Physical examination system based on cloud calculation
A cloud computing and cloud service technology, applied in the medical field, can solve problems such as difficulty in discovering physical conditions, high cost of physical examination equipment, and difficulty in discovering major diseases.
Inactive Publication Date: 2016-08-31
吴本刚
0 Cites 4 Cited by
AI-Extracted Technical Summary
Problems solved by technology
[0003] At present, due to factors such as the high cost of medical examination equipment and the high requirement for professional skills, people's health checkups and physical status ch...
Method used
The present embodiment arranges physical examination data collection module 1, physical examination data processing module 2 and physical examination result display module 3, has realized the construction of physical examination system, and the user can not complete health examination, physical condition physical examination by hospital or physical examination center; Efficiently realize the processing of low-cost medical examination data, set up the credible combination evaluation sub-module 22, improve the credibility of the cloud service combination solution supporting big data services, and realize the most profitable use of cloud storage and computing resources, and The evaluation time is saved and the evaluation speed is improved; the physical examination data search sub-unit used to find the physical examination data required for the sub-task of the physical examination result analysis is set, which improves the efficiency of the physical examination data search and further improves the speed of analyzing the physical examination results. In this embodiment, the values of α=0.25 and β=0.45 are used, and the efficiency of medical examination data search is increased by 2.8%.
The present embodiment is provided with physical examination data collection module 1, physical examination data processing module 2 and physical examination result display module 3, has realized the construction of physical examination system, and the user can not complete health examination, physical condition physical examination by hospital or physical examination center; Efficiently realize the processing of low-cost medical examination data, set up the credible combination evaluation sub-module 22, improve the credibility of the cloud service combination solution supporting big data services, and realize the most profitable use of cloud storage and computing resources, and The evaluation time is saved and the evaluation speed is improved; the physical examination data search sub-unit used to find the physical examination data required for the sub-task of the physical examination result analysis is set, which improves the efficiency of the physical examination data search and further improves the speed of analyzing the physical examination results. In this embodiment, the values of α=0.26 and β=0.5 are used, and the efficiency of medical examination data search is increased by 2.5%.
The present embodiment is provided with physical examination data collection module 1, physical examination data processing module 2 and physical examination result display module 3, has realized the construction of physical examination system, and the user can not complete health examination, physical condition physical examination by hospital or physical examination center; Efficiently realize the processing of low-cost medical examination data, set up the credible combination evaluation sub-module 22, improve the credibility of the cloud service combination solution supporting big data services, ...
Abstract
The invention discloses a physical examination system based on cloud calculation. The system comprises a physical examination data collecting module, a physical examination data processing module and a physical examination result display module, wherein the physical examination data processing module comprises a task planning submodule, a credible combination assessment submodule, a task execution submodule and a physical examination callout submodule. According to the invention, health examination and physical state examination can be completed for users without going to hospitals or physical examination centers, physical examination data search efficiency is improved while the physical examination data is processed, the speed for analyzing the physical examination result is further increased, and the processing cost is lowered.
Application Domain
Data processing applicationsWeb data indexing +3
Technology Topic
Cloud computingPhysical examination +6
Image
Examples
- Experimental program(5)
Example Embodiment
[0038] Example 1
[0039] See figure 1 , figure 2 , The medical examination system based on cloud computing of this embodiment includes:
[0040] (1) Physical examination data collection module 1, used to collect required physical examination data through physical examination sensors according to physical examination requirements;
[0041] (2) Physical examination data processing module 2, used to process physical examination data and output physical examination results, including:
[0042] 1) The task planning sub-module 21 is used to divide the processing process of the physical examination data into data storage subtasks, index calculation subtasks, physical examination result analysis subtasks, and physical examination result storage subtasks, and match each subtask to meet its requirements. The required cloud service resource pool forms a cloud service portfolio plan to obtain the storage resources and computing resources needed in the big data processing process;
[0043] 2) The credible combination evaluation sub-module 22 is used to perform the evaluation of the cloud service combination plan according to the task planning of the big data service generated by the task planning sub-module 21, select the optimal cloud service combination plan, and provide corresponding solutions for each subtask The storage and computing resources are specifically:
[0044] A. According to the cloud service resource pool SP v And corresponding service quality Historical records, model the utility function X of the cloud service combination scheme and initialize the parameters of the utility function in the model, set the mission plan G={G obtained by the mission planning submodule 21 1 ,G 2 ,G 3 ,G 4 },corresponding The constraint is C={C 1 ,C 2 ,C 3 ,C 4 }, each subtask G v Corresponding cloud service resource pool SP v Total m v Services, for the cloud service resource pool SP v Service SP vω , Which contains The number of history records is L vω , By SP v The γth feasible cloud service portfolio solution formed is CS γ ,V∈[1,4],ω∈[1,m v ], the definition model is:
[0045] X ( CS γ ) = X k 4 Q O S max ( k ) - X v = 1 4 X ω = 1 m v X h = 1 L v ω q d ( SP v ω R h ) X x v ω - h Q O S max ( k ) - Q O S min ( k ) X w k X ω = 1 m v X h = 1 L v ω q k ( SP v ω R h ) X x v ω - h ≤ C k , 1 ≤ k ≤ 4 X ω = 1 m v X h = 1 L v ω x v ω - h = 1 , x v ω - h A { 0 , 1 } X k d w k = 1 , w k A [ 0 , 1 ]
[0046] among them, For the kth dimension Maximum, For the kth dimension Minimum, SP vω R h Be affiliated with SP vω One of History, x vω-h Represents the parameters of the utility function in the model;
[0047] B. Sort the feasible cloud service combination schemes according to the utility function value from small to large, and select the first Z feasible cloud service combination schemes as the preferred cloud service combination scheme, and the value of Z is set according to the application instance;
[0048] C. Calculate the average value of the utility function for each group of preferred cloud service portfolio solutions;
[0049] D. Select the optimal cloud service combination plan with the largest average value of the utility function value as the optimal cloud service combination plan;
[0050] E. Record the utility function value of the preferred cloud service combination plan and the optimal combined cloud service plan, and use it as a sample for learning. If a new preferred cloud service combination plan has appeared, its function value will be directly called;
[0051] 3) The task execution sub-module 23 is used to execute the data storage subtask, index calculation subtask, physical examination result analysis subtask, and physical examination result storage subtask in sequence according to the optimal cloud service combination plan;
[0052] 4) The physical examination result call-out submodule 24 is used to extract the physical examination result from the cloud service resource pool storing the physical examination result;
[0053] (3) The physical examination result display module 3 is used to issue a physical examination result recall command to the physical examination result recall submodule 24 and display the physical examination result extracted by the physical examination result recall submodule.
[0054] Wherein, the task execution sub-module 23 includes a data indexing unit for establishing a physical examination data index for the physical examination result analysis subtask; the data indexing unit includes a physical examination data searching subunit, and the physical examination data searching subunit is used for searching physical examinations. Analyze the physical examination data required by the subtasks, and perform the following operations:
[0055] Let x i Is a peer node in an unstructured peer-to-peer network, Is the local resource pool, Is the neighbor node resource information pool, i∈[1,n], n is the total number of nodes in the peer-to-peer network, initiate a query request M j The node is x j , At x j According to the probability p j The set of randomly selected peer nodes is p j ×{x j1 ,x j2 ,...X jm },j∈[1,n];
[0056] When peer node x i Received x j Query request sent M j When, check with Does it contain satisfy query request M j If yes, create a query response message based on the physical examination data and the location information of the peer node where the physical examination data is located And according to x j Location information, the response information Return to x j , Then x j Minus 1, if x j The life value of is 0, and the query request M is discarded j , If it is not 0, use Q learning algorithm to calculate p j ×{x j1 ,x j2 ,...X jm } The Q value of each peer node in the query request M j Forward to p j ×{x j1 ,x j2 ,...X jm } The node with the largest Q value, probability p j The value range when the network is idle is (5,8], and the value range when the network is congested is [0,3);
[0057] The calculation formula for setting the Q value is:
[0058] Q n e w = Q o l d + αQ l e a r n + β X I [ N x j μ ( t ) ( T x j μ - T ′ x j μ ) T ′ x j μ X T x j μ ] X 1 + N x j μ ( t ) T x j μ
[0059] Among them, Q new Represents the new value of Q, Q old Represents the old value of Q, Q learn Represents the value to be learned, α represents the learning rate, β represents the congestion factor, Represents time t node x jμ The number of pending query request messages in the cache queue, Means p j ×{x j1 ,x j2 ,...X jm } In node x jμ The time required to process a query request message, Means p j ×{x j1 ,x j2 ,...X jm } In node x jμ The actual time required to process a query request message; function I[x] in x> When 0, the value is 1, and when x≤0, the value is 0, the value range of α is [0.25, 0.3], and the value range of β is [0.45, 0.5].
[0060] Wherein, the physical examination sensor is a trace element analyzer sensor, a weight scale sensor, an ECG monitor sensor, a pulse monitor sensor, a blood pressure monitor sensor, a blood lipid monitor sensor, a blood glucose monitor sensor, a vision monitor sensor, and body temperature monitoring One or more of sensor, whole body thermal imaging monitor sensor, transcranial Doppler monitor sensor, bone mineral density and bone age monitor sensor, human body bioelectric signal monitor sensor, stethoscope sensor.
[0061] In this embodiment, a physical examination data collection module 1, a physical examination data processing module 2 and a physical examination result display module 3 are provided to realize the construction of the physical examination system. The user can complete the physical examination and physical condition examination without going through the hospital or the physical examination center; For the processing of cost-effective medical examination data, a credible portfolio evaluation sub-module 22 is set up, which improves the credibility of the cloud service portfolio supporting big data services, realizes the most profitable use of cloud storage and computing resources, and saves evaluation Time, improve the evaluation speed; set up a physical examination data search sub-unit to find the physical examination data required by the subtask of physical examination result analysis, which improves the efficiency of physical examination data search and further improves the speed of analyzing the physical examination results. For example, α=0.25, β=0.45, and the efficiency of searching for physical examination data is increased by 2.8%.
Example Embodiment
[0062] Example 2
[0063] See figure 1 , figure 2 , The medical examination system based on cloud computing of this embodiment includes:
[0064] (1) Physical examination data collection module 1, used to collect required physical examination data through physical examination sensors according to physical examination requirements;
[0065] (2) Physical examination data processing module 2, used to process physical examination data and output physical examination results, including:
[0066] 1) The task planning sub-module 21 is used to divide the processing process of the physical examination data into data storage subtasks, index calculation subtasks, physical examination result analysis subtasks, and physical examination result storage subtasks, and match each subtask to meet its requirements. The required cloud service resource pool forms a cloud service portfolio plan to obtain the storage resources and computing resources needed in the big data processing process;
[0067] 2) The credible combination evaluation sub-module 22 is used to perform the evaluation of the cloud service combination plan according to the task planning of the big data service generated by the task planning sub-module 21, select the optimal cloud service combination plan, and provide corresponding solutions for each subtask The storage and computing resources are specifically:
[0068] A. According to the cloud service resource pool SP v And corresponding service quality Historical records, model the utility function X of the cloud service combination scheme and initialize the parameters of the utility function in the model, set the mission plan G={G obtained by the mission planning submodule 21 1 ,G 2 ,G 3 ,G 4 },corresponding The constraint is C={C 1 ,C 2 ,C 3 ,C 4 }, each subtask G v Corresponding cloud service resource pool SP v Total m v Services, for the cloud service resource pool SP v Service SP vω , Which contains The number of history records is L vω , By SP v The γth feasible cloud service portfolio solution formed is CS γ ,V∈[1,4],ω∈[1,m v ], the definition model is:
[0069] X ( CS γ ) = X k 4 Q O S max ( k ) - X v = 1 4 X ω = 1 m v X h = 1 L v ω q d ( SP v ω R h ) X x v ω - h Q O S max ( k ) - Q O S min ( k ) X w k X ω = 1 m v X h = 1 L v ω q k ( SP v ω R h ) X x v ω - h ≤ C k , 1 ≤ k ≤ 4 X ω = 1 m v X h = 1 L v ω x v ω - h = 1 , x v ω - h A { 0 , 1 } X k d w k = 1 , w k A [ 0 , 1 ]
[0070] among them, For the kth dimension Maximum, For the kth dimension Minimum, SP vω R h Be affiliated with SP vω One of History, x vω-h Represents the parameters of the utility function in the model;
[0071] B. Sort the feasible cloud service combination schemes according to the utility function value from small to large, and select the first Z feasible cloud service combination schemes as the preferred cloud service combination scheme, and the value of Z is set according to the application instance;
[0072] C. Calculate the average value of the utility function for each group of preferred cloud service portfolio solutions;
[0073] D. Select the optimal cloud service combination plan with the largest average value of the utility function value as the optimal cloud service combination plan;
[0074] E. Record the utility function value of the preferred cloud service combination plan and the optimal combined cloud service plan, and use it as a sample for learning. If a new preferred cloud service combination plan has appeared, its function value will be directly called;
[0075] 3) The task execution sub-module 23 is used to execute the data storage subtask, index calculation subtask, physical examination result analysis subtask, and physical examination result storage subtask in sequence according to the optimal cloud service combination plan;
[0076] 4) The physical examination result call-out submodule 24 is used to extract the physical examination result from the cloud service resource pool storing the physical examination result;
[0077] (3) The physical examination result display module 3 is used to issue a physical examination result recall command to the physical examination result recall submodule 24 and display the physical examination result extracted by the physical examination result recall submodule.
[0078] Wherein, the task execution sub-module 23 includes a data indexing unit for establishing a physical examination data index for the physical examination result analysis subtask; the data indexing unit includes a physical examination data searching subunit, and the physical examination data searching subunit is used for searching physical examinations. Analyze the physical examination data required by the subtasks, and perform the following operations:
[0079] Let x i Is a peer node in an unstructured peer-to-peer network, Is the local resource pool, Is the neighbor node resource information pool, i∈[1,n], n is the total number of nodes in the peer-to-peer network, initiate a query request M j The node is x j , At x j According to the probability p j The set of randomly selected peer nodes is p j ×{x j1 ,x j2 ,...X jm },j∈[1,n];
[0080] When peer node x i Received x j Query request sent M j When, check with Does it contain satisfy query request M j If yes, create a query response message based on the physical examination data and the location information of the peer node where the physical examination data is located And according to x j Location information, the response information Return to x j , Then x j Minus 1, if x j The life value of is 0, and the query request M is discarded j , If it is not 0, use Q learning algorithm to calculate p j ×{x j1 ,x j2 ,...X jm } The Q value of each peer node in the query request M j Forward to p j ×{x j1 ,x j2 ,...X jm } The node with the largest Q value, probability p j The value range when the network is idle is (5,8], and the value range when the network is congested is [0,3);
[0081] The calculation formula for setting the Q value is:
[0082] Q n e w = Q o l d + αQ l e a r n + β X I [ N x j μ ( t ) ( T x j μ - T ′ x j μ ) T ′ x j μ X T x j μ ] X 1 + N x j μ ( t ) T x j μ
[0083] Among them, Q new Represents the new value of Q, Q old Represents the old value of Q, Q learn Represents the value to be learned, α represents the learning rate, β represents the congestion factor, Represents time t node x jμ The number of pending query request messages in the cache queue, Means p j ×{x j1 ,x j2 ,...X jm } In node x jμ The time required to process a query request message, Means p j ×{x j1 ,x j2 ,...X jm } In node x jμ The actual time required to process a query request message; function I[x] in x> When 0, the value is 1, and when x≤0, the value is 0, the value range of α is [0.25, 0.3], and the value range of β is [0.45, 0.5].
[0084] Wherein, the physical examination sensor is a trace element analyzer sensor, a weight scale sensor, an ECG monitor sensor, a pulse monitor sensor, a blood pressure monitor sensor, a blood lipid monitor sensor, a blood glucose monitor sensor, a vision monitor sensor, and body temperature monitoring One or more of sensor, whole body thermal imaging monitor sensor, transcranial Doppler monitor sensor, bone mineral density and bone age monitor sensor, human body bioelectric signal monitor sensor, stethoscope sensor.
[0085] In this embodiment, a physical examination data collection module 1, a physical examination data processing module 2 and a physical examination result display module 3 are provided to realize the construction of the physical examination system. The user can complete the physical examination and physical condition examination without going through the hospital or the physical examination center; For the processing of cost-effective medical examination data, a credible portfolio evaluation sub-module 22 is set up, which improves the credibility of the cloud service portfolio supporting big data services, realizes the most profitable use of cloud storage and computing resources, and saves evaluation Time, improve the evaluation speed; set up a physical examination data search sub-unit to find the physical examination data required by the subtask of physical examination result analysis, which improves the efficiency of physical examination data search and further improves the speed of analyzing the physical examination results. For example, the value α=0.26, β=0.5, and the efficiency of physical examination data search is increased by 2.5%.
Example Embodiment
[0086] Example 3
[0087] See figure 1 , figure 2 , The medical examination system based on cloud computing of this embodiment includes:
[0088] (1) Physical examination data collection module 1, used to collect required physical examination data through physical examination sensors according to physical examination requirements;
[0089] (2) Physical examination data processing module 2, used to process physical examination data and output physical examination results, including:
[0090] 1) The task planning sub-module 21 is used to divide the processing process of the physical examination data into data storage subtasks, index calculation subtasks, physical examination result analysis subtasks, and physical examination result storage subtasks, and match each subtask to meet its requirements. The required cloud service resource pool forms a cloud service portfolio plan to obtain the storage resources and computing resources needed in the big data processing process;
[0091] 2) The credible combination evaluation sub-module 22 is used to perform the evaluation of the cloud service combination plan according to the task planning of the big data service generated by the task planning sub-module 21, select the optimal cloud service combination plan, and provide corresponding solutions for each subtask The storage and computing resources are specifically:
[0092] A. According to the cloud service resource pool SP v And corresponding service quality Historical records, model the utility function X of the cloud service combination scheme and initialize the parameters of the utility function in the model, set the mission plan G={G obtained by the mission planning submodule 21 1 ,G 2 ,G 3 ,G 4 },corresponding The constraint is C={C 1 ,C 2 ,C 3 ,C 4 }, each subtask G v Corresponding cloud service resource pool SP v Total m v Services, for the cloud service resource pool SP v Service SP vω , Which contains The number of history records is L vω , By SP v The γth feasible cloud service portfolio solution formed is CS γ ,V∈[1,4],ω∈[1,m v ], the definition model is:
[0093] X ( CS γ ) = X k 4 Q O S max ( k ) - X v = 1 4 X ω = 1 m v X h = 1 L v ω q d ( SP v ω R h ) X x v ω - h Q O S max ( k ) - Q O S min ( k ) X w k X ω = 1 m v X h = 1 L v ω q k ( SP v ω R h ) X x v ω - h ≤ C k , 1 ≤ k ≤ 4 X ω = 1 m v X h = 1 L v ω x v ω - h = 1 , x v ω - h A { 0 , 1 } X k d w k = 1 , w k A [ 0 , 1 ]
[0094] among them, For the kth dimension Maximum, For the kth dimension Minimum, SP vω R h Be affiliated with SP vω One of History, x vω-h Represents the parameters of the utility function in the model;
[0095] B. Sort the feasible cloud service combination schemes according to the utility function value from small to large, and select the first Z feasible cloud service combination schemes as the preferred cloud service combination scheme, and the value of Z is set according to the application instance;
[0096] C. Calculate the average value of the utility function for each group of preferred cloud service portfolio solutions;
[0097] D. Select the optimal cloud service combination plan with the largest average value of the utility function value as the optimal cloud service combination plan;
[0098] E. Record the utility function value of the preferred cloud service combination plan and the optimal combined cloud service plan, and use it as a sample for learning. If a new preferred cloud service combination plan has appeared, its function value will be directly called;
[0099] 3) The task execution sub-module 23 is used to execute the data storage subtask, index calculation subtask, physical examination result analysis subtask, and physical examination result storage subtask in sequence according to the optimal cloud service combination plan;
[0100] 4) The physical examination result call-out submodule 24 is used to extract the physical examination result from the cloud service resource pool storing the physical examination result;
[0101] (3) The physical examination result display module 3 is used to issue a physical examination result recall command to the physical examination result recall submodule 24 and display the physical examination result extracted by the physical examination result recall submodule.
[0102] Wherein, the task execution sub-module 23 includes a data indexing unit for establishing a physical examination data index for the physical examination result analysis subtask; the data indexing unit includes a physical examination data searching subunit, and the physical examination data searching subunit is used for searching physical examinations. Analyze the physical examination data required by the subtasks, and perform the following operations:
[0103] Let x i Is a peer node in an unstructured peer-to-peer network, Is the local resource pool, Is the neighbor node resource information pool, i∈[1,n], n is the total number of nodes in the peer-to-peer network, initiate a query request M j The node is x j , At x j According to the probability p j The set of randomly selected peer nodes is p j ×{x j1 ,x j2 ,...X jm },j∈[1,n];
[0104] When peer node x i Received x j Query request sent M j When, check with Does it contain satisfy query request M j If yes, create a query response message based on the physical examination data and the location information of the peer node where the physical examination data is located And according to x j Location information, the response information Return to x j , Then x j Minus 1, if x j The life value of is 0, and the query request M is discarded j , If it is not 0, use Q learning algorithm to calculate p j ×{x j1 ,x j2 ,...X jm } The Q value of each peer node in the query request M j Forward to p j ×{x j1 ,x j2 ,...X jm } The node with the largest Q value, probability p j The value range when the network is idle is (5,8], and the value range when the network is congested is [0,3);
[0105] The calculation formula for setting the Q value is:
[0106] Q n e w = Q o l d + αQ l e a r n + β X I [ N x j μ ( t ) ( T x j μ - T ′ x j μ ) T ′ x j μ X T x j μ ] X 1 + N x j μ ( t ) T x j μ
[0107] Among them, Q new Represents the new value of Q, Q old Represents the old value of Q, Q learn Represents the value to be learned, α represents the learning rate, β represents the congestion factor, Represents time t node x jμ The number of pending query request messages in the cache queue, Means p j ×{x j1 ,x j2 ,...X jm } In node x jμ The time required to process a query request message, Means p j ×{x j1 ,x j2 ,...X jm } In node x jμ The actual time required to process a query request message; function I[x] in x> When 0, the value is 1, and when x≤0, the value is 0, the value range of α is [0.25, 0.3], and the value range of β is [0.45, 0.5].
[0108] Wherein, the physical examination sensor is a trace element analyzer sensor, a weight scale sensor, an ECG monitor sensor, a pulse monitor sensor, a blood pressure monitor sensor, a blood lipid monitor sensor, a blood glucose monitor sensor, a vision monitor sensor, and body temperature monitoring One or more of sensor, whole body thermal imaging monitor sensor, transcranial Doppler monitor sensor, bone mineral density and bone age monitor sensor, human body bioelectric signal monitor sensor, stethoscope sensor.
[0109] In this embodiment, a physical examination data collection module 1, a physical examination data processing module 2 and a physical examination result display module 3 are provided to realize the construction of the physical examination system. The user can complete the physical examination and physical condition examination without going through the hospital or the physical examination center; For the processing of cost-effective medical examination data, a credible portfolio evaluation sub-module 22 is set up, which improves the credibility of the cloud service portfolio supporting big data services, realizes the most profitable use of cloud storage and computing resources, and saves evaluation Time, improve the evaluation speed; set up a physical examination data search sub-unit to find the physical examination data required by the subtask of physical examination result analysis, which improves the efficiency of physical examination data search and further improves the speed of analyzing the physical examination results. For example, the value α=0.27, β=0.49, and the efficiency of searching the physical examination data is increased by 3%.
PUM


Description & Claims & Application Information
We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.