CN118210909B - Disaster emergency auxiliary decision-making method, disaster emergency auxiliary decision-making device, computer equipment and storage medium - Google Patents
Disaster emergency auxiliary decision-making method, disaster emergency auxiliary decision-making device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN118210909B CN118210909B CN202410628154.9A CN202410628154A CN118210909B CN 118210909 B CN118210909 B CN 118210909B CN 202410628154 A CN202410628154 A CN 202410628154A CN 118210909 B CN118210909 B CN 118210909B
- Authority
- CN
- China
- Prior art keywords
- disaster
- text
- openfoam
- model
- question
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000001149 cognitive effect Effects 0.000 claims abstract description 43
- 238000004088 simulation Methods 0.000 claims abstract description 42
- 230000008569 process Effects 0.000 claims abstract description 20
- 230000015654 memory Effects 0.000 claims description 28
- 238000003058 natural language processing Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims 1
- 239000012530 fluid Substances 0.000 abstract description 9
- 239000007787 solid Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 239000007788 liquid Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Computing Systems (AREA)
- Human Computer Interaction (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of disaster emergency, and discloses a disaster emergency auxiliary decision-making method, a disaster emergency auxiliary decision-making device, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring disaster problem text, wherein the disaster problem text comprises disaster problem scene data, and the disaster problem scene data comprises fluid dynamics data; inputting the disaster problem text into a pre-established cognitive model, and generating OpenFOAM input data related to disaster problem scene data; creating an OpenFOAM model by using OpenFOAM input data; and running a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on disaster problem scene data to obtain a disaster scene simulation result. The simulation model is built through participation of the cognitive model, simulation efficiency is improved, the disaster evolution process simulated through the simulation model is more accurate, and disaster emergency measures obtained based on simulation results are more effective.
Description
Technical Field
The invention relates to the technical field of disaster emergency, in particular to a disaster emergency auxiliary decision-making method, a disaster emergency auxiliary decision-making device, computer equipment and a storage medium.
Background
In order to meet the emergency treatment demands caused by disasters such as fire and waterlogging, an expert is required to evaluate the disaster situation according to related knowledge, visual judgment and previous experience, and provide advice according to the evaluation result, and a commander makes emergency measures according to the advice of the expert. However, when a disaster occurs, if an expert cannot rush to the scene in time, an effective suggestion cannot be provided in time, and effective treatment measures cannot be taken for the disaster at the first time; if the expert gives the advice remotely, the advice is not accurate enough because the field situation cannot be acquired accurately. In addition, experts are limited by subjective judgment, limited information and time pressure, which can lead to inaccurate judgment, so that measures provided for commanders are suggested to be incapable of effectively disposing disasters.
Disclosure of Invention
In view of the above, the invention provides a disaster emergency auxiliary decision-making method, a disaster emergency auxiliary decision-making device, computer equipment and a storage medium, so as to solve the problem that measures advice provided by specialists to commanders cannot be used for effectively disposing disasters.
In a first aspect, the present invention provides a disaster emergency auxiliary decision-making method, the method comprising: acquiring disaster problem texts, wherein the disaster problem texts comprise disaster problem scene data; inputting the disaster problem text into a pre-established cognitive model, and performing intelligent question answering through the cognitive model to generate OpenFOAM input data related to disaster problem scene data; creating an OpenFOAM model by using OpenFOAM input data; and running a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on disaster problem scene data to obtain a disaster scene simulation result.
When a disaster occurs, a simulation model is established, the evolution process of the disaster is simulated through the simulation model, and effective control measures can be provided by combining simulation results. In the embodiment of the invention, the disaster problem text is input into the pre-established cognitive model, intelligent question answering is carried out through the cognitive model, and the OpenFOAM input data can be obtained, so that the OpenFOAM model is created by using the OpenFOAM input data, namely, in the embodiment of the invention, the OpenFOAM input data used for creating the simulation model is obtained by carrying out intelligent question answering through the cognitive model, and the simulation model is built through participation of the cognitive model, so that the simulation efficiency is improved, and the learning and operation cost of related personnel is reduced. Meanwhile, the model has better expandability due to the automation characteristic, and is suitable for different types of disaster specialized problems, so that an innovative and efficient solution is provided for coping with complex disaster problems. In addition, the disaster problem text is obtained according to the disaster site situation, and the disaster problem text can truly reflect the disaster site situation, so that the disaster evolution process simulated by the cognitive model according to the simulation model created by the disaster problem text is more accurate, and the disaster emergency measures obtained based on the simulation result can be more effective.
In an alternative embodiment, acquiring disaster question text includes: acquiring an initial disaster problem text; inputting the initial disaster problem text into a pre-trained text classifier, and determining the type of the initial disaster problem text; and if the type of the question text is a disaster field question, determining the initial disaster question text as a disaster question text.
In an alternative embodiment, the text classifier comprises a text filter and a full connection layer, wherein the text filter is used for receiving the initial disaster problem text and outputting text characteristics of the initial disaster problem text; the full connection layer is used for obtaining the type of the initial disaster problem text according to the text classification characteristics.
In an alternative embodiment, the cognitive model includes a knowledge graph and a natural language processing model, and the step of intelligently asking and answering the disaster problem text by the cognitive model to obtain OpenFOAM input data related to disaster problem scene data includes: forming a prompt according to the professional knowledge in the knowledge base and the disaster problem text; inputting the prompt into a natural language processing model to obtain a first answer text; extracting triples from the first answer text; matching the triples with the knowledge graph to obtain related node data; updating the prompt according to the related node data; and inputting the updated prompt into the natural language processing model to obtain a second answer text, wherein the second answer text comprises OpenFOAM input data related to disaster question scene data.
In an alternative embodiment, the prompt is composed according to the expertise and the disaster problem text in the knowledge base, and the method comprises the following steps: the text of each file in the knowledge base is segmented to obtain a plurality of text blocks; establishing a vector index of each text block; vectorizing the disaster problem text to obtain a problem text vector; calculating the similarity between the problem text vector and each vector index, and determining a plurality of target vector indexes with the highest similarity with the problem text vector; acquiring a target text block corresponding to the target vector index; and splicing the target text block and the disaster problem text to obtain a prompt.
In an alternative embodiment, the method further comprises: and generating an emergency strategy according to the disaster scene simulation result.
In a second aspect, the present invention provides a disaster emergency auxiliary decision device, comprising: the disaster problem text acquisition module is used for acquiring a disaster problem text, wherein the disaster problem text comprises disaster problem scene data; the intelligent question-answering module is used for inputting the disaster question text into a pre-established cognitive model, carrying out intelligent question-answering through the cognitive model, and generating OpenFOAM input data related to disaster question scene data; the model creation module is used for creating an OpenFOAM model by using the OpenFOAM input data; the simulation module is used for running a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on disaster problem scene data to obtain a disaster scene simulation result.
In a third aspect, the present invention provides a computer device comprising: the system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the disaster emergency auxiliary decision method according to the first aspect or any implementation mode corresponding to the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the disaster relief aid decision method of the first aspect or any of its corresponding embodiments.
In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to perform the disaster relief aid decision method of the first aspect or any of its corresponding embodiments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a disaster emergency assistance decision making method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another disaster emergency assistance decision making method according to an embodiment of the present invention;
FIG. 3 is a flow chart of yet another disaster relief aid decision method according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of a disaster emergency assistance decision making device according to an embodiment of the present invention;
Fig. 5 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
When disasters such as fire disaster, waterlogging and the like occur, the situation of the site disasters needs to be prejudged according to experts, so that corresponding treatment measures are suggested. However, the expert is limited by subjective judgment, limited information and time pressure, which can lead to inaccurate judgment, so that the disaster cannot be effectively treated by the treatment measures obtained according to the judgment result. The embodiment of the invention provides a disaster emergency auxiliary decision-making method, which is used for constructing a simulation model by combining a cognitive model, and simulating a disaster evolution process of a disaster scene by using the simulation model, so that a disaster scene simulation result is obtained, and the effectiveness of disaster emergency measures is improved.
According to an embodiment of the present invention, there is provided a disaster relief aid decision making method embodiment, it being noted that the steps shown in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in an order different from that shown or described herein.
In this embodiment, a disaster emergency auxiliary decision method is provided, fig. 1 is a flowchart of the disaster emergency auxiliary decision method according to an embodiment of the present invention, and as shown in fig. 1, the flowchart includes the following steps:
step S101, acquiring disaster problem text, wherein the disaster problem text comprises disaster problem scene data.
In an alternative embodiment, the disaster scenario-related data in the disaster problem scenario data includes hydrodynamic data, environmental data, and the like. Illustratively, if strong wind weather occurs in the city, disaster scene data includes shaking data of a building, wind speed, wind direction, building data, and the like.
In an alternative embodiment, the disaster problem text is generated by personnel at the disaster site according to the site situation, and can reflect the real situation of the disaster site. Disasters include, but are not limited to, waterlogging, earthquakes, fires, and the like.
Illustratively, the disaster scenario includes:
Scene one: if waterlogging occurs, acquiring disaster problem texts including waterlogging geographic positions; urban city center environmental conditions: heavy rainfall causes serious waterlogging on a plurality of roads in a city center, water accumulation depth reaches 1 meter, and water enters a part of residential buildings in low-lying areas due to traffic paralysis; time range: heavy rainfall is expected to last for 24 hours, and waterlogging conditions may further worsen.
Scene II: if an earthquake occurs, acquiring disaster problem texts at the moment comprises the geographical position of the earthquake, the environmental conditions of remote mountain areas, the occurrence of a Richner 6.0-level earthquake and landslide of mountain bodies nearby the earthquake, which lead to road interruption, serious damage of a plurality of villages, collapse of part houses and time range: and the information such as rescue work needs to be carried out as soon as possible in the golden period of rescue within 72 hours after the earthquake occurs.
Scene III: if a fire disaster occurs, acquiring a disaster problem text which comprises the geographical location of the fire disaster; environmental conditions of a mall: fire disasters occur in the market, the fire rapidly spreads, and a large amount of dense smoke causes extremely low visibility and difficult evacuation of people. Inflammable and explosive articles exist near the fire source, and the fire can be further expanded; time range: the fire is needed to be controlled rapidly to prevent spreading and the like within 1 hour after the fire is generated in the initial stage of extinguishing.
In an alternative embodiment, emergency management personnel analyze the impact of various potentially adverse factors on the disaster site based on fluid dynamics principles to take effective measures for rescue. The hydrodynamic data analysis of disaster problem scenario data includes one or more factors:
1. Geographic data: including geographical information such as the terrain, geographical location, terrain elevation, surface type, etc. of the disaster area.
2. Weather data: including meteorological conditions in the disaster area such as temperature, humidity, wind speed, wind direction, etc.
3. Liquid data: for liquid fluid dynamics problems, physical parameters including liquid, such as density, viscosity, and surface tension, are required. If the disaster is waterlogging, the hydrodynamic data includes liquid data.
4. Solid data: for solid fluid dynamics problems, physical parameters including solids, such as density, elastic modulus, and stiffness, are required. If the disaster is an earthquake, the hydrodynamic data includes solid data.
5. Boundary condition data: including boundary conditions defined at the boundaries of the disaster area such as inlet velocity, outlet pressure, and boundary resistance.
6. Initial condition data: including the initial state of the problem simulation such as speed, pressure, temperature, etc.
Hydrodynamic data is used to build numerical models and solve hydrodynamic equations for predicting and analyzing the fluid behavior and dynamics involved in disasters. The specific data content and requirements will vary depending on the type of disaster and the specific problem.
Step S102, inputting the disaster problem text into a pre-established cognitive model, and performing intelligent question answering through the cognitive model to generate OpenFOAM input data related to disaster problem scene data.
OpenFOAM is itself an open-source Computational Fluid Dynamics (CFD) software package that provides a series of numerical modeling and solving tools for modeling and analyzing hydrodynamic problems. In the embodiment of the invention, the cognitive model is trained by a specific domain language (domain-specific language, DSL), and can understand the basic concepts and related terms of the OpenFOAM, learn the documents and examples of the OpenFOAM, and understand the working principle and the using method of the OpenFOAM.
In an alternative embodiment, the OpenFOAM input data includes initial conditions, boundary conditions, physical parameters, and the like.
Step S103, creating an OpenFOAM model by using the OpenFOAM input data. The OpenFOAM model is a simulation model for simulating a disaster evolution process.
In an alternative embodiment, the OpenFOAM model includes a geometric model, a mesh model, a physical model, and a suitable solver.
Step S104, running a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on disaster problem scene data to obtain a disaster scene simulation result.
When a disaster occurs, a simulation model is established, the evolution process of the disaster is simulated through the simulation model, and effective control measures can be provided by combining simulation results. In the embodiment of the invention, the disaster problem text is input into the pre-established cognitive model, intelligent question answering is carried out through the cognitive model, and the OpenFOAM input data can be obtained, so that the OpenFOAM model is created by using the OpenFOAM input data, namely, in the embodiment of the invention, the OpenFOAM input data used for creating the simulation model is obtained by carrying out intelligent question answering through the cognitive model, and the simulation model is built through participation of the cognitive model, so that the simulation efficiency is improved, and the learning and operation cost of related personnel is reduced. Meanwhile, the model has better expandability due to the automation characteristic, and is suitable for different types of disaster specialized problems, so that an innovative and efficient solution is provided for coping with complex disaster problems. In addition, the disaster problem text is obtained according to the disaster site situation, and the disaster problem text can truly reflect the disaster site situation, so that the disaster evolution process simulated by the cognitive model according to the simulation model created by the disaster problem text is more accurate, and the disaster emergency measures obtained based on the simulation result can be more effective.
In this embodiment, a disaster emergency auxiliary decision method is provided, fig. 2 is a flowchart of the disaster emergency auxiliary decision method according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:
step S201, acquiring disaster problem text, wherein the disaster problem text comprises disaster problem scene data, and the disaster problem scene data comprises fluid dynamics data.
Specifically, the step S201 includes:
step S2011, obtaining an initial disaster problem text.
In step S2012, the initial disaster question text is input into a pre-trained text classifier, and the type of the initial disaster question text is determined.
In an alternative embodiment, the text classifier includes a text classifier and a full connection layer, and the text filter is configured to receive the initial disaster question text and output text features of the initial disaster question text. The full connection layer is used for obtaining the type of the initial disaster problem text according to the text classification characteristics.
And step S2013, if the type of the question text is a disaster field question, determining the initial disaster question text as a disaster question text.
In order to reduce the illusion generated by the large language model, in the embodiment of the invention, the cognitive model only answers the disaster emergency field questions, and other field questions do not need to be answered. The questions are filtered by adding text filters to limit the scope of questions that the cognitive model can answer. The text filter needs to be trained with data to achieve the above effect. The specific training method comprises the following steps: the problems are divided into disaster field problems and non-disaster field problems in advance, and classification data are input into a text filter to be used as classification tasks.
The execution steps comprise:
The problem set data is divided into two types, one is a general problem and the other is a professional problem, and there are 50 problems respectively for the two, and 100 problems are all. The common problems are relatively common problems, and the requirements on professional knowledge are low; the professional questions are test questions, and like the test questions, the answer to the professional questions needs to have more knowledge. The classified questions are input as training data to a text filter AlBERT, and the result of ALBERT is input to a full connection layer to obtain a classification result L of the text. According to the labels in the data set, only the parameters of the full connection layer need to be updated during training. Generally, using ALBERT for text classification tasks, a simple classifier is made based on softmax (normalized exponential function) using the class word vector H of ALBERT results to predict the probability of the class label L:
the formula is P (l|h) =softmax (WH),
W is a parameter matrix of the classification task, and finally all parameters in ALBERT and W are fine-tuned by maximizing the logarithmic probability of the correct label. In the embodiment of the invention, the probability of each label is obtained by using the full connection layer.
The formula is modified to P (l|h) =fc (H).
Step S202, inputting the disaster problem text into a pre-established cognitive model, and performing intelligent question answering through the cognitive model to generate OpenFOAM input data related to disaster problem scene data. Please refer to step S102 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S203, creating an OpenFOAM model by using the OpenFOAM input data. Please refer to step S103 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S204, running a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on disaster problem scene data to obtain a disaster scene simulation result. Please refer to step S104 in the embodiment shown in fig. 1 in detail, which is not described herein.
In this embodiment, a disaster emergency auxiliary decision method is provided, and fig. 3 is a flowchart of the disaster emergency auxiliary decision method according to an embodiment of the present invention, as shown in fig. 3, where the flowchart includes the following steps:
Step S301, acquiring disaster problem text, wherein the disaster problem text comprises disaster problem scene data, and the disaster problem scene data comprises fluid dynamics data. Please refer to step S101 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S302, inputting the disaster problem text into a pre-established cognitive model, and performing intelligent question answering through the cognitive model to generate OpenFOAM input data related to disaster problem scene data.
Specifically, the cognitive model includes a knowledge graph and a natural language processing model, and step S302 specifically includes:
step S3021, forming a prompt according to the professional knowledge and the disaster problem text in the knowledge base.
Specifically, step S3021 includes:
And a1, dividing texts of all files in a knowledge base into blocks to obtain a plurality of text blocks.
In an alternative embodiment, the knowledge base includes a plurality of files Fi (i=1, 2, …, n), the text in each file is partitioned by searching based on LANGCHAIN, and Dij (i=1, 2, …, n; j=1, 2, …, m) represents the j-th text block of the i-th file.
Step a2, a vector index Vi (i=1, 2, …, n×m) of each text block is established.
And a step a3, vectorizing the disaster problem text to obtain a problem text vector Q.
And a4, calculating the similarity between the problem text vector and each vector index, and determining a plurality of target vector indexes with the highest similarity with the problem text vector.
Step a5, obtaining a target text block corresponding to the target vector index;
and a step a6, splicing the target text block and the disaster problem text to obtain a prompt.
In an alternative embodiment, the target text block and the disaster question text are spliced in the form of P4 to obtain the prompt.
In step S3022, the prompt is input to the natural language processing model to obtain a first answer text.
In an alternative embodiment, the service retrieves expertise associated with the question from a knowledge base based on LANGCHAIN, and then inputs the expertise into a natural language processing model along with the matched question, to finally obtain the first answer text. ChatGLM-6B, chatGPT, etc. can be selected for use as the natural language processing model.
Step S3023, extracting triples from the first answer text.
In an alternative embodiment, entities and relationships are extracted from the first answer text obtained in step S3022 based on a custom BiLSTM-CRF-GNN algorithm model.
BiLSTM is a variant of a two-way recurrent neural network that captures context information of a text sequence through two LSTM networks (one forward and one reverse). BiLSTM performs well in entity recognition tasks because it can take into account both contextual information of the current word, which is important for determining the semantics of the word and the entity boundaries.
The CRF is a model for sequence labeling, which considers the dependency between tags and can output a globally optimal tag sequence. In entity identification, the CRF may help ensure correctness of entity boundaries, e.g., to ensure that entities do not cross boundaries of other entities.
GNN is a neural network model that specifically processes graph structure data. In entity relationship triplet extraction, GNNs can be used to model dependencies between entities, as well as interactions between entities and relationships. By constructing entities and relationships in text into a graph, GNNs can propagate information in the graph, thereby better identifying the entities and relationships.
Through the combination of the three parts, the BiLSTM-CRF-GNN model can effectively extract entities and relations from texts, and triple data is generated.
And step S3024, matching the triples with the knowledge graph to obtain related node data.
Step S3025, updating the hint based on the relevant node data.
Step S3026, inputting the updated prompt into the natural language processing model to obtain a second answer text, where the second answer text includes OpenFOAM input data related to disaster question scene data.
In the embodiment of the invention, the entity node of the problem (the problem provided by the emergency management worker) is extracted through the natural language processing model, then the data is matched in the knowledge graph, the found data is the data with strong specialization and relatively accuracy, but the matched data is the structured data at the moment and does not accord with the habit of human reading, and finally the structured data is translated into the answer according with the habit of human reading through the natural language processing model.
Step S303, creating an OpenFOAM model by using the OpenFOAM input data. Please refer to step S103 in the embodiment shown in fig. 1 in detail, which is not described herein.
Step S304, running a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on disaster problem scene data to obtain a disaster scene simulation result. Please refer to step S104 in the embodiment shown in fig. 1 in detail, which is not described herein.
In an alternative embodiment, after the disaster scenario simulation result is obtained by executing the step S304, the method further includes the following steps:
and generating an emergency strategy according to the disaster scene simulation result.
In an alternative embodiment, the cognitive model in the step S302 may not only generate OpenFOAM input data related to disaster problem scene data, but also perform other intelligent questions and answers in addition to assisting in creating the OpenFOAM model. Illustratively, if a question is asked about how to process an emergency event, the cognitive model automatically matches the corresponding emergency plan and similar cases before, and analyzes command organization architecture, command actions of related personnel, required emergency materials and the like. In the embodiment of the invention, two feedback loops are realized: a fast response loop and a depth analysis loop. The intelligent question and answer result can be directly output through the cognitive model, the user can be quickly responded, the OpenFOAM model can be additionally built through the cognitive model, and the depth analysis is realized. The two-way loop combining the rapid response and the deep analysis effectively improves the decision speed and accuracy under the emergency condition, and especially can make a scientific response decision more quickly in disaster emergency management.
The embodiment also provides a disaster emergency auxiliary decision device, which is used for realizing the above embodiment and the preferred implementation, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The embodiment provides a disaster emergency auxiliary decision-making device, as shown in fig. 4, including:
The disaster problem text obtaining module 401 is configured to obtain a disaster problem text, where the disaster problem text includes disaster problem scene data, and the disaster problem scene data includes fluid dynamics data;
The intelligent question-answering module 402 is configured to input a disaster question text into a pre-established cognitive model, perform intelligent question-answering through the cognitive model, and generate OpenFOAM input data related to disaster question scene data;
A model creation module 403, configured to create an OpenFOAM model using OpenFOAM input data;
The simulation module 404 is configured to operate a solver in the OpenFOAM model through a pre-established script or an automation tool, and perform disaster evolution process simulation based on disaster problem scene data, so as to obtain a disaster scene simulation result.
Further functional descriptions of the above respective modules are the same as those of the above corresponding embodiments, and are not repeated here.
The disaster relief aid decision making device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application SPECIFIC INTEGRATED Circuit) Circuit, a processor and a memory executing one or more software or fixed programs, and/or other devices that can provide the above functions.
The embodiment of the invention also provides computer equipment, which is provided with the disaster emergency auxiliary decision-making device shown in the figure 4.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 5, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 5.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform a method for implementing the embodiments described above.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device further comprises input means 30 and output means 40. The processor 10, memory 20, input device 30, and output device 40 may be connected by a bus or other means, for example in fig. 5.
The input device 30 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the computer apparatus, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointer stick, one or more mouse buttons, a trackball, a joystick, and the like. The output means 40 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. Such display devices include, but are not limited to, liquid crystal displays, light emitting diodes, displays and plasma displays. In some alternative implementations, the display device may be a touch screen.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Portions of the present invention may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or aspects in accordance with the present invention by way of operation of the computer. Those skilled in the art will appreciate that the form of computer program instructions present in a computer readable medium includes, but is not limited to, source files, executable files, installation package files, etc., and accordingly, the manner in which the computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Herein, a computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by a computer.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (7)
1. A disaster emergency aid decision making method, the method comprising:
Acquiring disaster problem text, wherein the disaster problem text comprises disaster problem scene data;
Inputting the disaster problem text into a pre-established cognitive model, and performing intelligent question answering through the cognitive model to generate OpenFOAM input data related to disaster problem scene data, wherein the OpenFOAM input data comprises initial conditions, boundary conditions and physical parameters;
creating an OpenFOAM model by using the OpenFOAM input data;
Operating a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on the disaster problem scene data to obtain a disaster scene simulation result;
the acquiring disaster question text comprises the following steps:
acquiring an initial disaster problem text;
Inputting the initial disaster problem text into a pre-trained text classifier, and determining the type of the initial disaster problem text;
if the type of the question text is a disaster field question, determining the initial disaster question text as the disaster question text;
the text classifier includes a text filter and a full-join layer,
The text filter is used for receiving the initial disaster problem text and outputting text classification characteristics of the initial disaster problem text;
The full connection layer is used for obtaining the type of the initial disaster problem text according to the text classification characteristics;
The cognitive model comprises a knowledge graph and a natural language processing model, and the step of intelligently asking and answering the disaster problem text by the cognitive model to obtain OpenFOAM input data related to the disaster problem scene data comprises the following steps of:
forming a prompt according to the professional knowledge in the knowledge base and the disaster problem text;
inputting the prompt into a natural language processing model to obtain a first answer text;
extracting triples from the first answer text;
matching the triples with a knowledge graph to obtain related node data;
Updating the prompt according to the related node data;
and inputting the updated prompt into the natural language processing model to obtain a second answer text, wherein the second answer text comprises OpenFOAM input data related to the disaster question scene data.
2. The method according to claim 1, wherein the composing the prompt with the disaster question text based on the expertise in the knowledge base comprises:
partitioning the text of each file in the knowledge base to obtain a plurality of text blocks;
Establishing a vector index of each text block;
vectorizing the disaster problem text to obtain a problem text vector;
Calculating the similarity between the problem text vector and each vector index, and determining a plurality of target vector indexes with the highest similarity with the problem text vector;
Acquiring a target text block corresponding to the target vector index;
and splicing the target text block and the disaster problem text to obtain the prompt.
3. The method as recited in claim 1, further comprising:
and generating an emergency strategy according to the disaster scene simulation result.
4. A disaster emergency aid decision making device, the device comprising:
the disaster problem text acquisition module is used for acquiring disaster problem texts, wherein the disaster problem texts comprise disaster problem scene data;
The intelligent question-answering module is used for inputting the disaster question text into a pre-established cognitive model, carrying out intelligent question-answering through the cognitive model, and generating OpenFOAM input data related to the disaster question scene data, wherein the OpenFOAM input data comprises initial conditions, boundary conditions and physical parameters;
The model creation module is used for creating an OpenFOAM model by using the OpenFOAM input data;
The simulation module is used for running a solver in the OpenFOAM model through a pre-established script or an automation tool, and simulating a disaster evolution process based on the disaster problem scene data to obtain a disaster scene simulation result;
the acquiring disaster question text comprises the following steps:
acquiring an initial disaster problem text;
Inputting the initial disaster problem text into a pre-trained text classifier, and determining the type of the initial disaster problem text;
if the type of the question text is a disaster field question, determining the initial disaster question text as the disaster question text;
the text classifier includes a text filter and a full-join layer,
The text filter is used for receiving the initial disaster problem text and outputting text classification characteristics of the initial disaster problem text;
The full connection layer is used for obtaining the type of the initial disaster problem text according to the text classification characteristics;
The cognitive model comprises a knowledge graph and a natural language processing model, and the step of intelligently asking and answering the disaster problem text by the cognitive model to obtain OpenFOAM input data related to the disaster problem scene data comprises the following steps of:
forming a prompt according to the professional knowledge in the knowledge base and the disaster problem text;
inputting the prompt into a natural language processing model to obtain a first answer text;
extracting triples from the first answer text;
matching the triples with a knowledge graph to obtain related node data;
Updating the prompt according to the related node data;
and inputting the updated prompt into the natural language processing model to obtain a second answer text, wherein the second answer text comprises OpenFOAM input data related to the disaster question scene data.
5. A computer device, comprising:
a memory and a processor, the memory and the processor being communicatively connected to each other, the memory having stored therein computer instructions, the processor executing the computer instructions to perform the disaster relief aid decision method of any one of claims 1 to 3.
6. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform the disaster relief aid decision method according to any of claims 1 to 3.
7. A computer program product comprising computer instructions for causing a computer to perform the disaster relief aid decision method as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410628154.9A CN118210909B (en) | 2024-05-21 | 2024-05-21 | Disaster emergency auxiliary decision-making method, disaster emergency auxiliary decision-making device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410628154.9A CN118210909B (en) | 2024-05-21 | 2024-05-21 | Disaster emergency auxiliary decision-making method, disaster emergency auxiliary decision-making device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118210909A CN118210909A (en) | 2024-06-18 |
| CN118210909B true CN118210909B (en) | 2024-09-10 |
Family
ID=91454684
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410628154.9A Active CN118210909B (en) | 2024-05-21 | 2024-05-21 | Disaster emergency auxiliary decision-making method, disaster emergency auxiliary decision-making device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118210909B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330957A (en) * | 2022-10-10 | 2022-11-11 | 南京信息工程大学 | Method for simulating diffusion of fire smoke in building and emergency scheme calling method |
| CN117668181A (en) * | 2023-11-20 | 2024-03-08 | 招商局金融科技有限公司 | Information processing method, device, terminal equipment and storage medium |
| CN117851570A (en) * | 2024-01-11 | 2024-04-09 | 哈尔滨工业大学 | Star crowd intelligent cooperative control method and system based on large language model |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102348358B1 (en) * | 2019-11-06 | 2022-01-11 | (주)하몬소프트 | Simulation apparatus and method for fire evacuation based on virtual reality |
| CN116384209B (en) * | 2023-05-30 | 2023-08-08 | 江苏伟岸纵横科技股份有限公司 | Disaster simulation method for emergency simulation exercise |
| CN117350093A (en) * | 2023-08-29 | 2024-01-05 | 华电电力科学研究院有限公司 | Temperature-based fault early warning method, system, device and medium |
-
2024
- 2024-05-21 CN CN202410628154.9A patent/CN118210909B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115330957A (en) * | 2022-10-10 | 2022-11-11 | 南京信息工程大学 | Method for simulating diffusion of fire smoke in building and emergency scheme calling method |
| CN117668181A (en) * | 2023-11-20 | 2024-03-08 | 招商局金融科技有限公司 | Information processing method, device, terminal equipment and storage medium |
| CN117851570A (en) * | 2024-01-11 | 2024-04-09 | 哈尔滨工业大学 | Star crowd intelligent cooperative control method and system based on large language model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118210909A (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200050942A1 (en) | Deep learning model for cloud based technical support automation | |
| CN111523640B (en) | Training method and device for neural network model | |
| CN106097043A (en) | The processing method of a kind of credit data and server | |
| EP3862891A2 (en) | Method and apparatus for retrieving multi-turn dialogue, storage medium, and electronic device | |
| US20210311729A1 (en) | Code review system | |
| CN110929524A (en) | Data screening method, device, equipment and computer readable storage medium | |
| US20180060782A1 (en) | Recommending personalized jobs from automated review of writing samples and resumes | |
| Holanda et al. | JOINT: Java ontology integrated toolkit | |
| US10762089B2 (en) | Open ended question identification for investigations | |
| CN114048024A (en) | Task deployment method, device, equipment, storage medium and product | |
| US10824777B2 (en) | Employing natural language processing to facilitate geospatial analysis | |
| CN113762061A (en) | Quantitative perception training method and device for neural network and electronic equipment | |
| CN118210909B (en) | Disaster emergency auxiliary decision-making method, disaster emergency auxiliary decision-making device, computer equipment and storage medium | |
| CN117876090A (en) | Risk identification method, electronic device, storage medium, and program product | |
| CN112558966A (en) | Depth model visualization data processing method and device and electronic equipment | |
| US20200287798A1 (en) | Systems and methods for a resilient infrastructure simulation environment | |
| US11501654B2 (en) | Automated decision making for selecting scaffolds after a partially correct answer in conversational intelligent tutor systems (ITS) | |
| CN112182346A (en) | Method and equipment for extracting entity information of emergency | |
| Sebillo et al. | A territorial intelligence-based approach for smart emergency planning | |
| CN117151247B (en) | Method, apparatus, computer device and storage medium for modeling machine learning task | |
| Othman | Metamodelling Approach for Managing Disaster Management Knowledge | |
| US20220300799A1 (en) | Neuro-Symbolic Approach for Entity Linking | |
| US20220108205A1 (en) | Generative reasoning for symbolic discovery | |
| Mota | The never-ending recursion | |
| CN118760898A (en) | City field-oriented large language model training method and city generation type intelligent method and device |
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 | ||
| GR01 | Patent grant |