Blood pressure measurement quality control method and device based on artificial intelligence image recognition, terminal and medium

Abstract

This application provides a blood pressure measurement quality control method, device, terminal, and medium based on artificial intelligence image recognition. The invention uses facial recognition technology to store the facial information of subjects undergoing their first standardized blood pressure measurement. Before subsequent standardized blood pressure monitoring and follow-up, subjects can automatically log into the system via facial recognition. The invention also uses artificial intelligence image recognition and processing technology to perform quality control on subjects undergoing standardized blood pressure measurements, ensuring standardized measurement posture and effectively reducing measurement errors. Furthermore, if inaccurate posture is detected during blood pressure measurement, the invention will promptly remind the subject to adjust their posture through various means (such as voice, screen display, or flashing warning lights). Further, the invention matches a large amount of standardized blood pressure measurement data with facial information, which can be used to analyze and identify the facial features of hypertensive patients, thereby providing new clinical diagnostic and treatment evidence for hypertension.

Description

Technical Field

[0001] This application relates to the field of blood pressure measurement quality control technology, and in particular to blood pressure measurement quality control methods, devices, terminals and media based on artificial intelligence image recognition. Background Technology

[0002] Blood pressure measurement is the main means of assessing blood pressure levels, diagnosing hypertension, and observing the effectiveness of antihypertensive treatment. Blood pressure is the lateral pressure exerted by blood on the blood vessel walls when blood flows within the vessels.

[0003] However, current standardized blood pressure measurement still has the following shortcomings: First, current standardized blood pressure measurement usually only reminds subjects to follow the blood pressure measurement guidelines verbally or in writing, but it is still difficult to control the subject's posture during real-time measurement. Incorrect posture usually has a significant impact on the standardized blood pressure measurement results. Second, current standardized blood pressure measurement usually requires swiping a medical card or health insurance card for identification, meaning that a hardware card is required for medical treatment, which is inconvenient and results in a poor measurement experience for the subject. Finally, current standardized blood pressure measurement data does not include facial information; it only collects and records personal health data. The lack of facial data makes it impossible to analyze the correlation between facial information and blood pressure health, which is detrimental to the development of hypertension research. Summary of the Invention

[0004] In view of the shortcomings of the prior art described above, the purpose of this application is to provide a solution to the technical problem of poor quality control in blood pressure measurement in the prior art.

[0005] To achieve the above and other related objectives, a first aspect of this application provides a blood pressure measurement quality control method based on artificial intelligence image recognition, comprising: acquiring facial image information of a subject for identity recognition; after confirming the identity information of the subject, acquiring an image of the subject undergoing blood pressure measurement and extracting posture feature information; and determining, based on the posture feature information, whether the posture of the subject during the blood pressure measurement process meets the quality control requirements; the quality control requirements include at least some body parts being positioned according to posture requirements and / or some body parts remaining in an inactive state.

[0006] In some embodiments of the first aspect of this application, some body parts in the quality control requirements are positioned according to posture requirements, including any one or more of the following requirements: the test subject's back is against the chair back, the test subject's feet are flat on the ground, and the test subject's palms are facing upwards; some body parts in the quality control requirements are kept in an inactive state, including any one or two of the following requirements: the test subject's sitting posture is kept in an inactive state and / or the test subject's mouth is kept in an inactive state.

[0007] In some embodiments of the first aspect of this application, the method of determining whether the back of the test subject is close to the chair back includes: determining the position of the back of the test subject based on the posture feature information; and determining whether the back of the test subject is close to the chair back by the gap distance and contact area between the back of the test subject and the chair back.

[0008] In some embodiments of the first aspect of this application, the method of determining whether the subject's feet are flat on the ground includes: determining the position of the subject's feet based on the posture feature information; and determining whether the subject's feet are flat on the ground by the gap distance and contact area between the subject's feet and the ground.

[0009] In some embodiments of the first aspect of this application, the method for determining whether the palm of the subject's hand is facing upward includes: if fingerprint modal information, palm print modal information, or palm vein modal information are extracted from the posture feature information, then the palm is determined to be facing upward.

[0010] In some embodiments of the first aspect of this application, the method of determining whether the palm of the subject's hand is facing upward includes: if nail modal information is extracted from the posture feature information, then the palm is determined to be facing downward.

[0011] In some embodiments of the first aspect of this application, the method for determining whether the subject's sitting posture remains inactive includes: after acquiring images of the subject's blood pressure measurement process, extracting posture feature information from all process images, converting all extracted posture features into vectors, comparing them pairwise, and calculating the similarity between the vectors; if the similarity between any two posture features is lower than a preset threshold, it is determined that the subject failed to maintain an inactive sitting posture during the blood pressure measurement process.

[0012] In some embodiments of the first aspect of this application, the method for determining whether the subject's sitting posture remains inactive includes: after acquiring an image of the subject's blood pressure measurement process, setting multiple key body feature points and tracking the coordinate changes of the key body feature points in real time; if the coordinate change of any of the key body feature points exceeds a preset threshold, it is determined that the subject failed to maintain an inactive sitting posture during the blood pressure measurement process.

[0013] In some embodiments of the first aspect of this application, the method for determining whether the subject's mouth remains inactive includes: after acquiring process images of the subject undergoing blood pressure measurement, extracting posture feature information from all process images and determining the mouth position; converting the subject's mouth features in all process images into vectors and comparing them pairwise to calculate the similarity between the vectors; if the similarity between any two mouth features is lower than a preset threshold, it is determined that the subject failed to keep their mouth still during the blood pressure measurement process.

[0014] In some embodiments of the first aspect of this application, the method for determining whether the subject's mouth remains inactive includes: after acquiring images of the subject's blood pressure measurement process, setting multiple mouth feature points, and calculating the ratio of mouth width to length based on these mouth feature points; comparing the changes in the ratio of mouth width to length in multiple frames of images, and if the changes are greater than a preset threshold, determining that the subject failed to keep their mouth still during the blood pressure measurement process.

[0015] In some embodiments of the first aspect of this application, if it is determined that the subject's posture during blood pressure measurement does not meet quality control requirements, a real-time posture adjustment reminder is issued.

[0016] In some embodiments of the first aspect of this application, massive amounts of blood pressure measurement data are matched with facial feature data, and a correlation between hypertension type and patient facial features is established based on the matching results.

[0017] To achieve the above and other related objectives, a second aspect of this application provides a blood pressure measurement quality control device based on artificial intelligence image recognition, comprising: an identity recognition module for acquiring facial image information of a subject for identity recognition; a feature extraction module for acquiring images of the subject undergoing blood pressure measurement after confirming the subject's identity information, and extracting posture feature information; and a quality control module for determining whether the subject's posture during blood pressure measurement meets quality control requirements based on the posture feature information; wherein the quality control requirements include at least some body parts being positioned according to posture requirements and / or some body parts remaining inactive.

[0018] To achieve the above and other related objectives, a third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the blood pressure measurement quality control method based on artificial intelligence image recognition.

[0019] To achieve the above and other related objectives, a fourth aspect of this application provides an electronic terminal, comprising: a processor and a memory; the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes the blood pressure measurement quality control method based on artificial intelligence image recognition.

[0020] As described above, the blood pressure measurement quality control method, device, terminal, and medium based on artificial intelligence image recognition of this application have the following beneficial effects: This invention uses facial recognition technology to store the facial information of subjects undergoing their first standardized blood pressure measurement. Before subsequent standardized blood pressure monitoring and follow-up, the subjects can automatically log into the system via facial recognition. Furthermore, this invention also uses artificial intelligence image recognition and processing technology to perform blood pressure measurement quality control on subjects undergoing standardized blood pressure measurements, ensuring that the subjects' measurement posture is standardized and effectively reducing measurement errors. Moreover, once an inaccurate posture is detected during blood pressure measurement, the invention will promptly remind the subject to adjust their posture through various means (such as voice, screen display, or flashing warning lights). Further, this invention matches a large amount of standardized blood pressure measurement data with facial information, which can be used to analyze and identify the characteristic facial features of hypertensive patients, thereby providing new clinical diagnostic and treatment evidence for hypertension. Attached Figure Description

[0021] Figure 1 The diagram shown is a flowchart of a blood pressure measurement quality control method based on artificial intelligence image recognition in one embodiment of this application.

[0022] Figure 2 The diagram shown is a structural schematic of a blood pressure measurement quality control device based on artificial intelligence image recognition in one embodiment of this application.

[0023] Figure 3 The diagram shown is a structural schematic of a quality control terminal in one embodiment of this application. Detailed Implementation

[0024] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.

[0025] It should be noted that in the following description, reference is made to the accompanying drawings, which illustrate several embodiments of this application. It should be understood that other embodiments may also be used, and changes in mechanical composition, structure, electrical system, and operation may be made without departing from the spirit and scope of this application. The following detailed description should not be considered limiting, and the scope of the embodiments of this application is defined only by the claims of the published patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. Spatially related terms, such as “upper,” “lower,” “left,” “right,” “below,” “below,” “lower part,” “above,” “upper part,” etc., may be used herein to illustrate the relationship between one element or feature shown in the figures and another element or feature.

[0026] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," and "holding" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0027] Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context indicates otherwise. The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data used can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising,” “including,” indicate the presence of the stated features, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. It should be further understood that the terms “or” and “and / or” as used herein are interpreted as inclusive, or mean any one or any combination thereof. Thus, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will only occur if the combination of elements, functions, or operations is inherently mutually exclusive in some way.

[0028] To address the various problems encountered in existing standardized blood pressure measurements, this invention employs facial recognition technology to store the facial information of subjects undergoing their first standardized blood pressure measurement. This allows for automatic login to the system via facial recognition before subsequent standardized blood pressure monitoring and follow-up. Furthermore, this invention utilizes artificial intelligence image recognition and processing technology to perform quality control on subjects undergoing standardized blood pressure measurements, ensuring standardized measurement posture and effectively reducing measurement errors. Moreover, if inaccurate posture is detected during blood pressure measurement, the invention promptly reminds the subject to adjust their posture through various means (such as voice, screen display, or flashing warning lights). Further, this invention matches a large amount of standardized blood pressure measurement data with facial information, enabling the analysis and identification of characteristic facial features in hypertensive patients, thereby providing new clinical diagnostic and treatment evidence for hypertension.

[0029] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the invention.

[0030] like Figure 1 The diagram illustrates a flowchart of a blood pressure measurement quality control method based on artificial intelligence image recognition, according to an embodiment of the present invention. This embodiment of the blood pressure measurement quality control method based on artificial intelligence image recognition mainly includes steps S11 to S13.

[0031] It is worth noting that the method in this embodiment can be applied not only to the quality control of blood pressure measurement, but also to the quality control of blood glucose measurement, eye disease detection, dental disease detection, and other related fields.

[0032] It should also be understood that the method provided in this embodiment can be applied to a variety of hardware devices, such as controllers like ARM (Advanced RISC Machines), FPGA (Field Programmable Gate Array), SoC (System on Chip), DSP (Digital Signal Processing), or MCU (Microcontroller Unit); or it can be applied to personal computers such as desktop computers, laptops, tablets, smartphones, smart bracelets, smartwatches, smart helmets, smart TVs, and personal digital assistants; it can also be applied to servers, which can be arranged on one or more physical servers according to various factors such as function and load, or can be composed of distributed or centralized server clusters.

[0033] Step S11: Obtain the facial image information of the test subject for identity recognition.

[0034] Specifically, facial images of the subject can be acquired using an image acquisition device, and then a facial recognition algorithm can be used to identify the subject's identity information. The image acquisition device includes, but is not limited to, cameras, video cameras, camera modules integrating optical systems or CCD chips, and camera modules integrating optical systems and CMOS chips. The facial recognition algorithm includes, but is not limited to, MTCNN, Cascade CNN, DenseBox, Faceness-Net, HR, Face R-CNN, or SSH algorithms. It should be noted that this embodiment does not limit the image acquisition device or the facial recognition algorithm. In fact, any hardware device capable of acquiring images and any algorithm capable of facial recognition in the prior art can be applied to the technical solution of this embodiment.

[0035] It is worth noting that current standardized blood pressure measurements typically require swiping a medical card or health insurance card for identification, meaning that a physical card is necessary for medical visits, which is inconvenient and results in a poor blood pressure measurement experience for the patient. Therefore, this invention utilizes facial recognition technology for identification, eliminating the need for physical cards such as medical cards or health insurance cards in existing technologies, improving recognition efficiency, and significantly enhancing the user experience.

[0036] Step S12: After confirming the identity information of the subject, obtain images of the subject's blood pressure measurement process and extract posture feature information.

[0037] In some examples, target detection algorithms can be used to extract posture feature information from images of the subject undergoing blood pressure measurement. The posture feature extraction process includes human body segmentation, human posture recognition, and data classification. Human body segmentation refers to the detection of key points on the human skeleton, primarily detecting posture-related key points, and the output of these key points is human skeletal information. Human posture recognition mainly includes action feature extraction. Data classification mainly includes data similarity calculation and a classifier. The target detection algorithm, also known as a target extraction algorithm, is an image segmentation algorithm based on the geometric and statistical features of the target. It combines target segmentation and recognition, locating the target and determining its position and size. The target detection algorithms involved in this embodiment include, but are not limited to, candidate region-based target detection algorithms (such as R-CNN, Fast R-CNN, FPN, etc.) and single-shot target detection algorithms (such as SSD algorithm, YOLO algorithm, etc.), etc., and are not specifically limited in this embodiment.

[0038] It should be noted that the images of the subject undergoing blood pressure measurement usually refer to a set of images that cover all images of the subject during the entire process of blood pressure measurement.

[0039] Step S13: Based on the posture feature information, determine whether the subject's posture during the blood pressure measurement process meets the quality control requirements; the quality control requirements include at least some body parts being positioned according to the posture requirements and / or some body parts being kept in an inactive state.

[0040] In some examples, the body parts are positioned according to posture requirements, including the subject's back being pressed against the chair back. Specifically, if the subject's back is pressed against the chair back during blood pressure measurement, their posture is considered correct; otherwise, their posture is considered incorrect.

[0041] Furthermore, the method for determining whether the subject's back is close to the chair back includes: determining the position of the subject's back based on the posture feature information; and determining whether the subject's back is close to the chair back by the gap distance and contact area between the subject's back and the chair back.

[0042] Specifically, if there is still a gap between the subject's back and the chair back, it indicates that the subject's back is not in contact with the chair back, and the current blood pressure measurement posture is not standard. If there is no gap between the subject's back and the chair back, it indicates that the subject's back is in contact with the chair back. Furthermore, to prevent some subjects from having their backs in contact with the chair back but still having an incorrect posture, which could affect the accuracy of the blood pressure measurement results (e.g., hunching over or lying down), this embodiment also determines the contact area between the subject's back and the chair back. If the contact area is greater than a preset threshold, it indicates that the subject's back is close to the chair back; otherwise, the subject's back is not close to the chair back.

[0043] In some examples, the body parts are positioned according to the required posture, including the subject's feet being placed flat on the ground. It is important to note that "feet flat on the ground" means that both feet are flat and in contact with the ground. For clarity, the following incorrect postures are provided as examples: the subject standing on one foot (e.g., crossing their legs), the subject standing on their toes, the subject standing with their feet on the side, etc. These postures do not meet the requirement of feet being flat on the ground and will affect the accuracy of blood pressure measurement.

[0044] Furthermore, the method for determining whether the subject's feet are flat on the ground includes: determining the position of the subject's feet based on the posture feature information; and determining whether the feet are flat on the ground by the gap distance and contact area between the subject's feet and the ground. Specifically, if there is still a gap between either foot and the ground, it indicates that the current blood pressure measurement posture is not standard; if there is no gap between either foot and the ground, it indicates that both feet are in contact with the ground. Further, if there is no gap between either foot and the ground, it is then determined whether the contact area between the feet and the ground is greater than a preset threshold. If it is greater than the preset threshold, it indicates that the feet are flat on the ground; otherwise, the feet are not flat.

[0045] In some examples, the body parts are positioned according to posture requirements, including the subject's hand with the palm facing upwards. The method for determining whether the subject's hand is facing upwards includes: if fingerprint modality information, palm print modality information, or palm vein modality information can be extracted from the image, then the subject's palm is facing upwards; otherwise, the palm is facing downwards. Another method for determining whether the palm is facing upwards includes: if fingernail modality information can be extracted from the image, then the subject's palm is facing downwards.

[0046] It should be understood that fingerprint recognition is a commonly used biometric identification technology that uses the texture of the skin of the fingers for identification; palm print recognition is a technology that uses the texture of the skin of the palm for identification; palm veins are blue veins that are faintly visible through the skin of the palm, and palm vein image information can be obtained by illuminating the palm with infrared light and sensing the light reflected from the palm with a sensor.

[0047] In some examples, keeping certain body parts inactive includes keeping the subject in a seated position. The method for determining whether the subject kept a seated position inactive during blood pressure measurement is as follows.

[0048] Judgment Method 1) After acquiring images of the subject undergoing blood pressure measurement, posture feature information is extracted from all images. All extracted posture features are converted into vectors and compared pairwise to calculate the similarity between the vectors. If the similarity between any two posture features is lower than a preset threshold, it can be determined that the subject failed to maintain a non-active sitting posture during the blood pressure measurement process.

[0049] Judgment Method 2) After obtaining the process image of the subject's blood pressure measurement, set multiple key body feature points (such as shoulder feature points, arm feature points, waist feature points, leg feature points, etc.), and track the coordinate changes of the key body feature points in real time. If the coordinate change of any of the key body feature points exceeds the preset threshold, it can be determined that the subject failed to keep his sitting posture in an inactive state during the blood pressure measurement process.

[0050] In some examples, keeping certain body parts inactive includes the subject keeping their mouth still. The method for determining whether the subject kept their mouth still during blood pressure measurement is as follows:

[0051] Judgment Method 1) After acquiring images of the subject undergoing blood pressure measurement, extract posture feature information from all images and determine the mouth position. Convert the mouth features of the subject in all images into vectors and compare them pairwise to calculate the similarity between the vectors. If the similarity between any two mouth features is lower than a preset threshold, it can be determined that the subject failed to keep their mouth still during the blood pressure measurement (e.g., the subject talking, eating, chewing gum, etc. during the measurement).

[0052] Judgment Method 2) After acquiring images of the subject undergoing blood pressure measurement, multiple mouth feature points are set, such as multiple feature points on the left, right, top, and bottom of the mouth corners. Based on these mouth feature points, the ratio of mouth width to length is calculated. The changes in the ratio of mouth width to length in multiple frames are compared. If the change is greater than a preset threshold, it can be determined that the subject failed to keep their mouth still during the blood pressure measurement process.

[0053] In some examples, the blood pressure measurement quality control method further includes: if it is determined that the subject's posture during the blood pressure measurement process does not meet the quality control requirements, a real-time posture adjustment reminder is issued. The reminder methods include, but are not limited to, voice reminders, display screen reminders, and flashing indicator lights. For example, if it is determined that some body parts of the subject are not positioned according to the required posture during the blood pressure measurement process, such as the back not being firmly against the chair back, the feet not being flat on the ground, or the palm of the measuring arm facing down, a real-time posture adjustment reminder is issued, reminding the subject that the back should be firmly against the chair back, the feet should be flat on the ground, and the palm of the measuring arm should face up. As another example, if it is determined that some body parts of the subject are not kept in a static state during the blood pressure measurement process, such as mouth movement or changes in sitting posture, a real-time posture adjustment reminder is issued, reminding the subject to refrain from speaking or moving during the blood pressure measurement process.

[0054] In some examples, the blood pressure measurement quality control method further includes: matching massive amounts of blood pressure measurement data with facial feature data, and establishing a correlation between hypertension type and patient facial features based on the matching results. For example, patients with malignant hypertension often appear pale; patients with slow-onset hypertension often appear red due to skin congestion, etc., and these will not be listed in detail here.

[0055] like Figure 2 The diagram illustrates the structure of a blood pressure measurement quality control device based on artificial intelligence image recognition according to an embodiment of the present invention. The blood pressure measurement quality control device 200 based on artificial intelligence image recognition in this embodiment includes an identity recognition module 201, a feature extraction module 202, and a quality control module 203.

[0056] The identity recognition module 201 is used to acquire the facial image information of the test subject for identity recognition; the feature extraction module 202 is used to acquire the process image of the test subject's blood pressure measurement after confirming the test subject's identity information, and extract posture feature information; the quality control module 203 is used to determine whether the test subject's posture during the blood pressure measurement process meets the quality control requirements based on the posture feature information; the quality control requirements include at least some body parts being placed according to posture requirements and / or some body parts being kept in an inactive state.

[0057] It should be noted that the blood pressure measurement quality control device in this embodiment is similar to the blood pressure measurement quality control method described above, and therefore will not be repeated. It should be understood that the division of the various modules in the above device is merely a logical functional division; in actual implementation, they can be fully or partially integrated into a single physical entity, or physically separated. Furthermore, these modules can all be implemented in software via processing element calls; they can all be implemented in hardware; or some modules can be implemented in software via processing element calls, while others are implemented in hardware. For example, the feature extraction module can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and its function can be called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0058] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more digital signal processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to form a system-on-a-chip (SOC).

[0059] like Figure 3 The diagram shows a structural schematic of a quality control terminal in one embodiment of the present invention. The quality control terminal in this embodiment includes: a processor 31, a memory 32, and a communicator 33; the memory 32 is connected to the processor 31 and the communicator 33 via a system bus and communicates with them; the memory 32 stores computer programs; the communicator 33 communicates with other devices; and the processor 31 runs the computer programs, enabling the electronic terminal to execute the various steps of the blood pressure measurement quality control method based on artificial intelligence image recognition as described above.

[0060] The system bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include Random Access Memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0061] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0062] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the blood pressure measurement quality control method based on artificial intelligence image recognition.

[0063] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented using computer program-related hardware. The aforementioned computer program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0064] In the embodiments provided in this application, the computer-readable and writable storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disc storage devices, disk storage devices or other magnetic storage devices, flash memory, USB flash drive, portable hard drive, or any other medium capable of storing desired program code in the form of instructions or data structures and accessible by a computer. Additionally, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer-readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are intended for non-transient, tangible storage media. The disks and optical discs used in the application include compact discs (CDs), laser discs, optical discs, digital multifunction discs (DVDs), floppy disks, and Blu-ray discs, where disks typically copy data magnetically, while optical discs use lasers to copy data optically.

[0065] In summary, this application provides a blood pressure measurement quality control method, device, terminal, and medium based on artificial intelligence image recognition. This invention uses facial recognition technology to store the facial information of subjects undergoing their first standardized blood pressure measurement. Before subsequent standardized blood pressure monitoring and follow-up, subjects can automatically log into the system via facial recognition. Furthermore, this invention uses artificial intelligence image recognition and processing technology to perform quality control on subjects undergoing standardized blood pressure measurements, ensuring standardized measurement posture and effectively reducing measurement errors. Moreover, if inaccurate posture is detected during blood pressure measurement, the invention will promptly remind the subject to adjust their posture through various means (such as voice, screen display, or flashing warning lights). Further, this invention matches a large amount of standardized blood pressure measurement data with facial information, which can be used to analyze and identify the facial features of hypertensive patients, thereby providing new clinical diagnostic and treatment evidence for hypertension. Therefore, this application effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0066] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.

Claims

1. A quality control method for blood pressure measurement based on artificial intelligence image recognition, characterized in that, include: To obtain facial image information of test subjects for identity recognition; After confirming the identity information of the test subject, images of the test subject undergoing blood pressure measurement are obtained, and posture feature information is extracted. Based on the posture feature information, it is determined whether the subject's posture during the blood pressure measurement process meets the quality control requirements; the quality control requirements include at least some body parts being positioned according to the posture requirements and some body parts being kept in an inactive state; The quality control requirements specify the placement of certain body parts according to posture requirements, including combinations of the following: the subject's back is pressed against the chair back, the subject's feet are flat on the ground, and the subject's palms are facing upwards. The quality control requirement that certain body parts remain inactive includes a combination of the following requirements: the subject's sitting posture remains inactive and the subject's mouth remains inactive; The methods for determining whether a test subject's sitting posture is maintained in an inactive state include a combination of the following requirements: (1) After obtaining the process images of the subject's blood pressure measurement, the posture feature information of all process images is extracted, and all extracted posture features are converted into vectors and compared pairwise to calculate the similarity between the vectors; if the similarity between any two posture features is lower than a preset threshold, it is determined that the subject failed to keep his sitting posture in an inactive state during the blood pressure measurement process. (2) After obtaining the process image of the subject's blood pressure measurement, set multiple key body feature points and track the coordinate changes of the key body feature points in real time; if the coordinate change of any of the key body feature points exceeds the preset threshold, it is determined that the subject failed to keep his sitting posture in an inactive state during the blood pressure measurement process. The methods for determining whether a subject's mouth remains inactive include a combination of the following requirements: (1) After obtaining the process images of the subject's blood pressure measurement, the posture feature information of all process images is extracted and the mouth position is determined; the mouth features of the subject in all process images are converted into vectors and compared pairwise to calculate the similarity between the vectors; if the similarity between any two mouth features is lower than the preset threshold, it is determined that the subject failed to keep his mouth still during the blood pressure measurement process. (2) After obtaining the process image of the subject's blood pressure measurement, set multiple mouth feature points and calculate the ratio of mouth width and length based on these mouth feature points; compare the changes in the ratio of mouth width and length of multiple frames of images, and if the changes are greater than a preset threshold, it is determined that the subject failed to keep his mouth still during the blood pressure measurement process. Massive amounts of blood pressure measurement data are matched with facial feature data, and the correlation between hypertension type and patient facial features is established based on the matching results; among which, hypertension type includes malignant hypertension and slow-onset hypertension; The method for determining whether the subject's back is close to the chair back includes: determining the position of the subject's back based on the posture feature information; and determining whether the subject's back is close to the chair back by the gap distance and contact area between the subject's back and the chair back. The method for determining whether the subject's feet are flat on the ground includes: determining the position of the subject's feet based on the posture feature information; and determining whether the subject's feet are flat on the ground by the gap distance and contact area between the subject's feet and the ground. The method for determining whether the palm of the subject's hand is facing upward includes: if fingerprint modal information, palm print modal information, or palm vein modal information are extracted from the posture feature information, then the palm is determined to be facing upward; The method for determining whether the palm of the subject's hand is facing upward includes: if nail modal information is extracted from the posture feature information, then the palm is determined to be facing downward; If the subject's posture during blood pressure measurement is determined to be inconsistent with quality control requirements, a real-time posture adjustment reminder will be issued.

2. A blood pressure measurement quality control device based on artificial intelligence image recognition, characterized in that, include: The identity recognition module is used to acquire the facial image information of the test subject for identity recognition. The feature extraction module is used to acquire images of the blood pressure measurement process of the subject after confirming the subject's identity information, and to extract posture feature information. The quality control module is used to determine whether the subject's posture during blood pressure measurement meets the quality control requirements based on the posture feature information; the quality control requirements include at least some body parts being positioned according to the posture requirements and some body parts being kept in an inactive state; The quality control requirements specify the placement of certain body parts according to posture requirements, including combinations of the following: the subject's back is pressed against the chair back, the subject's feet are flat on the ground, and the subject's palms are facing upwards. The quality control requirement that certain body parts remain inactive includes a combination of the following requirements: the subject's sitting posture remains inactive and the subject's mouth remains inactive; The methods for determining whether a test subject's sitting posture is maintained in an inactive state include a combination of the following requirements: (1) After obtaining the process images of the subject's blood pressure measurement, the posture feature information of all process images is extracted, and all extracted posture features are converted into vectors and compared pairwise to calculate the similarity between the vectors; if the similarity between any two posture features is lower than a preset threshold, it is determined that the subject failed to keep his sitting posture in an inactive state during the blood pressure measurement process. (2) After obtaining the process image of the subject's blood pressure measurement, set multiple key body feature points and track the coordinate changes of the key body feature points in real time; if the coordinate change of any of the key body feature points exceeds the preset threshold, it is determined that the subject failed to keep his sitting posture in an inactive state during the blood pressure measurement process. The methods for determining whether a subject's mouth remains inactive include a combination of the following requirements: (1) After obtaining the process images of the subject's blood pressure measurement, the posture feature information of all process images is extracted and the mouth position is determined; the mouth features of the subject in all process images are converted into vectors and compared pairwise to calculate the similarity between the vectors; if the similarity between any two mouth features is lower than the preset threshold, it is determined that the subject failed to keep his mouth still during the blood pressure measurement process. (2) After obtaining the process image of the subject's blood pressure measurement, set multiple mouth feature points and calculate the ratio of mouth width and length based on these mouth feature points; compare the changes in the ratio of mouth width and length of multiple frames of images, and if the changes are greater than a preset threshold, it is determined that the subject failed to keep his mouth still during the blood pressure measurement process. Massive amounts of blood pressure measurement data are matched with facial feature data, and the correlation between hypertension type and patient facial features is established based on the matching results; among which, hypertension type includes malignant hypertension and slow-onset hypertension; The method for determining whether the subject's back is close to the chair back includes: determining the position of the subject's back based on the posture feature information; and determining whether the subject's back is close to the chair back by the gap distance and contact area between the subject's back and the chair back. The method for determining whether the subject's feet are flat on the ground includes: determining the position of the subject's feet based on the posture feature information; and determining whether the subject's feet are flat on the ground by the gap distance and contact area between the subject's feet and the ground. The method for determining whether the palm of the subject's hand is facing upward includes: if fingerprint modal information, palm print modal information, or palm vein modal information are extracted from the posture feature information, then the palm is determined to be facing upward; The method for determining whether the palm of the subject's hand is facing upward includes: if nail modal information is extracted from the posture feature information, then the palm is determined to be facing downward; If the subject's posture during blood pressure measurement is determined to be inconsistent with quality control requirements, a real-time posture adjustment reminder will be issued.

3. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the blood pressure measurement quality control method based on artificial intelligence image recognition as described in claim 1.

4. A quality control terminal, characterized in that, include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory, so that the terminal performs the blood pressure measurement quality control method based on artificial intelligence image recognition as described in claim 1.

Images