CN112732929A - Ontology-based movement track modeling and semantic query system and construction method - Google Patents
Ontology-based movement track modeling and semantic query system and construction method Download PDFInfo
- Publication number
- CN112732929A CN112732929A CN202110013055.6A CN202110013055A CN112732929A CN 112732929 A CN112732929 A CN 112732929A CN 202110013055 A CN202110013055 A CN 202110013055A CN 112732929 A CN112732929 A CN 112732929A
- Authority
- CN
- China
- Prior art keywords
- activity
- track
- inclusion
- ontology
- association
- 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 description 6
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 230000000694 effects Effects 0.000 claims description 98
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 11
- 230000002085 persistent effect Effects 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002045 lasting effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/387—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Library & Information Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a body-based moving track modeling and semantic query system, which comprises a moving track data preprocessing module, an incidence relation and inclusion relation calculating module, a moving track body model building and storing module and a moving track data semantic query module, wherein the moving track data preprocessing module is used for preprocessing the moving track data; the invention preprocesses the moving track data set and then expands the dimensionality of the data set; then, respectively calculating the label incidence relation and the label containing relation under the same dimension and the label incidence relation under different dimensions; the method comprises the steps of establishing a body model facing the moving track according to a classification and comparison method and an association and inclusion relation, and finally applying the association and inclusion relation to moving track data query to realize a semantic query function based on association and inclusion relation combination.
Description
Technical Field
The invention relates to the field of analysis and query of movement track data, in particular to a system and a construction method for modeling and semantic query of a movement track based on an ontology.
Background
At present, for a certain domain knowledge, an ontology provides a set of terms, concepts and relationships to describe a certain domain, and an ontology model is constructed by classifying and comparing the domain knowledge, but the construction of the ontology model at semantic and structural levels is still a huge challenge. The research on the moving track is widely focused on the fields of track clustering, track classification, position recommendation and the like through the technologies of classification, clustering and the like in artificial intelligence, but the analysis of the association relationship and the inclusion relationship among the moving track data is omitted. Semantic query is mainly performed through SPARQL language, at present, some researches only combine related research fields with semantic query, and a structured data set is mapped into an RDF data set, so that the purpose of obtaining corresponding semantic query results is achieved, and analysis and comparison of semantic query performance are omitted.
It will thus be seen that the prior art and methods are susceptible to further improvement and development.
Disclosure of Invention
The invention aims to solve the technical problem of providing a mobile track modeling and semantic query system and a construction method based on an ontology aiming at solving the defects of the prior art and the method, and aims to analyze the incidence relation and the inclusion relation between mobile track data from a semantic level and further improve the query efficiency of the mobile track data.
In order to achieve the above object, the present invention provides an ontology-based mobile trajectory modeling and semantic query system, which includes:
the mobile track data preprocessing module is used for adding corresponding position information, activity information and vehicle information to each mobile track point of the data in a longitude and latitude positioning mode and expanding the dimensionality of the data set;
the association relation and inclusion relation calculation module receives the data processed by the moving track data preprocessing module, calculates the label association relation under the same dimensionality and the label association relation under different dimensionalities respectively by adopting two methods, namely weight cosine similarity and point-wise information (PMI), and calculates the label inclusion relation under the same dimensionality by adopting an inclusion probability method;
the mobile track ontology model building and storing module is used for receiving the information of the label inclusion relationship calculated by the association relationship and inclusion relationship calculating module, building an ontology model facing to the mobile track according to the classification and comparison method and the association and inclusion relationship, and storing the ontology model into a database in a persistent mode;
and the moving track data semantic query module is used for performing semantic mapping processing on data in a moving track data set in the body model in the moving track body model building and storing module, applying the association and inclusion relation to the moving track data query and building a semantic query system for combining the association and the inclusion relation.
In the above technical solution, the moving trajectory data preprocessing module specifically includes:
the mobile track data expansion unit is used for adding a specific position location for each track point through a positioning technology according to the recorded longitude and latitude of the mobile track point and adding a specific activity for each track point according to the specific position of the building and the time period of the recorded track; according to the incidence relation between the position of the track point and the activity, adding a travel mode related to the track and the activity;
and a moving track data representation unit which represents a moving track by nine-tuple < start _ date, start _ time, start _ coordinate, activity, end _ date, end _ time, end _ coordinate, location, transportation _ mode > based on the expanded position, activity and travel mode dimensions, wherein the start _ date, the start _ time, the start _ coordinate, the end _ date, the end _ time and the end _ coordinate respectively represent a start date, a start time, a start coordinate, an end date, an end time and an end coordinate of recording the moving track point.
In the above technical solution, the association relation and inclusion relation calculating module specifically includes:
a weight recording unit which analyzes the relationship between activity-activity, position-position and activity-position and records the weight w using a two-dimensional matrixijThe row represents activity i, the column represents position j, and the weight of the label in the same dimension and the weight of the label in different dimensions are recorded;
a label incidence relation calculation unit under the same dimension, which respectively uses vectors to represent the weight (v) of each activity i and the position j0，…vi，…vn) Respectively calculating label incidence relations in an activity dimension and a position dimension by adopting the weight cosine similarity;
a label incidence relation calculation unit under different dimensions according to p (w) of a two-dimensional weight matrixi)，p(wj) And p (w)i，wj) Calculating the degree of association between activities and positions using the PMI method, where p (w)i，wj) A weight representing co-occurrence of activity and location;
an inclusion relation calculation unit which calculates an inclusion relation according to the weight w recorded in the two-dimensional matrixijFor example, at the same position z, there are two activities x and y, the inclusion of activities x and y is calculated, and whether activities x and y occur at the same position z is determined by using methods and conditions including probabilities p (y | x), p (x | y), p (x | z), and p (y | z), where p (x | z) and p (y | z) represent boolean values.
In the above technical solution, the module for constructing and storing the movement trajectory ontology model specifically includes: and the ontology model building and storing unit is used for realizing ontology modeling of the movement track by using a Prot g e tool through a classification and comparison method and the analyzed association and inclusion relation, and storing the ontology model into a database through a jena tool in a persistent mode.
In the above technical solution, the movement trajectory data semantic query module specifically includes:
the semantic mapping unit is used for mapping the data in the movement track data set into an RDF data set through a d2rq tool and realizing semantic query operation on the data in the data set;
and the semantic query unit applies the association and the inclusion relation to the movement track data query.
In order to achieve the above object, the present invention further provides a method for constructing a system for modeling a movement trajectory and querying semantics based on an ontology, comprising the following steps:
s1, preprocessing the data, and expanding information of position, activity and trip mode dimensionality for the movement track data set through a longitude and latitude positioning technology;
s2, sequentially adopting weight cosine similarity and PMI (point-wise mutual information) to calculate label incidence relations under the same dimensionality and label incidence relations under different dimensionalities for the movement track data preprocessed in the step S1, and adopting a containment probability method to calculate label containment relations under the same dimensionality;
s3, constructing an ontology model facing to the movement track by using a classification and comparison method, association and inclusion relations, and storing the ontology model into a database in a persistent manner;
s4, carrying out semantic mapping processing on the data in the movement track data set in the ontology model, applying the association and inclusion relation to the movement track data query, and constructing a semantic query system combining the association and inclusion relation.
In the above technical solution, the step S1 specifically includes:
s11, adding a specific position location for each track point through a positioning technology according to the recorded longitude and latitude of the mobile track point, and adding a specific activity for each track point according to the specific position of the building and the time period of the recorded track; according to the incidence relation between the position of the track point and the activity, adding a travel mode related to the track and the activity;
and S12, based on the expanded position, activity and travel mode dimensions, representing the moving track by a nine-tuple < start _ date, start _ time, start _ coordinate, activity, end _ date, end _ time, end _ coordinate, location and transportation _ mode >, wherein the start _ date, the start _ time, the start _ coordinate, the end _ date, the end _ time and the end _ coordinate respectively represent the starting date, the starting time, the starting coordinates, the ending dates, the ending times and the ending coordinates for recording the moving track points.
In the above technical solution, the step S2 specifically includes:
s21, analyzing the relation between activity-activity, position-position and activity-position, recording the weight w by using a two-dimensional matrixijThe row represents activity i, the column represents position j, and the weight of the label in the same dimension and the weight of the label in different dimensions are recorded;
s22, calculating the incidence relation of the labels in the same dimension, and respectively representing the weight (v) of each activity i and each position j by using a vector0，…vi，…vn) Respectively calculating label incidence relations in an activity dimension and a position dimension by adopting the weight cosine similarity;
s23, calculating the incidence relation of the labels under different dimensions according to p (w) of a two-dimensional weight matrixi)，p(wj) And p (w)i，wj) Calculating the degree of association between activity and position using the PMI method, where p (w)i，wj) A weight representing co-occurrence of activity and location;
s24, calculating the inclusion relation according to the weight w recorded in the two-dimensional matrixijFor example, at the same position z, there are two activities x and y, the inclusion of activities x and y is calculated, and whether activities x and y occur at the same position z is determined by using methods and conditions including probabilities p (y | x), p (x | y), p (x | z), and p (y | z), where p (x | z) and p (y | z) represent boolean values.
In the above technical solution, the step S3 specifically includes: s31, using a Prot g é tool to realize ontology modeling of the movement track through a classification and comparison method and the analyzed association and inclusion relation, and storing the ontology model into a database through a jena tool in a persistent mode.
In the above technical solution, the step S4 specifically includes:
s41, realizing semantic mapping operation, mapping the data in the moving track data set into an RDF data set through a d2rq tool, and realizing semantic query operation on the data in the data set;
and S42, applying the association and inclusion relations to the moving track data query to construct a semantic query system combining the association and inclusion relations.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, a moving track data set is preprocessed, and corresponding position information, activity information and vehicle information are added to each track point, so that the dimensionality of the data set is expanded; calculating label incidence relations under the same dimensionality and label incidence relations under different dimensionalities respectively by adopting two methods, namely weight cosine similarity and point-wise mutual information (PMI), and calculating label inclusion relations under the same dimensionality by adopting an inclusion probability method; designing a body model facing to the moving track according to the relations of classification and comparison methods, association, inclusion and the like, and storing the body model into a database in a lasting way; and applying the association and inclusion relation to the mobile track data query to realize semantic query based on association and inclusion relation combination. The invention analyzes the incidence relation and the inclusion relation between the moving track data from the semantic level, further improves the query efficiency of the moving track data, and can be widely applied to the scenes of analyzing and querying the moving track data.
Drawings
FIG. 1 is a functional block diagram of a preferred embodiment of an ontology-based mobile trajectory modeling and semantic query system provided by the present invention;
FIG. 2 is a flow chart of a preferred embodiment of a method for constructing an ontology-based mobile trajectory modeling and semantic query system according to the present invention.
Detailed Description
The invention discloses a method and a system for modeling a movement track and querying semantics based on an ontology, which are further described in detail below by referring to the attached drawings and embodiments in order to make the purpose, the technical scheme and the advantages of the invention clearer and clearer. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a functional block diagram of an ontology-based movement track modeling and semantic query system provided in the present invention, which includes a movement track data preprocessing module 100, an association and containment relationship calculating module 200, a movement track ontology model constructing and storing module 300, and a movement track data semantic query module 400.
The mobile trajectory data preprocessing module 100 preprocesses data, and expands the position, activity and travel mode dimensionality for a mobile trajectory data set through the longitude and latitude positioning technology. The association relation and inclusion relation calculation module 200 sequentially calculates the label association relation in the same dimension and the label association relation in different dimensions by using the weight cosine similarity and the PMI (point-wise mutual information), and calculates the label inclusion relation in the same dimension by using an inclusion probability method. The movement track ontology model building and storing module 300 uses a classification and comparison method, association and inclusion relation to build an ontology model facing to the movement track, and stores the ontology model into a database in a persistent manner. The mobile track data semantic query module 400 applies the association and inclusion relationship to the mobile track data query, so as to implement the semantic query function based on the association and inclusion relationship combination.
Specifically, the movement trajectory data preprocessing module 100 specifically includes:
the mobile track data expansion unit is used for adding a specific position location for each track point through a positioning technology according to the recorded longitude and latitude of the mobile track point and adding a specific activity for each track point according to the specific position of the building and the time period of the recorded track; according to the incidence relation between the position of the track point and the activity, adding a travel mode related to the track and the activity;
and a moving track data representation unit which represents a moving track by nine-tuple < start _ date, start _ time, start _ coordinate, activity, end _ date, end _ time, end _ coordinate, location, transportation _ mode > based on the expanded position, activity and travel mode dimensions, wherein the start _ date, the start _ time, the start _ coordinate, the end _ date, the end _ time and the end _ coordinate respectively represent a start date, a start time, a start coordinate, an end date, an end time and an end coordinate of recording the moving track point.
Specifically, the association and containment relationship calculation module 200 specifically includes:
a weight recording unit which analyzes the relationship between activity-activity, position-position and activity-position, records the weight w using a two-dimensional matrixijThe row represents activity i, the column represents position j, and the weight of the label in the same dimension and the weight of the label in different dimensions are recorded;
a label incidence relation calculation unit under the same dimension, which respectively uses vectors to represent the weight (v) of each activity i and the position j0，…vi，…vn) Respectively calculating label incidence relations in an activity dimension and a position dimension by adopting the weight cosine similarity;
a label incidence relation calculation unit under different dimensions according to p (w) of a two-dimensional weight matrixi)，p(wj) And p (w)i，wj) Calculating the degree of association between activity and position using the PMI method, where p (w)i，wj) A weight representing co-occurrence of activity and location;
an inclusion relation calculation unit which calculates an inclusion relation according to the weight w recorded in the two-dimensional matrixijFor example, at the same position z, there are two activities x and y, the inclusion of activities x and y is calculated, and whether activities x and y occur at the same position z is determined by using methods and conditions including probabilities p (y | x), p (x | y), p (x | z), and p (y | z), where p (x | z) and p (y | z) represent boolean values.
Further, the module 300 for constructing and storing the movement trajectory ontology model specifically includes: and the ontology model building and storing unit is used for realizing ontology modeling of the movement track by using a Prot g e tool through a classification and comparison method and the analyzed association and inclusion relation, and storing the ontology model into a database through a jena tool in a persistent mode.
Further, the movement trajectory data semantic query module 400 specifically includes:
the semantic mapping unit is used for mapping the data in the movement track data set into an RDF data set through a d2rq tool and realizing semantic query operation on the data in the data set;
and the semantic query unit applies the association and inclusion relation to the mobile track data query to realize semantic query based on association and inclusion relation combination.
Referring to fig. 2, the following is a specific construction method of the ontology-based movement trajectory modeling and semantic query system, including four steps S101, S102, S103, and S104:
step S101, preprocessing data, and expanding position, activity and travel mode dimensionality for a movement track data set through a longitude and latitude positioning technology;
in this embodiment, the step S101 specifically includes the following steps:
s11, adding a specific position location for each track point through a positioning technology according to the recorded longitude and latitude of the mobile track point, and adding a specific activity for each track point according to the specific position of the building and the time period of the recorded track; according to the incidence relation between the position of the track point and the activity, adding a travel mode related to the track and the activity;
s12, based on the expanded position, activity and travel mode dimensions, representing a moving track by a nine-tuple < start _ date, start _ time, start _ coordinate, activity, end _ date, end _ time, end _ coordinate, location and transportation _ mode >, wherein the start _ date, the start _ time, the start _ coordinate, the end _ date, the end _ time and the end _ coordinate respectively represent the starting date, the starting time, the starting coordinates, the ending date, the ending time and the ending coordinates of the recorded moving track point;
step S102, calculating label incidence relations under the same dimensionality and label incidence relations under different dimensionalities respectively by adopting weight cosine similarity and PMI (point-wise mutual information), and calculating label inclusion relations under the same dimensionality by adopting an inclusion probability method;
in this embodiment, the step S102 specifically includes the steps of:
s21, analyzing the relation between activity-activity, position-position and activity-position, recording the weight w by using a two-dimensional matrixijThe row represents activity i, the column represents position j, and the weight of the label in the same dimension and the weight of the label in different dimensions are recorded;
s22, calculating the incidence relation of the labels in the same dimension, and respectively representing the weight (v) of each activity i and each position j by using a vector0，…vi，…vn) Respectively calculating label incidence relations in an activity dimension and a position dimension by adopting the weight cosine similarity;
s23, calculating the incidence relation of the labels under different dimensions according to p (w) of a two-dimensional weight matrixi)，p(wj) And p (w)i，wj) Calculating the degree of association between activity and position using the PMI method, where p (w)i，wj) A weight representing co-occurrence of activity and location;
s24, calculating the inclusion relation according to the weight w recorded in the two-dimensional matrixijCalculating the inclusion relationship between the label x and the label y, for example, at the same position z, there are two activities x and y, calculating the inclusion condition of the activities x and y, and determining whether the activities x and y are present at the same position z by using methods and conditions including probabilities p (y | x), p (x | y), p (x | z), and p (y | z), wherein p (x | z) and p (y | z) represent boolean values;
s103, constructing an ontology modeling of the movement track by using a Prot é tool through a classification and comparison method and the analyzed association and inclusion relation, and persistently storing the ontology model into a database through a jena tool;
step S104, applying the association and inclusion relation to the mobile track data query, thereby constructing a semantic query system combining the association and inclusion relation;
in this embodiment, the step S104 specifically includes the steps of:
s41, realizing semantic mapping operation, mapping the data in the moving track data set into an RDF data set through a d2rq tool, and realizing semantic query operation on the data in the data set;
and S42, applying the association and inclusion relation to the movement track data query to realize the function of semantic query based on the association and inclusion relation combination.
In summary, the invention adds corresponding position information, activity information and vehicle information to each track point by preprocessing the moving track data set, and expands the dimensionality of the data set; calculating label incidence relations under the same dimensionality and label incidence relations under different dimensionalities respectively by adopting two methods, namely weight cosine similarity and point-wise mutual information (PMI), and calculating label inclusion relations under the same dimensionality by adopting an inclusion probability method; designing a body model facing to the moving track according to the relations of classification and comparison methods, association, inclusion and the like, and storing the body model into a database in a lasting way; and applying the association and inclusion relation to the mobile track data query to realize semantic query based on association and inclusion relation combination. The invention analyzes the incidence relation and the inclusion relation between the moving track data from the semantic level, further improves the query efficiency of the moving track data, and can be widely applied to the scenes of analyzing and querying the moving track data.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the foregoing description, and that all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.
Claims (10)
1. An ontology-based mobile trajectory modeling and semantic query system, comprising:
the mobile track data preprocessing module is used for adding corresponding position information, activity information and vehicle information to each mobile track point of the data in a longitude and latitude positioning mode and expanding the dimensionality of the data set;
the incidence relation and inclusion relation calculation module receives the data processed by the moving track data preprocessing module, calculates label incidence relations under the same dimensionality and label incidence relations under different dimensionalities respectively by adopting two methods of weight cosine similarity and point-wise mutual information (PMI), and calculates label inclusion relations under the same dimensionality by adopting an inclusion probability method;
the mobile track ontology model building and storing module is used for receiving the information of the label inclusion relationship calculated by the association relationship and inclusion relationship calculating module, building an ontology model facing to the mobile track according to the classification and comparison method and the association and inclusion relationship, and storing the ontology model into a database in a persistent mode;
and the moving track data semantic query module is used for performing semantic mapping processing on data in a moving track data set in the body model in the moving track body model building and storing module, applying the association and inclusion relation to the moving track data query and building a semantic query system for combining the association and the inclusion relation.
2. The ontology-based mobile trajectory modeling and semantic query system according to claim 1, wherein the mobile trajectory data preprocessing module specifically comprises:
the mobile track data expansion unit is used for adding a specific position location for each track point through a positioning technology according to the recorded longitude and latitude of the mobile track point and adding a specific activity for each track point according to the specific position of the building and the time period of the recorded track; according to the incidence relation between the position of the track point and the activity, adding a travel mode related to the track and the activity;
and a moving track data representation unit which represents a moving track by nine-tuple < start _ date, start _ time, start _ coordinate, activity, end _ date, end _ time, end _ coordinate, location, transportation _ mode > based on the expanded position, activity and travel mode dimensions, wherein the start _ date, the start _ time, the start _ coordinate, the end _ date, the end _ time and the end _ coordinate respectively represent a start date, a start time, a start coordinate, an end date, an end time and an end coordinate of recording the moving track point.
3. The ontology-based mobile trajectory modeling and semantic query system of claim 1, wherein the association and containment relationship calculation module specifically comprises:
a weight recording unit which analyzes the relationship between activity-activity, position-position and activity-position and records the weight w using a two-dimensional matrixijThe row represents activity i, the column represents position j, and the weight of the label in the same dimension and the weight of the label in different dimensions are recorded;
a label incidence relation calculation unit under the same dimension, which respectively uses vectors to represent the weight (v) of each activity i and the position j0,…vi,…vn) Respectively calculating label incidence relations in an activity dimension and a position dimension by adopting the weight cosine similarity;
a label incidence relation calculation unit under different dimensions according to p (w) of a two-dimensional weight matrixi),p(wj) And p (w)i,wj) Calculating the degree of association between activity and position using the PMI method, where p (w)i,wj) A weight representing co-occurrence of activity and location;
an inclusion relation calculation unit which calculates an inclusion relation according to the weight w recorded in the two-dimensional matrixijFor example, at the same position z, there are two activities x and y, the inclusion of activities x and y is calculated, and whether activities x and y occur at the same position z is determined by using methods and conditions including probabilities p (y | x), p (x | y), p (x | z), and p (y | z), where p (x | z) and p (y | z) represent boolean values.
4. The ontology-based mobile track modeling and semantic query system according to claim 1, wherein the mobile track ontology model building and storing module specifically comprises:
and the ontology model building and storing unit is used for realizing ontology modeling of the movement track by using a Prot g e tool through a classification and comparison method and the analyzed association and inclusion relation, and storing the ontology model into a database through a jena tool in a persistent mode.
5. The ontology-based movement track modeling and semantic query system according to claim 1, wherein the movement track data semantic query module specifically comprises:
the semantic mapping unit is used for mapping the data in the movement track data set into an RDF data set through a d2rq tool and realizing semantic query operation on the data in the data set;
and the semantic query unit applies the association and the inclusion relation to the movement track data query.
6. A method for constructing a moving track modeling and semantic query system based on an ontology is characterized by comprising the following steps:
s1, preprocessing the data, and expanding information of position, activity and trip mode dimensionality for the movement track data set through a longitude and latitude positioning technology;
s2, sequentially adopting weight cosine similarity and PMI (point-wise mutual information) to calculate label incidence relations under the same dimensionality and label incidence relations under different dimensionalities for the movement track data preprocessed in the step S1, and adopting a containment probability method to calculate label containment relations under the same dimensionality;
s3, constructing an ontology model facing to the movement track by using a classification and comparison method, association and inclusion relations, and storing the ontology model into a database in a persistent manner;
s4, carrying out semantic mapping processing on the data in the movement track data set in the ontology model, applying the association and inclusion relation to the movement track data query, and constructing a semantic query system combining the association and inclusion relation.
7. The method for constructing an ontology-based movement trajectory modeling and semantic query system according to claim 6, wherein the step S1 specifically includes:
s11, adding a specific position location for each track point through a positioning technology according to the recorded longitude and latitude of the mobile track point, and adding a specific activity for each track point according to the specific position of the building and the time period of the recorded track; according to the incidence relation between the position of the track point and the activity, adding a travel mode related to the track and the activity;
and S12, based on the expanded position, activity and travel mode dimensions, representing the moving track by a nine-tuple < start _ date, start _ time, start _ coordinate, activity, end _ date, end _ time, end _ coordinate, location and transportation _ mode >, wherein the start _ date, the start _ time, the start _ coordinate, the end _ date, the end _ time and the end _ coordinate respectively represent the starting date, the starting time, the starting coordinates, the ending dates, the ending times and the ending coordinates for recording the moving track points.
8. The method for constructing an ontology-based movement trajectory modeling and semantic query system according to claim 6, wherein the step S2 specifically includes:
s21, analyzing the relation between activity-activity, position-position and activity-position, recording the weight w by using a two-dimensional matrixijThe row represents activity i, the column represents position j, and the weight of the label in the same dimension and the weight of the label in different dimensions are recorded;
s22, calculating the incidence relation of the labels in the same dimension, and respectively representing the weight (v) of each activity i and each position j by using a vector0,…vi,…vn) Respectively calculating label incidence relations in an activity dimension and a position dimension by adopting the weight cosine similarity;
s23, calculating the incidence relation of the labels under different dimensions according to p (w) of a two-dimensional weight matrixi),p(wj) And p (w)i,wj) Calculating the degree of association between activity and position using the PMI method, where p (w)i,wj) A weight representing co-occurrence of activity and location;
s24, calculating the inclusion relation according to the weight w recorded in the two-dimensional matrixijCalculating the inclusion relationship of tag x to tag y, e.g. at the same position z, there are two activities x and y, calculating the inclusion of activities x and y, such thatWhether activities x and y occur at the same location z is determined using methods and conditions including probabilities p (y | x), p (x | y), p (x | z), and p (y | z), where p (x | z) and p (y | z) represent boolean values.
9. The method for constructing an ontology-based movement trajectory modeling and semantic query system according to claim 6, wherein the step S3 specifically includes:
s31, using a Prot g é tool to realize ontology modeling of the movement track through a classification and comparison method and the analyzed association and inclusion relation, and storing the ontology model into a database through a jena tool in a persistent mode.
10. The method for constructing an ontology-based movement trajectory modeling and semantic query system according to claim 6, wherein the step S4 specifically includes:
s41, realizing semantic mapping operation, mapping the data in the moving track data set into an RDF data set through a d2rq tool, and realizing semantic query operation on the data in the data set;
and S42, applying the association and inclusion relations to the moving track data query to construct a semantic query system combining the association and inclusion relations.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110013055.6A CN112732929A (en) | 2021-01-06 | 2021-01-06 | Ontology-based movement track modeling and semantic query system and construction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110013055.6A CN112732929A (en) | 2021-01-06 | 2021-01-06 | Ontology-based movement track modeling and semantic query system and construction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112732929A true CN112732929A (en) | 2021-04-30 |
Family
ID=75591336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110013055.6A Pending CN112732929A (en) | 2021-01-06 | 2021-01-06 | Ontology-based movement track modeling and semantic query system and construction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112732929A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361979A (en) * | 2021-08-10 | 2021-09-07 | 湖南高至科技有限公司 | Profile-oriented ontology modeling method and device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN111783739A (en) * | 2020-07-29 | 2020-10-16 | 中国人民解放军国防科技大学 | Communication radiation source similar motion trajectory comparison method |
-
2021
- 2021-01-06 CN CN202110013055.6A patent/CN112732929A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN111783739A (en) * | 2020-07-29 | 2020-10-16 | 中国人民解放军国防科技大学 | Communication radiation source similar motion trajectory comparison method |
Non-Patent Citations (1)
| Title |
|---|
| PENGSHAO等: "Ontology-Based Modeling and Semantic Query for Mobile Trajectory Data", 《IEEE》, pages 1 - 6 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113361979A (en) * | 2021-08-10 | 2021-09-07 | 湖南高至科技有限公司 | Profile-oriented ontology modeling method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | A comprehensive survey on graph neural networks | |
| Cortez | Data mining with neural networks and support vector machines using the R/rminer tool | |
| CN110633409A (en) | Rule and deep learning fused automobile news event extraction method | |
| CN111666406B (en) | Short text classification prediction method based on word and label combination of self-attention | |
| CN111858940B (en) | Multi-head attention-based legal case similarity calculation method and system | |
| CN111046952A (en) | Method and device for establishing label mining model, storage medium and terminal | |
| JP6877374B2 (en) | How to train a model that outputs a vector that represents the tag set that corresponds to the image | |
| CN111461231B (en) | Short message sending control method, device and storage medium | |
| CN112465144B (en) | Multi-mode demonstration intention generation method and device based on limited knowledge | |
| CN109636047A (en) | User activity prediction model training method, system, equipment and storage medium | |
| Wang et al. | Kullback-leibler divergence based graph pruning in robotic feature mapping | |
| CN114119058A (en) | User portrait model construction method and device and storage medium | |
| Jiang et al. | L2mm: learning to map matching with deep models for low-quality gps trajectory data | |
| CN112732929A (en) | Ontology-based movement track modeling and semantic query system and construction method | |
| Le et al. | Tracked-vehicle retrieval by natural language descriptions with domain adaptive knowledge | |
| CN113988071A (en) | Intelligent dialogue method and device based on financial knowledge graph and electronic equipment | |
| Li et al. | Self-supervised contrastive representation learning for large-scale trajectories | |
| Ali et al. | A life-long SLAM approach using adaptable local maps based on rasterized LIDAR images | |
| CN110674265B (en) | Unstructured information oriented feature discrimination and information recommendation system | |
| CN115797795B (en) | Remote sensing image question-answer type retrieval system and method based on reinforcement learning | |
| CN115658845A (en) | Intelligent question-answering method and device suitable for open-source software supply chain | |
| CN115658856A (en) | Intelligent question-answering system and method based on polymorphic document views | |
| CN112487811B (en) | Cascading information extraction system and method based on reinforcement learning | |
| CN111897884B (en) | Data relationship information display method and terminal equipment | |
| US11897140B2 (en) | Systems and methods for operating robots using object-oriented Partially Observable Markov Decision Processes |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210430 |
|
| WD01 | Invention patent application deemed withdrawn after publication |