Photovoltaic power station digital asset full life cycle management method and system

Abstract

The invention discloses a photovoltaic power station digital asset full life cycle management method and system, and belongs to the technical field of data management, and the method comprises the steps: carrying out the entity modeling of a photovoltaic power station according to the use demands of a photovoltaic power station digital asset use object, and obtaining a structured data set; according to the importance of the structured data in the structured data set, carrying out differential storage on the structured data; according to the data search request, screening out target data from a database by using a lightweight search engine constructed based on a mapping relationship between conditional search logic and the unique identifier of the photovoltaic power station; and constructing a data quality scoring function based on linear regression, obtaining the score of the target data through the data quality scoring function, and perfecting the target data by taking corresponding measures according to the score level of the target data. The technical problems that in the prior art, range definition is fuzzy, storage architecture adaptability is insufficient, data access efficiency and coverage are difficult to consider, and data quality is difficult to guarantee are solved.

Description

Technical Field

[0001] This invention relates to the field of data management technology, specifically to a method and system for the full lifecycle management of digital assets in photovoltaic power plants. Background Technology

[0002] With the rapid development of the photovoltaic industry, the scale and complexity of digital assets in photovoltaic power plants continue to rise. During the evolution of digital resources, companies within the industry are gradually revealing a series of core pain points that urgently need to be addressed: First, traditional modeling methods have a vague definition of the management scope of digital assets, often resulting in coverage that is too broad or too narrow, leading to insufficient matching with actual business needs and making it difficult to support precise operations. Second, the singular data storage model has structural defects, failing to simultaneously address the global consistency of core data and the flexible expansion needs of peripheral data, creating a contradiction where uniformity leads to inflexibility, and vice versa. Third, the data query process faces dual bottlenecks in efficiency and coverage; pursuing rapid retrieval makes it difficult to obtain full-domain data, while focusing on full-domain data acquisition significantly reduces search efficiency, failing to balance the business's dual demands for speed and comprehensiveness. Fourth, existing solutions have significant shortcomings in data quality control, failing to build a comprehensive control system covering data consistency, integrity, and accuracy, resulting in persistent problems such as inconsistencies between multi-source data, missing key information, and high data error rates. Summary of the Invention

[0003] To address the technical problems of existing technologies, such as ambiguous scope definition, insufficient adaptability of storage architecture, difficulty in balancing data access efficiency and coverage, and difficulty in guaranteeing data quality, this invention provides a method and system for the full lifecycle management of digital assets in photovoltaic power plants. It involves entity modeling based on the usage needs of the users of the photovoltaic power plant's digital assets, differentiated storage based on the importance of structured data, constructing a lightweight search engine through the mapping relationship between conditional search logic and the unique identifier of the photovoltaic power plant, obtaining a score for the target data by constructing a data quality scoring function, and taking corresponding measures to improve the target data based on the score level. This solves the technical problems of existing technologies, including ambiguous scope definition, insufficient adaptability of storage architecture, difficulty in balancing data access efficiency and coverage, and difficulty in guaranteeing data quality.

[0004] To address the aforementioned technical problems, this invention provides a method for full lifecycle management of digital assets in photovoltaic power plants, comprising the following steps: Based on the usage needs of the users of the photovoltaic power station's digital assets, a structured data set is obtained by performing entity modeling of the photovoltaic power station; Based on the importance of structured data in the structured dataset, structured data is stored differently through data channels; A lightweight search engine is built based on the mapping relationship between conditional search logic and the unique identifier of a photovoltaic power station; Based on the data search request, a lightweight search engine is used to filter the target data from the database; A data quality scoring function is constructed based on linear regression. The score of the target data is obtained through the data quality scoring function, and corresponding measures are taken to improve the target data according to the score level.

[0005] Preferably, the step of obtaining a structured data set by performing entity modeling of the photovoltaic power station based on the usage needs of the users of the photovoltaic power station's digital assets includes: Based on the usage needs of the users of the digital assets of photovoltaic power plants, obtain three-dimensional physical information representing the physical spatial state of the photovoltaic power plant and temporal process information representing the physical temporal trajectory. The three-dimensional physical information and time process information are bound to the corresponding entities to form an entity dataset, and then a structured data set is constructed based on the entity dataset.

[0006] Preferably, the step of differentially storing structured data through data channels based on the importance of the structured data in the structured dataset includes: Structured data is divided into core structured data and non-core structured data based on the degree of sharing and reuse of structured data in each business domain. Core structured data is synchronized to the master data management platform for centralized storage through data channels, while non-core structured data is synchronized to business domain data storage nodes for storage. Finally, non-core structured data is integrated into the master data management platform via RPC.

[0007] Preferably, the step of using a lightweight search engine to filter target data from the database according to the data search request includes: Based on the data search request, obtain the conditional query logic, use a lightweight search engine to obtain the unique identifier of the photovoltaic power station corresponding to the conditional query logic, and use the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the only search condition to search the database to obtain the target data.

[0008] Preferably, the step of searching the database to obtain target data using the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the unique search condition includes: The first target data is obtained by searching the database in the master data management platform using the unique identifier of the photovoltaic power station corresponding to the condition query logic as the unique search condition; Using the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the unique search condition, the database in the business domain data storage node is searched to obtain the second target data, and the target data is formed based on the first target data and the second target data.

[0009] Preferably, the data quality scoring function constructed based on linear regression includes: Using data consistency, correctness, validity, and completeness as initial data quality scoring benchmarks, the weights of the initial data quality scoring benchmarks are obtained through linear regression, and a data quality scoring function is constructed based on the initial data quality scoring benchmarks and weights.

[0010] Preferably, the step of obtaining the weights of the initial data quality scoring benchmark through linear regression includes: Acquire historical photovoltaic power plant data, and obtain the feature values ​​of the initial data quality scoring benchmark based on the historical photovoltaic power plant data; A linear regression model is constructed using the feature value of any one of the initial data quality scoring benchmarks as the target value and the feature values ​​of the other benchmarks in the initial data quality scoring benchmark as the input features. The predicted value is obtained based on the feature values ​​of the linear regression model and other benchmarks. If the difference between the target value and the predicted value is less than the preset difference, the benchmark corresponding to the target value with the difference less than the preset difference will be removed from the initial data quality scoring benchmark to obtain the final data quality scoring benchmark. The initial weights of the final data quality scoring benchmark are obtained using the analytic hierarchy process (AHP). The initial scores of the historical target data are obtained based on the initial weights and the feature values ​​of the historical target data in the historical photovoltaic power station data. The initial weights are then corrected based on the initial scores and business feedback to obtain the weights of the initial data quality scoring benchmark.

[0011] The beneficial effects of this plan are: To address the issues of ambiguous scope definition and insufficient matching with business needs, the method focuses on the usage needs of users of photovoltaic power plant digital assets for entity modeling. This anchors the actual business demands from the source, avoiding the problem of overly broad or narrow scope in traditional modeling. It ensures that the structured data set is accurately aligned with business needs, providing a foundation for precise operation. To address the issue that a single storage model cannot simultaneously ensure both the uniformity of core data and the flexibility of peripheral data, a design based on data importance and differentiated storage can be implemented. This allows for unified storage of core data to ensure global consistency, while peripheral data can be stored using business domain data storage nodes, thus resolving the contradiction between uniformity and flexibility. To address the challenge of balancing data query efficiency and full coverage, a lightweight search engine is built by mapping conditional search logic with the unique identifier of the power station. This not only enables accurate association of data across the entire domain based on the unique identifier, but also improves retrieval speed through lightweight design. This can simultaneously meet the business's dual needs for fast retrieval and full coverage, thereby breaking through the query bottleneck. To address the issues of inadequate data quality control and prominent problems with multi-source data, a data quality scoring function is constructed using linear regression, and a mechanism for improving data based on scoring levels is established. This creates a quantitative control system covering data consistency, completeness, and accuracy, which can specifically identify and resolve issues such as inconsistency, missing information, and high error rates in multi-source data, thereby filling the gap in comprehensive data quality control. To address the issue of low weight accuracy caused by strongly correlated benchmarks in the initial data quality scoring, this paper proposes a method that uses the feature value of any one benchmark as the target value and the remaining benchmarks as input features for modeling. If the difference between the target value and the model's predicted value is less than a preset threshold, it indicates that the information of that target benchmark can be replaced by other benchmarks, suggesting a strong correlation. By eliminating these strongly correlated benchmarks, redundant interference is removed from subsequent weight calculations, thereby improving the accuracy of the obtained weights.

[0012] This invention also provides a full lifecycle management system for digital assets of photovoltaic power plants, applicable to the aforementioned method for full lifecycle management of digital assets of photovoltaic power plants, comprising: The entity modeling module is used to perform entity modeling of photovoltaic power plants based on the usage requirements of the users of photovoltaic power plant digital assets and obtain a set of structured data. The storage module is used to differentiate the storage of structured data through data channels based on the importance of the structured data in the structured data set. A lightweight search engine building module is used to build a lightweight search engine based on the mapping relationship between conditional search logic and the unique identifier of a photovoltaic power station. The target data filtering module is used to filter target data from the database using a lightweight search engine based on data search requests; The scoring acquisition module is used to construct a data quality scoring function based on linear regression, and to obtain the score of the target data through the data quality scoring function.

[0013] The beneficial effects of this plan are: This approach utilizes entity modeling based on the usage needs of users of photovoltaic power plant digital assets. It differentiates the storage of structured data according to its importance, constructs a lightweight search engine by mapping conditional search logic to the unique identifier of the photovoltaic power plant, and obtains a score for the target data through a data quality scoring function. Based on the score level, corresponding measures are taken to improve the target data. This solution addresses the technical problems of existing technologies, such as ambiguous scope definition, insufficient storage architecture adaptability, difficulty in balancing data access efficiency and coverage, and difficulty in guaranteeing data quality.

[0014] The present invention also provides a computer device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for full lifecycle management of digital assets of a photovoltaic power station.

[0015] The present invention also provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, performs the steps of the method for full lifecycle management of digital assets of a photovoltaic power station. Attached Figure Description

[0016] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0017] Figure 1 This is a flowchart illustrating a method for full lifecycle management of digital assets in photovoltaic power plants according to the present invention. Figure 2 This is a logic diagram of entity modeling in a method for full lifecycle management of digital assets of photovoltaic power plants according to the present invention; Figure 3 This is a sequence diagram of interface calls in a method for full lifecycle management of digital assets of photovoltaic power plants according to the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only one preferred embodiment of this invention and are only used to explain this invention. They do not limit the scope of protection of this invention. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0019] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of the operations (or steps) can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it may also have additional steps not included in the figures; the process may correspond to a method, function, procedure, subroutine, subroutine, etc.

[0020] Example 1: like Figure 1 As shown, a method for full lifecycle management of digital assets of photovoltaic power plants includes the following steps: S1: Based on the usage requirements of the users of the photovoltaic power station digital assets, perform entity modeling of the photovoltaic power station to obtain a structured data set.

[0021] The users of photovoltaic power plant digital assets specifically refer to downstream application scenarios after the power plant is completed, such as operation and maintenance, power plant transactions, and electricity transactions. Since these downstream scenarios are not concerned with the documents generated during the power plant construction process, but rather with the resulting data, such as the main structure of the power plant, its foundation (roof), and some brief process information, a physical model of the power plant is created to meet user needs. Firstly, the model data generated in this way is more easily understood and accepted by downstream users; secondly, the model data is more stable and robust, and will not change due to changes in the power plant construction process, which has a smaller impact on the entire data asset management system. Finally, compared to document-based modeling, this modeling method is more cohesive and fundamental, without needing to concern itself with many business logic aspects of the construction process, thus simplifying the design of external read / write interfaces.

[0022] Specifically, the process of obtaining a structured data set by performing entity modeling of the photovoltaic power station based on the usage requirements of the users of the photovoltaic power station's digital assets includes: Based on the usage needs of the users of the digital assets of photovoltaic power plants, obtain three-dimensional physical information representing the physical spatial state of the photovoltaic power plant and temporal process information representing the physical temporal trajectory. The three-dimensional physical information and time process information are bound to the corresponding entities to form an entity dataset, and then a structured data set is constructed based on the entity dataset.

[0023] like Figure 2As shown, the 3D physical information corresponds to the spatial attributes of entities such as the power station structure and foundation in the physical domain (e.g., the installation location of components, the 3D layout of the roof), digitizing the spatial characteristics of various static assets in the physical domain. The temporal process information corresponds to the dynamic management processes such as nodes and logs in the process domain (e.g., the creation time of nodes, the process sequence of log records), digitizing the temporal characteristics of management behaviors and asset status changes in the process domain. Binding the 3D physical information and temporal process information to their corresponding entities essentially uses the power station as the core connection point to associate the physical domain and the process domain, ultimately forming a structured data set. In this embodiment, modeling data is acquired based on the needs of the users, limiting the core dimensions and boundaries of entity modeling from the source. This avoids the drawbacks of traditional modeling where the management scope is too broad or too narrow, allowing the structured data set to directly connect with business scenarios (e.g., maintenance personnel focusing on equipment operation trajectories, and planning personnel focusing on the spatial layout of the power station), ensuring that data assets can effectively support the work needs of different roles. Furthermore, entity modeling significantly reduces storage costs and subsequent digital maintenance costs.

[0024] S2: Based on the importance of the structured data in the structured dataset, the structured data is stored differently through data channels.

[0025] As a preferred embodiment, the step of differentially storing structured data through a data channel based on the importance of the structured data in the structured data set includes: Structured data is divided into core structured data and non-core structured data based on the degree of sharing and reuse of structured data in each business domain. Core structured data is synchronized to the master data management platform for centralized storage through data channels, while non-core structured data is synchronized to business domain data storage nodes for storage. Finally, non-core structured data is integrated into the master data management platform via RPC.

[0026] The master data management platform is specifically a data asset management platform, while the business domain data storage nodes are third-party data service providers. By synchronizing core structured data to the master data management platform for centralized storage, data consistency and accuracy are ensured. Data is categorized and stored according to its degree of sharing and reuse, thus avoiding the waste of resources due to the dispersed storage of core data and the redundancy caused by non-core data occupying master platform resources.

[0027] S3: A lightweight search engine is built based on the mapping relationship between conditional search logic and the unique identifier of a photovoltaic power station.

[0028] Understandably, conditional search logic refers to the set of filtering rules corresponding to user query needs. Specifically, it revolves around the business scenario of photovoltaic power plant digital assets, breaking down user search requests into combinations of filtering conditions that can be recognized by the system and are related to the attributes of the power plant assets. For example: filtering by entity type: such as searching for all inverter data of a certain power plant; filtering by time range: such as searching for the operating parameters of a certain component in Q3 2025; filtering by data attribute: such as searching for equipment records where voltage fluctuations exceed a threshold; filtering by business scenario: such as searching for business cooperation data of a certain grid-connected project. The combination rules of these specific filtering conditions (entity, time, attribute, scenario, etc.) constitute the conditional search logic.

[0029] S4: Based on the data search request, use a lightweight search engine to filter the target data from the database.

[0030] In another embodiment, the step of filtering target data from the database using a lightweight search engine based on a data search request includes: Based on the data search request, obtain the conditional query logic, use a lightweight search engine to obtain the unique identifier of the photovoltaic power station corresponding to the conditional query logic, and use the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the only search condition to search the database to obtain the target data.

[0031] like Figure 3 As shown, the search logic is handled by a search engine, while the database storage only provides information retrieval by power station number. The specific query method is as follows: first, the power station number is retrieved based on the search criteria, and then the database is queried based on the power station number. This query method satisfies both the business's need for fast retrieval and comprehensive coverage. Furthermore, even without database sharding, the database storage can support single-table storage of hundreds of millions of data entries, thus overcoming the database query bottleneck. In this embodiment, database binlog messages are also used to help the business monitor data changes in real time. The database binlog is synchronized to the big data platform, supporting near real-time data applications on the big data platform.

[0032] In some embodiments, the step of searching the database to obtain target data using the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the unique search condition includes: The first target data is obtained by searching the database in the master data management platform using the unique identifier of the photovoltaic power station corresponding to the condition query logic as the unique search condition; Using the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the unique search condition, the database in the business domain data storage node is searched to obtain the second target data, and the target data is formed based on the first target data and the second target data.

[0033] S5: Construct a data quality scoring function based on linear regression, obtain the score of the target data through the data quality scoring function, and take corresponding measures to improve the target data according to the score level of the target data.

[0034] As a preferred embodiment, the construction of the data quality scoring function based on linear regression includes: Using data consistency, correctness, validity, and completeness as initial data quality scoring benchmarks, the weights of the initial data quality scoring benchmarks are obtained through linear regression, and a data quality scoring function is constructed based on the initial data quality scoring benchmarks and weights.

[0035] Specifically, the process of obtaining the weights for the initial data quality scoring benchmark through linear regression includes: Acquire historical photovoltaic power plant data, and obtain the feature values ​​of the initial data quality scoring benchmark based on the historical photovoltaic power plant data; A linear regression model is constructed using the feature value of any one of the initial data quality scoring benchmarks as the target value and the feature values ​​of the other benchmarks in the initial data quality scoring benchmark as the input features. The predicted value is obtained based on the feature values ​​of the linear regression model and other benchmarks. If the difference between the target value and the predicted value is less than the preset difference, the benchmark corresponding to the target value with a difference less than the preset difference will be removed from the initial data quality scoring benchmark to obtain the final data quality scoring benchmark. The initial weights of the final data quality scoring benchmark are obtained using the analytic hierarchy process (AHP). The initial scores of the historical target data are obtained based on the initial weights and the feature values ​​of the historical target data in the historical photovoltaic power plant data. The initial weights are then corrected based on the initial scores and business feedback to obtain the weights of the initial data quality scoring benchmark.

[0036] In this embodiment, considering the presence of strongly correlated benchmarks in the initial data quality scoring, which could lead to low weight accuracy, a model is constructed using the feature value of any benchmark as the target value and the remaining benchmarks as input features. If the difference between the target value and the model's predicted value is less than a preset difference, it indicates that the information of that target benchmark can be replaced by other benchmarks, suggesting a strong correlation. By eliminating such strongly correlated benchmarks, redundant interference is eliminated for subsequent weight calculations, thereby improving the accuracy of the obtained weights. It is understood that the preset difference can be flexibly set according to user needs. Business feedback specifically refers to the evaluation of the initial score by personnel involved in the actual use of data in photovoltaic power plant operations, maintenance, scheduling, and finance, based on their work scenarios. Correcting the initial weights through business feedback solves the problem of mismatch between weights and business value, ensuring that subsequent data quality scores are no longer detached from business operations but rather accurate indicators reflecting the data's ability to support business needs.

[0037] Specific measures can be as follows: 1. Excellent (90-100 points): Routine monitoring, no need for proactive repair, simply include in the routine data quality monitoring list, automatically generate a data quality report weekly, and confirm no new issues. 2. Acceptable (70-89 points): Light optimization, supplement as needed, initiate lightweight repairs for non-critical issues, no manual intervention required, the system automatically completes the repairs, and only sampling verification is needed after repair. 3. Needing Repair (40-69 points): Key repair, manual verification, initiate a priority repair process, first locate the problem type (e.g., error → correction, inconsistency → calibration), then handle it specifically, requiring a combination of automatic system repair and manual verification, and full verification is required after repair to ensure no residual issues. 4. Critical Defect (0-39 points): Emergency repair, business collaboration, trigger emergency repair pre-emptive action, escalate the problem to the operation and maintenance and data teams for collaborative handling, take in-depth repair actions for critical issues, the affected business needs to be suspended during the repair process (e.g., temporarily suspend fault diagnosis), and multi-party verification is required after repair (operation and maintenance, scheduling, and data teams jointly confirm) to ensure the data is fully usable.

[0038] Example 2: This embodiment also provides a full lifecycle management system for digital assets of photovoltaic power plants, applicable to the aforementioned method for full lifecycle management of digital assets of photovoltaic power plants, including: The entity modeling module is used to perform entity modeling of photovoltaic power plants based on the usage requirements of the users of photovoltaic power plant digital assets and obtain a set of structured data. The storage module is used to differentiate the storage of structured data through data channels based on the importance of the structured data in the structured data set. A lightweight search engine building module is used to build a lightweight search engine based on the mapping relationship between conditional search logic and the unique identifier of a photovoltaic power station. The target data filtering module is used to filter target data from the database using a lightweight search engine based on data search requests; The scoring acquisition module is used to construct a data quality scoring function based on linear regression, and to obtain the score of the target data through the data quality scoring function.

[0039] Example 3: This embodiment also provides a computer device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions that the processor can execute. When the computer device is running, the processor communicates with the memory through the bus, and the processor executes the machine-readable instructions to perform the steps of the method for full lifecycle management of digital assets of a photovoltaic power station.

[0040] Example 4: This embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for full lifecycle management of digital assets of a photovoltaic power station.

[0041] The specific embodiments described above are preferred embodiments of the photovoltaic power plant digital asset full life cycle management method and system of the present invention, and are not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to the specific embodiments described above. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A method for full lifecycle management of digital assets of photovoltaic power plants, characterized in that, Includes the following steps: Based on the usage needs of the users of the photovoltaic power station's digital assets, a structured data set is obtained by performing entity modeling of the photovoltaic power station; Based on the importance of structured data in the structured dataset, structured data is stored differently through data channels; A lightweight search engine is built based on the mapping relationship between conditional search logic and the unique identifier of a photovoltaic power station; Based on the data search request, a lightweight search engine is used to filter the target data from the database; A data quality scoring function is constructed based on linear regression. The score of the target data is obtained through the data quality scoring function, and corresponding measures are taken to improve the target data according to the score level.

2. The method for full lifecycle management of digital assets of photovoltaic power plants according to claim 1, characterized in that, The process of obtaining a structured data set by performing entity modeling of the photovoltaic power station based on the usage needs of the users of the photovoltaic power station's digital assets includes: Based on the usage needs of the users of the digital assets of photovoltaic power plants, obtain three-dimensional physical information representing the physical spatial state of the photovoltaic power plant and temporal process information representing the physical temporal trajectory. The three-dimensional physical information and time process information are bound to the corresponding entities to form an entity dataset, and then a structured data set is constructed based on the entity dataset.

3. The method for full lifecycle management of digital assets of photovoltaic power plants according to claim 1, characterized in that, The method of differentially storing structured data through data channels based on the importance of the structured data in the structured dataset includes: Structured data is divided into core structured data and non-core structured data based on the degree of sharing and reuse of structured data in each business domain. Core structured data is synchronized to the master data management platform for centralized storage through data channels, while non-core structured data is synchronized to business domain data storage nodes for storage. Finally, non-core structured data is integrated into the master data management platform via RPC.

4. The method for full lifecycle management of digital assets of photovoltaic power plants according to claim 1, characterized in that, The step of using a lightweight search engine to filter target data from the database based on the data search request includes: Based on the data search request, obtain the conditional query logic, use a lightweight search engine to obtain the unique identifier of the photovoltaic power station corresponding to the conditional query logic, and use the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the only search condition to search the database to obtain the target data.

5. The method for full lifecycle management of digital assets of photovoltaic power plants according to claim 4, characterized in that, The process of searching the database to obtain target data using the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the unique search condition includes: The first target data is obtained by searching the database in the master data management platform using the unique identifier of the photovoltaic power station corresponding to the condition query logic as the unique search condition; Using the unique identifier of the photovoltaic power station corresponding to the conditional query logic as the unique search condition, the database in the business domain data storage node is searched to obtain the second target data, and the target data is formed based on the first target data and the second target data.

6. The method for full lifecycle management of digital assets of photovoltaic power plants according to claim 1, characterized in that, The data quality scoring function based on linear regression includes: Using data consistency, correctness, validity, and completeness as initial data quality scoring benchmarks, the weights of the initial data quality scoring benchmarks are obtained through linear regression, and a data quality scoring function is constructed based on the initial data quality scoring benchmarks and weights.

7. The method for full lifecycle management of digital assets of photovoltaic power plants according to claim 6, characterized in that, The weights for obtaining the initial data quality scoring benchmark through linear regression include: Acquire historical photovoltaic power plant data, and obtain the feature values ​​of the initial data quality scoring benchmark based on the historical photovoltaic power plant data; A linear regression model is constructed using the feature value of any one of the initial data quality scoring benchmarks as the target value and the feature values ​​of the other benchmarks in the initial data quality scoring benchmark as the input features. The predicted value is obtained based on the feature values ​​of the linear regression model and other benchmarks. If the difference between the target value and the predicted value is less than the preset difference, the benchmark corresponding to the target value with the difference less than the preset difference will be removed from the initial data quality scoring benchmark to obtain the final data quality scoring benchmark. The initial weights of the final data quality scoring benchmark are obtained using the analytic hierarchy process (AHP). The initial scores of the historical target data are obtained based on the initial weights and the feature values ​​of the historical target data in the historical photovoltaic power station data. The initial weights are then corrected based on the initial scores and business feedback to obtain the weights of the initial data quality scoring benchmark.

8. A full lifecycle management system for digital assets of a photovoltaic power station, applicable to the full lifecycle management method for digital assets of a photovoltaic power station as described in any one of claims 1-7, characterized in that, include: The entity modeling module is used to perform entity modeling of photovoltaic power plants based on the usage requirements of the users of photovoltaic power plant digital assets and obtain a set of structured data. The storage module is used to differentiate the storage of structured data through data channels based on the importance of the structured data in the structured data set. A lightweight search engine building module is used to build a lightweight search engine based on the mapping relationship between conditional search logic and the unique identifier of a photovoltaic power station. The target data filtering module is used to filter target data from the database using a lightweight search engine based on data search requests; The scoring acquisition module is used to construct a data quality scoring function based on linear regression, and to obtain the score of the target data through the data quality scoring function.

9. A computer device, comprising: The computer device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of a photovoltaic power plant digital asset lifecycle management method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, performs the steps of a method for full lifecycle management of digital assets of a photovoltaic power station as described in any one of claims 1-7.

Images