CN112818071A - Traffic management field knowledge graph construction method and device based on unified road network - Google Patents
Traffic management field knowledge graph construction method and device based on unified road network Download PDFInfo
- Publication number
- CN112818071A CN112818071A CN202110177130.2A CN202110177130A CN112818071A CN 112818071 A CN112818071 A CN 112818071A CN 202110177130 A CN202110177130 A CN 202110177130A CN 112818071 A CN112818071 A CN 112818071A
- Authority
- CN
- China
- Prior art keywords
- data
- road network
- traffic management
- knowledge graph
- management field
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims description 23
- 238000009434 installation Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000004540 process dynamic Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Chemical & Material Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a traffic management field knowledge graph construction method and device based on a unified road network, wherein the method comprises the steps of obtaining data of multiple data sources in the traffic management field; determining entities of multiple categories based on the data of multiple data sources, constructing a unified road network based on basic data in the data of multiple data sources, setting region classification and road network classification on the unified road network, and filling the entities of multiple categories and index data and labels of various entities into the unified road network to obtain a mode layer of a knowledge graph of the traffic management field; and writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field. By analyzing the entities and the relations in the traffic management field, the hierarchical road network, the index data and the labels are fused, the knowledge graph in the traffic management field is automatically constructed, the construction efficiency of the knowledge graph can be improved, and the labor cost is reduced.
Description
Technical Field
The invention relates to the technical field of traffic management, in particular to a traffic management field knowledge graph construction method and device based on a unified road network.
Background
The knowledge graph is a knowledge base which describes natural things by entities and relations, knowledge is composed of nodes and connecting lines, the nodes are called entities, and the connecting lines are called relations and are used for describing the relations between the two entities.
Aiming at the field of traffic management, the professional knowledge is strong, the data structure is complex, the information amount is huge, and the processing of traffic management events usually needs expert experience as guidance. Under the background, an expert knowledge base, namely a knowledge graph is constructed to guide application to become an effective way for solving business problems.
However, the manual construction of the knowledge graph is costly and time-consuming, so how to fuse expert experiences in the traffic management field and automatically construct the domain knowledge graph from massive traffic management service data becomes a problem to be solved urgently.
Disclosure of Invention
The embodiment of the invention provides a traffic management field knowledge graph construction method and device based on a unified road network, which are used for automatically constructing a knowledge graph, reducing the labor cost and improving the construction efficiency of the knowledge graph.
In a first aspect, an embodiment of the present invention provides a method for constructing a knowledge graph in a traffic management field based on a unified road network, including:
acquiring data of multiple data sources in the traffic management field; determining a plurality of categories of entities based on the data of the plurality of data sources;
constructing a unified road network based on basic data in the data of the multiple data sources, and setting regional grading and road network grading on the unified road network;
filling the entities of the multiple categories and the index data and the labels of the entities into the unified road network to obtain a mode layer of the knowledge graph of the traffic management field;
and writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field.
According to the technical scheme, the entities and the relations in the traffic management field are analyzed, the hierarchical road network, the index data and the labels are fused, the knowledge graph in the traffic management field is automatically constructed, the construction efficiency of the knowledge graph can be improved, and the labor cost is reduced.
Optionally, constructing a unified road network based on the basic data in the data of the multiple data sources includes:
generating a basic road section according to link (line) level road network data of the bottom road section of the basic data;
mounting all equipment and installation points on the basic road section;
and on the basis of a route matching algorithm, performing correlation matching on the basic road section and link-level data of the internet to obtain the unified road network.
Optionally, the generating a basic road segment according to the link-level road network data of the bottom road segment of the basic data includes:
for the links separated from the road network data, merging nodes which are positioned in a first preset range and are connected with only one link into one node to obtain the road network data which has all the nodes and meets the topological relation;
determining whether links entering or exiting from the nodes in the road network data which have the nodes and meet the topological relation belong to the same road, and if not, marking the nodes as suspected intersection nodes;
merging the suspected intersection nodes in the second preset range to obtain intersection node data;
and determining the shortest route in the intersection node data as a basic road section according to a shortest route algorithm.
Optionally, the filling the unified road network with the entities of the multiple categories and the index data and the labels of the entities of the various categories to obtain the mode layer of the knowledge graph of the traffic management field includes:
integrating dynamic data in the data of the multiple data sources to obtain index data of various entities;
analyzing dynamic data in the data of the multiple data sources to generate labels of various entities;
and after writing various entities into the unified road network, mounting the index data and the labels of the various entities on the various entities in the unified road network to obtain a mode layer of the knowledge graph of the traffic management field.
Optionally, writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field, where the method includes:
preprocessing the data of the multiple data sources;
dividing the preprocessed data into a plurality of batches;
and synchronizing the data of a plurality of batches to a mode layer of the knowledge graph of the traffic management field according to an entity signature strategy to obtain the knowledge graph of the traffic management field.
Optionally, the dividing the preprocessed data into a plurality of batches includes:
determining whether the preprocessed data has an updating identification bit, if so, dividing the preprocessed data into a batch according to updating time;
and if the data does not exist, dividing the data according to the preset data quantity to obtain data of a plurality of batches.
In a second aspect, an embodiment of the present invention provides a traffic management domain knowledge graph constructing apparatus based on a unified road network, including:
the acquisition unit is used for acquiring data of multiple data sources in the traffic management field; determining a plurality of categories of entities based on the data of the plurality of data sources;
the processing unit is used for constructing a unified road network based on basic data in the data of the multiple data sources and setting regional grading and road network grading on the unified road network; filling the entities of the multiple categories and the index data and the labels of the entities into the unified road network to obtain a mode layer of the knowledge graph of the traffic management field; and writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field.
Optionally, the processing unit is specifically configured to:
generating a basic road section according to link-level road network data of the bottom road section of the basic data;
mounting all equipment and installation points on the basic road section;
and on the basis of a route matching algorithm, performing correlation matching on the basic road section and link-level data of the internet to obtain the unified road network.
Optionally, the processing unit is specifically configured to:
for the links separated from the road network data, merging nodes which are positioned in a first preset range and are connected with only one link into one node to obtain the road network data which has all the nodes and meets the topological relation;
determining whether links entering or exiting from the nodes in the road network data which have the nodes and meet the topological relation belong to the same road, and if not, marking the nodes as suspected intersection nodes;
merging the suspected intersection nodes in the second preset range to obtain intersection node data;
and determining the shortest route in the intersection node data as a basic road section according to a shortest route algorithm.
Optionally, the processing unit is specifically configured to:
integrating dynamic data in the data of the multiple data sources to obtain index data of various entities;
analyzing dynamic data in the data of the multiple data sources to generate labels of various entities;
and after writing various entities into the unified road network, mounting the index data and the labels of the various entities on the various entities in the unified road network to obtain a mode layer of the knowledge graph of the traffic management field.
Optionally, the processing unit is specifically configured to:
preprocessing the data of the multiple data sources;
dividing the preprocessed data into a plurality of batches;
and synchronizing the data of a plurality of batches to a mode layer of the knowledge graph of the traffic management field according to an entity signature strategy to obtain the knowledge graph of the traffic management field.
Optionally, the processing unit is specifically configured to:
determining whether the preprocessed data has an updating identification bit, if so, dividing the preprocessed data into a batch according to updating time;
and if the data does not exist, dividing the data according to the preset data quantity to obtain data of a plurality of batches.
In a third aspect, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the intersection management domain knowledge graph construction method based on the unified road network according to the obtained program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable non-volatile storage medium, which includes computer-readable instructions, and when the computer reads and executes the computer-readable instructions, the computer is caused to execute the method for building a traffic management domain knowledge graph based on a unified road network.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic diagram of a system architecture according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a traffic management domain knowledge graph construction method based on a unified road network according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a region hierarchy and a road network hierarchy according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating data synchronization according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a traffic management domain knowledge graph construction device based on a unified road network according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a system architecture provided in an embodiment of the present invention. As shown in fig. 1, the system architecture may be a server 100, and the server 100 may include a processor 110, a communication interface 120, and a memory 130.
The communication interface 120 is used for communicating with other terminal devices, and transceiving information transmitted by the other terminal devices to implement communication.
The processor 110 is a control center of the server 100, connects various parts of the entire server 100 using various interfaces and lines, performs various functions of the server 100 and processes data by running or executing software programs and/or modules stored in the memory 130 and calling data stored in the memory 130. Alternatively, processor 110 may include one or more processing units.
The memory 130 may be used to store software programs and modules, and the processor 110 executes various functional applications and data processing by operating the software programs and modules stored in the memory 130. The memory 130 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to a business process, and the like. Further, the memory 130 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
It should be noted that the structure shown in fig. 1 is only an example, and the embodiment of the present invention is not limited thereto.
Based on the above description, fig. 2 shows in detail a flow of the unified road network-based traffic management domain knowledge graph construction method according to the embodiment of the present invention, where the flow may be executed by the unified road network-based traffic management domain knowledge graph construction apparatus.
As shown in fig. 2, the process specifically includes:
In the embodiment of the invention, the traffic management field has rich data sources, including basic data: the dynamic data comprises data uploaded by a detector, alarm data of traffic management departments, GPS data and the like, and the static data comprises vehicles, drivers, six-in-one law violation, accidents and the like, and also comprises service data accumulated by each service system and external data such as public sentiments, weather and the like accessed from the Internet.
The data of multiple data sources in the traffic management field can be combed to generalize into multiple categories of entities, such as entities of five categories of people, assets, places, events and organizations.
Specifically, a basic road section is generated according to the line link-level road network data of the bottom road section of the basic data; mounting all equipment and installation points on the basic road section; and performing correlation matching on the basic road section and link-level data of the internet based on a route matching algorithm to obtain the unified road network.
When the basic road section is generated, for the links separated from the road network data, the nodes which are located in a first preset range and only connected by one link are combined into one node, and the road network data which has all the nodes and meets the topological relation is obtained. And determining whether links entering or exiting from the nodes in the road network data which have the nodes and meet the topological relation belong to the same road, and if not, marking the nodes as suspected intersection nodes. Merging the suspected intersection nodes in the second preset range to obtain intersection node data; and determining the shortest route in the intersection node data as a basic road section according to a shortest route algorithm.
The first preset range and the second preset range may be set empirically. After the basic road section is determined, the topological rule verification can be performed on the basic road section for accurate data and avoidance of road section overlapping. The verified basic road segment is the final result.
On the basis of the unified road network constructed in the above manner, regional classification and road network classification can be set.
As shown in fig. 3, in the area hierarchy, the top level is a city, and the next level is a prefecture, which is further divided into each key area.
In the road network classification, the top layer is a road entity, the next level is a road section and an intersection, the road section is a section of road between two physical intersections, and the road sections are connected through the intersections. The next level is a link entity, the link entity is used for dividing the road sections in a finer granularity mode, and the link entity is introduced into the map, so that the mutation event can be positioned more accurately. POI is introduced into the traffic map as a key point entity, can assist the positioning of traffic events and enrich road network information. The road network relationship can be shown in table 1.
TABLE 1
The method comprises the steps that indexes and labels can be mounted on a uniform road network after regional classification and road network classification are set, dynamic data in data of multiple data sources are integrated, and index data of various entities are obtained; analyzing dynamic data in data of multiple data sources to generate labels of various entities; and after writing the various entities into the unified road network, mounting the index data and the labels of the various entities onto the various entities in the unified road network to obtain a mode layer of the knowledge graph in the traffic management field.
Taking mounting points and equipment for mounting as an example, the mounting points and the equipment are mounted on a road network, the first-level corresponding relation of the mounting points is a road section and an intersection, and the first-level corresponding relation of the equipment is the mounting points. Based on the unified road network, the relationship between the equipment and the installation points and the roads can be inferred, as shown in table 2.
TABLE 2
| Entity one | Entity two | Relationships between | Corresponding mode |
| Mounting point | Road section | Is located at | Many-to-one |
| Mounting point | Crossing | Is located at | Many-to-one |
| Device | Mounting point | Is mounted on | Many-to-one |
For dynamic data such as driving data, gps and the like, the data size is huge, the timeliness is strong, and the data is difficult to be represented and stored graphically. Aiming at the situation, various algorithms are adopted to process dynamic data, the dynamic data are integrated into indexes representing certain data characteristics and are mounted on various entities, so that an index system is formed and used for tracking the real-time state of each entity, and part of indexes are shown in table 3.
TABLE 3
And (3) updating each index of each type of entity as an entity index attribute into the map in real time, and constructing the knowledge map of the traffic management field fused with the real-time index system.
And generating various entity related labels through rule discrimination and algorithm identification, using the labels as entity label attributes of the traffic management map, writing the labels into the map, and not only limiting the labels to vehicles. The labels of the vehicles are shown in table 4, taking the vehicles as an example.
TABLE 4
Based on the information, the final mode layer of the knowledge graph in the traffic management field can be obtained.
And 204, writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field.
And when the mode layer construction of the knowledge graph in the traffic management field is completed, data filling is required. At this time, the data of multiple data sources needs to be preprocessed, and then the preprocessed data is divided into multiple batches. And finally, synchronizing the data of a plurality of batches to a mode layer of the knowledge graph of the traffic management field according to an entity signature strategy to obtain the knowledge graph of the traffic management field.
During preprocessing, the method mainly comprises data cleaning, data enhancement, data fusion and the like.
Wherein, data cleaning: the following data were mainly excluded: 1. data type error 2, outlier 3, duplicate data
Data enhancement: and for the entity with the missing key field, adopting a natural language processing technology to extract relevant information from the description field as supplement. And for the entity with missing coordinates, adopting a geocoding technology for position supplement.
Data fusion: and (3) fusing similar data such as illegal and accident data according to an event similarity algorithm, and fusing entities with similarity reaching a threshold into one entity.
After preprocessing the data of multiple data sources, batching the data, mainly determining whether the preprocessed data has an updating identification bit, and if so, dividing the preprocessed data into batches according to the updating time; and if the data does not exist, dividing the data according to the preset data quantity to obtain data of a plurality of batches.
Because the map bottom layer stores the selective map database, source data are written in by each source through the map synchronous adapter. The method mainly has two problems, namely, the data synchronization range is determined, and the real-time monitoring of the data ensures that each tiny change (increase, delete, change and check) is synchronized.
The data can be classified according to the data synchronization range, and the data is classified into two types according to whether the updating zone bit exists or not, wherein one type is the zone bit-free data, and the data needs to be updated in a full amount every time, such as a vehicle table, a driver table, a road table and the like. The data volume of a part of tables needing to be updated in full volume is huge, so that a batch processing strategy is formulated, and each batch contains a fixed data volume; the other type is data with an update mark, such as illegal and accident, the latest changed data can be confirmed according to the update time, the data in the range needs to be updated synchronously every time, and the data is limited in data volume and can be read in as a batch.
Aiming at the synchronization of data, an entity signature strategy can be adopted, an entity signature is generated for each entity and is stored in a signature library, whether the signature exists in the signature library is checked before the data are synchronized each time, if the signature exists, the data are synchronized before, the data are filtered; if the data does not exist, the data base corresponding entity is updated, and the signature base is updated. The specific process of data synchronization may be as shown in fig. 4, and specifically includes:
and step 401, deleting the expired entity.
And the data of the knowledge graph is ensured to be updated in real time for the expired entities to be deleted.
At step 402, the entity tag is deleted.
After the expired entity is deleted, the corresponding entity tag is also deleted.
At step 403, the data is batched.
The data is divided into two types according to whether the updating zone bit exists or not, wherein one type is the zone bit-free data, and the data needs to be updated in full quantity every time, such as a vehicle table, a driver table, a road table and the like. The data volume of a part of tables needing to be updated in full volume is huge, so that a batch processing strategy is formulated, and each batch contains a fixed data volume; the other type is data with an update mark, such as illegal and accident, the latest changed data can be confirmed according to the update time, the data in the range needs to be updated synchronously every time, and the data is limited in data volume and can be read in as a batch.
And acquiring data of the current batch.
At step 405, an entity signature is generated.
And generating an entity signature for each entity of the data of the current batch by adopting an entity signature strategy.
And determining whether each entity of the data of the current batch is repeated, and directly updating the label without repetition.
Data in the graph database needs to be updated corresponding to the duplicated entities.
And correspondingly updating the signature library of the repeated entity to indicate that the repeated entity is updated.
The tag data for each entity is updated.
And step 410, rebuilding the relation.
And performing relation reconstruction corresponding to the updated entity.
Step 411, determine whether the next batch of data is empty, if yes, end, otherwise go to step 412.
At step 412, a batch of data is removed.
And continuously acquiring the next batch of data.
Based on the steps, a complete knowledge graph of the traffic management field can be obtained, a hierarchical road network and an index system are fused through the combing of entities and relations of the traffic management field, personalized labels of various entities are added, the complete knowledge graph of the traffic management field is finally constructed, the complete knowledge graph is applied to the modeling of vehicle portraits, driver portraits, intersection portraits and the like, the urban traffic element holographic portraits are created, and the portrait is served for portrayal display in a control system; and 3, reasoning and discovering a new relationship by combining a reasoning rule base, and applying the new relationship to systems such as police service supervision and the like.
In the embodiment of the invention, data of multiple data sources in the traffic management field are acquired; determining entities of multiple categories based on the data of multiple data sources, constructing a unified road network based on basic data in the data of multiple data sources, setting region classification and road network classification on the unified road network, and filling the entities of multiple categories and index data and labels of various entities into the unified road network to obtain a mode layer of a knowledge graph of the traffic management field; and writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field. By analyzing the entities and the relations in the traffic management field, the hierarchical road network, the index data and the labels are fused, the knowledge graph in the traffic management field is automatically constructed, the construction efficiency of the knowledge graph can be improved, and the labor cost is reduced.
Based on the same technical concept, fig. 5 exemplarily shows a structure of a traffic management domain knowledge graph construction apparatus based on a unified road network according to an embodiment of the present invention, and the apparatus can execute a traffic management domain knowledge graph construction process based on a unified road network.
As shown in fig. 5, the apparatus specifically includes:
the acquiring unit 501 is configured to acquire data of multiple data sources in the traffic management field; determining a plurality of categories of entities based on the data of the plurality of data sources;
a processing unit 502, configured to construct a unified road network based on basic data in the data of multiple data sources, and set a region classification and a road network classification on the unified road network; filling the entities of the multiple categories and the index data and the labels of the entities into the unified road network to obtain a mode layer of the knowledge graph of the traffic management field; and writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field.
Optionally, the processing unit 502 is specifically configured to:
generating a basic road section according to link-level road network data of the bottom road section of the basic data;
mounting all equipment and installation points on the basic road section;
and on the basis of a route matching algorithm, performing correlation matching on the basic road section and link-level data of the internet to obtain the unified road network.
Optionally, the processing unit 502 is specifically configured to:
for the links separated from the road network data, merging nodes which are positioned in a first preset range and are connected with only one link into one node to obtain the road network data which has all the nodes and meets the topological relation;
determining whether links entering or exiting from the nodes in the road network data which have the nodes and meet the topological relation belong to the same road, and if not, marking the nodes as suspected intersection nodes;
merging the suspected intersection nodes in the second preset range to obtain intersection node data;
and determining the shortest route in the intersection node data as a basic road section according to a shortest route algorithm.
Optionally, the processing unit 502 is specifically configured to:
integrating dynamic data in the data of the multiple data sources to obtain index data of various entities;
analyzing dynamic data in the data of the multiple data sources to generate labels of various entities;
and after writing various entities into the unified road network, mounting the index data and the labels of the various entities on the various entities in the unified road network to obtain a mode layer of the knowledge graph of the traffic management field.
Optionally, the processing unit 502 is specifically configured to:
preprocessing the data of the multiple data sources;
dividing the preprocessed data into a plurality of batches;
and synchronizing the data of a plurality of batches to a mode layer of the knowledge graph of the traffic management field according to an entity signature strategy to obtain the knowledge graph of the traffic management field.
Optionally, the processing unit 502 is specifically configured to:
determining whether the preprocessed data has an updating identification bit, if so, dividing the preprocessed data into a batch according to updating time;
and if the data does not exist, dividing the data according to the preset data quantity to obtain data of a plurality of batches.
Based on the same technical concept, an embodiment of the present invention further provides a computing device, including:
a memory for storing program instructions;
and the processor is used for calling the program instructions stored in the memory and executing the intersection management domain knowledge graph construction method based on the unified road network according to the obtained program.
Based on the same technical concept, the embodiment of the invention also provides a computer-readable non-volatile storage medium, which comprises computer-readable instructions, and when the computer reads and executes the computer-readable instructions, the computer is enabled to execute the method for constructing the traffic management domain knowledge graph based on the unified road network.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A traffic management field knowledge graph construction method based on a unified road network is characterized by comprising the following steps:
acquiring data of multiple data sources in the traffic management field; determining a plurality of categories of entities based on the data of the plurality of data sources;
constructing a unified road network based on basic data in the data of the multiple data sources, and setting regional grading and road network grading on the unified road network;
filling the entities of the multiple categories and the index data and the labels of the entities into the unified road network to obtain a mode layer of the knowledge graph of the traffic management field;
and writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field.
2. The method of claim 1, wherein constructing a unified road network based on underlying data in the data from the multiple data sources comprises:
generating a basic road section according to the line link-level road network data of the bottom road section of the basic data;
mounting all equipment and installation points on the basic road section;
and on the basis of a route matching algorithm, performing correlation matching on the basic road section and link-level data of the internet to obtain the unified road network.
3. The method as claimed in claim 2, wherein the generating of the base segment from the road network data of the line link level of the underlying segment of the base data comprises:
for the links separated from the road network data, merging nodes which are positioned in a first preset range and are connected with only one link into one node to obtain the road network data which has all the nodes and meets the topological relation;
determining whether links entering or exiting from the nodes in the road network data which have the nodes and meet the topological relation belong to the same road, and if not, marking the nodes as suspected intersection nodes;
merging the suspected intersection nodes in the second preset range to obtain intersection node data;
and determining the shortest route in the intersection node data as a basic road section according to a shortest route algorithm.
4. The method according to claim 1, wherein the populating the unified road network with the index data and labels of the entities of the plurality of categories and the entities of the various categories to obtain the model layer of the knowledge graph of the traffic management domain comprises:
integrating dynamic data in the data of the multiple data sources to obtain index data of various entities;
analyzing dynamic data in the data of the multiple data sources to generate labels of various entities;
and after writing various entities into the unified road network, mounting the index data and the labels of the various entities on the various entities in the unified road network to obtain a mode layer of the knowledge graph of the traffic management field.
5. The method of any of claims 1 to 4, wherein writing data of the multiple data sources to a schema layer of a knowledge graph of the traffic management domain to obtain the knowledge graph of the traffic management domain comprises:
preprocessing the data of the multiple data sources;
dividing the preprocessed data into a plurality of batches;
and synchronizing the data of a plurality of batches to a mode layer of the knowledge graph of the traffic management field according to an entity signature strategy to obtain the knowledge graph of the traffic management field.
6. The method of claim 5, wherein the dividing the pre-processed data into a plurality of batches comprises:
determining whether the preprocessed data has an updating identification bit, if so, dividing the preprocessed data into a batch according to updating time;
and if the data does not exist, dividing the data according to the preset data quantity to obtain data of a plurality of batches.
7. The utility model provides a traffic control field knowledge map construction equipment based on unified road network which characterized in that includes:
the acquisition unit is used for acquiring data of multiple data sources in the traffic management field; determining a plurality of categories of entities based on the data of the plurality of data sources;
the processing unit is used for constructing a unified road network based on basic data in the data of the multiple data sources and setting regional grading and road network grading on the unified road network; filling the entities of the multiple categories and the index data and the labels of the entities into the unified road network to obtain a mode layer of the knowledge graph of the traffic management field; and writing the data of the multiple data sources into a mode layer of the knowledge graph of the traffic management field to obtain the knowledge graph of the traffic management field.
8. The apparatus as claimed in claim 7, wherein said processing unit is specifically configured to:
generating a basic road section according to the line link-level road network data of the bottom road section of the basic data;
mounting all equipment and installation points on the basic road section;
and on the basis of a route matching algorithm, performing correlation matching on the basic road section and link-level data of the internet to obtain the unified road network.
9. A computing device, comprising:
a memory for storing program instructions;
a processor for calling program instructions stored in said memory to execute the method of any one of claims 1 to 6 in accordance with the obtained program.
10. A computer-readable non-transitory storage medium including computer-readable instructions which, when read and executed by a computer, cause the computer to perform the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110177130.2A CN112818071A (en) | 2021-02-09 | 2021-02-09 | Traffic management field knowledge graph construction method and device based on unified road network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110177130.2A CN112818071A (en) | 2021-02-09 | 2021-02-09 | Traffic management field knowledge graph construction method and device based on unified road network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112818071A true CN112818071A (en) | 2021-05-18 |
Family
ID=75864646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110177130.2A Pending CN112818071A (en) | 2021-02-09 | 2021-02-09 | Traffic management field knowledge graph construction method and device based on unified road network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112818071A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658439A (en) * | 2021-07-21 | 2021-11-16 | 武汉理工大学 | Holographic intersection signal control autonomous optimization method |
| CN114328955A (en) * | 2021-12-17 | 2022-04-12 | 南京沃科电子科技有限公司 | Automobile electronic knowledge map control system |
| CN115083168A (en) * | 2022-08-23 | 2022-09-20 | 河北博士林科技开发有限公司 | Multi-level traffic simulation network construction method based on multi-source data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008413A (en) * | 2019-03-14 | 2019-07-12 | 海信集团有限公司 | A kind of traffic trip problem querying method and device |
| CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
| CN111160753A (en) * | 2019-12-25 | 2020-05-15 | 大连理工大学 | Knowledge graph-based road network node importance evaluation method |
| US20200410008A1 (en) * | 2019-06-27 | 2020-12-31 | International Business Machines Corporation | Auto generating reasoning query on a knowledge graph |
| CN112241424A (en) * | 2020-10-16 | 2021-01-19 | 中国民用航空华东地区空中交通管理局 | Air traffic control equipment application system and method based on knowledge graph |
-
2021
- 2021-02-09 CN CN202110177130.2A patent/CN112818071A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008413A (en) * | 2019-03-14 | 2019-07-12 | 海信集团有限公司 | A kind of traffic trip problem querying method and device |
| CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
| US20200410008A1 (en) * | 2019-06-27 | 2020-12-31 | International Business Machines Corporation | Auto generating reasoning query on a knowledge graph |
| CN111160753A (en) * | 2019-12-25 | 2020-05-15 | 大连理工大学 | Knowledge graph-based road network node importance evaluation method |
| CN112241424A (en) * | 2020-10-16 | 2021-01-19 | 中国民用航空华东地区空中交通管理局 | Air traffic control equipment application system and method based on knowledge graph |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113658439A (en) * | 2021-07-21 | 2021-11-16 | 武汉理工大学 | Holographic intersection signal control autonomous optimization method |
| CN114328955A (en) * | 2021-12-17 | 2022-04-12 | 南京沃科电子科技有限公司 | Automobile electronic knowledge map control system |
| CN115083168A (en) * | 2022-08-23 | 2022-09-20 | 河北博士林科技开发有限公司 | Multi-level traffic simulation network construction method based on multi-source data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112818071A (en) | Traffic management field knowledge graph construction method and device based on unified road network | |
| CN106323301B (en) | Method and device for acquiring road information | |
| KR101815511B1 (en) | Framework for Traffic Simulation and Method for Simulation using Framework | |
| CN109754594A (en) | A kind of road condition information acquisition method and its equipment, storage medium, terminal | |
| WO2022227303A1 (en) | Information processing method and apparatus, computer device, and storage medium | |
| CN107704531B (en) | Automatic merging method for road network intersection nodes in OSM map data | |
| Shoman et al. | Deep learning framework for predicting bus delays on multiple routes using heterogenous datasets | |
| CN111383444B (en) | Method, device, server and storage medium for predicting road condition state | |
| CN114707035A (en) | Visual traffic initial point analysis system | |
| CN114969263A (en) | Construction method, construction device and application of urban traffic knowledge map | |
| William et al. | Edge based Web Computing for Traffic Control Management for Distributed Environment Conditions | |
| CN117150635B (en) | Multi-level road network construction method and device, electronic equipment and storage medium | |
| Tchuente et al. | Providing more regular road signs infrastructure updates for connected driving: A crowdsourced approach with clustering and confidence level | |
| CN116822627A (en) | Construction method of urban traffic knowledge graph | |
| CN111653115B (en) | Task dividing method and device and storage medium | |
| Wang et al. | Grid mapping for road network abstraction and traffic congestion identification based on probe vehicle data | |
| JP3621286B2 (en) | Road map vectorization method and apparatus | |
| Brown et al. | Vision-Based Methodology to Create a Highway Asset Inventory for Integration in a Digital Twin Model | |
| Volkov et al. | Spatio-temporal Data Sources Integration with Ontology for Road Accidents Analysis | |
| Zhao et al. | Spatiotemporal analysis of trajectory for a new real-time bus routes updated model | |
| Savosin et al. | Estimation and Aggregation Method of Open Data Sources for Road Accident Analysis | |
| Zilske | Transparent and versatile traffic simulation: Supply data, demand data, and software architecture | |
| CN106781482A (en) | Novel intelligent traffic data processing system | |
| Gunda | Network-wide traffic congestion visual analytics: A case study for Brisbane Bluetooth MAC scanner data | |
| US20220180741A1 (en) | Method, apparatus and computer program product for detecting a lane closure using probe data |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210518 |