Physiological index management method and management system

Abstract

The present invention discloses a physiological indicator management method and management system, wherein first physiological indicator information of a target object is obtained based on a first model, wherein the first physiological indicator information is used to indicate an abnormality of the first physiological indicator of the target object. Then, second physiological indicator information of the target object is obtained based on a second model, wherein the second physiological indicator information is used to indicate an abnormality of the second physiological indicator of the target object. The category of the target object is determined based on the first physiological indicator information and the second physiological indicator information. Finally, a physiological indicator management model is determined based on the category of the target object, and physiological indicator management information corresponding to the target object is obtained through the physiological indicator management model to complete the physiological indicator management of the target object, wherein the category and the physiological indicator management model have a corresponding relationship. It is possible to enable the target object to accurately and efficiently obtain its own corresponding physiological indicator management information.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a physiological index management method and management system. Background Art

[0002] With the development of society, the use of home medical devices is becoming more and more widespread. By using home medical devices, users can promptly know the measurement results of their corresponding physiological indicators, thereby improving the user's detection efficiency.

[0003] In related technologies, if a user wishes to seek further information on physiological indicator management based on measurement results, he or she needs to directly seek help from medical professionals, which greatly increases the user's health testing costs.

[0004] Based on the defects of the above-mentioned related technologies, there is an urgent need for a method that can accurately and efficiently manage physiological indicators so that users can obtain relevant information through automated means. Summary of the Invention

[0005] The main purpose of the present invention is to provide a physiological indicator management method and management system, aiming to enable users to obtain physiological indicator management information accurately and efficiently.

[0006] To achieve the above objectives, the present invention proposes a physiological index management method, which comprises:

[0007] Acquiring first physiological indicator information of the target object based on the first model, where the first physiological indicator information is used to indicate an abnormality of the first physiological indicator of the target object;

[0008] acquiring second physiological indicator information of the target object based on the second model, where the second physiological indicator information is used to indicate an abnormality of the second physiological indicator of the target object;

[0009] determining the category of the target object according to the first physiological indicator information and the second physiological indicator information;

[0010] A physiological indicator management model is determined based on the category of the target object, and physiological indicator management information corresponding to the target object is obtained through the physiological indicator management model to complete the physiological indicator management of the target object. The category has a corresponding relationship with the physiological indicator management model.

[0011] Optionally, before acquiring the second physiological indicator information of the target object based on the second model, the method further includes:

[0012] Identifying a target area of ​​the target object and acquiring a first video frame and a second video frame corresponding to the target area, wherein the first video frame is used to indicate an image corresponding to the target area at a current moment, and the second video frame is used to indicate an image corresponding to the target area at a target moment, where the target moment is a moment adjacent to the current moment;

[0013] determining a first color distribution of the target area based on the first video frame;

[0014] determining a second color distribution of the target area according to the first video frame and the second video frame;

[0015] Acquiring the second physiological indicator information of the target object based on the second model includes:

[0016] Based on the first color distribution, the second color distribution, the first video frame, and the second video frame, second physiological indicator information of the target object is obtained through the second model.

[0017] Optionally, acquiring second physiological indicator information of the target object through the second model based on the first color distribution, the second color distribution, the first video frame, and the second video frame includes:

[0018] Converting the first video frame and the second video frame into feature vectors respectively;

[0019] Acquiring historical second physiological indicator information of the target subject;

[0020] The second physiological indicator information of the target object is acquired through the second model according to the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information.

[0021] Optionally, acquiring the second physiological indicator information of the target object through the second model based on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information includes:

[0022] performing feature fusion on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information to obtain a first feature vector;

[0023] Performing feature extraction based on the first feature vector to obtain a second feature vector;

[0024] The second feature vectors obtained at different times are subjected to feature fusion by the second model to obtain second physiological indicator information of the target object.

[0025] Optionally, acquiring first physiological indicator information of the target object based on the first model includes:

[0026] Acquiring first data information of a first physiological indicator of the target object, where the first data information is used to indicate data information of the first physiological indicator obtained by the nth detection of the target object;

[0027] Acquire second data information of the historical first physiological indicator of the target object, where the second data information is used to indicate data information of the first physiological indicator obtained by the target object for the n-1th detection, where n>1;

[0028] Based on the first data information and the second data information, the first model determines first physiological indicator information of the target object.

[0029] Optionally, determining a physiological indicator management model based on the category of the target object, obtaining physiological indicator management information corresponding to the target object through the physiological indicator management model, and completing the physiological indicator management of the target object includes:

[0030] Obtaining the category of the target object;

[0031] Determining the physiological indicator management model corresponding to the target object based on the mapping relationship between the category and the physiological indicator management model;

[0032] The physiological indicator management information corresponding to the target object is obtained through the physiological indicator management model to complete the physiological indicator management of the target object.

[0033] Optionally, before determining the category of the target object according to the first physiological indicator information and the second physiological indicator information, the method further includes:

[0034] Acquiring target physiological indicator information of the target object, where the target physiological indicator information is used to indicate situation information of the target physiological indicator of the target object;

[0035] The determining the category of the target object according to the first physiological indicator information and the second physiological indicator information includes:

[0036] The category of the target object is determined according to the first physiological indicator information, the second physiological indicator information, and the target physiological indicator information.

[0037] The present invention also proposes a physiological index management system.

[0038] The system includes: a first acquisition module, a second acquisition module, a determination module, and a management module; the first acquisition module is used to acquire first physiological indicator information of a target object based on a first model, where the first physiological indicator information is used to indicate an abnormality of the first physiological indicator of the target object;

[0039] The second acquisition module is used to acquire second physiological indicator information of the target object based on the second model, where the second physiological indicator information is used to indicate an abnormality of the second physiological indicator of the target object;

[0040] The determining module is configured to determine the category of the target object based on the first physiological indicator information and the second physiological indicator information;

[0041] The management module is used to determine a physiological indicator management content acquisition model based on the category of the target object, obtain the information content of the physiological indicator management corresponding to the target object through the physiological indicator management content acquisition model, and complete the physiological indicator management of the target object. The category and the physiological indicator management content acquisition model have a corresponding relationship.

[0042] The present invention also provides a medical device, which includes a physiological indicator management device, a processor, a Wi-Fi module, and a camera.

[0043] The technical solution of the present invention employs a method of acquiring first physiological indicator information of a target object based on a first model, wherein the first physiological indicator information indicates an abnormality of the first physiological indicator of the target object. Then, based on a second model, acquiring second physiological indicator information of the target object, wherein the second physiological indicator information indicates an abnormality of the second physiological indicator of the target object. The target object's category is determined based on the first and second physiological indicator information. Finally, a physiological indicator management model is determined based on the target object's category, and physiological indicator management information corresponding to the target object is acquired using the physiological indicator management model to complete physiological indicator management of the target object. The category and the physiological indicator management model have a corresponding relationship. Thus, abnormalities of the first and second physiological indicators of the target object are acquired using the first and second models, and the category of the target object can be determined based on the abnormalities of each physiological indicator. Because the category and the physiological indicator management model have a corresponding relationship, the physiological indicator management model can be automatically matched and determined based on the determined target object category. Furthermore, the target object can obtain the corresponding physiological indicator management information by matching the determined physiological indicator management model, completing physiological indicator management. This entire process is automated, eliminating the need for manual intervention. The category of the target object is determined by the physiological indicator information of the target object, and the physiological indicator management model is matched for the target object based on the category, so that the physiological indicator management model can meet the personalized characteristics of the target object, thereby achieving accurate and efficient acquisition of the corresponding physiological indicator management information. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0045] Figure 1 A flowchart of a physiological indicator management method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic structural diagram of a second model provided by an embodiment of the present invention;

[0047] Figure 3 A schematic diagram of the structure of a physiological indicator management system provided by an embodiment of the present invention.

[0048] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] In addition, in the present invention, descriptions such as "first" and "second" are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0051] Research on related technologies has revealed that with the development of society, home medical devices are becoming increasingly popular. For example, products that measure physiological indicators such as blood pressure, blood sugar, uric acid, and electrocardiogram (ECG) have gradually entered thousands of households, allowing users to obtain timely measurement results of their corresponding physiological indicators. However, in related technologies, users can only obtain the measurement results of their physiological indicators based on home medical devices. When seeking further information on physiological indicator management based on the measurement results, this is impossible and they can only seek help from medical professionals.

[0052] Based on this, the present invention proposes a physiological indicator management method. This method eliminates manual effort and instead uses automation to automatically match and determine a physiological indicator management model based on the identified target subject's category. By matching the identified physiological indicator management model, the target subject can accurately and efficiently obtain its corresponding physiological indicator management information.

[0053] Reference Figures 1 to 3 , Figure 1 A flowchart of a physiological indicator management method provided by an embodiment of the present invention; Figure 2 A schematic structural diagram of a second model provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a physiological indicator management system provided by an embodiment of the present invention.

[0054] In an embodiment of the present invention, the physiological index management method provides an efficient and accurate way to obtain information on the physiological index management of a target object; Figure 1 As shown:

[0055] The technical solution of the present invention includes:

[0056] S11: Acquire first physiological indicator information of the target object based on the first model.

[0057] The target object refers to a user who has a need for physiological indicator management. The target object can be a user with normal physiological indicators or a user with abnormal physiological indicators. The first physiological indicator information is used to indicate the abnormality of the first physiological indicator of the target object. The first physiological indicator refers to a physiological indicator that can obtain data information through measurement. For example, the first physiological indicator can include but is not limited to blood pressure, blood sugar, uric acid, and blood lipids. In the embodiment of the invention, for the sake of convenience of description, the first physiological indicator is exemplarily determined as blood pressure. In actual applications, it can be replaced with blood sugar, uric acid, blood lipids, etc. according to different situations, and is not limited here.

[0058] The first model is used to indicate an abnormality in a first physiological indicator of the target subject. The abnormality may include: normal first physiological indicator and abnormal first physiological indicator. In an embodiment of the present invention, the first model may be a Long Short-Term Memory (LSTM) network model, which is a deep learning model commonly used to process sequence data. In this embodiment of the present invention, it is used to determine abnormal blood pressure of the user.

[0059] S12: Acquire second physiological indicator information of the target object based on the second model.

[0060] Second physiological indicator information is used to indicate abnormalities in a second physiological indicator of the target subject. This second physiological indicator is quantifiable data obtained through indirect measurement, but can, to a certain extent, reflect the target subject's health status. For example, this second physiological indicator can be the target subject's complexion. When this second physiological indicator is complexion, it can be determined by combining physiological indicators such as lip color and sweating. Corresponding second physiological indicator information may include, but is not limited to, good complexion, poor complexion, and poor complexion.

[0061] The second model is a feature extraction model, which needs to be pre-trained before being applied. The pre-training process can be: pre-setting training data and corresponding labels, inputting the training data and corresponding labels into the second model for supervised training until the second model training is completed. The training data is an image of a specific area of ​​the target object, such as a facial image. The label is the second physiological indicator information corresponding to the target object. For example, when the second physiological indicator is the complexion of the target object, the labels may include: good complexion, poor complexion, and bad complexion, etc. The label can be marked manually or automatically, which is not limited here.

[0062] S13: Determine the category of the target object according to the first physiological indicator information and the second physiological indicator information.

[0063] When the first physiological indicator is blood pressure, the corresponding first physiological indicator information can be normal blood pressure or abnormal blood pressure; when the second physiological indicator is complexion, the corresponding second physiological indicator information can be good complexion, poor complexion, or bad complexion. The user's category can be determined based on the first and second physiological indicator information of the target object.

[0064] It should be noted that the first physiological indicator information and the second physiological indicator information in the embodiment of the present application may include abnormal conditions of one or more physiological indicators, which is not limited here.

[0065] S14: Determine a physiological indicator management model based on the category of the target object, obtain physiological indicator management information corresponding to the target object through the physiological indicator management model, and complete the physiological indicator management of the target object.

[0066] There is a corresponding relationship between the category and the physiological indicator management model. The category can be determined based on the first physiological indicator information and the second physiological indicator information. It should be noted that in addition to the first physiological indicator information and the second physiological indicator information, the category of the target object can also be determined in combination with the target physiological indicator information. The target physiological indicator information may include but is not limited to: height, weight, and age.

[0067] When determining the target subject's category based on the first and second physiological indicator information, for example, if the first physiological indicator information indicates the target subject has abnormal blood pressure and the second physiological indicator information indicates the target subject has a poor complexion, the corresponding target subject category is (abnormal blood pressure, poor complexion). Based on the determined target subject category, a corresponding physiological indicator management model can be matched to the target subject.

[0068] The physiological indicator management model can be a question-and-answer model. Different target object categories correspond to different physiological indicator management models. Different physiological indicator management models have different knowledge graphs. Therefore, the physiological indicator management model corresponding to the target object has a strong correlation with its category, which facilitates the target object to obtain targeted and personalized physiological indicator management information from the physiological indicator management model, ultimately achieving physiological indicator management.

[0069] In this embodiment, a physiological indicator management method is proposed. The method first obtains first physiological indicator information of a target subject based on a first model, wherein the first physiological indicator information indicates an abnormality in the first physiological indicator of the target subject. Then, based on a second model, second physiological indicator information of the target subject is obtained, wherein the second physiological indicator information indicates an abnormality in the second physiological indicator of the target subject. The target subject's category is determined based on the first and second physiological indicator information. Finally, a physiological indicator management model is determined based on the target subject's category. Physiological indicator management information corresponding to the target subject is obtained using the physiological indicator management model, thereby completing physiological indicator management for the target subject. The category and the physiological indicator management model have a corresponding relationship. Thus, abnormalities in the first and second physiological indicators of the target subject are obtained using the first and second models, and the category of the target subject can be determined based on the abnormalities in each physiological indicator. Because the category and the physiological indicator management model have a corresponding relationship, matching and determining the physiological indicator management model based on the determined target subject category can be automated. Furthermore, the target subject can obtain the corresponding physiological indicator management information by matching the determined physiological indicator management model, thereby completing physiological indicator management. This entire process is automated, eliminating the need for manual intervention. The category of the target object is determined by the physiological indicator information of the target object, and the physiological indicator management model is matched for the target object based on the category, so that the physiological indicator management model can meet the personalized characteristics of the target object, thereby achieving accurate and efficient acquisition of the corresponding physiological indicator management information.

[0070] Optionally, the aforementioned S12 mentions “obtaining second physiological indicator information of the target object based on the second model”. In an embodiment of the present invention, a method for obtaining the second physiological indicator information is provided. The second physiological indicator information is exemplarily represented by an abnormality in the complexion state of the target object. Before obtaining the second physiological indicator information of the target object, two color distributions related to the target object need to be obtained. The specific obtaining method is as follows:

[0071] A1: Identify a target area of ​​the target object, and obtain a first video frame and a second video frame corresponding to the target area.

[0072] The target area refers to a portion of the target object that is relevant to determining the second physiological indicator. For example, when the second physiological indicator is the target object's complexion, the corresponding target area may be the target object's face. Identification of the target area can be accomplished using a camera, a camera, or other device with recognition capabilities.

[0073] The first video frame is used to indicate the image corresponding to the target area at the current moment, and the second video frame is used to indicate the image corresponding to the target area at the target moment, where the target moment is a moment adjacent to the current moment. That is, the first video frame and the second video frame are acquired continuously, and the first video frame and the second video frame are adjacent video frames. The images displayed in the first video frame and the second video frame are images of the target area acquired at adjacent moments. For example, if the first video frame is the image of the target area acquired at the 3rd second, the second video frame can be the image of the target area acquired at the 2nd second or the image of the target area acquired at the 4th second.

[0074] A2: Determine a first color distribution of the target area based on the first video frame.

[0075] The first color distribution of the target area of ​​the target object determined based on the first video frame refers to the color distribution determined based on the image corresponding to the target area of ​​the target object captured at the current moment. This first color distribution can be determined by dividing the captured image into multiple grids, calculating the color distribution of each grid, and using the statistical results as the first color distribution. This first color distribution can reflect the state of the target area of ​​the target object at the current moment.

[0076] Taking the target area as the facial area as an example, the first color distribution refers to the color distribution obtained by statistically analyzing the image of the facial area of ​​the target object at the current moment. The color distribution can reflect the complexion of the target object, which can be determined based on the lip color of the target object shown in the image.

[0077] A3: Determine a second color distribution of the target area according to the first video frame and the second video frame.

[0078] According to the previous description, the first video frame and the second video frame are images of the target area of ​​the target object acquired at adjacent moments, and the second color distribution of the target area is determined based on the first video frame and the second video frame. The reason why the second color distribution of the target area needs to be determined is that the second physiological indicator information of the target object is determined solely based on the first color distribution of the target area determined by the first video frame, which has a large degree of randomness and is easily affected by the environment. For example, due to a sudden change in the ambient light, the second physiological indicator information determined may be wrong. Therefore, when the first video frame and the second video frame at adjacent moments are combined to jointly determine the second color distribution, it can be combined with the first color distribution to eliminate the influence of accidental factors such as ambient light to a certain extent, and to a certain extent ensure the accuracy of the output result of the second model.

[0079] The second color distribution can be determined by dividing the images corresponding to the two adjacent video frames into a plurality of grids, calculating the color distribution of each grid, and using the statistical results as the second color distribution. The second color distribution can reflect the state of the target area of ​​the target object at adjacent moments, that is, the color distribution calculated by dividing the target area into the plurality of grids in the pixel difference images of the adjacent video frames.

[0080] It should be noted that the aforementioned steps A2 and A3 must be performed in full, and the two steps can be performed simultaneously.

[0081] After determining the first and second color distributions, the method for obtaining the second physiological indicator information may include obtaining the second physiological indicator information of the target subject using a second model based on the first and second color distributions, the first video frame, and the second video frame. Specifically, the second model determines the second physiological indicator information based on the two obtained color distributions and the two video frames.

[0082] Through the above-mentioned method for obtaining the second physiological indicator information, the first color distribution is determined based on the image of the target area obtained at the current moment, and the second color distribution is determined based on the image of the target area at the adjacent moment. Combining the first color distribution and the second color distribution can avoid errors in the environment at a single moment, eliminate interference caused by environmental factors, and improve the accuracy of the second physiological indicator information determined based on the first color distribution, the second color distribution and the corresponding two video frames.

[0083] The aforementioned method for obtaining the second physiological indicator information includes "obtaining the second physiological indicator information of the target object through a second model based on the first color distribution, the second color distribution, the first video frame, and the second video frame." In the embodiments provided by the present invention, this can be achieved by first converting the first video frame and the second video frame into feature vectors. Then, the historical second physiological indicator information of the target object is obtained. Finally, the second physiological indicator information of the target object is obtained through the second model based on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information.

[0084] The historical second physiological indicator information refers to the target subject's second physiological indicator information acquired before the current moment. If the second physiological indicator is the target subject's complexion, the second physiological indicator information is used to indicate abnormalities in the target subject's complexion. This historical second physiological indicator information may include, but is not limited to, good complexion, poor complexion, and poor complexion.

[0085] The first video frame and the second video frame are each converted into a feature vector. The two acquired feature vectors, the first color distribution, the second color distribution, and the historical second physiological indicator information of the target object are fed as input data into a second model, which then acquires the second physiological indicator information of the target object. It should be noted that the first video frame displays a grid diagram of the facial region of the original image, while the second video frame displays a grid diagram of the facial region of the pixel difference image. By processing each feature vector and the historical second physiological indicator information, the second model is able to acquire the second physiological indicator information of the target object.

[0086] Through the method of obtaining the second physiological indicator information provided above, the two color distributions and the two video frames are converted into feature vectors, and the historical second physiological indicator information of the target object is obtained. By converting into feature vectors, the second model can obtain the corresponding information, thereby improving the efficiency of determining the second physiological indicator information of the target object.

[0087] The aforementioned method for obtaining the second physiological indicator information mentions "obtaining the second physiological indicator information of the target object through the second model based on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information." In the embodiment provided by the present invention, the method for obtaining the second physiological indicator information can be: first, feature fusion is performed on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information to obtain a first feature vector. Feature extraction is then performed based on the first feature vector to obtain a second feature vector. Finally, the second feature vectors obtained at different times are feature fused by the second model to obtain the second physiological indicator information of the target object.

[0088] Specifically, the process is to fuse the acquired first color distribution, the second color distribution, the feature vector obtained from the facial grid map of the original image at the current moment corresponding to the first video frame, and the feature vector obtained from the facial grid map of the pixel difference image of the adjacent video frame corresponding to the second video frame with the acquired historical second physiological indicator information to obtain the first feature vector. The fusion process can be performed by a deep neural network (DNN). In an embodiment of the present invention, the fusion of each feature vector can be achieved through the DNN network.

[0089] After obtaining the first eigenvector, feature extraction is performed to obtain a second eigenvector. This second eigenvector contains feature information extracted from the first color distribution, the second color distribution, and the first and second video frames. The feature extraction process can be performed using an LSTM model. It should be noted that in embodiments of the present invention, an LSTM model can be used to record historical information, and the recorded historical second eigenvector can serve as a reference for subsequent feature extraction.

[0090] After obtaining the second eigenvector, the second eigenvectors obtained by feature extraction at different times are subjected to feature fusion, and the second physiological indicator information of the target object, that is, the complexion status of the target object, can be obtained by calculation based on the result of the feature fusion.

[0091] Feature fusion can be achieved through the DNN network, which also includes a sofmax layer. The sofmax layer can be used to calculate the fusion features of the second feature vectors at different times to obtain the complexion status of the target object at the current moment.

[0092] In this embodiment, the second eigenvectors at different times are fused because this eliminates the effects of lighting, such as sudden changes in lighting at a specific moment. Furthermore, multiple second eigenvectors provide more information, thereby ensuring the accuracy of the second physiological indicator information of the target subject determined based on the second eigenvectors.

[0093] Through the method for obtaining the second physiological indicator information provided above, a first feature vector is obtained after feature fusion of each feature vector combined with historical second physiological indicator information, and a second feature vector is obtained by feature extraction from the first feature vector. Feature fusion is performed on the second feature vectors at different moments to determine the second physiological indicator information of the target object. Since feature fusion is performed on the second feature vectors at different moments, more reference information is provided in the process of determining the second physiological indicator, while avoiding deviations caused by accidental events at a single moment, thereby improving the accuracy of determining the second physiological indicator information.

[0094] Figure 2 A schematic diagram of the structure of a second model provided by an embodiment of the present invention, see Figure 2As shown, two grid images are first acquired, representing the contents of the first and second video frames described above. The first and second video frames (i.e., the two grid images in the figure) are then fed into a convolutional neural network. After concatenation and flattening, a feature vector is obtained. The two statistical color distributions (i.e., the first and second color distributions described above), the feature vector corresponding to the first and second video frames, and the historical second physiological indicator information obtained by the memory unit are fed into a DNN network for fusion to obtain the first feature vector. The LSTM network then extracts features to obtain the second feature vector. The DNN then fuses the second feature vectors obtained by the LSTM network at different times, and calculates the second physiological indicator information of the target subject based on the fused features. The DNN, composed of multiple fully connected layers and sofmax layers, integrates the input signal information, while the LSTM network records historical information.

[0095] Optionally, regarding the aforementioned step S11 of “obtaining first physiological indicator information of the target subject based on the first model,” in embodiments of the present invention, the method for obtaining the first physiological indicator information may include: first obtaining first data information of the first physiological indicator of the target subject; then obtaining second data information of the target subject's historical first physiological indicator; and finally determining the first physiological indicator information of the target subject using the first model based on the first data information and the second data information.

[0096] The first data information is used to indicate data information of the first physiological indicator obtained by the target object during the n-th detection, and the second data information is used to indicate data information of the first physiological indicator obtained by the target object during the n-1-th detection, where n>1.

[0097] Therefore, the first physiological indicator information needs to be determined based on the data information of the first physiological indicator obtained from the current test of the target subject and the data information of the first physiological indicator obtained from the historical test. The first data information and the second data information obtained from the two tests can be used to determine whether the current test result of the target subject is abnormal compared to the historical test results.

[0098] For example, when the first physiological indicator is blood pressure, the first data information obtained for the target subject's first physiological indicator is the target subject's currently measured blood pressure information, and the second data information obtained for the target subject's historical first physiological indicator is the target subject's historically measured blood pressure information, which is the blood pressure information obtained during the target subject's last measurement. By comparing the first data information and the second data information, it is possible to determine whether the target subject's first physiological indicator information, i.e., blood pressure, is abnormal. The determination of abnormality can refer to medical standards. For example, according to the World Health Organization, hypertension is diagnosed in adults when a systolic blood pressure ≥140 mmHg, a diastolic blood pressure ≥90 mmHg, or only one of these conditions is met. A systolic blood pressure between 130 and 139 mmHg or a diastolic blood pressure between 85 and 89 mmHg is considered prehypertension. Therefore, the target subject's first physiological indicator information can be determined based on the obtained first data information and the second data information.

[0099] It should be noted that the various data information of the target object obtained in the embodiments of the present invention, including but not limited to the first data information, the second data information, the first video frame and the second video frame, etc., should be strictly in accordance with the requirements of relevant national laws and regulations when applied in examples, and the informed consent or separate consent of the personal information subject (such as the target object) should be obtained. Subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

[0100] The method for obtaining first physiological indicator information provided above enables the first model to determine the target subject's first physiological indicator information based on the acquired data of the target subject's first physiological indicator from two consecutive tests. By combining the two sets of data, it is possible to easily determine the changing trend of the target subject's first physiological indicator, which helps the first model more accurately determine the target subject's first physiological indicator information based on this changing trend, thereby improving the reliability of the first model's determination results to a certain extent.

[0101] The aforementioned S14 mentions "determining a physiological indicator management model based on the category of the target object, obtaining physiological indicator management information corresponding to the target object through the physiological indicator management model, and completing physiological indicator management of the target object." In an embodiment of the present invention, the method for completing physiological indicator management may be: first, obtaining the category of the target object; then, based on the mapping relationship between the category and the physiological indicator management model, determining the physiological indicator management model corresponding to the target object; finally, obtaining physiological indicator management information corresponding to the target object through the physiological indicator management model, and completing physiological indicator management of the target object.

[0102] The category of the target object mentioned above is determined based on the first physiological indicator information and the second physiological indicator information. When the first physiological indicator is blood pressure, the corresponding first physiological indicator information can be normal blood pressure or abnormal blood pressure, where abnormal blood pressure can include hypertension and pre-hypertension. When the second physiological indicator is complexion, the corresponding second physiological indicator information can be good complexion, poor complexion, and poor complexion. The category of the target object can be determined based on the determined first physiological indicator information and the second physiological indicator information. For example, when it is determined that the first physiological indicator information of the target object is abnormal blood pressure and the second physiological indicator information is poor complexion, the corresponding category of the target object is (abnormal blood pressure, poor complexion).

[0103] It should be noted that in the present invention, there is a correspondence between the target object category and the physiological indicator management model, that is, different target object categories correspond to different physiological indicator management models. The physiological indicator management model is a model used to manage the physiological indicators of the target object. The management method can be to determine the target object's physiological indicators based on the target object category and provide relevant suggestions or methods to improve the physiological indicators based on the physiological indicators.

[0104] The physiological indicator management model can be understood as a question-and-answer model or a medical consultation model. Different physiological indicator management models involve different knowledge graphs, which are strongly correlated with the target object's category. Thus, once the target object's category is determined, a physiological indicator management model that matches the target object's category can be determined based on the mapping relationship between the category and the physiological indicator management model. This physiological indicator management model can then be used to obtain the target object's corresponding physiological indicator management information, thus completing the target object's physiological indicator management.

[0105] It should be noted that in this embodiment, the mapping relationship between the target object category and the physiological indicator management model can be predetermined. The specific determination method can be through the establishment of an index table mapping method, the establishment of a database identifier retrieval method, or other methods that can achieve a one-to-one correspondence between the category and the physiological indicator management model, which are not limited here. The specific method for establishing the mapping relationship between the category and the physiological indicator management model can be determined by those skilled in the art based on actual circumstances.

[0106] The above-mentioned method for performing physiological indicator management determines the target subject's category and then, based on the mapping relationship between the category and the physiological indicator management model, determines a physiological indicator management model corresponding to the target subject's category. This allows the target subject to implement targeted, personalized physiological indicator management based on the physiological indicator management model. This helps improve the accuracy and relevance of the target subject's physiological indicator management, meets the target subject's usage needs, and enhances the target user's user experience and efficiency.

[0107] When determining the category of the target object, it is mentioned above that "the category of the target object is determined based on the first physiological indicator information and the second physiological indicator information". In one possible implementation method, in addition to the first physiological indicator information and the second physiological indicator information, the target physiological indicator information can also be combined to jointly determine the category of the target object. The combination of multiple physiological indicator information makes the physiological indicator situation of the target object richer, which is conducive to subsequently matching it with a more accurate physiological indicator management model.

[0108] Therefore, before "determining the category of the target object based on the first physiological indicator information and the second physiological indicator information", the target physiological indicator information of the target object can be obtained, and then the category of the target object can be determined based on the first physiological indicator information, the second physiological indicator information and the target physiological indicator information.

[0109] The target physiological indicator information is used to indicate the target physiological indicator status information of the target subject. The target physiological indicator may include, but is not limited to, age, height, weight, and gender. For example, when the target physiological indicator is age, the corresponding target physiological indicator information may include: under 40 years old, over 55 years old, and 40-55 years old; when the target physiological indicator is gender, the corresponding target physiological indicator information may include: male and female. The degree of obesity can be determined based on height and weight. The specific determination method can refer to the current height-weight standards and will not be repeated here. The corresponding target physiological indicator information may include: obese, normal, and thin.

[0110] Through the method for determining the category of the target object provided above, in addition to the first physiological indicator information and the second physiological indicator information, the target physiological indicator information is added to jointly determine the category of the target object, which can make the category of the target object more diverse and more accurate. In this way, the physiological indicator management model determined based on the category of the target object can be more in line with the physiological indicator information of the target object, thereby improving the accuracy and relevance of the physiological indicator management of the target object.

[0111] The present invention also proposes a physiological index management system. Figure 3A schematic structural diagram of a physiological indicator management system provided by an embodiment of the present invention, the physiological indicator management system includes an acquisition module 100, a second acquisition module 200, a determination module 300 and a management module 400;

[0112] The first acquisition module 100 is configured to acquire first physiological indicator information of a target object based on a first model, where the first physiological indicator information is used to indicate an abnormality of the first physiological indicator of the target object;

[0113] The second acquisition module 200 is used to acquire second physiological indicator information of the target object based on the second model, where the second physiological indicator information is used to indicate an abnormality of the second physiological indicator of the target object;

[0114] The determination module 300 is configured to determine the category of the target object based on the first physiological indicator information and the second physiological indicator information;

[0115] The management module 400 is used to determine a physiological indicator management content acquisition model based on the category of the target object, obtain the information content of the physiological indicator management corresponding to the target object through the physiological indicator management content acquisition model, and complete the physiological indicator management of the target object. The category and the physiological indicator management content acquisition model have a corresponding relationship.

[0116] In a possible implementation, the first acquisition module 100 is configured to:

[0117] Acquiring first data information of a first physiological indicator of the target object, where the first data information is used to indicate data information of the first physiological indicator obtained by the nth detection of the target object;

[0118] Acquire second data information of the historical first physiological indicator of the target object, where the second data information is used to indicate data information of the first physiological indicator obtained by the target object for the n-1th detection, where n>1;

[0119] Based on the first data information and the second data information, the first model determines first physiological indicator information of the target object.

[0120] In a possible implementation, the system includes a color distribution determination module, wherein the color distribution determination module is configured to:

[0121] Identifying a target area of ​​the target object and acquiring a first video frame and a second video frame corresponding to the target area, wherein the first video frame is used to indicate an image corresponding to the target area at a current moment, and the second video frame is used to indicate an image corresponding to the target area at a target moment, where the target moment is a moment adjacent to the current moment;

[0122] determining a first color distribution of the target area based on the first video frame;

[0123] determining a second color distribution of the target area according to the first video frame and the second video frame;

[0124] The second acquisition module 200 is configured to:

[0125] Based on the first color distribution, the second color distribution, the first video frame, and the second video frame, second physiological indicator information of the target object is obtained through the second model.

[0126] In a possible implementation, the second acquisition module 200 is configured to:

[0127] Converting the first video frame and the second video frame into feature vectors respectively;

[0128] Acquiring historical second physiological indicator information of the target subject;

[0129] The second physiological indicator information of the target object is acquired through the second model according to the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information.

[0130] In a possible implementation, the second acquisition module 200 is configured to:

[0131] performing feature fusion on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information to obtain a first feature vector;

[0132] Performing feature extraction based on the first feature vector to obtain a second feature vector;

[0133] The second feature vectors obtained at different times are subjected to feature fusion by the second model to obtain second physiological indicator information of the target object.

[0134] In one possible implementation, the management module 400 is configured to:

[0135] Obtaining the category of the target object;

[0136] Determining the physiological indicator management model corresponding to the target object based on the mapping relationship between the category and the physiological indicator management model;

[0137] The physiological indicator management information corresponding to the target object is obtained through the physiological indicator management model to complete the physiological indicator management of the target object.

[0138] In a possible implementation, the system further includes an indicator acquisition module, wherein the indicator acquisition module is configured to:

[0139] Acquiring target physiological indicator information of the target object, where the target physiological indicator information is used to indicate situation information of the target physiological indicator of the target object;

[0140] The determining module 300 is configured to:

[0141] The category of the target object is determined according to the first physiological indicator information, the second physiological indicator information, and the target physiological indicator information.

[0142] An embodiment of the present invention provides a physiological indicator management system, comprising: a first acquisition module, a second acquisition module, a determination module, and a management module. The first acquisition module is configured to acquire first physiological indicator information of a target object based on a first model, the first physiological indicator information being used to indicate an abnormality in the first physiological indicator of the target object; the second acquisition module is configured to acquire second physiological indicator information of the target object based on a second model, the second physiological indicator information being used to indicate an abnormality in the second physiological indicator of the target object; the determination module is configured to determine the category of the target object based on the first and second physiological indicator information; and the management module is configured to determine a physiological indicator management content acquisition model based on the category of the target object, and to acquire physiological indicator management information corresponding to the target object using the physiological indicator management content acquisition model to complete physiological indicator management of the target object. The category and the physiological indicator management content acquisition model have a corresponding relationship. Thus, abnormalities in the first and second physiological indicators of the target object are acquired using the first and second models, and the category of the target object can be determined based on the abnormalities in each physiological indicator. Because the category and the physiological indicator management model have a corresponding relationship, matching and determination of the physiological indicator management model can be automatically completed based on the determined category of the target object. Furthermore, the target subject can obtain the corresponding physiological indicator management information by matching the determined physiological indicator management model, thus completing physiological indicator management. The entire process does not rely on manual methods, but is carried out in an automated manner. The target subject's category is determined based on the target subject's physiological indicator information, and the physiological indicator management model is matched to the target subject based on the category. This physiological indicator management model can be adapted to the target subject's individual characteristics, thereby enabling accurate and efficient acquisition of the target subject's corresponding physiological indicator management information.

[0143] An embodiment of the present invention also provides a medical device, which includes the aforementioned physiological indicator management device, processor, wifi module and camera. The processor and wifi module are used to obtain first data information of a first physiological indicator and input the first data information into the physiological indicator management device, and the camera is used to identify the target area of ​​the target object. In one possible implementation, the medical device may also include a cuff for detecting blood pressure and a device for detecting other physiological indicators, which are not limited here. In one possible implementation, the medical device may also include a microphone and a speaker for real-time communication with the target object. The display screen can be set, but it is not set when the display function of the display screen affects the acquisition of data information of the target object.

[0144] The embodiments of the present application also provide corresponding devices and computer-readable storage media for implementing the solutions provided by the embodiments of the present application.

[0145] The device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes a key technology identification method described in any embodiment of the present application.

[0146] In practical applications, the computer-readable storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0147] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0148] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0149] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0150] The above descriptions are merely optional embodiments of the present invention and do not limit the patent scope of the present invention. All equivalent structural transformations made using the contents of the present description and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. A physiological index management method, characterized in that: include Acquiring first physiological indicator information of the target object based on the first model, where the first physiological indicator information is used to indicate an abnormality of the first physiological indicator of the target object, and the first physiological indicator is a physiological indicator from which data information is obtained by measurement; Acquiring second physiological indicator information of the target object based on the second model, where the second physiological indicator information is used to indicate an abnormality of the second physiological indicator of the target object, where the second physiological indicator is quantifiable data obtained by indirect measurement; determining the category of the target object according to the first physiological indicator information and the second physiological indicator information; Determine a physiological indicator management model based on the category of the target object, obtain physiological indicator management information corresponding to the target object through the physiological indicator management model, and complete the physiological indicator management of the target object, wherein the category has a corresponding relationship with the physiological indicator management model; Before acquiring the second physiological indicator information of the target object based on the second model, the method further includes: Identifying a target area of ​​the target object and acquiring a first video frame and a second video frame corresponding to the target area, wherein the first video frame is used to indicate an image corresponding to the target area at a current moment, and the second video frame is used to indicate an image corresponding to the target area at a target moment, where the target moment is a moment adjacent to the current moment; determining a first color distribution of the target area based on the first video frame; determining a second color distribution of the target area according to the first video frame and the second video frame; Acquiring the second physiological indicator information of the target object based on the second model includes: Based on the first color distribution, the second color distribution, the first video frame, and the second video frame, second physiological indicator information of the target object is obtained through the second model.

2. The physiological index management method according to claim 1, characterized in that: The acquiring second physiological indicator information of the target object by using the second model based on the first color distribution, the second color distribution, the first video frame, and the second video frame includes: Converting the first video frame and the second video frame into feature vectors respectively; Acquiring historical second physiological indicator information of the target subject; The second physiological indicator information of the target object is acquired through the second model according to the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information.

3. The physiological index management method according to claim 2, characterized in that: The acquiring, by the second model, the second physiological indicator information of the target object based on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information includes: performing feature fusion on the first color distribution, the second color distribution, the feature vector corresponding to the first video frame, the feature vector corresponding to the second video frame, and the historical second physiological indicator information to obtain a first feature vector; Performing feature extraction based on the first feature vector to obtain a second feature vector; The second feature vectors obtained at different times are subjected to feature fusion by the second model to obtain second physiological indicator information of the target object.

4. The physiological index management method according to claim 1, wherein: The acquiring first physiological indicator information of the target object based on the first model includes: Acquiring first data information of a first physiological indicator of the target object, where the first data information is used to indicate data information of the first physiological indicator obtained by the nth detection of the target object; Acquire second data information of the historical first physiological indicator of the target object, where the second data information is used to indicate data information of the first physiological indicator obtained by the target object for the n-1th detection, where n>1; Based on the first data information and the second data information, the first model determines first physiological indicator information of the target object.

5. The physiological index management method according to claim 1, wherein: The step of determining a physiological indicator management model based on the category of the target object, obtaining physiological indicator management information corresponding to the target object through the physiological indicator management model, and completing the physiological indicator management of the target object includes: Obtaining the category of the target object; Determining the physiological indicator management model corresponding to the target object based on the mapping relationship between the category and the physiological indicator management model; The physiological indicator management information corresponding to the target object is obtained through the physiological indicator management model to complete the physiological indicator management of the target object.

6. The physiological index management method according to claim 1, wherein: Before determining the category of the target object according to the first physiological indicator information and the second physiological indicator information, the method further includes: Acquiring target physiological indicator information of the target object, where the target physiological indicator information is used to indicate situation information of the target physiological indicator of the target object; The determining the category of the target object according to the first physiological indicator information and the second physiological indicator information includes: The category of the target object is determined according to the first physiological indicator information, the second physiological indicator information, and the target physiological indicator information.

7. A physiological index management system, characterized in that: The system includes: a first acquisition module, a second acquisition module, a determination module, and a management module; The first acquisition module is configured to acquire first physiological indicator information of the target object based on the first model, wherein the first physiological indicator information is used to indicate an abnormality of the first physiological indicator of the target object, and the first physiological indicator is a physiological indicator of which data information is obtained by measurement; The second acquisition module is configured to acquire second physiological indicator information of the target object based on the second model, where the second physiological indicator information is used to indicate an abnormality of the second physiological indicator of the target object, and the second physiological indicator is quantifiable data obtained by indirect measurement; The determining module is configured to determine the category of the target object based on the first physiological indicator information and the second physiological indicator information; The management module is configured to determine a physiological indicator management model based on the category of the target object, obtain information content of physiological indicator management corresponding to the target object through the physiological indicator management model, and complete the physiological indicator management of the target object, wherein the category and the physiological indicator management model have a corresponding relationship; Before acquiring the second physiological indicator information of the target object based on the second model, the method further includes: Identifying a target area of ​​the target object and acquiring a first video frame and a second video frame corresponding to the target area, wherein the first video frame is used to indicate an image corresponding to the target area at a current moment, and the second video frame is used to indicate an image corresponding to the target area at a target moment, where the target moment is a moment adjacent to the current moment; determining a first color distribution of the target area based on the first video frame; determining a second color distribution of the target area according to the first video frame and the second video frame; Acquiring the second physiological indicator information of the target object based on the second model includes: Based on the first color distribution, the second color distribution, the first video frame, and the second video frame, second physiological indicator information of the target object is obtained through the second model.

8. A medical device, characterized in that The device includes the physiological indicator management system as claimed in claim 7, a processor, a Wi-Fi module and a camera.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an implementation program for implementing the physiological indicator management method. When the implementation program for implementing the physiological indicator management method is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images