CN113779429A - Traffic congestion situation prediction method, device, equipment and storage medium - Google Patents
Traffic congestion situation prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113779429A CN113779429A CN202111095934.4A CN202111095934A CN113779429A CN 113779429 A CN113779429 A CN 113779429A CN 202111095934 A CN202111095934 A CN 202111095934A CN 113779429 A CN113779429 A CN 113779429A
- Authority
- CN
- China
- Prior art keywords
- traffic
- data
- target
- preset
- text data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000004458 analytical method Methods 0.000 claims abstract description 25
- 238000010586 diagram Methods 0.000 claims description 38
- 230000011218 segmentation Effects 0.000 claims description 27
- 239000013598 vector Substances 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000007499 fusion processing Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001052 transient effect Effects 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Navigation (AREA)
Abstract
The invention relates to the technical field of big data, and discloses a traffic congestion situation prediction method, a device, equipment and a storage medium, which are used for improving the accuracy of constructing a traffic congestion semantic association relation. The traffic jam situation prediction method comprises the following steps: extracting target text data from a preset user microblog webpage, wherein the target text data are used for describing microblog text data of a target city traffic condition; carrying out named entity recognition on the target text data through a preset traffic entity recognition model to obtain target entity data; performing semantic analysis on target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information; and sending the traffic jam path information to the navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information. In addition, the invention also relates to a block chain technology, and the traffic jam path information can be stored in the block chain nodes.
Description
Technical Field
The invention relates to the technical field of intelligent recommendation of big data, in particular to a traffic congestion situation prediction method, a traffic congestion situation prediction device, traffic congestion situation prediction equipment and a storage medium.
Background
In real life, traffic jam has no clear definition, which is mainly a psychological feeling of people, and the most direct method is to verify the feeling of people on traffic conditions, wherein the judgment on the traffic conditions is accurate. In recent years, the search for new fields by data mining and geographic information technology has become a new direction of geographic research. Social media is characterized by the participation of a large number of internet users. The wide use of microblogs provides a large number of sources for social media data, and microblog users can share personal information such as daily life and emotion. Each microblog has release time, content, longitude and latitude and the like. Therefore, the traffic condition of the user at any time and any place can be accurately obtained by analyzing the corresponding microblog information content.
In the construction of the semantic association relationship, a common method is a graph neural network GNN, which is a strong graph data deep representation learning method, but in the heterogeneous information network field containing different nodes and edges, the accuracy of the GNN in the construction of the semantic association relationship is low.
Disclosure of Invention
The invention provides a traffic jam situation prediction method, a device, equipment and a storage medium, which are used for improving the accuracy of constructing a traffic jam semantic association relation.
To achieve the above object, a first aspect of the present invention provides a traffic congestion situation prediction method, including: extracting target text data from a preset user microblog webpage, wherein the target text data are used for describing microblog text data of a target city traffic condition; carrying out named entity recognition on the target text data through a preset traffic entity recognition model to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to a traffic jam situation; performing semantic analysis on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information; and sending the traffic jam path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information.
Optionally, in a first implementation manner of the first aspect of the present invention, the extracting target text data from a preset user microblog webpage, where the target text data is microblog text data for describing a target urban traffic condition, includes: acquiring initial text data from a preset user microblog webpage according to preset microblog registration data through a preset data acquisition task; when the initial text data is not null, sequentially performing text error correction and segmentation processing on the initial text data to obtain a plurality of segmented text data; performing word segmentation processing and part-of-speech tagging on the segmented text data respectively to obtain a plurality of text word segmentations, and matching the text word segmentations according to preset traffic keywords to obtain at least one matched word segmentations; and screening the segmented text data according to the at least one matched word segmentation to obtain target text data, wherein the target text data is used for describing microblog text data of traffic conditions.
Optionally, in a second implementation manner of the first aspect of the present invention, the performing named entity recognition on the target text data through a preset traffic entity recognition model to obtain target entity data, where the target entity data is used to indicate a multidimensional entity object related to a traffic congestion situation, and the method includes: performing text preprocessing on the target text data to obtain processed text data; performing text vectorization on the processed text data through a word vector conversion network in a preset traffic entity recognition model to obtain a plurality of text vectors; and calling an entity identification network in the preset traffic entity identification model to perform mapping transformation and entity relationship extraction on the plurality of text vectors to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to the traffic jam situation.
Optionally, in a third implementation manner of the first aspect of the present invention, the performing semantic analysis on the target entity data through the trained heteromorphic image attention network model to obtain traffic jam path information includes: mapping a multi-dimensional entity object in the target entity data to the same feature space through a node level attention neural network in a trained heteromorphic graph attention network model to obtain a plurality of nodes, wherein each node is used for vector representation; converting the plurality of nodes into a plurality of meta-paths according to a preset semantic path type, and respectively carrying out weight calculation on the node pairs in each meta-path to obtain a plurality of node weights, wherein each node weight is used for indicating the semantic relevance of any two nodes; and performing semantic fusion processing on the plurality of nodes and the plurality of node weights through a semantic level attention neural network in the trained heteromorphic image attention network model to obtain traffic jam path information.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the sending the traffic congestion path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic congestion path information includes: packaging the traffic jam path information into a message to be sent, and writing the message to be sent into a preset message sending queue; judging whether the preset message sending queue is not a null value or not through a preset timing task; if the preset message sending queue is not null, sending the message to be sent to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information; and acquiring a data receiving result returned by the navigation terminal, and removing the message to be sent from the preset message sending queue when the data receiving result is successful.
Optionally, in a fifth implementation manner of the first aspect of the present invention, before extracting target text data from a preset user microblog webpage, where the target text data is microblog text data describing a target urban traffic condition, the method for predicting a traffic congestion situation further includes: acquiring heterogeneous pattern data, wherein the heterogeneous pattern data is used for indicating information of a plurality of node connection paths related to the traffic jam state content; and training an initial heteromorphic image attention network model based on a gradient descent algorithm and the isomorphic image sample data until the loss function value is less than or equal to a preset threshold value to obtain the trained heteromorphic image attention network model.
Optionally, in a sixth implementation manner of the first aspect of the present invention, after the sending the traffic congestion path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic congestion path information, the method for predicting a traffic congestion situation further includes: acquiring a traffic jam time period, and storing the new driving route, the traffic jam time period and the traffic jam path information into a preset data table; receiving a traffic thermodynamic diagram generation request sent by a target terminal, performing data analysis and thermodynamic diagram generation processing on the preset data table according to the traffic thermodynamic diagram generation request to obtain traffic thermodynamic diagram data, and sending the traffic thermodynamic diagram data to the target terminal.
A second aspect of the present invention provides a traffic congestion situation prediction apparatus, including: the extraction module is used for extracting target text data from a preset user microblog webpage, wherein the target text data are used for describing microblog text data of a target city traffic condition; the identification module is used for carrying out named entity identification on the target text data through a preset traffic entity identification model to obtain target entity data, and the target entity data is used for indicating a multi-dimensional entity object related to a traffic jam situation; the analysis module is used for carrying out semantic analysis on the target entity data through the trained heteromorphic image attention network model to obtain traffic jam path information; and the sending module is used for sending the traffic jam path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information.
Optionally, in a first implementation manner of the second aspect of the present invention, the extracting module is specifically configured to: acquiring initial text data from a preset user microblog webpage according to preset microblog registration data through a preset data acquisition task; when the initial text data is not null, sequentially performing text error correction and segmentation processing on the initial text data to obtain a plurality of segmented text data; performing word segmentation processing and part-of-speech tagging on the segmented text data respectively to obtain a plurality of text word segmentations, and matching the text word segmentations according to preset traffic keywords to obtain at least one matched word segmentations; and screening the segmented text data according to the at least one matched word segmentation to obtain target text data, wherein the target text data is used for describing microblog text data of traffic conditions.
Optionally, in a second implementation manner of the second aspect of the present invention, the identification module is specifically configured to: performing text preprocessing on the target text data to obtain processed text data; performing text vectorization on the processed text data through a word vector conversion network in a preset traffic entity recognition model to obtain a plurality of text vectors; and calling an entity identification network in the preset traffic entity identification model to perform mapping transformation and entity relationship extraction on the plurality of text vectors to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to the traffic jam situation.
Optionally, in a third implementation manner of the second aspect of the present invention, the analysis module is specifically configured to: mapping a multi-dimensional entity object in the target entity data to the same feature space through a node level attention neural network in a trained heteromorphic graph attention network model to obtain a plurality of nodes, wherein each node is used for vector representation; converting the plurality of nodes into a plurality of meta-paths according to a preset semantic path type, and respectively carrying out weight calculation on the node pairs in each meta-path to obtain a plurality of node weights, wherein each node weight is used for indicating the semantic relevance of any two nodes; and performing semantic fusion processing on the plurality of nodes and the plurality of node weights through a semantic level attention neural network in the trained heteromorphic image attention network model to obtain traffic jam path information.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the sending module is specifically configured to: packaging the traffic jam path information into a message to be sent, and writing the message to be sent into a preset message sending queue; judging whether the preset message sending queue is not a null value or not through a preset timing task; if the preset message sending queue is not null, sending the message to be sent to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information; and acquiring a data receiving result returned by the navigation terminal, and removing the message to be sent from the preset message sending queue when the data receiving result is successful.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the traffic congestion situation prediction apparatus further includes: the acquisition module is used for acquiring heterogeneous pattern data, and the heterogeneous pattern data is used for indicating information of a plurality of node connection paths related to the traffic jam state content; and the training module is used for training an initial heteromorphic image attention network model based on a gradient descent algorithm and the isomorphic image sample data until the loss function value is less than or equal to a preset threshold value, so that the trained heteromorphic image attention network model is obtained.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the traffic congestion situation prediction apparatus further includes: the storage module is used for acquiring a traffic jam time period and storing the new driving route, the traffic jam time period and the traffic jam path information into a preset data table; the generating module is used for receiving a traffic thermodynamic diagram generating request sent by a target terminal, performing data analysis and thermodynamic diagram generating processing on the preset data table according to the traffic thermodynamic diagram generating request to obtain traffic thermodynamic diagram data, and sending the traffic thermodynamic diagram data to the target terminal.
A third aspect of the present invention provides a traffic congestion situation prediction apparatus, including: a memory and at least one processor, the memory having stored therein a computer program; the at least one processor invokes the computer program in the memory to cause the traffic congestion situation prediction apparatus to execute the traffic congestion situation prediction method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute the above-described traffic congestion situation prediction method.
According to the technical scheme, target text data are extracted from a preset user microblog webpage, and the target text data are used for describing microblog text data of a target city traffic condition; carrying out named entity recognition on the target text data through a preset traffic entity recognition model to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to a traffic jam situation; performing semantic analysis on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information; and sending the traffic jam path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information. In the embodiment of the invention, named entity recognition is carried out on target text data in a preset user microblog webpage through a preset traffic entity recognition model to obtain target entity data, semantic analysis is carried out on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information, so that a navigation terminal plans a new driving route according to the traffic path information, and the accuracy of constructing the traffic jam semantic association relationship is improved.
Drawings
Fig. 1 is a schematic diagram of an embodiment of a traffic congestion situation prediction method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of another embodiment of a traffic congestion situation prediction method according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an embodiment of a traffic congestion situation prediction apparatus according to the embodiment of the present invention;
fig. 4 is a schematic diagram of another embodiment of a traffic congestion situation prediction apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of an embodiment of a traffic congestion situation prediction apparatus according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a traffic congestion situation prediction method, a traffic congestion situation prediction device, traffic congestion situation prediction equipment and a storage medium, which are used for performing data mining on microblog text data through an attention network model of a heteromorphic graph to obtain traffic congestion information and improve the accuracy of constructing a traffic congestion semantic association relation.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a detailed flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a traffic congestion situation prediction method according to an embodiment of the present invention includes:
101. target text data are extracted from a preset user microblog webpage, and the target text data are used for describing microblog text data of a target city traffic condition.
The preset user microblog webpage can be a traffic police microblog webpage or a social microblog webpage, and is not limited herein. The target text data may be "cheval traffic policeman: regarding the problem that students in the city primary school who go up and down to learn to cause road congestion in the west of the Yangtze river reflected by net friends, the traffic police team has already dealt with the traffic police, and the traffic police team can also be' traffic police in the city of the Yangtze river: the Yangtze river west road shopping center is always a key area for weekend traveling, has large weekend traffic, is easy to cause congestion, and can also be other text data, and is not limited in the specific points. Specifically, the server logs in a preset user microblog webpage at regular time according to preset user login information, the server crawls the preset user microblog webpage, filters and screens the acquired microblog text, screens out microblog text data related to traffic to obtain target text data, and the target text data are used for describing microblog text data of a target city traffic condition and are stored in a preset microblog database. The target city may be wuhan or nanjing, and is not limited herein.
It is to be understood that the execution subject of the present invention may be a traffic congestion situation prediction apparatus, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject.
102. And carrying out named entity identification on the target text data through a preset traffic entity identification model to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to the traffic jam situation.
The preset traffic entity recognition model comprises a word vector conversion network and an entity recognition network. Specifically, the server processes the screened microblog text data (i.e., the target text data) through a word vector conversion network (e.g., word2cec or bert), and extracts target entity data related to the traffic condition through an entity identification network (e.g., a long short term memory network LSTM or a bidirectional long short term memory network BiLSTM), where the target entity data includes various types, that is, the target entity data is used to indicate a multidimensional entity object related to the traffic congestion situation. For example: the multi-dimensional entity objects include time of day, place, weather, geographic event, and number of occurrences of related content, among others.
103. And performing semantic analysis on target entity data through the trained attention network model of the heteromorphic image to obtain traffic jam path information.
It can be understood that the server can quickly and accurately mine traffic jam information according to the constructed heterogeneous information network (i.e., the trained heterogeneous map attention network model) and provide traffic information for vehicle navigation. Specifically, the server inputs the multi-dimensional entity object into the trained heteromorphic image attention netIn the network model, a multi-dimensional entity object is mapped to the same characteristic space to obtain a plurality of nodes; and performing semantic fusion and path clustering analysis according to a preset semantic path type and a plurality of nodes through a node level attention neural network and a semantic level attention neural network in the trained heteromorphic image attention network model to obtain traffic jam path information. All entities are constructed into an attention network HAN of the heteromorphic image by calculating weights among the entities, the HAN is constructed into G ═ (V, E), and a plurality of nodes comprise microblog texts D ═ { D }1,d2,...,dmAt the place P ═ P }1,p2,...,pmT ═ T at time1,t2,...,tmAnd weather is S ═ S1,s2,...,smAnd so on. Each node is vugou.gtu.gtu.s. The geometry E of the edge represents the association between nodes, and two entity objects (i.e., any two nodes mapped to the same feature space) can be connected by different semantic paths (meta-paths) including the text-to-location dependency r1Text to semantic dependency r2Text to time dependency r3And the like. Further, the server stores the traffic congestion path information in a block chain database, which is not limited herein.
104. And sending the traffic jam path information to the navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information.
It can be understood that the server can quickly and accurately mine traffic jam information according to the trained heterogeneous graph attention network model, and provide traffic information for vehicle navigation. Specifically, the server sends the traffic jam path information to a preset message queue, sends the traffic jam path information to the navigation terminal through the preset message queue, and sets the traffic jam path information as a navigation element, so that the navigation terminal plans a new route according to the navigation element, and the new route is used for indicating a navigation path avoiding jam.
In the embodiment of the invention, named entity recognition is carried out on target text data in a preset user microblog webpage through a preset traffic entity recognition model to obtain target entity data, semantic analysis is carried out on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information, so that a navigation terminal plans a new driving route according to the traffic path information, and the accuracy of constructing the traffic jam semantic association relationship is improved.
Referring to fig. 2, another embodiment of the method for predicting a traffic congestion situation according to the embodiment of the present invention includes:
201. target text data are extracted from a preset user microblog webpage, and the target text data are used for describing microblog text data of a target city traffic condition.
It can be understood that the preset user microblog webpage contains the traffic condition information issued by the user. Optionally, the server acquires initial text data from a preset user microblog webpage according to preset microblog registration data through a preset data acquisition task; when the initial text data is not null, the server sequentially performs text error correction and segmentation processing on the initial text data to obtain a plurality of segmented text data; the server carries out word segmentation processing and part-of-speech tagging on the segmented text data respectively to obtain a plurality of text word segmentations, and matches the text word segmentations according to preset traffic keywords to obtain at least one matched word segmentations; and the server screens a plurality of segmented text data according to at least one matched word segmentation to obtain target text data, wherein the target text data is used for describing microblog text data of traffic conditions.
For example, the server may execute the preset data acquisition task every 30 minutes, or may execute the preset data acquisition task every 15 minutes, which is not limited herein. The preset data acquisition task acquires initial text data according to the issuing time of each topic microblog in the microblog webpage of the user in sequence, wherein the initial text data comprises information such as microblog text content, issuing time, issuers and issuing places. It should be noted that a preset user microblog webpage is an entry point, and a preset data acquisition task is used for acquiring microblog data of the user microblog webpage updated in real time, so that the problems of limited logging in of microblogs and real-time updating of microblog data can be solved.
Further, before step 201, the server obtains heterogeneous pattern data, where the heterogeneous pattern data is used to indicate information of a plurality of node connection paths related to the content of the traffic congestion state; the server trains an initial heteromorphic image attention network model based on a gradient descent algorithm and the isomorphic image sample data until a loss function value is smaller than or equal to a preset threshold value, and a trained heteromorphic image attention network model is obtained.
202. And carrying out named entity identification on the target text data through a preset traffic entity identification model to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to the traffic jam situation.
As can be appreciated, the target entity data is used to indicate a multi-dimensional entity object that is relevant to a traffic congestion situation. For example, the time is when the student gets on or off school or on weekends, and the location is school or shopping center, so that traffic jam condition is easy to occur. Further, the server inputs the entity data identified in the target text data into a preset traffic entity identification model through a semi-supervised learning mode, continues to identify the entity objects in the residual microblog text data in the target text data, and stops named entity identification until the entity objects in the residual microblog text data are null values.
Optionally, the server performs text preprocessing on the target text data to obtain processed text data; the server carries out text vectorization on the processed text data through a word vector conversion network in a preset traffic entity recognition model to obtain a plurality of text vectors; and the server calls an entity identification network in a preset traffic entity identification model to perform mapping transformation and entity relationship extraction on the plurality of text vectors to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to the traffic jam situation. For example, the server screens out target text data having a word count smaller than a preset word count and/or removes y preset punctuation symbols and preset emoticons in the target text data. The number of the preset words may be 3, or may also be 4, and is not limited herein. In addition, the target text data comprises a plurality of microblog text data, the server analyzes the similarity between any two microblog text data, if the similarity between any two microblog text data is higher than a preset threshold value, the server determines that any two microblog text data are the same microblog content, and subjects of any two microblog text data are subjected to duplicate removal.
203. And performing semantic analysis on target entity data through the trained attention network model of the heteromorphic image to obtain traffic jam path information.
Different meta paths in the heterogeneous pattern data are used for extracting different semantic information, and different nodes can be connected through various different relations. The server learns the node-level weight and the semantic-level weight in the initial heterogeneous graph attention network model based on the attention mechanism and the heterogeneous graph body data, so that the heterogeneous graph attention network model HAN is constructed, and relevant information related to traffic jam is excavated according to the constructed heterogeneous graph attention network model. Optionally, the server maps the multidimensional entity object in the target entity data to the same feature space through a trained node-level attention neural network in the heteromorphic graph attention network model to obtain a plurality of nodes, wherein each node is used for vector representation; the server converts the multiple nodes into multiple meta-paths according to a preset semantic path type, and performs weight calculation on node pairs in each meta-path respectively to obtain multiple node weights, wherein each node weight is used for indicating semantic relevance of any two nodes; and the server performs semantic fusion processing on the plurality of nodes and the plurality of node weights through a semantic level attention neural network in the trained heteromorphic image attention network model to obtain traffic jam path information.
It should be noted that, the weight of the node pair (i, j) based on the meta-path by the server may be expressed as:
wherein the content of the first and second substances,attnoderepresenting an execution node level attention neural network, hiRepresenting the characteristics of node i, hjRepresenting the characteristics of node j, represented as a given meta-path, equation one above, shows that, given meta-path, the server depends on their mapping characteristics based on the node weights corresponding to node pairs (i, j) of the meta-path. For example, the preset semantic path type is location-time-traffic jam, the server generates two meta paths, namely primary school near the city, school going to and going to school, road congestion of the Yangtze river west and shopping center of the Yangtze river west, road congestion of the Yangtze river west and road congestion of the Yangtze river west, the two meta paths cause the same road congestion at different times and different places, and the traffic jam of the Yangtze river west can occur both at the time of going to and going to school and at the time of weekend, so the weight of the meta paths at different time periods is different. The weight of the meta-path is also related to the occurrence frequency of the related content, and the weight is larger when the frequency is larger, and is smaller when the frequency is smaller. The node-level attention mechanism aims to understand the importance of the meta-path based neighbors and assign them different attention values. When the preset semantic path type is a time-location-road condition or a time-weather-road condition, the corresponding nodes are different, and the corresponding node weights are also different.
Further, the server learns the importance of the semantics by the semantic level attention and integrates the nodes under a plurality of semantics to be expressed as:
wherein, attsemA deep neural network representing the execution of semantic level attention,
the attention of formula two representing semantic levels may obtain various types of semantic information for the output of the node level attention module.
Is the output weight at the node level, and Z is the output weight at the semantic level.
204. And sending the traffic jam path information to the navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information.
The navigation terminal has a unique identification value, and the server determines the navigation terminal according to the transfer identification value. Optionally, the server packages the traffic congestion path information into a message to be sent, and writes the message to be sent into a preset message sending queue; the server judges whether a preset message sending queue is not a null value or not through a preset timing task; if the preset message sending queue is not null, the server sends the message to be sent to the navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information; and the server acquires a data receiving result returned by the navigation terminal, and removes the message to be sent from a preset message sending queue when the data receiving result is successful.
205. And acquiring a traffic jam time period, and storing the new driving route, the traffic jam time period and the traffic jam path information into a preset data table.
The preset data table may be a memory data table, or may be a relational data table, which is not limited herein. Specifically, the server acquires a traffic jam time period and a new driving route sent by the navigation terminal, and generates an insertion statement based on the new driving route, the traffic jam time period, traffic jam path information and a preset data table; the server executes the insert sentence to store the new driving route, the traffic jam time period and the traffic jam path information into a preset data table. Further, the server can also acquire traffic flow statistical data related to the traffic jam path information and update the traffic flow statistical data to a preset data table.
206. Receiving a traffic thermodynamic diagram generation request sent by a target terminal, performing data analysis and thermodynamic diagram generation processing on a preset data table according to the traffic thermodynamic diagram generation request to obtain traffic thermodynamic diagram data, and sending the traffic thermodynamic diagram data to the target terminal.
Specifically, the server receives a traffic thermodynamic diagram generation request sent by a target terminal, and performs parameter analysis on the traffic thermodynamic diagram generation request to obtain a target time period; the server analyzes data of a preset data table based on the target time period to obtain analyzed time data and geospatial data; and calling a preset thermodynamic diagram generation interface to convert the analyzed time data and the geospatial data into traffic thermodynamic diagram data, wherein the traffic thermodynamic diagram data comprises traffic flow thermodynamic diagram data, and sending the traffic thermodynamic diagram data to a target terminal.
In the embodiment of the invention, named entity recognition is carried out on target text data in a preset user microblog webpage through a preset traffic entity recognition model to obtain target entity data, semantic analysis is carried out on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information, so that a navigation terminal plans a new driving route according to the traffic path information, and the accuracy of constructing the traffic jam semantic association relationship is improved.
With reference to fig. 3, the traffic congestion situation prediction method in the embodiment of the present invention is described above, and a traffic congestion situation prediction apparatus in the embodiment of the present invention is described below, where an embodiment of the traffic congestion situation prediction apparatus in the embodiment of the present invention includes:
the extraction module 301 is configured to extract target text data from a preset user microblog webpage, where the target text data is microblog text data describing a target city traffic condition;
the identification module 302 is configured to perform named entity identification on target text data through a preset traffic entity identification model to obtain target entity data, where the target entity data is used to indicate a multidimensional entity object related to a traffic congestion situation;
the analysis module 303 is configured to perform semantic analysis on the target entity data through the trained heteromorphic image attention network model to obtain traffic congestion path information;
the sending module 304 is configured to send the traffic jam path information to the navigation terminal, so that the navigation terminal plans a new driving route according to the traffic jam path information.
Further, the traffic congestion path information is stored in the block chain database, which is not limited herein.
In the embodiment of the invention, named entity recognition is carried out on target text data in a preset user microblog webpage through a preset traffic entity recognition model to obtain target entity data, semantic analysis is carried out on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information, so that a navigation terminal plans a new driving route according to the traffic path information, and the accuracy of constructing the traffic jam semantic association relationship is improved.
Referring to fig. 4, another embodiment of the traffic congestion situation prediction apparatus according to the embodiment of the present invention includes:
the extraction module 301 is configured to extract target text data from a preset user microblog webpage, where the target text data is microblog text data describing a target city traffic condition;
the identification module 302 is configured to perform named entity identification on target text data through a preset traffic entity identification model to obtain target entity data, where the target entity data is used to indicate a multidimensional entity object related to a traffic congestion situation;
the analysis module 303 is configured to perform semantic analysis on the target entity data through the trained heteromorphic image attention network model to obtain traffic congestion path information;
the sending module 304 is configured to send the traffic jam path information to the navigation terminal, so that the navigation terminal plans a new driving route according to the traffic jam path information.
Optionally, the extracting module 301 may be further specifically configured to:
acquiring initial text data from a preset user microblog webpage according to preset microblog registration data through a preset data acquisition task;
when the initial text data is not null, sequentially performing text error correction and segmentation processing on the initial text data to obtain a plurality of segmented text data;
respectively carrying out word segmentation processing and part-of-speech tagging on the segmented text data to obtain a plurality of text participles, and matching the text participles according to preset traffic keywords to obtain at least one matched participle;
and screening a plurality of segmented text data according to at least one matched word segmentation to obtain target text data, wherein the target text data is used for describing microblog text data of traffic conditions.
Optionally, the identifying module 302 may be further specifically configured to:
performing text preprocessing on the target text data to obtain processed text data;
performing text vectorization on the processed text data through a word vector conversion network in a preset traffic entity recognition model to obtain a plurality of text vectors;
and calling an entity identification network in a preset traffic entity identification model to perform mapping transformation and entity relationship extraction on the plurality of text vectors to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to the traffic jam situation.
Optionally, the analysis module 303 may be further specifically configured to:
mapping a multi-dimensional entity object in target entity data to the same feature space through a node level attention neural network in a trained heteromorphic graph attention network model to obtain a plurality of nodes, wherein each node is used for vector representation;
converting a plurality of nodes into a plurality of meta-paths according to a preset semantic path type, and respectively carrying out weight calculation on node pairs in each meta-path to obtain a plurality of node weights, wherein each node weight is used for indicating the semantic relevance of any two nodes;
and performing semantic fusion processing on the plurality of nodes and the plurality of node weights through a semantic level attention neural network in the trained heteromorphic image attention network model to obtain traffic jam path information.
Optionally, the sending module 304 may be further specifically configured to:
packaging the traffic jam path information into a message to be sent, and writing the message to be sent into a preset message sending queue;
judging whether a preset message sending queue is not a null value or not through a preset timing task;
if the preset message sending queue is not null, sending the message to be sent to the navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information;
and acquiring a data receiving result returned by the navigation terminal, and removing the message to be sent from a preset message sending queue when the data receiving result is successful.
Optionally, the traffic congestion situation prediction apparatus further includes:
an obtaining module 305, configured to obtain heterogeneous pattern data, where the heterogeneous pattern data is used to indicate information of a plurality of node connection paths related to traffic congestion status content;
the training module 306 is configured to train an initial heteromorphic image attention network model based on a gradient descent algorithm and the isomorphic image sample data until the loss function value is less than or equal to a preset threshold value, so as to obtain a trained heteromorphic image attention network model.
Optionally, the traffic congestion situation prediction apparatus further includes:
the storage module 307 is configured to acquire a traffic jam time period, and store the new driving route, the traffic jam time period, and the traffic jam path information into a preset data table;
the generating module 308 is configured to receive a traffic thermodynamic diagram generating request sent by a target terminal, perform data analysis and thermodynamic diagram generating processing on a preset data table according to the traffic thermodynamic diagram generating request to obtain traffic thermodynamic diagram data, and send the traffic thermodynamic diagram data to the target terminal.
In the embodiment of the invention, named entity recognition is carried out on target text data in a preset user microblog webpage through a preset traffic entity recognition model to obtain target entity data, semantic analysis is carried out on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information, so that a navigation terminal plans a new driving route according to the traffic path information, and the accuracy of constructing the traffic jam semantic association relationship is improved.
Fig. 3 and 4 describe the traffic congestion situation prediction apparatus in the embodiment of the present invention in detail from the perspective of modularization, and the traffic congestion situation prediction apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a traffic congestion situation prediction apparatus 500 according to an embodiment of the present invention, where the traffic congestion situation prediction apparatus 500 may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of computer program operations in the traffic congestion situation prediction apparatus 500. Still further, the processor 510 may be configured to communicate with the storage medium 530, and execute a series of computer program operations in the storage medium 530 on the traffic congestion situation prediction apparatus 500.
The traffic congestion situation prediction apparatus 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the traffic congestion situation prediction apparatus configuration shown in fig. 5 does not constitute a limitation of the traffic congestion situation prediction apparatus, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored thereon a computer program, which, when run on a computer, causes the computer to execute the steps of the traffic congestion situation prediction method.
The invention further provides a traffic congestion situation prediction device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the traffic congestion situation prediction method in the above embodiments.
Further, the computer-readable storage medium 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 the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several computer programs to enable a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A traffic congestion situation prediction method is characterized by comprising the following steps:
extracting target text data from a preset user microblog webpage, wherein the target text data are used for describing microblog text data of a target city traffic condition;
carrying out named entity recognition on the target text data through a preset traffic entity recognition model to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to a traffic jam situation;
performing semantic analysis on the target entity data through a trained heteromorphic image attention network model to obtain traffic jam path information;
and sending the traffic jam path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information.
2. The method for predicting the traffic congestion situation according to claim 1, wherein the extracting target text data from a preset microblog webpage of the user, the target text data being used for describing microblog text data of traffic conditions of a target city, comprises:
acquiring initial text data from a preset user microblog webpage according to preset microblog registration data through a preset data acquisition task;
when the initial text data is not null, sequentially performing text error correction and segmentation processing on the initial text data to obtain a plurality of segmented text data;
performing word segmentation processing and part-of-speech tagging on the segmented text data respectively to obtain a plurality of text word segmentations, and matching the text word segmentations according to preset traffic keywords to obtain at least one matched word segmentations;
and screening the segmented text data according to the at least one matched word segmentation to obtain target text data, wherein the target text data is used for describing microblog text data of traffic conditions.
3. The method according to claim 1, wherein the named entity recognition is performed on the target text data through a preset traffic entity recognition model to obtain target entity data, and the target entity data is used for indicating a multi-dimensional entity object related to the traffic congestion situation, and includes:
performing text preprocessing on the target text data to obtain processed text data;
performing text vectorization on the processed text data through a word vector conversion network in a preset traffic entity recognition model to obtain a plurality of text vectors;
and calling an entity identification network in the preset traffic entity identification model to perform mapping transformation and entity relationship extraction on the plurality of text vectors to obtain target entity data, wherein the target entity data is used for indicating a multi-dimensional entity object related to the traffic jam situation.
4. The method for predicting traffic congestion situation according to claim 1, wherein the obtaining traffic congestion path information by performing semantic analysis on the target entity data through the trained heteromorphic image attention network model comprises:
mapping a multi-dimensional entity object in the target entity data to the same feature space through a node level attention neural network in a trained heteromorphic graph attention network model to obtain a plurality of nodes, wherein each node is used for vector representation;
converting the plurality of nodes into a plurality of meta-paths according to a preset semantic path type, and respectively carrying out weight calculation on the node pairs in each meta-path to obtain a plurality of node weights, wherein each node weight is used for indicating the semantic relevance of any two nodes;
and performing semantic fusion processing on the plurality of nodes and the plurality of node weights through a semantic level attention neural network in the trained heteromorphic image attention network model to obtain traffic jam path information.
5. The method for predicting the traffic congestion situation according to claim 1, wherein the step of sending the traffic congestion path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic congestion path information comprises:
packaging the traffic jam path information into a message to be sent, and writing the message to be sent into a preset message sending queue;
judging whether the preset message sending queue is not a null value or not through a preset timing task;
if the preset message sending queue is not null, sending the message to be sent to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information;
and acquiring a data receiving result returned by the navigation terminal, and removing the message to be sent from the preset message sending queue when the data receiving result is successful.
6. The method according to any one of claims 1 to 5, wherein before extracting target text data from a preset microblog webpage of a user, the target text data is used for microblog text data describing traffic conditions of a target city, the method further comprises:
acquiring heterogeneous pattern data, wherein the heterogeneous pattern data is used for indicating information of a plurality of node connection paths related to the traffic jam state content;
and training an initial heteromorphic image attention network model based on a gradient descent algorithm and the isomorphic image sample data until the loss function value is less than or equal to a preset threshold value to obtain the trained heteromorphic image attention network model.
7. The method according to any one of claims 1 to 5, wherein after the sending the traffic congestion path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic congestion path information, the method further comprises:
acquiring a traffic jam time period, and storing the new driving route, the traffic jam time period and the traffic jam path information into a preset data table;
receiving a traffic thermodynamic diagram generation request sent by a target terminal, performing data analysis and thermodynamic diagram generation processing on the preset data table according to the traffic thermodynamic diagram generation request to obtain traffic thermodynamic diagram data, and sending the traffic thermodynamic diagram data to the target terminal.
8. A traffic congestion situation prediction apparatus, characterized by comprising:
the extraction module is used for extracting target text data from a preset user microblog webpage, wherein the target text data are used for describing microblog text data of a target city traffic condition;
the identification module is used for carrying out named entity identification on the target text data through a preset traffic entity identification model to obtain target entity data, and the target entity data is used for indicating a multi-dimensional entity object related to a traffic jam situation;
the analysis module is used for carrying out semantic analysis on the target entity data through the trained heteromorphic image attention network model to obtain traffic jam path information;
and the sending module is used for sending the traffic jam path information to a navigation terminal so that the navigation terminal plans a new driving route according to the traffic jam path information.
9. A traffic congestion situation prediction apparatus characterized by comprising: a memory and at least one processor, the memory having stored therein a computer program;
the at least one processor invokes the computer program in the memory to cause the traffic congestion situation prediction apparatus to perform the traffic congestion situation prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for traffic congestion situation prediction according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111095934.4A CN113779429A (en) | 2021-09-18 | 2021-09-18 | Traffic congestion situation prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111095934.4A CN113779429A (en) | 2021-09-18 | 2021-09-18 | Traffic congestion situation prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113779429A true CN113779429A (en) | 2021-12-10 |
Family
ID=78852088
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111095934.4A Pending CN113779429A (en) | 2021-09-18 | 2021-09-18 | Traffic congestion situation prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113779429A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114234995A (en) * | 2021-12-21 | 2022-03-25 | 浙江数智交院科技股份有限公司 | Navigation method, navigation device, electronic equipment and storage medium |
| CN116386895A (en) * | 2023-04-06 | 2023-07-04 | 之江实验室 | Epidemic public opinion entity identification method and device based on heterogeneous graph neural network |
| CN116681176A (en) * | 2023-06-12 | 2023-09-01 | 济南大学 | Traffic flow prediction method based on clustering and heterogeneous graph neural network |
-
2021
- 2021-09-18 CN CN202111095934.4A patent/CN113779429A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114234995A (en) * | 2021-12-21 | 2022-03-25 | 浙江数智交院科技股份有限公司 | Navigation method, navigation device, electronic equipment and storage medium |
| CN116386895A (en) * | 2023-04-06 | 2023-07-04 | 之江实验室 | Epidemic public opinion entity identification method and device based on heterogeneous graph neural network |
| CN116386895B (en) * | 2023-04-06 | 2023-11-28 | 之江实验室 | Epidemic public opinion entity identification method and device based on heterogeneous graph neural network |
| CN116681176A (en) * | 2023-06-12 | 2023-09-01 | 济南大学 | Traffic flow prediction method based on clustering and heterogeneous graph neural network |
| CN116681176B (en) * | 2023-06-12 | 2024-05-03 | 济南大学 | Traffic flow prediction method based on clustering and heterogeneous graph neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111783419B (en) | Address similarity calculation method, device, equipment and storage medium | |
| CN113779429A (en) | Traffic congestion situation prediction method, device, equipment and storage medium | |
| CN111708873A (en) | Intelligent question answering method and device, computer equipment and storage medium | |
| CN112199608B (en) | Social media rumor detection method based on network information propagation graph modeling | |
| CN111767725B (en) | Data processing method and device based on emotion polarity analysis model | |
| CN112800170A (en) | Question matching method and device and question reply method and device | |
| CN112149400B (en) | Data processing method, device, equipment and storage medium | |
| KR102368188B1 (en) | Ai-based job matching system | |
| CN112819023A (en) | Sample set acquisition method and device, computer equipment and storage medium | |
| CN114511249A (en) | Grid partitioning method and device, electronic equipment and storage medium | |
| CN116741396A (en) | Article classification method and device, electronic equipment and storage medium | |
| CN116127066A (en) | Text clustering method, text clustering device, electronic equipment and storage medium | |
| CN115587192A (en) | Relationship information extraction method, device and computer readable storage medium | |
| CN115841334A (en) | Abnormal account identification method and device, electronic equipment and storage medium | |
| CN115131058A (en) | Account identification method, device, equipment and storage medium | |
| CN115292460A (en) | Topic recommendation method and device, electronic equipment and storage medium | |
| CN114722174A (en) | Word extraction method and device, electronic equipment and storage medium | |
| CN115168590A (en) | Text feature extraction method, model training method, device, equipment and medium | |
| CN115205546A (en) | Model training method and device, electronic equipment and storage medium | |
| CN114398903A (en) | Intention recognition method and device, electronic equipment and storage medium | |
| CN113343012A (en) | News matching method, device, equipment and storage medium | |
| Hettiarachchi et al. | Next generation data classification and linkage: Role of probabilistic models and artificial intelligence | |
| CN113761123A (en) | Keyword acquisition method and device, computing equipment and storage medium | |
| CN111615178A (en) | Method and device for identifying wireless network type and model training and electronic equipment | |
| Ageno Pulido et al. | The talp participation at tac-kbp 2013 |
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 |