Multi-user-oriented wind power forecast data pushing method and system

Abstract

The invention discloses a multi-user-oriented wind power forecast data pushing method and system. The method comprises the steps that user data and wind power plant related data are collected; feature extraction is carried out on the user data, clustering analysis is completed by using a clustering algorithm, and a comprehensive user portrait is constructed; inputting related data of the wind power plant into the LSTM model, and customizing and generating exclusive wind power forecast data meeting different user requirements; matching the wind power forecast data with the user portrait through a matching algorithm, and formulating a pushing strategy according to the user type to complete data pushing; and finally, collecting user feedback information, and updating and optimizing a user portrait and a pushing strategy in real time. According to the method, multi-user demand difference is fully considered, pertinence and effectiveness of wind power forecast data pushing are remarkably improved through data driving and dynamic optimization, high-quality data support is provided for users in all links of a wind power industry chain, and improvement of wind power operation management efficiency and decision scientificity is facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power forecast data push, and relates to a wind power forecast data push method and system for multiple users. Background Art

[0002] Amidst the global push to develop clean energy, wind power, as a key renewable energy source, continues to expand in scale and contribute a growing portion of the energy mix. Wind power forecast data helps wind power companies rationally plan power generation, grid dispatchers scientifically allocate power resources, and financial investment institutions accurately assess project risks. It plays a key role in improving the stability, cost-effectiveness, and safety of wind power system operations. However, current methods for distributing wind power forecast data present numerous challenges. For one thing, existing methods often employ standardized data content and strategies, failing to fully consider the significant differences in data needs, business scenarios, and usage objectives among diverse users within the wind power industry chain, including power generation companies, power grid dispatching departments, energy research institutions, and financial investment institutions. For example, power generation companies prioritize short-term power forecasts related to equipment operation to optimize power generation efficiency, while financial investment institutions require long-term wind power data and risk assessment information to support investment decisions. A unified approach to data dissemination fails to meet diverse needs, resulting in low data utilization. Furthermore, traditional methods lack dynamic optimization mechanisms, making it difficult to adjust data content and strategies to meet evolving user needs. As market conditions and weather conditions change, or as users adjust their business strategies, these fixed methods become unable to adapt to these new demands. Consequently, the distributed wind power forecast data becomes disconnected from actual user needs, failing to provide accurate and effective data support. Furthermore, in data processing and model application, traditional methods fail to fully leverage multi-source data and advanced algorithms, resulting in insufficient accuracy and relevance of wind power forecast data, further impacting the effectiveness of data dissemination. Summary of the Invention

[0003] The purpose of the present invention is to solve the technical problem that the existing technology does not take into account the significant differences in data requirements, business scenarios and usage purposes of different users, and lacks a dynamic optimization mechanism, resulting in inaccurate wind power data push, and to provide a wind power forecast data push method and system for multiple users.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A first aspect of the present invention provides a method for pushing wind power forecast data to multiple users, comprising the following steps: Collect user data and wind farm related data; Extract features from collected user data, perform cluster analysis on users through clustering algorithms, and build user portraits; The collected wind farm-related data is input into the LSTM model to generate customized wind power forecast data according to different user needs; Match wind power forecast data with user profiles and formulate corresponding push strategies based on different user types; push wind power forecast data based on the push strategies; Collect user feedback on the pushed wind power forecast data, and update and optimize user portraits and push strategies in real time based on the feedback information.

[0005] Furthermore, the user data includes user basic data and user behavior data; the user basic data includes at least the user's industry type, enterprise size, geographical location, specific role in the wind power industry chain, business focus and technical preferences; the user behavior data includes at least the user's historical query records, data usage frequency, and operating behaviors in different business scenarios.

[0006] Furthermore, the user portrait is constructed as follows: Based on the clustered user features, calculate user similarity and predict the target user's rating; The calculation formula of the user similarity is:

[0007] in, Represents a user and users similarity; Represents a user Data 's rating; Represents a user Data 's rating; Predict the target user's rating based on the ratings of other users similar to the target user:

[0008] in, Represents a user Data 's rating; For users Most similar A collection of users.

[0009] Furthermore, the wind power forecast data is matched with the user portrait using feature matching, similarity matching, demand priority matching or scenario-aware matching.

[0010] Furthermore, the user's feedback information on the pushed wind power forecast data includes at least satisfaction evaluation, data demand changes, and business scenario changes.

[0011] A second aspect 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 processor implements the above-mentioned method for pushing wind power forecast data to multiple users when executing the computer program.

[0012] A third aspect of the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-mentioned method for pushing wind power forecast data to multiple users.

[0013] A fourth aspect of the present invention provides a computer program product, the computer program product comprising computer instructions, the computer instructions instructing a computer to execute the above-mentioned method for pushing wind power forecast data for multiple users.

[0014] A fifth aspect of the present invention provides a wind power forecast data push system for multiple users, comprising: Data acquisition module, collecting user data and wind farm related data; The user portrait construction module extracts features from the collected user data, performs cluster analysis on users through clustering algorithms, and constructs user portraits; The wind power forecast data generation module inputs the collected wind farm-related data into the LSTM model and generates customized wind power forecast data according to different user needs; The data push module matches wind power forecast data with user profiles and formulates corresponding push strategies based on different user types; according to the push strategies, the wind power forecast data is pushed; The feedback module collects user feedback on the pushed wind power forecast data, and updates and optimizes user portraits and push strategies in real time based on the feedback information.

[0015] Furthermore, the multi-user oriented wind power forecast data push system further includes: The blockchain security module encrypts the data of each module; manages the access and use of data through the blockchain's smart contract function, allowing users to set data access rights and usage rules; and clearly records and authenticates each data provider and push link on the blockchain.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for pushing wind power forecast data for multiple users, which comprehensively collects user data and wind farm related data, covering user basic information, behavior data, feedback data, as well as conventional and expanded wind power data such as meteorology and equipment operation, providing a rich and accurate data basis for subsequent analysis, avoiding analysis deviations caused by data missing, and effectively improving the completeness and reliability of the data; constructing user portraits by performing feature extraction and cluster analysis on user data, deeply mining the demand characteristics of different user types, accurately characterizing user needs, breaking the limitations of the traditional unified push mode, and enabling data push to meet the personalized needs of different users such as power generation companies, power grid dispatching departments, and financial investment institutions, significantly improving the adaptability and utilization of data; using LSTM The model combines multi-source data to customize and generate exclusive wind power forecast data, giving full play to the advantages of advanced algorithms and multi-source information fusion. Compared with traditional data processing methods, it greatly improves the accuracy and pertinence of wind power forecast data, providing more reliable data support for user decision-making; matches wind power forecast data with user portraits and formulates differentiated push strategies, accurately pushes data according to user type and business scenario, and dynamically optimizes push through an adaptive weight adjustment mechanism when meteorological conditions change or the power market fluctuates, ensuring that data is delivered to users at the right time and in an appropriate manner, greatly enhancing the timeliness and effectiveness of data push; based on user feedback, user portraits and push strategies are updated and optimized in real time, and a dynamic cycle optimization system is established. It can quickly respond to changes in market environment, user business strategy adjustments and other demand changes, so that data push is always consistent with user actual needs, continuously improve user satisfaction, and provide high-quality and sustainable data services to users in all links of the wind power industry chain, helping to improve wind power operation and management efficiency and decision-making scientificity, and promote the efficient development of the wind power industry.

[0017] Furthermore, the present invention discloses a wind power forecast data push system for multiple users. The feedback module collects user feedback information in real time, driving the dynamic update and optimization of user profiles and push strategies. The blockchain security module uses encryption algorithms, smart contracts, and identity authentication mechanisms to provide all-round security protection for system data. Data encryption ensures the security of data during collection, transmission, and storage, preventing data leakage; smart contracts enable flexible management of data access rights and usage rules; blockchain records and identity authentication enhance data source traceability. In a certain wind power data sharing project, the risk of data tampering is close to zero, greatly enhancing user trust in the data and protecting system data security and user rights. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a block diagram of the wind power forecast data push method for multiple users according to the present invention. DETAILED DESCRIPTION

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Generally, the components of the embodiments of the present invention described and marked in the drawings herein can be arranged and designed in various different configurations.

[0021] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0022] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not require further definition or explanation in subsequent drawings.

[0023] The present invention is described in further detail below with reference to the accompanying drawings: See also Figure 1 The present invention discloses a method for pushing wind power forecast data to multiple users, comprising the following steps: Collect user data and wind farm related data; Extract features from collected user data, perform cluster analysis on users through clustering algorithms, and build user portraits; The collected wind farm-related data is input into the LSTM model to generate customized wind power forecast data according to different user needs; Match wind power forecast data with user profiles and formulate corresponding push strategies based on different user types; push wind power forecast data based on the push strategies; Collect user feedback on the pushed wind power forecast data, and update and optimize user portraits and push strategies in real time based on the feedback information.

[0024] An embodiment of the present invention provides a method for pushing wind power forecast data to multiple users, comprising the following steps: S1, collecting user data and wind farm related data; the user data includes user basic data and user behavior data; the user basic data at least includes the user's industry type, enterprise size, geographical location, specific role in the wind power industry chain, business focus and technical preferences; the user behavior data at least includes the user's historical query records, data usage frequency, and operation behavior in different business scenarios.

[0025] Specifically, information on relevant companies was collected through internal company surveys and online questionnaires. Wind power developers, identified as large, conglomerate operations, are geographically distributed across multiple wind energy resource-rich regions within the province. They play a role in project development and construction within the wind power industry chain, with a focus on offshore wind power development and a preference for high-power wind turbine technology and intelligent operations and maintenance. Operation and maintenance providers, primarily medium-sized, are located in wind farm clusters and are responsible for routine maintenance and troubleshooting of wind turbines within the industry chain. Their focus is on onshore wind power operations and maintenance, with a preference for condition monitoring and fault diagnosis. The company's internal wind power data management platform records user queries over the past three months. For example, one developer regularly queries short-term wind power forecast data for the next seven days each week, specifically querying parameters such as wind speed and power. Some operation and maintenance providers query real-time equipment operating data from different wind farms multiple times daily, demonstrating high data usage. In business scenarios such as wind power project bidding, users primarily query long-term wind power forecast data for the project location.

[0026] Regarding wind power-related data: We collaborate with meteorological authorities to obtain real-time meteorological data, including wind speed, wind direction, temperature, and air pressure, for multiple wind farms within the province. We collect operational data, such as generator power, blade speed, and gearbox oil temperature, from wind turbine monitoring systems. We also utilize historical wind power forecast data from the past five years for reference. We access satellite remote sensing data to obtain macro-climate and geographic information for the wind farm areas. For offshore wind farms, we collect marine environmental data, such as wave height and seawater temperature. We use web crawlers to capture social media discussions about wind power and gauge public interest. We collaborate with power trading centers and transportation authorities to obtain electricity market transaction data and transportation energy demand data.

[0027] S2, extract features from the collected user data, perform cluster analysis on users through clustering algorithms, and build user portraits; In S201, the collected user data was imported into a data cleaning tool to remove more than 200 duplicate records and correct more than 50 erroneous data. Missing data such as geographic location were supplemented using the neighbor value filling method. A normalization algorithm was used to unify different types of data into the scale range of [0,1] to improve the accuracy of subsequent analysis.

[0028] S202: For power generation companies, we delve into their equipment maintenance plans and find that one company plans to overhaul 10 wind turbines in the next quarter. At the same time, we explore their needs to improve unit performance, such as increasing the power generation efficiency of wind turbines at low wind speeds. For power grid dispatching departments, we focus on exploring their attention to real-time changes in the power market, such as the impact of real-time electricity price fluctuations on wind power dispatching, and cross-regional power allocation needs.

[0029] S203: When a power generation company announces the expansion of its offshore wind power business, the system immediately captures this dynamic change and updates the company's business focus, technology preferences and other characteristics in the user portrait.

[0030] In S204, the K-Means algorithm is used to classify the 100 users into five categories. Initial cluster centers are set, and after multiple iterations, users with similar characteristics and needs are grouped into the same category based on their multi-dimensional features. For example, companies focusing on offshore wind power development and high-power wind turbine technology are grouped together.

[0031] In S205, each user is assigned a score for different types of wind power forecast data based on factors such as their historical query history, usage duration, and operation frequency. For example, a developer scores short-term wind speed forecast data with a score of 4 out of 5, forming a user-data score matrix R. The cosine similarity formula is used to calculate the similarity between users. For example, if user u and user v both score short-term wind power forecast data and equipment operation data, the formula calculates a similarity of 0.8 between the two users, indicating that the two users have high similarity in their data needs.

[0032] The calculation formula of the user similarity is:

[0033] in, Represents a user and users similarity; Represents a user Data 's rating; Represents a user Data 's rating.

[0034] S206: Predict the target user's rating for the unrated data based on the ratings of other users similar to the target user. For example, if the average rating of the k users most similar to user u for a certain long-term wind power forecast data is 3, the formula predicts that user u's rating for the data is 2.8.

[0035] The formula for predicting the target user's score is:

[0036] in, Represents a user Data 's rating; For users Most similar A collection of users.

[0037] S3 inputs the collected wind farm-related data into the LSTM model to generate customized wind power forecast data based on different user needs; S301: Data cleaning tools are used to remove outliers from the collected wind power-related data, such as wind speed records with obvious errors. Missing equipment operation data is filled in using linear interpolation. Feature engineering is used to extract key features relevant to wind power forecasting, such as correlation analysis between wind speed and direction in meteorological data and generator power in equipment operation data. Multi-source data fusion algorithms are used to effectively integrate meteorological data, equipment operation data, and satellite remote sensing data.

[0038] In step S302, a long short-term memory (LSTM) network was used to train the processed data and build a wind power forecast model. Electricity market transaction data and transportation energy demand data were introduced as new feature variables to optimize the model structure. After 100 rounds of iterative training, the model's prediction accuracy reached over 90%.

[0039] S303 uses the trained LSTM model to generate customized wind power forecast data for different users. For example, forecast data containing wind power project risk assessments and investment return forecasts for the next three years is generated for financial investment institutions; and detailed wind power characteristic analysis data processed by specific algorithms is generated for energy research institutions.

[0040] S4, matching wind power forecast data with user profiles and formulating corresponding push strategies based on different user types; pushing wind power forecast data according to the push strategies; Matching wind power forecast data with user portraits adopts feature matching, similarity matching, demand priority matching or scenario-aware matching.

[0041] Feature matching involves matching wind power forecast data's time scale, parameter type, and regional scope with features in the user profile. For example, if a power generation company focuses on power forecast data for a specific region over the next 24 hours, the system will prioritize data that meets this feature.

[0042] Similarity matching specifically uses the cosine similarity formula to calculate the similarity between wind power forecast data and the user's historical query data. For example, if the similarity between a certain wind power forecast data and a certain user's historical query data is 0.7, it indicates that the data is more consistent with the user's historical needs.

[0043] Demand priority matching specifically involves sorting matching data based on the demand priorities extracted from user profiles. When the power market fluctuates significantly, an adaptive weight adjustment mechanism is introduced to dynamically increase the matching weight of market-related wind power data, such as adjusting the market data matching weight from 0.3 to 0.5.

[0044] Scenario-aware matching specifically means that when it is detected that a power generation company is in the equipment maintenance period, the system automatically senses the business scenario and pushes power complementary data and alternative energy solutions of surrounding wind farms during the maintenance period; when the power grid dispatching department faces peak electricity demand, it pushes wind power emergency dispatch forecast data for high-load periods.

[0045] Develop corresponding push strategies based on different user types, specifically: For power generation companies, the day's short-term wind power forecast data is pushed to 30 power generation companies in the province through the company's internal information management system at 8 a.m. every day; one week before equipment maintenance, relevant alternative energy data is pushed through a professional wind power operation APP.

[0046] For the grid dispatching department, the dynamic change data of wind power is pushed in real time through the data interface with the grid dispatching system, and the forecast data is updated in time when the meteorological conditions change or the electricity market fluctuates.

[0047] For energy research institutions, the latest wind power research-related data and research reports, such as wind power characteristics analysis reports, are sent to 10 energy research institutions in the province via email on the 1st of each month; customized data is pushed based on the research projects and key directions of the research institutions.

[0048] For financial investment institutions, one month before the wind power project is approved, long-term wind power forecast data, risk assessment reports and investment return forecast data for the project location will be pushed to five financial investment institutions in the province through a dedicated investment information platform.

[0049] S5 collects user feedback on the pushed wind power forecast data and uses this feedback to update and optimize the user profile and push strategy in real time. Within one week of data push, user feedback on the pushed data can be collected through the platform's built-in satisfaction rating system and feedback forms. For example, if 20 satisfaction ratings, 5 feedback on changes in data requirements, and 3 feedback on changes in business scenarios are collected, the user profile and push strategy can be updated and optimized in real time. For example, if a user reports an increased demand for wind power forecast data, the system will increase the weight of this data in the user profile and adjust the push strategy, increasing the push frequency of this data from once a week to three times a week.

[0050] An embodiment of the present invention provides a wind power forecast data push system for multiple users, comprising: Data acquisition module, collecting user data and wind farm related data; The user portrait construction module extracts features from the collected user data, performs cluster analysis on users through clustering algorithms, and constructs user portraits; The wind power forecast data generation module inputs the collected wind farm-related data into the LSTM model and generates customized wind power forecast data according to different user needs; The data push module matches wind power forecast data with user profiles and formulates corresponding push strategies based on different user types; according to the push strategies, the wind power forecast data is pushed; The feedback module collects user feedback on the pushed wind power forecast data, and updates and optimizes user portraits and push strategies in real time based on the feedback information.

[0051] One embodiment of the present invention provides a wind power forecast data push system for multiple users, further comprising: a blockchain security module for encrypting data in each module; managing data access and use through the blockchain's smart contract function, allowing users to set data access rights and usage rules; and clearly recording and authenticating each data provider and push link on the blockchain.

[0052] In another embodiment of the present invention, an electronic device is provided, comprising a processor and a memory, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions; the processor described in the embodiment of the present invention can be used for the operation of a wind power forecast data push method for multiple users.

[0053] In another embodiment of the present invention, a storage medium is provided, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a terminal device, used to store programs and data. It is understood that the computer-readable storage medium herein may include both built-in storage media in the terminal device and, of course, extended storage media supported by the terminal device. It may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for being loaded and executed by a processor. These instructions may be one or more computer programs (including program code). It should be noted that more specific examples (a non-exhaustive list) of computer-readable storage media herein include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk-read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0054] Computer-readable storage media also include data signals propagated in baseband or as part of a carrier wave, which carry readable program code. Such propagated data signals can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than a readable storage medium, which can send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0055] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0056] The processor may load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the method for pushing wind power forecast data to multiple users in the above embodiment.

[0057] One embodiment of the present invention provides a computer program product, which includes computer instructions, and the computer instructions instruct a computer to execute the above-mentioned method for pushing wind power forecast data to multiple users.

[0058] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for pushing wind power forecast data to multiple users, characterized in that: The following steps are involved: Collect user data and wind farm related data; Extract features from collected user data, perform cluster analysis on users through clustering algorithms, and build user portraits; The collected wind farm-related data is input into the LSTM model to generate customized wind power forecast data according to different user needs; Match wind power forecast data with user profiles and develop corresponding push strategies based on different user types; Push wind power forecast data according to the push strategy; Collect user feedback on the pushed wind power forecast data, and update and optimize user portraits and push strategies in real time based on the feedback information.

2. The method for pushing wind power forecast data to multiple users according to claim 1, characterized in that: The user data includes user basic data and user behavior data; the user basic data includes at least the user's industry type, enterprise size, geographical location, specific role in the wind power industry chain, business focus and technical preferences; the user behavior data includes at least the user's historical query records, data usage frequency, and operation behavior in different business scenarios.

3. The method for pushing wind power forecast data to multiple users according to claim 1, characterized in that: The construction of user portrait is specifically as follows: Based on the clustered user features, calculate user similarity and predict the target user's rating; The calculation formula of the user similarity is: in, Represents a user and users similarity; Represents a user Data 's rating; Represents a user Data 's rating; Predict the target user's rating based on the ratings of other users similar to the target user: in, Represents a user Data 's rating; For users Most similar A collection of users.

4. The method for pushing wind power forecast data to multiple users according to claim 1, characterized in that: Matching wind power forecast data with user portraits adopts feature matching, similarity matching, demand priority matching or scenario-aware matching.

5. The method for pushing wind power forecast data to multiple users according to claim 1, characterized in that: The user's feedback information on the pushed wind power forecast data at least includes satisfaction evaluation, data demand changes and business scenario changes.

6. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for pushing wind power forecast data for multiple users as claimed in any one of claims 1 to 6 is implemented.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for pushing wind power forecast data for multiple users according to any one of claims 1 to 6 is implemented.

8. A computer program product comprising computer instructions, characterized in that: The computer instructions instruct the computer to execute the multi-user oriented wind power forecast data push method according to any one of claims 1 to 6.

9. A wind power forecast data push system for multiple users, characterized in that: include: Data acquisition module, collecting user data and wind farm related data; The user portrait construction module extracts features from the collected user data, performs cluster analysis on users through clustering algorithms, and constructs user portraits; The wind power forecast data generation module inputs the collected wind farm-related data into the LSTM model and generates customized wind power forecast data according to different user needs; The data push module matches wind power forecast data with user profiles and formulates corresponding push strategies based on different user types; Push wind power forecast data according to the push strategy; The feedback module collects user feedback on the pushed wind power forecast data, and updates and optimizes user portraits and push strategies in real time based on the feedback information.

10. The multi-user oriented wind power forecast data push system according to claim 9, characterized in that: Also includes: The blockchain security module encrypts the data of each module; manages the access and use of data through the blockchain's smart contract function, allowing users to set data access rights and usage rules; and clearly records and authenticates each data provider and push link on the blockchain.

Images