Medical data traceable management method and system based on Internet of Things

Abstract

The invention relates to the technical field of medical data traceability, and particularly discloses a medical data traceability management method and system based on the Internet of Things, and the method comprises the steps: analyzing the medical data transmission flow of a medical data uploading path, enabling an analysis result to comprise a load signal and a non-load signal, and carrying out the traceability management of the medical data based on the load signal; the method comprises the steps of processing and analyzing duration and occurrence frequency of load signals, marking corresponding historical uploading paths, analyzing the number of fluctuation paths in historical paths and load performance values of the fluctuation paths based on the fluctuation paths, generating fluctuation signals, and analyzing medical data needing to be traced based on the fluctuation signals. According to the method, the medical data needing to be traced are classified according to the traceability emergency degree, and the emergency traceability data are traced preferentially, so that the system resource occupation of the traceability request can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data tracing, and in particular to a medical data traceability management method and system based on the Internet of Things. Background Art

[0002] In the modern medical environment, data sources are no longer limited to traditional hospital information systems and paper medical records. The widespread use of IoT devices, wearable health monitoring devices, home medical monitoring instruments, and various smart medical devices in hospitals have generated massive amounts of data of various types. These data include physiological parameters, equipment operating status, environmental information, and other types, making data integration and management extremely complex. In medical disputes, medical accident investigations, and clinical research, being able to clearly trace the generation, modification, and use of medical data can help determine responsibilities, identify problems, and improve medical services.

[0003] However, the generation of massive and diverse medical data often causes server load. Under server load, medical data tracing may cause a certain degree of confusion.

[0004] To this end, we propose a medical data traceability management method and system based on the Internet of Things. Summary of the invention

[0005] The purpose of the present invention is to provide a medical data traceability management method and system based on the Internet of Things to solve the technical problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] In a first aspect, the present invention provides a medical data traceability management method based on the Internet of Things, comprising:

[0008] Step 1: Analyze the medical data transmission traffic of the medical data upload path, and the analysis results include load signals and non-load signals;

[0009] Step 2: Based on the load signal, the duration and occurrence times of the load signal are processed and analyzed to obtain a load performance value. If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuation path;

[0010] Step 3: Based on the fluctuation path, the number of fluctuation paths in the historical path and the load performance value of the fluctuation path are analyzed to obtain the fluctuation performance value BB. If the fluctuation performance value BB is greater than the fluctuation performance threshold, a fluctuation signal is generated.

[0011] Step 4: Based on the fluctuation signal, analyze the medical data that needs to be traced to obtain the traceability performance value ZS, sort based on the traceability performance value ZS to obtain a traceability sequence table, and trace the emergency traceability data during the load period based on the traceability sequence table.

[0012] As a further solution of the present invention: the load performance value FB is obtained as follows:

[0013] Obtain the time period for generating the load signal and the number of times the load signal appears, and analyze to obtain the load period ratio FS and the load number ratio FC;

[0014] The load period ratio FS and the load frequency ratio FC are weighted to obtain the load performance value FB.

[0015] As a further solution of the present invention: the load period ratio FS is obtained as follows:

[0016] In the historical monitoring cycle, the time period in which the load signal is generated is marked as a load period, and the duration corresponding to the load period is ratio-processed with the duration corresponding to the historical monitoring cycle to obtain a load period ratio FS.

[0017] As a further solution of the present invention: the load frequency ratio FC is obtained in the following manner:

[0018] During the historical monitoring period, the total number of occurrences of load signals and non-load signals is counted and marked as the total signal number. The number of occurrences of load signals is counted and ratioed with the total signal number to obtain the load number ratio FC.

[0019] As a further solution of the present invention: the fluctuation performance value BB is obtained as follows:

[0020] Obtain the number of fluctuation paths in the historical path and the load performance value of the fluctuation path, process and analyze to obtain the fluctuation number ratio BS and the fluctuation degree ratio BC;

[0021] The volatility quantity ratio BS and the volatility degree ratio BC are weighted to obtain the volatility performance value BB.

[0022] As a further solution of the present invention: the method of obtaining the fluctuation quantity ratio BS and the fluctuation degree ratio BC is as follows:

[0023] The number of fluctuation paths in the historical paths is counted and the ratio is processed with the total number of historical paths to obtain the fluctuation number ratio BS.

[0024] Obtain the load performance value of the fluctuation path, perform subtraction processing on it and the load performance threshold to obtain the fluctuation deviation value, sum and average all the fluctuation deviation values ​​to obtain the fluctuation deviation mean, perform ratio processing on the fluctuation deviation mean and the data anomaly threshold to obtain the fluctuation degree ratio BC.

[0025] As a further solution of the present invention: the retrospective performance value ZS is obtained as follows:

[0026] Obtain the medical data that needs to be traced, analyze to obtain the emergency medical data, obtain the cosine similarity value and the emergency medical data byte corresponding to the emergency medical data, and analyze to obtain the cosine similarity value deviation ratio YP and the byte ratio ZJ;

[0027] The cosine similarity value deviation ratio YP and the byte ratio ZJ are processed by the formula: The retrospective performance value ZS is calculated, where b1 and b2 are preset proportional coefficients, and both b1 and b2 are greater than 0.

[0028] As a further solution of the present invention: the cosine similarity value deviation ratio YP and the byte ratio ZJ are obtained as follows:

[0029] Obtain the cosine similarity value corresponding to the emergency medical data, perform absolute value processing on the difference between the cosine similarity value and the cosine similarity threshold to obtain the cosine similarity value deviation, perform ratio processing on the cosine similarity value deviation and the cosine similarity threshold to obtain the cosine similarity value deviation ratio YP;

[0030] All emergency medical data bytes are obtained, and the sum and average are processed to obtain the byte mean, and each emergency medical data byte is compared with the byte mean to obtain the byte ratio ZJ.

[0031] As a further solution of the present invention: the cosine similarity value is obtained as follows:

[0032] Use text analysis tools in natural language processing (NLP) technology to extract keywords of medical data that need to be traced and mark them as traceability keywords;

[0033] Integrate all preset emergency keywords into a preset keyword group, combine the traceability keyword with the preset keyword in the preset keyword group, and obtain a recombined keyword group;

[0034] The cosine similarity calculation formula is: , where A is the tracing keyword vector in the reorganized keyword group, B is the preset keyword vector of the reorganized keyword group, A・B is the dot product of the two vectors, ||A|| and ||B|| are the moduli of vector A and vector B respectively, and the cosine similarity value between the tracing keyword in the reorganized keyword group and the preset keyword is obtained.

[0035] In a second aspect, the present invention provides a medical data traceability management system based on the Internet of Things, comprising:

[0036] Data acquisition module: analyzes the medical data transmission flow of the medical data upload path, and the analysis results include load signals and non-load signals;

[0037] Fluctuation path marking module: Based on the load signal, the duration and number of occurrences of the load signal are processed and analyzed to obtain the load performance value. If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuation path;

[0038] Fluctuation signal generation module: Based on the fluctuation path, the number of fluctuation paths in the historical path and the load performance value of the fluctuation path are analyzed to obtain the fluctuation performance value BB. If the fluctuation performance value BB is greater than the fluctuation performance threshold, a fluctuation signal is generated;

[0039] Tracing sequence table determination module: Based on the fluctuation signal, the medical data to be traced is analyzed to obtain the tracing performance value ZS, which is sorted based on the tracing performance value ZS to obtain the tracing sequence table, and the emergency tracing data is traced during the load period based on the tracing sequence table.

[0040] Beneficial effects of the present invention:

[0041] (1) The present invention is based on analyzing the medical data transmission flow of the medical data upload path. The analysis results include load signals and non-load signals. Based on the load signal, the duration and number of occurrences of the load signal are processed and analyzed to obtain a load performance value. If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuation path. Based on the fluctuation path, the number of fluctuation paths in the historical path and the load performance value of the fluctuation path are analyzed to obtain a fluctuation performance value BB. If the fluctuation performance value BB is greater than the fluctuation performance threshold, a fluctuation signal is generated. The present invention is conducive to judging the overall volatility of historical medical data upload by analyzing the historical data of the medical data upload path;

[0042] (2) The present invention analyzes the medical data to be traced based on the fluctuation signal to obtain the tracing performance value ZS, sorts the data based on the tracing performance value ZS to obtain a tracing sequence table, and traces the urgent tracing data during the load period based on the tracing sequence table. The present invention classifies the medical data to be traced according to the urgency of tracing and gives priority to tracing the urgent tracing data, thereby effectively reducing the system resource usage of the tracing request. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described below in conjunction with the accompanying drawings.

[0044] Figure 1 It is a flowchart of a medical data traceability management method based on the Internet of Things according to an embodiment of the present invention;

[0045] Figure 2 The present invention is a system block diagram of a medical data traceability management system based on the Internet of Things. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0047] Embodiment 1:

[0048] See also Figure 1 As shown, a medical data traceability management method based on the Internet of Things according to an embodiment of the present invention includes the following steps:

[0049] Step 1: Obtain historical data of the medical data upload path, wherein the historical data includes data transmission flow, and analyze the historical data, wherein the analysis results include load signals and non-load signals;

[0050] During the historical monitoring period, the data transmission flow of the medical data upload path is obtained and compared with the medical data transmission flow threshold:

[0051] If the data transmission flow rate is greater than the data transmission flow rate threshold, a load signal is generated;

[0052] If the data transmission flow rate is less than or equal to the data transmission flow rate threshold, a non-load signal is generated;

[0053] It should be noted that the historical monitoring period includes but is not limited to one month, two months and three months;

[0054] Step 2: Based on the load signal, the duration and occurrence times of the load signal are processed and analyzed to obtain a load performance value. If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuation path;

[0055] In the historical monitoring cycle, the time period in which the load signal is generated is marked as the load period, and the duration corresponding to the load period is processed by ratio with the duration corresponding to the historical monitoring cycle to obtain the load period ratio FS;

[0056] In the historical monitoring period, the total number of occurrences of load signals and non-load signals is counted and marked as the total signal number. The number of occurrences of load signals is counted and compared with the total signal number to obtain the load number ratio FC.

[0057] The load period ratio FS and the load frequency ratio FC are processed by the formula: The load performance value FB is calculated, wherein s1 and s2 are both preset proportional coefficients, and both s1 and s2 are greater than 0;

[0058] It should be noted that the load performance value FB is obtained by processing the load period ratio FS and the load number ratio FC, which reflects the fluctuation of each historical path;

[0059] Compare the load performance value FB with the load performance threshold value:

[0060] If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuating path;

[0061] If the load performance value FB is less than the load performance threshold, the corresponding historical upload path is marked as a stable path;

[0062] Step 3: Based on the fluctuation path, the number of fluctuation paths in the historical path and the load performance value of the fluctuation path are analyzed to obtain the fluctuation performance value BB. If the fluctuation performance value BB is greater than the fluctuation performance threshold, a fluctuation signal is generated.

[0063] Count the number of fluctuation paths in the historical path, and compare it with the total number of historical paths to get the fluctuation number ratio BS;

[0064] Obtain the load performance value of the fluctuation path, perform subtraction processing on it and the load performance threshold to obtain the fluctuation deviation value, sum and average all the fluctuation deviation values ​​to obtain the fluctuation deviation mean, perform ratio processing on the fluctuation deviation mean and the data abnormality threshold to obtain the fluctuation degree ratio BC;

[0065] The fluctuation quantity ratio BS and the fluctuation degree ratio BC are processed by the formula: The volatility performance value BB is calculated, wherein a1 and a2 are both preset proportional coefficients, and a1 and a2 are both greater than 0;

[0066] It should be noted that the fluctuation performance value BB is obtained by processing the fluctuation quantity ratio BS and the fluctuation degree ratio BC. The fluctuation quantity ratio BS reflects the number of fluctuation paths in the historical path. The more fluctuation paths there are, the more unstable the historical upload path is. The fluctuation degree ratio BC reflects the fluctuation degree of the fluctuation path in the historical path. The greater the fluctuation degree, the more unstable the historical upload path is.

[0067] Compare the volatility performance value BB with the volatility performance threshold:

[0068] If the volatility performance value BB is greater than the volatility performance threshold, a volatility signal is generated;

[0069] If the volatility performance value BB is less than or equal to the volatility performance threshold, a stable signal is generated;

[0070] The technical solution of the embodiment of the present invention is mainly as follows: analyzing the medical data transmission traffic of the medical data upload path, the analysis results include load signals and non-load signals, based on the load signal, processing and analyzing the duration and number of occurrences of the load signal to obtain a load performance value, if the load performance value FB is greater than or equal to the load performance threshold, then marking the corresponding historical upload path as a fluctuating path, based on the fluctuating path, analyzing the number of fluctuating paths in the historical path and the load performance value of the fluctuating path to obtain a fluctuation performance value BB, if the fluctuation performance value BB is greater than the fluctuation performance threshold, then generating a fluctuation signal, the present invention analyzes the historical data of the medical data upload path, which is conducive to judging the overall volatility of historical medical data uploads.

[0071] Embodiment 2:

[0072] Based on Example 1, please refer to Figure 1 As shown, the medical data traceability management method based on the Internet of Things described in the embodiment of the present invention also includes the following steps:

[0073] Step 4: Based on the fluctuation signal, analyze the medical data to be traced to obtain the traceability performance value ZS, sort based on the traceability performance value ZS, obtain the traceability sequence table, and trace the emergency traceability data during the load period based on the traceability sequence table;

[0074] Use text analysis tools in natural language processing (NLP) technology to extract keywords of medical data that need to be traced and mark them as traceability keywords;

[0075] Integrate all preset emergency keywords into a preset keyword group, combine the traceability keyword with the preset keyword in the preset keyword group, and obtain a recombined keyword group;

[0076] It should be noted that the preset emergency keywords are set by those skilled in the art based on historical experience;

[0077] Get the cosine similarity value of each recombinant keyword group, and compare the cosine similarity value of each recombinant keyword group with the cosine similarity threshold:

[0078] If the cosine similarity value is less than the cosine similarity threshold, the recombined keyword group is ungrouped;

[0079] If the cosine similarity value is greater than or equal to the cosine similarity threshold, it means that the traceability keyword in the reorganized keyword group is similar to the preset keyword, and the medical data corresponding to the traceability keyword in the reorganized keyword group is marked as urgent traceability data;

[0080] It should be noted that if no preset keywords or traceability keywords remain after the reorganization is completed, the reorganization operation is stopped;

[0081] If the number of remaining traceability keywords is not 1 after the reorganization is completed, the reorganization operation will continue;

[0082] The cosine similarity value is obtained as follows:

[0083] The cosine similarity calculation formula is: , where A is the tracing keyword vector in the reorganized keyword group, B is the preset keyword vector of the reorganized keyword group, A・B is the dot product of the two vectors, ||A|| and ||B|| are the moduli of vector A and vector B respectively, and the cosine similarity value between the tracing keyword in the reorganized keyword group and the preset keyword is obtained;

[0084] For example, for "hypertension" and "blood pressure rises", all possible characters are used as a vocabulary, and the number of times the characters appear in each string is counted to form a vector. For "hypertension", the characters "high", "blood", "pressure", and "rise" in the vocabulary, and the character occurrence vector A is [1,1,1,0], and for "blood pressure rises", the character occurrence vector B is [1,1,1,1];

[0085] It should be noted that, among all the recombined keyword groups, if there is a cosine similarity value corresponding to a recombined keyword group, it means that there is a preset keyword similar to the tracing keyword in the preset keyword group, and then the medical data corresponding to the tracing keyword can be marked as urgent medical data. If there is no cosine similarity value corresponding to a recombined keyword group, it means that there is no keyword similar to the tracing keyword in the preset keyword, and then the medical data corresponding to the tracing keyword can be marked as non-urgent medical data. Based on the non-urgent medical data, the non-urgent medical data can be traced when the non-load signal is generated;

[0086] Obtain the cosine similarity value corresponding to the emergency medical data, perform absolute value processing on the difference between the cosine similarity value and the cosine similarity threshold to obtain the cosine similarity value deviation, perform ratio processing on the cosine similarity value deviation and the cosine similarity threshold to obtain the cosine similarity value deviation ratio YP;

[0087] Obtain all emergency medical data bytes, sum and average them to obtain a byte mean, and compare each emergency medical data byte with the byte mean to obtain a byte ratio ZJ;

[0088] The cosine similarity value deviation ratio YP and the byte ratio ZJ are processed by the formula: The retrospective performance value ZS is calculated, where b1 and b2 are preset proportional coefficients, and both b1 and b2 are greater than 0;

[0089] Sort the traceability performance values ​​ZS corresponding to the emergency medical data from large to small to obtain a traceability sequence table, and trace the emergency traceability data during the load period based on the traceability sequence table to reduce the system resources occupied by traceability requests;

[0090] The technical solution of the embodiment of the present invention is mainly as follows: based on the fluctuation signal, the medical data that needs to be traced is analyzed to obtain the traceability performance value ZS, the traceability performance value ZS is sorted to obtain the traceability sequence table, and the urgent traceability data is traced during the load period based on the traceability sequence table. The present invention can effectively reduce the system resource occupation of the traceability request by classifying the medical data that needs to be traced according to the traceability urgency and giving priority to the urgent traceability data.

[0091] Embodiment 3:

[0092] Based on Example 1 and Example 2, please refer to Figure 1 , Figure 2 As shown, a medical data traceability management system based on the Internet of Things according to an embodiment of the present invention includes:

[0093] Data acquisition module: analyzes the data transmission flow of the medical data upload path, and the analysis results include load signals and non-load signals;

[0094] Fluctuation path marking module: Based on the load signal, the duration and number of occurrences of the load signal are processed and analyzed to obtain the load performance value. If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuation path;

[0095] Fluctuation signal generation module: Based on the fluctuation path, the number of fluctuation paths in the historical path and the load performance value of the fluctuation path are analyzed to obtain the fluctuation performance value BB. If the fluctuation performance value BB is greater than the fluctuation performance threshold, a fluctuation signal is generated;

[0096] Tracing sequence table determination module: Based on the fluctuation signal, the medical data to be traced is analyzed to obtain the tracing performance value ZS, which is sorted based on the tracing performance value ZS to obtain the tracing sequence table, and the emergency tracing data is traced during the load period based on the tracing sequence table.

[0097] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A medical data traceability management method based on the Internet of Things, characterized in that: include: Step 1: Analyze the medical data transmission traffic of the medical data upload path, and the analysis results include load signals and non-load signals; Step 2: Based on the load signal, the duration and the number of occurrences of the load signal are processed and analyzed to obtain a load performance value. If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuation path; Step 3: Based on the fluctuation path, the number of fluctuation paths in the historical path and the load performance value of the fluctuation path are analyzed to obtain the fluctuation performance value BB. If the fluctuation performance value BB is greater than the fluctuation performance threshold, a fluctuation signal is generated. Step 4: Based on the fluctuation signal, analyze the medical data that needs to be traced to obtain the traceability performance value ZS, sort based on the traceability performance value ZS to obtain a traceability sequence table, and trace the emergency traceability data during the load period based on the traceability sequence table.

2. According to the method for traceability management of medical data based on the Internet of Things according to claim 1, it is characterized in that: The load performance value FB is obtained as follows: Obtain the time period for generating the load signal and the number of times the load signal appears, and analyze to obtain the load period ratio FS and the load number ratio FC; The load period ratio FS and the load frequency ratio FC are weighted to obtain the load performance value FB.

3. According to the method for traceability management of medical data based on the Internet of Things according to claim 2, it is characterized in that: The load period ratio FS is obtained as follows: In the historical monitoring cycle, the time period in which the load signal is generated is marked as a load period, and the duration corresponding to the load period is ratio-processed with the duration corresponding to the historical monitoring cycle to obtain a load period ratio FS.

4. The method for traceability management of medical data based on the Internet of Things according to claim 2, characterized in that: The load times ratio FC is obtained as follows: During the historical monitoring period, the total number of occurrences of load signals and non-load signals is counted and marked as the total signal number. The number of occurrences of load signals is counted and ratioed with the total signal number to obtain the load number ratio FC.

5. The method for traceability management of medical data based on the Internet of Things according to claim 1, characterized in that: The method for obtaining the fluctuation performance value BB is as follows: Obtain the number of fluctuation paths in the historical path and the load performance value of the fluctuation path, process and analyze to obtain the fluctuation number ratio BS and the fluctuation degree ratio BC; The volatility quantity ratio BS and the volatility degree ratio BC are weighted to obtain the volatility performance value BB.

6. The method for traceability management of medical data based on the Internet of Things according to claim 5, characterized in that: The method for obtaining the fluctuation quantity ratio BS and the fluctuation degree ratio BC is as follows: Count the number of fluctuation paths in the historical path, and compare it with the total number of historical paths to get the fluctuation number ratio BS; Obtain the load performance value of the fluctuation path, perform subtraction processing on it and the load performance threshold to obtain the fluctuation deviation value, sum and average all the fluctuation deviation values ​​to obtain the fluctuation deviation mean, perform ratio processing on the fluctuation deviation mean and the data anomaly threshold to obtain the fluctuation degree ratio BC.

7. The method for traceability management of medical data based on the Internet of Things according to claim 1, characterized in that: The retrospective performance value ZS is obtained as follows: Obtain the medical data that needs to be traced, analyze to obtain the emergency medical data, obtain the cosine similarity value and the emergency medical data byte corresponding to the emergency medical data, and analyze to obtain the cosine similarity value deviation ratio YP and the byte ratio ZJ; The cosine similarity value deviation ratio YP and the byte ratio ZJ are processed by the formula: The retrospective performance value ZS is calculated, where b1 and b2 are preset proportional coefficients, and both b1 and b2 are greater than 0.

8. The method for traceability management of medical data based on the Internet of Things according to claim 7, characterized in that: The cosine similarity value deviation ratio YP and the byte ratio ZJ are obtained as follows: Obtain the cosine similarity value corresponding to the emergency medical data, perform absolute value processing on the difference between the cosine similarity value and the cosine similarity threshold to obtain the cosine similarity value deviation, perform ratio processing on the cosine similarity value deviation and the cosine similarity threshold to obtain the cosine similarity value deviation ratio YP; All emergency medical data bytes are obtained, and the sum and average are processed to obtain the byte mean, and each emergency medical data byte is compared with the byte mean to obtain the byte ratio ZJ.

9. The method for traceability management of medical data based on the Internet of Things according to claim 8, characterized in that: The cosine similarity value is obtained as follows: Use text analysis tools in natural language processing (NLP) technology to extract keywords of medical data that need to be traced and mark them as traceability keywords; Integrate all preset emergency keywords into a preset keyword group, combine the traceability keyword with the preset keyword in the preset keyword group, and obtain a recombined keyword group; The cosine similarity calculation formula is: , where A is the tracing keyword vector in the reorganized keyword group, B is the preset keyword vector of the reorganized keyword group, A・B is the dot product of the two vectors, ||A|| and ||B|| are the moduli of vector A and vector B respectively, and the cosine similarity value between the tracing keyword in the reorganized keyword group and the preset keyword is obtained.

10. A medical data traceability management system based on the Internet of Things, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Data acquisition module: analyzes the medical data transmission flow of the medical data upload path, and the analysis results include load signals and non-load signals; Fluctuation path marking module: Based on the load signal, the duration and number of occurrences of the load signal are processed and analyzed to obtain the load performance value. If the load performance value FB is greater than or equal to the load performance threshold, the corresponding historical upload path is marked as a fluctuation path; Fluctuation signal generation module: Based on the fluctuation path, the number of fluctuation paths in the historical path and the load performance value of the fluctuation path are analyzed to obtain the fluctuation performance value BB. If the fluctuation performance value BB is greater than the fluctuation performance threshold, a fluctuation signal is generated; Tracing sequence table determination module: Based on the fluctuation signal, the medical data to be traced is analyzed to obtain the tracing performance value ZS, which is sorted based on the tracing performance value ZS to obtain the tracing sequence table, and the emergency tracing data is traced during the load period based on the tracing sequence table.

Images