CN112836018A - Method and device for processing emergency plan - Google Patents
Method and device for processing emergency plan Download PDFInfo
- Publication number
- CN112836018A CN112836018A CN202110181165.3A CN202110181165A CN112836018A CN 112836018 A CN112836018 A CN 112836018A CN 202110181165 A CN202110181165 A CN 202110181165A CN 112836018 A CN112836018 A CN 112836018A
- Authority
- CN
- China
- Prior art keywords
- emergency plan
- text
- knowledge
- emergency
- knowledge elements
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000002372 labelling Methods 0.000 claims description 58
- 238000003672 processing method Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000007499 fusion processing Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000008520 organization Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000010485 coping Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a method and a device for processing an emergency plan. The method for processing the emergency plan comprises the following steps: acquiring an emergency plan text to be processed; splitting the emergency plan text to obtain the split emergency plan text; determining emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining attributes of the emergency plan knowledge elements, and determining the relationship between the emergency plan knowledge elements; the preset emergency plan knowledge element model comprises a plurality of preset knowledge elements, attributes of the preset knowledge elements and relations among the preset knowledge elements; and constructing a knowledge map corresponding to the text of the emergency plan according to the emergency plan knowledge elements, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements. The method is used for improving the practicability, operability and applicability of the text data of the emergency plan.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a method and a device for processing an emergency plan.
Background
For the big data system of emergency plans (handling schemes for emergency events), most data resources are unstructured text. When processing emergency plan text data, an unstructured processing method is also adopted, such as: and adding description information to the text data of the emergency plan to form metadata, and then storing the metadata.
By adopting the processing mode, the practicability, operability and applicability of the text data of the emergency plan are poor.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for processing an emergency plan, so as to improve the practicability, operability, and applicability of text data of the emergency plan.
In a first aspect, an embodiment of the present application provides a method for processing an emergency plan, including: acquiring an emergency plan text to be processed; the emergency plan is a processing scheme of an emergency event; splitting the emergency plan text to obtain a split emergency plan text; determining emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining attributes of the emergency plan knowledge elements, and determining the relationship among the emergency plan knowledge elements; the preset emergency plan knowledge element model comprises a plurality of preset knowledge elements, attributes of the preset knowledge elements and relations among the preset knowledge elements; and constructing a knowledge graph corresponding to the text of the emergency plan according to the relationship among the knowledge elements of the emergency plan, the attributes of the knowledge elements of the emergency plan and the knowledge elements of the emergency plan.
In this application embodiment, compare with prior art, when handling emergent scheme text, split emergent scheme text earlier, then carry out the extraction of corresponding information through the emergent scheme text of predetermined emergent scheme knowledge element model after to the split again, corresponding information includes: emergency plan knowledge elements, attributes of the emergency plan knowledge elements, and relationships between the emergency plan knowledge elements; based on the corresponding information, a knowledge map corresponding to the emergency plan text is constructed, and further structured storage based on the emergency plan text data is achieved; through the structured storage mode, the stored data can be conveniently inquired or further analyzed, and the practicability, operability and applicability of the text data of the emergency plan are improved.
As a possible implementation manner, the splitting the emergency plan text to obtain a split emergency plan text includes: carrying out paragraph structure splitting on the emergency plan text to obtain the emergency plan text split into paragraphs; and performing text segmentation on the emergency plan file split into the paragraphs to obtain an emergency plan text split into text segments.
In the embodiment of the application, the emergency plan text is effectively split through paragraph structure splitting and text word segmentation.
As a possible implementation manner, the paragraph structure splitting is performed on the emergency plan text to obtain the emergency plan text split into paragraphs, including: and carrying out paragraph structure splitting on the emergency plan text through a preset regular matching and recursive algorithm to obtain the emergency plan text split into paragraphs.
In the embodiment of the application, the paragraph structure is split through the regular matching and the recursive algorithm, so that the effective splitting of the paragraph structure is realized.
As a possible implementation manner, the determining, according to a preset emergency plan knowledge element model, emergency plan knowledge elements in the split emergency plan text, determining attributes of the emergency plan knowledge elements, and determining relationships between the emergency plan knowledge elements includes: feeding back the preset emergency plan knowledge element model and the split emergency plan text to a labeling user side; receiving a labeling result fed back by the labeling user side; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements.
In the embodiment of the application, the preset emergency plan knowledge element model and the split emergency plan text are fed back to the labeling user side to label the corresponding information, so that the effective labeling of the corresponding information is realized.
As a possible implementation manner, the determining, according to a preset emergency plan knowledge element model, emergency plan knowledge elements in the split emergency plan text, determining attributes of the emergency plan knowledge elements, and determining relationships between the emergency plan knowledge elements includes: training an initial labeling model according to the preset emergency plan knowledge element model to obtain a trained labeling model; marking the split emergency plan text through the trained marking model to obtain a marking result; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements.
In the embodiment of the application, the labeling model is trained based on the preset emergency plan knowledge element model, and the effective and accurate labeling of the corresponding information can be realized through the trained labeling model.
As a possible implementation manner, the acquiring the emergency plan text to be processed includes: and acquiring the emergency plan text from a target website through a crawler technology based on preset emergency features.
In the embodiment of the application, the emergency plan text is effectively and accurately acquired based on the preset emergency characteristic and combined with the crawler technology.
As a possible implementation manner, the constructing a knowledge graph corresponding to the emergency plan text according to the emergency plan knowledge element, the attribute of the emergency plan knowledge element, and the relationship among the emergency plan knowledge elements includes: according to the relation between the emergency plan knowledge elements and the attributes of the emergency plan knowledge elements, carrying out fusion processing on the emergency plan knowledge elements in different emergency plan texts to obtain a structured data set; associating the emergency plan knowledge elements in the structured data set with preset knowledge elements corresponding to the emergency plan knowledge elements and attributes of the corresponding preset knowledge elements; and converting the structured data set into ternary group data through a preset data conversion tool to obtain a knowledge graph corresponding to the emergency plan text.
In the embodiment of the application, the emergency plan knowledge elements are fused to obtain a structured data set, the emergency plan knowledge elements are associated, and the structured data set is converted into ternary group data to realize effective construction of the knowledge map.
As a possible implementation, the method further includes: receiving a retrieval request of a target emergency plan; the retrieval request comprises information to be retrieved; determining a retrieval result corresponding to the information to be retrieved according to the information to be retrieved and a knowledge map corresponding to the emergency plan text; and feeding back the retrieval result.
In the embodiment of the application, based on the constructed knowledge graph, the information of the specified target emergency plan can be retrieved, and the effective application of the knowledge graph is realized.
In a second aspect, an embodiment of the present application provides a device for processing an emergency plan, including: the functional modules are used for implementing the method for processing the emergency plan described in the first aspect and any one of the possible implementation manners of the first aspect.
In a third aspect, an embodiment of the present application provides a readable storage medium, where a computer program is stored on the readable storage medium, and when the computer program is executed by a computer, the method for processing an emergency plan as described in the first aspect and any one of the possible implementation manners of the first aspect is performed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of a method for processing an emergency plan according to an embodiment of the present disclosure;
fig. 2 is a block diagram of a processing device of an emergency plan provided in the embodiment of the present application.
Icon: 200-emergency plan processing device; 210-an obtaining module; 220-processing module.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
The processing method of the emergency plan provided by the embodiment of the application can be applied to a data processing system of the emergency plan, and the data processing system can perform various kinds of management on the text data of the emergency plan, including structured storage of the data, query of the data, expansion of the data and the like.
The data processing system may comprise a front end and a back end, the back end being a data processing end and the front end being a user interaction end. Such as: the user initiates a data query request through the front end, the back end executes a corresponding data query process according to the data query request, and after obtaining a result, the result is fed back to the front end, and the front end feeds back to the user. For another example: the user initiates a data structuring processing request through the front end, the back end executes corresponding data structuring processing according to the structuring processing request, corresponding processing information is fed back to the front end after the processing is finished, and the front end feeds back the corresponding processing information to the user. The front end can be a client or a browser, and the back end can be a server. The processing method of the emergency plan provided by the embodiment of the application is generally applied to a server.
In the embodiment of the present application, the emergency plan may be understood as a processing scheme of an emergency event, and when the emergency event occurs, the corresponding management organization issues the emergency plan. Such as: when the epidemic situation happens, management organizations at all levels issue regional-level epidemic situation coping schemes, and the epidemic situation coping schemes are emergency plans.
Based on the introduction of the application scenario and the hardware operating environment, please refer to fig. 1, which is a flowchart of a processing method for an emergency plan provided in an embodiment of the present application, where the processing method may be applied to the server described in the foregoing embodiment, and the processing method includes:
step 110: and acquiring an emergency plan text to be processed.
Step 120: and splitting the emergency plan text to obtain the split emergency plan text.
Step 130: and determining the emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining the attributes of the emergency plan knowledge elements, and determining the relationship between the emergency plan knowledge elements. The preset emergency plan knowledge element model comprises a plurality of preset knowledge elements, attributes of the preset knowledge elements and relations among the preset knowledge elements.
Step 140: and constructing a knowledge map corresponding to the text of the emergency plan according to the emergency plan knowledge elements, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements.
In the embodiment of the application, compared with the prior art, when the emergency plan text is processed, the emergency plan text is split firstly, then the corresponding information of the split emergency plan text is extracted through a preset emergency plan knowledge element model, a knowledge graph corresponding to the emergency plan text is constructed based on the corresponding information, and then the structured storage based on the emergency plan text data is realized; through the structured storage mode, the stored data can be conveniently inquired or further analyzed, and the practicability, operability and applicability of the text data of the emergency plan are improved.
A detailed implementation of steps 110-140 is described next.
In step 110, the emergency plan text to be processed may have various sources, and as an alternative embodiment, the data may be uploaded by the user through the front end, where the emergency plan text to be processed is the specific emergency plan text.
As another alternative, the server actively obtains the emergency plan text by using a data mining algorithm or tool, where the emergency plan text to be processed is not the specific emergency plan text. In addition, in this embodiment, the server may further set a data acquisition period, and the server actively acquires and processes the emergency plan text after each data acquisition period, so as to expand the emergency plan text data.
In this embodiment, the data mining algorithm or tool may also have various embodiments, and as an alternative embodiment, step 110 includes: and acquiring an emergency plan text from the target website through a crawler technology based on the preset emergency characteristics.
Emergency features include, but are not limited to: keywords representing the text of the emergency plan, text identification representing the text of the emergency plan, and the like. The target website may be some specific key websites, such as: an administrative organization official network. The concrete implementation of the crawler technology belongs to the mature technology in the field, and is not described in detail in the embodiment of the application.
Regardless of the implementation, the emergency protocol text obtained in step 110 may be in the form of a file. Correspondingly, the number of emergency plan texts to be processed may be one or more copies (one or more files). It is understood that if the text is a copy, after the copy of emergency plan text is processed in the manner of steps 120-140, a knowledge-graph corresponding to the copy of emergency plan text can be obtained. If the number of the emergency plan texts is multiple, each emergency plan text is processed according to the steps 120 to 130, and then in step 140, a knowledge graph corresponding to the multiple emergency plan texts is constructed. Of course, in step 140, a knowledge graph corresponding to each emergency plan text may also be constructed, that is, the final knowledge graph corresponding to a plurality of emergency plan texts may be one or a plurality of knowledge graphs, which is not limited in the embodiment of the present application.
In the embodiment of the present application, for the emergency plan text to be processed, storage may be implemented by using a MongoDB (open source database) database.
After the emergency plan text to be processed is acquired in step 110, in step 120, the emergency plan text is split to obtain the split emergency plan text. Before the splitting process, the mature text recognition technology can be used for performing text recognition on the emergency plan in the file form to obtain corresponding text information, and then the splitting process is performed based on the text information. In addition, before the splitting processing, preprocessing can be performed by adopting a basic processing mode of the text information such as information denoising processing, and then splitting can be performed based on the preprocessed text information.
For the splitting of the text information, as an optional implementation, step 120 includes: carrying out paragraph structure splitting on the emergency plan text to obtain the emergency plan text split into paragraphs; and performing text segmentation on the emergency plan file split into the paragraphs to obtain the emergency plan text split into text segments.
In the embodiment, the emergency plan text is firstly split into paragraphs, and then the paragraphs are subjected to text word segmentation, so that a better splitting effect can be ensured.
The paragraph structure splitting is carried out on the urgent plan text, and the paragraph structure splitting can be realized through a preset regular matching and a recursion algorithm.
The process of text-tokenizing a paragraph may include: the emergency plan text split into the paragraphs is fed back to the front end, manual word segmentation is carried out by a front end user, and then automatic text word segmentation is carried out by using word segmentation tools such as jieba and the like. Of course, the word segmentation may be performed only by the front-end user or only by using a word segmentation tool such as jieba or the like, which is not limited in the embodiment of the present application.
After the split emergency plan text is obtained in step 120, in step 130, the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements, and the relationships between the emergency plan knowledge elements are determined according to the preset emergency plan knowledge element model.
The preset emergency plan knowledge element model can be understood as a preset emergency plan knowledge element standard database (data system), and the standard database is information such as various standard emergency plan knowledge elements which are subjected to structured processing and attributes and relationships of the standard emergency plan knowledge elements. The construction of the knowledge element model will be described next.
During construction, a theory can be constructed based on a text knowledge framework, and the field and the category of the emergency plan knowledge element system are determined by means of an ontology model (namely, an existing knowledge framework model). Such as: comprehensive emergency plans, special emergency plans, field disposal emergency plans and the like. And then, necessary and basic knowledge elements in the regularization plan are analyzed by carrying out structuralized processing on the related texts of the emergency events.
By way of example, the comprehensive emergency protocol includes, but is not limited to: general rules, accident risk description, emergency organization and responsibility, early warning and information reporting, emergency response, information disclosure, post treatment, safeguard measures, emergency plan management and the like. The special emergency protocol includes but is not limited to: accident risk analysis, emergency command agencies and responsibilities, disposal procedures, disposal measures and the like. The field disposition emergency protocol includes, but is not limited to: accident risk analysis, emergency work duties, emergency treatment, notes, accessories and the like. Based on these, the core knowledge elements involved include: emergency event information, emergency organization, emergency resources, emergency response procedures, and emergency safeguards.
And further determining the representation specification of the emergency plan knowledge elements based on the preliminarily determined knowledge element system. Specifically, core knowledge elements such as disaster-causing factors, disaster-bearing carriers, counterparts and the like in an emergency can be analyzed based on source data such as common sense knowledge, fact experience knowledge, reasoning knowledge and the like, expression specifications of emergency knowledge elements are researched by establishing a metadata analysis method based on a regularization plan and a regularization case, concepts, connotations and extensions of the emergency elements are determined, and an emergency element knowledge concept system and a rule system are formed.
After the representation specification is determined, defining the emergency plan knowledge element and attribute information (which can be understood as a label) of the specification, determining all the component elements and attribute information of the ontology model, and establishing the relationship between the elements and the attribute information, the relationship between the elements and the elements, and the relationship between the elements, the attribute information and the instances. The relationship between the elements, the attribute information, and the instances is optional, and may or may not be configured. After determining the relationships, a final emergency plan knowledge element model can be established based on the relationships.
Therefore, in the established model of knowledge elements of the emergency plan, the method comprises the following steps: the relationship among the plurality of preset knowledge elements, the attributes of the plurality of preset knowledge elements, and the plurality of preset knowledge elements. The preset emergency plan knowledge elements can be understood as a standardized knowledge system, and the structuralization of the unstructured emergency plan text can be realized by taking the standardized knowledge system as a reference standard.
In the embodiments of the present application, the relationship between knowledge elements may include, but is not limited to: relationships such as membership, responsibility, support, and safeguard are not listed in the embodiments of the present application.
For the attributes of a knowledge element, we can understand the class labels of the knowledge element, such as: the attribute information of each personnel element involved in the emergency plan may be a role in the emergency organization. For another example: what is involved in the emergency protocol: the attribute information of the object elements such as emergency equipment and communication equipment can be emergency resources. The embodiments in the present application are merely exemplary, and in practical applications, different implementations may be possible according to different specifications or standards.
In the embodiment of the present application, the preset emergency plan knowledge element model may be stored by using a MySQL (open source database) database.
In combination with the pre-defined emergency protocol knowledge element model, step 130 may adopt two alternative embodiments. In a first alternative embodiment, step 130 comprises: feeding back a preset emergency plan knowledge element model and the split emergency plan text to a labeling user side; receiving a labeling result fed back by a labeling user side; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relation between the emergency plan knowledge elements.
In a first alternative embodiment, a manual labeling mode is adopted: the method comprises the following steps of feeding back a reference standard (namely a preset emergency plan knowledge element model) and an object to be labeled (namely a split emergency plan text) to a labeling user side, labeling the object to be labeled by a labeling user through the reference standard provided by the labeling user side, wherein the labeling content comprises the following steps: knowledge elements, knowledge element attributes, and relationships between knowledge elements.
After the manual labeling is completed, the labeling result is fed back to the server through the labeling user side, and the server can determine the emergency plan knowledge elements, the attributes of the emergency plan knowledge elements and the relation between the emergency plan knowledge elements in the split emergency plan text based on the labeling result.
In the embodiment of the application, the preset emergency plan knowledge element model and the split emergency plan text are fed back to the labeling user side to label the corresponding information, so that the effective labeling of the corresponding information is realized.
In a second alternative embodiment, step 130 comprises: training an initial labeling model according to a preset emergency plan knowledge element model to obtain a trained labeling model; marking the split emergency plan text through a trained marking model to obtain a marking result; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relation between the emergency plan knowledge elements.
In this embodiment, when the annotation model is trained, the annotated emergency plan text and the corresponding annotation result thereof can be used as a training data set to train the annotation model. The acquisition of the training data set may be implemented by the first embodiment: feeding back a preset emergency plan knowledge element model and other split emergency plan texts to a labeling user side, manually labeling to obtain corresponding labeling results, and forming a training data set by the labeling results and the corresponding emergency plan texts.
In the embodiment of the present application, the labeling model may adopt a Bert model, and the corresponding algorithm is an LSTM (Long Short-Term Memory) neural network algorithm.
After the training of the model is completed based on the training data set, the labeling model can be directly applied to the automatic labeling of the split emergency plan text, and a corresponding labeling result is obtained.
In addition, for the trained labeling model, optimization can be realized by adopting various modes such as model precision testing, repeated training and the like so as to ensure the accuracy of the labeling model.
In the embodiment of the application, the labeling model is trained based on the preset emergency plan knowledge element model, and the effective and accurate labeling of the corresponding information can be realized through the trained labeling model.
After determining the corresponding information corresponding to the emergency plan in step 130, in step 140, a knowledge graph corresponding to the text of the emergency plan is constructed according to the relationship among the knowledge elements of the emergency plan, the attributes of the knowledge elements of the emergency plan, and the knowledge elements of the emergency plan.
As an alternative embodiment, step 140 includes: according to the relation between the emergency plan knowledge elements and the attributes of the emergency plan knowledge elements, carrying out fusion processing on the emergency plan knowledge elements in different emergency plan texts to obtain a structured data set; associating the emergency plan knowledge elements in the structured data set with preset knowledge elements corresponding to the emergency plan knowledge elements and attributes of the corresponding preset knowledge elements; and converting the structured data set into ternary data through a preset data conversion tool to obtain a knowledge graph corresponding to the emergency plan text.
In this embodiment, the process of the fusion process may be understood as the alignment of the entities and the relationships, and the fusion of the entities and the relationships is performed based on the emergency plan knowledge elements involved in different emergency plan texts and by using the attribute information. Such as: aiming at two emergency plan knowledge elements, if the two emergency plan knowledge elements are in an upper-lower relation, the two emergency plan knowledge elements are associated according to the upper-lower relation; and the attribute information of the two emergency plan knowledge elements is the same, so that the two emergency plan knowledge elements can be classified under the same attribute information. For another example: although there is no direct relationship among the plurality of emergency plan knowledge elements, the corresponding attribute information is the same, and the emergency plan knowledge elements can be classified into the same attribute information.
The alignment and fusion process for entities and relationships belongs to the mature technology in the field, and will not be described in further detail in the embodiments of the present application.
Further, after obtaining the structured data set, the knowledge elements in the data set may be associated (linked) with a preset emergency plan knowledge element model, which may be understood as a benchmarking, so that each knowledge element in the data set has a corresponding standard data source.
After the association is completed, the data is converted into the data format of the knowledge graph, namely the triple data, by using a data conversion tool, and then the construction of the knowledge graph can be completed. The data conversion tool may be D2RQ (a data conversion platform), and the triple data may be RDF (Resource Description Framework) triple data.
In the embodiment of the application, the emergency plan knowledge elements are fused to obtain a structured data set, the emergency plan knowledge elements are associated, and the structured data set is converted into ternary group data to realize effective construction of the knowledge map.
After completion of the construction of the knowledge-graph in step 140, the storage of the knowledge-graph may be accomplished using Neo4j (a kind of graph database).
Based on the stored knowledge-graph, various applications may be made. As an optional implementation, the processing method further includes: receiving a retrieval request of a target emergency plan; the retrieval request comprises information to be retrieved; determining a retrieval result corresponding to the information to be retrieved according to the information to be retrieved and the knowledge map corresponding to the emergency plan text; and feeding back a retrieval result.
In this embodiment, the user may query the information of the emergency plan, and may initiate a retrieval request through the front end. The target emergency plan is an emergency plan which needs to be inquired by a user. The information to be retrieved may include, but is not limited to: the search keyword (which may be one of the knowledge elements), the topic name corresponding to the emergency plan text, and the like. For the front end, there may be provided: full text retrieval, semantic retrieval, time retrieval and the like.
And based on the information to be retrieved, the server inquires in the knowledge graph, feeds back the knowledge graph corresponding to the target emergency plan to the front end in the form of the knowledge graph after the knowledge graph part corresponding to the target emergency plan is found, and then displays the knowledge graph at the front end.
In addition, in the foregoing embodiment, the knowledge graph constructed in step 140 may be an integrated knowledge graph corresponding to multiple emergency plan texts, or each emergency plan text corresponds to a knowledge graph, and if the first manner is adopted, only the knowledge graph part corresponding to the emergency plan text may be displayed during displaying, and the whole displaying is not performed. If the second mode is adopted, the corresponding knowledge graph is directly displayed during displaying.
In the embodiment of the application, based on the constructed knowledge graph, the information of the specified target emergency plan can be retrieved, and the effective application of the knowledge graph is realized.
In the embodiment of the application, based on the constructed knowledge graph, data query application, data calling, data expansion and other applications can be performed. For data invocation, for example, it may be invoked assuming that the knowledge graph is required as a data source in other data processing flows. For data expansion, for example, the stored knowledge graph can be further expanded and expanded according to the subsequent acquisition of more emergency plan texts.
Based on the same inventive concept, please refer to fig. 2, an embodiment of the present application further provides a processing apparatus 200 for an emergency plan, which includes an obtaining module 210 and a processing module 220.
The obtaining module 210 is configured to obtain an emergency plan text to be processed. The processing module 220 is configured to: splitting the emergency plan text to obtain a split emergency plan text; determining emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining attributes of the emergency plan knowledge elements, and determining the relationship among the emergency plan knowledge elements; and constructing a knowledge graph corresponding to the text of the emergency plan according to the relationship among the knowledge elements of the emergency plan, the attributes of the knowledge elements of the emergency plan and the knowledge elements of the emergency plan.
In this embodiment of the application, the processing module 220 is specifically configured to: carrying out paragraph structure splitting on the emergency plan text to obtain the emergency plan text split into paragraphs; and performing text segmentation on the emergency plan file split into the paragraphs to obtain an emergency plan text split into text segments.
In this embodiment of the application, the processing module 220 is further specifically configured to: and carrying out paragraph structure splitting on the emergency plan text through a preset regular matching and recursive algorithm to obtain the emergency plan text split into paragraphs.
In this embodiment of the application, the processing module 220 is further specifically configured to: feeding back the preset emergency plan knowledge element model and the split emergency plan text to a labeling user side; receiving a labeling result fed back by the labeling user side; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements.
In this embodiment of the application, the processing module 220 is further specifically configured to: training an initial labeling model according to the preset emergency plan knowledge element model to obtain a trained labeling model; marking the split emergency plan text through the trained marking model to obtain a marking result; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements.
In this embodiment of the application, the obtaining module 210 is specifically configured to obtain the emergency plan text from the target website through a crawler technology based on a preset emergency characteristic.
In this embodiment of the application, the processing module 220 is further specifically configured to: according to the relation between the emergency plan knowledge elements and the attributes of the emergency plan knowledge elements, carrying out fusion processing on the emergency plan knowledge elements in different emergency plan texts to obtain a structured data set; associating the emergency plan knowledge elements in the structured data set with preset knowledge elements corresponding to the emergency plan knowledge elements and attributes of the corresponding preset knowledge elements; and converting the structured data set into ternary group data through a preset data conversion tool to obtain a knowledge graph corresponding to the emergency plan text.
In the embodiment of the present application, the processing module 220 is further configured to receive a retrieval request of the target emergency plan; the retrieval request comprises information to be retrieved; determining a retrieval result corresponding to the information to be retrieved according to the information to be retrieved and a knowledge map corresponding to the emergency plan text; and feeding back the retrieval result.
The respective functional modules of the processing apparatus 200 of the emergency plan correspond to the respective steps in the processing method of the emergency plan described in the foregoing embodiment, and therefore, the embodiments of the respective functional modules refer to the embodiments of the respective steps corresponding thereto, and are not repeatedly described in the embodiment of the present application.
Based on the same inventive concept, an embodiment of the present application further provides a readable storage medium, where a computer program is stored on the readable storage medium, and when the computer program is executed by a computer, the method for processing an emergency plan described in the foregoing embodiment is executed.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for processing an emergency plan is characterized by comprising the following steps:
acquiring an emergency plan text to be processed; the emergency plan is a processing scheme of an emergency event;
splitting the emergency plan text to obtain a split emergency plan text;
determining emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining attributes of the emergency plan knowledge elements, and determining the relationship among the emergency plan knowledge elements; the preset emergency plan knowledge element model comprises a plurality of preset knowledge elements, attributes of the preset knowledge elements and relations among the preset knowledge elements;
and constructing a knowledge graph corresponding to the text of the emergency plan according to the relationship among the knowledge elements of the emergency plan, the attributes of the knowledge elements of the emergency plan and the knowledge elements of the emergency plan.
2. The processing method according to claim 1, wherein the splitting the emergency plan text to obtain a split emergency plan text comprises:
carrying out paragraph structure splitting on the emergency plan text to obtain the emergency plan text split into paragraphs;
and performing text segmentation on the emergency plan file split into the paragraphs to obtain an emergency plan text split into text segments.
3. The processing method according to claim 2, wherein the performing paragraph structure splitting on the contingent plan text to obtain the contingent plan text split into paragraphs comprises:
and carrying out paragraph structure splitting on the emergency plan text through a preset regular matching and recursive algorithm to obtain the emergency plan text split into paragraphs.
4. The processing method according to claim 1, wherein the determining emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining attributes of the emergency plan knowledge elements, and determining relationships among the emergency plan knowledge elements comprises:
feeding back the preset emergency plan knowledge element model and the split emergency plan text to a labeling user side;
receiving a labeling result fed back by the labeling user side; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements.
5. The processing method according to claim 1, wherein the determining emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining attributes of the emergency plan knowledge elements, and determining relationships among the emergency plan knowledge elements comprises:
training an initial labeling model according to the preset emergency plan knowledge element model to obtain a trained labeling model;
marking the split emergency plan text through the trained marking model to obtain a marking result; the labeling result comprises: and the emergency plan knowledge elements in the split emergency plan text, the attributes of the emergency plan knowledge elements and the relationship among the emergency plan knowledge elements.
6. The processing method according to claim 1, wherein the obtaining of the emergency plan text to be processed comprises:
and acquiring the emergency plan text from a target website through a crawler technology based on preset emergency features.
7. The processing method according to claim 1, wherein the constructing a corresponding knowledge graph of the emergency plan text according to the emergency plan knowledge element, the attributes of the emergency plan knowledge element and the relationship between the emergency plan knowledge elements comprises:
according to the relation between the emergency plan knowledge elements and the attributes of the emergency plan knowledge elements, carrying out fusion processing on the emergency plan knowledge elements in different emergency plan texts to obtain a structured data set;
associating the emergency plan knowledge elements in the structured data set with preset knowledge elements corresponding to the emergency plan knowledge elements and attributes of the corresponding preset knowledge elements;
and converting the structured data set into ternary group data through a preset data conversion tool to obtain a knowledge graph corresponding to the emergency plan text.
8. The processing method according to claim 1, characterized in that it further comprises:
receiving a retrieval request of a target emergency plan; the retrieval request comprises information to be retrieved;
determining a retrieval result corresponding to the information to be retrieved according to the information to be retrieved and a knowledge map corresponding to the emergency plan text;
and feeding back the retrieval result.
9. An emergency response plan processing apparatus, comprising:
the acquisition module is used for acquiring an emergency plan text to be processed; the emergency plan is a processing scheme of an emergency event;
the processing module is used for splitting the emergency plan text to obtain the split emergency plan text;
determining emergency plan knowledge elements in the split emergency plan text according to a preset emergency plan knowledge element model, determining attributes of the emergency plan knowledge elements, and determining the relationship among the emergency plan knowledge elements; the preset emergency plan knowledge element model comprises a plurality of preset knowledge elements, attributes of the preset knowledge elements and relations among the preset knowledge elements;
and constructing a knowledge graph corresponding to the text of the emergency plan according to the relationship among the knowledge elements of the emergency plan, the attributes of the knowledge elements of the emergency plan and the knowledge elements of the emergency plan.
10. The processing apparatus according to claim 9, wherein the processing module is specifically configured to perform paragraph structure splitting on the emergency plan text to obtain the emergency plan text split into paragraphs; and performing text segmentation on the emergency plan file split into the paragraphs to obtain an emergency plan text split into text segments.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110181165.3A CN112836018A (en) | 2021-02-07 | 2021-02-07 | Method and device for processing emergency plan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110181165.3A CN112836018A (en) | 2021-02-07 | 2021-02-07 | Method and device for processing emergency plan |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112836018A true CN112836018A (en) | 2021-05-25 |
Family
ID=75933296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110181165.3A Pending CN112836018A (en) | 2021-02-07 | 2021-02-07 | Method and device for processing emergency plan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112836018A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965921A (en) * | 2021-09-22 | 2022-01-21 | 南方电网数字电网研究院有限公司 | Network security emergency response method and response system for power system |
| CN113962072A (en) * | 2021-10-12 | 2022-01-21 | 深圳市城市公共安全技术研究院有限公司 | Emergency plan checking method and device and computer readable storage medium |
| CN115345411A (en) * | 2022-04-29 | 2022-11-15 | 水利部交通运输部国家能源局南京水利科学研究院 | Matrix fusion algorithm-based body evolution method in dam break emergency plan field |
| CN116521303A (en) * | 2023-07-04 | 2023-08-01 | 四川易诚智讯科技有限公司 | Dynamic display method and system of emergency plan based on multi-source data fusion |
| CN116521304A (en) * | 2023-07-04 | 2023-08-01 | 四川易诚智讯科技有限公司 | Method and system for generating and displaying structured fine granularity plan |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609456A (en) * | 2012-01-12 | 2012-07-25 | 凤凰在线(北京)信息技术有限公司 | System and method for real-time and smart article capturing |
| US20150095331A1 (en) * | 2012-12-21 | 2015-04-02 | Cloud Computing Center Chinese Academy Of Sciences | Establishing and querying methods of knowledge library engine based on emergency management |
| CN108376160A (en) * | 2018-02-12 | 2018-08-07 | 北京大学 | A kind of Chinese knowledge mapping construction method and system |
| CN108763333A (en) * | 2018-05-11 | 2018-11-06 | 北京航空航天大学 | A kind of event collection of illustrative plates construction method based on Social Media |
| CN111563173A (en) * | 2020-05-09 | 2020-08-21 | 北京中科院软件中心有限公司 | Knowledge graph construction method and system based on manufacturing field |
| CN111753099A (en) * | 2020-06-28 | 2020-10-09 | 中国农业科学院农业信息研究所 | Method and system for enhancing file entity association degree based on knowledge graph |
| CN112100397A (en) * | 2020-09-07 | 2020-12-18 | 南京航空航天大学 | Electric power plan knowledge graph construction method and system based on bidirectional gating circulation unit |
-
2021
- 2021-02-07 CN CN202110181165.3A patent/CN112836018A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102609456A (en) * | 2012-01-12 | 2012-07-25 | 凤凰在线(北京)信息技术有限公司 | System and method for real-time and smart article capturing |
| US20150095331A1 (en) * | 2012-12-21 | 2015-04-02 | Cloud Computing Center Chinese Academy Of Sciences | Establishing and querying methods of knowledge library engine based on emergency management |
| CN108376160A (en) * | 2018-02-12 | 2018-08-07 | 北京大学 | A kind of Chinese knowledge mapping construction method and system |
| CN108763333A (en) * | 2018-05-11 | 2018-11-06 | 北京航空航天大学 | A kind of event collection of illustrative plates construction method based on Social Media |
| CN111563173A (en) * | 2020-05-09 | 2020-08-21 | 北京中科院软件中心有限公司 | Knowledge graph construction method and system based on manufacturing field |
| CN111753099A (en) * | 2020-06-28 | 2020-10-09 | 中国农业科学院农业信息研究所 | Method and system for enhancing file entity association degree based on knowledge graph |
| CN112100397A (en) * | 2020-09-07 | 2020-12-18 | 南京航空航天大学 | Electric power plan knowledge graph construction method and system based on bidirectional gating circulation unit |
Non-Patent Citations (2)
| Title |
|---|
| 吴斌: "《网络科学与计算》", 31 August 2019, 北京邮电大学出版社, pages: 212 - 216 * |
| 蔡圆媛: "《大数据环境下基于知识整合的语义计算技术与应用》", 31 August 2018, 北京理工大学出版社有限责任公司, pages: 154 - 160 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113965921A (en) * | 2021-09-22 | 2022-01-21 | 南方电网数字电网研究院有限公司 | Network security emergency response method and response system for power system |
| CN113962072A (en) * | 2021-10-12 | 2022-01-21 | 深圳市城市公共安全技术研究院有限公司 | Emergency plan checking method and device and computer readable storage medium |
| CN115345411A (en) * | 2022-04-29 | 2022-11-15 | 水利部交通运输部国家能源局南京水利科学研究院 | Matrix fusion algorithm-based body evolution method in dam break emergency plan field |
| CN115345411B (en) * | 2022-04-29 | 2023-05-05 | 水利部交通运输部国家能源局南京水利科学研究院 | Matrix fusion algorithm-based dam break emergency plan field ontology evolution method |
| CN116521303A (en) * | 2023-07-04 | 2023-08-01 | 四川易诚智讯科技有限公司 | Dynamic display method and system of emergency plan based on multi-source data fusion |
| CN116521304A (en) * | 2023-07-04 | 2023-08-01 | 四川易诚智讯科技有限公司 | Method and system for generating and displaying structured fine granularity plan |
| CN116521303B (en) * | 2023-07-04 | 2023-09-12 | 四川易诚智讯科技有限公司 | Dynamic display method and system of emergency plan based on multi-source data fusion |
| CN116521304B (en) * | 2023-07-04 | 2023-12-01 | 四川易诚智讯科技有限公司 | Method and system for generating and displaying structured fine granularity plan |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112836018A (en) | Method and device for processing emergency plan | |
| CN108932294B (en) | Resume data processing method, device, equipment and storage medium based on index | |
| US20130117268A1 (en) | Identifying and suggesting classifications for financial data according to a taxonomy | |
| CN106294520B (en) | Carry out identified relationships using the information extracted from document | |
| US20120179658A1 (en) | Cleansing a Database System to Improve Data Quality | |
| CN111680634A (en) | Document file processing method and device, computer equipment and storage medium | |
| CN111259160A (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN113190689B (en) | Construction method, device, equipment and medium of electric power safety knowledge graph | |
| CN110941702A (en) | Retrieval method and device for laws and regulations and laws and readable storage medium | |
| CN107870915A (en) | Instruction to search result | |
| CN111858236A (en) | Knowledge graph monitoring method and device, computer equipment and storage medium | |
| CN116881395A (en) | Public opinion information detection method and device | |
| CN114722789B (en) | Data report integrating method, device, electronic equipment and storage medium | |
| CN113050933B (en) | Brain graph data processing method, device, equipment and storage medium | |
| CN113312486B (en) | Signal portrait construction method and device, electronic equipment and storage medium | |
| CN115269862A (en) | Electric power question-answering and visualization system based on knowledge graph | |
| AU2019290658B2 (en) | Systems and methods for identifying and linking events in structured proceedings | |
| CN113032515A (en) | Method, system, device and storage medium for generating chart based on multiple data sources | |
| CN111309773A (en) | Vehicle information query method, device and system and storage medium | |
| CN112380264A (en) | Policy analysis and matching method and device based on personal full life cycle | |
| CN111177501B (en) | Label processing method, device and system | |
| Bakar | Latent Semantic Analysis and Particle Swarm Optimization for Requirements Reuse in Software Product Line: A Research Plan | |
| CN113868419B (en) | Text classification method, device, equipment and medium based on artificial intelligence | |
| Hutcheson | 8.2. 2 Practical Considerations for a Term Bank: Termium | |
| CN116991873A (en) | Target report data processing method and device based on knowledge graph and server |
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 |