CN117912645A - Blood preservation whole-flow supervision method and system based on Internet of things - Google Patents
Blood preservation whole-flow supervision method and system based on Internet of things Download PDFInfo
- Publication number
- CN117912645A CN117912645A CN202310317146.8A CN202310317146A CN117912645A CN 117912645 A CN117912645 A CN 117912645A CN 202310317146 A CN202310317146 A CN 202310317146A CN 117912645 A CN117912645 A CN 117912645A
- Authority
- CN
- China
- Prior art keywords
- blood
- information
- wireless sensor
- storage environment
- quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004555 blood preservation Methods 0.000 title claims abstract description 46
- 210000004369 blood Anatomy 0.000 claims abstract description 526
- 239000008280 blood Substances 0.000 claims abstract description 526
- 238000003860 storage Methods 0.000 claims abstract description 131
- 230000008859 change Effects 0.000 claims abstract description 51
- 238000012544 monitoring process Methods 0.000 claims abstract description 15
- 238000011160 research Methods 0.000 claims abstract description 10
- 230000007613 environmental effect Effects 0.000 claims description 30
- 238000011156 evaluation Methods 0.000 claims description 29
- 238000001514 detection method Methods 0.000 claims description 26
- 238000011176 pooling Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 17
- 230000002776 aggregation Effects 0.000 claims description 14
- 238000004220 aggregation Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 12
- 238000013441 quality evaluation Methods 0.000 claims description 12
- 208000014951 hematologic disease Diseases 0.000 claims description 10
- 208000019838 Blood disease Diseases 0.000 claims description 8
- 208000018706 hematopoietic system disease Diseases 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 4
- 230000002123 temporal effect Effects 0.000 claims 6
- 230000006855 networking Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 239000013598 vector Substances 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 6
- 238000013507 mapping Methods 0.000 description 4
- 230000004931 aggregating effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000004321 preservation Methods 0.000 description 3
- 102000003929 Transaminases Human genes 0.000 description 2
- 108090000340 Transaminases Proteins 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 239000000427 antigen Substances 0.000 description 2
- 102000036639 antigens Human genes 0.000 description 2
- 108091007433 antigens Proteins 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 208000028867 ischemia Diseases 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005057 refrigeration Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 210000001185 bone marrow Anatomy 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011476 stem cell transplantation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/22—Social work or social welfare, e.g. community support activities or counselling services
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/60—Healthcare; Welfare
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Epidemiology (AREA)
- Strategic Management (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Child & Adolescent Psychology (AREA)
- Bioethics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a blood preservation whole-process supervision method and system based on the Internet of things, comprising the following steps: obtaining blood collection information and comparing the blood collection information with preset blood indexes, and judging whether the collected blood accords with the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result; when the condition constraint is met, warehousing the blood, and generating label information; sensing blood storage environment information by using a wireless sensor network, acquiring the change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information; and carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, and preferentially matching early warning blood through the blood demand information. The invention effectively ensures the storage quality of blood by carrying out full-flow monitoring on blood preservation, and selects the blood with reasonable storage time for blood transfusion treatment or clinical scientific research so as to obtain better effect.
Description
Technical Field
The invention relates to the technical field of blood management, in particular to a blood preservation whole-flow supervision method and system based on the Internet of things.
Background
In recent years, the contradiction between the rapid increase of clinical blood demand and the implementation of gratuitous blood donation system in China is increasingly prominent. The blood cell preservation technology has important significance for regulating clinical reasonable blood use, rare blood type transfusion, bone marrow stem cell transplantation, tumor treatment, war preparation blood storage and the like. The traditional blood transfusion mode plays an important role in medical aid, and the low-temperature refrigeration technology for prolonging the shelf life of blood and component blood is attracting more and more attention because of uncertain clinical demand of blood, blood type or component blood type. At present, the storage of blood mainly depends on a traditional refrigerator or a refrigeration house, and when a blood bag is taken, whether the quality of blood meets the standard or not is mostly detected manually and pushed to a blood using place.
At present, due to the fact that monitoring means are lacked in the blood preservation management process, the judgment of the blood quality of blood is completely dependent on personal experience of medical staff to judge, medical accidents are easily caused by misjudgment, in addition, in clinical research, the blood preservation time length can influence research results, namely, timeliness labels in blood preservation are important, most blood samples in current clinical research lack timeliness labels, and most sample preservation time is too long, so that the optimal blood sample is matched for clinical research projects, and it is particularly important to furthest utilize the existing blood samples to prevent blood resource waste. In blood preservation management, how to utilize the internet of things technology to conduct blood preservation whole-flow supervision, and adding an aging informatization label for blood is one of the problems to be solved at present.
Disclosure of Invention
In order to solve the technical problems, the invention provides a blood preservation whole-flow supervision method and system based on the Internet of things.
The invention provides a blood preservation whole-flow supervision method based on the Internet of things, which comprises the following steps:
acquiring blood collection information, comparing the blood collection information with preset blood indexes, and judging whether the collected blood accords with the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result;
when the condition constraint is met, warehousing the blood, and generating label information according to the blood collection information to be matched with the blood;
Sensing blood storage environment information by using a wireless sensor network, acquiring the change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information;
And carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, preferentially matching early warning blood through the blood demand information, and selecting reasonable blood for delivery.
In this scheme, acquire blood collection information, according to blood collection information compares with predetermineeing blood index, judges through the comparison result whether the blood of gathering accords with the condition constraint that the current blood index of target blood bank corresponds, specifically does:
Obtaining basic information and common blood disease information of blood donors through questionnaire distribution, screening the blood donors according to the basic information and the common blood disease information, obtaining physical examination information in preset time by utilizing data retrieval according to the basic information, performing information verification, and generating blood label information;
If the current blood donor does not have relevant physical examination information, collecting a blood sample of the blood donor, and generating blood collection information according to the detection information of the blood sample and the basic information;
Setting condition constraint according to the judgment standard corresponding to each current blood detection index of the target blood bank, setting blood storage priority according to the stock information of the target blood bank, and judging whether the blood collection information accords with the condition constraint;
if the blood label information accords with the current preset grade standard, generating blood label information based on the blood collection information for warehousing;
And if the grade information does not accord with the current preset grade standard, the corresponding blood donators are classified into a waiting queue, and the notification of the blood donators in the waiting queue is carried out according to the update of the target blood bank warehousing priority.
In this scheme, utilize wireless sensor network perception blood storage environment information, acquire the change characteristic of blood storage environment in real time, specifically do:
Performing advanced distribution of different types of wireless sensor nodes according to the spatial layout of the target blood bank, acquiring storage environment parameters of the target blood bank through the wireless sensor nodes at preset positions, performing convergence transmission through the convergence nodes in the wireless sensor network, and preprocessing the acquired storage environment parameters;
Obtaining a topological structure of a wireless sensor network in a target blood bank, and representing the topological structure through a directed graph G= (V, E), wherein V represents wireless sensor nodes in the target blood bank, and E represents connection relations among the wireless sensor nodes;
The method comprises the steps of taking category information and history data of environmental information collected by wireless sensor nodes as attribute characteristics of nodes in a directed graph, obtaining the distance between the wireless sensor nodes through Manhattan distance, and judging whether the two nodes are adjacent or not according to the Manhattan distance;
The directed graph is subjected to representation learning through a graph convolution neural network, time features and space features in a wireless sensor topological structure are mined, corresponding time weights and space weights are generated, and the features are aggregated according to the time weights and the space weights;
the method comprises the steps of carrying out weighted calculation on neighbor nodes, carrying out summation on the weighted characteristics to update the characteristics of the nodes, representing blood storage environment information of the current time step by the aggregated characteristics, and inputting the aggregated characteristics into an output layer;
And training the loss function of the output layer until convergence, predicting the blood storage environment information after a preset time step, and acquiring the change characteristics of the blood storage environment in real time.
In this scheme, mining time feature and space feature in wireless sensor topological structure, generating corresponding time weight and space weight, according to time weight and space weight carry out the aggregate to the feature, specifically do:
Acquiring dynamic correlation of blood storage environment parameters in a historical time step and a future time step through an attention introducing mechanism, calculating time weight according to a time attention function on time sequence, and effectively extracting historical monitoring data corresponding to wireless sensor nodes;
In addition, a pooling layer and a full-connection layer are introduced into the graph convolution neural network, the average pooling operation and the maximum pooling operation in the pooling layer are utilized to sample neighbor nodes, and the weight of the current wireless sensor node contribution to other wireless sensor nodes in the topological structure is calculated and used as the spatial weight;
and acquiring the time weight and the space weight of the neighbor nodes, and carrying out aggregation updating on the features through the feature transfer of the graph convolution neural network and a neighbor aggregation mechanism.
In this scheme, based on the time sequence change characteristic of storage environment combines with blood collection information, analysis blood quality information specifically does:
Acquiring influencing factors of blood quality through a big data retrieval and expert recommendation method, calculating pearson correlation coefficients with a blood storage environment according to the influencing factors, and screening influencing factors of which the pearson correlation coefficients accord with a preset threshold;
Setting an evaluation index according to the influence factors obtained by screening, constructing a blood quality evaluation system based on the evaluation index and corresponding evaluation standards, evaluating the stock blood of the target blood bank through the blood quality evaluation system, and verifying through the detection data of the preset blood detection index;
Constructing a blood quality prediction model based on deep learning, generating training data according to evaluation data of a blood evaluation system, and training the blood quality prediction model through the training data;
And taking the time sequence of the blood storage environment change characteristics as input of a blood quality prediction model, analyzing the influence on the blood quality according to the blood storage environment change characteristics and the storage time length, and outputting blood quality information after the preset time.
In this scheme, according to blood quality information carries out blood quality early warning, acquires blood demand information, through blood demand information priority matching early warning blood, selects reasonable blood to go out of stock, specifically does:
Presetting a blood quality information threshold, judging whether the blood quality information corresponding to the current timestamp in the blood preservation environment is smaller than the preset blood quality information threshold, if so, carrying out blood quality early warning, and extracting blood label information of the blood quality early warning;
Marking the extracted blood label information, determining the stock position according to the marked blood label information, setting the ex-warehouse priority, and updating the ex-warehouse priority according to the real-time change of the blood quality information;
Blood demand information is obtained through basic information of clinical scientific research or clinical manifestations of patients, blood recommendation is carried out according to the blood demand information and the current ex-warehouse priority, marked blood is preferentially used for matching judgment, and best-fit blood is selected for ex-warehouse.
The second aspect of the invention also provides a blood preservation whole-flow supervision system based on the Internet of things, which comprises: the blood preservation whole-flow supervision method based on the Internet of things comprises a memory and a processor, wherein the memory comprises a blood preservation whole-flow supervision method program based on the Internet of things, and the blood preservation whole-flow supervision method program based on the Internet of things realizes the following steps when being executed by the processor:
acquiring blood collection information, comparing the blood collection information with preset blood indexes, and judging whether the collected blood accords with the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result;
when the condition constraint is met, warehousing the blood, and generating label information according to the blood collection information to be matched with the blood;
Sensing blood storage environment information by using a wireless sensor network, acquiring the change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information;
And carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, preferentially matching early warning blood through the blood demand information, and selecting reasonable blood for delivery.
The invention discloses a blood preservation whole-process supervision method and system based on the Internet of things, comprising the following steps: obtaining blood collection information and comparing the blood collection information with preset blood indexes, and judging whether the collected blood accords with the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result; when the condition constraint is met, warehousing the blood, and generating label information; sensing blood storage environment information by using a wireless sensor network, acquiring the change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information; and carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, and preferentially matching early warning blood through the blood demand information. The invention effectively ensures the storage quality of blood by carrying out full-flow monitoring on blood preservation, and selects the blood with reasonable storage time for blood transfusion treatment or clinical scientific research so as to obtain better effect.
Drawings
FIG. 1 shows a flow chart of a blood preservation whole-flow supervision method based on the Internet of things;
FIG. 2 illustrates a flow chart of a method of the present invention for acquiring in real time a changing characteristic of a blood storage environment;
FIG. 3 is a flow chart of a method of analyzing blood quality information by storing time series change characteristics of an environment and blood collection information in accordance with the present invention;
Fig. 4 shows a block diagram of a blood preservation whole-flow supervision system based on the internet of things.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a blood preservation whole-process supervision method based on the internet of things.
As shown in fig. 1, the first aspect of the present invention provides a blood preservation whole-process supervision method based on the internet of things, including:
S102, acquiring blood collection information, comparing the blood collection information with preset blood indexes, and judging whether the collected blood meets the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result;
S104, when the condition constraint is met, warehousing the blood, and generating label information according to the blood collection information to be matched with the blood;
s106, sensing blood storage environment information by using a wireless sensor network, acquiring change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information;
S108, carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, preferentially matching early warning blood through the blood demand information, and selecting reasonable blood for delivery.
Before blood donation, a blood donator distributes and acquires basic information and common blood disease information of the blood donator through a questionnaire at a mobile client, screens the blood donator according to the basic information and the common blood disease information, performs information verification according to physical examination information in preset time obtained by data retrieval according to the basic information, and generates blood label information, wherein the data verified by the information can also comprise past blood donation places, blood donation types, blood donation amounts, blood detection results, where blood is used, whether blood can be donated, whether the blood is in an interval period and the like; if the current blood donor does not have relevant physical examination information, collecting a blood sample of the blood donor, and generating blood collection information according to the detection information of the blood sample and the basic information; setting condition constraints according to the judgment standards corresponding to the current blood detection indexes of the target blood bank, wherein the blood detection indexes commonly comprise blood types, blood diseases, transaminase, antigen detection and the like; acquiring an ischemia type according to inventory information of a target blood bank, setting blood storage priority, and judging whether the blood collection information accords with the condition constraint; if the blood label information accords with the current preset grade standard, generating blood label information based on the blood collection information for warehousing; and if the grade information does not accord with the current preset grade standard, the corresponding blood donators are classified into a waiting queue, and the notification of the blood donators in the waiting queue is carried out according to the update of the target blood bank warehousing priority.
FIG. 2 illustrates a flow chart of a method of the present invention for acquiring in real time a changing characteristic of a blood storage environment.
According to the embodiment of the application, the wireless sensor network is utilized to sense the information of the blood storage environment, and the change characteristics of the blood storage environment are obtained in real time, specifically:
S202, performing advanced distribution of different types of wireless sensor nodes according to the spatial layout of a target blood bank, acquiring storage environment parameters of the target blood bank through the wireless sensor nodes at preset positions, performing aggregation transmission through aggregation nodes in a wireless sensor network, and preprocessing the acquired storage environment parameters;
S204, obtaining a topological structure of a wireless sensor network in a target blood bank, and representing the topological structure through a directed graph G= (V, E), wherein V represents wireless sensor nodes in the target blood bank, and E represents connection relations among the wireless sensor nodes;
S206, using the type information and the history data of the environmental information collected by the wireless sensor nodes as attribute characteristics of the nodes in the directed graph, obtaining the distance between the wireless sensor nodes through Manhattan distance, and judging whether the two nodes are adjacent or not according to the Manhattan distance;
S208, performing representation learning on the directed graph through a graph convolutional neural network, mining time features and space features in a wireless sensor topological structure, generating corresponding time weights and space weights, and aggregating the features according to the time weights and the space weights;
S210, carrying out weighted calculation on the neighbor nodes, carrying out summation on the weighted characteristics to update the characteristics of the nodes, and inputting the aggregated characteristics into an output layer through blood storage environment information of the aggregated characteristics representing the current time step;
s212, training the loss function of the output layer until convergence, predicting the blood storage environment information after a preset time step, and acquiring the change characteristics of the blood storage environment in real time.
The wireless sensor network monitors environmental parameters such as temperature and humidity in the blood storage environment at multiple points, and the environmental parameters of a plurality of sensors are fused in time and space due to zero drift or signal distortion of a single sensor, so that the environmental parameters of the blood storage environment are better reflected. And taking the sink node in the wireless sensor network as a target node, acquiring neighbor nodes of the target node based on the topological structure of the wireless sensor through a graph convolution neural network, and carrying out fusion prediction on the environmental parameters of blood storage by utilizing characteristic transfer and neighbor aggregation to obtain the blood storage environmental state after a preset time step.
The dynamic correlation of blood storage environment parameters in historical time steps and future time steps is obtained by introducing an attention mechanism, the attention mechanism is used for mapping the historical monitoring data of different wireless sensor nodes into three different vectors of query Q, key K and value V, the three vectors are learned to obtain a time attention function Tatt (Q, K, V),Where Q represents a matrix containing query conditions, K represents a matrix containing key values, V represents a matrix containing values of elements, and d k represents the dimension of each query condition in query Q. Calculating time weight according to a time attention function on time sequence, and effectively extracting historical monitoring data corresponding to the wireless sensor node;
In addition, in order to distinguish the importance of different wireless sensor nodes on blood storage space monitoring, different space weights are allocated to different neighbor nodes, a pooling layer and a full-connection layer are introduced into the graph convolution neural network, average pooling operation and maximum pooling operation in the pooling layer are utilized to sample the neighbor nodes, the weight of the current wireless sensor node contributing to other wireless sensor nodes in a topological structure is calculated and is used as the space weight, so that the graph convolution neural network is more focused on the sampled wireless sensor nodes, and the calculation formula of the space attention K att is as follows: where σ represents the activation function, f represents the fully connected layer, AP represents the average pooling operation, MP represents the maximum pooling operation,/> Representing a mapping function, and X i represents the characteristic of the environmental parameter monitored by the wireless sensor at the moment i;
Applying the time weight and the space weight to neighbor nodes of the target node, aggregating the features through a feature transfer and neighbor aggregation mechanism of the graph convolution neural network, updating the feature representation of the target node, representing the blood storage environment information of the current time step, and preferably, predicting the blood storage environment information of the next time step through the aggregated features by taking the gate control circulation network as an output layer.
FIG. 3 shows a flow chart of a method of analyzing blood quality information by storing time-varying characteristics of an environment and blood collection information in accordance with the present invention.
According to the embodiment of the invention, the time sequence change characteristics based on the storage environment are combined with the blood collection information, and the blood quality information is analyzed, specifically:
s302, acquiring influence factors of blood quality through a big data retrieval and expert recommendation method, calculating a pearson correlation coefficient with a blood storage environment according to the influence factors, and screening the influence factors of which the pearson correlation coefficient meets a preset threshold;
s304, setting an evaluation index according to the influence factors obtained by screening, constructing a blood quality evaluation system based on the evaluation index and corresponding evaluation standards, evaluating stock blood of a target blood bank through the blood quality evaluation system, and verifying through detection data of preset blood detection indexes;
S306, constructing a blood quality prediction model based on deep learning, generating training data according to evaluation data of a blood evaluation system, and training the blood quality prediction model through the training data;
S308, taking the time sequence of the blood storage environment change characteristics as input of a blood quality prediction model, analyzing the influence on the blood quality according to the blood storage environment change characteristics and the storage time length, and outputting blood quality information after a preset time.
After screening the influencing factors, analyzing the influence degree of index change corresponding to each evaluation index on the blood quality, presetting a scoring threshold value area or corresponding scoring grade information according to the index change amount and the influence degree, simultaneously acquiring index weight according to the pearson correlation coefficient, carrying out weighted summation on scores to acquire evaluation information, generating blood quality verification information through preset blood detection indexes, and correcting a blood quality evaluation system through the verification information.
Presetting a blood quality information threshold, judging whether the blood quality information corresponding to the current timestamp in the blood preservation environment is smaller than the preset blood quality information threshold, if so, carrying out blood quality early warning, and extracting blood label information of the blood quality early warning; marking the extracted blood label information, determining the stock position according to the marked blood label information, setting the ex-warehouse priority, and updating the ex-warehouse priority according to the real-time change of the blood quality information; blood demand information is obtained through basic information of clinical scientific research or clinical manifestations of patients, blood recommendation is carried out according to the blood demand information and the current ex-warehouse priority, marked blood is preferentially used for matching judgment, and best-fit blood is selected for ex-warehouse.
According to the embodiment of the invention, the environmental parameters are regulated according to the change of the blood storage environmental information, specifically:
Acquiring the predicted information of the blood storage environment after a preset time step, generating an environment parameter vector according to the predicted information of the blood storage environment, acquiring the optimal environment characteristic of blood storage through big data analysis, and generating a standard environment parameter vector;
Comparing the environment parameter vector corresponding to the predicted information of the blood storage environment after the preset time step with the standard environment parameter vector to obtain the deviation of the environment parameter, and judging whether the deviation of the environment parameter is larger than a preset deviation threshold value or not;
If the environmental parameter deviation is not greater than the preset mode, generating feedback information according to the environmental parameter deviation, and sending the feedback information to corresponding equipment for adjustment;
And simultaneously, acquiring environmental characteristics according to the predicted information of the blood storage environment, acquiring a regulation scheme with similarity meeting a preset standard from an environmental regulation database through the environmental characteristics and the feedback information, and carrying out adaptive regulation on the basis of the feedback information according to the regulation scheme.
It should be noted that, a regulation database of the blood storage environment is constructed, and the historical environmental characteristics and the corresponding regulation scheme are stored in the database, and because most of environmental changes of the blood pool are similar, for example, environmental changes caused by opening of a pool door in the process of accessing the blood sample, searching the historical environmental regulation scheme during environmental regulation can improve the environmental regulation efficiency and ensure the optimal preservation environment of the blood.
Fig. 4 shows a block diagram of a blood preservation whole-flow supervision system based on the internet of things.
The second aspect of the present invention also provides a blood preservation whole-process supervision system 4 based on the internet of things, the system comprising: the memory 41 and the processor 42, wherein the memory comprises a blood preservation whole-flow supervision method program based on the internet of things, and the blood preservation whole-flow supervision method program based on the internet of things realizes the following steps when being executed by the processor:
acquiring blood collection information, comparing the blood collection information with preset blood indexes, and judging whether the collected blood accords with the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result;
when the condition constraint is met, warehousing the blood, and generating label information according to the blood collection information to be matched with the blood;
Sensing blood storage environment information by using a wireless sensor network, acquiring the change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information;
And carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, preferentially matching early warning blood through the blood demand information, and selecting reasonable blood for delivery.
Before blood donation, a blood donator distributes and acquires basic information and common blood disease information of the blood donator through a questionnaire at a mobile client, screens the blood donator according to the basic information and the common blood disease information, performs information verification according to physical examination information in preset time obtained by data retrieval according to the basic information, and generates blood label information, wherein the data verified by the information can also comprise past blood donation places, blood donation types, blood donation amounts, blood detection results, where blood is used, whether blood can be donated, whether the blood is in an interval period and the like; if the current blood donor does not have relevant physical examination information, collecting a blood sample of the blood donor, and generating blood collection information according to the detection information of the blood sample and the basic information; setting condition constraints according to the judgment standards corresponding to the current blood detection indexes of the target blood bank, wherein the blood detection indexes commonly comprise blood types, blood diseases, transaminase, antigen detection and the like; acquiring an ischemia type according to inventory information of a target blood bank, setting blood storage priority, and judging whether the blood collection information accords with the condition constraint; if the blood label information accords with the current preset grade standard, generating blood label information based on the blood collection information for warehousing; and if the grade information does not accord with the current preset grade standard, the corresponding blood donators are classified into a waiting queue, and the notification of the blood donators in the waiting queue is carried out according to the update of the target blood bank warehousing priority.
According to the embodiment of the application, the wireless sensor network is utilized to sense the information of the blood storage environment, and the change characteristics of the blood storage environment are obtained in real time, specifically:
Performing advanced distribution of different types of wireless sensor nodes according to the spatial layout of the target blood bank, acquiring storage environment parameters of the target blood bank through the wireless sensor nodes at preset positions, performing convergence transmission through the convergence nodes in the wireless sensor network, and preprocessing the acquired storage environment parameters;
Obtaining a topological structure of a wireless sensor network in a target blood bank, and representing the topological structure through a directed graph G= (V, E), wherein V represents wireless sensor nodes in the target blood bank, and E represents connection relations among the wireless sensor nodes;
The method comprises the steps of taking category information and history data of environmental information collected by wireless sensor nodes as attribute characteristics of nodes in a directed graph, obtaining the distance between the wireless sensor nodes through Manhattan distance, and judging whether the two nodes are adjacent or not according to the Manhattan distance;
The directed graph is subjected to representation learning through a graph convolution neural network, time features and space features in a wireless sensor topological structure are mined, corresponding time weights and space weights are generated, and the features are aggregated according to the time weights and the space weights;
the method comprises the steps of carrying out weighted calculation on neighbor nodes, carrying out summation on the weighted characteristics to update the characteristics of the nodes, representing blood storage environment information of the current time step by the aggregated characteristics, and inputting the aggregated characteristics into an output layer;
And training the loss function of the output layer until convergence, predicting the blood storage environment information after a preset time step, and acquiring the change characteristics of the blood storage environment in real time.
The wireless sensor network monitors environmental parameters such as temperature and humidity in the blood storage environment at multiple points, and the environmental parameters of a plurality of sensors are fused in time and space due to zero drift or signal distortion of a single sensor, so that the environmental parameters of the blood storage environment are better reflected. And taking the sink node in the wireless sensor network as a target node, acquiring neighbor nodes of the target node based on the topological structure of the wireless sensor through a graph convolution neural network, and carrying out fusion prediction on the environmental parameters of blood storage by utilizing characteristic transfer and neighbor aggregation to obtain the blood storage environmental state after a preset time step.
The dynamic correlation of blood storage environment parameters in historical time steps and future time steps is obtained by introducing an attention mechanism, the attention mechanism is used for mapping the historical monitoring data of different wireless sensor nodes into three different vectors of query Q, key K and value V, the three vectors are learned to obtain a time attention function Tatt (Q, K, V),Where Q represents a matrix containing query conditions, K represents a matrix containing key values, V represents a matrix containing values of elements, and d k represents the dimension of each query condition in query Q. Calculating time weight according to a time attention function on time sequence, and effectively extracting historical monitoring data corresponding to the wireless sensor node;
In addition, in order to distinguish the importance of different wireless sensor nodes on blood storage space monitoring, different space weights are allocated to different neighbor nodes, a pooling layer and a full-connection layer are introduced into the graph convolution neural network, average pooling operation and maximum pooling operation in the pooling layer are utilized to sample the neighbor nodes, the weight of the current wireless sensor node contributing to other wireless sensor nodes in a topological structure is calculated and is used as the space weight, so that the graph convolution neural network is more focused on the sampled wireless sensor nodes, and the calculation formula of the space attention K att is as follows: where σ represents the activation function, f represents the fully connected layer, AP represents the average pooling operation, MP represents the maximum pooling operation,/> Representing a mapping function, and X i represents the characteristic of the environmental parameter monitored by the wireless sensor at the moment i;
Applying the time weight and the space weight to neighbor nodes of the target node, aggregating the features through a feature transfer and neighbor aggregation mechanism of the graph convolution neural network, updating the feature representation of the target node, representing the blood storage environment information of the current time step, and preferably, predicting the blood storage environment information of the next time step through the aggregated features by taking the gate control circulation network as an output layer.
According to the embodiment of the invention, the time sequence change characteristics based on the storage environment are combined with the blood collection information, and the blood quality information is analyzed, specifically:
Acquiring influencing factors of blood quality through a big data retrieval and expert recommendation method, calculating pearson correlation coefficients with a blood storage environment according to the influencing factors, and screening influencing factors of which the pearson correlation coefficients accord with a preset threshold;
Setting an evaluation index according to the influence factors obtained by screening, constructing a blood quality evaluation system based on the evaluation index and corresponding evaluation standards, evaluating the stock blood of the target blood bank through the blood quality evaluation system, and verifying through the detection data of the preset blood detection index;
Constructing a blood quality prediction model based on deep learning, generating training data according to evaluation data of a blood evaluation system, and training the blood quality prediction model through the training data;
And taking the time sequence of the blood storage environment change characteristics as input of a blood quality prediction model, analyzing the influence on the blood quality according to the blood storage environment change characteristics and the storage time length, and outputting blood quality information after the preset time.
After screening the influencing factors, analyzing the influence degree of index change corresponding to each evaluation index on the blood quality, presetting a scoring threshold value area or corresponding scoring grade information according to the index change amount and the influence degree, simultaneously acquiring index weight according to the pearson correlation coefficient, carrying out weighted summation on scores to acquire evaluation information, generating blood quality verification information through preset blood detection indexes, and correcting a blood quality evaluation system through the verification information.
Presetting a blood quality information threshold, judging whether the blood quality information corresponding to the current timestamp in the blood preservation environment is smaller than the preset blood quality information threshold, if so, carrying out blood quality early warning, and extracting blood label information of the blood quality early warning; marking the extracted blood label information, determining the stock position according to the marked blood label information, setting the ex-warehouse priority, and updating the ex-warehouse priority according to the real-time change of the blood quality information; blood demand information is obtained through basic information of clinical scientific research or clinical manifestations of patients, blood recommendation is carried out according to the blood demand information and the current ex-warehouse priority, marked blood is preferentially used for matching judgment, and best-fit blood is selected for ex-warehouse.
The third aspect of the present invention further provides a computer readable storage medium, where the computer readable storage medium includes a blood preservation whole-flow supervision method program based on the internet of things, and when the blood preservation whole-flow supervision method program based on the internet of things is executed by a processor, the steps of the blood preservation whole-flow supervision method based on the internet of things are implemented.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a read-On1y memory (ROM), a random access memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A blood preservation whole-flow supervision method based on the Internet of things is characterized by comprising the following steps of
Acquiring blood collection information, comparing the blood collection information with preset blood indexes, and judging whether the collected blood accords with the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result;
when the condition constraint is met, warehousing the blood, and generating label information according to the blood collection information to be matched with the blood;
Sensing blood storage environment information by using a wireless sensor network, acquiring the change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information;
And carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, preferentially matching early warning blood through the blood demand information, and selecting reasonable blood for delivery.
2. The method for supervising the whole blood preservation process based on the internet of things according to claim 1, wherein the method is characterized in that blood collection information is obtained, the blood collection information is compared with a preset blood index, and whether the collected blood meets the condition constraint corresponding to the current blood index of the target blood bank is judged according to the comparison result, specifically:
Obtaining basic information and common blood disease information of blood donors through questionnaire distribution, screening the blood donors according to the basic information and the common blood disease information, obtaining physical examination information in preset time by utilizing data retrieval according to the basic information, performing information verification, and generating blood label information;
If the current blood donor does not have relevant physical examination information, collecting a blood sample of the blood donor, and generating blood collection information according to the detection information of the blood sample and the basic information;
Setting condition constraint according to the judgment standard corresponding to each current blood detection index of the target blood bank, setting blood storage priority according to the stock information of the target blood bank, and judging whether the blood collection information accords with the condition constraint;
if the blood label information accords with the current preset grade standard, generating blood label information based on the blood collection information for warehousing;
And if the grade information does not accord with the current preset grade standard, the corresponding blood donators are classified into a waiting queue, and the notification of the blood donators in the waiting queue is carried out according to the update of the target blood bank warehousing priority.
3. The method for supervising the whole blood preservation process based on the internet of things according to claim 1, wherein the method is characterized in that the wireless sensor network is utilized to sense the information of the blood storage environment, and the change characteristics of the blood storage environment are obtained in real time, specifically:
Performing advanced distribution of different types of wireless sensor nodes according to the spatial layout of the target blood bank, acquiring storage environment parameters of the target blood bank through the wireless sensor nodes at preset positions, performing convergence transmission through the convergence nodes in the wireless sensor network, and preprocessing the acquired storage environment parameters;
Obtaining a topological structure of a wireless sensor network in a target blood bank, and representing the topological structure through a directed graph G= (V, E), wherein V represents wireless sensor nodes in the target blood bank, and E represents connection relations among the wireless sensor nodes;
The method comprises the steps of taking category information and history data of environmental information collected by wireless sensor nodes as attribute characteristics of nodes in a directed graph, obtaining the distance between the wireless sensor nodes through Manhattan distance, and judging whether the two nodes are adjacent or not according to the Manhattan distance;
The directed graph is subjected to representation learning through a graph convolution neural network, time features and space features in a wireless sensor topological structure are mined, corresponding time weights and space weights are generated, and the features are aggregated according to the time weights and the space weights;
the method comprises the steps of carrying out weighted calculation on neighbor nodes, carrying out summation on the weighted characteristics to update the characteristics of the nodes, representing blood storage environment information of the current time step by the aggregated characteristics, and inputting the aggregated characteristics into an output layer;
And training the loss function of the output layer until convergence, predicting the blood storage environment information after a preset time step, and acquiring the change characteristics of the blood storage environment in real time.
4. The method for monitoring and managing the whole blood preservation process based on the internet of things according to claim 3, wherein the mining of the temporal features and the spatial features in the topology structure of the wireless sensor generates corresponding temporal weights and spatial weights, and the feature aggregation is performed according to the temporal weights and the spatial weights, specifically:
Acquiring dynamic correlation of blood storage environment parameters in a historical time step and a future time step through an attention introducing mechanism, calculating time weight according to a time attention function on time sequence, and effectively extracting historical monitoring data corresponding to wireless sensor nodes;
In addition, a pooling layer and a full-connection layer are introduced into the graph convolution neural network, the average pooling operation and the maximum pooling operation in the pooling layer are utilized to sample neighbor nodes, and the weight of the current wireless sensor node contribution to other wireless sensor nodes in the topological structure is calculated and used as the spatial weight;
and acquiring the time weight and the space weight of the neighbor nodes, and carrying out aggregation updating on the features through the feature transfer of the graph convolution neural network and a neighbor aggregation mechanism.
5. The method for monitoring the whole blood preservation process based on the internet of things according to claim 1, wherein the method is characterized in that the method is used for analyzing the blood quality information by combining time sequence change characteristics of a storage environment with blood collection information, and specifically comprises the following steps:
Acquiring influencing factors of blood quality through a big data retrieval and expert recommendation method, calculating pearson correlation coefficients with a blood storage environment according to the influencing factors, and screening influencing factors of which the pearson correlation coefficients accord with a preset threshold;
Setting an evaluation index according to the influence factors obtained by screening, constructing a blood quality evaluation system based on the evaluation index and corresponding evaluation standards, evaluating the stock blood of the target blood bank through the blood quality evaluation system, and verifying through the detection data of the preset blood detection index;
Constructing a blood quality prediction model based on deep learning, generating training data according to evaluation data of a blood evaluation system, and training the blood quality prediction model through the training data;
And taking the time sequence of the blood storage environment change characteristics as input of a blood quality prediction model, analyzing the influence on the blood quality according to the blood storage environment change characteristics and the storage time length, and outputting blood quality information after the preset time.
6. The whole blood preservation process supervision method based on the internet of things according to claim 1, wherein the blood quality pre-warning is performed according to the blood quality information, the blood demand information is obtained, the pre-warning blood is preferentially matched through the blood demand information, and reasonable blood is selected for delivery, specifically:
Presetting a blood quality information threshold, judging whether the blood quality information corresponding to the current timestamp in the blood preservation environment is smaller than the preset blood quality information threshold, if so, carrying out blood quality early warning, and extracting blood label information of the blood quality early warning;
Marking the extracted blood label information, determining the stock position according to the marked blood label information, setting the ex-warehouse priority, and updating the ex-warehouse priority according to the real-time change of the blood quality information;
Blood demand information is obtained through basic information of clinical scientific research or clinical manifestations of patients, blood recommendation is carried out according to the blood demand information and the current ex-warehouse priority, marked blood is preferentially used for matching judgment, and best-fit blood is selected for ex-warehouse.
7. Blood preservation full-flow supervision system based on thing networking, characterized in that, this system includes: the blood preservation whole-flow supervision method based on the Internet of things comprises a memory and a processor, wherein the memory comprises a blood preservation whole-flow supervision method program based on the Internet of things, and the blood preservation whole-flow supervision method program based on the Internet of things realizes the following steps when being executed by the processor:
acquiring blood collection information, comparing the blood collection information with preset blood indexes, and judging whether the collected blood accords with the condition constraint corresponding to the current blood index of the target blood bank according to the comparison result;
when the condition constraint is met, warehousing the blood, and generating label information according to the blood collection information to be matched with the blood;
Sensing blood storage environment information by using a wireless sensor network, acquiring the change characteristics of the blood storage environment in real time, combining the time sequence change characteristics of the storage environment with blood collection information, and analyzing blood quality information;
And carrying out blood quality early warning according to the blood quality information, acquiring blood demand information, preferentially matching early warning blood through the blood demand information, and selecting reasonable blood for delivery.
8. The internet of things-based blood preservation whole-flow supervision system of claim 7, wherein the wireless sensor network is utilized to sense information of a blood storage environment, and change characteristics of the blood storage environment are obtained in real time, specifically:
Performing advanced distribution of different types of wireless sensor nodes according to the spatial layout of the target blood bank, acquiring storage environment parameters of the target blood bank through the wireless sensor nodes at preset positions, performing convergence transmission through the convergence nodes in the wireless sensor network, and preprocessing the acquired storage environment parameters;
Obtaining a topological structure of a wireless sensor network in a target blood bank, and representing the topological structure through a directed graph G= (V, E), wherein V represents wireless sensor nodes in the target blood bank, and E represents connection relations among the wireless sensor nodes;
The method comprises the steps of taking category information and history data of environmental information collected by wireless sensor nodes as attribute characteristics of nodes in a directed graph, obtaining the distance between the wireless sensor nodes through Manhattan distance, and judging whether the two nodes are adjacent or not according to the Manhattan distance;
The directed graph is subjected to representation learning through a graph convolution neural network, time features and space features in a wireless sensor topological structure are mined, corresponding time weights and space weights are generated, and the features are aggregated according to the time weights and the space weights;
the method comprises the steps of carrying out weighted calculation on neighbor nodes, carrying out summation on the weighted characteristics to update the characteristics of the nodes, representing blood storage environment information of the current time step by the aggregated characteristics, and inputting the aggregated characteristics into an output layer;
And training the loss function of the output layer until convergence, predicting the blood storage environment information after a preset time step, and acquiring the change characteristics of the blood storage environment in real time.
9. The blood preservation whole-flow supervision system based on the internet of things according to claim 8, wherein the mining of the temporal features and the spatial features in the wireless sensor topology structure generates corresponding temporal weights and spatial weights, and the feature aggregation is performed according to the temporal weights and the spatial weights, specifically:
Acquiring dynamic correlation of blood storage environment parameters in a historical time step and a future time step through an attention introducing mechanism, calculating time weight according to a time attention function on time sequence, and effectively extracting historical monitoring data corresponding to wireless sensor nodes;
In addition, a pooling layer and a full-connection layer are introduced into the graph convolution neural network, the average pooling operation and the maximum pooling operation in the pooling layer are utilized to sample neighbor nodes, and the weight of the current wireless sensor node contribution to other wireless sensor nodes in the topological structure is calculated and used as the spatial weight;
and acquiring the time weight and the space weight of the neighbor nodes, and carrying out aggregation updating on the features through the feature transfer of the graph convolution neural network and a neighbor aggregation mechanism.
10. The internet of things-based blood preservation whole-process monitoring system according to claim 7, wherein the blood quality information is analyzed by combining time sequence change characteristics of a storage environment with blood collection information, specifically:
Acquiring influencing factors of blood quality through a big data retrieval and expert recommendation method, calculating pearson correlation coefficients with a blood storage environment according to the influencing factors, and screening influencing factors of which the pearson correlation coefficients accord with a preset threshold;
Setting an evaluation index according to the influence factors obtained by screening, constructing a blood quality evaluation system based on the evaluation index and corresponding evaluation standards, evaluating the stock blood of the target blood bank through the blood quality evaluation system, and verifying through the detection data of the preset blood detection index;
Constructing a blood quality prediction model based on deep learning, generating training data according to evaluation data of a blood evaluation system, and training the blood quality prediction model through the training data;
And taking the time sequence of the blood storage environment change characteristics as input of a blood quality prediction model, analyzing the influence on the blood quality according to the blood storage environment change characteristics and the storage time length, and outputting blood quality information after the preset time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310317146.8A CN117912645B (en) | 2023-03-29 | Blood preservation whole-flow supervision method and system based on Internet of things |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310317146.8A CN117912645B (en) | 2023-03-29 | Blood preservation whole-flow supervision method and system based on Internet of things |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117912645A true CN117912645A (en) | 2024-04-19 |
CN117912645B CN117912645B (en) | 2024-08-02 |
Family
ID=
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080208750A1 (en) * | 2005-01-19 | 2008-08-28 | Yan Chen | Method and System of Using Rfid in the Workflow of Blood Center |
US20170053067A1 (en) * | 2015-08-18 | 2017-02-23 | International Business Machines Corporation | Cloud-based blood bank collaborative communication and recommendation |
CN109411038A (en) * | 2018-09-28 | 2019-03-01 | 石海燕 | Blood information acquisition Compare System and comparison method, storage medium in a kind of blood transfusion |
CN109911497A (en) * | 2019-01-31 | 2019-06-21 | 青岛海尔生物医疗股份有限公司 | A kind of blood-safety management system |
WO2020047739A1 (en) * | 2018-09-04 | 2020-03-12 | 安徽中科智能感知大数据产业技术研究院有限责任公司 | Method for predicting severe wheat disease on the basis of multiple time-series attribute element depth features |
CN111367961A (en) * | 2020-02-27 | 2020-07-03 | 西安交通大学 | Time sequence data event prediction method and system based on graph convolution neural network and application thereof |
CN111737909A (en) * | 2020-06-10 | 2020-10-02 | 哈尔滨工业大学 | Structural health monitoring data anomaly identification method based on space-time graph convolutional network |
CN113345565A (en) * | 2021-07-05 | 2021-09-03 | 上海新程医学科技有限公司 | Matching management terminal, matching optimization method and system for blood infusion and storage medium |
CN114821766A (en) * | 2022-03-10 | 2022-07-29 | 电子科技大学 | Behavior identification method based on space-time convolution and time sequence feature fusion |
CN115547473A (en) * | 2022-11-10 | 2022-12-30 | 淮安市第二人民医院 | Medical treatment is with intelligent blood bank information management platform |
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080208750A1 (en) * | 2005-01-19 | 2008-08-28 | Yan Chen | Method and System of Using Rfid in the Workflow of Blood Center |
US20170053067A1 (en) * | 2015-08-18 | 2017-02-23 | International Business Machines Corporation | Cloud-based blood bank collaborative communication and recommendation |
WO2020047739A1 (en) * | 2018-09-04 | 2020-03-12 | 安徽中科智能感知大数据产业技术研究院有限责任公司 | Method for predicting severe wheat disease on the basis of multiple time-series attribute element depth features |
CN109411038A (en) * | 2018-09-28 | 2019-03-01 | 石海燕 | Blood information acquisition Compare System and comparison method, storage medium in a kind of blood transfusion |
CN109911497A (en) * | 2019-01-31 | 2019-06-21 | 青岛海尔生物医疗股份有限公司 | A kind of blood-safety management system |
CN111367961A (en) * | 2020-02-27 | 2020-07-03 | 西安交通大学 | Time sequence data event prediction method and system based on graph convolution neural network and application thereof |
CN111737909A (en) * | 2020-06-10 | 2020-10-02 | 哈尔滨工业大学 | Structural health monitoring data anomaly identification method based on space-time graph convolutional network |
CN113345565A (en) * | 2021-07-05 | 2021-09-03 | 上海新程医学科技有限公司 | Matching management terminal, matching optimization method and system for blood infusion and storage medium |
CN114821766A (en) * | 2022-03-10 | 2022-07-29 | 电子科技大学 | Behavior identification method based on space-time convolution and time sequence feature fusion |
CN115547473A (en) * | 2022-11-10 | 2022-12-30 | 淮安市第二人民医院 | Medical treatment is with intelligent blood bank information management platform |
Non-Patent Citations (1)
Title |
---|
"RFID传感技术融合在血液管理中的应用", 《REID新闻中心 微血站公众号》, 31 October 2019 (2019-10-31), pages 1 - 4 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110139067B (en) | Wild animal monitoring data management information system | |
US20060100969A1 (en) | Learning-based method for estimating cost and statistics of complex operators in continuous queries | |
CN112966714B (en) | Edge time sequence data anomaly detection and network programmable control method | |
CN112017789B (en) | Triage data processing method, triage data processing device, triage data processing equipment and triage data processing medium | |
CN113270197A (en) | Health prediction method, system and storage medium based on artificial intelligence | |
WO2021103823A1 (en) | Model update system, model update method, and related device | |
CN113971527A (en) | Data risk assessment method and device based on machine learning | |
CN117473571B (en) | Data information security processing method and system | |
CN116562514B (en) | Method and system for immediately analyzing production conditions of enterprises based on neural network | |
CN116865994A (en) | Network data security prediction method based on big data | |
CN110689140A (en) | Method for intelligently managing rail transit alarm data through big data | |
CN113435825B (en) | Intelligent management method, system and storage medium based on soil-borne disease control | |
CN117094535B (en) | Artificial intelligence-based energy supply management method and system | |
CN117764562A (en) | intelligent access control equipment management method and system based on Internet of things | |
CN117912645B (en) | Blood preservation whole-flow supervision method and system based on Internet of things | |
CN115964504B (en) | Food safety risk prediction method and system | |
CN117912645A (en) | Blood preservation whole-flow supervision method and system based on Internet of things | |
CN115662595A (en) | User information management method and system based on online diagnosis and treatment system | |
CN116361628A (en) | Fault category intelligent analysis method and device based on VFD room | |
CN115221955A (en) | Multi-depth neural network parameter fusion system and method based on sample difference analysis | |
CN116401604B (en) | Method for classifying and detecting cold head state and predicting service life | |
CN114171206A (en) | Model training method, sensing disease prediction method, device, equipment and storage medium | |
CN111723872A (en) | Pedestrian attribute identification method and device, storage medium and electronic device | |
CN117807450B (en) | Urban intelligent public transportation system and method | |
CN117391456B (en) | Village management method and service platform system based on artificial intelligence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |