Business scheduling method combining business and group leader cockpit and related equipment

Abstract

The invention discloses a business and group leader cockpit combined business scheduling method and related equipment. The method comprises the following steps: constructing a three-dimensional dynamic data matrix by acquiring equipment operation data and environment monitoring data of a plurality of power plants; analyzing the business team operation log and the group leader decision record based on a natural language processing technology, and generating dynamic user portraits of the business team and the group leader; real-time change characteristics are extracted according to the three-dimensional dynamic data matrix, and dynamic scheduling strategy information is generated through a multi-objective optimization algorithm according to the equipment operation frequency characteristic coefficient, the strategic index sensitivity coefficient and the real-time change characteristics; and pushing an equipment operation instruction of the dynamic scheduling strategy information to the business cockpit according to the business authority corresponding to the business cockpit, and pushing a strategic decision support graph of the visual scheduling instruction set to the group cockpit according to the business authority corresponding to the group cockpit. A comprehensive business scheduling solution is provided, and powerful support is provided for business and management layers.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular, to a business scheduling method and related devices that combine business and group leadership cockpits. Background Art

[0002] In the energy group operation and management, the coordinated scheduling of multiple power plants has long faced the dual problems of data fragmentation and decision-making level disconnection. Traditional scheduling systems usually adopt a single-dimensional data monitoring mode. The business side focuses on collecting equipment operation parameters, and the management level relies on regular summary reports, resulting in insufficient matching between real-time scheduling instructions and strategic goals. The following limitations still exist in the prior art:

[0003] 1. Static data application: Traditional cockpits focus on data visualization display, lacking a dynamic decision-making mechanism to convert real-time data streams into executable scheduling instructions. The generation of scheduling strategies depends on manual experience configuration and cannot adapt to the rapid changes in the complex working conditions of multiple power plants;

[0004] 2. Lack of role collaboration: The operation interfaces of business teams and the group decision-making system are independent of each other. There is a decision-making time lag between abnormal handling at the equipment layer and resource allocation at the strategic layer, and the cross-level instruction transmission efficiency is low;

[0005] 3. Weak feedback loop: The parameters of existing scheduling models are fixed and cannot be dynamically corrected according to the deviation between business execution feedback and strategic goals, resulting in cumulative errors between scheduling strategies and real-time working conditions.

[0006] Therefore, there is an urgent need for a method to solve at least one of the above problems. Summary of the Invention

[0007] The present application provides a business scheduling method and related devices that combine business and group leadership cockpits, aiming to solve the problem that traditional scheduling systems usually adopt a single-dimensional data monitoring mode, the business side focuses on collecting equipment operation parameters, and the management level relies on regular summary reports, resulting in insufficient matching between real-time scheduling instructions and strategic goals.

[0008] In a first aspect, the present application provides a business scheduling method that combines business and group leadership cockpits. The method includes:

[0009] Obtain the equipment operation data and environmental monitoring data of multiple power plants to construct a three-dimensional dynamic data matrix based on preset data stratification rules; wherein, the three-dimensional dynamic data matrix includes equipment layer parameters, business layer parameters, and management layer parameters. The equipment layer parameters include unit operation status parameters, the business layer parameters include production load distribution parameters, and the management layer parameters include cross-power plant coordinated scheduling indicators;

[0010] Parse the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders; the dynamic user portrait of the business team includes the characteristic coefficient of equipment operation frequency, and the dynamic user portrait of the group leaders includes the sensitivity coefficient of strategic indicators;

[0011] Extract real-time change features from the three-dimensional dynamic data matrix, and generate dynamic scheduling policy information through a multi-objective optimization algorithm based on the equipment operation frequency characteristic coefficient, the strategic indicator sensitivity coefficient, and the real-time change features; the dynamic scheduling policy information includes equipment start-stop plans, load distribution ratios, and cross-power plant resource allocation plans;

[0012] Push the equipment operation instructions of the dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and push the strategic decision support graph of the visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit; the equipment operation instructions at least include the priority mark for abnormal condition handling, and the strategic decision support graph at least includes the heat map of scheduling benefit prediction.

[0013] In some embodiments, constructing the three-dimensional dynamic data matrix based on the preset data layering rules includes: performing standardized processing on the equipment operation data and the environmental monitoring data to obtain the basic data stream of the equipment layer; performing dynamic layering based on the preset clustering algorithm according to the basic data stream of the equipment layer and the corresponding equipment types; constructing a data cube of the business layer according to the business parameters corresponding to the business cockpit and the time series characteristics of the production plan data; performing coupling analysis on the management indicator data corresponding to the group leader cockpit and the preset group strategic goals, and generating dynamic management indicators through a sliding time window algorithm; splicing the basic data stream of the equipment layer, the data cube of the business layer, and the dynamic management indicators under the unified time stamp to form a three-dimensional dynamic data matrix with spatio-temporal correlation characteristics.

[0014] In some embodiments, parsing the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders includes: performing named entity recognition on the operation logs to extract equipment operation entities and operation timing characteristics; calculating the equipment operation frequency characteristic coefficient according to the equipment operation entities, operation timing characteristics, and operation interval time; performing semantic role annotation on the group leader decision-making records to construct a strategic indicator association graph, and calculating the strategic indicator sensitivity coefficient corresponding to the strategic indicator association graph through an attention mechanism; inputting the operation frequency characteristic coefficient and the strategic indicator sensitivity coefficient into the corresponding user portrait generation network respectively to generate dynamic user portraits of the business team and the group leaders.

[0015] In some embodiments, extracting real-time change features according to the three-dimensional dynamic data matrix includes: intercepting time-slice data of the three-dimensional dynamic data matrix through a sliding time window; extracting time-series change features of device-layer parameters and correlation features of service-layer parameters from the device-layer parameters and service-layer parameters of the three-dimensional dynamic data matrix; performing wavelet packet transform decomposition on the management-layer parameters of the three-dimensional dynamic data matrix to extract multi-scale management index fluctuation features; and fusing the time-series change features, service-layer parameter correlation features, and multi-scale management index fluctuation features to generate a real-time change feature vector containing the above features.

[0016] In some embodiments, generating dynamic scheduling policy information according to the device operation frequency feature coefficient, strategic index sensitivity coefficient, and real-time change features through a multi-objective optimization algorithm includes: constructing a multi-objective function including device loss cost, energy utilization efficiency, and strategic synergy degree; performing normalization processing on the device operation frequency feature coefficient as a constraint condition, and determining weight allocation for the strategic index sensitivity coefficient through the entropy weight method; introducing real-time change features into the Pareto front solution set for dynamic correction to generate dynamic scheduling policy information that meets multiple constraints.

[0017] In some embodiments, pushing device operation instructions of dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and pushing a strategic decision support map of a visual scheduling instruction set to the group leadership cockpit according to the business permissions corresponding to the group leadership cockpit includes: performing dynamic encryption processing on the device operation instructions, matching the encrypted device operation instructions with the operation permission level of the business cockpit, and pushing the abnormal condition handling priority mark corresponding to the device operation instructions that match successfully to the business cockpit; performing homomorphic encryption processing on the strategic decision support map, and generating the scheduling benefit prediction heat map through a visual rendering engine; matching the scheduling benefit prediction heat map with the operation permission level of the group leadership cockpit, and pushing the scheduling benefit prediction heat map that matches successfully to the group leadership cockpit.

[0018] In some embodiments, after pushing device operation instructions of dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and pushing a strategic decision support map of a visual scheduling instruction set to the group leadership cockpit according to the business permissions corresponding to the group leadership cockpit, it further includes: obtaining operation response data of the business cockpit and feedback correction instructions of the group leadership cockpit; updating the weight parameters of the dynamic user portrait according to the operation response data and feedback correction instructions of the group leadership cockpit through a preset adaptive learning model, and performing index reconstruction on the three-dimensional dynamic data matrix to complete the dynamic closed-loop optimization of the dynamic scheduling policy information.

[0019] In a second aspect, the present application provides a business scheduling device combining business and group leadership cockpits, including:

[0020] A data acquisition unit, configured to acquire equipment operation data and environmental monitoring data of multiple power plants, so as to construct a three-dimensional dynamic data matrix based on a preset data layering rule; wherein, the three-dimensional dynamic data matrix includes equipment layer parameters, business layer parameters and management layer parameters, the equipment layer parameters include unit operation status parameters, the business layer parameters include production load distribution parameters, and the management layer parameters include cross-power plant collaborative scheduling indicators;

[0021] A portrait generation unit, configured to parse the operation logs of the business team and the decision-making records of the group leadership based on natural language processing technology, and generate dynamic user portraits of the business team and the group leadership; wherein the dynamic user portrait of the business team includes an equipment operation frequency characteristic coefficient, and the dynamic user portrait of the group leadership includes a strategic indicator sensitivity coefficient;

[0022] A strategy generation unit, configured to extract real-time change features according to the three-dimensional dynamic data matrix, and generate dynamic scheduling strategy information through a multi-objective optimization algorithm according to the equipment operation frequency characteristic coefficient, the strategic indicator sensitivity coefficient and the real-time change features; the dynamic scheduling strategy information includes an equipment start-stop plan, a load distribution ratio and a cross-power plant resource allocation plan;

[0023] A scheduling completion unit, configured to push the equipment operation instructions of the dynamic scheduling strategy information to the business cockpit according to the business permissions corresponding to the business cockpit, and push the strategic decision support graph of the visual scheduling instruction set to the group leadership cockpit according to the business permissions corresponding to the group leadership cockpit; the equipment operation instructions at least include an abnormal condition handling priority mark, and the strategic decision support graph at least includes a scheduling benefit prediction heat map.

[0024] In a third aspect, the present application provides a computer device, including a memory and a processor; the memory is used to store a computer program; the processor is configured to execute the computer program and implement the method provided in any embodiment of the present application when executing the computer program.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and when the computer-readable instructions are executed by a processor, one or more processors are caused to execute the method provided in any embodiment of the present application.

[0026] The present application discloses a business scheduling method and related devices combining business and group leadership cockpits. The business scheduling method provides a comprehensive scheduling solution by integrating multi-source data, using natural language processing and multi-objective optimization algorithms, aiming to improve the collaborative efficiency of the business and management levels.

[0027] By obtaining equipment operation data (such as unit status, load) and environmental monitoring data (such as emissions, temperature) from multiple power plants, the data is divided into the equipment layer, business layer, and management layer to construct a three-dimensional matrix covering parameters such as equipment operation, production load, and cross-power plant collaborative scheduling.

[0028] Parse the operation logs of the business team and the decision-making records of the management layer, extract characteristic coefficients (such as operation frequency, sensitivity), and generate dynamic portraits of the business team and the management layer to reflect their operation habits and concerns.

[0029] Extract real-time change characteristics from the three-dimensional matrix for optimization calculation. Combine the characteristics of the user portrait and use a multi-objective optimization algorithm to generate a dynamic scheduling strategy covering equipment start-stop, load distribution, and resource allocation. Push information according to role permissions. The business cockpit receives equipment instructions, and the management cockpit receives visualization graphs. Provide a heat map of abnormal condition priorities and benefit predictions to assist decision-making.

[0030] The method provided improves the timeliness and accuracy of scheduling decisions through real-time data integration and dynamic adjustment. By integrating equipment, business, and management data, it provides a comprehensive perspective and avoids the limitations of single-dimensional analysis. The dynamic user portrait helps the scheduling strategy adapt to the needs of different teams and management layers, providing personalized support. Provide intuitive visualization tools such as heat maps to help the management layer quickly understand benefit predictions and improve decision-making efficiency. Promote information sharing and collaboration between the business team and the management layer, optimize resource allocation, and improve overall operational efficiency.

[0031] In summary, through integrating multi-source data, using advanced algorithms and visualization technologies, the method provides a comprehensive business scheduling solution, significantly improving the real-time performance, accuracy, and collaborative efficiency of scheduling, and providing strong support for the business and management layers.

[0032] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] To more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0034] Figure 1 It is a schematic flowchart of the steps of a business scheduling method combining a business cockpit and a group leadership cockpit provided by an embodiment of this application;

[0035] Figure 2 It is a schematic diagram of the interface of the group leadership cockpit provided by an embodiment of the present application;

[0036] Figure 3 It is a schematic diagram of the interface of the business cockpit provided by an embodiment of the present application;

[0037] Figure 4 It is a schematic structural diagram of the business scheduling device combining the business and the group leadership cockpit provided by an embodiment of the present application;

[0038] Figure 5 It is a schematic block diagram of the structure of the computer device provided by an embodiment of the present application.

[0039] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Detailed Embodiments

[0040] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0041] The flowcharts shown in the accompanying drawings are only illustrative examples, and do not necessarily include all contents and operations / steps, nor do they necessarily need to be executed in the described order. For example, some operations / steps can also be decomposed, combined, or partially merged, so the actual execution order may change according to the actual situation.

[0042] It should be understood that in order to facilitate the clear description of the technical solutions in the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

[0043] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0044] It should also be understood that the term " / and" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0045] The following will, with reference to the accompanying drawings, elaborate on some embodiments of the present application. Without conflict, the following embodiments and the features in the embodiments may be combined with each other.

[0046] In the energy group operation and management, the collaborative scheduling of multiple power plants has long faced the dual problems of data fragmentation and decision-making level disconnection. Traditional scheduling systems usually adopt a single-dimensional data monitoring mode. The business side focuses on collecting equipment operation parameters, and the management level relies on regular summary reports, resulting in insufficient matching degree between real-time scheduling instructions and strategic goals. The following limitations still exist in the existing technologies:

[0047] 1. Static data application: Traditional cockpits focus on data visualization display, lacking a dynamic decision-making mechanism to convert real-time data streams into executable scheduling instructions. The generation of scheduling strategies depends on manual experience configuration and cannot adapt to the rapid changes in the complex working conditions of multiple power plants;

[0048] 2. Lack of role collaboration: The operation interfaces of the business team and the group decision-making system are independent of each other. There is a decision-making time lag between the abnormal handling at the equipment layer and the resource allocation at the strategic layer, and the cross-level instruction transmission efficiency is low;

[0049] 3. Weak feedback closed-loop: The parameters of the existing scheduling models are fixed and cannot be dynamically corrected according to the deviation between the business execution feedback and the strategic goal, resulting in cumulative errors between the scheduling strategy and the real-time working conditions.

[0050] Therefore, there is an urgent need for a method to solve at least one of the above problems.

[0051] To solve the above problems, please refer to Figure 1 , Figure 1 is a schematic flowchart of a business scheduling method combining a business cockpit and a group leadership cockpit provided by an embodiment of the present application. The execution device of the method is the device including a computer device.

[0052] To solve the above problems, please refer to Figure 1 . Specifically, as Figure 1 shown, the provided method includes steps S101 to S104. Among them, the computer device can be a handheld terminal, a laptop computer, a wearable device, or a robot, etc., and is used to implement steps S101 to S104 and their corresponding embodiments.

[0053] Please refer to Figures 2 - 3 , where the business cockpit is a visualization operation platform for the front-line business teams of power plants, integrating real-time equipment operation data, abnormal handling instructions, and operation priority information, supporting rapid response to equipment abnormalities, execution of scheduling instructions, and feedback of execution results.

[0054] The core functions are to receive specific operation instructions in the dynamic scheduling strategy (such as equipment start / stop, load adjustment), display the priority marks of abnormal working conditions (such as a red alarm that requires immediate handling), and provide the upload of operation records and feedback on the execution progress.

[0055] The Group Leadership Cockpit is a strategic decision-making support system for senior managers of energy groups. It displays the benefits of cross-power-plant resource allocation, the achievement of strategic goals, and risk warnings through visual maps, and assists in formulating long-term resource plans and strategic adjustments.

[0056] The core functions are to display the heat maps of scheduling benefit predictions (such as regional cost fluctuations, carbon emission trends), provide early warnings of strategic indicator deviations (such as continuous cost overrun in a certain power plant), and support simulating the impact of different scheduling schemes on strategic goals (such as the feasibility analysis of "increasing the proportion of wind power").

[0057] The steps are described in detail as follows:

[0058] Step S101. Obtain the equipment operation data and environmental monitoring data of multiple power plants to construct a three-dimensional dynamic data matrix based on preset data layering rules; among them, the three-dimensional dynamic data matrix includes equipment layer parameters, business layer parameters, and management layer parameters. The equipment layer parameters include unit operation status parameters, the business layer parameters include production load distribution parameters, and the management layer parameters include cross-power-plant collaborative scheduling indicators.

[0059] Specifically, this step integrates the equipment operation data of multiple power plants (such as unit temperature, power output) and environmental monitoring data (such as weather, grid demand), and divides the data into three dimensions through preset rules:

[0060] Equipment layer parameters: The unit status collected in real time (such as fault alarms, energy consumption efficiency).

[0061] Business layer parameters: Production task allocation (such as load distribution among power plants, power output priority).

[0062] Management layer parameters: Cross-power-plant collaborative goals (such as cost control, carbon emission indicators).

[0063] Collect equipment data in real time through Internet of Things sensors, clean it and store it in a unified platform. Define data layering rules. For example, classify sensor data as the equipment layer, production plan data as the business layer, and strategic KPIs as the management layer. Dynamically update the matrix, such as refreshing the equipment status every 5 minutes and adjusting the load distribution every hour.

[0064] Break the traditional single data monitoring mode and realize the real-time association of equipment, business, and management data. Provide a real-time and comprehensive data foundation for subsequent strategy generation and reduce information fragmentation.

[0065] Step S102. Parse the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders; the dynamic user portrait of the business team includes the equipment operation frequency characteristic coefficient, and the dynamic user portrait of the group leaders includes the strategic indicator sensitivity coefficient.

[0066] Specifically, use natural language processing (NLP) to parse two types of text data: Operation logs of the business team: Extract the equipment operation frequency and common operation types (such as "Unit A is restarted 3 times a day"). Decision-making records of the group leaders: Analyze strategic concerns (such as "Prioritize carbon emission reduction" or "Improve cross-regional power supply efficiency").

[0067] Generate two types of portraits: Portrait of the business team: Quantify operation habits (such as a high "equipment operation frequency characteristic coefficient" indicates frequent intervention in equipment). Portrait of the group leaders: Quantify strategic preferences (such as a high "strategic indicator sensitivity coefficient" indicates a low tolerance for cost fluctuations). Extract keywords (such as "shutdown", "load adjustment") from the text in the logs and count the operation frequencies. Analyze the high-frequency words (such as "emission reduction", "profit") in the decision-making records and calculate the sensitivity coefficient. Dynamic update of the portrait: For example, if the leader frequently mentions "disaster recovery power supply" recently, then increase the relevant sensitivity weight. Quantify the behavior patterns and decision-making preferences of different roles to provide personalized input for policy generation. By continuously learning user behavior, the portrait automatically adjusts with operations and decisions, improving the collaboration efficiency.

[0068] Step S103. Extract real-time change features from the three-dimensional dynamic data matrix, and generate dynamic scheduling policy information through a multi-objective optimization algorithm based on the equipment operation frequency characteristic coefficient, the strategic indicator sensitivity coefficient, and the real-time change features; the dynamic scheduling policy information includes the equipment start-stop plan, the load distribution ratio, and the cross-power plant resource allocation plan.

[0069] Specifically, identify key changes from the three-dimensional matrix, such as a sudden drop in the unit efficiency of a certain power plant or a sharp increase in regional electricity demand. Combine the operation frequency in the user portrait (such as whether the business team can respond quickly) and the strategic sensitivity (such as whether the leader attaches importance to costs), and use an algorithm (such as a genetic algorithm) to balance multiple objectives: equipment safety (such as avoiding overload), business efficiency (such as meeting the load standard), and strategic indicators (such as minimizing the total cost).

[0070] The output policies include: Equipment start-stop plan: Shut down inefficient units and start standby units. Load distribution ratio: Assign the power supply task in the high-demand area to the power plant with the optimal efficiency. Cross-power plant resource allocation: Call the standby fuel or maintenance team of other power plants.

[0071] When a sudden failure occurs in a power plant, the system calculates the load gap based on real-time data. Considering the high sensitivity of the leadership to power supply stability, it preferentially allocates resources from neighboring power plants. If the operation frequency coefficient of the business team is low (indicating slow response), more detailed disposal steps will be automatically generated (such as "close the valve of unit B within 15 minutes").

[0072] The strategy is adjusted in real time according to the working conditions and user profiles, reducing the dependence on manual experience. It takes into account safety, efficiency and strategic goals to avoid neglecting one thing while attending to another.

[0073] Step S104. Push the equipment operation instructions of the dynamic scheduling strategy information corresponding to the business permissions of the business cockpit to the business cockpit, and push the strategic decision-making support graph of the visual scheduling instruction set corresponding to the business permissions of the group leadership cockpit to the group leadership cockpit; the equipment operation instructions shall at least include the priority mark for abnormal condition handling, and the strategic decision-making support graph shall at least include the heat map for predicting the scheduling benefits.

[0074] Specifically, the strategy is disassembled into two types of instructions according to the permissions:

[0075] Business cockpit: Receive the operation instructions with priority marks (such as "immediately handle the overheating of unit C") to support rapid execution. Group leadership cockpit: Receive the visual graph (such as a heat map showing the predicted scheduling benefits in the next 24 hours) to assist in strategic decision-making.

[0076] Business side: Push the equipment operation list, with abnormal marks in red (such as "give priority to repairing the faulty unit"). Leadership side: Display the heat map, where the red area indicates that the future cost of a certain power plant may exceed the standard, and the green area indicates compliance. Furthermore, in terms of permission control, the business team cannot view the cost data at the strategic level, and the leadership does not directly operate the equipment.

[0077] Avoid information overload, and different roles only obtain the necessary information. The leadership quickly identifies risks through the heat map, and the business team executes efficiently according to the priorities. Real-time push ensures cross-level collaboration and shortens the cycle of "discovering problems - formulating strategies - executing".

[0078] In some embodiments, constructing a three-dimensional dynamic data matrix based on a preset data layering rule includes: performing normalization processing on the device operation data and environmental monitoring data to obtain a basic data stream at the device layer; performing dynamic layering based on a preset clustering algorithm according to the basic data stream at the device layer and the corresponding device types; constructing a data cube at the business layer according to the business parameters corresponding to the business cockpit and the time series characteristics of the production plan data; performing coupling analysis on the management index data corresponding to the group leadership cockpit and the preset group strategic objectives, and generating dynamic management indicators through a sliding time window algorithm; performing matrix tensor splicing on the basic data stream at the device layer, the data cube at the business layer, and the dynamic management indicators under a unified time stamp to form a three-dimensional dynamic data matrix with spatio-temporal correlation characteristics.

[0079] By unifying the formats of the device operation data (such as temperature, power) and environmental data (such as weather, grid load) of different power plants, the unit differences are eliminated. Classify the data according to device types (such as coal-fired units, wind turbines), for example, group the operating states of the same type of devices into one group through an algorithm. According to the time pattern of the production plan (such as load distribution during peak hours), construct business data blocks that change over time (such as hourly load targets). Combine the group strategic indicators (such as cost control) with the management data (such as the operating cost of the power plant), and analyze the changing trend of the indicators through dynamic time segmentation (such as the most recent 7 days). Align the device, business, and management layer data at a unified time to form a three-dimensional matrix including space (power plant location), time (changing trend), and level (device / business / management).

[0080] For example, if the power generation of a wind farm fluctuates due to wind speed changes, the system automatically classifies its data with other wind power devices in the same region and associates it with the load distribution plan at the business layer and the regional power supply stability indicator at the management layer.

[0081] Eliminate the data format differences among multiple power plants and achieve cross-system integration. Real-time display the linkage relationship among device operation, business plan, and strategic objectives. For example, when it is found that the efficiency of a power plant decreases, quickly locate its impact on the overall cost. Through the spatio-temporal correlation matrix, provide a global perspective for subsequent scheduling and avoid the blind spots of traditional single-dimensional monitoring.

[0082] In some embodiments, parsing the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders, including: performing named entity recognition on the operation logs to extract device operation entities and operation timing features; calculating the device operation frequency feature coefficient according to the device operation entities, operation timing features, and operation interval time; performing semantic role annotation on the group leader decision-making records to construct a strategic indicator association graph, and calculating the strategic indicator sensitivity coefficient corresponding to the strategic indicator association graph through an attention mechanism; respectively inputting the operation frequency feature coefficient and the strategic indicator sensitivity coefficient into the corresponding user portrait generation network to generate dynamic user portraits of the business team and the group leaders.

[0083] Specifically, for operation log parsing: identify key operations from the logs (such as "restart of unit A"), and count the operation time, frequency, and interval (such as 3 operations per hour). Extract the core objectives in the decision-making (such as "reduce carbon emissions"), and construct an objective association graph (such as the relationship of "carbon emissions - cost - power supply volume").

[0084] Calculate the device operation frequency coefficient (such as a high coefficient indicates frequent intervention in the device). At the same time, quantify the strategic sensitivity through weight analysis (such as higher sensitivity to "cost" than to "power supply volume"). Adjust the feature coefficients in real time according to the latest logs and decision-making records.

[0085] For example, if the business team frequently operates a certain unit to deal with faults, the system automatically increases its operation frequency coefficient, and gives priority to providing detailed operation steps when generating scheduling instructions later. The group leaders have emphasized "disaster backup power supply" many times recently, and the system increases the sensitivity of this indicator, and gives priority to ensuring the allocation of backup power when generating strategies.

[0086] Quantify the operation habits of the business team and the strategic preferences of the leadership, so that the scheduling strategy is closer to the actual needs. Through the dynamic portrait, the system can automatically predict the concerns of different roles, shortening the chain of "problem discovery - strategy formulation - instruction issuance". Automatically adjust the strategy according to the changes in user behavior. For example, provide more simplified instructions for teams with weak operation capabilities.

[0087] In some embodiments, extracting the real-time change features according to the three-dimensional dynamic data matrix includes: intercepting the time slice data of the three-dimensional dynamic data matrix through a sliding time window; extracting the device layer parameter time series change features and the business layer parameter association features from the device layer parameters and business layer parameters of the three-dimensional dynamic data matrix; performing wavelet packet transform decomposition on the management layer parameters of the three-dimensional dynamic data matrix to extract multi-scale management index fluctuation features; fusing the time series change features, business layer parameter association features, and multi-scale management index fluctuation features to generate a real-time change feature vector.

[0088] By intercepting three-dimensional data at fixed time intervals (such as every 15 minutes), short-term changes (such as a sudden drop in the power of a certain unit) are analyzed.

[0089] The device layer captures the trend of device parameters (such as a continuous increase in temperature). The business layer analyzes the correlation between load distribution and device status (such as a decrease in efficiency due to overload in a certain power plant). The management layer decomposes strategic indicators (such as cost) into fluctuations at different time scales (such as hourly cost fluctuations, daily trends), and identifies abnormal signals (such as cost exceeding the standard for three consecutive days). Integrate the real-time changes of devices, business, and management into a comprehensive feature vector (such as "decrease in the efficiency of Unit A + regional load overlimit + abnormal cost fluctuations").

[0090] For example, if the efficiency of a coal-fired unit decreases due to a fault, the system discovers through time slicing that its power continuously falls below the threshold, and at the same time correlates with the imbalance of load distribution in the business layer and cost overrun in the management layer, triggering the instruction of "urgently deploying standby units".

[0091] Track the whole process from device anomalies to strategic deviations, avoiding the limitation of traditional methods that only focus on single problems. Through multi-scale feature analysis, potential risks (such as abnormal cost fluctuation trends) are warned in advance, reducing cumulative errors. The fused feature vector clearly points to the root cause of the problem. For example, considering both device failures and strategic goal deviations at the same time, a more reasonable scheduling plan is generated.

[0092] In some embodiments, generating dynamic scheduling policy information according to the device operation frequency characteristic coefficient, strategic indicator sensitivity coefficient, and real-time change characteristics through a multi-objective optimization algorithm includes: constructing a multi-objective function including device loss cost, energy utilization efficiency, and strategic synergy degree; normalizing the device operation frequency characteristic coefficient as a constraint condition, and determining the weight distribution of the strategic indicator sensitivity coefficient through the entropy weight method; introducing real-time change characteristics into the Pareto front solution set for dynamic correction to generate dynamic scheduling policy information that meets multiple constraints.

[0093] Simultaneously optimize three core objectives - reducing device losses (such as extending the life of the unit), improving energy utilization efficiency (such as reducing the unit power generation cost), and meeting group strategic synergy (such as cross-power plant resource allocation meeting emission reduction targets). Convert the operation frequency of the business team (such as the upper limit of the number of operations per day) into a limiting condition to avoid over-reliance on manual intervention. Dynamically allocate target weights according to the group leader's attention to strategic indicators (such as attaching more importance to cost control or power supply stability). Combine real-time data (such as a sudden failure in a certain power plant), and dynamically correct the policy in the preset optimal solution set (such as temporarily increasing the load of standby units).

[0094] For example, when the electricity demand in a certain region surges, the system preferentially selects power plants with high energy efficiency to increase the load, while avoiding overusing aging equipment and ensuring compliance with the group's carbon emission targets.

[0095] Avoid one-sidedness caused by optimizing a single goal (such as only pursuing efficiency while ignoring equipment losses). Adjust the strategy in real-time driven by data. For example, quickly switch to an alternative plan in case of sudden failures. Ensure that the scheduling strategy is always consistent with the long-term goals of the group (such as low-carbon transformation).

[0096] In some embodiments, the device operation instructions of the dynamic scheduling strategy information are pushed to the business cockpit according to the business permissions corresponding to the business cockpit, and the strategic decision support map of the visual scheduling instruction set is pushed to the group leadership cockpit according to the business permissions corresponding to the group leadership cockpit, including: performing dynamic encryption processing on the device operation instructions, matching the encrypted device operation instructions with the operation permission level of the business cockpit, and pushing the exception condition handling priority mark corresponding to the device operation instructions with successful matching to the business cockpit; performing homomorphic encryption processing on the strategic decision support map, and generating the scheduling benefit prediction heat map through a visual rendering engine; matching the scheduling benefit prediction heat map with the operation permission level of the group leadership cockpit, and pushing the scheduling benefit prediction heat map with successful matching to the group leadership cockpit.

[0097] Specifically, the business-side instruction encryption dynamically encrypts the device operation instructions (such as "shut down the faulty unit"), and only allows the business team with the corresponding permissions to decrypt and view them to prevent misoperation or information leakage. The leadership-side map encryption uses a more advanced encryption technology for the strategic decision map (such as the cost prediction heat map) to ensure data security when viewed by the leadership and does not affect the visualization effect. Permission matching means that the business team only receives the exception handling instructions of the power plants under its jurisdiction (such as tasks marked as "urgent").

[0098] The group leadership views the global heat map but cannot directly operate the equipment.

[0099] The business team of a certain power plant receives an encrypted instruction: "Overhaul Unit A within 1 hour", and other power plant teams cannot view this instruction. The group leadership sees the warning "The cost in Area C may exceed the standard tomorrow" in the heat map but has no right to modify the specific equipment parameters.

[0100] Prevent unauthorized operations or data leakage through hierarchical encryption. Different roles only obtain the necessary information to avoid information overload. Clearly define the boundaries between the execution of the business team and the decision-making of the leadership level to reduce cross-level interference.

[0101] In some embodiments, after pushing the device operation instructions of the dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and pushing the strategic decision-making support graph of the visual scheduling instruction set to the group leadership cockpit according to the business permissions corresponding to the group leadership cockpit, it further includes: obtaining the operation response data of the business cockpit and the feedback correction instructions of the group leadership cockpit; updating the weight parameters of the dynamic user profile according to the operation response data and the feedback correction instructions of the group leadership cockpit through a preset adaptive learning model, and reconstructing the indicators of the three-dimensional dynamic data matrix to complete the dynamic closed-loop optimization of the dynamic scheduling policy information.

[0102] By obtaining in real time the execution results of the scheduling instructions by the business team (such as whether the fault is repaired) and the feedback from the leadership on the strategic effects (such as whether the cost meets the standard). Automatically adjust the user profile weights (such as reducing the operation frequency coefficient after the business team's response speed increases) and the three-dimensional data matrix indicators (such as increasing the monitoring of new strategic goals) according to the feedback data. The updated data and profile are re-input into the optimization model to generate more accurate scheduling policies. If the business team delays responding to a certain type of fault multiple times, the system automatically increases the disposal priority coefficient of this type of fault, and preferentially allocates spare resources in subsequent policies. If the group leadership feedbacks that the weight of "disaster recovery power supply" is insufficient, the system adds a disaster recovery resource monitoring indicator to the matrix to optimize the subsequent scheduling plan.

[0103] The system continuously improves through feedback, reducing manual intervention. Dynamically updates the policy as the capabilities of the business team improve or the strategic goals are adjusted. Real-time corrects the deviation between the data and the policy to avoid systematic errors caused by long-term execution.

[0104] In some embodiments, by embedding an AI prediction model in the three-dimensional dynamic data matrix, analyze the long-term trends of device layer parameters (such as vibration frequency, temperature), and predict potential faults (such as "risk of unit bearing wear"). Combine the operation frequency characteristics of the business team to automatically generate preventive maintenance instructions (such as "reduce the unit load by 10% in the next 3 days"). Synchronize the prediction results to the group cockpit to show the impact of the fault prediction on the strategic goals (such as "the maintenance cost increases by 5%").

[0105] Shift from "post-fault handling" to "pre-fault prevention" to reduce downtime losses. The leadership can anticipate fluctuations in maintenance costs in advance and adjust the resource allocation plan.

[0106] In some embodiments, the operation instructions of the business cockpit (such as "shut down unit A") are stored on the chain, recording the operation time, execution personnel and equipment status changes. The strategic decision instructions of the group cockpit (such as "reduce the power supply in a certain area") verify the authority through smart contracts to ensure that only authorized personnel can trigger key instructions. Provide a full-link audit function to support rapid tracing of the reasons for deviations in instruction execution (such as "a load distribution error was caused by an overstepping of operating authority").

[0107] Ensure that operation and decision-making data cannot be tampered with to meet compliance audit requirements. Clarify cross-level operational responsibilities to reduce buck-passing and execution deviations.

[0108] In some embodiments, the business cockpit uses AR glasses to overlay real-time data from the equipment (such as pressure values and current fluctuations) to guide on-site personnel to perform maintenance according to the steps (such as "rotate the valve to the red position"). The group cockpit simulates the operating status of the group's power plants under different scheduling schemes (such as "the impact of shutting down a power plant on the regional power grid") by building a 3D digital twin sandbox, and supports gesture interaction to adjust strategic parameters.

[0109] Reduce the operational error rate of front-line personnel and shorten the time for troubleshooting. The leadership can intuitively perceive the overall impact of strategic adjustments and improve the accuracy of decision-making.

[0110] In some embodiments, a dynamic pricing model is introduced into the cross-power plant resource allocation plan to adjust the internal resource call price in real time according to the supply and demand relationship (such as regional peak electricity consumption) (such as "the cost of using coal-fired units during the peak period will increase by 20%"). The business cockpit displays the current resource prices and guides the team to choose the most cost-effective allocation plan (such as "prioritize wind power to replace high-priced coal"). The group cockpit shows the impact of price fluctuations on strategic goals (such as "dynamic pricing reduces total quarterly costs by 8%"). Use price levers to guide efficient resource allocation and reduce waste. The real-time pricing model helps the group balance short-term expenditures with long-term strategic investments.

[0111] See also Figure 4 As shown, Figure 4 : is a structural diagram of a business scheduling device 200 for combining business and group leader cockpit provided in an embodiment of the present application. The business scheduling device 200 for combining business and group leader cockpit is used to execute the steps of the business scheduling method for combining business and group leader cockpit shown in the above embodiments. The business scheduling device 200 for combining business and group leader cockpit can be a single server or a server cluster, or the business scheduling device 200 for combining business and group leader cockpit can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device or a robot, etc.

[0112] like Figure 4As shown in the figure, the business scheduling device 200 combined with the business and group leadership cockpits includes:

[0113] A data acquisition unit 201, configured to acquire equipment operation data and environmental monitoring data of multiple power plants, and construct a three-dimensional dynamic data matrix based on a preset data layering rule; wherein, the three-dimensional dynamic data matrix includes equipment layer parameters, business layer parameters, and management layer parameters, the equipment layer parameters include unit operation status parameters, the business layer parameters include production load distribution parameters, and the management layer parameters include cross-power plant collaborative scheduling indicators;

[0114] A portrait generation unit 202, configured to parse the operation logs of the business team and the decision-making records of the group leadership based on natural language processing technology, and generate dynamic user portraits of the business team and the group leadership; wherein the dynamic user portrait of the business team includes an equipment operation frequency characteristic coefficient, and the dynamic user portrait of the group leadership includes a strategic indicator sensitivity coefficient;

[0115] A strategy generation unit 203, configured to extract real-time change characteristics according to the three-dimensional dynamic data matrix, and generate dynamic scheduling strategy information through a multi-objective optimization algorithm according to the equipment operation frequency characteristic coefficient, the strategic indicator sensitivity coefficient, and the real-time change characteristics; the dynamic scheduling strategy information includes an equipment start-stop plan, a load distribution ratio, and a cross-power plant resource allocation plan;

[0116] A scheduling completion unit 204, configured to push equipment operation instructions of the dynamic scheduling strategy information to the business cockpit according to the business permissions corresponding to the business cockpit, and push a strategic decision-making support map of the visual scheduling instruction set to the group leadership cockpit according to the business permissions corresponding to the group leadership cockpit; the equipment operation instructions at least include an abnormal condition handling priority mark, and the strategic decision-making support map at least includes a scheduling benefit prediction heat map.

[0117] It should be noted that those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the business scheduling device and each unit combined with the business and group leadership cockpits described above can refer to the corresponding processes in the business scheduling embodiments combined with the business and group leadership cockpits described in the above embodiments, and will not be elaborated here.

[0118] The above-mentioned business scheduling combined with the business and group leadership cockpits can be implemented in the form of a computer program, and this computer program can run on a device as shown in Figure 4 the figure.

[0119] Please refer to Figure 5 , Figure 5It is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application. The computer device includes a processor, a memory, and a network interface connected through a device bus. Among them, the memory may include a storage medium and an internal memory.

[0120] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can be made to execute any business scheduling combined with the business and the group leadership cockpit.

[0121] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0122] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can be made to execute any business scheduling combined with the business and the group leadership cockpit.

[0123] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 5 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0124] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0125] Among them, in one embodiment, the processor is used to run the computer program stored in the memory to obtain the device operation data and environmental monitoring data of multiple power plants, so as to construct a three-dimensional dynamic data matrix based on a preset data stratification rule; wherein, the three-dimensional dynamic data matrix includes device layer parameters, business layer parameters, and management layer parameters, the device layer parameters include unit operation status parameters, the business layer parameters include production load distribution parameters, and the management layer parameters include cross-power plant collaborative scheduling indicators;

[0126] Parse the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders; the dynamic user portrait of the business team includes the device operation frequency characteristic coefficient, and the dynamic user portrait of the group leaders includes the strategic index sensitivity coefficient;

[0127] Extract the real-time change characteristics from the three-dimensional dynamic data matrix, and generate dynamic scheduling policy information through a multi-objective optimization algorithm based on the device operation frequency characteristic coefficient, the strategic index sensitivity coefficient, and the real-time change characteristics; the dynamic scheduling policy information includes the device start-stop plan, the load distribution ratio, and the cross-power plant resource allocation plan;

[0128] Push the device operation instructions of the dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and push the strategic decision support graph of the visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit; the device operation instructions at least include the priority mark for abnormal condition handling, and the strategic decision support graph at least includes the scheduling benefit prediction heat map.

[0129] In some embodiments, the construction of the three-dimensional dynamic data matrix based on the preset data layering rules includes: performing standardization processing on the device operation data and the environmental monitoring data to obtain the basic data stream of the device layer; performing dynamic layering based on the preset clustering algorithm according to the basic data stream of the device layer and the corresponding device type; constructing a data cube of the business layer according to the business parameters corresponding to the business cockpit and the time series characteristics of the production plan data; performing coupling analysis on the management index data corresponding to the group leader cockpit and the preset group strategic goals, and generating management dynamic indexes through a sliding time window algorithm; splicing the basic data stream of the device layer, the data cube of the business layer, and the management dynamic indexes under the same time stamp to form a three-dimensional dynamic data matrix with spatio-temporal correlation characteristics.

[0130] In some embodiments, the parsing of the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders includes: performing named entity recognition on the operation logs to extract device operation entities and operation timing characteristics; calculating the device operation frequency characteristic coefficient according to the device operation entities, operation timing characteristics, and operation interval time; performing semantic role annotation on the group leader decision-making records to construct a strategic index association graph, and calculating the strategic index sensitivity coefficient corresponding to the strategic index association graph through an attention mechanism; respectively inputting the operation frequency characteristic coefficient and the strategic index sensitivity coefficient into the corresponding user portrait generation network to generate dynamic user portraits of the business team and the group leaders.

[0131] In some embodiments, extracting real-time change features according to the three-dimensional dynamic data matrix includes: intercepting time-slice data of the three-dimensional dynamic data matrix through a sliding time window; extracting time-series change features of device-layer parameters and correlation features of service-layer parameters from the device-layer parameters and service-layer parameters of the three-dimensional dynamic data matrix; performing wavelet packet transform decomposition on the management-layer parameters of the three-dimensional dynamic data matrix to extract multi-scale management index fluctuation features; and fusing the time-series change features, service-layer parameter correlation features, and multi-scale management index fluctuation features to generate a real-time change feature vector containing the above.

[0132] In some embodiments, generating dynamic scheduling policy information according to the device operation frequency feature coefficient, strategic index sensitivity coefficient, and real-time change features through a multi-objective optimization algorithm includes: constructing a multi-objective function including device loss cost, energy utilization efficiency, and strategic synergy degree; performing normalization processing on the device operation frequency feature coefficient as a constraint condition, and determining the weight distribution of the strategic index sensitivity coefficient through the entropy weight method; introducing real-time change features into the Pareto front solution set for dynamic correction to generate dynamic scheduling policy information that meets multiple constraints.

[0133] In some embodiments, pushing device operation instructions of dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and pushing a strategic decision support map of a visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit includes: performing dynamic encryption processing on the device operation instructions, matching the encrypted device operation instructions with the operation permission level of the business cockpit, and pushing the abnormal condition handling priority mark corresponding to the successfully matched device operation instructions to the business cockpit; performing homomorphic encryption processing on the strategic decision support map, and generating the scheduling benefit prediction heat map through a visual rendering engine; matching the scheduling benefit prediction heat map with the operation permission level of the group leader cockpit, and pushing the successfully matched scheduling benefit prediction heat map to the group leader cockpit.

[0134] In some embodiments, after pushing device operation instructions of dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and pushing a strategic decision support map of a visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit, it further includes: obtaining operation response data of the business cockpit and feedback correction instructions of the group leader cockpit; updating the weight parameters of the dynamic user profile according to the operation response data and feedback correction instructions of the group leader cockpit through a preset adaptive learning model, and performing index reconstruction on the three-dimensional dynamic data matrix to complete the dynamic closed-loop optimization of the dynamic scheduling policy information.

[0135] It should be noted that those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described processor can refer to the corresponding process in the business scheduling embodiments of the combination of business and the group leader cockpit described in the above embodiments, and will not be elaborated herein.

[0136] An embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. The processor executes the program instructions to implement the steps of the business scheduling method of the combination of business and the group leader cockpit provided in the above embodiments of the present application.

[0137] Among them, the computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device.

[0138] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or substitutions within the technical scope disclosed by the present application, and these modifications or substitutions should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A business scheduling method combining business and the leadership cockpit of the group, characterized in that, Including: Obtain the equipment operation data and environmental monitoring data of multiple power plants to construct a three-dimensional dynamic data matrix based on a preset data stratification rule; wherein, the three-dimensional dynamic data matrix includes equipment layer parameters, business layer parameters, and management layer parameters, the equipment layer parameters include unit operation status parameters, the business layer parameters include production load distribution parameters, and the management layer parameters include cross-power plant collaborative scheduling indicators; Parse the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders; wherein the dynamic user portrait of the business team includes the equipment operation frequency characteristic coefficient, and the dynamic user portrait of the group leaders includes the strategic indicator sensitivity coefficient; Extract real-time change characteristics according to the three-dimensional dynamic data matrix, and generate dynamic scheduling strategy information through a multi-objective optimization algorithm based on the equipment operation frequency characteristic coefficient, strategic indicator sensitivity coefficient, and real-time change characteristics; the dynamic scheduling strategy information includes equipment start-stop plans, load distribution ratios, and cross-power plant resource allocation plans; Push the equipment operation instructions of the dynamic scheduling strategy information to the business cockpit according to the business permissions corresponding to the business cockpit, and push the strategic decision support graph of the visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit; the equipment operation instructions at least include abnormal condition handling priority marks, and the strategic decision support graph at least includes a scheduling benefit prediction heat map.

2. The method according to claim 1, wherein The construction of the three-dimensional dynamic data matrix based on the preset data stratification rule includes: Perform standardization processing on the equipment operation data and environmental monitoring data to obtain the basic data stream of the equipment layer; Perform dynamic stratification based on the preset clustering algorithm according to the basic data stream of the equipment layer and the corresponding equipment types; Construct a business layer data cube according to the business parameters corresponding to the business cockpit and the time series characteristics of the production plan data; Perform coupling analysis on the management layer index data corresponding to the group leader cockpit and the preset group strategic goals, and generate management layer dynamic indicators through a sliding time window algorithm; Perform matrix tensor splicing on the basic data stream of the equipment layer, the business layer data cube, and the management layer dynamic indicators under the same time stamp to form a three-dimensional dynamic data matrix with spatio-temporal correlation characteristics.

3. The method according to claim 1, wherein The parsing of the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology to generate dynamic user portraits of the business team and the group leaders includes: Perform named entity recognition on the operation logs to extract equipment operation entities and operation timing characteristics; Calculate the equipment operation frequency characteristic coefficient according to the equipment operation entities, operation timing characteristics, and operation interval time; Perform semantic role annotation on the group leader decision-making records, construct a strategic indicator association graph, and calculate the strategic indicator sensitivity coefficient corresponding to the strategic indicator association graph through an attention mechanism; Input the operation frequency characteristic coefficient and the strategic indicator sensitivity coefficient into the corresponding user portrait generation network respectively to generate dynamic user portraits of the business team and the group leaders.

4. The method according to claim 1, wherein The extraction of real-time change characteristics according to the three-dimensional dynamic data matrix includes: Intercept the time slice data of the three-dimensional dynamic data matrix by sliding the time window; Extract the time series change characteristics of the device layer parameters and the correlation characteristics of the business layer parameters from the device layer parameters and the business layer parameters of the three-dimensional dynamic data matrix; Perform wavelet packet transform decomposition on the management layer parameters of the three-dimensional dynamic data matrix to extract the multi-scale management index fluctuation characteristics; Fuse the time series change characteristics, the correlation characteristics of the business layer parameters, and the multi-scale management index fluctuation characteristics to generate the real-time change feature vector; 5. The method according to claim 1, wherein Generate dynamic scheduling policy information according to the device operation frequency characteristic coefficient, the strategic index sensitivity coefficient, and the real-time change characteristics through a multi-objective optimization algorithm, including: Construct a multi-objective function including device loss cost, energy utilization efficiency, and strategic synergy degree; Normalize the device operation frequency characteristic coefficient as a constraint condition, and determine the weight distribution of the strategic index sensitivity coefficient by the entropy weight method; Introduce real-time change characteristics into the Pareto front solution set for dynamic correction to generate dynamic scheduling policy information that meets multiple constraints; 6. The method according to claim 1, wherein Push the device operation instructions of the dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and push the strategic decision support map of the visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit, including: Perform dynamic encryption processing on the device operation instructions, match the encrypted device operation instructions with the operation permission level of the business cockpit, and push the abnormal condition handling priority mark corresponding to the successfully matched device operation instructions to the business cockpit; Perform homomorphic encryption processing on the strategic decision support map, and generate the scheduling benefit prediction heat map through a visual rendering engine; Match the scheduling benefit prediction heat map with the operation permission level of the group leader cockpit, and push the successfully matched scheduling benefit prediction heat map to the group leader cockpit; 7. The method according to claim 1, characterized in that, After pushing the device operation instructions of the dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and pushing the strategic decision support map of the visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit, it further includes: Obtain the operation response data of the business cockpit and the feedback correction instructions of the group leader cockpit; Update the weight parameters of the dynamic user profile according to the operation response data and the feedback correction instructions of the group leader cockpit through a preset adaptive learning model, and perform index reconstruction on the three-dimensional dynamic data matrix to complete the dynamic closed-loop optimization of the dynamic scheduling policy information; 8. A business scheduling device combining a business and a group leadership cockpit, characterized in that, The device includes: A data acquisition unit for acquiring the device operation data and environmental monitoring data of multiple power plants to construct a three-dimensional dynamic data matrix based on a preset data layering rule; wherein, the three-dimensional dynamic data matrix includes device layer parameters, business layer parameters, and management layer parameters, the device layer parameters include unit operation status parameters, the business layer parameters include production load distribution parameters, and the management layer parameters include cross-power plant coordinated scheduling indicators; An image generation unit, configured to parse the operation logs of the business team and the decision-making records of the group leaders based on natural language processing technology, and generate dynamic user portraits of the business team and the group leaders; wherein the dynamic user portrait of the business team includes the characteristic coefficient of equipment operation frequency, and the dynamic user portrait of the group leaders includes the sensitivity coefficient of strategic indicators; A policy generation unit, configured to extract real-time change features according to the three-dimensional dynamic data matrix, and generate dynamic scheduling policy information through a multi-objective optimization algorithm according to the characteristic coefficient of equipment operation frequency, the sensitivity coefficient of strategic indicators, and the real-time change features; the dynamic scheduling policy information includes an equipment start-stop plan, a load distribution ratio, and a cross-power plant resource allocation plan; A scheduling completion unit, configured to push the equipment operation instructions of the dynamic scheduling policy information to the business cockpit according to the business permissions corresponding to the business cockpit, and push the strategic decision support map of the visual scheduling instruction set to the group leader cockpit according to the business permissions corresponding to the group leader cockpit; the equipment operation instructions at least include an abnormal condition handling priority mark, and the strategic decision support map at least includes a scheduling benefit prediction heat map.

9. A computer device, characterized in that, It includes a memory and a processor; the memory is used to store computer programs; the processor is used to execute the computer programs and implement the method according to any one of claims 1 to 7 when executing the computer programs.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer-readable instructions are executed by the processor, one or more processors are caused to execute the steps of the method according to any one of claims 1 to 7.

Images