Physiological index management method and system

Abstract

The invention discloses a physiological index management method and system, and the method comprises the steps: obtaining the first physiological index information of a target object based on a first model, and enabling the first physiological index information to be used for indicating the abnormal condition of a first physiological index of the target object; and second physiological index information of the target object is obtained based on a second model, wherein the second physiological index information is used for indicating the abnormal condition of a second physiological index of the target object. And determining the category of the target object according to the first physiological index information and the second physiological index information. Finally, a physiological index management model is determined based on the category of the target object, physiological index management information corresponding to the target object is obtained through the physiological index management model, physiological index management of the target object is completed, and the category and the physiological index management model have a corresponding relation. The target object can accurately and efficiently acquire own corresponding physiological index management information.

Description

Technical Field

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

[0002] With the development of society, the use of current household medical devices has become increasingly widespread. By using household medical devices, users can timely obtain the measurement results of their corresponding physiological indexes, improving the detection efficiency of users.

[0003] In the related art, when a user expects to seek further information on physiological index management based on the measurement results, they need to directly seek help from medical professionals, greatly increasing the user's health detection cost.

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

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

[0006] To achieve the above object, the physiological index management method proposed by the present invention includes: Obtaining first physiological index information of a target object based on a first model, where the first physiological index information is used to indicate the abnormal situation of the first physiological index of the target object; Obtaining second physiological index information of the target object based on a second model, where the second physiological index information is used to indicate the abnormal situation of the second physiological index of the target object; Determining the category of the target object according to the first physiological index information and the second physiological index information; Determining a physiological index management model based on the category of the target object, and obtaining information on physiological index management corresponding to the target object through the physiological index management model to complete the physiological index management of the target object, where there is a corresponding relationship between the category and the physiological index management model.

[0007] Optionally, before obtaining the second physiological index information of the target object based on the second model, the method further includes: Identifying the target area of the target object, and obtaining a first video frame and a second video frame corresponding to the target area, where 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, and the target moment is an adjacent moment of the current moment; Determine the first color distribution of the target area based on the first video frame; Determine the second color distribution of the target area according to the first video frame and the second video frame; The obtaining the second physiological index 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, obtain the second physiological index information of the target object through the second model.

[0008] Optionally, the obtaining the second physiological index information of the target object based on the first color distribution, the second color distribution, the first video frame, and the second video frame, through the second model includes: Convert the first video frame and the second video frame into feature vectors respectively; Obtain the historical second physiological index information of the target object; 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 index information, obtain the second physiological index information of the target object through the second model.

[0009] Optionally, the obtaining the second physiological index information of the target object 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 index information, through the second model includes: Perform 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 index information to obtain a first feature vector; Perform feature extraction based on the first feature vector to obtain a second feature vector; Fuse the second feature vectors obtained at different times by the second model to obtain the second physiological index information of the target object.

[0010] Optionally, the obtaining the first physiological index information of the target object based on the first model includes: Obtain the first data information of the first physiological index of the target object, where the first data information is used to indicate the data information of the first physiological index obtained by the target object in the nth detection; Obtain the second data information of the historical first physiological index of the target object, where the second data information is used to indicate the data information of the first physiological index obtained by the target object in the (n - 1)-th detection, where n > 1; Based on the first data information and the second data information, the first physiological index information of the target object is determined by the first model.

[0011] Optionally, the determining the physiological index management model based on the category of the target object, obtaining the information on the physiological index management corresponding to the target object through the physiological index management model, and completing the physiological index management of the target object includes: Obtain the category of the target object; Based on the mapping relationship between the category and the physiological index management model, determine the physiological index management model corresponding to the target object; Obtain the information on the physiological index management corresponding to the target object through the physiological index management model, and complete the physiological index management of the target object.

[0012] Optionally, before determining the category of the target object according to the first physiological index information and the second physiological index information, the method further includes: Obtain the target physiological index information of the target object, where the target physiological index information is used to indicate the situation information of the target physiological index of the target object; The determining the category of the target object according to the first physiological index information and the second physiological index information includes: Determine the category of the target object according to the first physiological index information, the second physiological index information, and the target physiological index information.

[0013] The present invention also proposes a physiological index management system, 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 obtain the first physiological index information of the target object based on the first model, where the first physiological index information is used to indicate the abnormal situation of the first physiological index of the target object; The second acquisition module is used to obtain the second physiological index information of the target object based on the second model, where the second physiological index information is used to indicate the abnormal situation of the second physiological index of the target object; The determination module is used to determine the category of the target object according to the first physiological index information and the second physiological index information; The management module is used to determine a physiological index management content acquisition model based on the category of the target object, obtain the information content of the physiological index management corresponding to the target object through the physiological index management content acquisition model, and complete the physiological index management of the target object. There is a corresponding relationship between the category and the physiological index management content acquisition model.

[0014] The present invention also provides a medical device, which includes a physiological index management device, a processor, a wifi module, and a camera.

[0015] The technical solution of the present invention is to obtain the first physiological index information of the target object based on the first model, where the first physiological index information is used to indicate the abnormal situation of the first physiological index of the target object. Then, the second physiological index information of the target object is obtained based on the second model, where the second physiological index information is used to indicate the abnormal situation of the second physiological index of the target object. The category of the target object is determined according to the first physiological index information and the second physiological index information. Finally, a physiological index management model is determined based on the category of the target object, and the information of the physiological index management corresponding to the target object is obtained through the physiological index management model, so as to complete the physiological index management of the target object. There is a corresponding relationship between the category and the physiological index management model. In this way, the abnormal situations of the first physiological index and the second physiological index of the target object are obtained through the first model and the second model, and the category of the target object can be determined by combining the abnormal situations of each physiological index. Since there is a corresponding relationship between the category and the physiological index management model, the matching determination of the physiological index management model can be automatically completed according to the determined category of the target object. Furthermore, the target object can obtain the corresponding information of the physiological index management through the matched physiological index management model, so as to complete the physiological index management. The whole process does not rely on manual methods, but is carried out in an automated way. And the category of the target object is determined according to the situation of the physiological index information of the target object, and the physiological index management model is matched for the target object in combination with the category, so that the physiological index management model can conform to the personalized characteristics of the target object, and thus it can accurately and efficiently obtain the information of the physiological index management corresponding to itself. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the structures shown in these drawings without creative efforts.

[0017] Figure 1 It is a flowchart of a physiological index management method provided by an embodiment of the present invention; Figure 2 Schematic structural diagram of a second model provided by an embodiment of the present invention; Figure 3 Schematic structural diagram of a physiological index management system provided by an embodiment of the present invention.

[0018] The implementation, functional characteristics and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0020] In addition, in the present invention, descriptions such as "first" and "second" are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between various embodiments may be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions appears to be contradictory or unable to be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0021] In the research on related technologies, it is found that with the development of society, current household medical devices are becoming more and more popular. For example, products for measuring physiological indexes such as blood pressure, blood sugar, uric acid, and electrocardiogram have gradually entered thousands of households, enabling users to timely obtain the measurement results of their corresponding physiological indexes. However, in related technologies, users can only obtain the measurement results of physiological indexes based on household medical devices. When they expect to seek further information on physiological index management according to the measurement results, they cannot achieve it and can only seek help from medical professionals.

[0022] Based on this, the present invention proposes a physiological index management method. It can be carried out in an automated manner without relying on manual methods, and the matching determination of the physiological index management model is automatically completed according to the determined category of the target object. The target object can accurately and efficiently obtain the information on its corresponding physiological index management through the matched physiological index management model.

[0023] Refer to Figures 1 to 3 , Figure 1 Flowchart of a physiological index management method provided by an embodiment of the present invention;Figure 2 Schematic diagram of a second model provided by an embodiment of the present invention; Figure 3 Schematic diagram of a physiological index management system provided by an embodiment of the present invention.

[0024] In the 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; as Figure 1 shown: The technical solution of the present invention includes: S11: Obtain the first physiological index information of the target object based on the first model.

[0025] The target object refers to a user with a need for physiological index management. The target object can be a user with normal physiological indexes or a user with abnormal physiological indexes. The first physiological index information is used to indicate the abnormal situation of the first physiological index of the target object. The first physiological index refers to a physiological index that can obtain data information through measurement. For example, the first physiological index may include but is not limited to blood pressure, blood sugar, uric acid, and blood lipid, etc. In the embodiment of the invention, for the convenience of description, the first physiological index is exemplarily determined as blood pressure. In actual applications, it can be replaced with blood sugar, uric acid, and blood lipid, etc. according to different situations, which is not limited herein.

[0026] The first model is used to indicate the abnormal situation of the first physiological index of the target object. The abnormal situation may include: the first physiological index is normal and the first physiological index is abnormal. In the embodiment of the present invention, the first model can be a Long Short-Term Memory (LSTM) network model, which is a deep learning model commonly used to process sequence data and is used to determine the abnormal situation of the user's blood pressure in the embodiment of the present invention.

[0027] S12: Obtain the second physiological index information of the target object based on the second model.

[0028] The second physiological index information is used to indicate the abnormal situation of the second physiological index of the target object. The second physiological index is quantifiable data that is not directly measured, but can reflect the health status of the target object to a certain extent. For example, the second physiological index can be the complexion state of the target object. When the second physiological index is the complexion state, it can be comprehensively determined by combining physiological indexes such as lip color and sweating volume. The corresponding second physiological index information may include but is not limited to: good complexion, poor complexion, and very poor complexion.

[0029] The second model is a feature extraction model that needs to be pre-trained before application. The pre-training process can be as follows: pre-set training data and corresponding labels, and input the training data and corresponding labels into the second model for supervised training until the second model is trained. The training data is an image of a specific area of the target object, such as a face image. The label is the second physiological index information corresponding to the target object. For example, when the second physiological index is the complexion state of the target object, the labels can include: good complexion, poor complexion, and very poor complexion. The labels can be marked manually or automatically, and no limitation is made here.

[0030] S13: Determine the category of the target object according to the first physiological index information and the second physiological index information.

[0031] When the first physiological index is blood pressure, the corresponding first physiological index information can be normal blood pressure and abnormal blood pressure; when the second physiological index is complexion state, the corresponding second physiological index information can be good complexion, poor complexion, or very poor complexion. The category of the user can be determined according to the first physiological index information and the second physiological index information of the target object.

[0032] It should be noted that both the first physiological index information and the second physiological index information in the embodiments of the present application can include the abnormal conditions of one or more physiological indexes, and no limitation is made here.

[0033] S14: Determine a physiological index management model based on the category of the target object, and obtain the physiological index management information corresponding to the target object through the physiological index management model to complete the physiological index management of the target object.

[0034] There is a corresponding relationship between the category and the physiological index management model. The category can be determined according to the first physiological index information and the second physiological index information. It should be noted that in addition to the first physiological index information and the second physiological index information, the target physiological index information can also be combined to jointly determine the category of the target object. The target physiological index information can include but is not limited to: height, weight, and age, etc.

[0035] When determining the category of the target object based on the first physiological index information and the second physiological index information, for example, assume that the first physiological index information shows that the blood pressure of the target object is abnormal, and the second physiological index information shows that the complexion state of the target object is poor. At this time, the corresponding category of the target object is (abnormal blood pressure, poor complexion state). The corresponding physiological index management model can be matched according to the determined category of the target object.

[0036] The physiological index management model can be a question-and-answer model, and the physiological index management models corresponding to different categories of target objects are different. Different physiological index management models have different knowledge graphs. Therefore, the physiological index management model corresponding to the target object has a strong correlation with its category, which is convenient for the target object to obtain targeted and personalized physiological index management information from the physiological index management model, and finally realize physiological index management.

[0037] In this embodiment, a physiological index management method is proposed. The method first obtains the first physiological index information of the target object based on the first model, where the first physiological index information is used to indicate the abnormal condition of the first physiological index of the target object. Then, the second physiological index information of the target object is obtained based on the second model, where the second physiological index information is used to indicate the abnormal condition of the second physiological index of the target object. The category of the target object is determined according to the first physiological index information and the second physiological index information. Finally, the physiological index management model is determined based on the category of the target object, and the physiological index management information corresponding to the target object is obtained through the physiological index management model, and the physiological index management of the target object is completed, where there is a corresponding relationship between the category and the physiological index management model. In this way, the abnormal conditions of the first physiological index and the second physiological index of the target object are obtained through the first model and the second model, and the category of the target object can be determined by combining the abnormal conditions of each physiological index. Since there is a corresponding relationship between the category and the physiological index management model, the matching determination of the physiological index management model can be automatically completed according to the determined category of the target object. Furthermore, the target object can obtain the corresponding physiological index management information through the matched physiological index management model to complete the physiological index management. The whole process does not rely on manual methods, but is carried out in an automated manner. And the category of the target object is determined based on the situation of the physiological index information of the target object, and the physiological index management model is matched for the target object in combination with the category, so that the physiological index management model can conform to the personalized characteristics of the target object, and thus can accurately and efficiently obtain the physiological index management information corresponding to itself.

[0038] Optionally, in step S12 mentioned above, "obtaining the second physiological index information of the target object based on the second model", in the embodiment of the present invention, a method for obtaining the second physiological index information is provided. The second physiological index information is exemplarily represented as the abnormal condition of the complexion state of the target object. Before obtaining the second physiological index information of the target object, two color distributions related to the target object need to be obtained. The specific obtaining method is as follows: A1: Identify the target area of the target object and obtain the first video frame and the second video frame corresponding to the target area.

[0039] The target area refers to a partial area of the target object related to determining the second physiological index. For example, when the second physiological index is the complexion state of the target object, the corresponding target area can be the facial area of the target object. The identification of the target area can be completed by devices such as cameras, cameras, or other devices with identification functions.

[0040] Among them, 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 an adjacent moment to the current moment. That is, the first video frame and the second video frame are continuously acquired, the first video frame and the second video frame are adjacent video frames to each other, and 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 an image of the target area acquired at the 3rd second, then the second video frame can be an image of the target area acquired at the 2nd second or an image of the target area acquired at the 4th second.

[0041] A2: Determine the first color distribution of the target area based on the first video frame.

[0042] The first color distribution of the target area of the target object determined according to the first video frame refers to the color distribution determined according to the image corresponding to the target area of the target object acquired at the current moment. The determination of this first color distribution can be: dividing the acquired image into multiple grids, counting the color distribution of each grid, and taking the statistical result 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.

[0043] Taking the target area as the facial area as an example, this first color distribution refers to the color distribution obtained by counting the image of the facial area of the target object acquired at the current moment. This color distribution can reflect the complexion state of the target object, and this complexion state can be determined according to the lip color of the target object shown in the image, etc.

[0044] A3: Determine the second color distribution of the target area according to the first video frame and the second video frame.

[0045] As can be seen from the previous description, the first video frame and the second video frame are images of the target area of the target object obtained at adjacent times. Based on the first video frame and the second video frame, the second color distribution of the target area is determined. The reason for determining the second color distribution of the target area is that it has a large randomness to determine the second physiological index information of the target object based only on the first color distribution of the target area determined from the first video frame, and it is extremely vulnerable to the influence of the environment. For example, because the environmental lighting suddenly changes, the determined second physiological index information is prone to errors. Therefore, when combining the first video frame and the second video frame at adjacent times to jointly determine the second color distribution, it can combine the first color distribution and exclude the influence of accidental factors such as environmental lighting to a certain extent, and ensure the accuracy of the output result of the second model to a certain extent.

[0046] The determination of the second color distribution can be as follows: divide the images corresponding to two adjacent video frames obtained into multiple grids, count the color distribution of each grid, and use the statistical result as the second color distribution. The second color distribution can reflect the state of the target area of the target object at adjacent times, that is, the pixel difference image of adjacent video frames. After dividing the target area into multiple grids, the counted color distribution.

[0047] It should be noted that the aforementioned steps A2 and A3 must all be carried out, and the two steps can be carried out simultaneously.

[0048] After the determination of the first color distribution and the second color distribution is completed, the method for obtaining the second physiological index information can be: based on the first color distribution, the second color distribution, the first video frame, and the second video frame, obtain the second physiological index information of the target object through the second model. That is, combining the two obtained color distributions and the situation of the two video frames, the second index information is determined by the second model.

[0049] Through the above-provided method for obtaining the second physiological index information, the first color distribution is determined based on the image of the target area obtained at the current time, the second color distribution is determined based on the image of the target area at adjacent times, and the first color distribution and the second color distribution are combined, which can avoid the errors of the environment at a single time, exclude the interference caused by environmental factors, and improve the accuracy of the second physiological index information determined based on the first color distribution, the second color distribution, and the corresponding two video frames.

[0050] The aforementioned method for obtaining the second physiological index information includes "obtaining the second physiological index 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, it can be implemented in the following manner: First, convert the first video frame and the second video frame into feature vectors respectively. Then, obtain the historical second physiological index information of the target object. Finally, 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 index information, obtain the second physiological index information of the target object through the second model.

[0051] Among them, the historical second physiological index information refers to the second physiological index information of the target object obtained before the current moment. When the second physiological index is the complexion state of the target object, this second physiological index information is used to indicate the abnormal conditions of the complexion state of the target object. That is, the historical second physiological index information may include, but is not limited to: good complexion, poor complexion, and very poor complexion.

[0052] Convert the first video frame and the second video frame into feature vectors respectively, and use the two obtained feature vectors, the first color distribution, the second color distribution, and the historical second physiological index information of the target object as input data and send them into the second model, and the second model obtains the second physiological index information of the target object. It should be noted that the first video frame shows a grid map of the face area of the original image, and the second video frame shows a grid map of the face area of the pixel difference image. Through the processing of each feature vector and the historical second physiological index information, the second model can obtain the second physiological index information of the target object.

[0053] Through the above-provided method for obtaining the second physiological index information, two color distributions and two video frames are converted into feature vectors, and the historical second physiological index information of the target object is obtained. By converting them into feature vectors, it is convenient for the second model to obtain the corresponding information and improve the efficiency of determining the second physiological index information of the target object.

[0054] In the method for obtaining the second physiological index information mentioned above, it is stated that "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 index information, the second physiological index information of the target object is obtained through the second model". In the embodiments provided by the present invention, the method for obtaining the second physiological index information may be as follows: 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 index information to obtain a first feature vector. Then, feature extraction is performed based on the first feature vector to obtain a second feature vector. Finally, the second feature vectors obtained at different times are subjected to feature fusion by the second model to obtain the second physiological index information of the target object.

[0055] Specifically, this process is to fuse the obtained first color distribution, the second color distribution, the feature vector obtained from the original image face mesh map at the current moment corresponding to the first video frame, and the feature vector obtained from the pixel difference image face mesh map of the adjacent video frame corresponding to the second video frame with the obtained historical second physiological index information to obtain a first feature vector. The fusion process can be performed by a Deep Neural Netswork (DNN). In the embodiments of the present invention, the fusion of each feature vector can be achieved through the DNN network.

[0056] After obtaining the first feature vector, feature extraction needs to be performed on it to obtain a second feature vector, and the second feature vector contains the feature information extracted from the first color distribution, the second color distribution, the first video frame, and the second video frame. The feature extraction process can be completed by an LSTM model. It should be noted that in the embodiments of the present invention, the LSTM model can be used to record historical information, and the recorded historical second feature vectors can be used as a reference for subsequent feature extraction.

[0057] After obtaining the second feature vector, the second feature vectors obtained by performing feature extraction at different times are subjected to feature fusion, and the second physiological index information of the target object, that is, the complexion state of the target object, can be calculated according to the result of the feature fusion.

[0058] Feature fusion can be achieved through the DNN network. The DNN network also includes a sofmax layer. Using the sofmax layer, the fusion features of the second feature vectors at different times can be calculated to obtain the complexion state of the target object at the current moment.

[0059] In this embodiment, the reason for performing feature fusion on the second feature vectors at different times is that by using the second feature vectors at different times, the influence of light can be eliminated, that is, the influence of sudden changes in light at a certain moment on the obtained feature vectors can be avoided. At the same time, multiple second feature vectors can provide more information, thereby ensuring the accuracy of the second physiological index information of the target object determined based on the second feature vectors.

[0060] Through the method for obtaining the second physiological index information provided above, after performing feature fusion on each feature vector in combination with the historical second physiological index information, a first feature vector is obtained. The second feature vector is obtained by performing feature extraction on the first feature vector. The second physiological index information of the target object is determined by performing feature fusion on the second feature vectors at different times. Since feature fusion is performed on the second feature vectors at different times, more information is referred to in the process of determining the second physiological index. At the same time, the deviation caused by accidental events at a single moment is avoided, and the accuracy of determining the second physiological index information is improved.

[0061] Figure 2 The following is a schematic structural diagram of a second model provided by an embodiment of the present invention. Refer to Figure 2 As shown, first, two grid images need to be obtained, that is, the content presented by the aforementioned first video frame and the second video frame respectively, and the first video frame and the second video frame (i.e., the two grid images in the figure) are input into a convolutional neural network, and feature vectors are obtained after splicing and flattening. The two statistical color distributions (i.e., the aforementioned first color distribution and 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 index information obtained by the memory unit are jointly input into the DNN network for fusion to obtain a first feature vector, and then the second feature vector is obtained by performing feature extraction on the first feature vector by the LSTM network. The second feature vectors obtained by the LSTM network at different times are subjected to feature fusion by the DNN network, and the second physiological index information of the target object is calculated based on the fusion features. Among them, the DNN is composed of multiple fully connected layers and a softmax layer, which can synthesize the information of the input signal, and the LSTM network can record historical information.

[0062] Optionally, in the aforementioned S11, it is mentioned that "obtaining the first physiological index information of the target object based on the first model". In the embodiment of the present invention, the method for obtaining the first physiological index information may be: first, obtaining the first data information of the first physiological index of the target object. Then, obtaining the second data information of the historical first physiological index of the target object, and finally, based on the first data information and the second data information, determining the first physiological index information of the target object by the first model.

[0063] Among them, the first data information is used to indicate the data information of the first physiological index obtained from the nth detection of the target object, and the second data information is used to indicate the data information of the first physiological index obtained from the (n - 1)th detection of the target object, where n > 1.

[0064] It can be seen from this that the first physiological index information needs to be jointly determined based on the data information of the first physiological index obtained from the current detection of the target object and the data information of the first physiological index obtained from the historical detection. Through the first data information and the second data information obtained from the two detections respectively, it can be judged whether the current detection result of the target object is abnormal compared with the historical detection situation.

[0065] For example, when the first physiological index is blood pressure, the first data information of the first physiological index of the target object obtained is the blood pressure information currently measured by the target object, and the second data information of the historical first physiological index of the target object obtained is the blood pressure information measured by the target object historically, and this blood pressure information is the one obtained from the previous detection of the target object. By comparing the first data information and the second data information, the first physiological index information of the target object, that is, whether the blood pressure is abnormal, can be determined. The determination of whether it is abnormal can refer to the standards in medicine. For example, according to the regulations of the World Health Organization, when the systolic blood pressure of an adult ≥ 140 mmHg, the diastolic blood pressure ≥ 90 mmHg or only one of them meets the standard, it can be diagnosed as hypertension. When the systolic blood pressure is between 130 - 139 mmHg or the diastolic blood pressure is between 85 - 89 mmHg, it is regarded as prehypertension. Thus, based on the obtained first data information and second data information, the first physiological index information of the target object can be determined.

[0066] It should be noted that in the embodiments of the present invention, various data information obtained for the target object, including but not limited to the first data information, the second data information, the first video frame, and the second video frame, etc., should strictly obtain the informed consent or separate consent of the personal information subject (such as: the target object) according to the requirements of relevant national laws and regulations, and carry out subsequent data use and processing behaviors within the scope authorized by laws and regulations and the personal information subject.

[0067] Through the above - provided method for obtaining the first physiological index information, based on the data information of the first physiological index of the target object obtained from the two successive detections, the first model can determine the first physiological index information of the target object. By combining the data information of the two times, it is convenient to determine the change trend of the first physiological index of the target object, which is beneficial for the first model to more accurately judge the first physiological index information of the target object in combination with this change trend, and to a certain extent, improve the reliability of the determination result of the first model.

[0068] In the above-mentioned S14, it is mentioned that "determine a physiological index management model based on the category of the target object, obtain the information on the physiological index management corresponding to the target object through the physiological index management model, and complete the physiological index management of the target object". In the embodiments of the present invention, the method for completing physiological index management may be as follows: First, obtain the category of the target object, and then determine the physiological index management model corresponding to the target object based on the mapping relationship between the category and the physiological index management model. Finally, obtain the information on the physiological index management corresponding to the target object through the physiological index management model, and complete the physiological index management of the target object.

[0069] It is mentioned above that the category of the target object is determined based on the first physiological index information and the second physiological index information. When the first physiological index is blood pressure, the corresponding first physiological index information may be normal blood pressure and abnormal blood pressure, and the situations included in abnormal blood pressure may include hypertension and prehypertension. When the second physiological index is complexion state, the corresponding second physiological index information may be good complexion, poor complexion, and very poor complexion. The category of the target object can be determined according to the determined first physiological index information and the second physiological index information. For example, when it is determined that the first physiological index information of the target object is abnormal blood pressure and the second physiological index information is poor complexion, the corresponding category of the target object is (abnormal blood pressure, poor complexion).

[0070] It should be noted that there is a corresponding relationship between the category of the target object and the physiological index management model in the present invention, that is, different categories of the target object correspond to different physiological index management models. The physiological index management model is a model used to manage the physiological indexes of the target object, and the management method may be to determine the situation of the physiological indexes of the target object based on the category of the target object, and put forward relevant suggestions or improvement methods for the physiological indexes based on the situation of the physiological indexes.

[0071] The physiological index management model can be understood as a kind of question-and-answer model or a kind of consultation model. There are differences in the knowledge graphs involved in different physiological index management models, and there is a strong correlation with the category of the target object. In this way, when the category of the target object is determined, based on the mapping relationship between the category and the physiological index management model, the physiological index management model adapted to the category of the target object can be determined, and the information on the physiological index management corresponding to the target object can be obtained through this physiological index management model, so that the physiological index management of the target object can be completed.

[0072] It should be noted that in this embodiment, the mapping relationship between the category of the target object and the physiological index management model can be pre-determined. The specific determination method can be by establishing an index table mapping, or by establishing a database identifier retrieval, as well as other methods that can achieve a one-to-one correspondence between the category and the physiological index management model, which will not be limited here. The specific method of establishing the mapping relationship between the category and the physiological index management model can be determined by those skilled in the art according to the actual situation.

[0073] Through the method for completing physiological index management provided above, after determining the category of the target object, based on the mapping relationship between the category and the physiological index management model, the physiological index management model corresponding to the category of the target object is determined, enabling the target object to achieve targeted and personalized physiological index management based on this physiological index management model. It is beneficial to improve the accuracy and relevance of the physiological index management of the target object, meet the usage requirements of the target object, and improve the usage experience and efficiency of the target user.

[0074] It was mentioned above that "determine the category of the target object according to the first physiological index information and the second physiological index information". In a possible implementation manner, in addition to the first physiological index information and the second physiological index information, the target physiological index information can also be combined to jointly determine the category of the target object. The combination of multiple physiological index information makes the physiological index situation of the target object richer, which is beneficial to subsequently matching a more accurate physiological index management model for it.

[0075] Therefore, before "determine the category of the target object according to the first physiological index information and the second physiological index information", the target physiological index information of the target object can be obtained, and then the category of the target object is determined according to the first physiological index information, the second physiological index information, and the target physiological index information.

[0076] Among them, the target physiological index information is used to indicate the situation information of the target physiological index of the target object. The target physiological index can include but is not limited to age, height, weight, and gender, etc. For example, when the target physiological index is age, the corresponding target physiological index information can include: under 40 years old, over 55 years old, and 40 - 55 years old; when the target physiological index is gender, the corresponding target physiological index information can include: male and female; based on height and weight, the obesity degree can be jointly determined. The specific determination method can refer to the current height - weight standard, which will not be elaborated here. The corresponding target physiological index information can include: obese, normal, and thin, etc.

[0077] Through the method for determining the category of a target object provided above, in addition to the first physiological index information and the second physiological index information, the target physiological index information is added to jointly determine the category of the target object, which can make the determination of the category of the target object more diverse and accurate. In this way, the physiological index management model determined based on the category of the target object can better fit the situation of the physiological index information of the target object, thereby improving the accuracy and relevance of the physiological index management of the target object.

[0078] The present invention also provides a physiological index management system. Figure 3 FIG. 5 is a schematic structural diagram of a physiological index management system provided by an embodiment of the present invention. The physiological index management system includes an acquisition module 100, a second acquisition module 200, a determination module 300, and a management module 400. The first acquisition module 100 is configured to acquire first physiological index information of a target object based on a first model, where the first physiological index information is used to indicate an abnormal condition of a first physiological index of the target object. The second acquisition module 200 is configured to acquire second physiological index information of the target object based on a second model, where the second physiological index information is used to indicate an abnormal condition of a second physiological index of the target object. The determination module 300 is configured to determine the category of the target object according to the first physiological index information and the second physiological index information. The management module 400 is configured to determine a physiological index management content acquisition model based on the category of the target object, and acquire information content of physiological index management corresponding to the target object through the physiological index management content acquisition model, so as to complete the physiological index management of the target object, and there is a corresponding relationship between the category and the physiological index management content acquisition model.

[0079] In a possible implementation manner, the first acquisition module 100 is configured to: Acquire first data information of a first physiological index of the target object, where the first data information is used to indicate data information of the first physiological index obtained by the nth detection of the target object. Acquire second data information of a historical first physiological index of the target object, where the second data information is used to indicate data information of the first physiological index obtained by the (n - 1)th detection of the target object, where n > 1. Based on the first data information and the second data information, the first model determines the first physiological index information of the target object.

[0080] In a possible implementation manner, the system includes a color distribution determination module, and the color distribution determination module is configured to: Identify the target area of the target object, and obtain a first video frame and a second video frame corresponding to the target area. 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 an adjacent moment of the current moment; Determine the first color distribution of the target area based on the first video frame; Determine the second color distribution of the target area according to the first video frame and the second video frame; The second acquisition module 200 is configured to: Based on the first color distribution, the second color distribution, the first video frame, and the second video frame, obtain the second physiological index information of the target object through the second model.

[0081] In a possible implementation manner, the second acquisition module 200 is configured to: Convert the first video frame and the second video frame into feature vectors respectively; Obtain the historical second physiological index information of the target object; 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 index information, obtain the second physiological index information of the target object through the second model.

[0082] In a possible implementation manner, the second acquisition module 200 is configured to: Perform 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 index information to obtain a first feature vector; Perform feature extraction based on the first feature vector to obtain a second feature vector; Fuse the second feature vectors obtained at different times by the second model to obtain the second physiological index information of the target object.

[0083] In a possible implementation manner, the management module 400 is configured to: Obtain the category of the target object; Based on the mapping relationship between the category and the physiological index management model, determine the physiological index management model corresponding to the target object; Obtain the information on the physiological index management corresponding to the target object through the physiological index management model to complete the physiological index management of the target object.

[0084] In a possible implementation manner, the system further includes an index acquisition module, and the index acquisition module is configured to: acquire target physiological index information of the target object, where the target physiological index information is used to indicate the situation information of the target physiological index of the target object; The determining module 300 is configured to: determine the category of the target object according to the first physiological index information, the second physiological index information, and the target physiological index information.

[0085] In an embodiment of the present invention, a physiological index management system is proposed. The system includes: a first acquisition module, a second acquisition module, a determining module, and a management module. The first acquisition module is configured to acquire first physiological index information of a target object based on a first model, and the first physiological index information is used to indicate an abnormal situation of a first physiological index of the target object; the second acquisition module is configured to acquire second physiological index information of the target object based on a second model, and the second physiological index information is used to indicate an abnormal situation of a second physiological index of the target object; the determining module is configured to determine the category of the target object according to the first physiological index information and the second physiological index information; the management module is configured to determine a physiological index management content acquisition model based on the category of the target object, and acquire information content of physiological index management corresponding to the target object through the physiological index management content acquisition model, so as to complete the physiological index management of the target object. There is a corresponding relationship between the category and the physiological index management content acquisition model. In this way, the abnormal situations of the first physiological index and the second physiological index of the target object are acquired through the first model and the second model, and the category of the target object can be determined by combining the abnormal situations of each physiological index. Since there is a corresponding relationship between the category and the physiological index management model, the matching determination of the physiological index management model can be automatically completed according to the determined category of the target object. Furthermore, the target object can obtain corresponding information of physiological index management through the matched physiological index management model, so as to complete the physiological index management. The whole process does not need to rely on manual means, but is carried out in an automated manner. And the category of the target object is determined according to the situation of the physiological index information of the target object, and the physiological index management model is matched for the target object in combination with the category, so that the physiological index management model can conform to the personalized characteristics of the target object, and thus it is possible to accurately and efficiently obtain the information of the physiological index management corresponding to itself.

[0086] An embodiment of the present invention further provides a medical device, which includes the aforementioned physiological index management device, a processor, a Wi-Fi module, and a camera. The processor and the Wi-Fi module are used to obtain first data information of a first physiological index and input the first data information into the physiological index management device, and the camera is used to identify a target area of a target object. In a possible implementation manner, the medical device may further include a cuff for detecting blood pressure and a device for detecting other physiological indexes, which are not limited herein. In a possible implementation manner, the medical device may further include a microphone and a speaker for real-time communication with the target object. A display screen may be provided, but it is not provided when the display function of the display screen affects the acquisition of data information of the target object.

[0087] An embodiment of the present application further provides a corresponding device and a computer-readable storage medium for implementing the solution provided by the embodiment of the present application.

[0088] Wherein, 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.

[0089] In practical applications, the computer-readable storage medium may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium 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 of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0090] A computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device.

[0091] The program code contained on a computer-readable medium can be transmitted by any appropriate medium, including but not limited to wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0092] The computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0093] The above are only alternative embodiments of the present invention, and do not limit the patent scope of the present invention. Any equivalent structural transformation made by using the specification and drawings of the present invention under the inventive concept of the present invention, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. A physiological index management method, characterized in that, including obtaining first physiological index information of a target object based on a first model, where the first physiological index information is used to indicate an abnormal condition of a first physiological index of the target object; obtaining second physiological index information of the target object based on a second model, where the second physiological index information is used to indicate an abnormal condition of a second physiological index of the target object; determining a category of the target object according to the first physiological index information and the second physiological index information; determining a physiological index management model based on the category of the target object, and obtaining information on physiological index management corresponding to the target object through the physiological index management model, thereby completing the physiological index management of the target object, where there is a corresponding relationship between the category and the physiological index management model.

2. The physiological index management method according to claim 1, characterized in that, Before the obtaining the second physiological index information of the target object based on the second model, the method further includes: identifying a target area of the target object, and obtaining a first video frame and a second video frame corresponding to the target area, where the first video frame is used to indicate an image corresponding to the target area at the current moment, and the second video frame is used to indicate an image corresponding to the target area at a target moment, and the target moment is an adjacent moment of 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; The obtaining the second physiological index information of the target object based on the second model includes: obtaining the second physiological index 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.

3. The physiological index management method according to claim 2, characterized in that, The obtaining the second physiological index 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: respectively converting the first video frame and the second video frame into feature vectors; obtaining historical second physiological index information of the target object; obtaining the second physiological index information of the target object 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 index information.

4. The physiological index management method according to claim 3, wherein The obtaining the second physiological index information of the target object 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 index 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 index 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 the second physiological index information of the target object.

5. The physiological index management method according to claim 1, wherein The obtaining of the first physiological index information of the target object based on the first model includes: Obtaining first data information of the first physiological index of the target object, where the first data information is used to indicate the data information of the first physiological index obtained by the target object in the nth detection; Obtaining second data information of the historical first physiological index of the target object, where the second data information is used to indicate the data information of the first physiological index obtained by the target object in the (n - 1)th detection, where n > 1; Based on the first data information and the second data information, the first model determines the first physiological index information of the target object.

6. The physiological index management method according to claim 1, characterized in that The determining of the physiological index management model based on the category of the target object, and obtaining the information on the physiological index management corresponding to the target object through the physiological index management model to complete the physiological index management of the target object includes: Obtaining the category of the target object; Based on the mapping relationship between the category and the physiological index management model, determining the physiological index management model corresponding to the target object; Obtaining the information on the physiological index management corresponding to the target object through the physiological index management model to complete the physiological index management of the target object.

7. The physiological index management method according to claim 1, characterized in that, Before determining the category of the target object according to the first physiological index information and the second physiological index information, the method further includes: Obtaining the target physiological index information of the target object, where the target physiological index information is used to indicate the situation information of the target physiological index of the target object; The determining of the category of the target object according to the first physiological index information and the second physiological index information includes: Determining the category of the target object according to the first physiological index information, the second physiological index information, and the target physiological index information.

8. A physiological index management system, characterized in that The system includes: a first obtaining module, a second obtaining module, a determining module, and a management module; The first obtaining module is used to obtain the first physiological index information of the target object based on the first model, where the first physiological index information is used to indicate the abnormal situation of the first physiological index of the target object; The second obtaining module is used to obtain the second physiological index information of the target object based on the second model, where the second physiological index information is used to indicate the abnormal situation of the second physiological index of the target object; The determining module is used to determine the category of the target object according to the first physiological index information and the second physiological index information; The management module is used to determine the physiological index management content obtaining model based on the category of the target object, and obtain the information content on the physiological index management corresponding to the target object through the physiological index management content obtaining model to complete the physiological index management of the target object, and there is a corresponding relationship between the category and the physiological index management content obtaining model.

9. A medical device, characterized in that, The device includes a physiological index management device, a processor, a wifi module, and a camera.

10. A computer-readable storage medium, characterized in that, An implementation program for implementing the physiological index management method is stored on the computer-readable storage medium. When the implementation program for implementing the physiological index management method is executed by a processor, the steps of the method according to any one of claims 1-7 are implemented.

Images