CN116313127A - Decision support system based on pre-hospital first-aid big data - Google Patents
Decision support system based on pre-hospital first-aid big data Download PDFInfo
- Publication number
- CN116313127A CN116313127A CN202310297299.0A CN202310297299A CN116313127A CN 116313127 A CN116313127 A CN 116313127A CN 202310297299 A CN202310297299 A CN 202310297299A CN 116313127 A CN116313127 A CN 116313127A
- Authority
- CN
- China
- Prior art keywords
- help
- decision
- terminal
- representing
- aid
- 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.)
- Pending
Links
Images
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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to the technical field of big data, and discloses a decision support system based on pre-hospital first-aid big data, which comprises the following components: a terminal information acquisition module for determining the ID of the help seeking terminal of the help seeking person through the attribution of the help seeking terminal; the associated information acquisition module acquires associated information according to the ID of the help seeker help terminal; a correlation information processing module for generating correlation timing information based on the correlation information in a time order; a model generation module for generating a decision learning model; the decision classification module is used for inputting the associated time sequence information generated for the current help seeker into the decision learning model and outputting the first-aid class label; a rescue decision module that selects a corresponding rescue means based on the currently output first aid category label; the invention can carry out deep learning to construct a decision model based on the help seeker terminal help record such a data source comprehensive pre-hospital big data so as to judge the emergency degree of the first aid requirement of the help seeker.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a decision support system based on pre-hospital first-aid big data.
Background
For emergency help seekers who can normally inquire the illness state through communication, it is feasible to judge the emergency degree of emergency through manual recording of the illness state, but for some patients who cannot communicate with an operator, the illness state of the patient cannot be obtained through communication, whether the help seeker misreports or needs emergency cannot be judged, and the emergency degree of emergency needs cannot be judged.
Disclosure of Invention
The invention provides a decision support system based on pre-hospital emergency big data, which solves the technical problem that emergency call telephones which cannot communicate normally in the related art cannot judge the emergency degree of emergency demands.
The invention provides a decision support system based on pre-hospital first-aid big data, which comprises:
a terminal information acquisition module for determining the ID of the help seeking terminal of the help seeking person through the attribution of the help seeking terminal;
the associated information acquisition module acquires associated information according to the ID of the help seeker help terminal;
the system comprises a related information processing module, a time sequence processing module and a time sequence processing module, wherein the related information processing module is used for generating related time sequence information based on the related information according to time sequence from the time when the help seeking terminal terminates the help seeking call, and one sequence unit of the related time sequence information comprises corresponding related information before one time point;
a model generation module for generating a decision learning model;
the first aid category labels output by the decision learning model correspond to false alarms, emergency first aid and general rescue;
a model training module for training the decision learning model through historical associated time sequence information and corresponding first aid class labels;
the decision classification module is used for inputting the associated time sequence information generated for the current help seeker into the decision learning model and outputting the first-aid class label;
and a rescue decision module for selecting a corresponding rescue means based on the currently output first aid class label.
Further, the associated information includes other terminals contacted by the help seeking terminal, call duration corresponding to the contacted terminal, time corresponding to the contacted terminal, and IP address corresponding to the contacted terminal.
Further, the correlation timing information is generated from the correlation information after normalization.
Further, the decision learning model comprises an LSTM neural network, wherein the LSTM neural network comprises a plurality of LSTM units, and each LSTM unit inputs a sequence unit associated with time sequence information;
output state h of each LSTM cell t The calculation formula of (2) is as follows:
h t =o t ⊙tanh(C t )
W xo Representing input x t Transfer to o t The corresponding weight matrix is used to determine the weight matrix,representing the output state h of the last LSTM cell t-1 Transfer to o t Corresponding weight matrix, b o Representing bias terms, σ representing a sigmoid function;
f t ⊙C t-1 Door f for indicating forgetfulness t And output state C of last LSTM cell t-1 Multiplying point by point, f t ∈(0,1);Indicating input/output gate i t And intermediate state->Performing point-by-point multiplication;
W fx Representing input x t Transfer to f t The corresponding weight matrix is used to determine the weight matrix,representing the last LSTM cell state h t-1 Transfer to f t Corresponding weight matrix, b f Representing bias terms, σ representing a sigmoid function;
W xi Representing input x t Transfer to i t The corresponding weight matrix is used to determine the weight matrix,representing the last LSTM cell state h t-1 Transfer to i t Corresponding weight matrix, b i Represents the bias term, σ represents the sigmoid function.
W xC Representing input x t To transfer toCorresponding weight matrix, < >>Representing the last LSTM cell state h t-1 Transfer to->Corresponding weight matrix, b C Representing the bias term, tanh represents the hyperbolic tangent function.
Further, the output of the last LSTM cell of the LSTM neural network is connected to the softmax classifier, and the output emergency class labels correspond to false alarms, emergency and general rescue.
Further, if the first aid class label is an emergency first aid, determining the position directly based on the help seeker terminal, and dispatching the ambulance;
if the first-aid class label is false report, recording and marking;
if the first aid category is general rescue, the community or property where the help seeker is located is contacted to check the situation by the door-to-door system.
Further, vector alignment is performed when the sequence unit inputs the decision learning model.
Further, the vector of the sequence unit with the largest dimension is used as an alignment vector, the vector to be aligned is compared with the vector of the sequence unit with the largest digit, the missing dimension is determined, and vector alignment is performed by interpolation of 0 or 0.1.
The invention provides a first-aid decision-making method, which is implemented by applying the decision-making support system based on pre-hospital first-aid big data and comprises the following steps:
The invention has the beneficial effects that:
the invention can carry out deep learning based on the help-seeking terminal to record the data source of the data source before the comprehensive hospital to construct a decision model so as to judge the emergency degree of the emergency demand of the help-seeking person, and solves the problem that the emergency call which cannot normally communicate cannot judge the emergency degree of the emergency demand.
Drawings
Fig. 1 is a schematic block diagram of a decision support system based on pre-hospital emergency big data according to the present invention.
In the figure: the system comprises a terminal information acquisition module 101, a correlation information acquisition module 102, a correlation information processing module 103, a model generation module 104, a model training module 105, a decision classification module 106 and a rescue decision module 107.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It is to be understood that these embodiments are merely discussed so that those skilled in the art may better understand and implement the subject matter described herein and that changes may be made in the function and arrangement of the elements discussed without departing from the scope of the disclosure herein. Various examples may omit, replace, or add various procedures or components as desired. In addition, features described with respect to some examples may be combined in other examples as well.
Example 1
As shown in fig. 1, a decision support system based on pre-hospital emergency big data includes:
a terminal information acquisition module 101 for determining an ID of a help-seeking terminal of a help-seeking person through attribution of the help-seeking terminal;
an associated information acquisition module 102 that acquires associated information from the ID of the help seeker help terminal;
generally, a help seeking terminal is a terminal with a fixed communication ID such as a mobile phone.
The associated information comprises other terminals which are contacted by the help seeking terminal, the call duration corresponding to the contacted terminal, the time corresponding to the contacted terminal and the IP address corresponding to the contacted terminal;
the related information processing module 103 is configured to generate related timing information based on the related information according to a time sequence from when the help terminal terminates the help call, where a sequence unit of the related timing information includes corresponding related information before a time point, that is, the sequence unit is generated by accumulating, so as to avoid a situation that a corresponding related information blank occurs at some time points, resulting in a sequence unit blank;
in one embodiment of the invention, the correlation timing information is generated from the correlation information after normalization.
A model generation module 104 for generating a decision learning model;
the decision learning model comprises an LSTM neural network, wherein the LSTM neural network comprises a plurality of LSTM units, and each LSTM unit inputs a sequence unit associated with time sequence information;
output state h of each LSTM cell t The calculation formula of (2) is as follows:
h t =o t ⊙tanh(C t )
W xo Representing input x t Transfer to o t The corresponding weight matrix is used to determine the weight matrix,representing the output state h of the last LSTM cell t-1 Transfer to o t Corresponding weight matrix, b o Representing bias terms, σ representing a sigmoid function;
f t ⊙C t-1 Door f for indicating forgetfulness t And output state C of last LSTM cell t-1 Multiplying point by point, f t ∈(0,1);Indicating input/output gate i t And intermediate state->Performing point-by-point multiplication;
W fx Representing input x t Transfer to f t The corresponding weight matrix is used to determine the weight matrix,representing the last LSTM cell state h t-1 Transfer to f t Corresponding weight matrix, b f Representing bias terms, σ representing a sigmoid function;
W xi Representing input x t Transfer to i t The corresponding weight matrix is used to determine the weight matrix,representing the last LSTM cell state h t-1 Transfer to i t Corresponding weight matrix, b i Represents the bias term, σ represents the sigmoid function.
W xC Representing input x t To transfer toCorresponding toWeight matrix (W/W)>Representing the last LSTM cell state h t-1 Transfer to->Corresponding weight matrix, b C Representing a bias term, tanh representing a hyperbolic tangent function;
the output of the last LSTM unit of the LSTM neural network is connected with a softmax classifier, and the output first aid category label corresponds to false alarm, emergency first aid and general rescue;
a model training module 105 that trains the decision learning model by historical correlated timing information and corresponding first aid category labels;
in one embodiment of the invention, vector alignment is performed when the sequence unit inputs the decision learning model;
as a vector alignment mode, taking a vector of a sequence unit with the largest dimension as an alignment vector, comparing the vector to be aligned with a vector of a sequence unit with the largest digit, determining the missing dimension, and carrying out vector alignment by interpolation 0 or 0.1;
a decision classification module 106 for inputting the associated time sequence information generated for the current help seeker into a decision learning model and outputting an emergency class label;
a rescue decision module 107 that selects a corresponding rescue means based on the currently output first aid class label;
for example, if the emergency class tag is an emergency, the location is determined directly based on the help seeker terminal, and the ambulance is dispatched.
If the first-aid class label is false report, recording and marking;
if the first aid category is general rescue, the community or property where the help seeker is can be contacted to check the situation by the gate-on system.
In one embodiment of the present invention, an emergency decision method using the decision support system based on pre-hospital emergency big data is provided, which comprises the following steps:
The embodiment has been described above with reference to the embodiment, but the embodiment is not limited to the above-described specific implementation, which is only illustrative and not restrictive, and many forms can be made by those of ordinary skill in the art, given the benefit of this disclosure, are within the scope of this embodiment.
Claims (9)
1. A pre-hospital emergency big data based decision support system, comprising:
a terminal information acquisition module for determining the ID of the help seeking terminal of the help seeking person through the attribution of the help seeking terminal;
the associated information acquisition module acquires associated information according to the ID of the help seeker help terminal;
the system comprises a related information processing module, a time sequence processing module and a time sequence processing module, wherein the related information processing module is used for generating related time sequence information based on the related information according to time sequence from the time when the help seeking terminal terminates the help seeking call, and one sequence unit of the related time sequence information comprises corresponding related information before one time point;
a model generation module for generating a decision learning model;
the first aid category labels output by the decision learning model correspond to false alarms, emergency first aid and general rescue;
a model training module for training the decision learning model through historical associated time sequence information and corresponding first aid class labels;
the decision classification module is used for inputting the associated time sequence information generated for the current help seeker into the decision learning model and outputting the first-aid class label;
and a rescue decision module for selecting a corresponding rescue means based on the currently output first aid class label.
2. The decision support system based on pre-hospital emergency big data according to claim 1, wherein the associated information includes other terminals that call for help to connect with the terminal, and a call duration corresponding to the connected terminal, a time corresponding to the connected terminal, and an IP address corresponding to the connected terminal.
3. The pre-hospital emergency big data-based decision support system of claim 1, wherein the associated timing information is generated from the associated information after normalization.
4. The pre-hospital emergency big data-based decision support system according to claim 1, wherein the decision learning model comprises an LSTM neural network, the LSTM neural network comprising a plurality of LSTM units, each LSTM unit inputting a sequence unit associated with timing information;
output state h of each LSTM cell t The calculation formula of (2) is as follows:
h t =o t ⊙tanh(C t )
W xo Representing input x t Transfer to o t Corresponding toIs used for the weight matrix of the (c),representing the output state h of the last LSTM cell t-1 Transfer to o t Corresponding weight matrix, b o Representing bias terms, σ representing a sigmoid function;
f t ⊙C t-1 Door f for indicating forgetfulness t And output state C of last LSTM cell t-1 Multiplying point by point, f t ∈(0,1);Indicating input/output gate i t And intermediate state->Performing point-by-point multiplication;
W fx Representing input x t Transfer to f t The corresponding weight matrix is used to determine the weight matrix,representing the last LSTM cell state h t-1 Transfer to f t Corresponding weight matrix, b f Representing bias terms, σ representing a sigmoid function;
W xi Representing input x t Transfer to i t The corresponding weight matrix is used to determine the weight matrix,representing the last LSTM cell state h t-1 Transfer to i t Corresponding weight matrix, b i Representing bias terms, σ representing a sigmoid function;
5. The pre-hospital emergency big data-based decision support system of claim 4, wherein an output of a last LSTM cell of the LSTM neural network is connected to a softmax classifier, and the outputted emergency class labels correspond to false alarms, emergency and general aid.
6. The pre-hospital emergency big data-based decision support system of claim 1, wherein if the emergency category label is emergency, determining the location directly based on the help seeker terminal, dispatching the ambulance;
if the first-aid class label is false report, recording and marking;
if the first aid category is general rescue, the community or property where the help seeker is located is contacted to check the situation by the door-to-door system.
7. The pre-hospital emergency big data-based decision support system of claim 1, wherein the sequence unit performs vector alignment when inputting the decision learning model.
8. The decision support system based on pre-hospital emergency big data according to claim 7, wherein the vector of the sequence unit with the largest dimension is used as an alignment vector, the vector to be aligned is compared with the vector of the sequence unit with the largest digit, the missing dimension is determined, and the vector alignment is performed by interpolating 0 or 0.1.
9. A method of emergency decision making, characterized in that the application of a pre-hospital emergency big data based decision support system according to any of claims 1-8 performs the following steps:
step 101, determining the ID of a help seeking terminal of a help seeking person through the attribution of the help seeking terminal;
step 102, acquiring associated information according to the ID of the help seeker help-seeking terminal;
step 103, generating associated time sequence information based on the associated information according to a time sequence from the time when the help terminal terminates the help call;
step 104, generating a decision learning model;
step 105, training the decision learning model through the historical associated time sequence information and the corresponding first aid class labels;
step 106, inputting the associated time sequence information generated for the current help seeker into a decision learning model, and outputting an emergency class label;
step 107, selecting a corresponding rescue means based on the currently output first aid class label.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310297299.0A CN116313127A (en) | 2023-03-23 | 2023-03-23 | Decision support system based on pre-hospital first-aid big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310297299.0A CN116313127A (en) | 2023-03-23 | 2023-03-23 | Decision support system based on pre-hospital first-aid big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116313127A true CN116313127A (en) | 2023-06-23 |
Family
ID=86813042
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310297299.0A Pending CN116313127A (en) | 2023-03-23 | 2023-03-23 | Decision support system based on pre-hospital first-aid big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116313127A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116595896A (en) * | 2023-07-17 | 2023-08-15 | 合肥顺昌分布式能源综合应用技术有限公司 | Big data-based energy management system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105933861A (en) * | 2016-04-12 | 2016-09-07 | 邹勇松 | Emergency rescue processing method |
JP2018116340A (en) * | 2017-01-16 | 2018-07-26 | 株式会社日立製作所 | Emergency information system, and emergency information management method |
JP2020013234A (en) * | 2018-07-17 | 2020-01-23 | 株式会社日立製作所 | Emergency notification listening support system and emergency notification listening support method |
CN111028913A (en) * | 2019-11-29 | 2020-04-17 | 北京工业大学 | Hemodialysis treatment scheme aid decision-making method |
CN213042671U (en) * | 2020-08-10 | 2021-04-23 | 中南大学湘雅医院 | Pre-hospital emergency system |
CN115242359A (en) * | 2022-07-22 | 2022-10-25 | 重庆邮电大学 | Intelligent-old-age-care-oriented monitoring system and implementation method thereof |
CN115633124A (en) * | 2022-10-10 | 2023-01-20 | 上海传英信息技术有限公司 | Help seeking method, intelligent terminal and storage medium |
CN115798708A (en) * | 2022-11-25 | 2023-03-14 | 西安交通大学 | First-aid injury classification method based on long-time sequence |
-
2023
- 2023-03-23 CN CN202310297299.0A patent/CN116313127A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105933861A (en) * | 2016-04-12 | 2016-09-07 | 邹勇松 | Emergency rescue processing method |
JP2018116340A (en) * | 2017-01-16 | 2018-07-26 | 株式会社日立製作所 | Emergency information system, and emergency information management method |
JP2020013234A (en) * | 2018-07-17 | 2020-01-23 | 株式会社日立製作所 | Emergency notification listening support system and emergency notification listening support method |
CN111028913A (en) * | 2019-11-29 | 2020-04-17 | 北京工业大学 | Hemodialysis treatment scheme aid decision-making method |
CN213042671U (en) * | 2020-08-10 | 2021-04-23 | 中南大学湘雅医院 | Pre-hospital emergency system |
CN115242359A (en) * | 2022-07-22 | 2022-10-25 | 重庆邮电大学 | Intelligent-old-age-care-oriented monitoring system and implementation method thereof |
CN115633124A (en) * | 2022-10-10 | 2023-01-20 | 上海传英信息技术有限公司 | Help seeking method, intelligent terminal and storage medium |
CN115798708A (en) * | 2022-11-25 | 2023-03-14 | 西安交通大学 | First-aid injury classification method based on long-time sequence |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116595896A (en) * | 2023-07-17 | 2023-08-15 | 合肥顺昌分布式能源综合应用技术有限公司 | Big data-based energy management system |
CN116595896B (en) * | 2023-07-17 | 2023-09-22 | 合肥顺昌分布式能源综合应用技术有限公司 | Big data-based energy management system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20190171928A1 (en) | Dynamically managing artificial neural networks | |
EP3920048A1 (en) | Method and system for automated visual question answering | |
CN111133453A (en) | Artificial neural network | |
CN116186359B (en) | Integrated management method, system and storage medium for multi-source heterogeneous data of universities | |
CN116313127A (en) | Decision support system based on pre-hospital first-aid big data | |
CN112035671B (en) | State detection method and device, computer equipment and storage medium | |
US20150339591A1 (en) | Collegial Activity Learning Between Heterogeneous Sensors | |
CN107832720A (en) | information processing method and device based on artificial intelligence | |
CN110781970A (en) | Method, device and equipment for generating classifier and storage medium | |
CN109960811B (en) | Data processing method and device and electronic equipment | |
CN102178511A (en) | Disease prevention warning system and implementation method | |
CN114529747A (en) | Policy detection method, policy detection device, electronic apparatus, and storage medium | |
CN114022841A (en) | Personnel monitoring and identifying method and device, electronic equipment and readable storage medium | |
CN116935083B (en) | Image clustering method and device | |
US20240095539A1 (en) | Distributed machine learning with new labels using heterogeneous label distribution | |
CN112270334B (en) | Few-sample image classification method and system based on abnormal point exposure | |
CN112182498A (en) | Old people nursing device and method based on network representation learning | |
CN115457433A (en) | Attention detection method, attention detection device and storage medium | |
US11983246B2 (en) | Data analysis system, learning device, method, and program | |
Park et al. | Situation reasoning framework for the Internet of Things environments using deep learning results | |
CN116229581B (en) | Intelligent interconnection first-aid system based on big data | |
CN115601819B (en) | Multimode violence tendency recognition method, device, equipment and medium | |
CN116595978B (en) | Object category identification method, device, storage medium and computer equipment | |
KR102306932B1 (en) | Method for responding crisis using civil complaint data and system thereof | |
CN118015374A (en) | Small sample image recognition method and system |
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 |