Emergency fall prevention monitoring method and system for emergency monitoring

Abstract

The application provides an emergency fall prevention monitoring method and system for emergency monitoring. According to the target early warning parameter corresponding to each fall hidden danger element, the first emergency monitoring data is subjected to early warning processing to obtain fall hidden danger prompt data. In the above process, the first emergency monitoring data, the second emergency monitoring data and the analysis result characteristics can be processed to obtain the target early warning parameter corresponding to each fall hidden danger element. According to the target early warning parameter corresponding to each fall hidden danger element, the first emergency monitoring data is subjected to early warning processing to obtain fall hidden danger prompt data. The hidden danger point can be prompted in advance, so as to reduce the risk of falling injury of the patient and the family members.

Description

Technical Field

[0001] This application relates to the field of information monitoring technology, and more specifically, to an emergency fall prevention monitoring method and system for emergency monitoring. Background Technology

[0002] Hospitals have a high volume of people, including both healthy individuals and patients. Falls can lead to injuries to healthy people and worsen the condition of patients. Therefore, it is necessary to provide warnings about potential fall hazards. However, improving the accuracy of these warnings is currently a difficult problem to solve. Summary of the Invention

[0003] To address the technical problems existing in related technologies, this application provides an emergency fall prevention monitoring method and system for emergency monitoring.

[0004] Firstly, an emergency fall prevention monitoring method for emergency room monitoring is provided, including:

[0005] Acquire the first emergency monitoring data that needs to be processed, the first emergency monitoring data including at least one fall hazard element;

[0006] The first emergency monitoring data is analyzed and processed to obtain the second emergency monitoring data and the analysis result features. The second emergency monitoring data is used to represent the descriptive details of each attribute in the first emergency monitoring data.

[0007] The first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed to obtain the target warning parameters corresponding to each fall hazard element;

[0008] Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data is processed to obtain fall hazard warning data.

[0009] In this application, the first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed to obtain target warning parameters corresponding to each fall hazard element, including:

[0010] An artificial intelligence recognition thread is determined, wherein the artificial intelligence recognition thread includes at least one derivation unit, at least one compression unit, and at least one decision unit;

[0011] The first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed by the at least one derivative unit and the at least one decision unit to obtain at least one transitional emergency monitoring data.

[0012] The at least one compression unit and the at least one decision unit process the at least one transitional emergency monitoring data and the features of the analysis results to obtain the target early warning parameters corresponding to each fall hazard element.

[0013] In this application, the first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed by the not less than one derivative unit and the not less than one decision unit to obtain not less than one set of transitional emergency monitoring data, including:

[0014] The first emergency monitoring data and the second emergency monitoring data are integrated and processed to obtain the third emergency monitoring data;

[0015] The first derivative unit processes the third emergency monitoring data to obtain the first emergency monitoring data mining result;

[0016] The first decision unit processes the mining results and analysis results of the first emergency monitoring data to obtain the first transitional emergency monitoring data.

[0017] The a-1th transitional emergency monitoring data is processed by the a-th derivative unit to obtain the a-th emergency monitoring data mining result;

[0018] The a-th emergency monitoring data is obtained by processing the mining results and analysis results of the a-th emergency monitoring data through the a-th decision unit, where a takes the values ​​2, 3, ..., X, and X is the number of the derived units.

[0019] The not less than one transitional emergency monitoring data point is determined to include the X transitional emergency monitoring data points.

[0020] In this application, the derivation unit includes a feature extraction unit and an encoding unit; the a-th derivation unit processes the (a-1)th transitional emergency monitoring data to obtain the a-th emergency monitoring data mining result, including:

[0021] The feature extraction unit of the a-th coding unit processes the (a-1)-th transitional emergency monitoring data to obtain the a-th emergency monitoring hazard description content;

[0022] The a-th emergency monitoring hazard description content is downsampled by the encoding unit of the a-th encoding unit to obtain the a-th emergency monitoring data mining result.

[0023] In this application, the decision-making unit includes at least one dimensionless simplification unit, an important content identification unit, and a data debugging unit; the a-th decision-making unit processes the mining results of the a-th emergency monitoring data and the features of the analysis results to obtain the a-th transitional emergency monitoring data, including:

[0024] The first dimensionless simplification result is obtained by processing the mining result of the a-th emergency monitoring data through the first dimensionless simplification unit.

[0025] The first dimensionless simplification result and the features of the analysis result are processed by the important content identification unit to obtain the first candidate hidden danger point monitoring data;

[0026] The monitoring data of the first candidate potential hazard point and the mining result of the a-th emergency room monitoring data are fused to obtain the monitoring data of the second candidate potential hazard point.

[0027] The monitoring data of the second candidate hidden danger point is processed by the second dimensionless simplification unit to obtain the second dimensionless simplification result;

[0028] The data debugging unit processes the second dimensionless simplification result to obtain the monitoring data of the third candidate hidden danger point;

[0029] The monitoring data of the second candidate potential hazard point and the monitoring data of the third candidate potential hazard point are fused to obtain the a-th transitional emergency monitoring data.

[0030] In this application, the important content identification unit includes at least one feature extraction unit; the important content identification unit processes the features of the first dimensionless simplification result and the analysis result to obtain the first candidate hidden danger point monitoring data, including:

[0031] The first feature extraction unit performs data simplification processing on the first dimensionless simplification result to obtain the first simplification result.

[0032] The second feature extraction unit performs data simplification processing on the first dimensionless simplification result to obtain the second simplification result.

[0033] The first simplified result and the second simplified result are processed by a first function to obtain important content identification emergency monitoring data. The important content identification emergency monitoring data includes at least one fall hazard element and the matching relationship between each fall hazard element and the other fall hazard elements.

[0034] The first dimensionless simplification result is processed by the third feature extraction unit to obtain the important hidden danger description features;

[0035] The important hidden danger description features and the analysis result features are processed by a second function to obtain the monitoring data of the transitional hidden danger points;

[0036] Based on the monitoring data of the transitional potential hazard points and the emergency monitoring data of the important content identification, the monitoring data of the first candidate potential hazard points are determined.

[0037] In this application, the first candidate hazard point monitoring data is determined based on the transitional hazard point monitoring data and the important content identification emergency monitoring data, including:

[0038] The monitoring data of the aforementioned potential transition points are simplified to obtain a third simplified result;

[0039] The third simplified result and the set of important content identification results are processed by the first function to obtain the fourth simplified result;

[0040] The fourth simplified result is repaired to obtain the monitoring data of the first candidate hidden danger point.

[0041] In this application, the at least one compression unit and the at least one decision unit process the at least one transitional emergency monitoring data and the features of the analysis results to obtain target warning parameters corresponding to each fall hazard element, including:

[0042] The X+1 decision unit processes the Xth transitional emergency monitoring data and the features of the analysis results to obtain the first feature hazard point monitoring data;

[0043] The monitoring data of the first characteristic potential hazard point and the monitoring data of the Xth transitional emergency room are fused together to obtain the fusion result of the first potential hazard data.

[0044] The (X+b)th decision unit processes the fusion result of the (b-1)th hidden danger data and the features of the analysis result to obtain the monitoring data of the bth characteristic hidden danger point, where b takes the values ​​2, 3, ..., X in sequence. The fusion result of the (b-1)th hidden danger data is obtained by fusing the monitoring data of the (b-1)th characteristic hidden danger point and the (Xb-1)th transitional emergency monitoring data.

[0045] The b-th compression unit processes the monitoring data of the b-th characteristic hazard point to obtain the data fusion result of the b-th stripe hazard.

[0046] Based on the data fusion results of the Xth stripe hazard, the target warning parameters corresponding to each fall hazard element are determined.

[0047] In this application, the first emergency monitoring data is analyzed and processed to obtain second emergency monitoring data and the characteristics of the analysis results, including:

[0048] An analysis thread is determined, which includes Z residual units and Z loss units, where Z is an integer greater than or equal to 1;

[0049] The first emergency monitoring data is processed by Z encoding units through the Z residual units to obtain the key descriptive features corresponding to each fall hazard element.

[0050] The key descriptive features corresponding to each fall hazard element are compressed Z times using the Z loss units to obtain the second emergency monitoring data.

[0051] The emergency monitoring data output by the Zth loss unit is determined as the feature of the analysis result.

[0052] In this application, based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data is processed for warning to obtain fall hazard alert data, including:

[0053] Obtain the original emergency monitoring data corresponding to the first emergency monitoring data;

[0054] Determine the percentage between the first emergency monitoring data and the original emergency monitoring data;

[0055] Based on the percentage and the target warning parameter corresponding to each fall hazard element, determine the set warning parameter corresponding to each fall hazard element;

[0056] In the first emergency monitoring data, determine the attribute value of each fall hazard element;

[0057] For any fall hazard element, the product of the attribute value of the fall hazard element and the set warning parameter corresponding to the fall hazard element is determined as the target attribute value, thus obtaining the target attribute value corresponding to each fall hazard element.

[0058] The data for identifying fall hazard warnings includes at least one fall hazard element and the target attribute value corresponding to each fall hazard element.

[0059] Secondly, an emergency fall prevention monitoring system for emergency monitoring is provided, comprising a processor and a memory that communicate with each other, wherein the processor is used to read a computer program from the memory and execute it to implement the above-mentioned method.

[0060] This application provides an emergency fall prevention monitoring method and system for emergency monitoring. It acquires first emergency monitoring data requiring processing, which includes at least one fall hazard element. The first emergency monitoring data is analyzed to obtain second emergency monitoring data and analysis result features. The second emergency monitoring data represents the descriptive details of each attribute in the first emergency monitoring data. The first emergency monitoring data, second emergency monitoring data, and analysis result features are processed to obtain target warning parameters corresponding to each fall hazard element. Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data undergoes warning processing to obtain fall hazard alert data. In the above process, the first emergency monitoring data, second emergency monitoring data, and analysis result features are processed to obtain target warning parameters corresponding to each fall hazard element. Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data undergoes warning processing to obtain fall hazard alert data. This allows for early warning of potential hazards, thereby reducing the risk of falls for patients and their families. Attached Figure Description

[0061] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a flowchart of an emergency fall prevention monitoring method provided in an embodiment of this application. Detailed Implementation

[0063] To better understand the above technical solutions, the technical solutions of this application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this application and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. In the absence of conflict, the embodiments of this application and the technical features in the embodiments can be combined with each other.

[0064] Please see Figure 1 This paper illustrates an emergency fall prevention monitoring method for emergency monitoring, which may include the technical solutions described in steps S201-S204.

[0065] S201. Obtain the first emergency monitoring data that needs to be processed.

[0066] For example, the first emergency monitoring data is obtained through monitoring. For instance, the camera device can be a smart camera or a video camera. The executing entity in this application embodiment can be an emergency monitoring data processing device, or it can be an emergency monitoring data processing apparatus installed within the emergency monitoring data processing device.

[0067] The first emergency room monitoring data includes at least one potential fall risk factor.

[0068] Factors that could cause a fall include: water on the ground, uneven surfaces, etc.

[0069] The first emergency monitoring data that needs to be processed can be obtained in the following way: obtain the original emergency monitoring data and the preset data volume; process the original emergency monitoring data according to the preset data volume to obtain the first emergency monitoring data.

[0070] A preset data volume can be set in advance and stored in the preset storage space of the emergency monitoring data processing equipment. The preset data volume is smaller than the original emergency monitoring data volume, which reduces the amount of computation during the emergency monitoring data processing.

[0071] The raw emergency room monitoring data is captured by cameras in the emergency room monitoring data processing equipment, or acquired from other devices. Flickering occurs in the raw emergency room monitoring data. Once the raw emergency room monitoring data is set to a preset data volume, the resolution of the first batch of emergency room monitoring data is also adjusted to the resolution corresponding to the preset data volume.

[0072] S202. Analyze and process the first emergency room monitoring data to obtain the second emergency room monitoring data and the characteristics of the analysis results.

[0073] For example, the characteristics of the analysis results can be understood as the analysis of potential hazards and their locations in the monitoring data, such as locations with high pedestrian traffic, or those caused by sudden events.

[0074] The second emergency room monitoring data is used to represent the descriptive details of each attribute in the first emergency room monitoring data.

[0075] The first emergency room monitoring data can be analyzed and processed to obtain the second emergency room monitoring data and analysis result features as follows: An analysis thread is determined, comprising Z residual units and Z loss units, where Z is an integer greater than or equal to 1; the first emergency room monitoring data is processed through Z encoding units using the Z residual units to obtain the key descriptive features corresponding to each fall hazard element; the key descriptive features corresponding to each fall hazard element are compressed through Z compression units using the Z loss units to obtain the second emergency room monitoring data; the feature emergency room monitoring data output by the Zth loss unit is determined as the analysis result feature.

[0076] S203. Process the first emergency room monitoring data, the second emergency room monitoring data, and the characteristics of the analysis results to obtain the target warning parameters corresponding to each fall hazard element.

[0077] For example, the target warning parameter can be understood as being obtained based on the score of the hidden danger point, with each type of hidden danger corresponding to a separate warning parameter.

[0078] The target warning parameters corresponding to each fall hazard element can be obtained by processing the first emergency room monitoring data, the second emergency room monitoring data, and the features of the analysis results in the following manner: An artificial intelligence recognition thread is determined, which includes at least one derivative unit, at least one compression unit, and at least one decision unit; the first emergency room monitoring data, the second emergency room monitoring data, and the features of the analysis results are processed by at least one derivative unit and at least one decision unit to obtain at least one set of transitional emergency room monitoring data; the transitional emergency room monitoring data and the features of the analysis results are processed by at least one compression unit and at least one decision unit to obtain the target warning parameters corresponding to each fall hazard element.

[0079] S204. Based on the target warning parameters corresponding to each fall hazard element, perform warning processing on the first emergency monitoring data to obtain fall hazard warning data.

[0080] For example, the warning processing is based on the target warning parameters. For instance, if the target warning parameter is greater than a threshold, warning processing will be performed; if it is less than the threshold, warning processing will not be performed.

[0081] The fall hazard warning data can be obtained by processing the first emergency room monitoring data according to the target warning parameters corresponding to each fall hazard element in the following way: Obtain the original emergency room monitoring data corresponding to the first emergency room monitoring data; determine the percentage between the first emergency room monitoring data and the original emergency room monitoring data; determine the set warning parameter corresponding to each fall hazard element based on the percentage and the target warning parameter corresponding to each fall hazard element; determine the attribute value of each fall hazard element in the first emergency room monitoring data; for any fall hazard element, multiply the attribute value of the fall hazard element by the set warning parameter corresponding to the fall hazard element, and determine the target attribute value, thus obtaining the target attribute value corresponding to each fall hazard element; ensure that the fall hazard warning data includes at least one fall hazard element and the target attribute value corresponding to each fall hazard element.

[0082] The emergency fall prevention monitoring method provided in this application involves acquiring first emergency monitoring data that needs processing. The first emergency monitoring data is analyzed and processed to obtain second emergency monitoring data and analysis result features. The first emergency monitoring data, second emergency monitoring data, and analysis result features are then processed to obtain target warning parameters corresponding to each fall hazard element. Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data is processed to obtain fall hazard warning data. In the above process, the first emergency monitoring data, second emergency monitoring data, and analysis result features are processed to obtain target warning parameters corresponding to each fall hazard element. Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data is processed to obtain fall hazard warning data. This can minimize the risk of falls.

[0083] Another emergency fall prevention monitoring method for emergency monitoring provided in this application embodiment includes:

[0084] S401. Obtain the first emergency monitoring data that needs to be processed.

[0085] It is understandable that the execution process of S401 can be found in S201, and will not be repeated here.

[0086] S402. Analyze and process the first emergency room monitoring data to obtain the second emergency room monitoring data and the characteristics of the analysis results.

[0087] For example, the emergency monitoring data processing equipment acquires the first emergency monitoring data that needs to be processed, which is emergency monitoring data B. The emergency monitoring data processing equipment analyzes and processes emergency monitoring data B through an analysis thread to obtain the second emergency monitoring data B1 and the analysis result feature B.

[0088] S403, Determine the AI ​​recognition thread.

[0089] For example, the artificial intelligence recognition thread may include CNN, etc.

[0090] The artificial intelligence recognition thread includes at least one derivative unit, at least one compression unit, and at least one decision unit.

[0091] S404. Integrate and process the first and second emergency monitoring data to obtain the third emergency monitoring data.

[0092] The first and second emergency room monitoring data are integrated and processed to stitch them together along the trajectory dimension, resulting in the third emergency room monitoring data. The number of trajectories in the third emergency room monitoring data is the sum of the number of trajectories in the first and second emergency room monitoring data.

[0093] S405. The first derivative unit processes the third emergency monitoring data to obtain the first emergency monitoring data mining result.

[0094] The derived unit can perform convolution and downsampling processing on the third emergency monitoring data, and the height, width, and number of trajectories of the first emergency monitoring data mining result can be determined based on the parameters of the first derived unit in the artificial intelligence recognition thread.

[0095] S406. The first decision-making unit processes the characteristics of the first emergency monitoring data mining and analysis results to obtain the first transitional emergency monitoring data.

[0096] S407, Reset a to 2.

[0097] S408. The a-1th transitional emergency monitoring data is processed by the a-th derivative unit to obtain the a-th emergency monitoring data mining result.

[0098] The data mining result of the a-th emergency monitoring data can be obtained by processing the a-1 transitional emergency monitoring data through the a-th derivative unit as follows: the a-1 transitional emergency monitoring data is processed through the feature extraction unit of the a-th coding unit to obtain the description content of the a-th emergency monitoring hidden danger; the description content of the a-th emergency monitoring hidden danger is derived through the coding unit of the a-th coding unit to obtain the data mining result of the a-th emergency monitoring data.

[0099] Understandably, the processing procedure for the first derived unit is the same as that for the a-th derived unit.

[0100] S409. The a-th transitional emergency monitoring data is obtained by processing the mining and analysis results of the a-th emergency monitoring data through the a-th decision-making unit.

[0101] The decision-making unit includes at least one dimensionless simplification unit, an important content identification unit, and a data debugging unit.

[0102] The transitional emergency monitoring data can be obtained by processing the mining and analysis results of the a-th emergency monitoring data through the a-th decision unit as follows: The mining results of the a-th emergency monitoring data are processed through the first dimensionless simplification unit to obtain the first dimensionless simplification result; the first dimensionless simplification result and analysis results are processed through the important content identification unit to obtain the first candidate hazard point monitoring data; the first candidate hazard point monitoring data and the mining results of the a-th emergency monitoring data are fused to obtain the second candidate hazard point monitoring data; the second candidate hazard point monitoring data is processed through the second dimensionless simplification unit to obtain the second dimensionless simplification result; the second dimensionless simplification result is processed through the data debugging unit to obtain the third candidate hazard point monitoring data; the second candidate hazard point monitoring data and the third candidate hazard point monitoring data are fused to obtain the a-th transitional emergency monitoring data.

[0103] The height, width, and number of trajectories of the first transitional emergency monitoring data are the same as those of the first emergency monitoring data mining result.

[0104] The processing procedure of the decision-making unit is described below. The processing procedure of the decision-making unit provided in this application embodiment includes a decision-making unit. The decision-making unit includes two dimensionless simplification units, an important content identification unit, and a data debugging unit. The first dimensionless simplification unit of the decision-making unit processes the mining results of emergency monitoring data to obtain a first dimensionless simplification result. The important content identification unit of the decision-making unit processes the first dimensionless simplification result and the features of the analysis results to obtain first candidate hidden danger point monitoring data. The first candidate hidden danger point monitoring data and the mining result of the a-th emergency monitoring data are fused to obtain second candidate hidden danger point monitoring data. The second candidate hidden danger point monitoring data is processed by the second dimensionless simplification unit of the decision-making unit to obtain a second dimensionless simplification result. The data debugging unit of the decision-making unit processes the second dimensionless simplification result to obtain third candidate hidden danger point monitoring data. The second candidate hidden danger point monitoring data and the third candidate hidden danger point monitoring data are fused to obtain transitional emergency monitoring data.

[0105] The important content identification unit includes at least one feature extraction unit. The important content identification unit can process the first dimensionless simplification result and the analysis result features to obtain the first candidate hazard monitoring data in the following manner: The first feature extraction unit simplifies the first dimensionless simplification result to obtain a first simplified result; the second feature extraction unit simplifies the first dimensionless simplification result to obtain a second simplified result; the first and second simplified results are processed by a first function to obtain important content identification emergency monitoring data, which includes at least one fall hazard element and the matching relationship between each fall hazard element and the other fall hazard elements; the third feature extraction unit processes the first dimensionless simplification result to obtain important hazard description features; the important hazard description features and the analysis result features are processed by a second function to obtain transitional hazard monitoring data; based on the transitional hazard monitoring data and the important content identification emergency monitoring data, the first candidate hazard monitoring data is determined.

[0106] The first candidate hazard monitoring data can be determined based on the transitional hazard monitoring data and the important content identification emergency monitoring data in the following manner: the transitional hazard monitoring data is simplified to obtain a third simplified result; the third simplified result and the important content identification result set are processed by a first function to obtain a fourth simplified result; the fourth simplified result is repaired to obtain the first candidate hazard monitoring data.

[0107] S410. Determine whether a is equal to X.

[0108] If so, execute S411.

[0109] If not, update 'a' to 'a+1' and execute S408.

[0110] S411. Identify at least one transitional emergency monitoring data point, including X transitional emergency monitoring data points.

[0111] S412. Process at least one transitional emergency monitoring data and analysis result features through at least one compression unit and at least one decision unit to obtain the target early warning parameters corresponding to each fall hazard element.

[0112] The target warning parameters corresponding to each fall hazard element can be obtained by processing at least one transitional emergency monitoring data and analysis result features through at least one compression unit and at least one decision unit as follows: The X+1th decision unit processes the Xth transitional emergency monitoring data and analysis result features to obtain the first characteristic hazard point monitoring data; the first characteristic hazard point monitoring data and the Xth transitional emergency monitoring data are fused to obtain the first hazard data fusion result; the X+bth decision unit processes the b-1th hazard data fusion result and analysis result features to obtain the bth characteristic hazard point monitoring data, where b takes values ​​of 2, 3, ..., X, and the b-1th hazard data fusion result is obtained by fusing the b-1th characteristic hazard point monitoring data and the Xb-1th transitional emergency monitoring data; the bth compression unit processes the bth characteristic hazard point monitoring data to obtain the bth stripe hazard data fusion result; based on the Xth stripe hazard data fusion result, the target warning parameters corresponding to each fall hazard element are determined.

[0113] It is understood that the processing procedure of each decision unit in the analysis thread provided in the embodiments of this application is the same, and will not be described again here.

[0114] S413. Based on the target warning parameters corresponding to each fall hazard element, perform warning processing on the first emergency monitoring data to obtain fall hazard warning data.

[0115] The following is a description of the process for obtaining fall hazard warning data provided in this application embodiment, including first emergency room monitoring data and fall hazard warning data. The first emergency room monitoring data contains dark striped areas. After processing by an analysis thread and an artificial intelligence recognition thread corresponding to the first emergency room monitoring data, target warning parameters corresponding to each fall hazard element are obtained. Based on the target warning parameters corresponding to each fall hazard element, the first emergency room monitoring data is processed to obtain fall hazard warning data.

[0116] Before processing emergency monitoring data through the analysis thread and the artificial intelligence recognition thread, the analysis thread and the artificial intelligence recognition thread need to be trained to determine their respective parameters.

[0117] Thread training can be performed as follows: Obtain a training dataset, which includes at least one sample of emergency monitoring data, analytical emergency monitoring data corresponding to each sample of emergency monitoring data, at least one standard warning parameter corresponding to each sample of emergency monitoring data, and standard emergency monitoring data corresponding to each sample of emergency monitoring data; determine the original threads, which include an analysis thread and an artificial intelligence recognition thread; perform the first iteration training on the original threads using the training dataset to obtain the first transition thread; perform the (a+1)th iteration training on the a-th transition thread using the training dataset to obtain the (a+1)th transition thread, where a takes values ​​of 1, 2, 3, ..., until the a-th transition thread converges, and determine the a-th transition thread as the target thread, which includes the trained analysis thread and the artificial intelligence recognition thread.

[0118] The a+1th transition thread can be obtained by training the a-th transition thread using the training dataset for the (a+1)th iteration: The a-th transition thread processes the sample emergency monitoring data in the training dataset to obtain the prediction result, which includes the predicted emergency monitoring hazard description content corresponding to the sample emergency monitoring data, at least one predicted warning parameter, and the predicted emergency monitoring data; the loss value is determined based on the analyzed emergency monitoring data corresponding to the sample emergency monitoring data, at least one standard warning parameter, standard emergency monitoring data, and the prediction result; the thread parameters of the a-th transition thread are updated based on the loss value to obtain the (a+1)th transition thread.

[0119] The emergency fall prevention monitoring method provided in this application involves acquiring first emergency monitoring data that needs processing. The first emergency monitoring data is analyzed and processed to obtain second emergency monitoring data and analysis result features. An artificial intelligence recognition thread is determined. The first emergency monitoring data, second emergency monitoring data, and analysis result features are processed through at least one derivative unit and at least one decision unit to obtain at least one transitional emergency monitoring data. The at least one transitional emergency monitoring data and analysis result features are processed through at least one compression unit and at least one decision unit to obtain target warning parameters corresponding to each fall hazard element. Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data is processed for warning purposes to obtain fall hazard alert data.

[0120] The emergency monitoring data processing procedure provided in this application includes an analysis thread and an artificial intelligence recognition thread. The analysis thread and the artificial intelligence recognition thread are located in the emergency monitoring data processing device. The emergency monitoring data processing device can be a camera device, a terminal device, etc. For example, the camera device can be a smart camera or a video camera. The terminal device can be a mobile phone, tablet computer, computer, etc. The emergency monitoring data processing device acquires raw emergency monitoring data and a preset data volume, and processes the raw emergency monitoring data according to the preset data volume to obtain the first emergency monitoring data.

[0121] The emergency monitoring data processing procedure provided in this application embodiment obtains first emergency monitoring data that needs to be processed. The first emergency monitoring data is analyzed and processed to obtain second emergency monitoring data and analysis result features. An artificial intelligence recognition thread is determined. The first emergency monitoring data, the second emergency monitoring data, and the analysis result features are processed through at least one derivative unit and at least one decision unit to obtain at least one transitional emergency monitoring data. The at least one transitional emergency monitoring data and the analysis result features are processed through at least one compression unit and at least one decision unit to obtain the target warning parameters corresponding to each fall hazard element.

[0122] Based on the above, an emergency fall prevention monitoring device for emergency monitoring is provided, the device comprising:

[0123] The data acquisition module is used to acquire the first emergency monitoring data that needs to be processed, and the first emergency monitoring data includes at least one fall hazard element;

[0124] The feature acquisition module is used to analyze and process the first emergency monitoring data to obtain the second emergency monitoring data and the analysis result features. The second emergency monitoring data is used to represent the descriptive details of each attribute in the first emergency monitoring data.

[0125] The parameter acquisition module is used to process the first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results to obtain the target warning parameters corresponding to each fall hazard element;

[0126] The data prompting module is used to process the first emergency monitoring data for early warning based on the target early warning parameters corresponding to each fall hazard element, and obtain fall hazard prompting data.

[0127] Based on the above, an emergency fall prevention monitoring system for emergency monitoring is shown, including a processor and a memory that communicate with each other. The processor is used to read computer programs from the memory and execute them to implement the above-described method.

[0128] Based on the above, a computer-readable storage medium is also provided, on which a computer program stored implements the above method during runtime.

[0129] In summary, based on the above scheme, the first emergency room monitoring data that needs to be processed is obtained. This first emergency room monitoring data includes at least one fall hazard element. The first emergency room monitoring data is analyzed and processed to obtain second emergency room monitoring data and analysis result features. The second emergency room monitoring data is used to represent the descriptive details of each attribute in the first emergency room monitoring data. The first emergency room monitoring data, the second emergency room monitoring data, and the analysis result features are processed to obtain the target warning parameters corresponding to each fall hazard element. Based on the target warning parameters corresponding to each fall hazard element, the first emergency room monitoring data is processed to obtain fall hazard warning data. In the above process, the first emergency room monitoring data, the second emergency room monitoring data, and the analysis result features are processed to obtain the target warning parameters corresponding to each fall hazard element. Based on the target warning parameters corresponding to each fall hazard element, the first emergency room monitoring data is processed to obtain fall hazard warning data. This allows for early warning of potential hazards, thereby reducing the risk of falls for patients and their families.

[0130] It should be understood that the systems and modules described above can be implemented in various ways. For example, in some embodiments, the systems and modules can be implemented by hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the methods and systems described above can be implemented using computer-executable instructions and / or included in processor control code, for example, such code provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and modules of this application can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field-programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, or by a combination of the aforementioned hardware circuits and software (e.g., firmware).

[0131] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects may be any one or a combination of the above, or any other possible beneficial effects.

Claims

1. An emergency fall prevention monitoring method for emergency room monitoring, characterized in that, include: Acquire the first emergency monitoring data that needs to be processed, the first emergency monitoring data including at least one fall hazard element; The first emergency monitoring data is analyzed and processed to obtain the second emergency monitoring data and the analysis result features. The second emergency monitoring data is used to represent the descriptive details of each attribute in the first emergency monitoring data. The first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed to obtain the target warning parameters corresponding to each fall hazard element; Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data is processed to obtain fall hazard warning data; Specifically, the first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed to obtain target warning parameters corresponding to each fall hazard element, including: An artificial intelligence recognition thread is determined, wherein the artificial intelligence recognition thread includes at least one derivation unit, at least one compression unit, and at least one decision unit; The first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed by the at least one derivative unit and the at least one decision unit to obtain at least one transitional emergency monitoring data. The at least one compression unit and the at least one decision unit process the at least one transitional emergency monitoring data and the features of the analysis results to obtain the target warning parameters corresponding to each fall hazard element; Specifically, the first emergency monitoring data, the second emergency monitoring data, and the features of the analysis results are processed by at least one derivative unit and at least one decision unit to obtain at least one set of transitional emergency monitoring data, including: The first emergency monitoring data and the second emergency monitoring data are integrated and processed to obtain the third emergency monitoring data; The first derivative unit processes the third emergency monitoring data to obtain the first emergency monitoring data mining result; The first decision unit processes the mining results and analysis results of the first emergency monitoring data to obtain the first transitional emergency monitoring data. The a-1th transitional emergency monitoring data is processed by the a-th derivative unit to obtain the a-th emergency monitoring data mining result; The a-th emergency monitoring data is obtained by processing the mining results and analysis results of the a-th emergency monitoring data through the a-th decision unit, where a takes the values ​​2, 3, ..., X, and X is the number of the derived units. The not less than one transitional emergency monitoring data point is determined to include the X transitional emergency monitoring data points.

2. The method according to claim 1, characterized in that, The derivation unit includes a feature extraction unit and an encoding unit; the (a-1)th transitional emergency monitoring data is processed by the (a-1)th derivation unit to obtain the mining result of the (a)th emergency monitoring data, including: The feature extraction unit of the a-th coding unit processes the (a-1)-th transitional emergency monitoring data to obtain the a-th emergency monitoring hazard description content; The a-th emergency monitoring hazard description content is downsampled by the encoding unit of the a-th encoding unit to obtain the a-th emergency monitoring data mining result.

3. The method according to claim 1 or 2, characterized in that, The decision-making unit includes at least one dimensionless simplification unit, an important content identification unit, and a data debugging unit; the a-th decision-making unit processes the mining results and analysis results of the a-th emergency monitoring data to obtain the a-th transitional emergency monitoring data, including: The first dimensionless simplification result is obtained by processing the mining result of the a-th emergency monitoring data through the first dimensionless simplification unit. The first dimensionless simplification result and the features of the analysis result are processed by the important content identification unit to obtain the first candidate hidden danger point monitoring data; The monitoring data of the first candidate potential hazard point and the mining result of the a-th emergency room monitoring data are fused to obtain the monitoring data of the second candidate potential hazard point. The monitoring data of the second candidate hidden danger point is processed by the second dimensionless simplification unit to obtain the second dimensionless simplification result; The data debugging unit processes the second dimensionless simplification result to obtain the monitoring data of the third candidate hidden danger point; The monitoring data of the second candidate potential hazard point and the monitoring data of the third candidate potential hazard point are fused to obtain the a-th transitional emergency monitoring data.

4. The method according to claim 3, characterized in that, The important content identification unit includes at least one feature extraction unit; the important content identification unit processes the features of the first dimensionless simplification result and the analysis result to obtain the first candidate hidden danger point monitoring data, including: The first feature extraction unit performs data simplification processing on the first dimensionless simplification result to obtain the first simplification result. The second feature extraction unit performs data simplification processing on the first dimensionless simplification result to obtain the second simplification result. The first simplified result and the second simplified result are processed by a first function to obtain important content identification emergency monitoring data. The important content identification emergency monitoring data includes at least one fall hazard element and the matching relationship between each fall hazard element and the other fall hazard elements. The first dimensionless simplification result is processed by the third feature extraction unit to obtain the important hidden danger description features; The important hidden danger description features and the analysis result features are processed by a second function to obtain the monitoring data of the transitional hidden danger points; Based on the monitoring data of the transitional potential hazard points and the identification of the important content in the emergency room monitoring data, the first candidate potential hazard point monitoring data is determined. Specifically, the monitoring data for the first candidate potential hazard point is determined based on the monitoring data of the transitional hazard point and the emergency monitoring data for identifying important content, including: The monitoring data of the aforementioned potential transition points are simplified to obtain a third simplified result; The third simplified result and the set of important content identification results are processed by the first function to obtain the fourth simplified result; The fourth simplified result is repaired to obtain the monitoring data of the first candidate hidden danger point.

5. The method according to claim 1, characterized in that, The at least one compression unit and the at least one decision unit process the at least one transitional emergency monitoring data and the features of the analysis results to obtain target warning parameters corresponding to each fall hazard element, including: The X+1 decision unit processes the Xth transitional emergency monitoring data and the features of the analysis results to obtain the first feature hazard point monitoring data; The monitoring data of the first characteristic potential hazard point and the monitoring data of the Xth transitional emergency room are fused together to obtain the fusion result of the first potential hazard data. The (X+b)th decision unit processes the fusion result of the (b-1)th hidden danger data and the features of the analysis result to obtain the monitoring data of the bth characteristic hidden danger point, where b takes the values ​​2, 3, ..., X in sequence. The fusion result of the (b-1)th hidden danger data is obtained by fusing the monitoring data of the (b-1)th characteristic hidden danger point and the (Xb-1)th transitional emergency monitoring data. The b-th compression unit processes the monitoring data of the b-th characteristic hazard point to obtain the data fusion result of the b-th stripe hazard. Based on the data fusion results of the Xth stripe hazard, the target warning parameters corresponding to each fall hazard element are determined.

6. The method according to any one of claims 1-2, characterized in that, The first emergency monitoring data is analyzed and processed to obtain the second emergency monitoring data and the characteristics of the analysis results, including: An analysis thread is determined, which includes Z residual units and Z loss units, where Z is an integer greater than or equal to 1; The first emergency monitoring data is processed by Z encoding units through the Z residual units to obtain the key descriptive features corresponding to each fall hazard element. The key descriptive features corresponding to each fall hazard element are compressed Z times using the Z loss units to obtain the second emergency monitoring data. The emergency monitoring data output by the Zth loss unit is determined as the feature of the analysis result.

7. The method according to any one of claims 1-2, characterized in that, Based on the target warning parameters corresponding to each fall hazard element, the first emergency monitoring data is processed for warning, resulting in fall hazard alert data, including: Obtain the original emergency monitoring data corresponding to the first emergency monitoring data; Determine the percentage between the first emergency monitoring data and the original emergency monitoring data; Based on the percentage and the target warning parameter corresponding to each fall hazard element, determine the set warning parameter corresponding to each fall hazard element; In the first emergency monitoring data, determine the attribute value of each fall hazard element; For any fall hazard element, the product of the attribute value of the fall hazard element and the set warning parameter corresponding to the fall hazard element is determined as the target attribute value, thus obtaining the target attribute value corresponding to each fall hazard element. The data for identifying fall hazard warnings includes at least one fall hazard element and the target attribute value corresponding to each fall hazard element.

8. An emergency fall prevention monitoring system for emergency room monitoring, characterized in that, The method includes a processor and a memory that communicate with each other, the processor being configured to read a computer program from the memory and execute it to implement the method of any one of claims 1-7.

Images