CN116011564A - Entity relationship completion method, system and application for power equipment - Google Patents
Entity relationship completion method, system and application for power equipment Download PDFInfo
- Publication number
- CN116011564A CN116011564A CN202211694098.6A CN202211694098A CN116011564A CN 116011564 A CN116011564 A CN 116011564A CN 202211694098 A CN202211694098 A CN 202211694098A CN 116011564 A CN116011564 A CN 116011564A
- Authority
- CN
- China
- Prior art keywords
- entities
- power equipment
- entity
- equipment
- relation
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of machine learning algorithm application, and discloses a method, a system and an application for supplementing entity relation of power equipment, which are used for collecting data resources related to power equipment of a power distribution network, analyzing the collected information, extracting entities, attributes and interrelationships among the entities from various data sources, forming an ontology knowledge expression, and determining the entities and the relation to be analyzed; carrying out knowledge fusion processing on the data extracted from the data source, and finally storing the data in a knowledge base in a form of triples; and acquiring the pair of the power equipment entities with the same relation as the extracted pair from the existing knowledge graph in the obtained power equipment knowledge base, taking the association path between the pair of the power equipment entities as a characteristic, analyzing a group of relation paths connecting the two power equipment entities, and predicting the specific or missing relation existing between the two power equipment entities. The method has high precision and greatly improves the calculation efficiency.
Description
Technical Field
The invention belongs to the technical field of machine learning algorithm application, and particularly relates to an entity relationship completion method, system and application for power equipment.
Background
At present, with the continuous development of a power system and the deepening of smart grid construction, smart power distribution network power equipment has the characteristics of complex types, large data volume, complex structure and the like, so that reasonable analysis and visualization of smart power distribution network power equipment information and relations are necessary to improve and develop a power grid information system. The power equipment information of the data center is relatively complex, and the relationship between the equipment cannot be well reflected. In order to better manage and use the power equipment information of the power distribution network, a knowledge graph is constructed according to data resources related to the power equipment of the power distribution network, and the information of multiple aspects of the power equipment and the relation among the equipment can be effectively reflected. Along with the occurrence of a large number of knowledge graphs, a large amount of knowledge information is derived from documents and webpage information in the process of constructing the knowledge graphs, deviation often occurs in the process of extracting knowledge from the documents, the phenomenon that the connection relationship between the electric power equipment entities is lost or incomplete occurs, in the field of the knowledge graphs, the relationship complementation is a major key point and a difficult point, aiming at most of the existing technical models, the problem that the relationship is influenced mutually is mainly concentrated in the knowledge graphs with single relationship, and the calculation efficiency and the calculation precision are not high for complex knowledge graphs with large scale and multiple relationships. The graph-based entity relationship completion comprises a tensor decomposition embedding method and a path sorting algorithm, when the tensor decomposition embedding method is used in the process of the entity relationship completion of the knowledge graph, the entity and the relationship in the triples are trained into continuous low-dimensional vector space, the compatibility of the triples to the entity relationship correlation operation is realized, only the direct relationship between the entity and the entity in the knowledge graph is considered, the characteristics of the graph structure of the knowledge graph are ignored, and the model lacks of interpretability. The invention adopts a path sorting algorithm, generates the associated path feature set by a random walk and deep breadth first search method, combines the information stored in the relation path according to the multi-hop path between two entities in the graph, realizes the complementation of the semantic relation between the two entities, has the advantages of simple logic, easy realization and the like, and has the advantages of obviously improved calculation efficiency and accuracy, interpretability and good effect in the multi-relation large-scale knowledge graph.
Through the above analysis, the problems and defects existing in the prior art are as follows: in most of the existing technical models, the method mainly focuses on knowledge graphs with single relations, the problem of mutual influence among the relations is ignored, and for complex knowledge graphs with large scale and multiple relations, the calculation efficiency and the precision are not high.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a method, a system and an application for supplementing entity relationship for power equipment.
The invention is realized in such a way that the entity relationship completion method facing the power equipment comprises the following steps:
collecting data resources related to power equipment of a power distribution network, analyzing the collected information, extracting entities, attributes and interrelationships among the entities from various data sources, forming an ontology knowledge expression, and determining the entities and the relations to be analyzed;
step two, carrying out knowledge fusion processing on the data extracted from the data source in the step one, and finally storing the data in a knowledge base in a triplet form or importing the data into a Neo4j graph database to display the visual retrieval effect of the power equipment knowledge graph of the power distribution network;
extracting the application scene of the power equipment to be analyzed or the connection condition between the power equipment from the power equipment knowledge base obtained in the step two, acquiring the power equipment entity pairs with the same relation with the extracted power equipment entity pairs from the existing knowledge graph, and taking the association paths between the power equipment entity pairs as characteristics;
and fourthly, analyzing a group of relation paths connecting the two electric equipment entities, predicting the specific or missing relation existing between the two electric equipment entities or predicting whether the direct association path between the electric equipment entity pairs can achieve the function of the multi-hop relation path or not.
Further, the data resource of the step one power equipment comprises semi-structured or unstructured data crawled from a web page.
Further, the entity extracted from the various data sources in the step one comprises power distribution equipment in the power grid, the attribute comprises parameter, voltage, power and frequency information of each power equipment, the interrelation between the entities comprises connection conditions among the equipment and application scenes, and the application scenes comprise installation environments, installation positions and affiliated stations of the power equipment.
Further, the second step is stored in a knowledge base in a form of triples, which are respectively expressed in two ways, and the first step is that: entity, relationship, entity, the second is: entity, attribute value.
Further, the step four is to analyze a set of relationship paths connecting two electrical equipment entities, and predict a specific or missing relationship existing between the two electrical equipment entities, and the specific steps are as follows:
(1) Finding a group of potential and valuable power equipment relation paths r, screening all power equipment entity pairs (s 1, t 1) (s 2, t 2) (s 3, t 3) with the relation from the knowledge base obtained in the second step, wherein s and t respectively represent head and tail entities, taking the head and tail entities as positive examples of training samples, screening other power equipment entity pairs without the relation from the knowledge base as negative examples, or randomly replacing the head and tail entities in the positive examples to construct more negative examples;
(2) Generating and selecting a path feature set through a random walk, breadth-first search or depth-first search method, and extracting features, wherein each path is connected with two power equipment entities of each training sample;
(3) Calculating the characteristic value P (s- & gt t; pi) of each training sample j ) The characteristic value represents the path pi from the entity node s through the relationship j Probability of reaching the entity node t; or as a Boolean value, indicating whether a path pi exists between the entities s and t j The method comprises the steps of carrying out a first treatment on the surface of the Or the frequency and the frequency of the occurrence of the path between the entity s and the entity t;
(4) And training a classifier for the target relation according to the characteristic value of the training sample.
Further, in the step (4) of training the classifier for the target relationship, a scoring function is calculated
Wherein p is l Is the set of all paths linking node s and node t, θ j Is a certain path pi j P is the weight of path pi j If the score function output by the training device is larger, the probability that the two electric equipment entities have r relation is larger, and after the classifier is trained, the classifier can be used for predicting whether the target relation exists between the two electric equipment entities.
Another object of the present invention is to provide an entity relationship completion system for electric power equipment, the entity relationship completion system for electric power equipment includes:
the data acquisition module is used for acquiring data resources related to power equipment of the power distribution network;
the data analysis module is used for analyzing the acquired information, extracting entities, attributes and interrelationships among the entities from various data sources, forming an ontology knowledge expression and determining the entities and the relations to be analyzed;
the fusion processing module performs knowledge fusion processing on the data extracted from the data source, and finally stores the data in a knowledge base in a triplet form or imports the data into a Neo4j graph database to display the visual retrieval effect of the power equipment knowledge graph of the power distribution network;
the feature extraction module is used for extracting the application scene of the power equipment to be analyzed or the connection condition between the power equipment from the obtained power equipment knowledge base, acquiring the power equipment entity pairs with the same relation with the extracted power equipment entity pairs from the existing knowledge graph, and taking the association paths between the power equipment entity pairs as features;
and the relation prediction module is used for analyzing a group of relation paths connecting the two electric equipment entities and predicting specific or missing relation existing between the two electric equipment entities or multi-hop relation paths existing between the two electric equipment entities, and predicting whether the direct association paths between the electric equipment entity pairs can achieve the effect of the multi-hop relation paths.
In combination with the technical scheme and the technical problems to be solved, the technical scheme to be protected has the following advantages and positive effects:
first, aiming at the technical problems in the prior art and the difficulty in solving the problems, the technical problems solved by the technical proposal of the invention are analyzed in detail and deeply by tightly combining the technical proposal to be protected, the results and data in the research and development process, and the like, and some technical effects brought after the problems are solved have creative technical effects. The specific description is as follows:
according to the invention, collected information about power equipment of a power distribution network is analyzed, the information is stored in a knowledge base in a form of triples, a relation path to be analyzed is determined, power equipment entities with the same relation are extracted, a path feature set is generated and selected in a random walk mode and the like, so that the finite length from the head power equipment entity to the tail power entity is recorded, the random walk probability is calculated to calculate a feature value, and finally, each relation is trained by utilizing a machine learning classification algorithm, so that the weight of the path feature is obtained. The model is high in precision, the calculation efficiency is greatly improved, and an effective solution is provided for solving the problem of relationship completion of a large-scale knowledge graph.
Secondly, the technical scheme is regarded as a whole or from the perspective of products, and the technical scheme to be protected has the following technical effects and advantages:
according to the invention, the relationship among the entities is predicted through the acquired knowledge, so that the completion of the relationship among the entities can be realized, the completion of the entity type information can also be realized, and the hidden and potential missing relationship among the power equipment is completed through the relationship existing among the power equipment in the existing knowledge graph, so that the knowledge graph of the whole power equipment is further perfected, the application quality of the knowledge graph of the power equipment is improved, and the useful information is increased, thereby facilitating the subsequent work.
Thirdly, as inventive supplementary evidence of the claims of the present invention, the following important aspects are also presented:
the technical scheme of the invention overcomes the technical bias: according to the invention, semantic relation among the entities is considered, information stored in a multi-hop path combination relation path between two electric equipment entities is mined according to a constructed electric equipment knowledge graph, so that the completion of the semantic relation among the two entities is realized, the phenomena of complex and numerous equipment, weak data relation and missing or incomplete connection relation among the electric equipment entities in the existing electric power system are solved to a great extent, the relation among the electric equipment in the electric power system is more complete, and the subsequent management is facilitated. Compared with other model methods, the method has the advantages of simple logic, easy realization and the like, and in a large-scale knowledge graph with complex multi-relation, the calculation efficiency and the precision are obviously improved, and the method has the interpretability at the most important. In the aspect of storage, the Neo4j graph database stores the association information between the power equipment, compared with other relational databases, the storage efficiency and the extraction process of the data are greatly improved, the management level of the power equipment is improved, the utilization rate of the power equipment assets is improved, the safe operation of a power grid is ensured, and key technical support is provided for the data integration and intelligent application of power equipment management and manufacturing enterprises.
Drawings
FIG. 1 is a flow chart of an entity relationship completion method for power equipment provided by an embodiment of the invention;
FIG. 2 is a diagram of a power plant relationship provided by an embodiment of the present invention;
FIG. 3 is a relationship completion flow chart provided by an embodiment of the present invention;
fig. 4 is a schematic diagram of a knowledge graph structure of a power device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
1. The embodiments are explained. In order to fully understand how the invention may be embodied by those skilled in the art, this section is an illustrative embodiment in which the claims are presented for purposes of illustration.
As shown in fig. 1, the method for complementing entity relationship for electric power equipment provided by the embodiment of the invention includes:
s101, collecting data resources related to power equipment of a power distribution network, analyzing the collected information, extracting entities, attributes and interrelationships among the entities from various data sources to form an ontology knowledge expression, and determining the entities and the relations to be analyzed;
s102, carrying out knowledge fusion processing on the data extracted from the data source in the step S101, and finally storing the data in a knowledge base in a triplet form or importing the data into a Neo4j graph database to display the visual retrieval effect of the power distribution network power equipment knowledge graph;
s103, extracting the application scene of the power equipment to be analyzed or the connection condition between the power equipment from the power equipment knowledge base obtained in the step S102, acquiring the power equipment entity pairs with the same relation with the extracted power equipment entity pairs from the existing knowledge graph, and taking the association paths between the power equipment entity pairs as characteristics;
s104, analyzing a group of relation paths connecting two electric equipment entities, predicting specific or missing relation existing between the two electric equipment entities or predicting multi-hop relation paths existing between the two electric equipment entities, and predicting whether the direct association paths between the electric equipment entities can achieve the function of the multi-hop relation paths.
Examples:
an entity relationship completion method for power equipment comprises the following steps:
1) The method comprises the steps of collecting data resources related to power equipment of a power distribution network, wherein entities in a knowledge graph comprise power distribution equipment such as buses, transformers, lines, switches, loads and capacitors in the power grid, relationships among the entities comprise connection conditions among the equipment and application scenes, the application scenes comprise installation environments and installation positions of the power equipment, the power stations belong to the power stations and the like, and attributes of the entities comprise parameters, voltage, power, frequency and other information of the power equipment.
2) Building a knowledge graph based on the power equipment information, as shown in fig. 4:
2-1) information extraction: extracting entities from the database in the step 1), wherein the entities comprise names of electric equipment such as transformers and automatic regulators, the installation environment positions are suburbs and rural areas, the attributes belong to plant stations and the like, and the interrelationships among the entities form an ontology knowledge expression;
2-2) carrying out entity linking on the data extracted from the information in the step 2-1), selecting a group of candidate entity objects from a knowledge base according to entity index items obtained by entity extraction, and linking the entity index items to correct entity object knowledge processing through similarity calculation.
2-3) constructing a knowledge graph in a bottom-up mode, repeating the steps 2-1) -2-3 in each round of iterative updating to obtain entity nodes and attributes in the knowledge graph based on the power equipment information;
3) Feature extraction, taking the installation environment in an application scene as an example of the relationship of the stations:
3-1) screening out all pairs of electric equipment entities (s 1, t 1) (s 2, t 2) (s 3, t 3) having the same relation from the knowledge graph constructed in the step 2), wherein s and t respectively represent head and tail entities, taking the s and t as positive examples of training samples, taking fig. 2 as examples, giving a target relation r2, wherein the positive examples are (equipment 2, equipment 4), and the negative examples are (equipment 2, equipment 1) (equipment 1, equipment 4) (equipment 1, equipment 3), wherein the negative examples are other pairs of electric equipment entities which do not have the relation, and the negative examples are (equipment 2, equipment 1) (equipment 1, equipment 3);
3-2) generating and selecting multi-hop associated paths such as path feature sets (r 1, r 2), (r 1, r 3), (r 2, r 3) through methods such as random walk, breadth-first search, depth-first search and the like, wherein each path links the two power equipment entities of each training sample. Namely (device 2, device 4) corresponding path: (r 1, r 3), (device 2, device 1) corresponding path: (inverse relation of r2, r 3), (path corresponding to device 1, device 4): (r 1, r 4), (device 1, device 3) corresponding path: (r 3, r 4).
3-3) according to step 3-2), a pair of entities (s 1, t 1) and a path pi are given j The characteristic value is calculated as random walking probability P (s- & gt t & pi j ) I.e. the probability of reaching t given a random value starting from entity s, and pi j The relationship contained in the database.
4) Training the classifier according to the training samples:
4-1) calculating a scoring function based on the feature values calculated in step 3-3)
Wherein p is l Is the set of all paths linking node s and node t, θ j Is a certain path pi j P is the weight of path pi j Probability value size of (c). The method comprises the steps of carrying out a first treatment on the surface of the
4-2) outputting the score function of the trainer in step 4-1), wherein the larger the value is, the larger the probability that the two electric equipment entities have the target relationship is.
2. Application example. In order to prove the inventive and technical value of the technical solution of the present invention, this section is an application example on specific products or related technologies of the claim technical solution.
A computer device, characterized in that the computer device comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the power device oriented entity relationship completion method.
A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the power device oriented entity relationship completion method.
The information data processing terminal is characterized by being used for realizing the step of the entity relationship completion method facing the power equipment.
It should be noted that the embodiments of the present invention can be realized in hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those of ordinary skill in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The device of the present invention and its modules may be implemented by hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., as well as software executed by various types of processors, or by a combination of the above hardware circuitry and software, such as firmware.
3. Evidence of the effect of the examples. The embodiment of the invention has a great advantage in the research and development or use process, and has the following description in combination with data, charts and the like of the test process.
In the aspect of storage, the Neo4j graph database is used for storing the power equipment, compared with other relational databases, the performance is greatly improved, and the relational databases can support single relational query with foreign keys among tables and are not good at processing complex relations. When the number of columns in the table is reduced, the structural requirement is reduced, the empty problem is alleviated, but the query will involve more tables; when the number of columns in the table increases and the correlation between the knowledge is not strong, more null values will be generated. The graphic database takes nodes and edges as basic storage units and stores the nodes and edges in the form of triples, the main bodies and the objects of the triples correspond to vertexes in the graphic from the perspective of a graphic data model, the attributes correspond to directed edges, and the distributed storage and parallel processing of mass data with complex association can be realized based on the storage mode. The graph structure can directly map the triplet model, avoids data conversion to adapt to a storage structure, aims at performance reduction caused by connection of a large number of tables in a traditional relational database, can traverse nodes and edges in parallel, does not influence traversing speed in the graph, and supports large-scale expandability.
On the basis of a path sorting algorithm, the method for carrying out the entity relationship completion of the power equipment generates an associated path feature set by a random walk and deep breadth-first search method, and realizes the completion of the semantic relationship between two entities according to the information stored in the multi-hop path combination relationship path between the two entities in the graph. For the tensor decomposition model, the entity and the relation in the triplet are trained into a continuous low-dimensional vector space, so that the compatibility of the triplet for entity relation correlation operation is realized, only the direct relation between the entity and the entity in the knowledge graph is considered, and the semantic relation and the mutual influence between the relations are not considered. In the algorithm design process, because different relationships can influence each other, not only the topology information of adjacent nodes of the target relationship but also the topology information of other relationships are needed to be considered, and the influence of other relationships on the target relationship can be completely different. For example, a transformer is normally connected with a certain device under a parameter environment such as temperature, humidity and the like, but not all transformers can be normally connected with a device with the same attribute under the condition, and other related information of the device with the same attribute needs to be considered. Therefore, considering semantic relation among the relations is helpful to improve the precision of the link prediction result and has interpretability.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.
Claims (10)
1. The utility model provides an entity relationship completion method facing to electric power equipment, which is characterized in that the entity relationship completion method facing to electric power equipment comprises the following steps:
collecting data resources related to power equipment of a power distribution network, analyzing the collected information, extracting entities, attributes and interrelationships among the entities from various data sources, forming an ontology knowledge expression, and determining the entities and the relations to be analyzed;
step two, carrying out knowledge fusion processing on the data extracted from the data source in the step one, and finally storing the data in a knowledge base in a triplet form or importing the data into a Neo4j graph database to display the visual retrieval effect of the power equipment knowledge graph of the power distribution network;
extracting the application scene of the power equipment to be analyzed or the connection condition between the power equipment from the power equipment knowledge base obtained in the step two, acquiring the power equipment entity pairs with the same relation with the extracted power equipment entity pairs from the existing knowledge graph, and taking the association paths between the power equipment entity pairs as characteristics;
and fourthly, analyzing a group of relation paths connecting the two electric equipment entities, predicting the specific or missing relation existing between the two electric equipment entities or predicting whether the direct association path between the electric equipment entity pairs can achieve the function of the multi-hop relation path or not.
2. The method for supplementing physical relationships to a power device according to claim 1, wherein the step of providing the data resource of the power device includes climbing out semi-structured or unstructured data from a web page.
3. The method for supplementing entity relationship to electric power equipment according to claim 1, wherein the entity extracted from various types of data sources in the step one comprises power distribution equipment in a power grid, the attribute comprises parameters, voltages, power and frequency information of each electric power equipment, the interrelation between the entities comprises connection conditions between the equipment and application scenes, and the application scenes comprise installation environments, installation positions and plant stations of the electric power equipment.
4. The method for supplementing entity relationships to power devices according to claim 1, wherein the second step is stored in a knowledge base in a form of triples, which are respectively expressed in two ways, and the first step is that: entity, relationship, entity, the second is: entity, attribute value.
5. The method for supplementing entity relationship to power equipment according to claim 1, wherein the fourth step is to analyze a set of relationship paths connecting two power equipment entities and predict a specific or missing relationship existing between the two power equipment entities, and the specific steps are as follows:
(1) Finding a group of potential and valuable power equipment relation paths r, screening all power equipment entity pairs (s 1, t 1) (s 2, t 2) (s 3, t 3) with the relation from the knowledge base obtained in the second step, wherein s and t respectively represent head and tail entities, taking the head and tail entities as positive examples of training samples, screening other power equipment entity pairs without the relation from the knowledge base as negative examples, or randomly replacing the head and tail entities in the positive examples to construct more negative examples;
(2) Generating and selecting a path feature set through a random walk, breadth-first search or depth-first search method, and extracting features, wherein each path is connected with two power equipment entities of each training sample;
(3) Calculating the characteristic value P (s- & gt t; pi) of each training sample j ) The characteristic value represents the slaveThe entity node s starts out and passes through the relation path pi j Probability of reaching the entity node t; or as a Boolean value, indicating whether a path pi exists between the entities s and t j The method comprises the steps of carrying out a first treatment on the surface of the Or the frequency and the frequency of the occurrence of the path between the entity s and the entity t;
(4) And training a classifier for the target relation according to the characteristic value of the training sample.
6. The method of claim 5, wherein the step (4) is to calculate a scoring function in the target relationship training classifier
Wherein p is l Is the set of all paths linking node s and node t, θ j Is a certain path pi j P is the weight of path pi j If the score function output by the training device is larger, the probability that the two electric equipment entities have r relation is larger, and after the classifier is trained, the classifier can be used for predicting whether the target relation exists between the two electric equipment entities.
7. An electrical equipment-oriented entity relationship completion system for implementing the electrical equipment-oriented entity relationship completion method of any one of claims 1 to 6, characterized in that the electrical equipment-oriented entity relationship completion system comprises:
the data acquisition module is used for acquiring data resources related to power equipment of the power distribution network;
the data analysis module is used for analyzing the acquired information, extracting entities, attributes and interrelationships among the entities from various data sources, forming an ontology knowledge expression and determining the entities and the relations to be analyzed;
the fusion processing module performs knowledge fusion processing on the data extracted from the data source, and finally stores the data in a knowledge base in a triplet form or imports the data into a Neo4j graph database to display the visual retrieval effect of the power equipment knowledge graph of the power distribution network;
the feature extraction module is used for extracting the application scene of the power equipment to be analyzed or the connection condition between the power equipment from the obtained power equipment knowledge base, acquiring the power equipment entity pairs with the same relation with the extracted power equipment entity pairs from the existing knowledge graph, and taking the association paths between the power equipment entity pairs as features;
and the relation prediction module is used for analyzing a group of relation paths connecting the two electric equipment entities and predicting specific or missing relation existing between the two electric equipment entities or multi-hop relation paths existing between the two electric equipment entities, and predicting whether the direct association paths between the electric equipment entity pairs can achieve the effect of the multi-hop relation paths.
8. A computer device comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to perform the steps of the power device oriented entity relationship completion method of any of claims 1 to 6.
9. A computer readable storage medium storing a computer program which, when executed by a processor, causes the processor to perform the steps of the power device oriented entity relationship completion method of any of claims 1 to 6.
10. An information data processing terminal, characterized in that the information data processing terminal is configured to implement the steps of the power-equipment-oriented entity relationship completion method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211694098.6A CN116011564A (en) | 2022-12-28 | 2022-12-28 | Entity relationship completion method, system and application for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211694098.6A CN116011564A (en) | 2022-12-28 | 2022-12-28 | Entity relationship completion method, system and application for power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116011564A true CN116011564A (en) | 2023-04-25 |
Family
ID=86031203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211694098.6A Pending CN116011564A (en) | 2022-12-28 | 2022-12-28 | Entity relationship completion method, system and application for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116011564A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116955648A (en) * | 2023-07-19 | 2023-10-27 | 上海企卓元科技合伙企业(有限合伙) | Knowledge graph analysis method based on non-privacy data association |
-
2022
- 2022-12-28 CN CN202211694098.6A patent/CN116011564A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116955648A (en) * | 2023-07-19 | 2023-10-27 | 上海企卓元科技合伙企业(有限合伙) | Knowledge graph analysis method based on non-privacy data association |
| CN116955648B (en) * | 2023-07-19 | 2024-01-26 | 上海企卓元科技合伙企业(有限合伙) | Knowledge graph analysis method based on non-privacy data association |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jain et al. | Data mining techniques: a survey paper | |
| Angles | A comparison of current graph database models | |
| CN110059181A (en) | Short text stamp methods, system, device towards extensive classification system | |
| CN107291895B (en) | Quick hierarchical document query method | |
| WO2023155508A1 (en) | Graph convolutional neural network and knowledge base-based paper correlation analysis method | |
| CN103761286B (en) | A kind of Service Source search method based on user interest | |
| CN112685570A (en) | Multi-label graph-based power grid network frame knowledge graph construction method | |
| CN115438199A (en) | Knowledge platform system based on smart city scene data middling platform technology | |
| CN115017315A (en) | Leading edge theme identification method and system and computer equipment | |
| CN117556369A (en) | Power theft detection method and system for dynamically generated residual error graph convolution neural network | |
| CN116011564A (en) | Entity relationship completion method, system and application for power equipment | |
| Hu et al. | EGC: A novel event-oriented graph clustering framework for social media text | |
| CN115757810A (en) | Method for constructing standard ontology of knowledge graph | |
| Ma et al. | Matching descriptions to spatial entities using a Siamese hierarchical attention network | |
| CN117010373A (en) | Recommendation method for category and group to which asset management data of power equipment belong | |
| Hu et al. | Research on modeling of power grid information system based on knowledge graph | |
| CN116401338A (en) | Design feature extraction and attention mechanism based on data asset intelligent retrieval input and output requirements and method thereof | |
| Wu et al. | A summary of the latest research on knowledge graph technology | |
| Zheng | Individualized Recommendation Method of Multimedia Network Teaching Resources Based on Classification Algorithm in a Smart University | |
| Chen et al. | Research and application of cluster analysis algorithm | |
| Eibeck et al. | A simple and efficient approach to unsupervised instance matching and its application to linked data of power plants | |
| Chen et al. | Pre-training models based knowledge graph multi-hop reasoning for smart grid technology | |
| Cao et al. | A survey on visual data mining techniques and applications | |
| Bae et al. | SD-Miner: A spatial data mining system | |
| Wang | Network analytics er model–towards a conceptual view of network analytics |
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 |