Material transportation ontology generation method, device and equipment based on implicit concept mining

By adopting implicit concept mining methods in the field of material transportation, identifying type columns and data characteristics in relational database tables, and generating material transportation information ontology, solving the problem of semantic omission in the existing technology and improving the accuracy of the ontology and effectiveness.

CN118394859BActive Publication Date: 2024-11-01BEIJING BIG DATA ADVANCED TECH RES INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410608061.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-16
Publication Date
2024-11-01
Estimated Expiration
2044-05-16

AI Technical Summary

Technical Problem

In the field of material transportation, the existing dynamic generation technology of relational database ontology is easy to miss the semantic content of the original data due to the complex content of the data source, resulting in the loss of part of the semantic information of the generated ontology, which has a low accuracy rate.

Method used

Using an implicit concept mining method, we extract the relational database table from the material transportation information relational database, identify type columns, and use clustering algorithm to identify potential type columns to generate the material transportation information ontology to avoid semantic omissions and improve the accuracy of the ontology.

Benefits of technology

By identifying the type columns and relational data characteristics in the relational database table, applying ontology generation rules to generate more accurate ontology of material transportation information, improving the effectiveness and accuracy of the ontology, enhancing interoperability and knowledge with other systems Expression ability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118394859B_ABST
    Figure CN118394859B_ABST
Patent Text Reader

Abstract

The present application provides a method, device and equipment for generating a material transportation ontology based on implicit concept mining, and relates to the field of material transportation technology. The method comprises: extracting a relational database table from a material transportation information relational database; determining one or more type columns in the relational database table; the type column represents a data column with conceptual category semantics in the relational database table; extracting relational data features from the relational database table, the relational data features at least comprising: data columns, primary keys, foreign keys and constraint information of the relational database table; and applying ontology generation rules according to the relational data features and the type column to generate a material transportation information ontology.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of material transportation, and in particular to a method, device and equipment for generating a material transportation ontology based on implicit concept mining. Background Art

[0002] Currently, relational databases (RDBs) are widely used to store and manage large amounts of data in various fields and industries. However, due to the weak knowledge representation capabilities of relational data models, semantic integration, knowledge mining, understanding, and interoperability based on relational databases are very challenging.

[0003] Ontology refers to the standardized semantic description of a set of concepts in a specific field and their internal logical relationships. It provides a basic classification framework and association description mechanism for domain data, and then rationally organizes the semantics contained in the data. Ontology can be regarded as a digital abstraction of the semantic framework of human knowledge. It is a knowledge bridge between humans and machines, and has the advantages of being easy to query, expand, understand, and share. Automatically converting relational databases into ontologies can add semantics to data, achieve interoperability with other systems and applications, support reasoning about data, and create more flexible knowledge representations. Dynamic generation of ontology means that the system can automatically and agilely generate ontologies based on the structure and content of a given data source.

[0004] However, due to the complexity and diversity of the data source content in the material transportation relational database, the existing dynamic ontology generation technology for relational data has limited applicability and is prone to miss the semantic content of the original data, causing the generated ontology to lose some ontology semantic information. Therefore, it is necessary to develop a material transportation ontology generation method, device and equipment based on implicit concept mining to improve the accuracy of the generated ontology. Summary of the invention

[0005] In view of the above problems, the embodiments of the present application provide a method, device and equipment for generating a material transportation ontology based on implicit concept mining, so as to overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect of an embodiment of the present application, a method for generating a material transportation ontology based on implicit concept mining is provided, the method comprising:

[0007] Extracting a relational database table from a material transportation information relational database;

[0008] Determine one or more type columns in the relational database table; the type column represents a data column in the relational database table having conceptual category semantics;

[0009] Extracting relational data features from the relational database table, the relational data features at least including: data columns, primary keys, foreign keys and constraint information of the relational database table;

[0010] According to the relational data features and the type column, an ontology generation rule is applied to generate a material transportation information ontology.

[0011] In a possible implementation manner, determining one or more type columns in the relational database table includes:

[0012] Converting the relational database table into a numerical data matrix;

[0013] Selecting a data column from the numerical data matrix as a potential type column;

[0014] For each row of data in the numerical data matrix, deleting the value of the potential type column to obtain a feature vector to be clustered;

[0015] Clustering the feature vectors to be clustered to obtain multiple clusters;

[0016] Calculating a clustering quality score according to the plurality of clustering clusters, wherein the clustering quality score indicates the clustering quality of the plurality of clustering clusters;

[0017] All data columns in the numerical data matrix are traversed, and one or more type columns in the relational database table are determined according to the clustering quality score of each data column.

[0018] In a possible implementation, clustering the feature vectors to be clustered includes:

[0019] Determine the value of each data of the potential type column in the numerical data matrix;

[0020] Determine the number of types of all values ​​of the potential type column as the target cluster number;

[0021] The k-means clustering algorithm is used to cluster the feature vectors to be clustered according to the target number of clusters.

[0022] In a possible implementation, calculating a clustering quality score according to the multiple clusters includes:

[0023] Calculate the silhouette graph scores of the plurality of cluster clusters, and use the silhouette graph scores as clustering quality scores of the potential type columns.

[0024] In a possible implementation, applying ontology generation rules according to the relational data features and the type column to generate the material transportation information ontology includes:

[0025] For the relational database table, create a corresponding ontology class;

[0026] Creating a subclass for the type column, and generating a parent-child class relationship between the subclass and the ontology class;

[0027] For each common data column in the relational data feature that does not belong to the type column, create a data attribute with the same name in the ontology, whose domain is the ontology class and whose value range is the SQL data type of the common data column;

[0028] For each data column in the primary key of the relational data feature, a data attribute with the same name is created in the ontology, its domain is the ontology class, its value range is the SQL data type of the data column, and a key axiom is added to the data attribute with the same name.

[0029] In a possible implementation, creating a subclass for the type column includes:

[0030] For each of the type columns, a subclass is created for each value in the type column.

[0031] In a possible implementation, applying ontology generation rules according to the relational data features and the type column to generate the material transportation information ontology includes:

[0032] Create a class disjointness axiom based on the subclasses created for the type column.

[0033] The second aspect of the embodiment of the present application further provides a material transportation ontology generation device based on implicit concept mining, the device comprising:

[0034] An extraction module is used to extract a relational database table from a material transportation information relational database;

[0035] A type column determination module, used to determine one or more type columns in the relational database table; the type column represents a data column in the relational database table having conceptual category semantics;

[0036] A relational data feature extraction module, used to extract relational data features from the relational database table, wherein the relational data features at least include: data columns, primary keys, foreign keys and constraint information of the relational database table;

[0037] The ontology generation module is used to generate the material transportation information ontology by applying the ontology generation rules according to the relational data characteristics and the type column.

[0038] In a possible implementation, the type column determination module includes:

[0039] A matrix conversion submodule, used for converting the relational database table into a numerical data matrix;

[0040] A potential type column determination submodule is used to select a data column from the numerical data matrix as a potential type column;

[0041] A feature vector generation submodule, for deleting the value of the potential type column for each row of data in the numerical data matrix, to obtain a feature vector to be clustered;

[0042] A clustering submodule, used for clustering the feature vectors to be clustered to obtain a plurality of cluster clusters;

[0043] A clustering quality evaluation submodule, configured to calculate a clustering quality score according to the plurality of clusters, wherein the clustering quality score represents the clustering quality of the plurality of clusters;

[0044] The type column determination submodule is used to traverse all data columns in the numerical data matrix and determine one or more type columns in the relational database table according to the clustering quality score of each data column.

[0045] In a possible implementation, the clustering submodule includes:

[0046] A value determination unit, used for determining the value of each data of the potential type column in the numerical data matrix;

[0047] A target cluster number determination unit, used to determine the number of types of all values ​​of the potential type column as the target cluster number;

[0048] The clustering unit is used to cluster the feature vectors to be clustered according to the target number of clusters by using a k-means clustering algorithm.

[0049] In a possible implementation, the clustering quality assessment submodule includes:

[0050] The profile score calculation unit is used to calculate the profile scores of the multiple clusters and use the profile scores as the clustering quality scores of the potential type columns.

[0051] In a possible implementation, the ontology generation module includes:

[0052] A first generation submodule is used to create a corresponding ontology class for the relational database table;

[0053] A second generation submodule is used to create a subclass for the type column and generate a parent-child class relationship between the subclass and the ontology class;

[0054] A third generation submodule is used to create, for each common data column in the relational data feature that does not belong to the type column, a data attribute with the same name in the ontology, whose definition domain is the ontology class and whose value range is the SQL data type of the common data column;

[0055] The fourth generation submodule is used to create a data attribute with the same name in the ontology for each data column in the primary key of the relational data feature, whose definition domain is the ontology class and whose value range is the SQL data type of the data column, and add a key axiom for the data attribute with the same name.

[0056] In a possible implementation manner, the second generating submodule is further used to:

[0057] For each of the type columns, a subclass is created for each value in the type column.

[0058] In a possible implementation, the ontology generation module further includes:

[0059] The fifth generation submodule is used to create a class disjointness axiom according to each subclass created for the type column.

[0060] The third aspect of the embodiment of the present application also provides an electronic device, including a memory, a processor and a computer program stored on the memory, and the processor executes the computer program to implement the steps in the material transportation ontology generation method based on implicit concept mining described in the first aspect of the embodiment of the present application.

[0061] The fourth aspect of the embodiment of the present application also provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps in the material transportation ontology generation method based on implicit concept mining described in the first aspect of the embodiment of the present application are implemented.

[0062] The fifth aspect of the embodiments of the present application also provides a computer program product. When the computer program product is run on an electronic device, the processor is enabled to implement the steps in the material transportation ontology generation method based on implicit concept mining as described in the first aspect of the embodiments of the present application.

[0063] The embodiment of the present application provides a material transportation ontology generation method based on implicit concept mining, the method comprising: extracting a relational database table from a material transportation information relational database; determining one or more type columns in the relational database table; the type column represents a data column with concept category semantics in the relational database table; extracting relational data features from the relational database table, the relational data features at least including: data columns, primary keys, foreign keys and constraint information of the relational database table; applying ontology generation rules based on the relational data features and the type columns to generate a material transportation information ontology. The embodiment of the present application identifies the type column in the relational database table. As a special column in the relational database table, the type column can also express certain semantics and play the role of an ontology, and has concept category semantics. The present application combines the relational data features and the identified type columns, applies the ontology generation rules, and generates a material transportation information ontology to mine the implicit concepts (type columns with concept category semantics) in the relational database table, avoid semantic omissions, and obtain a more accurate ontology. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0065] Figure 1 It is a flowchart of the steps of a material transportation ontology generation method based on implicit concept mining provided by an embodiment of the present application;

[0066] Figure 2 It is a schematic diagram of a relational database table of a material transportation information relational database provided in an embodiment of the present application;

[0067] Figure 3 It is a structural schematic diagram of a material transportation ontology generation device based on implicit concept mining provided in an embodiment of the present application;

[0068] Figure 4 It is a schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The exemplary embodiments of the present application will be described in more detail below in conjunction with the accompanying drawings in the embodiments of the present application. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to enable the scope of the present application to be fully communicated to those skilled in the art.

[0070] Currently, relational databases are widely used to store and manage large amounts of data in various fields and industries. However, due to the weak knowledge representation capabilities of relational data models, semantic integration, knowledge mining, understanding and interactive operations based on relational databases are very challenging.

[0071] Ontology refers to the standardized semantic description of the concept set and its internal logical relationship in a specific field. It can provide a basic classification framework and association description mechanism for domain data, and then reasonably organize the semantics contained in the data. Ontology can be regarded as a digital abstraction of the semantic framework of human knowledge. It is a knowledge bridge between humans and machines, and has the advantages of being easy to query, expand, understand, and share. The currently popular knowledge graph is also an intelligent application based on ontology technology. Ontology modeling refers to the use of ontology-based knowledge representation methods to model knowledge. Its core task is to clarify the concepts, attributes, constraints and hierarchical relationships between concepts in the field. It usually includes the following steps: ① domain analysis and overview, ② definition of concepts and relationships, ③ establishment of classes and instances, and ④ definition of rules and constraints. Specifically, it is a process of describing knowledge by defining a set of ontology axioms. Ontology technology provides a standard semantic description for domain concepts and their relationships, and is the basis for data semantic integration and knowledge sharing.

[0072] Dynamic ontology means that the ontology content can be adjusted, added or deleted according to the underlying data source when the system is running, so that the ontology can be flexibly expanded, modified or deleted. This allows it to work in a constantly changing environment and quickly integrate and associate with other ontologies. Correspondingly, dynamic ontology generation means that the system can automatically and agilely generate an ontology based on the structure and content of a given data source.

[0073] Automatically converting relational databases into ontology can add semantics to data, achieve interoperability with other systems and applications, support reasoning about data, and create more flexible knowledge representation. Currently, there is a great demand for the use of ontology to perform semantic modeling on relational databases. Automatically generating ontologies from relational databases has always been a research hotspot in the field of semantic ontology. In order to improve the efficiency of relational data ontology modeling, academia and industry have proposed a variety of automatic ontology generation algorithms for relational data. For a given relational data source, such algorithms are responsible for automatically parsing ontology semantic features from the features of the relational database and generating ontology axioms.

[0074] However, the data source content and structure in the material transportation relational database are complex and diverse, which makes the applicability of existing ontology modeling technology limited. It is easy to miss the implicit semantics in the relational data, resulting in a high error rate in the generated ontology. Specifically, the existing relational database ontology generation method only considers the most basic ontology semantics in the relational database, the correspondence between the relational database table, field, primary and foreign keys and the ontology axioms, such as the table name corresponds to the class name, and the foreign key name corresponds to the object attribute, without splitting the table or combining the fields. This will cause some ontology information to be lost, and the applicability is limited. How to discover implicit classes and implicit relationships that are not explicitly expressed in the metadata in the relational database is also an area worthy of research.

[0075] In view of the above problems, the embodiment of the present application proposes a material transportation ontology generation method based on implicit concept mining to generate a more accurate material transportation information ontology. The following is a detailed description of the material transportation ontology generation method based on implicit concept mining provided by the embodiment of the present application through some embodiments and their application scenarios in conjunction with the accompanying drawings.

[0076] The first aspect of the embodiment of the present application provides a method for generating a material transportation ontology based on implicit concept mining, referring to Figure 1 , Figure 1 A flow chart of the steps of a material transportation ontology generation method based on implicit concept mining provided in an embodiment of the present application is as follows: Figure 1 As shown, the method includes:

[0077] Step S101, extracting a relational database table from a material transportation information relational database.

[0078] In this embodiment, the relational database belongs to a material transportation information relational database, which is mainly used to store material transportation relational data. Figure 2 As shown, Figure 2 A schematic diagram of a relational database table of a material transportation information relational database is shown, wherein the table on the right is a facility table, which has a facility id, a facility category code, a height, a length, and a width. The item object table on the left is the parent table associated with the foreign key of the facility table, and is only used to display the specific name of the item corresponding to the facility id. In step S101, the relational database table extracted from the material transportation information relational database is a relational data containing material transportation information.

[0079] Step S102, determining one or more type columns in the relational database table; the type column represents a data column with conceptual category semantics in the relational database table.

[0080] In this embodiment, it is necessary to determine the special type column from all the data columns in the relational database table to mine the implicit concept. The type column represents a data column with conceptual category semantics, which is used to indicate the type of the object of the row of data. For example, Figure 2 As shown, in the facility table, there is a data column of "facility category code", and each data in the data column is used to indicate the facility category to which the object of the row data (for example, item A or item B) is adapted. Existing relational database ontology generation methods often only consider the most basic ontology semantics (i.e., relational data features) in the relational database, such as the table name corresponds to the class name, and the foreign key name corresponds to the object attribute, while ignoring the special implicit semantics (i.e., the concept category semantics of the type column) contained in the special column (i.e., the type column) in the relational database table. This embodiment proposes that after extracting the relational database table, the type column contained therein is identified according to the relational database table, so as to automatically identify and reconstruct the concept category semantics (implicit concepts) involved in these type columns.

[0081] In a possible implementation, the step S102 of determining one or more type columns in the relational database table includes:

[0082] Step S1021, converting the relational database table into a numerical data matrix.

[0083] Specifically, each data in the relational database table is converted into a corresponding numerical value, so that the entire relational database table is loaded and converted into a numerical data matrix of size [N*M], where N represents the total number of rows in the relational database table, and M represents the total number of columns in the relational database table. The numerical value at the (i, j)th position in the numerical data matrix corresponds to the data in the i-th row and j-th column in the relational database table.

[0084] Step S1022: Select a data column from the numerical data matrix as a potential type column.

[0085] Step S1023: for each row of data in the numerical data matrix, delete the value of the potential type column to obtain a feature vector to be clustered.

[0086] Exemplarily, the third column of data is selected as a potential data column from a numerical data matrix of size 10*20 (a total of 10 rows and 20 columns), and then all the values ​​of the data column are deleted to obtain a 10*19 matrix. Each row of data in the matrix (a row of data corresponding to the value in the third column is deleted) is used as a feature vector to be clustered, that is, 10 19-dimensional feature vectors to be clustered can be obtained.

[0087] Step S1024: clustering the feature vectors to be clustered to obtain a plurality of clusters.

[0088] In a possible implementation, the step S1024, clustering the feature vectors to be clustered, includes:

[0089] Step S1024-a, determining the value of each data in the potential type column in the numerical data matrix; illustratively, Figure 2 As shown, with the facility category code as the potential type column, each data in the column is converted to a numerical value, for example, "small airport" is converted to the numerical value "0", "apron" is converted to the numerical value "1", "bridge" is converted to the numerical value "2", and "runway" is converted to the numerical value "3".

[0090] Step S1024-b, determining the number of types of all values ​​of the potential type column as the target cluster number;

[0091] Step S1024 - c, using the k-means clustering algorithm, clustering the feature vectors to be clustered according to the target number of clusters.

[0092] In this embodiment, the value corresponding to each data in the potential type column is first determined. Each value represents a type. If the values ​​of two data are equal, it means that the two data represent a type. Exemplarily, the values ​​corresponding to the data in the potential type column are 5, 5, 5, 5, 3, 3, 3, 1, 1, respectively, which means that there are three possible data types in the potential type column, and the corresponding values ​​are 5, 3 and 1, respectively, so 3 is determined as the target cluster number. Finally, the k-means clustering algorithm is used to cluster the feature vectors to be clustered obtained in step S1023 according to the target cluster number 3 to obtain 3 cluster clusters.

[0093] Step S1025: Calculate a clustering quality score according to the plurality of clusters, wherein the clustering quality score indicates the clustering quality of the plurality of clusters.

[0094] Specifically, the higher the clustering quality score, the better the clustering effect of the multiple clustering clusters obtained by clustering the data column as the potential type column, and the higher the possibility that the data column belongs to the type column; correspondingly, the lower the clustering quality score, the worse the clustering effect of the multiple clustering clusters obtained by clustering the data column as the potential type column, and the lower the possibility that the data column belongs to the type column.

[0095] In a possible implementation, the step S1025 of calculating the clustering quality score according to the multiple clusters includes:

[0096] Calculate the silhouette graph scores of the plurality of cluster clusters, and use the silhouette graph scores as clustering quality scores of the potential type columns.

[0097] In this embodiment, based on the generated multiple clusters, the Silhouette score is calculated and used as the clustering quality score of the potential type column. The Silhouette score is an indicator for evaluating the output quality of the clustering algorithm, which is mainly used to measure the similarity of an object to its own cluster and other clusters. The range of the Silhouette score is [-1,1], where a score of 1 indicates that the object matches well with its own cluster, but poorly with other adjacent clusters. Correspondingly, a score of -1 indicates that the object does not match well with its own cluster, but matches well with other adjacent clusters. A score of 0 indicates that the object is equally similar to its own cluster and adjacent clusters.

[0098] Step S1026, traverse all data columns in the numerical data matrix, and determine one or more type columns in the relational database table according to the clustering quality score of each data column.

[0099] Each data column in the numerical data matrix is ​​set as a potential type column in turn, and the above steps S1022 to S1025 are respectively performed to obtain a clustering quality score for each data column, so as to determine one or more data columns with the highest score as the type column of the relational database table.

[0100] Step S103: extracting relational data features from the relational database table, wherein the relational data features at least include: data columns, primary keys, foreign keys and constraint information of the relational database table.

[0101] Step S104, applying ontology generation rules according to the relational data features and the type column to generate a material transportation information ontology.

[0102] In the related art, although the database ontology generation method takes into account different relational data features and the most basic ontology semantics in the relational database, it mainly relies on tables, fields, primary and foreign keys as basic units to set rules common to all databases, for example, table names correspond to class names, and foreign key names correspond to object attributes. However, in actual application scenarios, the semantics expressed by relational data features often exist not only in the form of a single table, but some feature columns in the table can also be used as type columns to illustrate the type of object and express certain semantics to play the role of ontology. The present application not only considers the corresponding relationship between the relational database table, field, primary key, foreign key, etc. in the extracted relational data features and the ontology axioms, but also uses the clustering method through step S102 to identify special type columns from the relational database table, thereby applying the corresponding ontology generation rules, and discovering and reconstructing the ontology semantics implied by the type column according to the type column and relational data features, so as to obtain a new ontology containing implicit semantics and related relationships, generate a material transportation information ontology, and finally store the ontology in a commonly used ontology file format such as OWL to improve the effectiveness and accuracy of the generated ontology.

[0103] In a possible implementation, the step S104, applying ontology generation rules according to the relational data features and the type column to generate the material transportation information ontology, includes:

[0104] Step S1041: Create a corresponding ontology class for the relational database table.

[0105] Specifically, first define the ontology class for the entity table, and for the relational database table F, create the corresponding ontology class C T , that is, create a class Facility and represent the superclass of the Standard Template Library (STI) hierarchy.

[0106] Step S1042, create a subclass for the type column, generate a parent-child class relationship between the subclass and the ontology class, that is, generate different ontology semantic subclasses for different values ​​in the type column, and form an implicit parent-child relationship with the ontology semantic class of the relational database table, thereby achieving the purpose of dynamically generating an ontology based on implicit class semantics and relational data characteristics.

[0107] In a possible implementation, creating a subclass for the type column includes:

[0108] For each of the type columns, a subclass is created for each value in the type column.

[0109] Specifically, after the type column is identified or predicted in step S102, the type column is annotated for the ontology class, and each subclass is created according to the type column, that is, a subclass is created for each different value in the type column to generate a parent-child class relationship. Figure 2 As shown, through step S102, the data column "facility category code" in the relational database table is identified as a type column, and each different value in the column "facility category code" is found, and a subclass is created for each different value. For example, subclasses are created for "small airport", "airport", "bridge" and "runway" respectively, as the ontology class C created in step S1041. T A subclass of .

[0110] Step S1043: For each common data column in the relational data feature that does not belong to the type column, create a data attribute with the same name in the ontology, whose domain is the ontology class and whose value range is the SQL data type of the common data column. Specifically, define a data attribute for each non-primary key and non-type column, that is, for each common data column, create a data attribute with the same name in the ontology, and make the domain of the common data column the ontology class C created in step S1041. T , whose value range (Range) is the SQL data type dt of the ordinary data column.

[0111] Step S1044, for each data column in the primary key of the relational data feature, create a data attribute with the same name in the ontology, whose domain is the ontology class and whose value range is the SQL data type of the data column, and add a key axiom for the data attribute with the same name.

[0112] Specifically, a key data attribute is defined for each data column in the primary key, that is, for multiple data columns in the primary key, a data attribute with the same name is created in the ontology, and its definition domain is the ontology class C created in step S1041 T , whose value range (Range) is the SQL data type dt of the data column. Then add a key axiom (keyaxiom) for the data attribute with the same name. For example, Figure 2 As shown, a key axiom is created for the data column "facility id" in the relational database table, so that the key axiom is consistent with the ontology class C T Associated.

[0113] In a possible implementation, the step S104, applying ontology generation rules according to the relationship data features and the type column to generate the material transportation information ontology, further includes:

[0114] Step S1045: Create a class disjointness axiom based on each subclass created for the type column.

[0115] Specifically, a class disjoint attribute is created between the multiple subclasses obtained in step S1044 so that the data between different subclasses are disjoint, that is, any instance cannot belong to multiple subclasses at the same time.

[0116] In the related art, the ontology generation method ignores the type column contained in the relational database table, and only proposes a series of general ontology generation rules with tables, columns, primary and foreign keys as units. In the process of generating the ontology, it does not consider how to find the implicit type column in the relational database table, and naturally cannot extract the type column. The embodiment of the present application proposes a dynamic generation method of a relational database ontology based on implicit concept mining. The method first extracts the relational database table from the material transportation database, and then identifies the type column (i.e., implicit concept) in the relational database table that may have the semantics of the concept category through a clustering algorithm. Based on the determined one or more type columns and the extracted relational data features, different ontology generation rules are applied to obtain and export the generated ontology, which is stored in a common ontology file format such as Web Ontology Language (OWL), and obtains the material transportation information ontology. In the process of generating the ontology, the present application uses each column value in the type column as a new class, and the new class, as a subclass of the class pointed to by the relational database table, forms an implicit parent-child relationship with the ontology semantic class of the data relation table, thereby achieving the purpose of dynamically generating the ontology based on the implicit class and relationship, and improving the effectiveness and accuracy of the ontology generation.

[0117] The second aspect of the embodiment of the present application also provides a material transportation ontology generation device based on implicit concept mining, referring to Figure 3 , Figure 3 A schematic diagram of the structure of a material transportation ontology generation device based on implicit concept mining is shown in FIG. Figure 3 As shown, the device comprises:

[0118] An extraction module is used to extract a relational database table from a material transportation information relational database;

[0119] A type column determination module, used to determine one or more type columns in the relational database table; the type column represents a data column in the relational database table having conceptual category semantics;

[0120] A relational data feature extraction module, used to extract relational data features from the relational database table, wherein the relational data features at least include: data columns, primary keys, foreign keys and constraint information of the relational database table;

[0121] The ontology generation module is used to generate the material transportation information ontology by applying the ontology generation rules according to the relational data characteristics and the type column.

[0122] In a possible implementation, the type column determination module includes:

[0123] A matrix conversion submodule, used for converting the relational database table into a numerical data matrix;

[0124] A potential type column determination submodule is used to select a data column from the numerical data matrix as a potential type column;

[0125] A feature vector generation submodule, for deleting the value of the potential type column for each row of data in the numerical data matrix, to obtain a feature vector to be clustered;

[0126] A clustering submodule, used for clustering the feature vectors to be clustered to obtain a plurality of cluster clusters;

[0127] A clustering quality evaluation submodule, configured to calculate a clustering quality score according to the plurality of clusters, wherein the clustering quality score represents the clustering quality of the plurality of clusters;

[0128] The type column determination submodule is used to traverse all data columns in the numerical data matrix and determine one or more type columns in the relational database table according to the clustering quality score of each data column.

[0129] In a possible implementation, the clustering submodule includes:

[0130] A value determination unit, used for determining the value of each data of the potential type column in the numerical data matrix;

[0131] A target cluster number determination unit, used to determine the number of types of all values ​​of the potential type column as the target cluster number;

[0132] The clustering unit is used to cluster the feature vectors to be clustered according to the target number of clusters by using a k-means clustering algorithm.

[0133] In a possible implementation, the clustering quality assessment submodule includes:

[0134] The profile score calculation unit is used to calculate the profile scores of the multiple clusters and use the profile scores as the clustering quality scores of the potential type columns.

[0135] In a possible implementation, the ontology generation module includes:

[0136] A first generation submodule is used to create a corresponding ontology class for the relational database table;

[0137] A second generation submodule is used to create a subclass for the type column and generate a parent-child class relationship between the subclass and the ontology class;

[0138] A third generation submodule is used to create, for each common data column in the relational data feature that does not belong to the type column, a data attribute with the same name in the ontology, whose definition domain is the ontology class and whose value range is the SQL data type of the common data column;

[0139] The fourth generation submodule is used to create a data attribute with the same name in the ontology for each data column in the primary key of the relational data feature, whose definition domain is the ontology class and whose value range is the SQL data type of the data column, and add a key axiom for the data attribute with the same name.

[0140] In a possible implementation manner, the second generating submodule is further used to:

[0141] For each of the type columns, a subclass is created for each value in the type column.

[0142] In a possible implementation, the ontology generation module further includes:

[0143] The fifth generation submodule is used to create a class disjointness axiom according to each subclass created for the type column.

[0144] The present application also provides an electronic device, referring to Figure 4 , Figure 4 Schematic diagram of an electronic device proposed in an embodiment of the present application. Figure 4 As shown, the electronic device 100 includes: a memory 110 and a processor 120. The memory 110 and the processor 120 are connected via a bus communication. A computer program is stored in the memory 110. The computer program can be run on the processor 120 to implement the steps in the material transportation ontology generation method based on implicit concept mining disclosed in the embodiment of the present application.

[0145] The embodiment of the present application also provides a computer-readable storage medium on which a computer program / instruction is stored. When the computer program / instruction is executed by a processor, the steps in the material transportation ontology generation method based on implicit concept mining as disclosed in the embodiment of the present application are implemented.

[0146] The embodiment of the present application also provides a computer program product. When the computer program product is run on an electronic device, the processor is enabled to implement the steps of the material transportation ontology generation method based on implicit concept mining as disclosed in the embodiment of the present application.

[0147] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0148] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0151] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0152] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0153] The above is a detailed introduction to the material transportation ontology generation method, device and equipment based on implicit concept mining provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A material transportation ontology generation method based on implicit concept mining, characterized in that: The method comprises: Extracting a relational database table from a material transportation information relational database; Determine one or more type columns in the relational database table; the type columns represent data columns in the relational database table that have conceptual category semantics; Extracting relational data features from the relational database table, the relational data features at least including: data columns, primary keys, foreign keys and constraint information of the relational database table; According to the relational data features and the type column, applying ontology generation rules to generate material transportation information ontology; Wherein, determining one or more type columns in the relational database table includes: Converting the relational database table into a numerical data matrix; Selecting a data column from the numerical data matrix as a potential type column; For each row of data in the numerical data matrix, deleting the value of the potential type column to obtain a feature vector to be clustered; Clustering the feature vectors to be clustered to obtain multiple clusters; Calculating a clustering quality score according to the plurality of clustering clusters, wherein the clustering quality score indicates the clustering quality of the plurality of clustering clusters; Traversing all data columns in the numerical data matrix, and determining one or more type columns in the relational database table according to the clustering quality score of each data column; The clustering of the feature vectors to be clustered includes: Determine the value of each data of the potential type column in the numerical data matrix; Determine the number of types of all values ​​of the potential type column as the target cluster number; Using the k-means clustering algorithm, clustering the feature vectors to be clustered according to the target cluster number; The step of applying ontology generation rules according to the relational data features and the type column to generate the material transportation information ontology includes: For the relational database table, create a corresponding ontology class; Creating a subclass for the type column, and generating a parent-child class relationship between the subclass and the ontology class; For each common data column in the relational data feature that does not belong to the type column, create a data attribute with the same name in the ontology, whose domain is the ontology class and whose value range is the SQL data type of the common data column; For each data column in the primary key of the relational data feature, create a data attribute with the same name in the ontology, whose domain is the ontology class and whose value range is the SQL data type of the data column, and add a key axiom for the data attribute with the same name; The step of creating a subclass for the type column includes: For each of the type columns, create a subclass for each value in the type column; The step of applying ontology generation rules according to the relational data features and the type column to generate the material transportation information ontology includes: Create a class disjointness axiom based on the subclasses created for the type column.

2. The material transportation ontology generation method based on implicit concept mining according to claim 1 is characterized in that: The calculating the clustering quality score according to the plurality of clusters comprises: Calculate the silhouette graph scores of the plurality of cluster clusters, and use the silhouette graph scores as clustering quality scores of the potential type columns.

3. A material transportation ontology generation device based on implicit concept mining, characterized in that: The material transportation ontology generation method based on implicit concept mining according to claim 1 or 2, wherein the device comprises: An extraction module is used to extract a relational database table from a material transportation information relational database; A type column determination module, used to determine one or more type columns in the relational database table; the type column represents a data column in the relational database table having conceptual category semantics; A relational data feature extraction module, used to extract relational data features from the relational database table, wherein the relational data features at least include: data columns, primary keys, foreign keys and constraint information of the relational database table; The ontology generation module is used to generate the material transportation information ontology by applying the ontology generation rules according to the relational data characteristics and the type column.

4. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor is executed, the steps in the method for generating a material transportation ontology based on implicit concept mining as described in claim 1 or 2 are implemented.

5. A computer-readable storage medium, characterized in that: A computer program / instruction is stored, and when the computer program / instruction is executed by a processor, the steps in the material transportation ontology generation method based on implicit concept mining described in claim 1 or 2 are implemented.