Cross-domain semantic mapping and reasoning method and system

Abstract

The invention discloses a cross-domain semantic mapping and reasoning method and system. The method comprises the steps of obtaining first data and second data of target power grid equipment, and performing first preprocessing on the first data and the second data; presetting a first semantic algorithm, and performing semantic element extraction on the first data through the first semantic algorithm to obtain first extraction data; establishing a first mapping relationship between the first extracted data and the second data, and optimizing the first mapping relationship in combination with a first optimization algorithm; and performing cross-domain semantic mapping and reasoning according to the optimized first mapping relation. The efficiency of power grid equipment management is improved, errors and deviations caused by manual interpretation of standard terms are reduced, and the comprehensiveness and scientificity of power grid equipment management are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power networks, and in particular, to a cross - domain semantic mapping and reasoning method and system. Background Art

[0002] With the continuous development and expansion of the power grid, the types and quantities of power grid equipment are increasing day by day, and the management requirements for power grid equipment are also getting higher and higher. The standard terms of power grid equipment cover knowledge in multiple professional fields, including electrical engineering, mechanical engineering, materials science, etc. However, due to the semantic understanding differences between different fields, there are certain difficulties in the interpretation and implementation of the standard terms of power grid equipment in practical applications.

[0003] Currently, in the management of power grid equipment, the method of manually interpreting standard terms is usually adopted. This method not only has low efficiency, but also is prone to understanding deviations and errors. In addition, when professionals in different fields interpret the standard terms of power grid equipment, they often only focus on the knowledge in their own fields and lack cross - domain comprehensive analysis and understanding, resulting in the management of power grid equipment being insufficiently comprehensive and scientific.

[0004] To solve the above problems, there is an urgent need for a cross - domain semantic mapping and reasoning method for the standard terms of power grid equipment, which can automatically realize semantic understanding and association between standard terms in different fields, improve the efficiency and safety of power grid equipment management, and provide a strong guarantee for the stable operation of the power grid. Summary of the Invention

[0005] The purpose of this part is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this part, as well as in the abstract and title of the specification of this application, to avoid obscuring the purpose of this part, the abstract, and the title. However, such simplifications or omissions shall not be used to limit the scope of the present invention.

[0006] In view of the above - mentioned existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a cross - domain semantic mapping and reasoning method and system, which can solve the problems mentioned in the background art.

[0008] To solve the above technical problems, the present invention provides the following technical solutions:

[0009] In the first aspect, the present invention provides a cross - domain semantic mapping and reasoning method, including:

[0010] Obtain the first data and the second data of the target power grid equipment, and perform a first pre - processing on the first data and the second data;

[0011] Preset a first semantic algorithm, and extract semantic elements from the first data through the first semantic algorithm to obtain first extraction data;

[0012] Establish a first mapping relationship regarding the first extraction data and the second data, and optimize the first mapping relationship in combination with a first optimization algorithm;

[0013] Perform cross-domain semantic mapping and reasoning according to the optimized first mapping relationship.

[0014] As a preferred solution of the cross-domain semantic mapping and reasoning method of the present invention, wherein: the first semantic algorithm includes:

[0015] The first semantic algorithm is any algorithm for extracting target semantic elements from the first data;

[0016] The target semantic elements at least include a first attribute element, a first state element, and a first structured element.

[0017] As a preferred solution of the cross-domain semantic mapping and reasoning method of the present invention, wherein: the first optimization algorithm includes:

[0018] The first optimization algorithm is any algorithm for optimizing the first mapping relationship;

[0019] The first optimization algorithm at least includes configuring a first constraint, and the first constraint is used to constrain the first mapping relationship after the optimization is completed to obtain a first mapping relationship that meets the constraint conditions.

[0020] As a preferred solution of the cross-domain semantic mapping and reasoning method of the present invention, wherein: the first mapping relationship includes:

[0021] Match the target semantic elements extracted from the first data with the second data in combination with a first mapping model;

[0022] The first mapping model is any model with the target semantic elements and the second data as inputs and the first mapping relationship or relevant parameters that can directly or indirectly obtain the first mapping relationship as outputs.

[0023] As a preferred solution of the cross-domain semantic mapping and reasoning method of the present invention, wherein: the target semantic elements further include:

[0024] The first attribute element is the physical characteristic of the power grid equipment;

[0025] The first state element is the operating state of the power grid equipment;

[0026] The first structured element is the structural information of the power grid equipment.

[0027] As a preferred solution of the cross - domain semantic mapping and reasoning method described in the present invention, wherein: the first constraint includes:

[0028] A preset optimization objective constraint;

[0029] Obtain a first mapping relationship that satisfies the optimization objective constraint;

[0030] Perform cross - domain semantic mapping and reasoning according to the first mapping relationship that satisfies the optimization objective constraint.

[0031] As a preferred solution of the cross - domain semantic mapping and reasoning method described in the present invention, wherein: performing cross - domain semantic mapping and reasoning according to the first mapping relationship that satisfies the optimization objective constraint includes:

[0032] Obtain real - time first data of the target power grid equipment;

[0033] Determine real - time second data after mapping of the real - time first data according to the first mapping relationship that satisfies the optimization objective constraint;

[0034] The second data is the result of cross - domain semantic mapping and reasoning.

[0035] In a second aspect, the present invention provides a cross - domain semantic mapping and reasoning system, including:

[0036] A data processing module, configured to obtain first data and second data of the target power grid equipment, and perform first pre - processing on the first data and the second data;

[0037] A semantic extraction module, configured to preset a first semantic algorithm, and extract semantic elements from the first data through the first semantic algorithm to obtain first extraction data;

[0038] A relationship establishment module, configured to establish a first mapping relationship between the first extraction data and the second data, and optimize the first mapping relationship in combination with a first optimization algorithm;

[0039] An inference module, configured to perform cross - domain semantic mapping and reasoning according to the optimized first mapping relationship.

[0040] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method described above are implemented.

[0041] In a fourth aspect, the present invention provides a computer - readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a cross-domain semantic mapping and reasoning method and system, which acquires first data and second data of target power grid equipment, and performs first preprocessing on the first data and the second data; presets a first semantic algorithm, and extracts semantic elements from the first data through the first semantic algorithm to obtain first extraction data; establishes a first mapping relationship between the first extraction data and the second data, and optimizes the first mapping relationship by combining a first optimization algorithm; performs cross-domain semantic mapping and reasoning according to the optimized first mapping relationship. It can automatically realize semantic understanding and association of power grid equipment standard terms between different domains, improve the efficiency and safety of power grid equipment management, and provide a strong guarantee for the stable operation of the power grid. By using the preset semantic algorithm and optimization algorithm, the present invention can effectively extract key semantic elements of power grid equipment and establish an accurate mapping relationship, so as to realize cross-domain semantic mapping and reasoning. In addition, the present invention can also process real-time data to ensure the real-time and accuracy of power grid equipment management. Through these technical solutions, the present invention not only improves the efficiency of power grid equipment management, but also reduces errors and deviations caused by manual interpretation of standard terms, ensuring the comprehensiveness and scientificity of power grid equipment management. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings. Among them:

[0044] Figure 1 It is a method flow chart of a cross-domain semantic mapping and reasoning method and system provided by an embodiment of the present invention;

[0045] Figure 2 It is an internal structure diagram of a computer device of a cross-domain semantic mapping and reasoning method and system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0047] Embodiment 1

[0048] Reference Figure 1 - Figure 2 , which is the first embodiment of the present invention. This embodiment provides a cross - domain semantic mapping and reasoning method and system, including:

[0049] In the existing related technologies, there are some problems. For example, the phenomenon of data islands is serious, and it is difficult to effectively share and integrate data between different fields; the semantic understanding is inconsistent, resulting in understanding deviations when processing cross - domain data; and the reasoning ability is limited, making it difficult to handle complex and variable cross - domain reasoning tasks.

[0050] This application provides a method that can effectively solve the above - mentioned problems. Next, multiple embodiments will be combined to elaborate in detail how to implement the cross - domain semantic mapping and reasoning method for the standard terms of power grid equipment;

[0051] Figure 1 The method flow chart of a cross - domain semantic mapping and reasoning method and system is shown, including:

[0052] S101, obtain the first data and the second data of the target power grid equipment, and perform a first pre - processing on the first data and the second data;

[0053] In an optional embodiment, the target power grid equipment can be different equipment in the power grid, such as transformers, circuit breakers, disconnectors, etc. The means of obtaining the data of these target power grid equipment can include various methods, and can be specifically designed according to actual needs;

[0054] In an optional embodiment, the means of obtaining the data of these target power grid equipment include sensor monitoring, manual input, or receiving through a network interface;

[0055] In another optional embodiment, the target power grid equipment data may be data related to the standard terms of power grid equipment, and the standard terms of power grid equipment are extracted from these related data, and the standard terms of power grid equipment are used as the first data for subsequent processing;

[0056] In an optional embodiment, the second data is knowledge nodes or knowledge graphs in different related fields of the target power grid. These knowledge nodes or knowledge graphs can be information such as the operating status of the power grid, the maintenance history of power grid equipment, and power grid equipment failure cases. Through these knowledge nodes or knowledge graphs, in - depth analysis and reasoning of power grid equipment can be realized, thereby providing decision - making support for the stable operation of the power grid.

[0057] In an optional embodiment, the first pre - processing step may include data cleaning, format conversion, and standardization processing to ensure data quality and provide a consistent data format for subsequent processing steps.

[0058] In an alternative embodiment, the first preprocessing may further include semantic parsing of the grid equipment standard terms, extracting key information, and establishing a corresponding semantic model.

[0059] In the embodiments of the present application, the first data is the grid equipment standard terms, and specifically, the second data is the knowledge nodes in different related fields of the target grid.

[0060] In the embodiments of the present application, the first preprocessing includes semantic parsing of the grid equipment standard terms, extracting key information, and establishing a corresponding semantic model.

[0061] Exemplarily, the corresponding semantic model is established by using semantic modeling techniques known in the art, such as ontology construction and semantic network techniques, to realize the mapping relationship between the grid equipment standard terms and the knowledge nodes. This semantic model can capture and express the implicit semantic information in the grid equipment standard terms and associate it with the relevant data in the knowledge nodes.

[0062] It should be noted that in this way, the system can understand the semantic connections between different data sources, so that when performing cross-domain reasoning, it can more accurately identify and process information.

[0063] In the embodiments of the present application, the grid equipment standard terms may include the detailed specifications of various types of grid equipment, such as transformers, circuit breakers, relays, etc., as well as their operating parameters, performance indicators, and maintenance requirements. These terms are usually formulated by professional institutions to ensure the standardization and interoperability of grid equipment. Through semantic parsing, the system can identify key information such as equipment types, function descriptions, and applicable scopes in the terms and convert them into a structured data form for subsequent processing and analysis.

[0064] In the embodiments of the present application, the knowledge nodes in different fields include key information such as power system operating status, grid fault diagnosis, load forecasting, equipment maintenance plans, etc. These knowledge nodes establish a mapping relationship with the grid equipment standard terms through the semantic model, enabling the system to perform intelligent analysis and decision-making based on real-time data and historical data. For example, in power system operating status monitoring, the system can compare the real-time operating data of the transformer with the performance indicators in the standard terms, timely discover potential fault risks, and propose corresponding maintenance suggestions.

[0065] In the embodiments of the present application, the semantic model also supports dynamic updates and can continuously optimize and adjust the mapping relationship with the changes in the grid operating status and the accumulation of new knowledge to meet the real-time needs of the grid.

[0066] It should be noted that obtaining the first data and the second data of the target power grid equipment and performing the first preprocessing on the first data and the second data can ensure the accuracy and consistency of the data, providing a solid foundation for subsequent semantic element extraction and mapping relationship establishment. Through the first preprocessing, noise and inconsistencies in the data can be removed, ensuring data quality, thereby improving the accuracy and reliability of the entire cross-domain semantic mapping and reasoning process. In addition, the first preprocessing can also help the system better understand the semantic content of the power grid equipment standard terms, laying a foundation for subsequent semantic element extraction and mapping relationship establishment. Through such preprocessing steps, the system can more effectively identify and process the key information in the power grid equipment standard terms, providing support for establishing accurate mapping relationships and performing effective cross-domain reasoning.

[0067] S102, preset a first semantic algorithm, and extract semantic elements from the first data through the first semantic algorithm to obtain first extraction data;

[0068] In the embodiment of the present application, the first semantic algorithm includes:

[0069] The first semantic algorithm is any algorithm for extracting target semantic elements from the first data;

[0070] The target semantic elements at least include a first attribute element, a first status element, and a first structured element.

[0071] In an alternative embodiment, the first semantic algorithm can use natural language processing techniques based on deep learning, such as recurrent neural networks (RNNs) or long short-term memory networks (LSTMs), to achieve semantic understanding of power grid equipment standard terms. These algorithms can process sequential data and capture long-distance dependencies, thereby more accurately extracting the key semantic information in the terms. By training these models, the system can learn the complex relationships between different semantic elements, further improving the accuracy of mapping and reasoning. In addition, in order to adapt to the specific domain knowledge of power grid equipment standard terms, the algorithm can be customized, such as introducing domain-specific vocabulary and rules, to enhance the model's ability to understand professional terms.

[0072] In an alternative embodiment, the first semantic algorithm can also use a Transformer model based on the attention mechanism. This model can process all positions in the input sequence simultaneously through the self-attention mechanism, thus more effectively capturing global dependencies. Such a model is particularly suitable for processing long text data, can provide richer semantic representations, and helps to improve the performance of semantic mapping and reasoning. In addition, to further optimize the performance, pre-trained language models such as BERT or GPT can also be combined. These models are pre-trained on large-scale corpora and can capture deeper language rules and patterns, providing strong support for the semantic understanding of grid equipment standard terms.

[0073] In an alternative embodiment, the first semantic algorithm can also use a rule-based method to identify and extract key elements in grid equipment standard terms by defining a series of semantic rules. This method relies on expert knowledge and can accurately locate specific semantic information in the terms, such as equipment models, parameter ranges, etc. In this way, the system can convert unstructured text data into structured data for subsequent processing and analysis.

[0074] In the embodiment of the present application, the target semantic elements further include:

[0075] The first attribute element is the physical characteristics of the grid equipment;

[0076] The first state element is the operating state of the grid equipment;

[0077] The first structured element is the structural information of the grid equipment.

[0078] In the embodiment of the present application, the specific operation steps of the first semantic algorithm are as follows:

[0079] Perform word segmentation on the grid equipment standard terms to decompose the text into individual lexical units;

[0080] For example, when processing the term "transformer", the system will identify its attribute as an equipment name and associate it with relevant parameters such as rated power and voltage level.

[0081] Use natural language processing techniques, such as part-of-speech tagging, to identify the grammatical functions and semantic categories of each lexical unit;

[0082] For example, when the lexical unit "transformer" is tagged as a noun and its role in the sentence, such as the subject or object, is identified. Then, the system will further analyze the relationship between lexical units, such as the relationship between "transformer" and "rated power", and determine that they are the relationship between attribute and value.

[0083] Extract semantic elements related to power grid equipment according to the professional knowledge of power grid equipment, such as equipment models, parameter ranges, function descriptions, etc.;

[0084] For example, when taking key information such as the rated power, voltage level, cooling method, etc. of a transformer as the attribute elements of the equipment;

[0085] Furthermore, take the operating status of the transformer, such as load rate, temperature, etc. as the status elements;

[0086] Furthermore, take the internal structure information of the transformer, such as winding arrangement, core structure, etc. as the structured elements.

[0087] Furthermore, through the extraction of these semantic elements, the system can build a semantic model containing detailed information of power grid equipment.

[0088] Perform structured processing on the extracted semantic elements to form a structured semantic model for subsequent mapping and reasoning operations.

[0089] It should be noted that a first semantic algorithm is preset. By using the first semantic algorithm to extract semantic elements from the first data, the obtained first extraction data improves the efficiency of data processing because the preset algorithm can quickly identify and extract key information. It enhances the flexibility of the system and allows accurate semantic analysis of different types of power grid equipment data. Through the first semantic algorithm, the system can automatically identify and learn new semantic patterns, thereby continuously optimizing the accuracy of semantic element extraction. The first extraction data provides a solid foundation for subsequent semantic mapping and reasoning, ensuring the stability and reliability of the entire system.

[0090] S103, establish a first mapping relationship between the first extraction data and the second data, and optimize the first mapping relationship in combination with the first optimization algorithm;

[0091] In the embodiments of the present application, the first optimization algorithm includes:

[0092] The first optimization algorithm is any algorithm for optimizing the first mapping relationship;

[0093] The first optimization algorithm at least includes configuring a first constraint, and the first constraint is used to constrain the first mapping relationship after optimization to obtain a first mapping relationship that meets the constraint conditions.

[0094] In an alternative embodiment, the first optimization algorithm can be optimized using a genetic algorithm. A genetic algorithm is a search and optimization algorithm that mimics natural selection and genetic mechanisms. It iteratively optimizes the first mapping relationship through operations such as selection, crossover, and mutation in order to achieve a global optimal solution. In practical applications, genetic algorithms can handle complex optimization problems and have good robustness and global search capabilities. By setting an appropriate fitness function, it can be ensured that the optimization process proceeds in a direction to improve the accuracy of the mapping relationship. In addition, the parallel processing ability of genetic algorithms also makes them highly efficient when dealing with large-scale data.

[0095] In an alternative embodiment, the first optimization algorithm can also be optimized using a particle swarm optimization algorithm. Particle swarm optimization algorithm is an optimization technique based on swarm intelligence. It mimics the foraging behavior of bird flocks and searches the solution space through the interaction between particles. Each particle represents a potential solution in the problem space and updates its velocity and position by tracking its own historical best position and the historical best position of the swarm. This algorithm is simple and easy to implement and has good search capabilities in multi-dimensional spaces. It is suitable for dealing with continuous and discrete optimization problems. By adjusting parameters in the particle swarm algorithm, such as learning factors and inertia weights, the convergence speed and the quality of the solution can be further improved.

[0096] In the embodiments of the present application, the first optimization algorithm at least includes configuring a first constraint. The first constraint is used to constrain the first mapping relationship after the optimization is completed to obtain a first mapping relationship that satisfies the constraint conditions. The first constraint here is to ensure the accuracy and rationality of the mapping relationship. For example, constraint conditions can be set to ensure that the key information in the grid equipment standard terms can correctly correspond to the data in the knowledge nodes, avoiding logical contradictions or inconsistencies. Through such constraints, the quality of the mapping relationship can be improved and the reliability of the inference results can be ensured.

[0097] In an alternative embodiment, the first constraint can be a rule-based constraint. This rule is defined based on the logical relationship between the grid equipment standard terms and the knowledge nodes. For example, ensuring that the rated power of the transformer matches the actual operating data, or the voltage level of the circuit breaker is suitable for the grid operating state.

[0098] In an alternative embodiment, the first constraint can also be a case-based constraint that determines the mapping relationship between the standard terms of grid equipment and knowledge nodes by analyzing historical case data. For example, by reviewing past transformer failure cases, it can be found that a specific type of transformer is prone to overload problems under specific conditions, so these conditions are specially marked during the mapping process to improve the accuracy of future fault prediction. This case-based constraint helps the system learn and adapt to the specific behavior patterns of grid equipment, thus providing more accurate mapping and reasoning results in practical applications.

[0099] In the embodiment of the present application, the first constraint selects a case-based constraint;

[0100] In the embodiment of the present application, the first constraint includes:

[0101] A preset optimization objective constraint;

[0102] Obtain a first mapping relationship that satisfies the optimization objective constraint;

[0103] Perform cross-domain semantic mapping and reasoning based on the first mapping relationship that satisfies the optimization objective constraint.

[0104] In the embodiment of the present application, the preset optimization objective constraint is to reduce the mapping error rate, improve the mapping efficiency, or optimize the accuracy of the mapping result. Specifically:

[0105] The preset optimization objective constraint is achieved by setting a threshold value that defines the maximum acceptable range of the mapping error rate.

[0106] It should be noted that the system will adjust the mapping algorithm according to historical data and real-time feedback to ensure that the error rate is always lower than the threshold value. At the same time, the improvement of the mapping efficiency can be achieved by optimizing the computational complexity of the algorithm. For example, by adopting more efficient search strategies and data structures to reduce the computational time. As for the optimization of the accuracy of the mapping result, it may involve continuous learning and adjustment of the mapping rules to adapt to changes in the behavior patterns of grid equipment. Through the comprehensive consideration of these optimization objectives, the system can provide more reliable and efficient cross-domain semantic mapping and reasoning services.

[0107] Exemplarily, the threshold value can be set to 0.05, which means that the mapping error rate must be lower than 5%. The system will regularly check the mapping error rate and compare it with the threshold value. If the error rate exceeds the threshold value, the system will automatically trigger an optimization program to adjust the mapping algorithm parameters to reduce the error rate. In addition, the system can also dynamically adjust the threshold value according to different application scenarios and the characteristics of grid equipment to achieve the best mapping effect.

[0108] In the embodiment of the present application, the first mapping relationship includes:

[0109] The target semantic elements extracted from the first data are combined with the first mapping model to match the target semantic elements with the second data;

[0110] The first mapping model is any model with the target semantic elements and the second data as inputs and the first mapping relationship or relevant parameters from which the first mapping relationship can be directly or indirectly obtained as outputs.

[0111] In an alternative embodiment, the first mapping model can use a deep learning model, which is trained with a large amount of historical data and can learn complex non-linear mapping relationships. The model can be a convolutional neural network (CNN), a recurrent neural network (RNN), or a long short-term memory network (LSTM), etc., depending on the nature of the mapping task and the characteristics of the data. During the training process, the model continuously adjusts its internal parameters to minimize the difference between the predicted output and the actual output. In this way, the first mapping model can capture the deep features in the data and achieve high-precision matching during the mapping process.

[0112] In an alternative embodiment, the first mapping model can also use a deep learning model based on the attention mechanism, such as the Transformer model. This model can effectively capture the long-range dependencies in the sequence data through the self-attention mechanism, and thus can better understand the context information when processing semantic mapping tasks. This feature of the Transformer model has achieved remarkable results in the field of natural language processing, especially in machine translation, text summarization, and question-answering systems. In the cross-domain semantic mapping and reasoning system, the Transformer model can be trained to identify and associate the key semantic information between different domains, thereby improving the accuracy of mapping and the rationality of reasoning.

[0113] In the embodiments of the present application, the first mapping model is any model with the target semantic elements and the second data as inputs and the first mapping relationship or relevant parameters from which the first mapping relationship can be directly or indirectly obtained as outputs;

[0114] The present application selects the most basic neural network for model training. Using the most basic neural network can simplify the operation steps and reduce the demand for computing resources.

[0115] In an optional embodiment, the training process of the basic neural network is relatively simple, easy to understand and implement, which makes it particularly useful in the preliminary research and development stage. However, in order to further improve the mapping accuracy and the generalization ability of the model, this application may also adopt more complex neural network structures, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs), which perform excellently in processing image and sequence data. Through these advanced network structures, complex patterns and features in the data can be better captured, thus achieving better performance in the cross-domain semantic mapping and reasoning system.

[0116] It should be noted that this application does not limit the training steps of the first mapping model, and relevant technical personnel can design according to actual needs. However, the input of the first mapping model is the target semantic element and the second data, and the output is the first mapping relationship or relevant parameters that can directly or indirectly obtain the first mapping relationship. This is the part designed by this application. Therefore, no matter what operations relevant technical personnel perform to obtain the first mapping relationship or relevant parameters that can directly or indirectly obtain the first mapping relationship through the target semantic element and the second data, such operations should be within the protection scope of this application.

[0117] It should be noted that establishing the first mapping relationship between the first extracted data and the second data and optimizing the first mapping relationship in combination with the first optimization algorithm improves the accuracy of the mapping relationship and ensures the minimization of information loss during the data conversion process. Through the iteration of the optimization algorithm, the mapping relationship is continuously adjusted and improved to adapt to the characteristics of different data sets. The optimized mapping relationship can better adapt to new data inputs, enhancing the adaptability and flexibility of the system. The optimization process can also reduce the consumption of computing resources and improve the overall operating efficiency of the system.

[0118] S104, perform cross-domain semantic mapping and reasoning according to the optimized first mapping relationship.

[0119] In the embodiment of this application, performing cross-domain semantic mapping and reasoning according to the first mapping relationship that meets the optimization target constraints includes:

[0120] Obtain the real-time first data of the target power grid equipment;

[0121] Determine the real-time second data after mapping the real-time first data according to the first mapping relationship that meets the optimization target constraints;

[0122] The second data is the result of cross-domain semantic mapping and reasoning.

[0123] In summary, the present invention proposes a cross - domain semantic mapping and reasoning method, which obtains the first data and the second data of the target power grid equipment, and performs the first pre - processing on the first data and the second data; presets the first semantic algorithm, extracts semantic elements from the first data through the first semantic algorithm to obtain the first extracted data; establishes the first mapping relationship between the first extracted data and the second data, and optimizes the first mapping relationship in combination with the first optimization algorithm; performs cross - domain semantic mapping and reasoning according to the optimized first mapping relationship. It can automatically realize the semantic understanding and association of the standard terms of power grid equipment between different domains, improve the efficiency and safety of power grid equipment management, and provide a strong guarantee for the stable operation of the power grid. By using the preset semantic algorithm and optimization algorithm, the present invention can effectively extract the key semantic elements of power grid equipment and establish an accurate mapping relationship, so as to realize cross - domain semantic mapping and reasoning. In addition, the present invention can also process real - time data to ensure the real - time and accuracy of power grid equipment management. Through these technical solutions, the present invention not only improves the efficiency of power grid equipment management, but also reduces the errors and deviations caused by manual interpretation of standard terms, ensuring the comprehensiveness and scientificity of power grid equipment management.

[0124] Embodiment 2

[0125] In a preferred embodiment, when collecting various standard terms of power grid equipment, it not only covers national standards, industry standards, enterprise standards, but also includes international standards and special standard requirements for specific regions or projects. At the same time, the standard terms of historical versions are also collected to analyze the evolution trend of the standards.

[0126] In a preferred embodiment, advanced natural language processing tools, such as deep - learning - based language models, are used to perform more accurate lexical analysis, syntactic analysis and semantic role annotation on the standard terms. For example, through a deep neural network, the polysemy of words is judged more accurately, and its specific meaning in a specific standard term is determined in combination with the context.

[0127] In a preferred embodiment, after extracting the key semantic elements, a semantic element database is established, and data warehouse technology is used to manage it efficiently. It can be classified and stored according to the type, source, importance, etc. of the elements, which is convenient for subsequent query and analysis. At the same time, data mining technology is used to perform association analysis on the semantic elements to discover potential relationships and patterns.

[0128] In a preferred embodiment, when investigating the knowledge systems of multiple fields such as power engineering, mechanical engineering, materials science, and information technology, in addition to collecting literature materials such as standards, specifications, papers, and patents, the latest industry trends and cutting - edge knowledge can also be obtained by delving into channels such as industry forums, professional conference records, and expert blogs.

[0129] In a preferred embodiment, when constructing the ontology structure of the multi-domain knowledge graph, ontology evolution technology is introduced so that the ontology structure can be adjusted in a timely manner as knowledge is updated and developed. At the same time, a semantic similarity calculation method is used to automatically classify and associate newly added knowledge nodes, improving the construction efficiency of the knowledge graph.

[0130] In a preferred embodiment, when using entity recognition and relation extraction technologies, a combination of manual annotation and automatic annotation can be adopted. First, professional personnel annotate a part of typical literature materials as training data to train the automatic annotation model, and then a large number of literature materials are automatically annotated to improve the accuracy and efficiency of annotation.

[0131] In a preferred embodiment, when validating and correcting the knowledge graph, a quality evaluation index system is established, including aspects such as the integrity, accuracy, and consistency of knowledge. The knowledge graph is comprehensively evaluated regularly, and targeted corrections and optimizations are made according to the evaluation results.

[0132] In a preferred embodiment, a visual display interface design can be carried out. When selecting visualization tools and technologies, user experience testing can be conducted, and the most intuitive and easy-to-use tools and technologies are selected based on user feedback. For example, different chart libraries, graphic libraries, and map libraries are compared to analyze their effects in demonstrating the semantic interpretation of power grid equipment standard terms and cross-domain associations.

[0133] In a preferred embodiment, when designing the visual display interface, responsive design technology can be adopted to enable the interface to adapt to different device screen sizes and resolutions. At the same time, interaction design technology is used to increase the interactivity between the user and the interface, such as mouse hovering to display detailed information, clicking to expand more content, etc.

[0134] In a preferred embodiment, when presenting the conclusions and suggestions obtained through reasoning, data visualization storytelling technology can be adopted to present complex reasoning results to users in a vivid and interesting way. For example, the performance change trends and potential problems of power grid equipment are shown through forms such as animations and videos to improve users' understanding and attention.

[0135] In a preferred embodiment, a feedback mechanism can be designed. When designing user feedback channels, a multi-channel feedback method can be adopted, such as online questionnaires, comment areas, emails, etc., to facilitate users to provide feedback anytime and anywhere. At the same time, a feedback processing process is established to ensure that user feedback can be processed and replied to in a timely manner.

[0136] In a preferred embodiment, after collecting user feedback information, text analysis technology can be used to automatically classify and perform sentiment analysis on the feedback information. For example, the feedback information can be classified into different types such as praise, suggestions, complaints, etc., and the user's satisfaction with the method and the improvement direction can be analyzed.

[0137] In a preferred embodiment, when adjusting the semantic mapping model and inference algorithm according to user feedback information, incremental learning technology can be adopted to gradually update the model without affecting the performance of the original model. At the same time, a model version management system is established to facilitate the comparison and evaluation of different versions of the model.

[0138] In a preferred embodiment, when regularly collecting new grid equipment standard terms and actual application cases, an automated data collection system can be established to automatically collect data from relevant websites, databases and other channels using web crawler technology. At the same time, the collected data is cleaned and preprocessed to ensure the quality and usability of the data.

[0139] In a preferred embodiment, full life cycle management applications can also be carried out. When applying this method to all stages of the full life cycle management of grid equipment, a full life cycle management platform can be established to deeply integrate the semantic mapping and inference results with the equipment management process. For example, in the equipment selection stage, an online selection tool is provided to automatically recommend equipment that meets the requirements according to the needs and conditions input by the user; in the operation stage, the equipment status is monitored in real time, and potential faults are detected in a timely manner through an early warning system; in the maintenance stage, personalized maintenance plans are formulated to improve the maintenance efficiency and quality.

[0140] In a preferred embodiment, in the equipment design stage, when optimizing the design by combining cross-domain knowledge, collaborative design technology can be adopted to invite experts from different fields to participate in the design process together. Through an online collaboration platform, real-time communication and modification of the design scheme are realized, and the innovation and feasibility of the design are improved.

[0141] In a preferred embodiment, in the manufacturing stage, when ensuring that the equipment quality meets the standards, a quality traceability system can be established to associate the semantic mapping and inference results with the quality inspection data in the production process. Through technologies such as two-dimensional codes and RFID, the whole process of the equipment production process can be traced, and the controllability of product quality can be improved.

[0142] In a preferred embodiment, in the installation stage, when correctly installing the equipment, virtual reality (VR) and augmented reality (AR) technologies can be used to provide visual installation guidance for the installers. By simulating the installation process in a virtual environment, problems and risks in the installation can be discovered in advance, and the accuracy and efficiency of the installation can be improved.

[0143] In a preferred embodiment, during the decommissioning phase, when reasonably disposing of equipment, scientific decommissioning plans can be formulated by considering factors such as environmental impact assessment and resource recycling. Through semantic mapping and reasoning, analyze the environmental impact of equipment decommissioning and the recyclable resources to achieve the goal of sustainable development.

[0144] In a preferred embodiment, when analyzing the requirements of the power grid equipment management system, system engineering methods can be adopted to comprehensively analyze and model each link of power grid equipment management. When determining the integration interfaces and communication protocols with other systems, international standards and industry specifications can be referred to ensure the compatibility and reliability of the integration.

[0145] In a preferred embodiment, when integrating with power grid equipment monitoring systems, asset management systems, dispatching management systems, etc., middleware technology can be adopted to achieve loose coupling integration between different systems. Through the middleware, data conversion, filtering, and routing are realized, improving the flexibility and scalability of the integration.

[0146] In a preferred embodiment, when transmitting semantic mapping and reasoning results to other systems through data interfaces, a data security mechanism can be established to ensure the confidentiality, integrity, and availability of the data. For example, encryption technology, digital signature technology, etc. can be adopted to prevent data from being stolen or tampered with during transmission.

[0147] In a preferred embodiment, when receiving data from other systems, a data fusion and analysis platform can be established to integrate and analyze data from different systems. Using data mining and machine learning technologies, potential relationships and patterns in the data are discovered to provide richer data support for semantic mapping and reasoning.

[0148] In a preferred embodiment, when formulating a performance evaluation index system, domain experts and user representatives can be invited to participate to ensure the scientificity and practicality of the index system. The index system can include multiple aspects such as the accuracy of semantic mapping, the reliability of reasoning results, the usability of the visualization interface, the response time of the system, and scalability.

[0149] In a preferred embodiment, when regularly evaluating the performance of this method, automated performance testing tools can be used to comprehensively test each module of the method. For example, use stress testing tools to test the performance of the system under high load, and use functional testing tools to test whether the various functions of the system are normal.

[0150] In a preferred embodiment, when analyzing the evaluation results to identify existing problems and deficiencies, data analysis techniques such as statistical analysis and regression analysis can be used to deeply analyze the causes and influencing factors of the problems. According to the analysis results, targeted optimization plans are formulated to improve the performance and effectiveness of the method.

[0151] In a preferred embodiment, when improving the method by using optimization algorithms and techniques, comparative experiments of optimization algorithms can be conducted to select the most suitable optimization algorithm. For example, compare different genetic algorithms, simulated annealing algorithms, particle swarm optimization algorithms, etc., and analyze their performance in optimizing the semantic mapping model and inference algorithm. At the same time, in combination with the actual application scenario, appropriately adjust and improve the optimization algorithm to improve the optimization effect and efficiency.

[0152] Embodiment 3

[0153] This embodiment also provides a cross-domain semantic mapping and inference system, including:

[0154] A data processing module, configured to obtain the first data and the second data of the target power grid device, and perform a first preprocessing on the first data and the second data;

[0155] A semantic extraction module, configured to preset a first semantic algorithm, and extract semantic elements from the first data through the first semantic algorithm to obtain first extraction data;

[0156] A relationship establishment module, configured to establish a first mapping relationship between the first extraction data and the second data, and optimize the first mapping relationship in combination with a first optimization algorithm;

[0157] An inference module, configured to perform cross-domain semantic mapping and inference according to the optimized first mapping relationship.

[0158] The above-mentioned unit modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0159] This embodiment also provides a computer device, which can be a terminal, and its internal structure diagram can be as Figure 2As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a cross-domain semantic mapping and reasoning method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0160] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0161] Obtain the first data and the second data of the target power grid device, and perform a first preprocessing on the first data and the second data;

[0162] Preset a first semantic algorithm, and extract semantic elements from the first data through the first semantic algorithm to obtain first extracted data;

[0163] Establish a first mapping relationship between the first extracted data and the second data, and optimize the first mapping relationship in combination with a first optimization algorithm;

[0164] Perform cross-domain semantic mapping and reasoning according to the optimized first mapping relationship.

[0165] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

[0166] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The solutions in the embodiments of the present application can be implemented using various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript, etc.

[0167] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0168] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0169] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more of the flows Figure 1 or blocks or combinations of blocks.

[0170] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present application.

[0171] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to cover these changes and modifications.

Claims

1. A cross-domain semantic mapping and reasoning method, characterized in that: include: Acquire first data and second data of a target power grid device, and perform first preprocessing on the first data and the second data; Preset a first semantic algorithm, and extract semantic elements from the first data using the first semantic algorithm to obtain first extracted data; Establishing a first mapping relationship between the first extracted data and the second data, and optimizing the first mapping relationship in combination with a first optimization algorithm; Cross-domain semantic mapping and reasoning are performed based on the optimized first mapping relationship.

2. The cross-domain semantic mapping and reasoning method according to claim 1, characterized in that: The first semantic algorithm comprises: The first semantic algorithm is any algorithm for extracting target semantic elements from the first data; The target semantic element includes at least a first attribute element, a first state element and a first structural element.

3. The cross-domain semantic mapping and reasoning method according to claim 2, characterized in that: The first optimization algorithm comprises: The first optimization algorithm is any algorithm for optimizing the first mapping relationship; The first optimization algorithm at least includes configuring a first constraint, where the first constraint is used to constrain the first mapping relationship after the optimization is completed to obtain a first mapping relationship that meets the constraint condition.

4. The cross-domain semantic mapping and reasoning method according to claim 3, characterized in that: The first mapping relationship includes: According to the target semantic element extracted from the first data, in combination with the first mapping model, the target semantic element is matched with the second data; The first mapping model is any model that takes as input the target semantic element and the second data, and outputs the first mapping relationship or can directly or indirectly obtain relevant parameters of the first mapping relationship.

5. The cross-domain semantic mapping and reasoning method according to claim 4, characterized in that: The target semantic elements also include: The first attribute element is a physical characteristic of the power grid equipment; The first status element is the operating status of the power grid equipment; The first structural element is structural information of power grid equipment.

6. The cross-domain semantic mapping and reasoning method according to claim 5, characterized in that: The first constraint includes: Preset optimization target constraints; Acquire a first mapping relationship that satisfies the optimization objective constraint; Cross-domain semantic mapping and reasoning are performed according to the first mapping relationship that satisfies the optimization objective constraint.

7. The cross-domain semantic mapping and reasoning method according to claim 6, characterized in that: The performing cross-domain semantic mapping and reasoning according to the first mapping relationship that satisfies the optimization objective constraint includes: Obtaining real-time first data of target power grid equipment; Determine the real-time second data mapped from the real-time first data according to the first mapping relationship that satisfies the optimization objective constraint; The second data is the result of cross-domain semantic mapping and reasoning.

8. A cross-domain semantic mapping and reasoning system, characterized in that: include: A data processing module, used for acquiring first data and second data of a target power grid device, and performing first preprocessing on the first data and the second data; A semantic extraction module, configured to preset a first semantic algorithm, and extract semantic elements from the first data by using the first semantic algorithm to obtain first extracted data; A relationship establishing module, used to establish a first mapping relationship between the first extracted data and the second data, and optimize the first mapping relationship in combination with a first optimization algorithm; The reasoning module is used to perform cross-domain semantic mapping and reasoning according to the optimized first mapping relationship.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images