Real-time physical examination state monitoring system and method based on AI

Abstract

The invention relates to the technical field of data analysis, in particular to a real-time physical examination state monitoring system and method based on AI, and the system comprises a monitoring layer, an evaluation layer, and an early warning and refreshing layer. The body state parameters of a user are monitored in real time through the monitoring layer, the monitoring layer synchronously executes sorting and storage of the body state parameters of the user after monitoring the body state parameters of the user, and the evaluation layer synchronously calls the body state parameters of the user stored in the monitoring layer. According to the method, the body state parameters of the user are collected in real time through the wearable body state parameter monitoring equipment, and the safety of the user can be evaluated and judged in real time based on the body state parameters of the user; according to the invention, physical health safety management is provided for patients with heart and cardiovascular diseases, so that rehabilitation and treatment of the users are assisted, the treatment process of the users is safer, more instant and more reliable, and certain self-monitoring conditions are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a real-time physical examination status monitoring system and method based on AI. Background Art

[0002] Physical examination status monitoring is a method of continuously observing and evaluating various indicators of an individual's body during the physical examination process. Through professional equipment and technology, the body's physiological parameters, such as blood pressure and heart rate, are monitored in real time to promptly identify potential health problems, provide doctors with accurate diagnostic basis, and ensure the comprehensiveness and accuracy of physical examination results.

[0003] The invention patent with application number 201610647516.4 discloses a family health check-up monitoring system, which is characterized by comprising a cabinet and a control panel; the control panel can be stored inside the cabinet or unfolded outside the cabinet; the control panel is provided with a physical examination instrument compartment and a computer; the physical examination instrument compartment can be popped out or retracted from the control panel for placing physical examination sensors; the computer can be folded and embedded in the control panel; the cabinet is provided with a data processing equipment compartment, a specimen compartment, a laboratory equipment compartment, a transmission positioning device and a controller; the data processing equipment compartment is equipped with a data processing device, and the data processing device is used to receive the physical examination signal returned by the physical examination sensor and convert the physical examination signal into physical examination data; the specimen compartment can be popped out or retracted from the The box pops up or is retracted from the cabinet, and is used to place the physical examination specimens of the examinee; the test equipment compartment can pop up or be retracted from the box, and is used to install the test equipment, and the test equipment is used to obtain the physical examination data after testing and analyzing the physical examination specimens; the transmission and positioning device is used to send the physical examination specimens to the test equipment; the controller is respectively connected to the computer, the physical examination sensor, the data processing equipment, the test equipment and the transmission and positioning device, and is used to start or shut down the physical examination sensor, the data processing equipment and the test equipment, collect the physical examination data processed by the data processing equipment and the test equipment and upload them to the computer, and control the transmission and positioning device to send the physical examination specimens to the test equipment; the computer is used to display the physical examination data.

[0004] The application aims to address the problem that "with the intensification of environmental pollution and global climate change, the pressure of human life is constantly increasing, the global disease spectrum has undergone a major change, and malignant tumors, cardiovascular and cerebrovascular diseases are at the forefront all over the world, posing a major threat to human health."

[0005] However, for patients with heart and cardiovascular diseases, their physical condition requires long-term monitoring. Although there are wearable body condition parameter monitoring devices to monitor the patient's physical condition, there is no complete body condition parameter analysis technology to monitor the patient's physical condition safety in real time.

[0006] To this end, we proposed an AI-based real-time physical examination status monitoring system and method. Summary of the invention

[0007] In view of the above-mentioned shortcomings of the prior art, the present invention provides an AI-based real-time physical examination status monitoring system and method, which solves the technical problems raised in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] In the first aspect, a real-time physical examination status monitoring system based on AI includes: a monitoring layer, an evaluation layer, and an early warning and refresh layer;

[0010] The user's physical state parameters are monitored in real time by the monitoring layer. After the monitoring layer detects the user's physical state parameters, it synchronously sorts and stores the user's physical state parameters. The evaluation layer synchronously retrieves the user's physical state parameters stored in the monitoring layer, and evaluates the user's safety and the user's safety abnormality based on the user's physical state parameters. The early warning and refresh layer further receives the evaluation results of the user's safety and the user's safety abnormality, issues an early warning based on the evaluation results, and synchronously switches the system operation mode.

[0011] The evaluation layer includes a retrieval module, a control module and an evaluation module. The retrieval module is used to retrieve the user's physical state parameters stored in the monitoring layer. The control module is used to set the monitoring layer operation cycle and control the monitoring layer to operate continuously based on the monitoring layer operation cycle. The evaluation module is used to traverse the user's physical state parameters retrieved in the retrieval module and evaluate the user's safety and the user's safety abnormality through the user's physical state parameters.

[0012] The user security assessment logic in the assessment module is expressed as:

[0013]

[0014] Where: Q is the user security performance value; SIMM (P Long ,P Short ) is the similarity between the longest band and the shortest band in the user's electrocardiogram; The maximum difference between each group of peaks or valleys in the longest band of the user's electrocardiogram and the end value of the user's electrocardiogram safety judgment threshold, and the maximum difference between each group of peaks or valleys in the shortest band of the user's electrocardiogram and the user's electrocardiogram safety judgment threshold; (SPO2) max、(SPO2) min Set the maximum and minimum blood oxygen saturation values ​​of the user within the time domain of the user's electrocardiogram; max 、p min The maximum and minimum values ​​of the user's blood pressure within the time domain of the user's electrocardiogram; v is the user's average moving speed; s max 、s min Set the maximum and minimum heart rate values ​​of the user within the time domain of the user's electrocardiogram;

[0015] Among them, SIMM (P Long ,P Short ) When obtaining the similarity, the lengths of the two groups of bands are not considered. The user's ECG safety judgment threshold is manually set by the system end user. A group of position sensors are deployed at the ends of the user's limbs. The user's average moving speed v is the ratio of the distance between the first sensed position and the last sensed position to the corresponding time length of the user's ECG time domain. The larger the user safety performance value Q is, the more stable and safer the user's current state is. Conversely, the more unstable and dangerous the user's current state is.

[0016] Four groups of user safety judgment thresholds are set in the retrieval module, and the four groups of user safety judgment thresholds correspond to user safety judgments applied to electrocardiogram, blood oxygen saturation, heart rate and blood pressure levels. The retrieval module determines whether the user is safe based on the user safety judgment threshold and the user's physical state parameters retrieved in real time. If the judgment result is no, the module jumps to the refresh layer to run. If the judgment result is yes, the evaluation layer continues to execute.

[0017] Furthermore, the monitoring layer includes a monitoring module, a sorting module and a storage module. The monitoring module is used to monitor the user's physical state parameters in real time. The sorting module is used to set the sorting logic, receive the user's physical state parameters monitored by the monitoring module, and apply the sorting logic to sort the received user's physical state parameters. The storage module is used to receive the remaining user's physical state parameters sorted in the sorting module, store the user's physical state parameters, and synchronously upload them to the cloud for backup;

[0018] Among them, the monitoring module includes: a wearable electrocardiogram monitor, a wearable blood oxygen saturation monitor, and a heart rate and blood pressure smart bracelet. The user's body state parameters are the parameters collected by the wearable electrocardiogram monitor, the wearable blood oxygen saturation monitor, and the heart rate and blood pressure smart bracelet. The storage module is bound to a set of preset cloud databases. The operation of uploading the user's body state parameters to the cloud backup in the storage module is to copy the user's body state parameters, send the copied user's body state parameters to the cloud database, and store them in the cloud database.

[0019] Furthermore, the sorting logic set in the sorting module is expressed as:

[0020] Logic1: Select the user's electrocardiogram data monitored by the wearable electrocardiogram monitor as a reference for sorting the user's physical status parameters;

[0021] Logic2: Segment the bands in the electrocardiogram based on their similarity;

[0022] Logic 3: Obtain the segmentation results, identify the time threshold corresponding to each segmented continuous band in the segmentation results, and segment all user body state parameters based on the identified continuous band corresponding time threshold;

[0023] The calculation formula of the band similarity in the electrocardiogram is:

[0024]

[0025] Where: SIMM (a, b) is the similarity between band a and band b in the electrocardiogram; ∠ a , ∠b is the angle of band a and the angle of band b; is the slope of the preceding and following line segments on band a; L is the slope of the preceding and following line segments on band b; a , L b is the length of band a and band b; ω1, ω2, ω3 are weights; γ is the adjustment factor;

[0026] Among them, band a and band b are two groups of continuous adjacent bands in the electrocardiogram, each group of bands is an open downward angle formed by two groups of valley points and one group of peak points connected to each other. When the similarity of the two groups of bands is not less than 95%, they are judged to be similar, otherwise, they are judged to be dissimilar, and the vertical line at the intersection of the two groups of bands is used as the band dividing line to divide the electrocardiogram, and the segmented results are recorded as continuous bands.

[0027] Furthermore, the adjustment factor γ is 1 or -1. When the numerator of the fraction where the adjustment factor is located is less than or equal to the denominator, the adjustment factor γ is 1. When the numerator of the fraction where the adjustment factor is located is greater than the denominator, the adjustment factor γ is -1. The sum of the weights ω1, ω2, and ω3 is 1, and the values ​​of ω1, ω2, and ω3 are customized by the system end user.

[0028] After all user body state parameters are divided in Logic3, each group of sub-user body state parameters is the sorting result of the user body state parameters running by the sorting module;

[0029] Among them, the user's physical condition parameters include: electrocardiogram, blood oxygen saturation, heart rate and blood pressure.

[0030] Furthermore, the user body state parameters retrieved by the retrieval module each time are: the user body state parameters stored after the monitoring layer runs once based on the operation cycle and performs the sorting operation, the evaluation module runs synchronously with the retrieval module, and after each retrieval module runs, the user safety and user safety abnormality status are executed once, the retrieval module runs synchronously to monitor the running state of the evaluation module, and after the evaluation module runs, it runs again;

[0031] The operation cycle used by the monitoring layer is defined or followed by the system end user in the control module:

[0032] The lower the average similarity of the bands in the electrocardiogram of the user's physical state parameters, the shorter the monitoring layer operation cycle is; the higher the average similarity of the bands in the electrocardiogram, the longer the monitoring layer operation cycle is.

[0033] Furthermore, the evaluation module stores the user security evaluation results, and performs further evaluation of the user security abnormality when the user security evaluation results stored therein are not less than three groups. The user security abnormality evaluation logic in the evaluation module is expressed as:

[0034]

[0035] Wherein: Q1, Q2, Q3 are the three consecutive groups of user security assessment results most recently stored in the assessment module.

[0036] Furthermore, the warning and refresh layer includes a determination module, a warning module and a switching module. The determination module is used to receive the evaluation result of the user's safety abnormal situation in the evaluation module, and determine whether the user's current state is safe based on the evaluation result. The warning module is used to read the determination result of whether the user's current state is safe in the determination module, and when the determination result is no, send a warning message. The switching module switches the operating state of the monitoring module in the monitoring layer, so that the monitoring module is independent of the operating cycle of the monitoring layer, continuously and in real time monitors the user's physical state parameters and feeds back to the system end user;

[0037] The determination logic in the determination module is:

[0038] In the formula, if both (1) and (2) are not true, it means that the user's current state is stable and safe; if (1) is true and (2) is not true, it means that the user's current state is questionable. If (1) is true and (2) is not true twice in a row, it means that the user's current state is unstable and dangerous; if both (1) and (2) are true, it means that the user's current state is unstable and dangerous; if (1) is not true and (2) is true, it means that the user's current state is unstable and dangerous;

[0039] Among them, the early warning module is connected to the mobile computer device held by the system end user through a wireless network. The early warning message sent by the early warning module is text data or audio data preset by the system end. The early warning message is stored in the mobile computer device held by the system end user. When the early warning module is running, the early warning message is triggered to be broadcast in the mobile computer device.

[0040] Furthermore, the switching module continuously operates to control the monitoring module, the monitoring module operation cycle controlled by the switching module is within the range of 3 seconds / time to 10 seconds / time, the switching module is manually controlled to be closed by the system end user, and after the system end user controls the switching module to be closed, the system refreshes and operates;

[0041] The switching module operates in conjunction with the early warning module.

[0042] Furthermore, the retrieval module is interactively connected to the storage module via a wireless network, the storage module is interactively connected to the sorting module and the monitoring module via a wireless network, the retrieval module is interactively connected to the control module and the evaluation module via a wireless network, the evaluation module is interactively connected to the determination module via a wireless network, and the determination module is interactively connected to the early warning module and the switching module via a wireless network.

[0043] In a second aspect, a real-time physical examination status monitoring method based on AI comprises the following steps:

[0044] Step 1: Monitor the user's physical condition parameters, set the parameter sorting logic, and sort and store the monitored user's physical condition parameters;

[0045] Step 2: Retrieve the stored user body state parameters, and evaluate the user's safety and the abnormal change trend of the user's safety based on the user's body state parameters;

[0046] Step 21: Setting stage of the user's body condition parameter monitoring cycle;

[0047] Step 22: Setting the user security assessment logic;

[0048] Step 23: Setting the user security abnormal situation assessment logic;

[0049] Step 3: Obtain the user security and user security abnormality situation assessment results, determine whether the user is safe based on the assessment results, issue an early warning based on the determination results, and control the continuous operation of the monitoring module;

[0050] Step 31: Setting the logic for determining whether the user is safe;

[0051] Step 4: The monitoring module monitors the real-time feedback of the user's physical condition parameters.

[0052] Compared with the known public technology, the technical solution provided by the present invention has the following beneficial effects:

[0053] A real-time physical examination status monitoring system based on AI is provided. During operation, the system collects the user's physical status parameters in real time through a wearable physical status parameter monitoring device, and can evaluate and determine the user's safety in real time based on the user's physical status parameters, thereby providing physical health and safety management for users with heart and cardiovascular diseases, thereby assisting the user's rehabilitation and treatment, ensuring that the user's treatment process is safer, more immediate, and more reliable, and thus having certain self-monitoring conditions. At the same time, based on the execution of an AI-based real-time physical examination status monitoring method, the above system provides further operation logic support to ensure stable system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0055] Figure 1 It is a structural diagram of a real-time physical examination status monitoring system based on AI;

[0056] Figure 2 It is a flowchart of a real-time physical examination status monitoring method based on AI;

[0057] Figure 3 This is a schematic diagram of an example of a user's electrocardiogram segmentation operation in the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] The present invention will be further described below in conjunction with the embodiments.

[0060] Embodiment 1:

[0061] A real-time physical examination status monitoring system based on AI in this embodiment, such as Figure 1 As shown, it includes: monitoring layer, evaluation layer, early warning layer and refresh layer;

[0062] The user's physical state parameters are monitored in real time by the monitoring layer. After the monitoring layer detects the user's physical state parameters, it synchronously sorts and stores the user's physical state parameters. The evaluation layer synchronously retrieves the user's physical state parameters stored in the monitoring layer, and evaluates the user's safety and the user's safety abnormality based on the user's physical state parameters. The early warning and refresh layer further receives the evaluation results of the user's safety and the user's safety abnormality, issues an early warning based on the evaluation results, and synchronously switches the system operation mode.

[0063] The monitoring layer includes a monitoring module, a sorting module and a storage module. The monitoring module is used to monitor the user's physical state parameters in real time. The sorting module is used to set the sorting logic, receive the user's physical state parameters monitored by the monitoring module, and apply the sorting logic to sort the received user's physical state parameters. The storage module is used to receive the remaining user's physical state parameters sorted in the sorting module, store the user's physical state parameters, and upload them to the cloud for backup simultaneously.

[0064] The monitoring module includes: a wearable electrocardiogram monitor, a wearable blood oxygen saturation monitor, and a heart rate and blood pressure smart bracelet. The user's body state parameters are the parameters collected by the wearable electrocardiogram monitor, the wearable blood oxygen saturation monitor, and the heart rate and blood pressure smart bracelet. The storage module is bound to a set of preset cloud databases. The operation of uploading the user's body state parameters to the cloud backup in the storage module is to copy the user's body state parameters, send the copied user's body state parameters to the cloud database, and store them in the cloud database.

[0065] The evaluation layer includes a retrieval module, a control module and an evaluation module. The retrieval module is used to retrieve the user's physical state parameters stored in the monitoring layer. The control module is used to set the monitoring layer operation cycle and control the monitoring layer to operate continuously based on the monitoring layer operation cycle. The evaluation module is used to traverse the user's physical state parameters retrieved in the retrieval module and evaluate the user's safety and the user's safety abnormality through the user's physical state parameters.

[0066] The user security assessment logic in the assessment module is expressed as:

[0067]

[0068] Where: Q is the user security performance value; SIMM (P Long ,P Short ) is the similarity between the longest band and the shortest band in the user's electrocardiogram; The maximum difference between each group of peaks or valleys in the longest band of the user's electrocardiogram and the end value of the user's electrocardiogram safety judgment threshold, and the maximum difference between each group of peaks or valleys in the shortest band of the user's electrocardiogram and the user's electrocardiogram safety judgment threshold; (SPO2)max 、(SPO2) min Set the maximum and minimum blood oxygen saturation values ​​of the user within the time domain of the user's electrocardiogram; max 、p min The maximum and minimum values ​​of the user's blood pressure within the time domain of the user's electrocardiogram; v is the user's average moving speed; s max 、s min Set the maximum and minimum heart rate values ​​of the user within the time domain of the user's electrocardiogram;

[0069] Among them, SIMM (P Long ,P Short ) When calculating the similarity, the lengths of the two sets of bands are not considered. The user's ECG safety judgment threshold is manually set by the user on the system end. A set of position sensors are deployed at the ends of the user's limbs. The user's average moving speed v is the ratio of the distance between the first sensed position and the last sensed position to the corresponding time length of the user's ECG time domain. The larger the user safety performance value Q is, the more stable and safer the user's current state is. Conversely, the more unstable and dangerous the user's current state is.

[0070] Four sets of user safety judgment thresholds are set in the retrieval module. The four sets of user safety judgment thresholds correspond to user safety judgments at the electrocardiogram, blood oxygen saturation, heart rate and blood pressure levels. The retrieval module determines whether the user is safe based on the user safety judgment thresholds and the user's physical status parameters retrieved in real time. If the judgment result is no, the refresh layer will be jumped to run. If the judgment result is yes, the evaluation layer will continue to execute;

[0071] The evaluation module stores the user security evaluation results. When the user security evaluation results stored in the evaluation module are no less than three groups, further evaluation of the user security abnormality is performed. The evaluation logic of the user security abnormality in the evaluation module is expressed as follows:

[0072]

[0073] Where: Q1, Q2, Q3 are the three consecutive sets of user security assessment results most recently stored in the assessment module;

[0074] The early warning and refresh layer includes a determination module, an early warning module and a switching module. The determination module is used to receive the evaluation result of the user's safety abnormal situation in the evaluation module, and determine whether the user's current state is safe based on the evaluation result. The early warning module is used to read the determination result of whether the user's current state is safe in the determination module. When the determination result is no, a warning message is issued. The switching module switches the operating state of the monitoring module in the monitoring layer, so that the monitoring module is independent of the operating cycle of the monitoring layer, continuously and in real time monitors the user's physical state parameters and feeds back to the system end user;

[0075] The judgment logic in the judgment module is:

[0076] In the formula, if both (1) and (2) are not true, it means that the user's current state is stable and safe; if (1) is true and (2) is not true, it means that the user's current state is questionable. If (1) is true and (2) is not true twice in a row, it means that the user's current state is unstable and dangerous; if both (1) and (2) are true, it means that the user's current state is unstable and dangerous; if (1) is not true and (2) is true, it means that the user's current state is unstable and dangerous;

[0077] The warning module is connected to the mobile computer device held by the system end user through a wireless network. The warning message sent by the warning module is text data or audio data preset by the system end. The warning message is stored in the mobile computer device held by the system end user. When the warning module is running, the warning message is triggered to be broadcast in the mobile computer device.

[0078] The retrieval module is interactively connected to the storage module through a wireless network, the storage module is interactively connected to the sorting module and the monitoring module through a wireless network, the retrieval module is interactively connected to the control module and the evaluation module through a wireless network, the evaluation module is interactively connected to the determination module through a wireless network, and the determination module is interactively connected to the early warning module and the switching module through a wireless network.

[0079] In this embodiment, the monitoring module runs to monitor the user's physical state parameters in real time, the sorting module synchronously sets the sorting logic, receives the user's physical state parameters monitored by the monitoring module, and applies the sorting logic to sort the received user's physical state parameters. The storage module is post-operated to receive the remaining user's physical state parameters in the sorting module, store the user's physical state parameters, and synchronously upload them to the cloud for backup. The retrieval module further retrieves the user's physical state parameters stored in the monitoring layer. The control module synchronously sets the monitoring layer operation cycle, and controls the monitoring layer to run continuously based on the monitoring layer operation cycle. The evaluation module then traverses the user's physical state parameters retrieved from the retrieval module, and evaluates the user's safety and the user's safety abnormality through the user's physical state parameters. Finally, the determination module receives the user's safety abnormality evaluation result in the evaluation module, and determines whether the user's current state is safe based on the evaluation result. The early warning module reads the determination result of whether the user's current state is safe in the determination module. When the determination result is no, an early warning message is issued. The switching module switches the operation state of the monitoring module in the monitoring layer in real time, so that the monitoring module is independent of the monitoring layer operation cycle, continuously and in real time monitors the user's physical state parameters and provides feedback to the system end user.

[0080] Through the operation of the system in the above embodiment, real-time physical examination status monitoring effect is brought to patients with heart and cardiovascular diseases, ensuring that patients can understand their own physical status more promptly, and using this as a remote system to interact with the medical end, providing users with real-time safety protection.

[0081] Embodiment 2:

[0082] In terms of specific implementation, based on Example 1, this example refers to Figure 1 The AI-based real-time physical examination status monitoring system in Example 1 is further described in detail:

[0083] The sorting logic set in the sorting module is expressed as:

[0084] Logic1: Select the user's electrocardiogram data monitored by the wearable electrocardiogram monitor as a reference for sorting the user's physical status parameters;

[0085] Logic2: Segment the bands in the electrocardiogram based on their similarity;

[0086] Logic 3: Obtain the segmentation results, identify the time threshold corresponding to each segmented continuous band in the segmentation results, and segment all user body state parameters based on the identified continuous band corresponding time threshold;

[0087] The calculation formula for the band similarity in the electrocardiogram is:

[0088]

[0089] Where: SIMM (a, b) is the similarity between band a and band b in the electrocardiogram; ∠ a ,∠ b is the angle of band a and the angle of band b; is the slope of the preceding and following line segments on band a; L is the slope of the preceding and following line segments on band b; a , L b is the length of band a and band b; ω1, ω2, ω3 are weights; γ is the adjustment factor;

[0090] Among them, band a and band b are two groups of continuous adjacent bands in the electrocardiogram, each group of bands is an angle formed by two groups of valley points and one group of peak points connected to each other, and the two groups of bands are judged to be similar when the similarity is not less than 95%, otherwise, they are judged to be dissimilar, and the vertical line where the intersection of the two groups of bands is located is used as the band dividing line to divide the electrocardiogram, and the segmented results are recorded as continuous bands;

[0091] The adjustment factor γ is 1 or -1. When the numerator of the fraction where the adjustment factor is located is less than or equal to the denominator, the adjustment factor γ is 1. When the numerator of the fraction where the adjustment factor is located is greater than the denominator, the adjustment factor γ is -1. The sum of the weights ω1, ω2, and ω3 is 1, and the values ​​of ω1, ω2, and ω3 are customized by the system end user.

[0092] After all user body state parameters are divided in Logic3, each group of sub-user body state parameters is the sorting result of the user body state parameters running by the sorting module;

[0093] Among them, the user's physical condition parameters include: electrocardiogram, blood oxygen saturation, heart rate and blood pressure.

[0094] Through the above logic formula, data support is further provided for the sorting logic set in the sorting module, thereby realizing the sorting of the user's body state parameters by the sorting module.

[0095] like Figure 1 As shown, the user body state parameters retrieved by the retrieval module each time are: the user body state parameters stored after the monitoring layer runs once based on the operation cycle and performs the sorting operation, the evaluation module runs synchronously with the retrieval module, and after each retrieval module runs, the user safety and user safety abnormality situation are executed once, the retrieval module runs synchronously to monitor the running state of the evaluation module, and after the evaluation module runs, it runs again;

[0096] The operation cycle used by the monitoring layer is defined or followed by the system end user in the control module:

[0097] The lower the average similarity of the bands in the electrocardiogram of the user's physical state parameters, the shorter the monitoring layer operation cycle is; the higher the average similarity of the bands in the electrocardiogram, the longer the monitoring layer operation cycle is.

[0098] Through the above settings, a linkage operation logic is provided for the evaluation layer and the monitoring layer of the system in Example 1, ensuring that the system in Example 1 can run continuously to provide services to system users.

[0099] like Figure 1 As shown, the switching module continuously runs to control the monitoring module. The monitoring module operation cycle controlled by the switching module is within the range of 3 seconds / time to 10 seconds / time. The switching module is manually controlled to be closed by the system end user. After the system end user controls the switching module to be closed, the system refreshes and runs;

[0100] The switching module operates in conjunction with the early warning module.

[0101] Through the above settings, the linkage operation logic of the modules in the early warning and refresh layers is further limited.

[0102] Embodiment three:

[0103] In terms of specific implementation, based on Example 1, this example refers to Figure 2 The AI-based real-time physical examination status monitoring system in Example 1 is further described in detail:

[0104] A real-time physical examination status monitoring method based on AI, comprising the following steps:

[0105] Step 1: Monitor the user's physical condition parameters, set the parameter sorting logic, and sort and store the monitored user's physical condition parameters;

[0106] Step 2: Retrieve the stored user body state parameters, and evaluate the user's safety and the abnormal change trend of the user's safety based on the user's body state parameters;

[0107] Step 21: Setting stage of the user's body condition parameter monitoring cycle;

[0108] Step 22: Setting the user security assessment logic;

[0109] Step 23: Setting the user security abnormal situation assessment logic;

[0110] Step 3: Obtain the user security and user security abnormality situation assessment results, determine whether the user is safe based on the assessment results, issue an early warning based on the determination results, and control the continuous operation of the monitoring module;

[0111] Step 31: Setting the logic for determining whether the user is safe;

[0112] Step 4: The monitoring module monitors the real-time feedback of the user's physical condition parameters.

[0113] In summary, during the operation of the system in the above embodiment, the user's physical state parameters are collected in real time through the wearable physical state parameter monitoring device, and the user's safety can be evaluated and determined in real time based on the user's physical state parameters, thereby providing physical health and safety management for users with heart and cardiovascular diseases, thereby assisting the user's rehabilitation and treatment, ensuring that the user's treatment process is safer, more immediate and reliable, and thus having certain self-monitoring conditions.

[0114] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A real-time physical examination status monitoring system based on AI, characterized in that: include: Monitoring layer, assessment layer, early warning layer, and refresh layer; The user's physical state parameters are monitored in real time by the monitoring layer. After the monitoring layer detects the user's physical state parameters, it synchronously sorts and stores the user's physical state parameters. The evaluation layer synchronously retrieves the user's physical state parameters stored in the monitoring layer, and evaluates the user's safety and the user's safety abnormality based on the user's physical state parameters. The early warning and refresh layer further receives the evaluation results of the user's safety and the user's safety abnormality, issues an early warning based on the evaluation results, and synchronously switches the system operation mode. The evaluation layer includes a retrieval module, a control module and an evaluation module. The retrieval module is used to retrieve the user's physical state parameters stored in the monitoring layer. The control module is used to set the monitoring layer operation cycle and control the monitoring layer to operate continuously based on the monitoring layer operation cycle. The evaluation module is used to traverse the user's physical state parameters retrieved in the retrieval module and evaluate the user's safety and the user's safety abnormality through the user's physical state parameters. The user security assessment logic in the assessment module is expressed as: Where: Q is the user security performance value; SIMM (P Long ,P Short ) is the similarity between the longest band and the shortest band in the user's electrocardiogram; The maximum difference between each group of peaks or valleys in the longest band of the user's electrocardiogram and the end value of the user's electrocardiogram safety judgment threshold, and the maximum difference between each group of peaks or valleys in the shortest band of the user's electrocardiogram and the user's electrocardiogram safety judgment threshold; (SPO2) max 、(SPO2) min Set the maximum and minimum blood oxygen saturation values ​​of the user within the time domain of the user's electrocardiogram; max 、p min The maximum and minimum values ​​of the user's blood pressure within the time domain of the user's electrocardiogram; v is the user's average moving speed; s max 、s min Set the maximum and minimum heart rate values ​​of the user within the time domain of the user's electrocardiogram; Among them, SIMM (P Long ,P Short ) When obtaining the similarity, the lengths of the two groups of bands are not considered. The user's ECG safety judgment threshold is manually set by the system end user. A group of position sensors are deployed at the ends of the user's limbs. The user's average moving speed v is the ratio of the distance between the first sensed position and the last sensed position to the corresponding time length of the user's ECG time domain. The larger the user safety performance value Q is, the more stable and safer the user's current state is. Conversely, the more unstable and dangerous the user's current state is. Four groups of user safety judgment thresholds are set in the retrieval module, and the four groups of user safety judgment thresholds correspond to user safety judgments applied to electrocardiogram, blood oxygen saturation, heart rate and blood pressure levels. The retrieval module determines whether the user is safe based on the user safety judgment threshold and the user's physical state parameters retrieved in real time. If the judgment result is no, the module jumps to the refresh layer to run. If the judgment result is yes, the evaluation layer continues to execute.

2. The AI-based real-time physical examination status monitoring system according to claim 1, characterized in that: The monitoring layer includes a monitoring module, a sorting module and a storage module. The monitoring module is used to monitor the user's physical state parameters in real time. The sorting module is used to set the sorting logic, receive the user's physical state parameters monitored by the monitoring module, and apply the sorting logic to sort the received user's physical state parameters. The storage module is used to receive the remaining user's physical state parameters sorted in the sorting module, store the user's physical state parameters, and synchronously upload them to the cloud for backup; Among them, the monitoring module includes: a wearable electrocardiogram monitor, a wearable blood oxygen saturation monitor, and a heart rate and blood pressure smart bracelet. The user's body state parameters are the parameters collected by the wearable electrocardiogram monitor, the wearable blood oxygen saturation monitor, and the heart rate and blood pressure smart bracelet. The storage module is bound to a set of preset cloud databases. The operation of uploading the user's body state parameters to the cloud backup in the storage module is to copy the user's body state parameters, send the copied user's body state parameters to the cloud database, and store them in the cloud database.

3. The AI-based real-time physical examination status monitoring system according to claim 1, characterized in that: The sorting logic set in the sorting module is expressed as: Logic1: Select the user's electrocardiogram data monitored by the wearable electrocardiogram monitor as a reference for sorting the user's physical status parameters; Logic2: Segment the bands in the electrocardiogram based on their similarity; Logic 3: Obtain the segmentation results, identify the time threshold corresponding to each segmented continuous band in the segmentation results, and segment all user body state parameters based on the identified continuous band corresponding time threshold; The calculation formula of the band similarity in the electrocardiogram is: Where: SIMM (a, b) is the similarity between band a and band b in the electrocardiogram; ∠ a ,∠ b is the angle of band a and the angle of band b; is the slope of the preceding and following line segments on band a; L is the slope of the preceding and following line segments on band b; a , L b is the length of band a and band b; ω1, ω2, ω3 are weights; γ is the adjustment factor; Among them, band a and band b are two groups of continuous adjacent bands in the electrocardiogram, each group of bands is an open downward angle formed by two groups of valley points and one group of peak points connected to each other. When the similarity of the two groups of bands is not less than 95%, they are judged to be similar, otherwise, they are judged to be dissimilar, and the vertical line at the intersection of the two groups of bands is used as the band dividing line to divide the electrocardiogram, and the segmented results are recorded as continuous bands.

4. The AI-based real-time physical examination status monitoring system according to claim 3, characterized in that: The adjustment factor γ is 1 or -1. When the numerator of the fraction where the adjustment factor is located is less than or equal to the denominator, the adjustment factor γ is 1. When the numerator of the fraction where the adjustment factor is located is greater than the denominator, the adjustment factor γ is -1. The sum of the weights ω1, ω2, and ω3 is 1, and the values ​​of ω1, ω2, and ω3 are customized by the system end user. After all user body state parameters are divided in Logic3, each group of sub-user body state parameters is the sorting result of the user body state parameters running by the sorting module; Among them, the user's physical condition parameters include: electrocardiogram, blood oxygen saturation, heart rate and blood pressure.

5. The AI-based real-time physical examination status monitoring system according to claim 1, characterized in that: The user's physical state parameters retrieved by the retrieval module each time are: the user's physical state parameters stored after the monitoring layer runs once based on the operation cycle and performs the sorting operation, the evaluation module runs synchronously with the retrieval module, and after each retrieval module runs, the user's safety and user's safety abnormality situation are executed once, the retrieval module runs synchronously to monitor the running state of the evaluation module, and runs again after the evaluation module runs; The operation cycle used by the monitoring layer is defined or followed by the system end user in the control module: The lower the average similarity of the bands in the electrocardiogram of the user's physical state parameters, the shorter the monitoring layer operation cycle is; the higher the average similarity of the bands in the electrocardiogram, the longer the monitoring layer operation cycle is.

6. The AI-based real-time physical examination status monitoring system according to claim 1, characterized in that: The evaluation module stores the user security evaluation results, and performs further evaluation of the user security abnormality when the user security evaluation results stored therein are not less than three groups. The user security abnormality evaluation logic in the evaluation module is expressed as follows: Wherein: Q1, Q2, Q3 are the three consecutive groups of user security assessment results most recently stored in the assessment module.

7. The AI-based real-time physical examination status monitoring system according to claim 1 or 6, characterized in that: The warning and refresh layer includes a determination module, a warning module and a switching module. The determination module is used to receive the evaluation result of the user's safety abnormal situation in the evaluation module, and determine whether the user's current state is safe based on the evaluation result. The warning module is used to read the determination result of whether the user's current state is safe in the determination module. When the determination result is no, a warning message is issued. The switching module switches the operating state of the monitoring module in the monitoring layer, so that the monitoring module is independent of the operating cycle of the monitoring layer, continuously and in real time monitors the user's physical state parameters and feeds back to the system end user; The determination logic in the determination module is: In the formula, if both (1) and (2) are not true, it means that the user's current state is stable and safe; if (1) is true and (2) is not true, it means that the user's current state is questionable. If (1) is true and (2) is not true twice in a row, it means that the user's current state is unstable and dangerous; if both (1) and (2) are true, it means that the user's current state is unstable and dangerous; if (1) is not true and (2) is true, it means that the user's current state is unstable and dangerous; Among them, the early warning module is connected to the mobile computer device held by the system end user through a wireless network. The early warning message sent by the early warning module is text data or audio data preset by the system end. The early warning message is stored in the mobile computer device held by the system end user. When the early warning module is running, the early warning message is triggered to be broadcast in the mobile computer device.

8. The AI-based real-time physical examination status monitoring system according to claim 7, characterized in that: The switching module continuously runs to control the monitoring module. The monitoring module operation cycle controlled by the switching module is within the range of 3 seconds / time to 10 seconds / time. The switching module is manually controlled to be closed by the system end user. After the system end user controls the switching module to be closed, the system refreshes and runs; The switching module operates in conjunction with the early warning module.

9. The AI-based real-time physical examination status monitoring system according to claim 1, characterized in that: The retrieval module is interactively connected to the storage module via a wireless network, the storage module is interactively connected to the sorting module and the monitoring module via a wireless network, the retrieval module is interactively connected to the control module and the evaluation module via a wireless network, the evaluation module is interactively connected to the determination module via a wireless network, and the determination module is interactively connected to the early warning module and the switching module via a wireless network.

10. A real-time physical examination status monitoring method based on AI, the method being an implementation method of a real-time physical examination status monitoring system based on AI as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Monitor the user's physical condition parameters, set the parameter sorting logic, and sort and store the monitored user's physical condition parameters; Step 2: Retrieve the stored user body state parameters, and evaluate the user's safety and the abnormal change trend of the user's safety based on the user's body state parameters; Step 21: Setting stage of the user's body condition parameter monitoring cycle; Step 22: Setting the user security assessment logic; Step 23: Setting the user security abnormal situation assessment logic; Step 3: Obtain the user security and user security abnormality situation assessment results, determine whether the user is safe based on the assessment results, issue an early warning based on the determination results, and control the continuous operation of the monitoring module; Step 31: Setting the logic for determining whether the user is safe; Step 4: The monitoring module monitors the real-time feedback of the user's physical condition parameters.

Images