使得电子设备执行第一方面或第一方面中任意一种实施方式的方法。
第五方面以及第五方面中任意一种实现方式所对应的技术效果，可参见上述第一方面及第一方面中任意一种实现方式所对应的技术效果，此处不再赘述。
第六方面，本申请实施例提供一种电路系统，电路系统包括处理电路，处理电路被配置为执行第一方面或第一方面中任意一种实施方式的方法。
第六方面以及第六方面中任意一种实现方式所对应的技术效果，可参见上述第一方面及第一方面中任意一种实现方式所对应的技术效果，此处不再赘述。
第七方面，本申请实施例提供一种芯片系统，包括至少一个处理器和至少一个接口电路，至少一个接口电路用于执行收发功能，并将指令发送给至少一个处理器，当至少一个处理器执行指令时， 至少一个处理器执行第一方面或第一方面中任意一种实施方式的方法。
第七方面以及第七方面中任意一种实现方式所对应的技术效果，可参见上述第一方面及第一方面中任意一种实现方式所对应的技术效果，此处不再赘述。
第八方面，本申请实施例提供一种糖尿病风险检测系统，该系统包括第一电子设备和第二电子设备，第一电子设备用于执行如第一方面或第一方面中任意一种实施方式的方法，所述第二电子设备用于获取第一数据和/或第二数据后发送给所述第一电子设备。
第八方面以及第八方面中任意一种实现方式所对应的技术效果，可参见上述第一方面及第一方面中任意一种实现方式所对应的技术效果，此处不再赘述。
附图说明
图1为本申请实施例提供的一种系统的结构示意图；
图2为本申请实施例提供的一种可穿戴设备的结构示意图；
图3为本申请实施例提供的另一种可穿戴设备的结构示意图；
图4A为本申请实施例提供的界面示意图一；
图4B为本申请实施例提供的界面示意图二；
图4C为本申请实施例提供的界面示意图三；
图4D为本申请实施例提供的界面示意图四；
图5为本申请实施例提供的预热期示意图；
图6A为本申请实施例提供的界面示意图五；
图6B为本申请实施例提供的界面示意图六；
图7为本申请实施例提供的界面示意图七；
图8为本申请实施例提供的界面示意图八；
图9为本申请实施例提供的系统的结构示意图二；
图10为本申请实施例提供的电子设备的结构示意图。
具体实施方式
下面结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。其中，在本申请实施例的描述中，以下实施例中所使用的术语只是为了描述特定实施例的目的，而并非旨在作为对本申请的限制。如在本申请的说明书和所附权利要求书中所使用的那样，单数表达形式“一个”、“一种”、“所述”、“上述”、“该”和“这一”旨在包括例如“一个或多个”这种表达形式，除非其上下文中明确地有相反指示。还应当理解，在本申请以下各实施例中，“至少一个”、“一个或多个”是指一个或两个以上(包含两个)。
在本说明书中描述的参考“一个实施例”或“一些实施例”等意味着在本申请的一个或多个实施例中包括结合该实施例描述的特定特征、结构或特点。由此，在本说明书中的不同之处出现的语句“在一个实施例中”、“在一些实施例中”、“在其他一些实施例中”、“在另外一些实施例中”等不是必然都参考相同的实施例，而是意味着“一个或多个但不是所有的实施例”，除非是以其他方式另外特别强调。术语“包括”、“包含”、“具有”及它们的变形都意味着“包括但不限于”，除非是以其他方式另外特别强调。术语“连接”包括直接连接和间接连接，除非另外说明。“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。
在本申请实施例中，“示例性地”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性地”或者“例如”的任何实施例或设计方案不应被解释为比其它实施例或设计方案更优选或更具优势。确切而言，使用“示例性地”或者“例如”等词旨在以具体方式呈现相关概念。
随着科学技术的进步，可采用可穿戴设备实现无创糖尿病风险检测。例如：研究发现，人体进行血糖调节和心脏搏动的生理机制存在许多共同点。因此，可通过光电容积脉搏波描记法(photoplethysmography，PPG)检测血容量变化的过程，进而反映血糖调节和心血管健康信息。基于该原理，在可穿戴设备(如可穿戴手表或手环)中内置PPG传感器，通过该传感器采集PPG信号， 根据该PPG信号提取与糖尿病有关的特征，进而检测用户患有糖尿病的风险。
在一种相关方案中，用户佩戴内置PPG传感器的可穿戴设备。可穿戴设备通过该PPG传感器捕获脉搏信号，对该脉搏信号进行预处理，得到脉搏信号对应的波形。检测该波形中的多个峰值，从中提取第一组特征参数。分别以无糖尿病用户、糖尿病前期或糖尿病状态的用户分别作为对照组，从各个对照组对应的脉搏信号的波形中分别提取第二组特征参数。将第一组特征参数与第二组特征参数进行比较。最终根据该比较结果，确定该用户是处于正常状态、糖尿病前期状态或糖尿病状态。
在另一种相关方案中，用户佩戴内置PPG传感器的可穿戴设备。可穿戴设备通过PPG传感器获取脉搏信号，对该脉搏信号进行频域分析、线性分析、非线性分析等得到脉搏信号中的脉率(pulse rate，PR)序列等信息，并进一步分析得到所需的脉搏信号特征指标。根据分析得到的脉搏信号特征指标以及预先建立的脉搏信号特征指标与糖尿病病情对应关系的模型函数得到糖尿病病情评估结果。
上述相关方案根据脉搏信号进行糖尿病风险检测，在脉搏信号质量差、采集时间短的情况下，得到的糖尿病风险的检测结果准确性较低。
为了提高检测结果的准确性，通常需要长时间的采集脉搏信号，进而在采集的脉搏信号数据足够多的情况下评估用户在这段时间的糖尿病风险水平。但这种长时间采集脉搏信号的方案，一方面采集脉搏信号的周期较长，在给出风险评估结果前，用户需等待较长时间，容易引起用户焦虑等。另一方面，通过该方案得到的检测结果反映的是用户在此段时间的平均糖尿病风险水平。实际生活中，用户可能还会关心短时间(如前一天或近几天)的糖尿病风险水平，该长时间采集脉搏信号的方案则无法满足用户的该需求。因此，虽然通过长时间采集脉搏信号的方案能提高糖尿病风险的检测结果的准确性，但该方案带来的用户体验较差。
为了改善已有相关方案存在的问题，本申请实施例提供了一种无创的糖尿病风险检测的方法，能够提高短时间采集用户的生理数据(如PPG信号)后得到的糖尿病风险的检测结果的准确性。
本申请实施例提供的糖尿病风险检测方法可应用在多个电子设备组成的系统中。该多个电子设备包括可穿戴设备和其他电子设备、多个可穿戴设备、其他多个电子设备等。本申请实施例不限定该系统中包含的电子设备的数量。
例如：如图1所示，该系统为可穿戴设备100和其他电子设备200组成的系统。
示例性的，可穿戴设备100例如可以是智能手表、智能手环、智能脚环、无线耳机、智能眼镜、智能头盔等终端设备。可穿戴设备安装的操作系统包括但不限于 或者其它操作系统。在一些实施例中，可穿戴设备可以为固定式设备，也可以为便携式设备。本申请对可穿戴设备的具体类型、所安装的操作系统均不作限制。
示例性的，其他电子设备200例如可以是手机(mobile phone)、个人计算机(personal computer，PC)、平板电脑(Pad)、笔记本电脑、台式电脑、笔记本电脑、带收发功能的电脑、可穿戴设备、车载设备、人工智能(artificial intelligence，AI)设备等终端设备。该其他电子设备安装的操作系统包括但不限于或者其它操作系统。在一些实施例中，该其他电子设备可以为固定式设备，也可以为便携式设备。本申请对其他电子设备的具体类型、所安装的操作系统也不作限制。
图1中以包含一个可穿戴设备和其他电子设备为例进行说明，实际应用中，可穿戴设备和/或其他电子设备的数量可以为多个。
在该系统中，可穿戴设备100可以通过有线通信技术和/或无线通信技术与其他电子设备200建立通信连接。其中，无线通信技术包括但不限于以下的至少一种：近距离无线通信(near field communication，NFC)，蓝牙(bluetooth，BT)(例如，传统蓝牙或者低功耗(bluetooth low energy，BLE)蓝牙)，无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，紫蜂(Zigbee)，调频(frequency modulation，FM)，红外(infrared，IR)等。
在一些实施例中，可穿戴设备100与其他电子设备200都支持靠近发现功能。示例性地，可穿戴设备靠近该其他电子设备后，可穿戴设备和该其他电子设备能够互相发现对方，之后建立诸如Wi-Fi端到端(peer to peer，P2P)连接、蓝牙连接等无线通信连接。在建立无线通信连接后，可穿戴设备与该其他电子设备可通过该无线通信连接实现信号交互。
在一些实施例中，可穿戴设备100与其他电子设备200通过局域网，建立无线通信连接。比如，可穿戴设备100与其他电子设备200都连接至同一路由器。
在一些实施例中，可穿戴设备100与其他电子设备200通过蜂窝网络、因特网等，建立无线通信连接。比如，其他电子设备200通过路由器接入因特网，可穿戴设备100通过蜂窝网络接入因特网；进而，可穿戴设备100与其他电子设备200建立无线通信连接。
在一些实施例中，可穿戴设备100和其他电子设备200协同获取用于进行糖尿病风险检测的第一数据和第二数据，进而根据该第一数据和第二数据进行综合分析，得到用户的糖尿病风险的检测结果。本申请实施例不限定具体哪个设备获取哪些数据，也不限定由哪个设备将获取的数据进行综合分析。
比如，可穿戴设备100获取用于进行糖尿病风险检测的第一数据；其他电子设备200获取第二数据，该第二数据包括以下至少一项：用户的基本信息，如年龄、性别、身高、体重等，运动数据、睡眠数据、情绪数据、身体症状数据、药物使用数据等。第二数据的具体解释详见后文。可穿戴设备100将获取的第一数据发送给其他电子设备200，其他电子设备200根据该第一数据和第二数据进行综合分析，得到用户的糖尿病风险的检测结果。
又如，可穿戴设备100获取用于进行糖尿病风险检测的第一数据；其他电子设备200获取第二数据，该第二数据见前文所述。其他电子设备200将其获取的第二数据发送给可穿戴设备100，可穿戴设备100根据该第一数据和第二数据进行综合分析，得到用户的糖尿病风险的检测结果。
再如，可穿戴设备100获取用于进行糖尿病风险检测的第一数据，其他电子设备200获取部分第二数据，如用户的基本信息、身体症状数据、药物使用数据等。可穿戴设备获取部分第二数据，如运动数据、睡眠数据等。然后可穿戴设备将获取的第一数据和第二数据发送给其他电子设备200，由其他电子设备200将从可穿戴设备获取的第一数据和第二数据以及自身获取的第二数据进行综合分析，得到用户的糖尿病风险的检测结果。
再如，可穿戴设备100获取用于进行糖尿病风险检测的第一数据，其他电子设备200获取部分第二数据，如用户的基本信息、身体症状数据、药物使用数据等。可穿戴设备获取部分第二数据，如运动数据、睡眠数据等。然后其他电子设备200将获取的第二数据发送给可穿戴设备100，由可穿戴设备100将自身获取的第一数据和第二数据以及从其他电子设备200获取的第二数据进行综合分析，得到用户的糖尿病风险的检测结果。
示例性的，图2示出了可穿戴设备100的结构示意图。
可穿戴设备100可以包括处理器110，存储器120，通用串行总线(universal serial bus，USB)接口130，充电管理模块140，电源管理模块141，电池142，天线1，天线2，移动通信模块150，无线通信模块160，音频模块170，传感器模块180，按键190，马达191，指示器192，摄像头193，显示屏194等。其中传感器模块180可以包括光电容积脉搏波传感器180A，加速度(acceleration，ACC)传感器180B，温度传感器180C，触摸传感器180D等。
处理器110可以包括一个或多个处理单元，例如：处理器110可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器(graphics processing unit，GPU)，图像信号处理器(image signal processor，ISP)，控制器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。
控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器110中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器110中的存储器为高速缓冲存储器。该存储器可以保存处理器110刚用过或循环使用的指令或数据。如果处理器110需要再次使用该指令或数据，可从所述存储器中直接调用。避免了重复存取，减少了处理器110的等待时间，因而提高了系统的效率。
在一些实施例中，处理器110可以包括一个或多个接口，如USB接口130等。其中USB接口130可以是符合USB标准规范的接口，具体可以是Mini USB接口，Micro USB接口，USB type C接口等。USB接口130可以用于连接充电器为可穿戴设备100充电，也可以用于可穿戴设备100与外围设备之间传输数据。也可以用于连接耳机，通过耳机播放音频。该接口还可以用于连接其他设备，例如增 强现实(augmented reality，AR)设备等。
充电管理模块140用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。
电源管理模块141用于连接电池142，充电管理模块140与处理器110。电源管理模块141接收电池142和/或充电管理模块140的输入，为处理器110，存储器120，显示屏194，摄像头193，和无线通信模块160等供电。
可穿戴设备100的无线通信功能可以通过天线1，天线2，移动通信模块150，无线通信模块160等实现。
天线1和天线2用于发射和接收电磁波信号。可穿戴设备100中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用，以提高天线的利用率。例如：可以将天线1复用为无线局域网的分集天线。在另外一些实施例中，天线可以和调谐开关结合使用。
移动通信模块150可以提供应用在可穿戴设备100上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块150可以包括至少一个滤波器，开关，功率放大器，低噪声放大器(low noise amplifier，LNA)等。
无线通信模块160可以提供应用在可穿戴设备100上的包括无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，蓝牙(bluetooth，BT)，全球导航卫星系统(global navigation satellite system，GNSS)，调频(frequency modulation，FM)，近距离无线通信技术(near field communication，NFC)，红外技术(infrared，IR)等无线通信的解决方案。
在一些实施例中，可穿戴设备100的天线1和移动通信模块150耦合，天线2和无线通信模块160耦合，使得可穿戴设备100可以通过无线通信技术与网络以及其他设备通信。
可穿戴设备100通过GPU，显示屏194，以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏194和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器110可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。
显示屏194用于显示图像，视频等。显示屏194包括显示面板。显示面板可以采用液晶显示屏(liquid crystal display，LCD)，例如采用有机发光二极管(organic light-emitting diode，OLED)，有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrix organic light emitting diode，AMOLED)，柔性发光二极管(flex light-emitting diode，FLED)，Mini-led，Micro-led，Micro-oled，量子点发光二极管(quantum dot light emitting diodes，QLED)等生产制造。在一些实施例中，可穿戴设备100可以包括1个或N个显示屏194，N为大于1的正整数。
摄像头193用于捕获静态图像或视频。在一些实施例中，可穿戴设备100可以包括1个或N个摄像头193，N为大于1的正整数。
存储器120可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。存储器120可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储可穿戴设备100使用过程中所创建的数据(比如第一数据、第二数据)等。此外，存储器120可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。处理器110通过运行存储在存储器120的指令，和/或存储在设置于处理器中的存储器的指令，执行可穿戴设备100的各种功能应用以及数据处理。
可穿戴设备100可以通过音频模块170以及应用处理器等实现音频功能。例如音乐播放，录音等。
音频模块170用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转换为数字音频信号。音频模块170还可以用于对音频信号编码和解码。在一些实施例中，音频模块170可以设置于处理器110中，或将音频模块170的部分功能模块设置于处理器110中。可穿戴设备100可以通过音频模块170，例如音乐播放，录音等。音频模块170可以包括扬声器，受话器，麦克风，以及应用处理器等实现音频功能。
光电容积脉搏波传感器180A，可以通过光电容积脉搏波描记法(photoplethysmography，PPG)， 以发光二极管(light emitting diode，LED)光源和探测器为基础，通过测量经过人体血管和组织反射、吸收后的衰减光，获得PPG信号。光电容积脉搏波描记法的原理为：当光照透过皮肤组织然后再反射到光敏传感器时光照会有一定的衰减。在用户未进行大幅度运动的前提下，肌肉、骨骼、静脉和其他连接组织等对光的吸收是基本不变的，但是血液不同，由于动脉里有血液的流动，那么对光的吸收自然也有所变化。当把光转换成电信号时，正是由于动脉对光的吸收有变化而其他组织对光的吸收基本不变，得到的信号就可以分为直流(direct current，DC)信号和交流(alternating current，AC)信号。通过对提取的AC信号进行分析，能够得到血液流动的特点。可穿戴设备100通过光电容积脉搏传感器180A采集PPG信号进行分析，可以获得用户的生理数据，例如：心率、呼吸率、血氧等。在本申请的一些实施例中，通过分析PPG信号提取与糖尿病相关的特征，检测用户的糖尿病患病风险。
加速度传感器180B可检测可穿戴设备100在各个方向上(一般为三轴)加速度的大小。当可穿戴设备100静止时可检测出重力的大小及方向。还可以用于识别可穿戴设备姿态，应用于横竖屏切换，计步器等应用。在本申请的一些实施例中，加速度传感器180B测量加速度信号，其中，加速度信号可用于确定用户的状态，比如：静止状态、运动状态等。由于用户在不同状态下，生理数据(比如：呼吸率、心率、血氧、血糖等)可能有所差别。因此，为提高获得的用户的生理数据的准确性，可穿戴设备100还可以通过加速度传感器180B采集的加速度信号确定用户的状态。
温度传感器180C用于检测温度。在一些实施例中，可穿戴设备100利用温度传感器180C检测的温度，执行温度处理策略。例如，当温度传感器180C上报的温度超过阈值，可穿戴设备100执行降低位于温度传感器180C附近的处理器的性能，以便降低功耗实施热保护。在另一些实施例中，当温度低于另一阈值时，可穿戴设备100对电池142加热，以避免低温导致可穿戴设备100异常关机。在其他一些实施例中，当温度低于又一阈值时，可穿戴设备100对电池142的输出电压执行升压，以避免低温导致的异常关机。
触摸传感器180D，也称“触控器件”。触摸传感器180D可以设置于显示屏194，由触摸传感器180D与显示屏194组成触摸屏，也称“触控屏”。触摸传感器180D用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作传递给应用处理器，以确定触摸事件类型。可以通过显示屏194提供与触摸操作相关的视觉输出。在另一些实施例中，触摸传感器180D也可以设置于可穿戴设备100的表面，与显示屏194所处的位置不同。
可选的，传感器模块180还可以包括压力传感器，气压传感器，磁传感器，距离传感器，接近光传感器，陀螺仪传感器、指纹传感器，环境光传感器，骨传导传感器等。
按键190包括开机键，音量键等。按键190可以是机械按键。也可以是触摸式按键。可穿戴设备100可以接收按键输入，产生与可穿戴设备100的用户设置以及功能控制有关的键信号输入。
马达191可以产生振动提示。马达191可以用于来电振动提示，也可以用于触摸振动反馈。
指示器192可以是指示灯，可以用于指示充电状态，电量变化，也可以用于指示消息，未接来电，通知等。
可以理解，上述仅是举例说明本申请实施例中可穿戴设备的结构的，并不构成对可穿戴设备结构、形态的限制。本申请实施例对可穿戴设备的结构、形态不做限制。示例性的，图3示出了可穿戴设备的另一种示例性结构。如图3所示，可穿戴设备包括：处理器201、存储器202、收发器203。处理器201、存储器202的实现可参见前文所述处理器、存储器的实现。收发器203，用于可穿戴设备与其他设备(比如手机)交互。收发器203可以是基于诸如Wi-Fi、蓝牙或其他通信协议的器件。
在本申请另一些实施例中，可穿戴设备可以包括比图2、图3所示的更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者替换某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
可选的，关于电子设备200的结构可参考可穿戴设备100的结构，电子设备200可以具有比可穿戴设备100更多或者更少的结构，本申请对此不作具体限制。
本申请实施例提供的糖尿病风险检测的方法还可应用在其他任意能够获取用于进行糖尿病风险检测的第一数据以及第二数据的电子设备，如具备图2或图3所示结构的任意装置中，例如：手机、可穿戴设备中等。
本申请实施例提供一种无创的糖尿病风险检测方法，该方法通过获取用于进行糖尿病风险检测的第一数据以及第二数据，例如：用户的基本信息(如年龄、性别、身高、体重等)、饮食、运动、健康、睡眠等数据。根据该第二数据以及用于进行糖尿病风险检测的第一数据综合分析，能够在短时间内得到糖尿病风险检测结果。该检测结果为利用第二数据对用于进行糖尿病风险检测的第一数据得到的结果进行了校准，能够提高短时间检测结果的准确性。
本申请实施例中，第一数据包括各种能够反映糖尿病特征，进而用于进行糖尿病风险检测的数据。可选的，有些可穿戴设备内置PPG传感器，通过PPG传感器获取PPG信号(该PPG信号可以为根据脉搏信号、按压手指得到的信号等分析得到)并分析PPG信号提取与糖尿病相关的特征检测糖尿病风险。因此，该第一数据可以为PPG信号。可选的，有些可穿戴设备可内置眼内，通过分析佩戴者泪液中的葡萄糖含量来监测其血糖水平。因此，该第一数据可以为血糖值。可选的，有些可穿戴设备可佩戴在手指，通过给予手指压力会暂时堵塞血流，形成新的血液动力，从而产生独特的光信号，通过分析这些信号即可检测糖尿病风险。因此，该第一数据还可以为该光信号。总之，本申请实施例不限定第一数据的类型。
本申请实施例中，第二数据用于反映用户的生活信息，可以覆盖用户生活的各个方面。可选的，第二数据包括以下至少一项：基本信息、饮食、运动、身体症状、药物使用情况、睡眠等数据。用户的基本信息包括用户的年龄、性别、身高、体重等。用户的饮食数据包括用户进食时间、食物口味或成分以及饱腹感程度等。用户的运动数据包括用户运动时间、时长、运动强度、运动频率等。用户的睡眠数据包括用户的睡眠时间段、睡眠时长、是否深度睡眠、深度睡眠时间段、深度睡眠时长等。身体症状数据包括用户是否出现与糖尿病相关的身体症状，如三高一减等。用户的药物使用数据包括是否用药、药物类型、用药频率等。本申请实施例以及附图的有些描述中，将身体症状数据和药物使用数据描述为健康数据。第二数据还可以包括精神压力指数、情绪指数等，用于表示用户最近的精神压力大小、情绪是否良好等。
下文以本申请实施例提供的方法应用在可穿戴设备和手机组成的系统中为例进行说明。
在本申请的一些实施例中，手机接收用户进行糖尿病风险检测的触发操作。响应于该触发操作，手机获取第二数据，以及手机通过可穿戴设备获取第一数据。之后，手机根据该第一数据和第二数据检测用户患有糖尿病的风险，得到糖尿病风险检测结果。
其中，如前文所述，第一数据包括任意能够反映糖尿病特征，进而用于糖尿病风险检测的数据。第二数据包括以下至少一项：用户的基本信息、饮食、运动、健康、睡眠等数据。
其中，用户进行糖尿病风险检测的触发操作用于触发手机开启糖尿病风险检测功能。可选的，手机通过应用程序，例如“运动健康”这一应用为用户提供用于开启糖尿病风险检测功能的入口。又如，手机通过“小程序”为用户提供该功能的入口等。再如，手机通过服务卡片的推荐服务为用户提供该功能的入口等。那么，用户进行糖尿病风险检测的触发操作可以为在应用程序或小程序或服务卡片中的点击、滑动等一系列操作。可选的，该触发操作还可以为用户的某些快捷操作，例如通过手势或者按键的组合等方式的快捷操作。该触发操作还可以为用户的输入的语音命令，如调用语音助手开启糖尿病风险检测功能等。本申请实施例不限定该触发操作的具体实现形式。
示例性的，如图4A所示，手机的主页界面400中安装有“运动健康”这一应用401。用户点击该应用的图标，则手机显示如图4A所示的界面402。该界面402中显示该应用能够提供的所有功能模块的图标，如健康管理、智能减脂、心率测量、睡眠监测、糖尿病风险检测等功能模块的图标。用户点击该应用中的“糖尿病风险检测”这一功能模块的图标403，则手机跳转到如图4B所示的界面404，在该界面404中显示该模块提供的具体功能，例如：“长时检测”和“短时检测”这两种功能。
其中，“长时检测”和“短时检测”是根据糖尿病风险检测时所采集的第一数据的时间长度进行区分。“长时检测”所采集的第一数据的时间较长，通常为5天-7天；“短时检测”所采集的第一数据的时间较短，通常为1-2天。相应的，“长时检测”对应的检测结果比“短时检测”对应的检测结果的准确性更高，而用户等待结果的时间也较长。其中，上述5-7天和1-2天仅为示例性说明，意在区分长时检测和短时检测所需要采集的第一数据的时间长度，其具体时长根据电子设备的实际功能确定。可选的，在该界面404中为用户提供这两种功能的说明，以便于用户选择符合其需 求的检测功能。无论用户选择“短时检测”还是“长时检测”这一功能，相当于用户执行了糖尿病风险检测的触发操作。可选的，在其他可能的实现方式中，“糖尿病风险检测”这一功能模块提供的功能不区分“短时检测”还是“长时检测”功能，也即该模块可能仅提供一种默认的检测功能。只要手机检测到用户触发了该功能，则手机获取用于糖尿病风险检测的第一数据以及第二数据。
本申请实施例的方法既可应用在短时检测也可应用在长时检测的场景下，提高检测结果的准确性。下文以用户选择“短时检测”这一功能为例进行说明。
示例性的，如图4B所示，手机检测到用户选择该“短时检测”功能的操作405后，则获取用于糖尿病风险检测的第一数据以及第二数据。
可选的，手机可通过与用户交互的方式获取第二数据。示例性的，手机显示如图4B中所示的提示界面406。在该提示界面406中，手机显示用于采集第二数据的提示信息。例如：显示如下提示字样“即将为您进行短时糖尿病风险检测，该检测结果将在1-2天内提供给您；为了提高检测结果的准确性，需要您提供相关用户数据。您是否提供用户数据？”和对应的用于用户选择是否提供用户数据的选择控件“是”和“否”。
如果用户在提示界面406中选择“是”，则手机显示如图4B中界面407，在该界面407中，显示有需要用户提供的第二数据。该第二数据能够反映用户的日常生活习惯。第二数据的内容可以覆盖用户日常生活习惯的各个方面，用户所能提供的第二数据的类型越多，内容越详尽，越有助于提高检测结果的准确性。
示例性的，界面407中显示有用户需要提供的个人信息、运动、健康、饮食等相关第二数据。其中，个人信息具体包括用户的性别、年龄、身高、体重等。运动数据包括用户的运动时间段、运动时长、运动项目、运动频率(比如预设时间段内的运动次数，如一周三次、一月两次等)。身体症状数据、药物使用数据等。饮食数据包括用户最近的饮食类型(如清淡、油腻、偏甜)以及饱腹感程度(饱腹感程度是指用户进食后，是否感觉饥饿或者是否饱的程度，如五分饱、八分饱、十分饱)。可以理解的是，界面407中仅仅示例性的给出了一些需要用户提供的第二数据，实际设计中，可以包含更多或更少的需要用户提供的第二数据。
在一种可能的实现方式中，用户需要填写的所有第二数据都显示在同一个页面中，但由于用户需要填写的第二数据较多，当前页面无法完整的展示所有第二数据，则用户可通过滚动该页面以显示完整的第二数据。在一种可能的实现方式中，将用户需要填写的所有第二数据在不同的页面分别显示，例如：分别将用户的个人信息、运动、健康、饮食数据显示在四个不同的页面。用户可通过翻页或者点击页面下方的提示信息，如“下一步”的方式跳转到下一页面。如果用户不想提供某些第二数据，则可不填写相应的数据或者点击“跳过”。示例性的，用户填写完毕后，可点击“提交”等按钮向手机提交已填写的用户数据(图中未示出用户完成填写第二数据之后提交第二数据的显示界面)。在其他可能的实现方式中，手机与用户之间通过语音交互获取第二数据。总之，本申请实施例不限定手机在获取第二数据时与用户的交互方式。
可选的，手机还可通过其他方式获取第二数据，例如在获得用户授权的前提下，通过可穿戴设备或者用户在其他应用中已经录入的数据等方式获取第二数据。例如：在上述提示界面406中，用户选择“是”之后，手机显示提示界面，该提示界面可包含以下内容：“将通过可穿戴设备获取您的运动数据”以及对应的控件“同意”和“不同意”。和/或，“将通过运动健康这一应用中的睡眠检测模块获取您的睡眠数据”以及对应的控件“同意”和“不同意”。和/或，“将通过运动健康这一应用中的饮食管理模块获取您的饮食数据”以及对应的控件“同意”和“不同意”。和/或，“将通过运动健康中的健康管理模块获取您的健康信息”以及对应的控件“同意”和“不同意”。用户可分别针对每项第二数据对应的提示信息，选择同意或者不同意；对于某项第二数据对应的提示信息，如果用户选择“同意”，则手机可从对应的应用或模块中获得相应的第二数据。如果用户选择“不同意”，则手机可进一步显示类似于界面407的提示界面，提示用户输入对应的第二数据。
其中，手机可通过一个或多个可穿戴设备分别获取不同的第二数据，手机与可穿戴设备建立连接并通过可穿戴设备获取运动数据、心率数据等数据的方式可参考现有技术，本申请不再赘述。
此外，用户还可根据实际情况输入其想要输入的其他补充性的第二数据，手机可通过识别其中的关键词等方式获取到用户补充的第二数据。
总之，本申请实施例中，只要手机能够获取到第二数据即可，不限定手机获取第二数据的具体实现方式。
手机获取第二数据之后，如图4C中的界面408所示，提示用户手机将进一步从可穿戴设备(图中以智能手表为例)中获取第一数据(图中以PPG信号为例)。在用户授权后，如图4C中的界面409所示，提示用户可穿戴设备的相关信息，用户可通过点击“开始获取PPG信号”指示手机通过智能手表获取PPG信号。
可选的，上述图中的示例以手机先获取第二数据，然后再获取第一数据为例进行说明。实际应用中，手机也可先获取第一数据再获取第二数据，或者，同时获取第一数据和第二数据。相应的，为可穿戴设备和手机设计与这种数据获取方式对应的用户界面。例如：在其他可能的实现方式中，用户在界面404中点击“短时检测”后，一方面手机通过可穿戴设备获取第一数据(该过程可以手机的内部操作，也即用户不可见)，一方面显示如界面406所示的界面。本申请实施例不限定手机获取第二数据和第一数据的顺序。
之后，手机将获取到的第二数据和通过可穿戴设备获取的第一数据进行分析，得到用户的糖尿病风险检测结果。以可穿戴设备为智能手表为例，智能手表中可内置PPG传感器，通过该传感器获取到脉搏信号并对该脉搏信号进行分析得到PPG信号。智能手表将该PPG信号发送给手机。手机根据该PPG信号和获取的第二数据得到糖尿病风险检测结果。
可选的，手机先根据第一数据(PPG信号)得到初步的糖尿病风险值(为便于描述，本申请将该初步的糖尿病风险值描述为第一风险值)，然后根据获取到的第二数据和该第一风险值，得到最终的糖尿病风险值(为便于描述，本申请将该最终的糖尿病风险值描述为第二风险值)，将该第二风险值作为最终的糖尿病风险的检测结果。
可选的，根据第二数据调整第一风险值，得到第二风险值。
在一种可能的实现方式中，根据不同的第二数据对应的权重和第一风险值，得到第二风险值。例如：根据不同第二数据对应的权重调整第一风险值，得到第二风险值。其中，一项或一种第二数据对应的权重用于表示该项第二数据对检测结果的影响程度；某项或某种第二数据对检测结果的影响程度越大，对应的权重越大，相应的，对第一风险值的调整幅度越大。其中，该权重可预先设定。也即，根据不同第二数据对糖尿病的影响程度，调高或调低第一风险值。其中，某项或某种第二数据对糖尿病的影响程度较大，则对应的调整幅度较大。相应的，某项或某种第二数据对糖尿病的影响程度较小，则对应的调整幅度较小。示例性的，根据用户患有糖尿病的风险大小，设定不同风险的糖尿病对应的第一风险值。用户患有糖尿病的风险越大，则对应的第一风险值越大。比如：设定尚未患有糖尿病(健康用户)，其对应的第一风险值为60分以下；糖尿病前期，其对应的第一风险值为60-80分；糖尿病，其对应的第一风险值为80-100分。如果手机根据PPG信号得到的第一风险值为65分，手机分析用户的基本信息，确定该用户的体重为65kg、158cm，则用户体重偏重，由于体重对糖尿病的影响轻微，那么可轻微上调该第一风险值，比如上调3分，调整为68分；进一步的，手机分析用户的饮食数据，确定用户近期经常食用偏甜的食物，则由于饮食习惯相较于体重对糖尿病的影响较大，则进一步微调该第一风险值，比如上调5分，调整为73分。进一步的，手机分析用户的运动数据，确定用户规律锻炼，则由于运动有助于降低糖尿病风险，则降低3分，调整为70分。进一步的，手机分析用户的身体症状数据、药物使用数据，确定用户的用药以及当前出现的身体症状等，如果出现与糖尿病关联较大的症状，则由于该身体症状数据、药物使用数据对糖尿病影响较大，则上调8分，调整为78分。进一步的，手机还可分析其他能够获取到的第二数据，例如睡眠、是否有较大的精神压力、情绪是否良好等数据，并依次调整分值，得到第二风险值。将该第二风险值作为最终的糖尿病风险检测结果。可以理解的是，除了通过分析不同的第二数据对糖尿病风险的影响，进而在第一风险值的基础上依次调整该风险值外；还可以通过分析不同第二数据对糖尿病风险的影响，得到总的调整值，进而在第一风险值的基础上按照该总的调整值进行调整，得到第二风险值。
在另一种可能的实现方式中，不同的第一数据对应的调整幅度都相同，也即可以不对第一数据设置权重。或者，不同的第一数据有对应的预设调整值，按照该预设调整值调整即可，不同的第一数据对应的预设调整值可相同也可不同。
如果用户在提示界面406中选择“否”，则表示用户不希望提供第二数据，则手机仅根据从可穿戴设备获取到的第一数据得出糖尿病风险检测结果，也即将第一风险值作为糖尿病风险检测结果。
之后，手机输出糖尿病风险检测结果。通常，手机在显示界面中显示糖尿病风险检测结果。手机还可以语音播报等其他方式输出该检测结果。以手机在显示界面中显示糖尿病风险检测结果为例，在一种可能的实现方式中，如果手机能够获取到第二数据，则该检测结果为根据第二数据和第一数据综合分析得到的，那么手机直接显示第二风险值作为糖尿病风险检测结果。如果无法获取到第二数据，则检测结果为根据第一数据分析得到的，那么手机直接显示第一风险值作为糖尿病风险检测结果。在另一种可能的实现方式中，根据糖尿病风险值得到一个粗略的糖尿病风险评估结果。例如：糖尿病风险值为60分以下，则对应的评估结果为“评估结果良好，糖尿病风险低”；糖尿病风险值为60分-80分，则对应的评估结果为“评估结果一般，您当前可能处于糖尿病前期，具备糖尿病患病风险”；糖尿病风险值为80-100分，则对应的评估结果为“评估结果较差，具备极重的糖尿病患病风险”。手机显示该粗略的糖尿病风险评估结果。示例性的，如图4D中的界面410所示，在该界面中显示有“评估结果良好，糖尿病患病风险低”这一评估结果。
可选的，不论是以哪种方式输出该糖尿病风险检测结果，手机还可输出该检测结果对应的说明以及健康建议。例如：对于评估结果为“评估结果良好，糖尿病患病风险低”这一结果而言，其对应的说明可以为“根据可穿戴设备获取的PPG信号以及用户数据，将评估结果分为良好、一般和较差，您当前的评估结果良好，表明血糖浓度维持在良好水平”。示例性的，如界面410中所示，该评估结果对应的健康建议可以为：近日血糖健康状态良好，建议保持低糖低脂饮食，适度增加运动等。
可选的，如果“糖尿病风险检测”模块提供“短时检测”和“长时检测”两种功能，则可既输出短时检测结果，又输出长时检测结果。
例如，在同一界面既显示短时检测结果也显示长时检测结果。由于长时检测结果需要采集更多时间的第二数据，因此，在显示界面中可能出现的情况为：出现了短时检测结果，但长时检测结果仍处于预热期，尚无结果输出。示例性的，如图4D中的界面410所示，在该界面中显示有“短时检测结果：评估结果良好，糖尿病患病风险低”以及显示有“长时检测结果：当前处于预热期，尚无检测结果”。
其中，所述预热期可以理解为等待长时检测结果的时间段，或者说从开始采集第一数据至得到长时检测结果之间的时间段。
如果采集了较长时间的第一数据，那显示界面可能出现的情况为：既有短时检测结果，又有长时检测结果。示例性的，如图4D中的界面411所示，在该界面中显示有短时检测结果：评估结果良好，糖尿病患病风险低，以及显示有以图像表达的长时检测结果。
如前文所述，已有的糖尿病风险检测方案在“短时检测”时由于采集的第一数据不够充分，仅仅根据该第一数据得到的检测结果的准确性较低。而本申请实施例中，通过采集第二数据，根据该第二数据和第一数据综合分析，相当于利用第二数据对根据第一数据得到的糖尿病风险检测结果进行校准，得到校准后的糖尿病风险检测结果，提高了检测结果的准确性。
此外，与“长时检测”相比，本申请实施例提供的方案能够在更短的时间内快速给出糖尿病风险的检测结果，缓解用户等待过程中的焦虑，此外该检测结果能够反映用户短时间内存在的糖尿病风险情况，满足用户的需求，提高用户体验。
例如：如图5所示，T1为开始采集第一数据的时刻，T2为通过较长时间的采集第一数据得到长时风险检测结果的时刻。T1至T2之间为预热期。如果采用“长时检测”，则用户需要等到T2时刻才能得到长时检测的结果，而采用“短时检测”，则用户在T1至T2之间的某个时刻便可得到短时检测的结果，且该检测结果由于是根据第二数据进行了校准，其准确性较高。
可选的，本申请实施例中，手机还可根据采集的第二数据和第一数据确定该检测结果的置信度，也即检测结果的可信度或者说准确度。采集的第一数据的时长、采集的第一数据的质量、采集的第二数据的种类、采集的第二数据的详细程度等影响检测结果的置信度。其中，采集的第一数据的质量可通过确定第一数据是否有缺失、用户的状态等得到。例如：如果未采集到用户三餐、午睡等重要时间的第一数据，则该第一数据的质量较差。又如：第一数据可能受用户的运动状态影响，如果 在用户进行剧烈活动时采集第一数据，则该第一数据的质量较差。
采集的第一数据的时长越长、质量越高、采集的第二数据的种类越多、采集的第二数据越详细，则检测结果的置信度越高。换句话说，在采集同样的第一数据的情况下，手机能够获得的第二数据种类越多，越详细，其对应的检测结果的置信度越高。
例如：对于同一个用户，如果想检测其近三天的糖尿病风险，如果能获取到的第一数据包括其近三天的PPG信号，且获取到的第二数据仅包括该用户的基本信息以及饮食数据，其得到的检测结果为第一检测结果。如果能获取到的第一数据包括其近三天的PPG信号，且获取到的第二数据包括该用户的基本信息、饮食数据、身体症状数据、药物使用数据以及运动数据，其得到的检测结果为第二检测结果。那么，第二检测结果的置信度高于第一检测结果的置信度。
可选的，手机不仅输出检测结果，还要输出该检测结果的置信度。示例性的，如图6A所示的界面601和图6B所示的界面602，该界面601和界面602中显示有糖尿病风险检测结果以及该检测结果对应的置信度。置信度一般通过概率表示，本申请实施例中计算出概率值后，根据该概率值的取值得到其位于的区间范围，不同的区间范围对应一个粗略的高低情况，然后将置信度显示为该粗略的高低情况。例如：概率值低于60％对应的置信度为较低、概率值位于60％-75％之间为低，概率值位于75％-90％之间为较高，概率值位于90％以上为高。可选的，置信度还可以概率值的形式在界面中显示。
此外，手机还可提示用户置信度和第二数据之间的影响关系，也即提示用户所述糖尿病风险检测结果的置信度以及该置信度对应的第二数据。如界面601所示，如果用户点击置信度，则可进一步显示该置信度对应的所能获取到的第二数据，包括饮食数据、运动数据、身体症状数据、药物使用数据(其中身体症状数据、药物使用数据又包括药物使用数据和身体症状数据)、睡眠数据以及情绪类数据(如精神压力较大)。如界面602所示，如果用户点击置信度，则显示该置信度对应的所获取到的第二数据，仅包括运动数据，不包括其他数据。可见，界面602中所示的置信度要低于界面601中所示的置信度的原因在于，其获取的第二数据较少。
可选的，在所述置信度低于预设阈值的情况下，提示用户编辑已获取的第二数据或输入更多的第二数据(本申请中也可将该需要用户输入更多的第二数据描述为第三数据)。也即对于置信度较低的检测结果，手机还可进一步提示用户完善已获取的第二数据或输入更多的第二数据以提高检测结果的置信度。例如：手机可语音播出或显示如下字样：“当前检测结果的置信度较低，为了提高检测结果的准确性，请您进一步提供用户数据，在您提供更多的用户数据后，将为您再次输出检测结果。”这样，通过不断的引导用户输入更多的第二数据，提高检测结果的置信度。
在上文所述的方案中，手机所获取的第二数据为用户在一段时间内的所有的可能的第二数据。通常，获取第二数据的过程需要与用户交互，则会给用户带来一定的“交互负担”。此外，手机根据较多的第二数据确定检测结果，其采集量和计算量均较大。
为了减少获取的第二数据的数据量，减轻用户的交互负担以及手机的处理负担。可选的，在本申请的一些实施例中，可针对某些特定时间段，仅采集该特定时间段的第二数据。
可选的，在本申请的一些实施例中，确定采集到的第一数据的质量差或数据缺失时段，仅采集该时段的第二数据。通过采集一段时间的第一数据，对该段时间的第一数据进行统计分析，从中识别出第一数据的质量差或数据缺失的时间段。
例如：通过采集用户在一个月内的脉搏信号，根据该脉搏信号的波形、峰值等特征检测出脉搏信号质量差或数据缺失的时间段。比如，该时间段通常为用户午睡时间段，则在获取第二数据时，手机仅获取用户在该午睡时间段的第二数据。
示例性的，如图7所示，获取的用户在午睡时间段的第二数据包括用户的午餐的饱腹感程度(如无进食、三分饱、五分饱、八分饱、十分饱、十二分饱等)、午餐类型(如清淡、油腻、偏甜等)以及运动数据(如运动强度为低强度、中强度、极强强度等)。
可以理解的是，图7中所示的午睡时间段的第二数据仅为示例性说明，午睡时间段的第二数据不限于图7所示的数据。
可选的，考虑到针对一些重要时间段(如：夜间睡眠时段、三餐前后时段、午睡时段等)，如果出现第一数据缺失或质量差的情况，则对检测结果的准确性的影响较大。那么，针对这些重要时 间段，采集用户在这些重要时间段的第二数据。例如：针对夜间睡眠时段，获取用户的睡眠时间、睡眠时长、深度睡眠情况(如是否深度睡眠、深度睡眠时段和深度睡眠时长)等。针对三餐前后时段，分别获取用户的三餐的饱腹感程度、饮食类型以及运动数据等。针对午睡时段，获取用户的午睡时间、午睡时长等。
可选的，针对上述重要时间段，仅对这些重要时间段的第一数据进行统计，确定出这些重要时间段中的哪些时间段的第一数据质量较差或者数据缺失。例如：统计获取到的夜间睡眠时段、三餐前后时段以及午睡时段的第一数据，识别出用户在这些重要时间段是否存在第一数据质量差或数据缺失的时间段。假如仅缺失用户在夜间睡眠时段的第二数据，那么单独采集用户在夜间睡眠时段的第二数据。
可选的，考虑到夜间的第一数据一般较为稳定，在用户睡眠期间可以收集到一段质量相对稳定的第一数据，且该时间段的第一数据对检测结果的准确性影响较大。因此，手机通过收集睡眠时间段的第二数据，包括：入睡时间、睡前饮食、睡前是否运动等信息进一步排除用户睡前各项行为对检测结果的干扰，提高检测结果的准确性。
在一种可能的实现方式中，手机根据可穿戴设备所采集的数据，如ACC数据和心率等判断用户在通常的入睡时间的活动情况，进而判断是否有出现熬夜、进食、运动等活动的可能。如果用户出现了熬夜、进食、运动等活动，则手机与用户交互针对性收集用户的睡前饮食、运动等信息。
在另一种可能的实现方式中，无论手机是否可根据可穿戴设备采集到用户的活动情况，均针对性的收集入睡时间段的第二数据。
这样，基于不同时段数据对检测算法的重要性不同，重要数据段(如：夜间睡眠时段、三餐前后时段、午睡时段等)对出现信号质量差或缺失的情况会较大的影响检测结果的置信度。本申请实施例提供的上述方法在尽量减轻用户交互负担的前提下，单独进行信号质量差或缺失的重要数据段的针对性信息采集，可以提高检测结果的准确性。
可选的，手机获取的第二数据的差异会导致检测结果的置信度存在差异。有些数据对检测结果的置信度的影响较大，则手机可能仅获取这些数据，根据这些第二数据和第一数据得到的检测结果的置信度便可满足要求。而有些数据对检测结果的置信度的影响较小，则手机需要获取较多的第二数据，检测结果的置信度才能满足要求。
本申请实施例中，按照第二数据对检测结果的置信度的影响程度，得出不同第二数据的优先级。则手机可根据该优先级采集第二数据，采集高优先级的第二数据后，根据该高优先级的第二数据和第一数据确定检测结果以及检测结果的置信度，如果置信度满足要求，则无需进一步采集第二数据；如果置信度不满足要求则进一步采集下一优先级的第二数据。
也即，如果第二数据包括多种第二数据。那么，获取第一数据；按照不同第二数据的优先级的从高到低的顺序，获取第二数据；每次获取第二数据后，若根据已获取的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度等于或高于预设阈值，则停止获取第二数据。否则，若根据已获取的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度低于预设阈值，则继续获取第二数据，直至糖尿病风险检测结果的置信度等于或高于预设阈值。换句话说，可获取第一数据；按照不同第二数据的优先级，获取高优先级的第二数据；若根据高优先级的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度等于或高于预设阈值，则停止获取第二数据。若根据高优先级的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度低于预设阈值，则获取低优先级的第二数据并根据已获取的第二数据和第一数据确定糖尿病检测结果，直至糖尿病风险检测结果的置信度等于或高于预设阈值。
可选的，手机可使用神经网络模型进行训练，得到不同第二数据的优先级。在一种可能的实现方式中，训练得到或者设定得到一个通用的第二数据的优先级，该通用的优先级适用于所有用户。在一种可能的实现方式中，对于不同用户或不同群体，不同的第二数据的优先级可能不同。例如，对于某些用户，第二数据的优先级顺序为身体症状数据、药物使用数据>饮食数据>运动数据>睡眠数据；而对于另外一些用户，第二数据的优先级顺序为身体症状数据、药物使用数据>运动数据>睡眠数据>饮食数据。实际应用中，可针对不同或不同类用户分别确定其对应的第二数据的优先级。
示例性的，如图8所示，对于某一用户而言，其对应的不同第二数据的优先级顺序如下：身体 症状数据、药物使用数据>饮食数据>运动数据>睡眠数据，那么手机可先与用户交互获取身体症状数据、药物使用数据，并根据获取的身体症状数据、药物使用数据和第一数据确定糖尿病风险检测结果以及该检测结果的置信度，如果置信度高于预设阈值，则无需进一步获取其他第二数据；相反，如果置信度低于预设阈值，则按照优先级顺序进一步获取饮食数据。同理如果根据身体症状数据、药物使用数据、饮食数据和第一数据确定的检测结果的置信度仍低于预设阈值，则进一步获取运动数据，否则无需获取其他第二数据。依次类推，直至检测结果的置信度高于预设阈值，或者获取到所有可能的第二数据。
相比于用户需要一次性填写所有的第二数据而言，该方式能够减少用户填写的第二数据的数据量，减轻用户的交互负担。比如：假如身体症状数据、药物使用数据、饮食数据、运动数据分别位于不同的页面，相比于用户在这三种页面之间翻页，并且填写这三种页面的所有数据。采用这种按照优先级填写的方式，用户可能仅需填写身体症状数据、药物使用数据这一种类型的内容(也即一个页面的内容)，无需填写其他第二数据，减少用户的交互负担。
这样，本申请实施例提供的方法按照第二数据的优先级，依次收集不同优先级的第二数据，并在每次收集第二数据后计算检测结果以及检测结果的置信度；当置信度达标后即可停止收集第二数据，进而减少用户的“交互负担”。
在一些方案中，可以对本申请的多个实施例进行组合，并实施组合后的方案。可选的，各方法实施例的流程中的一些操作任选地被组合，并且/或者一些操作的顺序任选地被改变。并且，各流程的步骤之间的执行顺序仅是示例性的，并不构成对步骤之间执行顺序的限制，各步骤之间还可以是其他执行顺序。并非旨在表明所述执行次序是可以执行这些操作的唯一次序。本领域的普通技术人员会想到多种方式来对本文所述的操作进行重新排序。另外，应当指出的是，本文某个实施例涉及的过程细节同样以类似的方式适用于其他实施例，或者，不同实施例之间可以组合使用。
此外，方法实施例中的某些步骤可等效替换成其他可能的步骤。或者，方法实施例中的某些步骤可以是可选的，在某些使用场景中可以删除。或者，可以在方法实施例中增加其他可能的步骤。
并且，各方法实施例之间可以单独实施，或结合起来实施。
以上详细说明了本申请实施例提供的糖尿病风险检测方法。下面结合附图介绍能够实现本申请实施例提供的方法的系统和装置。
示例性的，如图9所示，该糖尿病风险检测系统900包括：
数据采集模块901，用于采集第一数据和第二数据。
可选的，按照采集的数据的不同，数据采集模块又可分为传感器采集模块9011和用户交互采集模块9012。其中，传感器采集模块9011用于采集通过传感器采集得到的数据，例如用户的PPG、ACC等第一数据和部分第二数据(该部分第二数据包括睡眠数据、运动数据等)。
可选的，用户交互采集模块9012用于通过与用户交互采集数据，包括用户基础信息，例如：用户年龄、性别、身高、体重等信息，药物使用数据、情绪数据等第二数据。
特征提取模块902，用于对第一数据(例如：PPG信号)进行预处理、分析第一数据是否缺失、确定第一数据质量，从第一数据中提取糖尿病相关特征等。
检测模块903，用户根据第一数据和第二数据进行糖尿病风险检测，得到检测结果。
可选的，该检测模块903还可具体包括短时检测模块和长时检测模块。
其中，短时检测模块，用于通过分析短时间采集的数据快速给出糖尿病检测结果，缓解用户等待过程中的焦虑，并反映用户短时间健康状况。
长时检测模块，用于经过一段时间的数据积累后，分析长时间采集到的数据给出更为准确的糖尿病检测结果。
输出模块904，用于输出糖尿病风险检测结果。
可选的，如果包含短时检测和长时检测，则输出短时检测结果和长时检测结果。
可选的，本申请实施例提供的系统还包括健康干预模块(图中未示出)，用于根据检测结果以及多次监测结果的改善情况，绘制糖尿病风险曲线，给出健康干预建议，反映用户健康状态。
上述系统中的所有模块可位于同一电子设备中，如手机、可穿戴设备等。可选的，上述系统中的模块位于多个不同的设备中。例如：数据采集模块和特征提取模块位于包括带有PPG检测模组的 手表/手环等设备中。检测模块、输出模块和健康干预模块位于手机中。又如：数据采集模块的数量为多个，可分别位于不同的设备中，例如：数据采集模块可分别位于可穿戴设备和手机中，可采集不同的数据。
以下结合图10详细说明本申请实施例提供的糖尿病风险检测装置。
在一种可能的设计中，图10为本申请实施例提供的电子设备的结构示意图。如图10所示，电子设备1000可以包括：收发单元1001和处理单元1002。电子设备1000作为糖尿病风险检测装置，可用于实现上述方法实施例中涉及的电子设备(以前述实施例中的手机为例)的功能。
其中，收发单元1001，用于支持电子设备与其他电子设备交互，例如：从其他电子设备(以前述实施例中的可穿戴设备为例)接收第一数据和/或第二数据。
处理单元1002，用于支持电子设备执行以下步骤：根据所述第一数据和第二数据确定糖尿病风险检测结果。
可选的，电子设备还包括输入单元1003和输出单元1004，其中，输入单元1003用于支持电子设备获取第二数据。
输出单元1004，用于支持电子设备执行以下步骤：输出糖尿病风险检测结果、输出所述糖尿病风险检测结果的置信度、提示用户所述糖尿病风险检测结果的置信度以及所述置信度对应的第二数据、在所述置信度低于预设阈值的情况下，提示用户编辑已获取的第二数据或输入更多的第二数据。
其中，收发单元可以包括接收单元和发送单元，可以由收发器或收发器相关电路组件实现，可以为收发器或收发模块。第一电子设备1000中的各个单元的操作和/或功能分别为了实现上述方法实施例中所述的糖尿病风险检测方法的相应流程，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能单元的功能描述，为了简洁，在此不再赘述。
可选地，图10所示的电子设备1000还可以包括存储单元(图10中未示出)，该存储单元中存储有程序或指令。当收发单元1001以及处理单元1002执行该程序或指令时，使得图10所示的电子设备1000可以执行上述方法实施例中所述的糖尿病风险检测方法。
图10所示的电子设备1000的技术效果可以参考上述方法实施例中所述的糖尿病风险检测方法的技术效果，此处不再赘述。
除了以电子设备1000的形式以外，本申请提供的技术方案也可以为电子设备中的功能单元或者芯片，或者与电子设备匹配使用的装置。
本申请实施例还提供一种芯片系统，包括：处理器，所述处理器与存储器耦合，所述存储器用于存储程序或指令，当所述程序或指令被所述处理器执行时，使得该芯片系统实现上述任一方法实施例中的方法。
可选地，该芯片系统中的处理器可以为一个或多个。该处理器可以通过硬件实现也可以通过软件实现。当通过硬件实现时，该处理器可以是逻辑电路、集成电路等。当通过软件实现时，该处理器可以是一个通用处理器，通过读取存储器中存储的软件代码来实现。
可选地，该芯片系统中的存储器也可以为一个或多个。该存储器可以与处理器集成在一起，也可以和处理器分离设置，本申请实施例并不限定。示例性地，存储器可以是非瞬时性处理器，例如只读存储器ROM，其可以与处理器集成在同一块芯片上，也可以分别设置在不同的芯片上，本申请实施例对存储器的类型，以及存储器与处理器的设置方式不作具体限定。
示例性地，该芯片系统可以是现场可编程门阵列(field programmable gate array，FPGA)，可以是专用集成芯片(AP设备plication specific integrated circuit，ASIC)，还可以是系统芯片(system on chip，SoC)，还可以是中央处理器(central processor unit，CPU)，还可以是网络处理器(network processor，NP)，还可以是数字信号处理电路(digital signal processor，DSP)，还可以是微控制器(micro controller unit，MCU)，还可以是可编程控制器(programmable logic device，PLD)或其他集成芯片。
应理解，上述方法实施例中的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。
本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质中存储有计算机程序， 当该计算机程序在计算机上上运行时，使得计算机执行上述相关步骤，以实现上述实施例中的糖尿病风险检测方法。
本申请实施例还提供一种计算机程序产品，当该计算机程序产品在计算机上运行时，使得计算机执行上述相关步骤，以实现上述实施例中的糖尿病风险检测方法。
另外，本申请实施例还提供一种装置。该装置具体可以是组件或模块，该装置可包括相连的一个或多个处理器和存储器。其中，存储器用于存储计算机程序。当该计算机程序被一个或多个处理器执行时，使得装置执行上述各方法实施例中的糖尿病风险检测方法。
其中，本申请实施例提供的装置、计算机可读存储介质、计算机程序产品或芯片均用于执行上文所提供的对应的方法。因此，其所能达到的有益效果可参考上文所提供的对应的方法中的有益效果，此处不再赘述。
结合本申请实施例公开内容所描述的方法或者算法的步骤可以硬件的方式来实现，也可以是由处理器执行软件指令的方式来实现。软件指令可以由相应地软件模块组成，软件模块可以被存放于随机存取存储器(random access memory，RAM)、闪存、只读存储器(read only memory，ROM)、可擦除可编程只读存储器(erasable programmable ROM，EPROM)、电可擦可编程只读存储器(electrically EPROM，EEPROM)、寄存器、硬盘、移动硬盘、只读光盘(CD-ROM)或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。当然，存储介质也可以是处理器的组成部分。处理器和存储介质可以位于专用集成电路(AP设备plication specific integrated circuit，ASIC)中。
通过以上的实施方式的描述，本领域技术人员可以清楚地了解到，为描述的方便和简洁，仅以上述各功能模块的划分进行举例说明。实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成；即将装置的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的方法，可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的。例如，所述模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式；例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，模块或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
计算机可读存储介质包括但不限于以下的任意一种：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何在本申请揭露的技术范围内的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (15)

  1. 一种糖尿病风险检测方法，其特征在于，所述方法包括：
    获取第一数据和第二数据；其中，所述第一数据包括通过光电容积脉搏波描记法PPG传感器获取的PPG信号；所述第二数据包括以下一项或多项：饮食数据、运动数据、身体症状数据、药物使用数据、睡眠数据、情绪数据；
    根据所述第一数据和第二数据确定糖尿病风险检测结果；
    输出所述糖尿病风险检测结果。
  2. 根据权利要求1所述的糖尿病风险检测方法，其特征在于，所述根据所述第一数据和第二数据确定糖尿病风险检测结果，包括：
    根据所述第一数据确定第一风险值；
    根据所述第二数据和所述第一风险值，得到第二风险值；其中，所述第二风险值用于表示所述糖尿病风险检测结果。
  3. 根据权利要求2所述的糖尿病风险检测方法，其特征在于，所述根据所述第二数据和所述第一风险值，得到第二风险值，包括：
    根据不同的第二数据对应的权重和所述第一风险值，得到所述第二风险值。
  4. 根据权利要求1至3任一项所述的糖尿病风险检测方法，其特征在于，所述方法还包括：
    输出所述糖尿病风险检测结果的置信度；其中，所述置信度用于表示所述糖尿病风险检测结果的准确度。
  5. 根据权利要求4所述的糖尿病风险检测方法，其特征在于，所述置信度根据以下至少一项或多项确定：获取的第一数据的时长、获取的第一数据在预设时间段内是否缺失、获取的第二数据的种类。
  6. 根据权利要求4或5所述的糖尿病风险检测方法，其特征在于，所述方法还包括：
    提示用户所述糖尿病风险检测结果的置信度以及所述置信度对应的第二数据。
  7. 根据权利要求6所述的糖尿病风险检测方法，其特征在于，所述方法还包括：
    在所述置信度低于预设阈值的情况下，提示用户编辑已获取的第二数据或输入第三数据。
  8. 根据权利要求1至7任一项所述的糖尿病风险检测方法，其特征在于，获取第二数据，包括：
    获取预设时间段的第二数据；
    其中，所述预设时间段包括以下一个或多个时间段：第一数据缺失的时间段、午睡时间段、饮食时间段、夜间睡眠时间段。
  9. 根据权利要求1至8任一项所述的糖尿病风险检测方法，其特征在于，所述第二数据包括多种第二数据；
    所述获取第一数据和第二数据，根据所述第一数据和第二数据确定糖尿病风险检测结果，包括：
    获取第一数据；
    按照不同第二数据的优先级从高到低的顺序，获取第二数据；
    若根据已获取的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度等于或高于预设阈值，则停止获取第二数据。
  10. 根据权利要求9所述的糖尿病风险检测方法，其特征在于，所述方法还包括：
    若根据已获取的第二数据和第一数据确定得到的糖尿病风险检测结果的置信度低于所述预设阈值，则继续获取第二数据，直至所述糖尿病风险检测结果的置信度等于或高于所述预设阈值。
  11. 根据权利要求1至10任一项所述的糖尿病风险检测方法，其特征在于，所述饮食数据包括以下一项或多项：进食时间、食物口味或成分以及饱腹感程度；
    运动数据包括以下一项或多项：运动时间、时长、运动强度、运动频率；
    睡眠数据包括以下一项或多项：睡眠时间段、睡眠时长、是否深度睡眠、深度睡眠时间段、深度睡眠时长；
    药物使用数据包括以下一项或多项：是否用药、药物类型、用药频率；
    情绪数据包括以下一项或多项：精神压力指数、情绪指数。
  12. 一种电子设备，其特征在于，所述电子设备包括：处理器和存储器，所述存储器与所述处理 器耦合，所述存储器用于存储计算机可读指令，当所述处理器从所述存储器中读取所述计算机可读指令，使得所述电子设备执行如权利要求1-11中任意一项所述的方法。
  13. 一种糖尿病风险检测系统，其特征在于，所述系统包括第一电子设备和第二电子设备，所述第一电子设备用于执行如权利要求1-11中任意一项所述的方法，所述第二电子设备用于获取第一数据和/或第二数据后发送给所述第一电子设备。
  14. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质包括计算机程序，当所述计算机程序在电子设备上运行时，使得所述电子设备执行如权利要求1-11中任意一项所述的方法。
  15. 一种计算机程序产品，其特征在于，当所述计算机程序产品在计算机上运行时，使得所述计算机执行如权利要求1-11中任意一项所述的方法。
PCT/CN2023/107318 2022-07-30 2023-07-13 糖尿病风险检测方法、电子设备及系统 WO2024027482A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210911487.3 2022-07-30
CN202210911487.3A CN117503133A (zh) 2022-07-30 2022-07-30 糖尿病风险检测方法、电子设备及系统

Publications (1)

Publication Number Publication Date
WO2024027482A1 true WO2024027482A1 (zh) 2024-02-08

Family

ID=89763206

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/107318 WO2024027482A1 (zh) 2022-07-30 2023-07-13 糖尿病风险检测方法、电子设备及系统

Country Status (2)

Country Link
CN (1) CN117503133A (zh)
WO (1) WO2024027482A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130024123A1 (en) * 2011-07-21 2013-01-24 Nellcor Puritan Bennett Ireland Methods and systems for determining physiological parameters using template matching
CN105160199A (zh) * 2015-09-30 2015-12-16 刘毅 基于持续血糖监测并具有干预信息的糖尿病管理信息处理和展示方法
WO2017120615A2 (en) * 2016-01-10 2017-07-13 Sanmina Corporation System and method for health monitoring including a user device and biosensor
CN110461215A (zh) * 2017-05-05 2019-11-15 三星电子株式会社 使用便携式设备确定健康标志
US20200245903A1 (en) * 2019-01-02 2020-08-06 Oxehealth Limited Method And Apparatus For Monitoring Of A Human Or Animal Subject
CN114121271A (zh) * 2020-08-31 2022-03-01 华为技术有限公司 血糖检测模型训练方法、血糖检测方法、系统及电子设备
CN114548158A (zh) * 2022-01-28 2022-05-27 广东工业大学 一种用于血糖预测的数据处理方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130024123A1 (en) * 2011-07-21 2013-01-24 Nellcor Puritan Bennett Ireland Methods and systems for determining physiological parameters using template matching
CN105160199A (zh) * 2015-09-30 2015-12-16 刘毅 基于持续血糖监测并具有干预信息的糖尿病管理信息处理和展示方法
WO2017120615A2 (en) * 2016-01-10 2017-07-13 Sanmina Corporation System and method for health monitoring including a user device and biosensor
CN110461215A (zh) * 2017-05-05 2019-11-15 三星电子株式会社 使用便携式设备确定健康标志
US20200245903A1 (en) * 2019-01-02 2020-08-06 Oxehealth Limited Method And Apparatus For Monitoring Of A Human Or Animal Subject
CN114121271A (zh) * 2020-08-31 2022-03-01 华为技术有限公司 血糖检测模型训练方法、血糖检测方法、系统及电子设备
CN114548158A (zh) * 2022-01-28 2022-05-27 广东工业大学 一种用于血糖预测的数据处理方法

Also Published As

Publication number Publication date
CN117503133A (zh) 2024-02-06

Similar Documents

Publication Publication Date Title
US10998101B1 (en) Health management
US11864723B2 (en) Sleep scoring based on physiological information
US20170300186A1 (en) Systems and methods for health management
CA2996475A1 (en) Portable devices and methods for measuring nutritional intake
US11627946B2 (en) Cycle-based sleep coaching
WO2023124860A1 (zh) 心脏活动监测方法及可穿戴设备
WO2021070472A1 (ja) 情報処理装置、情報処理システム及び情報処理方法
WO2024027482A1 (zh) 糖尿病风险检测方法、电子设备及系统
WO2020039827A1 (ja) 健康管理装置、健康管理方法、及びプログラム
WO2022187019A1 (en) Coaching based on menstrual cycle
US11925473B2 (en) Detecting sleep intention
JP2024513847A (ja) ウェアラブルベースの生理学的データからの妊娠関連合併症の識別と予測
Mena et al. Mobile personal health care system for noninvasive, pervasive, and continuous blood pressure monitoring: development and usability study
Kuncoro et al. Wireless-based portable device heart rate measurement as biomedical devices for stress detection
US20240074709A1 (en) Coaching based on reproductive phases
US20240156363A1 (en) Smart heart tracker
CN117393152B (zh) 一种数据处理方法、电子设备、可穿戴设备及通信系统
WO2023197957A1 (zh) 年龄检测方法及可穿戴设备
WO2022206641A1 (zh) 高血压风险检测方法及相关装置
US20230084205A1 (en) Techniques for menopause and hot flash detection and treatment
EP4358857A1 (en) Coaching based on reproductive phases
EP4278361A1 (en) Coaching based on menstrual cycle
Mena et al. Mobile Personal Healthcare System for Non-Invasive, Pervasive and Continuous Blood Pressure Monitoring: A Feasibility Study
CN116458867A (zh) 下肢动脉疾病检测的系统和终端设备
CN116195982A (zh) 健康检测方法及相关设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23849191

Country of ref document: EP

Kind code of ref document: A1