User demand determination method and device in multi-power system cooperation scene

Abstract

The invention belongs to the technical field of knowledge maps, and provides a user demand determination method and device in a multi-power-system cooperation scene, and the method comprises the steps: carrying out the semantic standardization of a plurality of power systems through a pre-generated ontology model of the power systems; generating a knowledge graph of the plurality of power systems according to the relationship among the plurality of power systems, the relationship among the plurality of modules in the single power system and the plurality of power systems after semantic standardization; and selecting at least one corresponding module from the plurality of power systems according to the demands of the user, the use habits of the user and the knowledge graph, and recommending the at least one corresponding module to the user. According to the method, the learning and using difficulties faced by a power system user when facing a large number of modules and subsystems and frequent updating are effectively solved, the learning cost of the user can be reduced, the working efficiency can be improved, and the user experience can be improved.

Description

Technical Field

[0001] This application belongs to the field of knowledge graph technology, and in particular to the field of user demand perception technology in power systems, specifically relating to a method and apparatus for determining user demand in a collaborative scenario of multiple power systems. Background Technology

[0002] Understandably, the rapid growth of data volume in existing internet applications has led to information overload. Artificial intelligence (AI) analysis can reliably and efficiently extract information of interest for information recommendation. This not only provides users with usable information services but also, even without explicitly stated needs, can accurately uncover personalized requirements by analyzing users' historical data interactions with other applications. Based on their interests and preferences, it can proactively provide users with the information they need. For this type of behavioral pattern mining, power system application data strategies can extract useful data from power applications, analyze application categories and behavioral patterns using AI, and recommend data application strategies for new applications. This simplifies the data extraction process and supports the strategy's deployment in new applications after expert validation. Specifically, the industry faces the following technical pain points:

[0003] (1) User behavior data of power systems in multiple power system scenarios is growing exponentially (smart meters, work order systems, equipment monitoring, etc.); while the data is growing, the number of corresponding systems is also increasing significantly, but the user convenience is significantly reduced. Specifically, the cost for users to use multiple power systems is increasing exponentially, and it is difficult to accurately find the system and corresponding module and unit that they need in the short term, which greatly affects the user experience.

[0004] (2) Traditional manual analysis is difficult to uncover users' implicit needs (such as energy-saving preferences and fault response tendencies);

[0005] (3) The information push is mismatched with the actual needs of users, which reduces service efficiency. Summary of the Invention

[0006] The method for determining user needs in multiple power system collaborative scenarios provided by this invention aims to simplify user operation and learning costs as much as possible in scenarios where multiple power systems are coupled.

[0007] Another object of the present invention is to provide an apparatus for reviewing system change operations. A further object of the present invention is to provide an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, implements the steps of the aforementioned system change operation review method. A further object of the present invention is to provide a readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the aforementioned system change operation review method.

[0008] In a first aspect, the present invention provides a method for determining user needs in a multi-power system collaborative scenario, the method comprising:

[0009] Semantic standardization of multiple power systems is performed using a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: power system physical structure, power system operating state, users and loads, and the time and space of the power system;

[0010] A knowledge graph of the multiple power systems is generated based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization.

[0011] Based on user needs, user habits, and the knowledge graph, at least one corresponding module is selected from multiple power systems and recommended to the user.

[0012] In some embodiments of this application, the step of generating the ontology model includes:

[0013] Identify the common concepts in a subset of the multiple power systems, the attributes of the common concepts, and the relationships between different concepts;

[0014] The ontology model is generated based on the same concepts, the attributes of the same concepts, and the relationships between different concepts.

[0015] In some embodiments of this application, the semantic standardization of multiple power systems using a pre-generated power system ontology model includes:

[0016] The ontology model maps concepts, attributes of concepts, and relationships between different concepts within another part of the multiple power systems.

[0017] In some embodiments of this application, a method for determining user demand in a multi-power system collaborative scenario further includes:

[0018] Learning node representations in knowledge graphs;

[0019] The implicit relationships between multiple concepts are uncovered through the learning results of the node representations.

[0020] In some embodiments of this application, mining implicit relationships between multiple concepts through the results of node representation learning includes:

[0021] Determine the topological similarity and path similarity between multiple nodes;

[0022] The similarity between the plurality of nodes is determined based on the topological similarity and the path similarity;

[0023] The implicit relationships are mined based on the similarity and the ontology model.

[0024] In some embodiments of this application, if the interface of any of the plurality of power systems changes, the method further includes:

[0025] The interfaces that have changed are determined based on the current interface dependency graph of the multiple power systems and the interface dependency graph of the multiple power systems when there are no interface changes; the interface dependency graph is used to represent all interfaces of the multiple power systems and the dependencies between all interfaces.

[0026] Based on the changed interface, the dependency direction is reversed in the current interface dependency graph to determine the scope of the impact of the changed interface in multiple power systems;

[0027] The knowledge graph is updated based on the scope of influence.

[0028] In some embodiments of this application, changes to the interface include: adding nodes, edges, deleting nodes, edges, and modifying nodes and edges in the interface dependency graph.

[0029] Secondly, the present invention provides a user demand determination device applied in a multi-power system collaborative scenario, the device comprising:

[0030] The semantic standardization module is used to perform semantic standardization on multiple power systems using a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: the physical structure of the power system, the operating state of the power system, users and loads, and the time and space of the power system;

[0031] The knowledge graph generation module is used to generate a knowledge graph of the multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization.

[0032] The user needs determination module is used to select at least one corresponding module from multiple power systems based on user needs, user habits, and the knowledge graph, and recommend it to the user.

[0033] In some embodiments of this application, a user demand determination device applied in a multi-power system collaborative scenario further includes:

[0034] An ontology model generation module is used to generate the ontology model; the ontology model generation module includes:

[0035] A concept determination unit is used to determine the common concepts in a subset of the multiple power systems, the attributes of the common concepts, and the relationships between different concepts.

[0036] The ontology model generation unit is used to generate the ontology model based on the same concept, the attributes of the same concept, and the relationship between different concepts.

[0037] In some embodiments of this application, the semantic standardization module includes:

[0038] Semantic standardization unit is used to map concepts, attributes of concepts, and relationships between different concepts in another part of the multiple power systems through the ontology model.

[0039] In some embodiments of this application, a user demand determination device for a multi-power system collaborative scenario further includes:

[0040] The node learning module is used to learn node representations in knowledge graphs.

[0041] The implicit relationship mining module is used to mine implicit relationships between multiple concepts based on the learning results of the node representations.

[0042] In some embodiments of this application, the implicit relationship mining module includes:

[0043] A similarity determination unit is used to determine the topological similarity and path similarity between multiple nodes;

[0044] A node similarity determination unit is used to determine the similarity between the plurality of nodes based on the topological similarity and the path similarity;

[0045] The implicit relationship mining subunit is used to mine the implicit relationship based on the similarity and the ontology model.

[0046] In some embodiments of this application, if the interface of any of the multiple power systems changes; a user demand determination device in a multi-power system collaborative scenario further includes:

[0047] The changed interface determination module is used to determine the changed interfaces based on the current interface dependency graph of the multiple power systems and the interface dependency graph of the multiple power systems when no interface changes have occurred; the interface dependency graph is used to represent all interfaces of the multiple power systems and the dependencies between all interfaces;

[0048] The scope of influence determination module is used to reverse the dependency direction in the current interface dependency graph based on the changed interface, so as to determine the scope of influence of the changed interface in multiple power systems.

[0049] The knowledge graph update module is used to update the knowledge graph according to the scope of influence.

[0050] In some embodiments of this application, changes to the interface include: adding nodes, edges, deleting nodes, edges, and modifying nodes and edges in the interface dependency graph.

[0051] Thirdly, the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of a method for determining user requirements in a multi-power system collaborative scenario.

[0052] Fourthly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for determining user requirements in a multi-power system collaborative scenario.

[0053] Fifthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for determining user requirements in a multi-power system collaborative scenario.

[0054] As described above, embodiments of the present invention provide a method and apparatus for determining user needs in a multi-power system collaborative scenario. The method for determining user needs in a multi-power system collaborative scenario includes: first, semantically standardizing multiple power systems using a pre-generated ontology model of the power system; then, generating a knowledge graph of multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the semantically standardized power systems; finally, selecting at least one corresponding module from the multiple power systems based on user needs, user habits, and the knowledge graph, and recommending it to the user.

[0055] In summary, this invention, by constructing a knowledge graph of the power system and combining it with intelligent querying and demand recommendation, can effectively solve the learning and usage difficulties faced by power system users when dealing with a large number of modules, subsystems, and frequent updates. This method not only reduces the learning cost for users but also improves work efficiency and enhances the user experience. Attached Figure Description

[0056] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0057] Figure 1 This is a flowchart illustrating a method for determining user needs in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 1 .

[0058] Figure 2 This is a schematic diagram illustrating an application scenario of a user demand determination method in a multi-power system collaborative scenario, as described in an embodiment of the present invention.

[0059] Figure 3 This is a flowchart illustrating a method for determining user needs in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 2 .

[0060] Figure 4 This is a flowchart illustrating step 400 of a method for determining user needs in a multi-power system collaborative scenario according to an embodiment of the present invention.

[0061] Figure 5 This is a flowchart illustrating a method for determining user needs in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 3 .

[0062] Figure 6 This is a flowchart illustrating step 600 of a method for determining user needs in a multi-power system collaborative scenario according to an embodiment of the present invention.

[0063] Figure 7 This is a flowchart illustrating a method for determining user needs in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 4 .

[0064] Figure 8 This is a flowchart illustrating a method for determining user needs in a multi-power system collaborative scenario, as described in a specific embodiment of the present invention.

[0065] Figure 9 This is a block diagram of a user demand determination device in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 1 .

[0066] Figure 10 This is a block diagram of a user demand determination device in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 2 .

[0067] Figure 11 This is a block diagram of the ontology model generation module 40 in an embodiment of the present invention.

[0068] Figure 12 This is a block diagram of a user demand determination device in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 3 .

[0069] Figure 13 This is a block diagram of the implicit relationship mining module 60 in an embodiment of the present invention.

[0070] Figure 14 This is a block diagram of a user demand determination device in a multi-power system collaborative scenario, as described in an embodiment of the present invention. Figure 4 .

[0071] Figure 15 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0072] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0073] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] It should be noted that the terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses. Without conflict, the embodiments and features in the embodiments of this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0075] Embodiments of the present invention provide a specific implementation of a method for determining user demand in a multi-power system collaborative scenario, see [link to implementation details]. Figure 1 The method includes:

[0076] Step 100: Semantically standardize multiple power systems using a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: power system physical structure, power system operating state, users and loads, and the time and space of the power system;

[0077] Step 200: Generate a knowledge graph of the multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization;

[0078] Step 300: Based on the user's needs, user habits, and the knowledge graph, select at least one corresponding module from the multiple power systems and recommend it to the user.

[0079] As described above, embodiments of the present invention provide a method for determining user needs in a multi-power system collaborative scenario, comprising: first, semantically standardizing multiple power systems using a pre-generated ontology model of the power system; next, generating a knowledge graph of multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules within a single power system, and the semantically standardized power systems; and finally, selecting at least one corresponding module from the multiple power systems based on user needs, user habits, and the knowledge graph, and recommending it to the user.

[0080] In summary, this invention, by constructing a knowledge graph of the power system and combining it with intelligent querying and demand recommendation, can effectively solve the learning and usage difficulties faced by power system users when dealing with a large number of modules, subsystems, and frequent updates. This method not only reduces the learning cost for users but also improves work efficiency and enhances the user experience.

[0081] See Figure 2Here, a specific scenario is provided to illustrate steps 100 to 300. Based on multiple existing power systems, a four-layer architecture is extracted: wide-area multi-scenario, business middle platform, capability middle platform, and basic platform. (Based on the separation of business and control, a flexible, unified, and scalable functional integration platform architecture is built. Multi-scenario functional applications are atomicized through the microservice concept of a unified business platform, and various business functions are combined through capability orchestration.) Based on the user's historical demand data, the structure of the above four layers is summarized into multiple scenarios and multiple functional groups, and a scenario and functional group matching matrix as shown in Table 1 is provided. Finally, the customer selects the most suitable functional group for adaptation.

[0082] Table 1. Field classification function group adaptation

[0083] Field classification A B C D E F G Function group adaptation 1+2+3 1+2+4 1+2+6 1+6 1 1+2+3 1+2+5

[0084] Regarding step 100, semantic standardization is a process that ensures consistency and interoperability in the understanding of information among different systems, modules, or components by unifying the semantic descriptions of data, interfaces, or services. Its core objective is to eliminate semantic ambiguity in multiple power systems so that data or services can be accurately and unambiguously parsed and used.

[0085] Specifically, in the process of semantic standardization, all relevant data and information need to have unified definitions and descriptions. This means that the same terms or data elements must maintain a consistent meaning in different contexts. For example, in different power systems, the definitions of concepts such as "customer," "order," and "electricity consumption" should be unified to avoid differences in understanding.

[0086] Step 100 can be implemented by defining a standard semantic model, for example, through standardization using data dictionaries, metadata management, ontology, etc. These models describe the relationships between data elements and the meanings of their conventions, enabling the system to share information across platforms and domains.

[0087] In addition, the concepts related to the ontology model in step 100 include: the physical structure of the power system, the operating state of the power system, the electricity market and economy, users and loads, and the temporal and spatial aspects of the power system, specifically:

[0088] (1) Physical structure of power system:

[0089] Power generation equipment:

[0090] Types: Thermal power plants, hydroelectric power plants, nuclear power plants, wind farms, photovoltaic power plants, etc.

[0091] Components: generators, boilers, turbines, photovoltaic panels, energy storage devices (such as batteries);

[0092] Power transmission equipment:

[0093] Power transmission lines: overhead lines, underground cables;

[0094] Substation: Transformers (step-up / step-down), circuit breakers, disconnect switches;

[0095] Power distribution equipment:

[0096] Power distribution network: distribution transformers, switchgear, feeders;

[0097] User-side equipment: smart meters, inverters, charging piles;

[0098] (2) Power system operating status:

[0099] Electrical parameters: voltage, current, active power, reactive power, frequency, harmonics;

[0100] Equipment status: operating status (normal / faulty), load rate, temperature, lifespan;

[0101] Power grid operation modes: steady-state operation, transient processes (such as short circuits), and islanding operation;

[0102] (3) Electricity Market and Economy:

[0103] Market participants: power generation companies, electricity sales companies, users, and grid operators;

[0104] Trading mechanisms: medium- and long-term contracts, spot market, and ancillary services market;

[0105] Electricity prices and costs: grid connection price, transmission and distribution price, carbon emission costs;

[0106] (4) Users and load:

[0107] User categories: Industrial users, Commercial users, Residential users;

[0108] Load characteristics: base load, peak-valley load, interruptible load;

[0109] Electricity consumption behavior: demand response, electric vehicle charging modes, smart home electricity consumption;

[0110] (5) The temporal and spatial aspects of power systems:

[0111] Time dimension: real-time data, historical data, and forecast data (such as load forecasting);

[0112] Geospatial: Power grid geographic information (GIS), equipment coordinates, and regional division.

[0113] For step 200, knowledge graph construction comprises four parts: schema layer design, data layer construction, knowledge storage, and computation and application. Data layer construction includes knowledge acquisition and knowledge fusion. The basic goal of the schema layer design module is to centralize the knowledge framework of twin datasets from multi-source heterogeneous data sources and endow it with an intelligent data generator. This involves constructing the knowledge framework, including basic domain concepts and their relationships, basic domain attributes, and domain constraint rules. Knowledge acquisition and fusion are then integrated into the comprehensive knowledge graph at the data layer. Data source entities and complex application schema layers mutually represent each other. Application entity targets are extracted based on multi-source heterogeneous data, linking the application data generation system, constructing the spatial and semantic information of application entities, storing knowledge through relational databases and graph databases, and finally, quantitatively analyzing the entity and relation coverage of the knowledge graph.

[0114] For step 300, based on the requirements analysis framework, typical scenario functional groups are constructed, a functional manual is formed, and optional configuration suggestions are proposed, as detailed in Table 2.

[0115] Table 2

[0116]

[0117]

[0118] In some embodiments of the present invention, see Figure 3 A method for determining user demand in a multi-power system collaborative scenario, further comprising:

[0119] Step 400: Generate the ontology model. Further, see... Figure 4 Step 400 includes:

[0120] Step 401: Determine the common concepts in a subset of the multiple power systems, the attributes of the common concepts, and the relationships between different concepts;

[0121] Specifically, with the support of ontology and rule base, knowledge factors and their relationships hidden in data resources are obtained through knowledge extraction and transformation, and then new knowledge is created by combining, reasoning and creating at the semantic level. This process needs to be dynamically adjusted in real time according to changes in data sources and user feedback.

[0122] Step 402: Based on the same concept, the attributes of the same concept, the relationship between different concepts, and the pre-established ontology model.

[0123] The following principles should be followed during the implementation of step 402:

[0124] 1) Clarity and objectivity, that is, the ontology should use natural language to give a clear and objective semantic definition of the defined terms.

[0125] 2) Completeness, that is, the given definition is complete and fully expresses the meaning of the term being described.

[0126] 3) Consistency, that is, the inferences derived from the term are compatible with the meaning of the term itself and do not contradict each other.

[0127] 4) Maximum monotonic extensibility, meaning that when adding general or special terms to the ontology, it is not necessary to modify its existing content.

[0128] 5) Minimal commitment, which means giving as few constraints as possible to the object being modeled.

[0129] 6) Minimize encoding deviation; the ontology should be established as independently as possible from the specific encoding language.

[0130] 7) The semantic differences between sibling concepts should be as small as possible.

[0131] 8) Implement multiple inheritance mechanisms using diverse conceptual hierarchies.

[0132] 9) Use standardized terminology whenever possible.

[0133] For step 402, there are three methods for constructing a knowledge ontology: top-down, bottom-up, and hybrid approaches. Top-down involves pre-defining several broad categories based on prior knowledge, refining them into smaller subcategories, and finally classifying different things into different categories. Top-down approaches require extensive industry domain knowledge, a clear understanding of the overall design and hierarchical structure, and generally require the participation of domain experts; complete coverage is also difficult. Bottom-up approaches start from existing data, obtaining relatively intuitive categories and hierarchies through data similarity and hierarchical analysis, and constructing the ontology using this structural information. The hybrid approach involves pre-defining ontology concepts and then supplementing and refining the ontology through a data layer.

[0134] In some embodiments of the present invention, step 100 includes:

[0135] The ontology model maps concepts, attributes of concepts, and relationships between different concepts within another part of the multiple power systems.

[0136] Specifically, the first step is to define semantic standards by analyzing business requirements, data models, and system functions. These standards may include terminology, definitions, relationships, and context. Next, a shared vocabulary or ontology is constructed to ensure that different systems and applications use the same terminology and definitions when exchanging data. Finally, specific data formats are abstracted into a unified semantic model, thereby ensuring that data from different sources can be represented and processed according to a unified standard.

[0137] For example, two different data sources might use "birthday" and "date of birth" to represent the same concept. Semantic normalization would unify them into a single standard field, such as "date of birth." For semantic inconsistencies between different systems or data sources, semantic mapping or alignment methods can be used to map different terms and concepts to a common standard or ontology. For example, "customer address" in system A can be mapped to "user address" in system B, ensuring semantic consistency between the two.

[0138] For data exchange between different systems, standardized data formats (such as Semantic Web standards like RDF and OWL) and protocols (such as the SPARQL query language) can be used for interaction. These standardized formats and protocols can ensure the consistency and shareability of data between different systems.

[0139] Finally, establish a semantic layer or intermediary layer: A unified semantic layer is built between different data sources and applications. This layer is responsible for managing and transforming semantic differences between different data sources. The semantic layer includes: a unified vocabulary, data transformation rules, and mapping mechanisms. In this way, different applications can perform unified semantic parsing and processing without directly modifying the data source.

[0140] In some embodiments of the present invention, see Figure 5 A method for determining user demand in a multi-power system collaborative scenario, further comprising:

[0141] Step 500: Learn node representations in the knowledge graph;

[0142] Step 600: Mine the implicit relationships between multiple concepts using the results of node representation learning.

[0143] For steps 500 and 600, nodes (i.e., entities, concepts, etc.) are mapped into a low-dimensional vector space to capture the semantic information of the nodes and further reveal the potential relationships between the nodes through these vector representations.

[0144] Once the vector representation of each node (concept) is obtained through node representation learning, these vectors can be used for various relation mining tasks:

[0145] Relational reasoning: By using the vector representations of nodes, one can attempt to predict the relationship between two nodes. For example, in a knowledge graph, if the representations of nodes A and B are known, and the relationship between them is undefined, geometric operations on vectors (such as vector addition or subtraction) can be used to infer their possible relationship.

[0146] Link prediction: By learning the representations of nodes, it is possible to predict the links that may exist in the graph (e.g., possible implicit relationships between entities). Link prediction can be achieved if two entities in a knowledge graph do not yet have an explicit relationship, but their possible relationship can be inferred from their embedding representations.

[0147] Cluster analysis: Applying the vector representation of nodes to clustering algorithms (such as K-means or hierarchical clustering) can automatically discover implicit groups or themes among concepts or entities in a graph. Similar nodes are clustered together, thus revealing potential associations between them.

[0148] Semantic similarity calculation: Node representations can be used to calculate the similarity between different nodes (such as cosine similarity or Euclidean distance). This helps to uncover the semantic similarity between nodes and thus discover their possible implicit relationships in different contexts.

[0149] Visualization of graph embeddings: Dimensionality reduction techniques (such as t-SNE or PCA) can reduce the high-dimensional vector embeddings of nodes to 2D or 3D space, facilitating visualization. In the visualized graph, the spatial positions between nodes reflect their semantic relationships; nodes that are close together represent semantically similar or related concepts.

[0150] In some embodiments of the present invention, see Figure 6 Step 600 includes:

[0151] Step 601: Determine the topological similarity and path similarity between multiple nodes;

[0152] Topological similarity between multiple nodes refers to the similarity of nodes in the graph structure, mainly focusing on the neighbor relationships and the positions of nodes in the graph. Specifically, similarity can be measured by calculating the ratio of the intersection to the union of the neighbor sets of two nodes, as shown in formula (1):

[0153]

[0154] In the above formula: J(A,B) represents the topological similarity between nodes A and B, N(A) is the set of neighbors of node A, and correspondingly, N(B) is the set of neighbors of node B.

[0155] Path similarity among multiple nodes considers not only direct neighbor relationships but also paths between nodes (i.e., pairs of nodes connected through a series of intermediate nodes), making it highly effective for capturing complex dependencies and semantic similarities. Specifically, a random walk is performed in the graph, and the probability of a walk path from node A to node B is counted (nodes with high path similarity are more likely to be reached via the same path).

[0156] Step 602: Determine the similarity between the plurality of nodes based on the topological similarity and the path similarity;

[0157] For topological similarity and path similarity, different weights can be assigned to them, and the similarity can be calculated by using a weighted average method.

[0158] Step 603: Mine the implicit relationship based on the similarity and the ontology model.

[0159] Once the similarity between nodes is obtained, implicit relationships can be further explored using the ontology model. Specifically, implicit relationships are discovered through similarity: based on the similarity between nodes, it is possible to identify which nodes have high similarity. High similarity between nodes may indicate that they have similar roles or attributes semantically.

[0160] For example, in a knowledge graph, two concepts (such as "transformer" and "voltage transformer") may have high structural similarity but are not directly connected. Through ontology models, it can be inferred that they may belong to the same category of entities, thereby discovering the implicit relationship between them.

[0161] An ontology model may contain specific descriptions or category information about node attributes, which can help to further understand the relationships between nodes with high similarity. Through an ontology model, node similarity can be mapped to a real-world knowledge domain, inferring more potential relationships.

[0162] In some embodiments of the present invention, see Figure 7 If the interface of any of the multiple power systems changes, a method for determining user requirements in a multi-power system collaborative scenario further includes:

[0163] Step 700: Determine the changed interfaces based on the current interface dependency graph of the multiple power systems and the interface dependency graph of the multiple power systems when no interface changes occur; the interface dependency graph is used to represent all interfaces of the multiple power systems and the dependencies between all interfaces;

[0164] Step 800: Reverse the dependency direction in the current interface dependency graph according to the changed interface to determine the scope of influence of the changed interface in the multiple power systems;

[0165] If node A depends on node B (i.e., there's an edge pointing from A to B), then reversing the dependency direction changes the dependency relationship to B depending on A, and the edge direction changes from A→B to B→A. Reversing the dependency of an interface can cause the original dependent to become the dependent, thus affecting the component's functionality or performance. The extent of the impact after reversal depends on the relationship between this interface and other components.

[0166] Step 900: Update the knowledge graph according to the scope of influence.

[0167] As described above, embodiments of the present invention provide a method for determining user needs in a multi-power system collaborative scenario, comprising: first, semantically standardizing multiple power systems using a pre-generated ontology model of the power system; next, generating a knowledge graph of multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules within a single power system, and the semantically standardized power systems; and finally, selecting at least one corresponding module from the multiple power systems based on user needs, user habits, and the knowledge graph, and recommending it to the user.

[0168] To address the challenges of diverse supporting system modules and subsystems in power systems, high learning costs for operating methods, and frequent updates, this invention utilizes knowledge graph technology to establish an intelligent knowledge base. This helps users quickly understand and master system functions, thereby reducing learning costs and improving work efficiency.

[0169] For further explanation of the plan, see Figure 8 The specific implementation of the user demand determination method in a multi-power system collaborative scenario provided by the present invention includes the following steps:

[0170] With the rapid development of power system networks, various supporting systems have also emerged, each containing dozens or even hundreds of modules, each with its own function. Furthermore, each supporting system may contain subsystems. In this situation, if power system users want to achieve their needs, they need to spend a lot of energy and time learning how to operate each supporting system. Moreover, the supporting systems are updated frequently, which further increases the learning cost for users.

[0171] On the other hand, with the rapid development of big data technology, power system networks have also accumulated massive amounts of related data. How to utilize this data to provide users with corresponding decision-making is also a technical problem that relevant personnel in this field urgently need to solve.

[0172] Based on the above issues, see Figure 8 A specific implementation method for determining user demand in a multi-power system collaborative scenario includes the following steps:

[0173] S1: Collects various documents, manuals, standards, API documents, user operation records, historical system update logs, and other data from the power system.

[0174] The collected text, tables, images, and other data are structured. The main content includes functional descriptions, interaction methods, operation steps, and update logs for supporting systems, subsystems, and modules.

[0175] S2: Establish an ontology library for the power sector to achieve semantic standardization of different system modules.

[0176] S3: Construct a knowledge graph for the power system.

[0177] First, relevant entities are identified from the data, including supporting systems, subsystems, functional modules, operation steps, interfaces, versions, and users. Next, the relationships between entities are determined; common relationships include "belongs to," "contains," "depends on," "implements," and "updates to." For example, supporting systems and subsystems have a containment relationship, subsystems and modules have an implementation relationship, and modules and operation steps have a dependency relationship. Based on the actual needs of the power system, possible entities and relationships within the system are defined. These entities and relationships will constitute the core elements of the knowledge graph.

[0178] Entities (Nodes): These include supporting systems, subsystems, functional modules, operation steps, users, interfaces, hardware devices, etc.

[0179] Edges: Define the relationships between entities, such as "contains", "depends", "implements", "updates", "executes", etc.

[0180] The following should be considered when designing an ontology model:

[0181] Hierarchical structure: For example, a supporting system may contain multiple subsystems, each subsystem may contain multiple modules, and each module may contain different operating steps.

[0182] Attribute definition: Define the attributes of each entity, such as the "functional description" and "interface specification" of the module, and the "running status" of the subsystem.

[0183] Relationship definition: For example, the "implementation" relationship between modules and functions, the "inclusion" relationship between subsystems and modules, etc.

[0184] It should be noted that when the supporting system or module is updated, the graph will automatically adjust and update the corresponding nodes and edges according to the new information.

[0185] S4: Select at least one corresponding module from multiple power systems based on user needs, user habits, and knowledge graphs, and recommend it to the user.

[0186] Specifically, NLP technology is used to process user-input queries. For example, a user might ask a question like "How to configure subsystem X?" The system parses the question, automatically extracts keywords, and finds relevant modules and steps in the knowledge graph. Based on the user's needs, the system extracts relevant modules, subsystems, and steps from the knowledge graph.

[0187] In addition, by analyzing users' historical queries and learning behaviors, personalized learning recommendations are provided based on knowledge graphs. For example, recommendations may be made to help users understand the functions of a certain module, learn the operation steps, or recommend relevant updated documentation based on current version changes.

[0188] Collect user feedback on knowledge graph query and learning recommendation functions to evaluate their accuracy and user satisfaction. Based on user feedback and query behavior, adjust and optimize the knowledge graph structure to ensure it better meets user needs. This may include adjusting entity relationships, adding new modules or functions, or optimizing the recommendation system's performance.

[0189] As described above, the specific embodiments of the present invention provide a method for determining user needs in a multi-power system collaborative scenario, comprising: first, semantically standardizing multiple power systems using a pre-generated ontology model of the power system; next, generating a knowledge graph of multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the semantically standardized power systems; and finally, selecting at least one corresponding module from the multiple power systems based on user needs, user habits, and the knowledge graph, and recommending it to the user.

[0190] This invention constructs a knowledge graph containing all information about various supporting systems, subsystems, modules, and functions by modeling their relationships. Based on the different modules and subsystems of the power system, a modular management strategy is formulated and dynamically updated in the knowledge graph to cope with frequent system changes. Natural language processing technology and a graph query engine help users query relevant modules and operation methods according to their needs, while providing personalized learning recommendations to reduce user learning costs. A user-friendly visual interface helps users clearly see the architecture, module relationships, and operation processes of the supporting systems, thereby simplifying the learning path.

[0191] Based on the same inventive concept, embodiments of this application also provide a user demand determination device for multiple power system collaborative scenarios, which can be used to implement the method described in the above embodiments, as shown in the following embodiments. Since the principle of the user demand determination device for multiple power system collaborative scenarios is similar to that of the user demand determination method for multiple power system collaborative scenarios, the implementation of the user demand determination device for multiple power system collaborative scenarios can refer to the implementation of the user demand determination method for multiple power system collaborative scenarios, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0192] Embodiments of the present invention provide a specific implementation of a user demand determination device for multiple power system collaborative scenarios, capable of implementing a user demand determination method in multiple power system collaborative scenarios. See [link to specific implementation details]. Figure 9 A user demand determination device for a multi-power system collaborative scenario specifically includes the following components:

[0193] Semantic standardization module 10 is used to perform semantic standardization on multiple power systems through a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: power system physical structure, power system operating state, users and loads, and the time and space of the power system;

[0194] The knowledge graph generation module 20 is used to generate a knowledge graph of the multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization.

[0195] User requirement determination module 30 is used to select at least one corresponding module from the multiple power systems based on user requirements, user usage habits, and the knowledge graph, and recommend it to the user.

[0196] In some embodiments of this application, see Figure 10 A user demand determination device applied in a multi-power system collaborative scenario, further comprising:

[0197] Ontology model generation module 40, used to generate the ontology model; see also Figure 11 The ontology model generation module 40 includes:

[0198] The concept determination unit 40a is used to determine the same concepts in a subset of the multiple power systems, the attributes of the same concepts, and the relationships between different concepts.

[0199] The ontology model generation unit 40b is used to generate the ontology model based on the same concept, the attributes of the same concept, and the relationship between different concepts.

[0200] In some embodiments of this application, the semantic standardization module includes:

[0201] Semantic standardization unit is used to map concepts, attributes of concepts, and relationships between different concepts in another part of the multiple power systems through the ontology model.

[0202] In some embodiments of this application, see Figure 12 A user demand determination device for multiple power system collaborative scenarios, further comprising:

[0203] The node learning module 50 is used to learn node representations in the knowledge graph.

[0204] The implicit relationship mining module 60 is used to mine implicit relationships between multiple concepts through the results of learning the node representations.

[0205] In some embodiments of this application, see Figure 13 The implicit relationship mining module 60 includes:

[0206] The similarity determination unit 60a is used to determine the topological similarity and path similarity between multiple nodes;

[0207] The node similarity determination unit 60b is used to determine the similarity between the plurality of nodes based on the topological similarity and the path similarity;

[0208] The implicit relationship mining subunit 60c is used to mine the implicit relationship based on the similarity and the ontology model.

[0209] In some embodiments of this application, see Figure 14 If the interface of any of the multiple power systems changes; a user demand determination device in a multi-power system collaborative scenario further includes:

[0210] The change interface determination module 70 is used to determine the changed interfaces based on the current interface dependency graph of the multiple power systems and the interface dependency graph of the multiple power systems when no interface changes have occurred; the interface dependency graph is used to represent all interfaces of the multiple power systems and the dependencies between all interfaces.

[0211] The scope of influence determination module 80 is used to reverse the dependency direction in the current interface dependency graph based on the changed interface, so as to determine the scope of influence of the changed interface in multiple power systems.

[0212] The knowledge graph update module 90 is used to update the knowledge graph according to the scope of influence.

[0213] In some embodiments of this application, changes to the interface include: adding nodes, edges, deleting nodes, edges, and modifying nodes and edges in the interface dependency graph.

[0214] The embodiments of this application also provide a specific implementation of an electronic device capable of implementing all steps in the user demand determination method under multiple power system collaborative scenarios in the above embodiments. See [link to implementation details]. Figure 15 The electronic devices specifically include the following:

[0215] Processor 1201, memory 1202, communications interface 1203, and bus 1204;

[0216] The processor 1201, memory 1202, and communication interface 1203 communicate with each other via bus 1204; the communication interface 1203 is used to realize information transmission between server-side devices and client-side devices and other related devices.

[0217] The processor 1201 is used to call the computer program in the memory 1202. When the processor executes the computer program, it implements all the steps in the user demand determination method under multiple power system collaborative scenarios in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0218] Step 100: Semantically standardize multiple power systems using a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: power system physical structure, power system operating state, users and loads, and the time and space of the power system;

[0219] Step 200: Generate a knowledge graph of the multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization;

[0220] Step 300: Based on the user's needs, user habits, and the knowledge graph, select at least one corresponding module from the multiple power systems and recommend it to the user.

[0221] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the user demand determination method under multiple power system collaborative scenarios in the above embodiments. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements all steps of the user demand determination method under multiple power system collaborative scenarios in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0222] Step 100: Semantically standardize multiple power systems using a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: power system physical structure, power system operating state, users and loads, and the time and space of the power system;

[0223] Step 200: Generate a knowledge graph of the multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization;

[0224] Step 300: Based on the user's needs, user habits, and the knowledge graph, select at least one corresponding module from the multiple power systems and recommend it to the user.

[0225] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0226] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0227] While this application provides method operation steps as shown in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the method can be executed sequentially as shown in the embodiments or drawings, or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0228] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0229] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0230] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0231] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0232] The embodiments described in this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0233] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0234] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A method for determining user demand in a multi-power system collaborative scenario, characterized in that, include: Semantic standardization of multiple power systems is performed using a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: power system physical structure, power system operating state, users and loads, and the time and space of the power system; A knowledge graph of the multiple power systems is generated based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization. Based on user needs, user habits, and the knowledge graph, at least one corresponding module is selected from multiple power systems and recommended to the user.

2. The user demand determination method according to claim 1, characterized in that, The steps for generating the ontology model include: Identify the common concepts in a subset of the multiple power systems, the attributes of the common concepts, and the relationships between different concepts; The ontology model is generated based on the same concepts, the attributes of the same concepts, and the relationships between different concepts.

3. The user demand determination method according to claim 1, characterized in that, The semantic standardization of multiple power systems through a pre-generated power system ontology model includes: The ontology model maps concepts, attributes of concepts, and relationships between different concepts within another part of the multiple power systems.

4. The user demand determination method according to claim 1, characterized in that, Also includes: Learning node representations in knowledge graphs; The implicit relationships between multiple concepts are uncovered through the learning results of the node representations.

5. The user requirement determination method according to claim 4, characterized in that, Mining implicit relationships between multiple concepts through the results of node representation learning includes: Determine the topological similarity and path similarity between multiple nodes; The similarity between the plurality of nodes is determined based on the topological similarity and the path similarity; The implicit relationships are mined based on the similarity and the ontology model.

6. The user requirement determination method according to any one of claims 1 to 5, characterized in that, If the interface of any of the multiple power systems changes; it also includes: The interfaces that have changed are determined based on the current interface dependency graph of the multiple power systems and the interface dependency graph of the multiple power systems when there are no interface changes; the interface dependency graph is used to represent all interfaces of the multiple power systems and the dependencies between all interfaces; Based on the changed interface, the dependency direction is reversed in the current interface dependency graph to determine the scope of the impact of the changed interface in multiple power systems; The knowledge graph is updated based on the scope of influence.

7. The user requirement determination method according to claim 6, characterized in that, The changes to the interface include: adding, deleting, and modifying nodes and edges in the interface dependency graph.

8. A user demand determination device for a multi-power system collaborative scenario, characterized in that, include: The semantic standardization module is used to perform semantic standardization on multiple power systems using a pre-generated ontology model of the power system; wherein, the concepts in the ontology model include: the physical structure of the power system, the operating state of the power system, users and loads, and the time and space of the power system; The knowledge graph generation module is used to generate a knowledge graph of the multiple power systems based on the relationships between the multiple power systems, the relationships between multiple modules in a single power system, and the multiple power systems after semantic standardization. The user needs determination module is used to select at least one corresponding module from multiple power systems based on user needs, user habits, and the knowledge graph, and recommend it to the user.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the steps of the user demand determination method in multiple power system collaborative scenarios as described in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the user demand determination method under multiple power system collaborative scenarios as described in any one of claims 1 to 7.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the user demand determination method in multiple power system collaborative scenarios as described in any one of claims 1 to 7.

Images