Knowledge graph construction and recommendation method and system of terminal electric energy consumption related standard

By building a knowledge graph of terminal power consumption-related standards and using OWL and RNN models, the problem of difficult to predict power consumption trends and recommended standards in the existing technology is solved, and a comprehensive understanding and standard optimization of the field of power consumption is achieved.

CN119025667APending Publication Date: 2024-11-26STATE GRID ENERGY RES INST CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411058463.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

The existing technology is difficult to fully understand and predict the development trends in the field of terminal power consumption, and it is impossible to accurately recommend the relevant standards for power consumption required by terminal energy users.

Method used

By obtaining standards and energy data related to terminal electricity consumption, entity identification and preprocessing, building a knowledge graph, using OWL ontology language for ontology modeling, storage as RDF data model, and using recurrent neural network model to simulate and deduce, recommended according to user needs Suitable electricity consumption standards.

Benefits of technology

It has achieved the integration and correlation of electricity consumption standards, regulations and market data, provided scientific basis and theoretical support, optimized standard formulation, reduced related risks, and improved recommendation accuracy and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025667A_ABST
    Figure CN119025667A_ABST
Patent Text Reader

Abstract

The invention provides a knowledge graph construction and recommendation method and system for a terminal electric energy consumption policy, and the method comprises the steps: obtaining the terminal electric energy consumption policy and corresponding energy data, recognizing the entities in the terminal electric energy consumption policy and the corresponding energy data, and obtaining an entity data set; constructing a knowledge graph of a terminal electric energy consumption policy based on the entity data set; and recommending a corresponding terminal electric energy consumption policy to the energy consumer through the knowledge graph according to the query demand of the energy consumer. According to the method, multiple information such as policies, laws and regulations, market data, consumption behaviors and the like are integrated and associated by constructing the knowledge graph, so that the mutual influence relationship between the policies and the data can be better understood, and a scientific basis and decision support are provided for a decision maker; meanwhile, reference is provided for a policy maker through simulation and deduction, the policy effect is optimized, and the decision risk is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for constructing and recommending a knowledge graph of terminal power consumption related standards. Background Art

[0002] Many scholars have conducted research on electricity consumption, and these studies have provided a lot of references for the study of electricity consumption, but there is still a need for an effective way, that is, to conduct a deeper study of electricity consumption through algorithms. At present, the information sources of terminal energy consumption related standards are diverse and rich in content, and it is difficult to obtain key information from them, so that it is impossible to fully understand and predict the development trend of terminal electricity consumption, and it is even more impossible to accurately recommend to terminal energy users, and it is difficult to propose appropriate terminal electricity consumption related standards according to user needs. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for constructing and recommending a knowledge graph of terminal power consumption related standards, aiming to solve the above-mentioned problems in the prior art.

[0004] The embodiment of the present invention provides a knowledge graph construction and recommendation method for terminal power consumption related standards, including:

[0005] Obtain terminal power consumption related standards and corresponding energy data, identify entities in the terminal power consumption related standards and the corresponding energy data, and obtain an entity data set; wherein the corresponding energy data includes relevant regulations in the energy field, energy market data and consumption behavior data, and the entities include energy-related standards, energy consumers, energy technologies and energy markets; specifically including:

[0006] Preprocessing the terminal power consumption related standards and the corresponding energy data to obtain a standard data set, inputting the standard data set into a term frequency-inverse document frequency TF-IDF keyword extraction model for entity recognition to obtain required entity data, and performing entity linking on the entity data and removing duplicate entities to obtain a final entity data set;

[0007] Based on the entity data set, a knowledge graph of terminal power consumption related standards is constructed, specifically including:

[0008] Extracting attributes and relationships from the entity data set to obtain attribute data and relationship data, performing ontology modeling using the OWL ontology language based on the entity data set, attribute data, and relationship data, storing the obtained data using an RDF data model, and generating a knowledge graph of terminal power consumption-related standards;

[0009] The ontology modeling based on the entity data set, attribute data and relationship data using the OWL ontology language specifically includes:

[0010] The application field is defined as providing personalized consultation and suggestions on relevant standards to energy consumers, and the entities are defined as energy-related standards, energy consumers, energy technologies and energy markets, and the attributes and relationships of the entities are set;

[0011] Among them, the attributes of energy-related standards include the objectives of relevant standards, the contents of relevant standards, the names of relevant standards, issuing agencies, implementing agencies and effective dates; the attributes of energy consumers include industry type, energy demand, geographical location and scale; the attributes of energy technology include energy type, technical characteristics and application scenarios; the attributes of energy market include market type, market scale and market participants;

[0012] The relationships between entities include applicable standards, influencing standards, other relevant standards, applicable technologies, influencing technological developments, accessible markets, and inaccessible markets;

[0013] According to the query needs of energy consumers, the corresponding terminal power consumption related standards are recommended to energy consumers through the knowledge graph, specifically including:

[0014] According to the query needs of energy consumers, the knowledge graph is simulated and deduced using a recurrent neural network (RNN) model, and corresponding terminal power consumption related standards are recommended to energy consumers based on the obtained prediction results.

[0015] The embodiment of the present invention provides a knowledge graph construction and recommendation system for terminal power consumption related standards, including:

[0016] The identification module is used to obtain terminal power consumption related standards and corresponding energy data, identify entities in the terminal power consumption related standards and the corresponding energy data, and obtain an entity data set; wherein the corresponding energy data includes relevant laws and regulations in the energy field, energy market data and consumer behavior data, and the entities include energy-related standards, energy consumers, energy technologies and energy markets; specifically used for:

[0017] Preprocessing the terminal power consumption related standards and the corresponding energy data to obtain a standard data set, inputting the standard data set into a term frequency-inverse document frequency TF-IDF keyword extraction model for entity recognition to obtain required entity data, and performing entity linking on the entity data and removing duplicate entities to obtain a final entity data set;

[0018] A construction module is used to construct a knowledge graph of terminal power consumption related standards based on the entity data set, specifically for:

[0019] Extracting attributes and relationships from the entity data set to obtain attribute data and relationship data, performing ontology modeling using the OWL ontology language based on the entity data set, attribute data, and relationship data, storing the obtained data using an RDF data model, and generating a knowledge graph of terminal power consumption-related standards;

[0020] The recommendation module is used to recommend corresponding terminal power consumption related standards to energy consumers through the knowledge graph according to the query requirements of energy consumers.

[0021] An embodiment of the present invention also provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of constructing a knowledge graph and recommending methods for the above-mentioned terminal power consumption-related standards are implemented.

[0022] An embodiment of the present invention also provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps of constructing and recommending a knowledge graph of the above-mentioned terminal power consumption related standards are implemented.

[0023] The use of the embodiments of the present invention may include the following beneficial effects: the embodiments of the present invention integrate and correlate various information such as electricity consumption-related standards, relevant regulations, market data and consumer behavior by constructing a knowledge graph, thereby better understanding the mutual influence relationship between electricity consumption-related standards and data, and thus providing scientific basis and theoretical support for standard setters; at the same time, through simulation and deduction, it provides reference for standard setters, helps optimize the standard setting effect, and reduces related risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0025] Figure 1 is a flow chart of a knowledge graph construction and recommendation method for terminal power consumption related standards according to an embodiment of the present invention;

[0026] Figure 2 is a schematic diagram of the deduction accuracy test results of an embodiment of the present invention;

[0027] Figure 3 is a schematic diagram of the deduction time test results of an embodiment of the present invention;

[0028] Figure 4 is a schematic diagram of satisfaction survey results according to an embodiment of the present invention;

[0029] Figure 5 It is a schematic diagram of the knowledge graph construction and recommendation system of terminal power consumption related standards in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0031] Method Embodiment

[0032] According to an embodiment of the present invention, a knowledge graph construction and recommendation method for terminal power consumption related standards is provided. Figure 1 is a flow chart of a knowledge graph construction and recommendation method for terminal power consumption related standards according to an embodiment of the present invention, such as Figure 1 As shown, the knowledge graph construction and recommendation method of terminal power consumption related standards according to an embodiment of the present invention specifically includes:

[0033] Step S101, obtaining terminal power consumption related standards and corresponding energy data, identifying entities in the terminal power consumption related standards and the corresponding energy data, and obtaining an entity data set; wherein the corresponding energy data includes relevant regulations in the energy field, energy market data and consumption behavior data, and the entities include energy-related standards, energy consumers, energy technologies and energy markets; specifically including:

[0034] Preprocessing the terminal power consumption related standards and the corresponding energy data to obtain a standard data set, inputting the standard data set into a term frequency-inverse document frequency TF-IDF keyword extraction model for entity recognition to obtain required entity data, and performing entity linking on the entity data and removing duplicate entities to obtain a final entity data set;

[0035] Step S102, constructing a knowledge graph of terminal power consumption related standards based on the entity data set, specifically including:

[0036] Extracting attributes and relationships from the entity data set to obtain attribute data and relationship data, performing ontology modeling using the OWL ontology language based on the entity data set, attribute data, and relationship data, storing the obtained data using an RDF data model, and generating a knowledge graph of terminal power consumption-related standards;

[0037] The ontology modeling based on the entity data set, attribute data and relationship data using the OWL ontology language specifically includes:

[0038] The application field is defined as providing personalized consultation and suggestions on relevant standards to energy consumers, and the entities are defined as energy-related standards, energy consumers, energy technologies and energy markets, and the attributes and relationships of the entities are set;

[0039] Among them, the attributes of energy-related standards include the objectives of relevant standards, the contents of relevant standards, the names of relevant standards, issuing agencies, implementing agencies and effective dates; the attributes of energy consumers include industry type, energy demand, geographical location and scale; the attributes of energy technology include energy type, technical characteristics and application scenarios; the attributes of energy market include market type, market scale and market participants;

[0040] The relationships between entities include applicable standards, influencing standards, other relevant standards, applicable technologies, influencing technological developments, accessible markets, and inaccessible markets;

[0041] Step S103, recommending corresponding terminal power consumption related standards to energy consumers through the knowledge graph according to the query requirements of energy consumers, specifically including:

[0042] According to the query needs of energy consumers, the knowledge graph is simulated and deduced using a recurrent neural network (RNN) model, and corresponding terminal power consumption related standards are recommended to energy consumers based on the obtained prediction results.

[0043] The above technical solution of the embodiment of the present invention is described in detail below in combination with the specific circumstances of the knowledge graph construction and recommendation method of the terminal power consumption related standards in the embodiment of the present invention.

[0044] The embodiments of the present invention propose a method for integrating and processing relevant information such as relevant standards, relevant regulations, market data and consumer behavior in the field of terminal power consumption. On this basis, a method for constructing a knowledge graph of terminal power consumption related standards and a two-way recommendation method for terminal power consumption related standards and users are proposed.

[0045] This method establishes the correlation and knowledge system between relevant standards and data in the field of electricity consumption. It can evaluate the effectiveness of relevant standards, predict energy consumption trends, and formulate corresponding risk response strategies, providing important support for sustainable energy development and standard setting.

[0046] The embodiment of the present invention relates to a knowledge graph, entity extraction, breakthrough construction and recommendation method for text information of terminal energy-related standards. Keywords and subject terms extracted from the relevant standard text are used as entity elements of the knowledge graph, and a method for establishing connections between entities is proposed.

[0047] 1. Entity extraction method

[0048] Entities are the basic components of knowledge graphs. Through entity extraction and recognition, relevant entities such as energy-related standards, energy technologies, and energy consumers can be automatically extracted from a large amount of text data, providing a basis for subsequent relationship extraction and knowledge graph construction. By identifying entities and associating them with entities in the knowledge graph, and inferring the implicit relationships between entities, it is helpful to deeply understand and analyze the relevant content of terminal power consumption-related standards.

[0049] The text is preprocessed by word segmentation, part-of-speech tagging, stop word removal, etc. to prepare text data for entity extraction and recognition; features, parts of speech, contextual relationships, word vectors, etc. in the text are extracted for training and rule matching of entity recognition models (preferably, the entity recognition model can be a term frequency-inverse document frequency TF-IDF (Term Frequency-Inverse Document Frequency) keyword extraction model); the labeled data is used for model training, and the trained model and rules are applied to new text to identify entities in the text, classify and label them, and post-process the identified entities, such as removing duplicate entities, entity linking (associating entities with entities in the knowledge graph), etc.

[0050] 2. Knowledge graph representation learning and graph construction methods

[0051] Identify and represent the entities involved in the knowledge graph of the terminal power consumption business model, including energy-related standards, energy consumers, energy technologies, and energy markets. Each entity uses a unique identifier and contains attribute information to describe the connection and interaction between entities, including "applicable standards", "influencing standards", "applicable technologies", "influencing technology development", "accessible markets", and "inaccessible markets". Each relationship can be associated with the head and tail entities. Record the attribute information of entities and relationships to describe their characteristics and attributes. For example, the attributes of energy-related standards include the objectives of relevant standards, the content of relevant standards, and the implementing agencies. Attributes are represented in the form of key-value pairs and associated with entities. Consider the contextual information of entities and relationships, including time, place, related events, etc. These contextual information can help better understand and analyze the knowledge graph of terminal power consumption related standards. Use unified standards and models to represent the knowledge graph to achieve interoperability and scalability. In this embodiment of the present invention, RDF (Resource Description Framework) is selected as the data model, and OWL (Web Ontology Language) is used to define the domain ontology so as to perform semantic reasoning and query in the knowledge graph.

[0052] 3. Scene definition and parameter setting

[0053] The application scenario is defined as providing personalized consultation and advice on relevant standards to energy consumers. Through the knowledge graph, energy consumers can understand the relevant standards for electricity consumption applicable to their region and industry, and obtain interpretation, guidance and advice on relevant standards according to their own needs and conditions. The knowledge graph will cover the relevant standards for terminal electricity consumption in a specific country or region, including various relevant standard documents, regulations and guidelines, as well as relevant energy consumer information, energy technology and energy market information. The entity definition and attribute settings are as follows:

[0054] Energy-related standards have attributes such as the name of the relevant standards, issuing agency, effective date, and objectives of the relevant standards; energy consumers have attributes such as industry type, energy demand, geographical location, and scale; energy technology has attributes such as energy type (solar energy, wind energy, etc.), technical characteristics, and application scenarios; energy market has attributes such as market type (competitive market, monopoly market, etc.), market size, and market participants. The relationship definition and parameter settings are as follows: Applicable standards describe the relationship between energy-related standards applicable to specific regions, industries, or energy consumers; Influence standards describe the impact of specific energy technologies or markets on energy-related standards; Other related standards describe the relationship between different energy-related standards, such as complementary, alternative, or conflicting relationships.

[0055] 4. Simulation process

[0056] The knowledge graph of terminal power consumption-related standards constructed above contains multiple entities and their relationships such as energy-related standards, energy consumer information, and energy technology. Now assume that the query requirement is to find energy-related standards applicable to a specific energy consumer. According to the attributes of the energy consumer such as industry type, geographical location, and energy demand, find the entity related to the energy consumer, and find the applicable standard relationship related to the energy consumer in the relationship. This relationship connects the energy consumer and the energy-related standard entity, so the hidden state in the RNN is represented as:

[0057] h n = o· tanh(c n ); (1)

[0058] h n is the hidden state, o is the output gate, c n is the cell state at the current time step, and the output of the current time step can be expressed as:

[0059] y n = softmax(Wy n * h n + b n ); (2)

[0060] In the formula, y n represents the model output, W is the learnable parameter of the model, and b n Represents the constant term to be optimized. According to the applicable standard relationship, find the energy-related standard entity and obtain its related attribute information, such as the name of the relevant standard, issuing agency, effective date, etc. According to the results obtained in the query process, the energy-related standard information applicable to the energy consumer is obtained, including the name of the relevant standard, issuing agency, effective date, etc. In the deduction process, the knowledge graph can help obtain new information or generate new conclusions from existing entities and relationships. By reasoning and querying the attributes and relationships of entities, potential associations and laws can be discovered, providing valuable information for standard setting and problem solving.

[0061] The entities in the terminal power consumption related standard knowledge graph proposed in the embodiment of the present invention refer to energy consumers, related standard documents, etc., while the relationships represent the connections between entities. The deduction accuracy can evaluate the accuracy of the knowledge graph in relational inference, that is, through the existing entities and relationships, it can be inferred whether the new relationship is consistent with the actual situation. The actual test results are as follows: Figure 2 shown.

[0062] In order to accurately compare the accuracy of each algorithm, six experimental tests were conducted on each algorithm. The accuracy of CRF in the test was between 89% and 94%, the performance of SVM was 91% to 95%, and the performance of RNN was 94% to 98%. Among the three algorithms, RNN had the highest accuracy and could perform simulation deduction most accurately.

[0063] The standards related to terminal power consumption will change over time. By deducing time, we can observe the changes in the formulation, modification, and abolition of relevant standards, as well as the impact of these changes on terminal power consumption behavior and the market. Deducing time can help analyze the long-term effects and trends of relevant standards. Figure 3 This is the test result of deducing time.

[0064] Among the three algorithms, RNN takes the least time to infer, taking 1-3ms, while SVM takes the second most time, taking 2-5ms, and CRF takes the longest time, taking between 4-7ms. The RNN model can use previous information and memory during the inference process. If the model can effectively use this prior knowledge and apply it to the current inference task, it can generate accurate results faster without repeated calculations or iterations.

[0065] Then, a questionnaire survey was conducted on the knowledge graph and simulation deduction of the embodiment of the present invention to investigate their satisfaction during use. The satisfaction was divided into five levels: A, B, C, and D. A was evaluated as unsatisfied, and E was the most satisfied. The questionnaires were randomly distributed to users and collected. Figure 4 For the survey results.

[0066] In the satisfaction survey results, 3% of the people were dissatisfied with the deduction of the embodiment of the present invention, 5% were relatively dissatisfied, 12% had no feeling, 32% were relatively satisfied, and 48% were very satisfied. A total of 80% of the people were satisfied with it, indicating that the deduction of the design of the embodiment of the present invention has been recognized by most people.

[0067] In 2023, the province's total social electricity consumption was 783.3 billion kWh, a year-on-year increase of 5.9%. Among them, the total social electricity consumption in southern Jiangsu, central Jiangsu, and northern Jiangsu was 426.3 billion kWh, 136.8 billion kWh, and 184.4 billion kWh, respectively, up 3.3%, 8.4%, and 10.9% year-on-year, accounting for 54.4%, 17.5%, and 23.5% of the province's total social electricity consumption. At 13:25 on August 12, 2023, the total power load of Jiangsu's power grid reached 132.11 million kilowatts, the maximum load of the whole grid this summer, an increase of 1.07 million kilowatts from the maximum load of 131.03 million kilowatts in 2022, a year-on-year increase of 0.8%. From December 2023 to January 2024, the maximum load of the whole grid was 131 million kilowatts (December 21), a year-on-year increase of 21.8%.

[0068] It is estimated that Jiangsu's total electricity consumption will be about 825 billion kWh in 2024, a year-on-year increase of about 5.3%. In 2024, Jiangsu's summer noon peak will have a maximum network load of 145 million kilowatts, a year-on-year increase of 9.6%, and an average annual growth rate of 5.7% in the past five years. In 2025, Jiangsu's total electricity consumption will be 843 billion kWh, a year-on-year increase of 2.2%; the maximum power load in summer dispatching will be about 149.5 million kilowatts, a year-on-year increase of 4.5%; the maximum power load in winter dispatching and the entire network will be about 134 million kilowatts, a year-on-year increase of 7.2%, which is expected to occur in the evening.

[0069] System Example

[0070] According to an embodiment of the present invention, a knowledge graph construction and recommendation system for terminal power consumption related standards is provided. Figure 5 is a schematic diagram of a knowledge graph construction and recommendation system for terminal power consumption related standards according to an embodiment of the present invention, such as Figure 5 As shown, the knowledge graph construction and recommendation system of terminal power consumption related standards according to an embodiment of the present invention specifically includes:

[0071] The identification module 50 is used to obtain terminal power consumption related standards and corresponding energy data, identify entities in the terminal power consumption related standards and the corresponding energy data, and obtain an entity data set; wherein the corresponding energy data includes relevant laws and regulations in the energy field, energy market data and consumer behavior data, and the entities include energy-related standards, energy consumers, energy technologies and energy markets; specifically used for:

[0072] Preprocessing the terminal power consumption related standards and the corresponding energy data to obtain a standard data set, inputting the standard data set into a term frequency-inverse document frequency TF-IDF keyword extraction model for entity recognition to obtain required entity data, and performing entity linking on the entity data and removing duplicate entities to obtain a final entity data set;

[0073] The construction module 52 is used to construct a knowledge graph of terminal power consumption related standards based on the entity data set, specifically for:

[0074] Extracting attributes and relationships from the entity data set to obtain attribute data and relationship data, performing ontology modeling using the OWL ontology language based on the entity data set, attribute data, and relationship data, storing the obtained data using an RDF data model, and generating a knowledge graph of terminal power consumption-related standards;

[0075] The recommendation module 54 is used to recommend corresponding terminal power consumption related standards to energy consumers through the knowledge graph according to the query requirements of energy consumers.

[0076] The embodiment of the present invention is a system embodiment corresponding to the above-mentioned method embodiment. The specific operations of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0077] In summary, the embodiment of the present invention integrates relevant information such as relevant standards, relevant regulations, market data, consumer behavior, etc. into a structured graph by constructing a knowledge graph of terminal power consumption-related standards, forming an association relationship and knowledge system between power consumption-related standards and data. Such a knowledge graph helps people fully grasp the elements and factors in the field of terminal power consumption, and provides a data basis and context information for simulation. Through simulation, it is possible to observe and analyze changes in the patterns, load peaks, energy demand, etc. of terminal power consumption, so as to predict future energy consumption trends and formulate reasonable energy planning and resource allocation strategies; simulation also helps to predict and evaluate risks in the terminal power consumption market and system, and formulate corresponding response strategies, and timely discover risk points by observing the evolution and diffusion of potential risk factors over time, and take corresponding measures to ensure the reliability and stability of energy supply.

[0078] Device Example 1

[0079] An embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps described in the method embodiment when executed by the processor.

[0080] Device Example 2

[0081] An embodiment of the present invention provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by a processor, the steps described in the method embodiment are implemented.

[0082] The computer-readable storage medium in this embodiment includes, but is not limited to, ROM, RAM, magnetic disk or optical disk, etc.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A knowledge graph construction and recommendation method for terminal power consumption related standards, characterized in that include: Obtain terminal power consumption related standards and corresponding energy data, identify entities in the terminal power consumption related standards and the corresponding energy data, and obtain an entity data set; wherein the corresponding energy data includes relevant regulations in the energy field, energy market data and consumption behavior data, and the entities include energy-related standards, energy consumers, energy technologies and energy markets; Constructing a knowledge graph of terminal power consumption related standards based on the entity data set; and According to the query requirements of energy consumers, the knowledge graph is used to recommend corresponding terminal power consumption related standards to energy consumers.

2. The method according to claim 1, characterized in that: Identifying the entities in the terminal power consumption related standards and the corresponding energy data to obtain the entity data set specifically includes: The terminal power consumption related standards and the corresponding energy data are preprocessed to obtain a standard data set, and the standard data set is input into a term frequency-inverse document frequency TF-IDF keyword extraction model for entity recognition to obtain the required entity data, and the entity data is entity linked and duplicate entities are removed to obtain the final entity data set.

3. The method according to claim 1, characterized in that Constructing a knowledge graph of terminal power consumption-related standards based on the entity data set specifically includes: Attribute extraction and relationship extraction are performed on the entity data set to obtain attribute data and relationship data. Ontology modeling is performed using the OWL ontology language based on the entity data set, attribute data and relationship data. The obtained data is stored through the RDF data model to generate a knowledge graph of terminal power consumption related standards.

4. The method according to claim 3, characterized in that The ontology modeling based on the entity data set, attribute data and relationship data using the OWL ontology language specifically includes: The application field is defined as providing personalized consultation and suggestions on relevant standards to energy consumers, and the entities are defined as energy-related standards, energy consumers, energy technologies and energy markets, and the attributes and relationships of the entities are set; Among them, the attributes of energy-related standards include the objectives of relevant standards, the contents of relevant standards, the names of relevant standards, issuing agencies, implementing agencies and effective dates; the attributes of energy consumers include industry type, energy demand, geographical location and scale; the attributes of energy technology include energy type, technical characteristics and application scenarios; the attributes of energy market include market type, market scale and market participants; The relationships between entities include applicable standards, influencing standards, other relevant standards, applicable technologies, influencing technological development, accessible markets and inaccessible markets.

5. The method according to claim 1, characterized in that According to the query requirements of energy consumers, the corresponding terminal power consumption related standards are recommended to energy consumers through the knowledge graph, specifically including: According to the query needs of energy consumers, the knowledge graph is simulated and deduced using a recurrent neural network (RNN) model, and corresponding terminal power consumption related standards are recommended to energy consumers based on the obtained prediction results.

6. A knowledge graph construction and recommendation system for terminal power consumption related standards, characterized by include: An identification module is used to obtain terminal power consumption related standards and corresponding energy data, identify entities in the terminal power consumption related standards and the corresponding energy data, and obtain an entity data set; wherein the corresponding energy data includes relevant laws and regulations in the energy field, energy market data and consumer behavior data, and the entities include energy-related standards, energy consumers, energy technologies and energy markets; A construction module, used to construct a knowledge graph of terminal power consumption related standards based on the entity data set; and The recommendation module is used to recommend corresponding terminal power consumption related standards to energy consumers through the knowledge graph according to the query requirements of energy consumers.

7. The system according to claim 6, characterized in that The identification module is specifically used for: The terminal power consumption related standards and the corresponding energy data are preprocessed to obtain a standard data set, and the standard data set is input into a term frequency-inverse document frequency TF-IDF keyword extraction model for entity recognition to obtain the required entity data, and the entity data is entity linked and duplicate entities are removed to obtain the final entity data set.

8. The system according to claim 6, characterized in that The building blocks are specifically used to: Attribute extraction and relationship extraction are performed on the entity data set to obtain attribute data and relationship data. Ontology modeling is performed using the OWL ontology language based on the entity data set, attribute data and relationship data. The obtained data is stored through the RDF data model to generate a knowledge graph of terminal power consumption related standards.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of a method for constructing and recommending a knowledge graph of terminal power consumption-related standards as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by the processor, the steps of the knowledge graph construction and recommendation method for terminal power consumption related standards as described in any one of claims 1-5 are implemented.