CN116010618A

CN116010618A - Risk knowledge graph generation method and device

Info

Publication number: CN116010618A
Application number: CN202211711068.1A
Authority: CN
Inventors: 杨秀中; 梁建民; 林天埜; 吴大维
Original assignee: Beijing Global Safety Technology Co Ltd
Current assignee: Beijing Global Safety Technology Co Ltd
Priority date: 2022-12-29
Filing date: 2022-12-29
Publication date: 2023-04-25

Abstract

The disclosure provides a risk knowledge graph generation method and device, wherein the method comprises the following steps: acquiring a risk information ontology model and a plurality of historical risk monitoring early warning information, wherein the risk information ontology model comprises: at least one conceptual entity, a relationship between the at least one conceptual entity; carrying out information extraction processing on the historical risk monitoring early warning information by combining the risk information ontology model, and determining triplet information corresponding to the historical risk monitoring early warning information; the triplet information is used to indicate at least one of: attribute data of instance entities, a relation between at least one instance entity and a relation between the instance entity and a concept entity in the historical risk monitoring and early warning information; according to the risk information ontology model and the triple information corresponding to the historical risk monitoring early warning information, a risk knowledge graph is generated, required data can be quickly searched and obtained based on the risk knowledge graph, the risk can be quickly handled, and the risk processing speed and the risk processing efficiency are improved.

Description

Risk knowledge graph generation method and device

Technical Field

The disclosure relates to the technical field of data processing, and in particular relates to a risk knowledge graph generation method and device.

Background

At present, urban safety risk monitoring and early warning relates to dozens of aspects such as urban lifeline, public safety, production safety, natural disasters and the like, and has the advantages of large data volume, high growth speed, and multiple data sources of risk monitoring and early warning data, so that the calculated amount of the risk monitoring and early warning data is large, the calculation speed is low, required data is difficult to extract from the risk monitoring and early warning data rapidly, and the urban risk processing capability is poor.

Disclosure of Invention

The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.

Therefore, a first objective of the present disclosure is to provide a risk knowledge graph generation method, which is used for solving the problems of large calculation amount, low calculation speed and difficult rapid extraction of required data in the prior art.

A second object of the present disclosure is to provide a risk knowledge graph generating apparatus.

A third object of the present disclosure is to propose an electronic device.

A fourth object of the present disclosure is to propose a computer readable storage medium.

To achieve the above objective, an embodiment of a first aspect of the present disclosure provides a method for generating a risk knowledge graph, including: acquiring a risk information ontology model and a plurality of historical risk monitoring early warning information, wherein the risk information ontology model comprises: at least one conceptual entity, a relationship between at least one of said conceptual entities;

Carrying out information extraction processing on the historical risk monitoring early warning information by combining the risk information ontology model, and determining triplet information corresponding to the historical risk monitoring early warning information; the triplet information is used to indicate at least one of: attribute data of instance entities in the historical risk monitoring and early warning information, at least one relationship among the instance entities, and a relationship between the instance entities and the concept entities;

and generating a risk knowledge graph according to the risk information ontology model and the triplet information corresponding to the plurality of historical risk monitoring early warning information.

Further, the step of performing information extraction processing on the historical risk monitoring and early warning information by combining the risk information ontology model to determine the triplet information corresponding to the historical risk monitoring and early warning information includes: performing information extraction processing on the historical risk monitoring early warning information to obtain at least one entity in the historical risk monitoring early warning information, attribute data of the entity and a relation among at least one entity; inquiring the risk information ontology model according to at least one entity to obtain instance entities in at least one entity; determining a relationship between the instance entity and a concept entity in the risk information ontology model; and generating triple information corresponding to the historical risk monitoring early warning information according to the attribute data of the instance entities, the relation between at least one instance entity and the relation between the instance entity and the concept entity.

Further, the querying the risk information ontology model according to at least one entity obtains an instance entity in at least one entity, including: for each entity in the historical risk monitoring early warning information, inquiring the risk information ontology model according to the entity, and determining whether a conceptual entity matched with the entity exists in the risk information ontology model; in the event that there is a conceptual entity in the risk information ontology model that matches the entity, the entity is determined to be an instance entity.

Further, the determining the relationship between the instance entity and the concept entity in the risk information ontology model includes: acquiring concept entities matched with the instance entities in the risk information ontology model; a relationship between the instance entity and the matching concept entity is determined.

Further, the generating the triplet information corresponding to the historical risk monitoring early warning information according to the attribute data of the instance entities, the relation between at least one instance entity and the relation between the instance entity and the concept entity includes: generating triple information comprising the instance entity, the affiliated relation among the instance entity and the attribute data according to the instance entity and the attribute data of the instance entity; generating triplet information comprising the instance entity, the concept entity and a relationship between the instance entity and the concept entity according to the relationship between the instance entity and the concept entity; from relationships between at least one of the instance entities, triple information is generated that includes the instance entity, other instance entities, and relationships between the instance entity and the other instance entities.

Further, the generating a risk knowledge graph according to the risk information ontology model and the triplet information corresponding to the plurality of historical risk monitoring and early warning information includes: for each triplet information corresponding to each historical risk monitoring and early warning information, adding the edges between the nodes into the risk information ontology model by taking the instance entity and the attribute data as nodes and taking the belonging relationship between the instance entity and the attribute data as edges under the condition that the triplet information comprises the instance entity, the belonging relationship between the instance entity and the attribute data; in the case that the triplet information comprises two instance entities and a relation between the two instance entities, taking the two instance entities as nodes and the relation between the two instance entities as edges, adding the nodes and the edges between the nodes into the risk information ontology model; and under the condition that the triplet information comprises an instance entity, a concept entity and a relation between the instance entity and the concept entity, taking the instance entity as a node, taking the relation between the instance entity and the concept entity as an edge, and adding the edge between the nodes into the risk information ontology model.

Further, the method further comprises: determining attribute data of each concept entity in the risk knowledge graph according to attribute data of a subordinate instance entity of the concept entity; and adding the attribute data of the concept entity into the risk knowledge graph.

Further, the method further comprises: acquiring a monitored risk source and attribute data of the risk source; inquiring the risk knowledge graph according to the risk source and attribute data of the risk source, and acquiring an instance entity matched with the risk source in the risk knowledge graph; acquiring a target instance entity connected with the instance entity through a relation; and determining risk treatment measures corresponding to the risk sources according to the target instance entity.

Further, the concept entities include at least one main concept entity, and subordinate concept entities of the main concept entity; the main conceptual entities include: a risk source entity, a disaster-bearing entity, a disaster-tolerant environment entity and a risk disposal entity; the relationship between the main concept entity and the corresponding subordinate concept entity is an upper-level relationship and a lower-level relationship; the relationship between at least one of the primary conceptual entities is a causal relationship.

According to the risk knowledge graph generation method, a risk information ontology model and a plurality of historical risk monitoring early warning information are obtained, wherein the risk information ontology model comprises the following steps: at least one conceptual entity, a relationship between the at least one conceptual entity; carrying out information extraction processing on the historical risk monitoring early warning information by combining the risk information ontology model, and determining triplet information corresponding to the historical risk monitoring early warning information; the triplet information is used to indicate at least one of: attribute data of instance entities, a relation between at least one instance entity and a relation between the instance entity and a concept entity in the historical risk monitoring and early warning information; according to the risk information ontology model and the triple information corresponding to the historical risk monitoring early warning information, a risk knowledge graph is generated, required data can be quickly searched and obtained based on the risk knowledge graph, the risk can be quickly handled, and the risk processing speed and the risk processing efficiency are improved.

To achieve the above object, an embodiment of a second aspect of the present disclosure provides a risk knowledge graph generating device, including: the system comprises an acquisition module, a risk information ontology model and a plurality of historical risk monitoring early warning information, wherein the risk information ontology model comprises: at least one conceptual entity, a relationship between at least one of said conceptual entities;

The determining module is used for carrying out information extraction processing on the historical risk monitoring early warning information by combining the risk information ontology model, and determining triplet information corresponding to the historical risk monitoring early warning information; the triplet information is used to indicate at least one of: attribute data of instance entities in the historical risk monitoring and early warning information, at least one relationship among the instance entities, and a relationship between the instance entities and the concept entities;

and the generation module is used for generating a risk knowledge graph according to the risk information ontology model and the triplet information corresponding to the plurality of historical risk monitoring early warning information.

Further, the determining module includes: the device comprises a first acquisition unit, a second acquisition unit, a determination unit and a generation unit; the first obtaining unit is used for extracting and processing the historical risk monitoring and early warning information to obtain at least one entity in the historical risk monitoring and early warning information, attribute data of the entity and the relation among at least one entity; the second obtaining unit is configured to query the risk information ontology model according to at least one entity, and obtain an instance entity in at least one entity; the determining unit is used for determining the relation between the instance entity and the concept entity in the risk information ontology model; the generating unit is configured to generate triplet information corresponding to the historical risk monitoring early warning information according to attribute data of the instance entities, a relationship between at least one instance entity, and a relationship between the instance entity and the concept entity.

Further, the second obtaining unit is specifically configured to, for each entity in the historical risk monitoring and early warning information, query the risk information ontology model according to the entity, and determine whether a conceptual entity matched with the entity exists in the risk information ontology model; in the event that there is a conceptual entity in the risk information ontology model that matches the entity, the entity is determined to be an instance entity.

Further, the determining unit is specifically configured to obtain a concept entity matched with the instance entity in the risk information ontology model; a relationship between the instance entity and the matching concept entity is determined.

Further, the generating unit is specifically configured to generate, according to the instance entity and attribute data of the instance entity, triplet information including the instance entity, a relationship between the instance entity and the attribute data, and the attribute data; generating triplet information comprising the instance entity, the concept entity and a relationship between the instance entity and the concept entity according to the relationship between the instance entity and the concept entity; from relationships between at least one of the instance entities, triple information is generated that includes the instance entity, other instance entities, and relationships between the instance entity and the other instance entities.

Further, the generating module is specifically configured to, for each triplet information corresponding to each historical risk monitoring and early warning information, add, in the case where the triplet information includes an instance entity, a relationship between the instance entity and the attribute data, an edge between the instance entity and the attribute data with the instance entity and the attribute data as nodes and the relationship between the instance entity and the attribute data as an edge, the edge between the nodes to the risk information ontology model; in the case that the triplet information comprises two instance entities and a relation between the two instance entities, taking the two instance entities as nodes and the relation between the two instance entities as edges, adding the nodes and the edges between the nodes into the risk information ontology model; and under the condition that the triplet information comprises an instance entity, a concept entity and a relation between the instance entity and the concept entity, taking the instance entity as a node, taking the relation between the instance entity and the concept entity as an edge, and adding the edge between the nodes into the risk information ontology model.

Further, the apparatus further comprises: adding a module; the determining module is further configured to determine, for each concept entity in the risk knowledge graph, attribute data of the concept entity according to attribute data of a subordinate instance entity of the concept entity; the adding module is configured to add attribute data of the concept entity to the risk knowledge graph.

Further, the acquiring module is further configured to acquire a monitored risk source and attribute data of the risk source; inquiring the risk knowledge graph according to the risk source and attribute data of the risk source, and acquiring an instance entity matched with the risk source in the risk knowledge graph; acquiring a target instance entity connected with the instance entity through a relation; the determining module is further configured to determine, according to the target instance entity, a risk disposition measure corresponding to the risk source.

The device for generating a risk knowledge graph in the embodiment of the disclosure obtains a risk information ontology model and a plurality of historical risk monitoring early warning information, wherein the risk information ontology model comprises: at least one conceptual entity, a relationship between the at least one conceptual entity; carrying out information extraction processing on the historical risk monitoring early warning information by combining the risk information ontology model, and determining triplet information corresponding to the historical risk monitoring early warning information; the triplet information is used to indicate at least one of: attribute data of instance entities, a relation between at least one instance entity and a relation between the instance entity and a concept entity in the historical risk monitoring and early warning information; according to the risk information ontology model and the triple information corresponding to the historical risk monitoring early warning information, a risk knowledge graph is generated, required data can be quickly searched and obtained based on the risk knowledge graph, the risk can be quickly handled, and the risk processing speed and the risk processing efficiency are improved.

To achieve the above object, an embodiment of a third aspect of the present disclosure provides an electronic device, including: the risk knowledge graph generation system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, and is characterized in that the processor realizes the risk knowledge graph generation method when executing the program.

In order to achieve the above object, a fourth aspect of the present disclosure provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the risk knowledge graph generation method as described above.

Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.

Drawings

The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

fig. 1 is a flow chart of a method for generating a risk knowledge graph according to an embodiment of the disclosure;

FIG. 2 is a schematic diagram of risk monitoring and early warning;

FIG. 3 is a partial schematic diagram of a risk knowledge graph;

fig. 4 is a flowchart of another risk knowledge graph generation method according to an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a risk knowledge graph generating device according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the disclosure.

Detailed Description

Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.

The method and device for generating a risk knowledge graph according to the embodiments of the present disclosure are described below with reference to the accompanying drawings.

Fig. 1 is a flow chart of a method for generating a risk knowledge graph according to an embodiment of the present disclosure. As shown in fig. 1, the method mainly comprises the following steps:

s101, acquiring a risk information ontology model and a plurality of historical risk monitoring early warning information, wherein the risk information ontology model comprises: at least one conceptual entity, a relationship between at least one conceptual entity.

In the embodiment of the application, the concept entity may include at least one main concept entity, and a subordinate concept entity of the main concept entity; the main conceptual entities include: a risk source entity, a disaster-bearing entity, a disaster-tolerant environment entity and a risk disposal entity; the relationship between the main concept entity and the corresponding subordinate concept entity is an upper-level relationship; the relationship between at least one of the primary conceptual entities is a causal relationship. The risk information ontology model herein may be constructed based on a preset area, for example, constructed based on a city, constructed based on a country, etc. In the following embodiments, a risk information ontology model constructed based on a city will be described as an example.

In the embodiment of the present application, taking a city as an example, a risk source entity refers to a risk element that threatens city security. Wherein the subordinate risk source entities of the risk source entity are, for example, an urban lifeline risk source, a public safety risk source, a production safety risk source, and a natural disaster risk source.

Wherein, subordinate risk source entities of the urban lifeline risk source are, for example, gas risk source, water supply risk source, drainage risk source, electric power risk source, bridge risk source, thermal risk source, piping lane risk source, tunnel risk source. Wherein subordinate risk source entities of public safety risk sources such as fire risk sources, traffic risk sources, special equipment risk sources, crowd-intensive places risk sources. Wherein, the subordinate risk source entity for producing the safety risk source is, for example, a hazardous chemical risk source, a coal mine risk source, a non-coal mine risk source, a firework and firecracker risk source, a building construction risk source and a industry trade risk source. Wherein the subordinate risk source entities of the natural disaster risk source are, for example, earthquake risk source, geological risk source, meteorological risk source, paddy-upland risk source, marine risk source, forest fire risk source.

In the embodiment of the application, the disaster-bearing entity refers to an urban main body directly affected and damaged by the disaster. The lower disaster-bearing entity of the disaster-bearing entity is, for example, public facilities, public dense places, office and residence areas, schools and training institutions, outsourcing places, important cultural relics protection units, news broadcasting institutions and the like.

In the embodiment of the application, the disaster recovery environment text refers to the external environment where the risk source entity and the disaster bearing entity are located. Wherein, the lower-level disaster-tolerant environment text of the disaster-tolerant environment text is, for example, a natural environment and a social environment.

Wherein, the text of the lower-level disaster-tolerant environment of the natural environment is such as a topography environment, a landform environment, a hydrologic environment, a climate environment, a vegetation environment, a soil environment and an animal and plant environment. The text of the lower-level disaster-tolerant environment of the social environment is, for example, an industrial and mining commerce environment, an underground pipeline environment, a traffic system environment, a public place environment and an economic market environment.

In the embodiment of the application, the risk handling entity refers to a series of necessary measures and activities of disaster reduction services adopted according to an urban safety monitoring and early warning system and a management system in the process of coping with urban risks. Wherein a subordinate risk handling entity of the risk handling entity, for example, prevention and preparation, monitoring and early warning, handling and rescue.

Wherein the subordinate risk handling entities of prevention and preparation, e.g., risk identification, risk prevention and control, risk assessment. Wherein the subordinate risk handling entities of monitoring and early warning are for example monitoring observation, prediction forecasting, risk early warning. Wherein subordinate risk handling entities handling and rescue, such as organizations and responsibilities, emergency resources, coordinated handling, personnel search and rescue, and evacuation.

In the embodiment of the application, the causal relationship between at least one main concept entity, for example, the disaster-tolerant environmental entity is a space-time distribution feature of a risk source entity; the disaster-bearing entity is a disaster-bearing system of a risk source entity; the risk source entity is a disaster causing capability evaluation object of the risk handling entity; the disaster-tolerant environmental entity is a risk monitoring/analyzing early warning object of a risk handling entity; the disaster-bearing entity is a vulnerability assessment object of the risk handling entity.

The concept entity may be expressed in at least one of the following ways: entity type representation, perceptual data type representation, file data type representation, multimedia type, etc. In the case where the representation modes of the concept entity are plural, the association relationship between the plural representation modes of the concept entity may be established.

S102, carrying out information extraction processing on historical risk monitoring early warning information by combining a risk information ontology model, and determining triplet information corresponding to the historical risk monitoring early warning information; the triplet information is used to indicate at least one of: attribute data of instance entities, a relation between at least one instance entity and a relation between the instance entity and a concept entity in the historical risk monitoring and early warning information.

In the embodiment of the application, the historical risk monitoring and early warning information can be risk monitoring and early warning information acquired through various acquisition modes at a historical time point. The risk monitoring and early warning information is, for example, "X month and X day in XX year, and extra heavy storm exists in XX place, so that X-ray waterlogging of the subway is caused. In the risk monitoring and early warning information, example entities such as 'ultra heavy rain', 'subway X line', and the like.

In the embodiment of the application, under the condition that the triplet information is used for indicating the attribute data of the instance entity in the historical risk monitoring and early warning information, three elements in the triplet information are respectively the instance entity, the belonging relation between the instance entity and the attribute data. Wherein, in the case that the triplet information is used to indicate the relationship between at least one instance entity, three elements in the triplet information are respectively one instance entity, the relationship, and another instance entity. Wherein, in the case that the triplet information is used to indicate the relationship between the instance entity and the concept entity, three elements in the triplet information are respectively the instance entity, the relationship and the concept entity.

And S103, generating a risk knowledge graph according to the risk information ontology model and the triplet information corresponding to the plurality of historical risk monitoring early warning information.

In this embodiment of the present application, the process of executing step 103 by the risk knowledge graph generating device may, for example, be that, for each triplet information corresponding to each historical risk monitoring and early warning information, in a case where the triplet information includes an instance entity, a relationship between the instance entity and attribute data, the instance entity and attribute data are taken as nodes,

taking the belonged relation between the instance entity and the attribute data as an edge, and adding the edge between the nodes into the risk information ontology 5 model; in the case where two instance entities and a relationship between the two instance entities are included in the triplet information, two by two

The instance entities are nodes, the relationship between the two instance entities is taken as an edge, and the edge between the nodes is added into the risk information ontology model; in the case that the triplet information comprises an instance entity, a concept entity and a relation between the instance entity and the concept entity, the instance entity is taken as a node, the relation between the instance entity and the concept entity is taken as an edge, and the edge between the nodes is added into the risk information ontology model.

0 in the embodiment of the present application, in order to further expand the risk knowledge graph, after step 103, the risk knowledge graph

The generating means may also perform the following procedure: determining attribute data of the concept entities according to attribute data of subordinate instance entities of the concept entities aiming at each concept entity in the risk knowledge graph; and adding attribute data of the concept entity into the risk knowledge graph.

In this embodiment of the present application, after the risk knowledge graph is generated, the risk knowledge graph generating device may further use the risk knowledge graph according to actual 5-case needs, and the corresponding risk knowledge graph generating device may further execute the following process: acquisition of

The monitored risk source and attribute data of the risk source; inquiring a risk knowledge graph according to the risk source and attribute data of the risk source, and acquiring an instance entity matched with the risk source in the risk knowledge graph; acquiring a target instance entity connected with the instance entity through a relation; and determining risk treatment measures corresponding to the risk sources according to the target instance entity.

Fig. 2 is a schematic diagram of risk monitoring and early warning. In FIG. 2, (1) after monitoring an instance entity of risk source entity 0 (urban risk source), such as a storm, a risk knowledge graph may be queried to obtain a matching risk source

An entity that obtains a risk handling entity in relation to the risk source entity, e.g., the risk handling entity may be preventive and ready; and combining the risk disposal entity to perform storm risk analysis, storm risk prevention and control measures, training, exercise and the like. (2) Inquiring a risk knowledge graph when the precipitation amount of the storm reaches a critical rainfall amount, and obtaining the storm matching with the critical rainfall amount

A matched risk source entity, a disaster-pregnant environment entity (urban disaster-pregnant environment) which is related to the risk source entity is obtained, for example, 5 mountain floods (the risk source entity which is related to the mountain floods is mountain floods), landslide hidden danger points (related to the establishment of landslide hidden danger points

The risk source entity of the system is landslide or mud-rock flow), urban waterlogging points (the risk source entity which is related to the urban waterlogging points is waterlogging), reservoirs (the risk source entity which is related to the reservoirs is a dam break), and risk disposal entities which are related to the disaster-pregnant environment entities are obtained, for example, the risk disposal entities are monitoring and early warning; meteorological in connection with the risk handling entity

Monitoring, river water level monitoring, coupling risk early warning and the like. (3) Inquiring a wind 0 risk knowledge graph when the disaster-tolerant environmental entity reaches the vulnerability threshold value, obtaining disaster-tolerant entity (urban disaster-tolerant entity) matched with the disaster-tolerant environmental entity reaching the vulnerability threshold value,

For example, farmland (farmland is flooded as a risk source entity related to farmland), public infrastructure (bridge rushing, road damage as a risk source entity related to public infrastructure), electric power facility (pole collapse as a risk source entity related to electric power facility), and acquiring a risk disposal entity related to disaster-bearing entity, for example, the risk disposal entity is disposal and rescue; and combining the risk treatment entity to carry out organization and responsibility determination, emergency resource determination, linkage treatment, personnel evacuation and the like.

Fig. 3 is a schematic diagram of a risk knowledge graph. In fig. 3, the urban risk source (risk source entity) includes natural disasters including storms; example entities under storms such as "extra heavy storms in XX-day XX place"; urban disaster-bearing bodies (disaster-bearing body entities) comprise public infrastructures, public foundation arrangements comprise subways and highways, instance entities under subways such as "subway X-rays", instance entities under highways such as "XX tunnels"; there is a relationship between "extra heavy storm in XX places on XX days" and "subway X line" and "XX tunnel".

Wherein, the attribute data of the ultra heavy rain in XX-day XX place can comprise: time: XX year XX month XX day "," accumulated average rainfall: 449 mm). The attribute data of the "subway X line" may include: "subway inland inundation" and "X people die". The attribute data of the "XX tunnel" may include, for example: "X people die" and "X cars are flooded".

Fig. 4 is a flowchart of another risk knowledge graph generation method according to an embodiment of the present disclosure. As shown in fig. 4, based on the embodiment shown in fig. 1, step 102 may specifically include the following steps:

And 1021, performing information extraction processing on the historical risk monitoring and early warning information, and acquiring at least one entity in the historical risk monitoring and early warning information, attribute data of the entity and a relation among the at least one entity.

In the embodiment of the present application, the risk knowledge graph generating device may input historical risk monitoring and early warning information into the entity extraction model, and obtain at least one entity output by the entity extraction model. The entity extraction model may be, for example, a conditional random field model crf+a language model BERT. The risk knowledge graph generating device can also be combined with the extracted entity to extract attribute data of the entity from the historical risk monitoring and early warning information. Taking risk monitoring and early warning information of 'XX year, X month and X day, extra heavy storm exists in XX places, and thus subway X-ray waterlogging' is taken as an example, attribute data of an entity 'extra heavy storm' such as time information 'XX year, X month and X day', address information 'XX places', and the like.

In the embodiment of the present application, the risk knowledge graph generating device may input the historical risk monitoring and early warning information and the at least one entity into the relationship extraction model, and obtain the relationship between the at least one entity output by the relationship extraction model. The relation extraction model may be, for example, a CASREL model.

Step 1022, according to the at least one entity query risk information ontology model, obtaining an instance entity in the at least one entity.

In this embodiment of the present application, the process of executing step 1022 by the device for generating a risk knowledge graph may be, for example, determining, for each entity in the historical risk monitoring and early warning information, whether a conceptual entity matching the entity exists in the risk information ontology model according to the entity query risk information ontology model; in the event that there is a conceptual entity in the risk information ontology model that matches the entity, the entity is determined to be an instance entity.

The concept entity is matched with the entity, which means that the entity is a lower concept of the concept entity, that is, one of the concept entities is the entity. For example, an entity "heavy rain" is a subordinate concept of the concept entity "flood risk source", which includes heavy rain.

Step 1023, determining the relationship between the instance entity and the concept entity in the risk information ontology model.

In this embodiment of the present application, the process of executing step 1023 by the device for generating a risk knowledge graph may be, for example, obtaining a concept entity matching with an instance entity in the risk information ontology model; relationships between instance entities and matching concept entities are determined.

Wherein the relationship between the instance entity and the matching concept entity, e.g., a superior-inferior relationship, etc. That is, the conceptual entity is a superior entity to the instance entity; an instance entity is a subordinate entity to a concept entity.

Step 1024, generating triple information corresponding to the historical risk monitoring and early warning information according to the attribute data of the instance entities, the relation between at least one instance entity and the relation between the instance entity and the concept entity.

In this embodiment of the present application, the step 1024 may be performed by the generating device of the risk knowledge graph, for example, generating, according to the instance entity and the attribute data of the instance entity, triple information including the instance entity, the relationship between the instance entity and the attribute data, and the attribute data; generating triple information comprising the instance entity, the concept entity and the relationship between the instance entity and the concept entity according to the relationship between the instance entity and the concept entity; from relationships between at least one instance entity, triple information is generated that includes instance entities, other instance entities, and relationships between instance entities and other instance entities.

According to the risk knowledge graph generation method, a risk information ontology model and a plurality of historical risk monitoring early warning information are obtained, wherein the risk information ontology model comprises the following steps: at least one conceptual entity, a relationship between the at least one conceptual entity; performing information extraction processing on the historical risk monitoring early warning information to obtain at least one entity in the historical risk monitoring early warning information, attribute data of the entity and a relation among the at least one entity; inquiring a risk information ontology model according to at least one entity to obtain instance entities in the at least one entity; determining a relationship between the instance entity and a concept entity in the risk information ontology model; generating triple information corresponding to historical risk monitoring early warning information according to attribute data of instance entities, the relation between at least one instance entity and the relation between instance entities and concept entities; the triplet information is used to indicate at least one of: attribute data of instance entities, a relation between at least one instance entity and a relation between the instance entity and a concept entity in the historical risk monitoring and early warning information; according to the risk information ontology model and the triple information corresponding to the historical risk monitoring early warning information, a risk knowledge graph is generated, required data can be quickly searched and obtained based on the risk knowledge graph, the risk can be quickly handled, and the risk processing speed and the risk processing efficiency are improved.

Fig. 5 is a schematic structural diagram of a risk knowledge graph generating device according to an embodiment of the present disclosure. As shown in fig. 5, includes: an acquisition module 51, a determination module 52 and a generation module 53.

The acquiring module 51 is configured to acquire a risk information ontology model and a plurality of historical risk monitoring early warning information, where the risk information ontology model includes: at least one conceptual entity, a relationship between at least one of said conceptual entities;

the determining module 52 is configured to perform information extraction processing on the historical risk monitoring and early warning information in combination with the risk information ontology model, and determine triplet information corresponding to the historical risk monitoring and early warning information; the triplet information is used to indicate at least one of: attribute data of instance entities in the historical risk monitoring and early warning information, at least one relationship among the instance entities, and a relationship between the instance entities and the concept entities;

and the generation module 53 is configured to generate a risk knowledge graph according to the risk information ontology model and the triplet information corresponding to the plurality of historical risk monitoring and early warning information.

Further, the determining module 52 includes: the device comprises a first acquisition unit, a second acquisition unit, a determination unit and a generation unit; the first obtaining unit is used for extracting and processing the historical risk monitoring and early warning information to obtain at least one entity in the historical risk monitoring and early warning information, attribute data of the entity and the relation among at least one entity; the second obtaining unit is configured to query the risk information ontology model according to at least one entity, and obtain an instance entity in at least one entity; the determining unit is used for determining the relation between the instance entity and the concept entity in the risk information ontology model; the generating unit is configured to generate triplet information corresponding to the historical risk monitoring early warning information according to attribute data of the instance entities, a relationship between at least one instance entity, and a relationship between the instance entity and the concept entity.

Further, the generating module 53 is specifically configured to, for each triplet information corresponding to each historical risk monitoring and early warning information, add, in a case where an instance entity, a relationship between the instance entity and the attribute data, and the attribute data are included in the triplet information, an edge between the nodes with the instance entity and the attribute data as nodes and the relationship between the instance entity and the attribute data as an edge, to the risk information ontology model; in the case that the triplet information comprises two instance entities and a relation between the two instance entities, taking the two instance entities as nodes and the relation between the two instance entities as edges, adding the nodes and the edges between the nodes into the risk information ontology model; and under the condition that the triplet information comprises an instance entity, a concept entity and a relation between the instance entity and the concept entity, taking the instance entity as a node, taking the relation between the instance entity and the concept entity as an edge, and adding the edge between the nodes into the risk information ontology model.

Further, the acquiring module 51 is further configured to acquire the monitored risk source and attribute data of the risk source; inquiring the risk knowledge graph according to the risk source and attribute data of the risk source, and acquiring an instance entity matched with the risk source in the risk knowledge graph; acquiring a target instance entity connected with the instance entity through a relation; the determining module 52 is further configured to determine, according to the target instance entity, a risk disposition measure corresponding to the risk source.

It should be noted that, for the description of each module in the present application, reference may be made to the method embodiments shown in fig. 1 to fig. 4, and detailed description thereof will not be given here.

Referring now to fig. 6, a schematic diagram of an electronic device 800 suitable for use in implementing embodiments of the present disclosure is shown. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and the like, and stationary terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 6 is merely an example and should not be construed to limit the functionality and scope of use of the disclosed embodiments.

As shown in fig. 6, the electronic device 800 may include a processing means (e.g., a central processor, a graphics processor, etc.) 801, which may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage means 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 are also stored. The processing device 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.

In general, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, and the like; an output device 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, etc.; storage 808 including, for example, magnetic tape, hard disk, etc.; communication means 809. The communication means 809 may allow the electronic device 800 to communicate wirelessly or by wire with other devices to exchange data. While fig. 6 shows an electronic device 800 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication device 809, or installed from storage device 808, or installed from ROM 802. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 801.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to:

acquiring a risk information ontology model and a plurality of historical risk monitoring early warning information, wherein the risk information ontology model comprises: at least one conceptual entity, a relationship between at least one of said conceptual entities;

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The present disclosure also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a risk knowledge graph generation method as described above.

The present disclosure also provides a computer program product which, when executed by an instruction processor in the computer program product, implements a risk knowledge graph generation method as described above.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present disclosure, the meaning of "a plurality" is at least two, such as two, three, etc., unless explicitly specified otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

Furthermore, each functional unit in the embodiments of the present disclosure may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.

Claims

1. The risk knowledge graph generation method is characterized by comprising the following steps of:

2. The method of claim 1, wherein the performing information extraction processing on the historical risk monitoring and early warning information in combination with the risk information ontology model to determine the triplet information corresponding to the historical risk monitoring and early warning information includes:

performing information extraction processing on the historical risk monitoring early warning information to obtain at least one entity in the historical risk monitoring early warning information, attribute data of the entity and a relation among at least one entity;

inquiring the risk information ontology model according to at least one entity to obtain instance entities in at least one entity;

determining a relationship between the instance entity and a concept entity in the risk information ontology model;

and generating triple information corresponding to the historical risk monitoring early warning information according to the attribute data of the instance entities, the relation between at least one instance entity and the relation between the instance entity and the concept entity.

3. The method of claim 2, wherein said querying the risk information ontology model from at least one of the entities to obtain an instance entity of the at least one of the entities comprises:

For each entity in the historical risk monitoring early warning information, inquiring the risk information ontology model according to the entity, and determining whether a conceptual entity matched with the entity exists in the risk information ontology model;

in the event that there is a conceptual entity in the risk information ontology model that matches the entity, the entity is determined to be an instance entity.

4. A method according to claim 2 or 3, wherein said determining the relationship between the instance entity and a conceptual entity in the risk information ontology model comprises:

acquiring concept entities matched with the instance entities in the risk information ontology model;

a relationship between the instance entity and the matching concept entity is determined.

5. The method according to claim 2, wherein generating the triplet information corresponding to the historical risk monitoring pre-warning information according to the attribute data of the instance entities, the relation between at least one of the instance entities, the relation between the instance entities and the concept entities, comprises:

generating triple information comprising the instance entity, the affiliated relation among the instance entity and the attribute data according to the instance entity and the attribute data of the instance entity;

Generating triplet information comprising the instance entity, the concept entity and a relationship between the instance entity and the concept entity according to the relationship between the instance entity and the concept entity;

from relationships between at least one of the instance entities, triple information is generated that includes the instance entity, other instance entities, and relationships between the instance entity and the other instance entities.

6. The method according to claim 1, wherein the generating a risk knowledge graph according to the risk information ontology model and the triplet information corresponding to the plurality of historical risk monitoring and early warning information includes:

for each triplet information corresponding to each historical risk monitoring and early warning information, adding the edges between the nodes into the risk information ontology model by taking the instance entity and the attribute data as nodes and taking the belonging relationship between the instance entity and the attribute data as edges under the condition that the triplet information comprises the instance entity, the belonging relationship between the instance entity and the attribute data;

In the case that the triplet information comprises two instance entities and a relation between the two instance entities, taking the two instance entities as nodes and the relation between the two instance entities as edges, adding the nodes and the edges between the nodes into the risk information ontology model;

and under the condition that the triplet information comprises an instance entity, a concept entity and a relation between the instance entity and the concept entity, taking the instance entity as a node, taking the relation between the instance entity and the concept entity as an edge, and adding the edge between the nodes into the risk information ontology model.

7. The method according to claim 1 or 6, characterized in that the method further comprises:

determining attribute data of each concept entity in the risk knowledge graph according to attribute data of a subordinate instance entity of the concept entity;

and adding the attribute data of the concept entity into the risk knowledge graph.

8. The method according to claim 1, wherein the method further comprises:

acquiring a monitored risk source and attribute data of the risk source;

Inquiring the risk knowledge graph according to the risk source and attribute data of the risk source, and acquiring an instance entity matched with the risk source in the risk knowledge graph;

acquiring a target instance entity connected with the instance entity through a relation;

and determining risk treatment measures corresponding to the risk sources according to the target instance entity.

9. The method of claim 1, wherein the concept entities comprise at least one primary concept entity and a subordinate concept entity of the primary concept entity;

the main conceptual entities include: a risk source entity, a disaster-bearing entity, a disaster-tolerant environment entity and a risk disposal entity;

the relationship between the main concept entity and the corresponding subordinate concept entity is an upper-level relationship and a lower-level relationship;

the relationship between at least one of the primary conceptual entities is a causal relationship.

10. The risk knowledge graph generation device is characterized by comprising:

the system comprises an acquisition module, a risk information ontology model and a plurality of historical risk monitoring early warning information, wherein the risk information ontology model comprises: at least one conceptual entity, a relationship between at least one of said conceptual entities;

11. The apparatus of claim 10, wherein the determining module comprises: the device comprises a first acquisition unit, a second acquisition unit, a determination unit and a generation unit;

the first obtaining unit is used for extracting and processing the historical risk monitoring and early warning information to obtain at least one entity in the historical risk monitoring and early warning information, attribute data of the entity and the relation among at least one entity;

the second obtaining unit is configured to query the risk information ontology model according to at least one entity, and obtain an instance entity in at least one entity;

The determining unit is used for determining the relation between the instance entity and the concept entity in the risk information ontology model;

the generating unit is configured to generate triplet information corresponding to the historical risk monitoring early warning information according to attribute data of the instance entities, a relationship between at least one instance entity, and a relationship between the instance entity and the concept entity.

12. The device according to claim 11, wherein the second acquisition unit is in particular adapted to,

13. The device according to claim 11 or 12, wherein the determining unit is specifically configured to,

14. The apparatus according to claim 11, wherein the generating unit is specifically configured to,

15. The apparatus of claim 10, wherein the generating module is configured to,

16. The apparatus according to claim 10 or 15, characterized in that the apparatus further comprises: adding a module;

the determining module is further configured to determine, for each concept entity in the risk knowledge graph, attribute data of the concept entity according to attribute data of a subordinate instance entity of the concept entity;

the adding module is configured to add attribute data of the concept entity to the risk knowledge graph.

17. The apparatus of claim 10, wherein the acquisition module is further configured to acquire a monitored risk source, and attribute data for the risk source; inquiring the risk knowledge graph according to the risk source and attribute data of the risk source, and acquiring an instance entity matched with the risk source in the risk knowledge graph; acquiring a target instance entity connected with the instance entity through a relation;

The determining module is further configured to determine, according to the target instance entity, a risk disposition measure corresponding to the risk source.

18. The apparatus of claim 10, wherein the concept entities comprise at least one primary concept entity and a subordinate concept entity of the primary concept entity;

19. An electronic device, comprising:

memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the risk knowledge graph generation method according to any one of claims 1-9 when executing the program.

20. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a risk knowledge-graph generation method according to any one of claims 1-9.