Vital sign monitoring system, method and equipment and storage medium

Abstract

The invention relates to the technical field of computers, in particular to a vital sign monitoring system, method and device and a storage medium. The system comprises a bionic assembly, a display device and a data analysis unit, the bionic assembly is worn on the neck of a tested person, and an acquisition device and a processing unit are embedded in the bionic assembly; the acquisition equipment is used for acquiring real-time vital sign information of a tested person and sending the real-time vital sign information to the processing unit; the processing unit is used for sending the real-time vital sign information, the pre-stored historical vital sign information and the health index information to the data analysis unit; the data analysis unit is used for inputting the real-time vital sign information, the historical vital sign information and the health index information into a pre-trained multi-modal fusion model to obtain illness risk assessment details, and sending the illness risk assessment details to the display device; the display device is used for displaying the received illness risk assessment details; based on this, deep detection of health problems is realized.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a vital sign monitoring system, method, device and storage medium. BACKGROUND

[0002] With the rapid development of science and technology and people's attention to their own health, various devices for detecting vital signs have emerged in recent years. For example, wristband devices, chest patch devices and wearable devices.

[0003] These devices are usually only used to monitor the basic vital sign parameters (such as heart rate, blood oxygen and body temperature) of the wearer, and cannot monitor the potential health problems of the wearer. SUMMARY

[0004] In order to solve the above technical problems, the present disclosure provides a vital sign monitoring system, method, device and storage medium.

[0005] In a first aspect, the present disclosure provides a vital sign monitoring system, the system comprising:

[0006] a bionic component, a display device and a data analysis unit, the bionic component being worn on the neck of a person to be measured, the bionic component embedding a collection device and a processing unit; the collection device is used to collect real-time vital sign information of the person to be measured when the person to be measured correctly wears the bionic component, and send the real-time vital sign information to the processing unit; the processing unit is used to send the received real-time vital sign information, pre-stored historical vital sign information and pre-stored health index information of the person to be measured to the data analysis unit; the data analysis unit is used to input the real-time vital sign information, the historical vital sign information and the health index information into a pre-trained multi-modal fusion model to obtain disease risk assessment details, and send the disease risk assessment details to the display device; the display device is used to display the received disease risk assessment details.

[0007] In some optional embodiments, the deviation value between the radius of curvature of the bionic component and the radius of curvature of the vertebral artery at the preset vertebral body level of the neck is less than a preset threshold value.

[0008] In some optional embodiments, when the collection device is a plurality of sensor units, the sensor units are filled with liquid metal, and a protective layer exists on the surface of the liquid metal.

[0009] In some optional embodiments, the bionic component is made of a flexible biocompatible material.

[0010] In some alternative implementations, the data acquisition device includes a temperature sensor, a pressure sensor, a laser scattering blood flow sensor, and a photoplethysmography (PPG) sensor; the temperature sensor is used to acquire the body temperature of the person being tested; the pressure sensor is used to acquire the blood pressure of the person being tested; the laser scattering blood flow sensor is used to acquire the blood flow velocity and heart rate of the person being tested; the PPG sensor is used to acquire the pulse of the person being tested; real-time vital signs information includes body temperature, blood pressure, blood flow velocity, heart rate, and pulse.

[0011] In some optional implementations, when real-time vital signs information includes body temperature, blood pressure, blood flow rate, heart rate, and pulse, the data analysis unit is specifically used for:

[0012] Before inputting real-time vital signs information, historical vital signs information, and health indicator information into the pre-trained multimodal fusion model, the real-time vital signs information and historical vital signs information are input into the pre-trained deep learning model to obtain the blood flow resistance index and heart rate variability index. The real-time vital signs information, historical vital signs information, health indicator information, blood flow resistance index, and heart rate variability index are then input into the multimodal fusion model to obtain the thrombosis grade and arteriosclerosis curve. The disease risk assessment details are the thrombosis grade and arteriosclerosis curve.

[0013] In some optional implementations, the data analysis unit is further configured to, after obtaining the disease risk assessment details, determine the intervention recommendations corresponding to the disease risk assessment details based on the pre-constructed mapping relationship between disease details and intervention recommendations, and send the intervention recommendations to the display device; the display device is further configured to display the intervention recommendations.

[0014] Secondly, this disclosure provides a method for monitoring vital signs, which is applied to the vital signs monitoring system described in the first aspect and any embodiment thereof, and the method includes:

[0015] Collect real-time vital signs information of the test subjects; obtain pre-stored historical vital signs information and health indicator information of the test subjects; input the real-time vital signs information, historical vital signs information and health indicator information into the pre-trained multimodal fusion model to obtain disease risk assessment details; and display the disease risk assessment details.

[0016] Thirdly, this disclosure provides a computer device, including:

[0017] The memory and the processing unit are interconnected and communicate with each other. The memory stores computer instructions, and the processing unit executes the vital signs monitoring method described in the second aspect by executing the computer instructions.

[0018] Fourthly, this disclosure provides a computer-readable storage medium storing computer instructions for causing a computer to perform the vital signs monitoring method described in the second aspect.

[0019] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0020] The vital signs monitoring system disclosed herein includes a bionic component, a display device, and a data analysis unit. The bionic component is worn around the neck of the subject and embeds a data acquisition device and a processing unit. The data acquisition device collects real-time vital signs information of the subject when the bionic component is correctly worn and sends this information to the processing unit. The processing unit sends the received real-time vital signs information, pre-stored historical vital signs information, and pre-stored health indicator information of the subject to the data analysis unit. The data analysis unit inputs the real-time vital signs information, historical vital signs information, and health indicator information into a pre-trained multimodal fusion model to obtain detailed disease risk assessment, and sends this detailed assessment to the display device. The display device displays the received disease risk assessment details. This solution, by introducing a data analysis unit, achieves in-depth analysis of real-time vital signs information, historical vital signs information, and health indicator information, enabling the exposure of potential health problems in the subject and thus achieving timely intervention. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0022] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a structural connection diagram of the vital signs monitoring system provided in the embodiments of this disclosure;

[0024] Figure 2 A flowchart illustrating the vital signs monitoring method provided in this embodiment of the disclosure;

[0025] Figure 3 This is a structural connection diagram of a computer device provided in an embodiment of the present disclosure. Detailed Implementation

[0026] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0027] Numerous specific details are set forth in the following description to provide a thorough understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of this disclosure, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0028] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0029] This disclosure provides a vital signs monitoring system, such as Figure 1 As shown, the vital signs monitoring system includes a bionic component 110, a display device 120, and a data analysis unit 130. The bionic component 110 is worn around the neck of the person being tested, and the bionic component 110 has an embedded acquisition device 111 and a processing unit 112.

[0030] In this system, the bionic component 110 and the display device 120 are terminals, while the data analysis unit 130 is located in the cloud. The data acquisition device 111 and the processing unit 112 are connected, either wired or wirelessly. The display device 120 and the data analysis unit 130 are connected via a network. The processing unit 112 and the data analysis unit 130 are also connected via a network.

[0031] The bionic component 110 embeds a data acquisition device 111 and a processing unit 112. The inner side of the bionic component 110 is the side closest to the human body, and the outer side is the side furthest from the human body. Before monitoring begins, the bionic component 110 needs to be correctly worn around the neck of the person being tested. When the person being tested wears the bionic component 110 correctly, the bionic component 110 fits snugly against the neck of the person being tested. The shape and material of the bionic component 110 are not limited in this embodiment.

[0032] In some alternative implementations, the biomimetic component 110 is made of a flexible biocompatible material.

[0033] Among them are flexible biocompatible materials such as medical-grade silicone and hydrogel.

[0034] Specifically, the bionic component 110 can be a patch-type component made of flexible biocompatible material. This patch-type component can fit perfectly against the human neck. In this embodiment, the use of flexible biocompatible material to make the bionic component reduces the pressure on the human body caused by long-term wear and improves wearing comfort. Moreover, the patch-type design ensures a close fit between the bionic component 110 and the human body, thereby improving the accuracy of the data collected by the data acquisition device 111.

[0035] In some alternative implementations, the deviation between the radius of curvature of the bionic component 110 and the radius of curvature of the vertebral artery at the preset vertebral body level in the neck is less than a preset threshold.

[0036] The pre-set cervical vertebrae refer to the C3 to C5 vertebrae in the neck. The deviation value refers to the difference between the radius of curvature of the bionic component 110 and the radius of curvature of the vertebral artery at the level of the pre-set cervical vertebrae; the deviation value is a positive number. The preset threshold is the maximum allowable radius of curvature deviation while ensuring fit and data accuracy; the preset threshold can be obtained through multiple experiments.

[0037] Specifically, when the deviation between the radius of curvature of the bionic component 110 and the radius of curvature of the horizontal vertebral artery of the C3 to C5 vertebrae is less than a preset threshold, it indicates that the bionic component 110 matches the anatomical features of the horizontal carotid artery of the C3 to C5 vertebrae. A bionic component 110 that meets this condition can remain in close contact with the human neck even when the neck is rotated 90°, thus ensuring that highly accurate vital sign data can still be collected when the subject is in motion. For example, the radius of curvature of the bionic component 110 can be set to 8-10 mm.

[0038] The data acquisition device 111 is used to collect the real-time vital signs information of the test subject when the test subject correctly wears the bionic component 110, and send the real-time vital signs information to the processing unit 112.

[0039] Real-time vital signs information refers to information that represents vital signs and is collected in real time. Real-time vital signs information includes, but is not limited to, blood pressure, heart rate, pulse, and blood oxygen.

[0040] Specifically, once the subject correctly wears the bionic component 110, the data acquisition device 111 immediately begins collecting the subject's real-time vital signs information. After acquiring the subject's real-time vital signs information, the data acquisition device 111 sends the collected information to the processing unit 112. The data acquisition device 111 is a general term for information acquisition devices, and it can be one or more sensor units. Each sensor unit is responsible for collecting one or more types of real-time vital signs information. Since the data acquisition device 111 is embedded in the bionic component 110, and the bionic component 110 has limited space, sensor units obtained through micro-nano fabrication technology can be preferentially used to reduce the space occupied by the data acquisition device 111.

[0041] In some alternative implementations, when the acquisition device 111 consists of multiple sensor units, the space between each sensor unit is filled with liquid metal, and a protective layer exists on the surface of the liquid metal.

[0042] Liquid metal is used to reduce signal interference between sensor units. Liquid metal includes, but is not limited to, gallium-based alloys, bismuth-based alloys, and mercury. A protective layer is used to prevent liquid metal leakage.

[0043] Specifically, to avoid mutual interference between sensor units, they are typically spaced apart; the larger the spacing, the less interference. However, when there are many sensor units, this spacing can occupy a significant amount of space. Therefore, to reduce space usage while ensuring signal non-interference, this embodiment fills the spaces between multiple sensor units with liquid metal for isolation. This allows for reducing the spacing between sensor units while avoiding signal interference, thereby minimizing space usage. Furthermore, to prevent liquid metal leakage, this embodiment applies a protective layer to the surface of the liquid metal to avoid damage to the sensor units.

[0044] In some alternative implementations, the acquisition device 111 includes a temperature sensor, a pressure sensor, a laser scattering blood flow sensor, and a photoplethysmography (PPG) sensor.

[0045] The system includes a temperature sensor for collecting the subject's body temperature, a pressure sensor for collecting the subject's blood pressure, a laser scattering blood flow sensor for collecting the subject's blood flow velocity and heart rate, and a photoplethysmography (PPG) sensor for collecting the subject's pulse. In this embodiment, real-time vital signs information includes body temperature, blood pressure, blood flow velocity, heart rate, and pulse. The aforementioned pressure sensors include, but are not limited to, differential pressure sensors and gauge pressure sensors. Furthermore, this embodiment uses a laser scattering blood flow sensor to collect blood flow velocity and heart rate because it can eliminate motion artifacts through low-coherence interferometry, improving the accuracy of the collected data.

[0046] The processing unit 112 is used to send the received real-time vital signs information, pre-stored historical vital signs information, and pre-stored health indicator information of the tested person to the data analysis unit 130.

[0047] The historical vital sign information refers to vital sign information collected within a preset historical period. This preset historical period can be configured in advance. The preset historical period is based on the current moment and traces back a certain time, such as the past 24 hours. The health indicator information of the tested individual can be information corresponding to various measured indicators in the results of the individual's most recent health check. For example, health indicator information includes at least one or more of the following: blood pressure, blood oxygen, blood glucose, current medical history, and past medical history. It should be noted that the health indicator information of the tested individual can be transmitted to the processing unit 112 via other electronic devices. For example, the processing unit 112 can be connected to an electronic device, and the examination report of the most recent health check can be transmitted to the processing unit 112 via the electronic device. If the tested individual has never undergone a health check, a health information form can be filled out manually and transmitted to the processing unit 112 via an electronic device. The aforementioned electronic device can be a computer, tablet, mobile phone, etc.

[0048] Specifically, after the data acquisition device 111 sends the acquired real-time vital signs information to the processing unit 112, the processing unit 112 first stores the received real-time vital signs information. After completing the storage operation, it retrieves the pre-stored historical vital signs information and the health indicator information of the tested person from the preset storage location. Then, it sends the real-time vital signs information, the pre-stored historical vital signs information, and the pre-stored health indicator information of the tested person to the data analysis unit 130.

[0049] In some optional embodiments, the processing unit 112 is also used to periodically and automatically clear pre-stored historical vital sign information. For example, it may clear the information every hour, and each time it clears the information up to a preset historical time period. By periodically clearing the information, the availability of the preset storage location can be ensured, and the efficiency of the processing unit 112 can be improved.

[0050] The data analysis unit 130 is used to input real-time vital sign information, historical vital sign information and health indicator information into a pre-trained multimodal fusion model to obtain disease risk assessment details, and send the disease risk assessment details to the display device 120.

[0051] In this context, a multimodal fusion model refers to a pre-trained machine learning model used for disease risk assessment. In this embodiment, there may be one or more multimodal fusion models, each used to assess the risk of a specific disease class. Therefore, during model training, the training data for each multimodal fusion model is different. For example, when a multimodal fusion model is used to assess the risk of a disease class A, its corresponding training data consists of indicators related to and characterizing disease class A.

[0052] Specifically, after the data analysis unit 130 receives the real-time vital signs information, historical vital signs information, and health indicator information transmitted by the processing unit 112, it inputs these information into a pre-trained multimodal fusion model. The multimodal fusion model is then used for feature extraction, feature relationship capture, and risk quantification to obtain detailed disease risk assessment information. After obtaining the detailed disease risk assessment information, it is sent to the display device 120.

[0053] It should be noted that in embodiments with multiple pre-trained multimodal fusion models, the data analysis unit 130 classifies the real-time vital signs information, historical vital signs information, and health indicator information before inputting them into the multimodal fusion model. Specifically, the classification is based on the type of indicators related to the disease to be assessed by the multimodal fusion model. For example, in one example, there are three pre-trained multimodal fusion models: pre-trained multimodal fusion model A, pre-trained multimodal fusion model B, and pre-trained multimodal fusion model C. Pre-trained multimodal fusion model A is used to assess the risk of disease A, pre-trained multimodal fusion model B is used to assess the risk of disease B, and pre-trained multimodal fusion model C is used to assess the risk of disease C. Taking pre-trained multimodal fusion model A as an example, the indicators related to disease A are A1, A2, and A3. Therefore, during classification, the indicator information corresponding to A1, A2, and A3 in real-time vital signs information, the indicator information corresponding to A1, A2, and A3 in historical vital signs information, and the indicator information corresponding to A1, A2, and A3 in health indicator information need to be grouped into one category. The aforementioned category of real-time vital signs information, historical vital signs information, and health indicator information is then used as input to a pre-trained multimodal fusion model A. After processing by the pre-trained multimodal fusion model A, the risk assessment details of the test subject having category A diseases are obtained. After obtaining the disease risk assessment details output by all pre-trained multimodal fusion models, all disease risk assessment details are sent to the display device. It should be noted that there may be overlap between indicators related to different diseases; for example, indicator M may be related to both category A and category B diseases.

[0054] In some optional implementations, the data analysis unit is further configured to, after obtaining the disease risk assessment details, determine the intervention recommendations corresponding to the disease risk assessment details based on the pre-built mapping relationship between disease details and intervention recommendations, and send the intervention recommendations to the display device.

[0055] The disease details can include disease severity or lesion extent. Correspondingly, the disease risk assessment details can include disease severity or lesion extent, or other information characterizing disease severity or lesion extent. The mapping relationship between disease details and intervention recommendations can be constructed by healthcare professionals using clinical data and experience.

[0056] Specifically, the cloud stores pre-built mapping relationships between disease details and intervention recommendations for various diseases. Therefore, the data analysis unit is also used to, after obtaining the disease risk assessment details, find the corresponding intervention recommendations from the mapping relationship between disease details and intervention recommendations that match the disease risk assessment details output by the multimodal fusion model, and send both the disease risk assessment details and intervention recommendations to the display device. This allows the test subjects to adjust their medication or seek timely medical attention based on the intervention recommendations.

[0057] In some optional implementations, when the real-time vital signs information includes body temperature, blood pressure, blood flow velocity, heart rate, and pulse, the data analysis unit 130 is specifically used to: input the real-time vital signs information and historical vital signs information into a pre-trained deep learning model before inputting the real-time vital signs information, historical vital signs information, and health indicator information into the pre-trained multimodal fusion model to obtain the blood flow resistance index and heart rate variability index; input the real-time vital signs information, historical vital signs information, health indicator information, blood flow resistance index, and heart rate variability index into the multimodal fusion model to obtain the thrombosis grade and arteriosclerosis curve, and the disease risk assessment details are the thrombosis grade and arteriosclerosis curve.

[0058] In this embodiment, the deep learning model and the multimodal fusion model are pre-trained models. The training data for both models were obtained from clinical data. The deep learning model was trained to predict the blood flow resistance index and heart rate variability index based on data such as body temperature, blood pressure, blood flow velocity, heart rate, and pulse. The multimodal fusion model was trained to assess the risk of cardiovascular disease in the tested individuals.

[0059] Specifically, in some application scenarios, pre-trained multimodal fusion models are used to assess cardiovascular and cerebrovascular diseases. In this scenario, the real-time vital sign information collected by the acquisition device includes at least information on indicators related to cardiovascular and cerebrovascular diseases. Naturally, the historical vital sign information and health indicator information stored in the data analysis unit also include at least information on indicators related to cardiovascular and cerebrovascular diseases. Indicators related to cardiovascular and cerebrovascular diseases include body temperature, blood pressure, blood flow velocity, heart rate, and pulse. Therefore, after receiving the real-time vital sign information, historical vital sign information, and health indicator information transmitted by the processing unit 112, the data analysis unit 130 obtains the real-time vital sign information corresponding to indicators such as body temperature, blood pressure, blood flow velocity, heart rate, and pulse from the real-time vital sign information, and obtains the historical vital sign information corresponding to indicators such as body temperature, blood pressure, blood flow velocity, heart rate, and pulse from the historical vital sign information; then, it inputs the real-time vital sign information and historical vital sign information corresponding to these indicators into the pre-trained deep learning model to predict the blood flow resistance index and heart rate variability index. Subsequently, real-time vital sign information, historical vital sign information, health indicator information, and blood flow resistance index and heart rate variability index output by the deep learning model, corresponding to indicators such as body temperature, blood pressure, blood flow velocity, heart rate, and pulse, are input into a pre-trained multimodal fusion model. Through feature extraction, feature relationship capture, and risk quantification, the thrombosis level of the tested individual and the arteriosclerosis curve of the tested individual within a preset historical time period are obtained. The horizontal axis of the arteriosclerosis curve represents time, and the vertical axis represents the plate stability index. The arteriosclerosis curve can well reflect the degree, development speed, and potential risk of arteriosclerosis in the tested individual. The disease risk assessment details in this embodiment include thrombosis level and arteriosclerosis curve. It should be noted that the arteriosclerosis curve also includes the current arteriosclerosis level.

[0060] Display device 120 is used to display the received disease risk assessment details.

[0061] Specifically, after receiving the disease risk assessment details sent by the data analysis unit 130, the display device 120 displays the disease risk assessment details. The display device 120 can be a terminal device carried by the test subject, such as a mobile phone or smart bracelet. The display device can also be a device with display function, such as a display screen, embedded in the bionic component 110 along with the data acquisition device and processing unit. If the display device is integrated into the bionic component 110, then the display device is located on the outside of the bionic component 110.

[0062] In some optional embodiments, when the display device 120 receives disease risk assessment details and intervention recommendations, it displays both the disease risk assessment details and intervention recommendations on the display device 120. For example, when the received disease risk assessment details include thrombosis grade and arteriosclerosis curve, the display device 120 receives the disease risk assessment details and intervention recommendations as follows: thrombosis grade, arteriosclerosis curve, intervention recommendations corresponding to the thrombosis grade, and intervention recommendations corresponding to the arteriosclerosis grade reflected in the arteriosclerosis curve. In this case, the thrombosis grade, arteriosclerosis curve, intervention recommendations corresponding to the thrombosis grade, and intervention recommendations corresponding to the arteriosclerosis grade can be displayed on the display device 120.

[0063] The vital signs monitoring system disclosed herein includes a bionic component, a display device, and a data analysis unit. The bionic component is worn around the neck of the subject and embeds a data acquisition device and a processing unit. The data acquisition device collects real-time vital signs information of the subject when the bionic component is correctly worn and sends this information to the processing unit. The processing unit sends the received real-time vital signs information, pre-stored historical vital signs information, and pre-stored health indicator information of the subject to the data analysis unit. The data analysis unit inputs the real-time vital signs information, historical vital signs information, and health indicator information into a pre-trained multimodal fusion model to obtain detailed disease risk assessment, and sends this detailed assessment to the display device. The display device displays the received disease risk assessment details. This solution, by introducing a data analysis unit, achieves in-depth analysis of real-time vital signs information, historical vital signs information, and health indicator information, enabling the exposure of potential health problems in the subject and thus achieving timely intervention.

[0064] According to an embodiment of this disclosure, a method for monitoring vital signs is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0065] This embodiment provides a vital signs monitoring method, which can be used in any of the vital signs monitoring systems described in the foregoing embodiments. Figure 2 This is a flowchart of a vital signs monitoring method according to an embodiment of the present disclosure, such as... Figure 2 As shown, the process includes the following steps:

[0066] S210 collects real-time vital signs information of the person being tested.

[0067] The vital signs monitoring system collects real-time vital signs information of the subjects and transmits it to the processing unit. For details regarding real-time vital signs information, please refer to the description of the collection equipment mentioned above; it will not be repeated here.

[0068] S220: Obtain the pre-stored historical vital signs and health indicators of the tested individuals.

[0069] The processing unit in the vital signs monitoring system retrieves the historical vital signs and health indicators of the tested individual from pre-stored data. It then sends the received real-time vital signs information, along with the retrieved historical vital signs and health indicators, to the data analysis unit. For details regarding historical vital signs and health indicators, please refer to the description of the processing unit mentioned above; further details will not be provided here.

[0070] S230 inputs real-time vital signs information, historical vital signs information, and health indicator information into a pre-trained multimodal fusion model to obtain details of disease risk assessment.

[0071] The data analysis unit in the vital signs monitoring system inputs the received real-time vital signs information, historical vital signs information, and health indicator information into a pre-trained multimodal fusion model to obtain the disease risk assessment details output by the multimodal fusion model, and then sends these disease risk assessment details to the display device. For details regarding the disease risk assessment details, please refer to the description of the data analysis unit mentioned above; it will not be repeated here.

[0072] S240 displays the details of the disease risk assessment.

[0073] The details of the disease risk assessment are displayed on the display device within the vital signs monitoring system. For information regarding the display, please refer to the aforementioned description of the display device; it will not be repeated here.

[0074] The vital sign monitoring method provided in this embodiment collects real-time vital sign information of the tested person; obtains pre-stored historical vital sign information and health indicator information corresponding to the tested person; inputs the real-time vital sign information, historical vital sign information, and health indicator information into a pre-trained multimodal fusion model to obtain disease risk assessment details; and displays the disease risk assessment details. This method uses a pre-trained multimodal fusion model to perform in-depth analysis of real-time vital sign information, historical vital sign information, and health indicator information, making it easier for the tested person to understand their own deeper health problems, thereby enabling them to take corresponding measures based on the disease risk assessment details output by the model, achieving the effect of timely detection and timely resolution.

[0075] This disclosure also provides a computer device; please refer to [link / reference].Figure 3 , Figure 3 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of this disclosure, such as... Figure 3 As shown, the computer device includes one or more processors 310, memory 320, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components are interconnected via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 3 Take the 310 processor as an example.

[0076] Processor 310 may be a central processing unit, a network processor, or a combination thereof. Processor 310 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPA), or any combination thereof.

[0077] The memory 320 stores instructions executable by at least one processor 310 to cause the at least one processor 310 to perform the method shown in the above embodiments.

[0078] The memory 320 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 320 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 320 may optionally include memory remotely located relative to the processor 310, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0079] The memory 320 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 320 may also include a combination of the above types of memory.

[0080] The computer device also includes a communication interface 330 for communicating with other devices or communication networks.

[0081] This disclosure also provides a computer-readable storage medium in which the methods described in this disclosure can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded over a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium may be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code that, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0082] In addition to the computer devices and computer-readable storage media described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the sound source localization method provided in any embodiment of this application.

[0083] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0084] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vital signs monitoring system, characterized in that, The system includes: The device includes a bionic component, a display device, and a data analysis unit. The bionic component is worn around the neck of the person being tested, and the bionic component has an embedded acquisition device and a processing unit. The acquisition device is used to acquire the real-time vital signs information of the test subject when the test subject correctly wears the bionic component, and send the real-time vital signs information to the processing unit. The processing unit is used to send the received real-time vital signs information, pre-stored historical vital signs information, and pre-stored health indicator information of the tested person to the data analysis unit. The data analysis unit is used to input the real-time vital signs information, the historical vital signs information, and the health indicator information into a pre-trained multimodal fusion model to obtain disease risk assessment details, and send the disease risk assessment details to the display device; The display device is used to display the received details of the disease risk assessment.

2. The system according to claim 1, characterized in that, The deviation between the radius of curvature of the bionic component and the radius of curvature of the vertebral artery at the preset vertebral body level in the neck is less than a preset threshold.

3. The system according to claim 1, characterized in that, When the acquisition device consists of multiple sensor units, the spaces between each sensor unit are filled with liquid metal, and a protective layer exists on the surface of the liquid metal.

4. The system according to any one of claims 1 to 3, characterized in that, The biomimetic components are made of flexible biocompatible materials.

5. The system according to claim 1, characterized in that, The data acquisition device includes a temperature sensor, a pressure sensor, a laser scattering blood flow sensor, and a photoplethysmography (PPG) sensor. The temperature sensor is used to collect the body temperature of the person being tested; The pressure sensor is used to collect the blood pressure of the person being tested; The laser scattering blood flow sensor is used to collect the blood flow velocity and heart rate of the person being tested; The photoplethysmography sensor is used to collect the pulse of the person being tested. The real-time vital signs information includes body temperature, blood pressure, blood flow rate, heart rate, and pulse.

6. The system according to claim 5, characterized in that, When the real-time vital signs information includes the body temperature, blood pressure, blood flow rate, heart rate, and pulse, the data analysis unit is specifically used for: Before inputting the real-time vital signs information, the historical vital signs information, and the health indicator information into the pre-trained multimodal fusion model, the real-time vital signs information and the historical vital signs information are input into the pre-trained deep learning model to obtain the blood flow resistance index and the heart rate variability index. The real-time vital signs information, the historical vital signs information, the health indicators, the blood flow resistance index, and the heart rate variability index are input into the multimodal fusion model to obtain the thrombosis grade and the arteriosclerosis curve. The disease risk assessment details are the thrombosis grade and the arteriosclerosis curve.

7. The system according to claim 1, characterized in that, The data analysis unit is further configured to, after obtaining the disease risk assessment details, determine the intervention recommendations corresponding to the disease risk assessment details based on the pre-constructed mapping relationship between disease details and intervention recommendations, and send the intervention recommendations to the display device; The display device is also used to display the intervention recommendations.

8. A method for monitoring vital signs, characterized in that, The method is applied to the vital signs monitoring system according to any one of claims 1 to 7, and the method includes: Collect real-time vital signs information of the tested personnel; Obtain the pre-stored historical vital signs and health indicators of the tested individuals; The real-time vital signs information, the historical vital signs information, and the health indicator information are input into a pre-trained multimodal fusion model to obtain detailed disease risk assessment. The details of the disease risk assessment will be displayed.

9. A computer device, characterized in that, include: The system includes a memory and a processing unit, which are interconnected. The memory stores computer instructions, and the processing unit executes the computer instructions to perform the vital signs monitoring method of claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the vital signs monitoring method of claim 8.

Images