Electric power enterprise intelligent collaborative office method and system based on artificial intelligence

Abstract

The invention discloses a power enterprise intelligent collaborative office method and system based on artificial intelligence, and relates to the technical field of power informatization. According to the intelligent collaborative office method and system for the power enterprise based on artificial intelligence, request data is received from a user terminal through a deep learning model, a service demand type, an emergency degree and task complexity are identified, a service priority index is generated, classification and priority distribution are carried out, and based on the service priority, the user terminal is subjected to intelligent collaborative office. The method comprises the following steps of: matching associated tasks and resource requirements through a model, retrieving related historical data to optimize a resource configuration path, dynamically tracking task progress, execution state and resource consumption, identifying a bottleneck in an execution process and generating an optimization instruction, and finally, dynamically adjusting model parameters and resource configuration rules through an adaptive learning algorithm. And a closed-loop feedback mechanism is formed. Information flow and resource configuration are effectively integrated, the flexibility and response speed of collaborative office are improved, and the development requirements of smart grids and smart cities are met.

Description

Technical Field

[0001] The present invention relates to the technical field of power informatization, and specifically to an intelligent collaborative office method and system for power enterprises based on artificial intelligence. Background Art

[0002] With the growth of global energy demand and the improvement of the digital level of power systems, power enterprises are facing the pressure of maintaining efficient operations in a more complex environment. The power industry requires a more flexible and intelligent collaborative office mode to cope with the increasing data and management needs. Traditional manual management and decentralized information processing can no longer meet the efficient collaborative needs across departments and regions. By introducing artificial intelligence, power enterprises can obtain support in aspects such as demand forecasting, resource scheduling, and emergency response, realize information integration, optimize the workflow, and improve management efficiency to adapt to the overall trend of the development of smart grids and smart cities.

[0003] For example, a collaborative office method and system with artificial intelligence learning ability, with the publication number CN116993307B, receives a collaborative office request from a user terminal, extracts service demand data from the collaborative office request; obtains demand feature information from the service demand data, generates corresponding communication data according to the demand feature information, and transmits the communication data to a data processing service; obtains data records of artificial intelligence learning, generates a data resource pool according to the data records, calls the data processing service to receive the communication data, matches the communication data with the data resource pool, and configures target collaborative work service data corresponding to the communication data; performs data management on the target collaborative work service data to convert it into a service data packet, uses the service data packet to match the corresponding target collaborative application, and calls and pushes the target collaborative application; can achieve more effective and practical-demand-compliant collaborative office, greatly improving the enterprise office efficiency and user experience.

[0004] The existing collaborative office methods of power enterprises mainly rely on traditional information systems and manual collaboration methods, lacking intelligent support and having obvious limitations. For example, a collaborative office method and system with artificial intelligence learning ability can achieve collaborative office processing based on artificial intelligence, but there are still problems in actual applications, such as insufficient accuracy of task response, low matching degree of resource allocation and actual task requirements, lag in optimization of the execution process, and poor adaptability of model adjustment. It is difficult to dynamically optimize the resource allocation path according to the urgency and complexity of tasks, and it is also impossible to achieve closed-loop adaptive adjustment of parameters and rules during the task execution process, resulting in low processing efficiency of key tasks and limited overall office intelligence level. First, relying on manual operations and single data rules, it is difficult to handle complex and multi-dimensional data requirements, leading to low information sharing and processing efficiency; second, the existing methods often rely on preset processes and lack dynamic response capabilities, unable to flexibly adapt to changing task requirements in actual operations. In addition, the existing collaborative office methods have insufficient intelligence levels in data analysis and task allocation, lacking intelligent algorithm support, resulting in low efficiency and low accuracy in resource allocation, response to emergencies and other links, and unable to fully meet the deep needs of power enterprises in intelligent office. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides an intelligent collaborative office method and system for power enterprises based on artificial intelligence, which solves the problems in the above background technology.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: An intelligent collaborative office method for power enterprises based on artificial intelligence includes the following steps: S1. Identify the business requirement type, urgency, and task complexity from the request data received from the user terminal according to the deep learning model, analyze the business requirement type, urgency, and task complexity, generate a business priority index, and classify and assign priorities to the requests according to the business priority index; S2. Based on the business priority index, match the associated tasks and resource requirements of the requests through the deep learning model, retrieve historical data and knowledge base information related to the business requirement type, urgency, and task complexity, and analyze and optimize the required resource allocation path; S3. Dynamically track the task progress, execution status, and resource consumption according to the deep learning model, identify the bottlenecks in the task execution process, and generate optimization instructions; S4. Based on the optimization instructions during the task execution process, dynamically adjust the parameters and resource allocation rules of the deep learning model through the adaptive learning algorithm.

[0007] Further, the specific process of analyzing the business requirement type, urgency, and task complexity to generate a business priority index is as follows: Parse the user request data according to the deep learning model, and extract the business requirement type, urgency, and task complexity features; Standardize the extracted features, assign weights to different features through a weighting algorithm, and perform a comprehensive operation to generate a business priority index.

[0008] Further, the specific process of classifying requests and assigning priorities according to the business priority index is as follows: Set a classification threshold according to the business priority index to divide the request levels; Compare the request data with the classification threshold to determine the priority category of the request; Generate a priority identifier according to the priority category and assign the request to the corresponding processing queue.

[0009] Further, based on the business priority index, the specific process of matching the associated tasks and resource requirements of the request through the deep learning model is as follows: Input the business priority index into the deep learning model to identify the associated tasks and required resources of the request; Retrieve resource information related to the business requirement type, urgency, and task complexity from historical data and the knowledge base; According to the retrieval results and request features, conduct resource requirement analysis and match the optimal resource allocation path.

[0010] Further, the specific process of analyzing and optimizing the required resource allocation path is as follows: Establish an optimization model for the resource allocation path according to the business priority index of the request; Obtain resource allocation data, including manpower, power equipment, and response time; Evaluate the performance of the resource allocation path through a multi-objective optimization algorithm and adjust the resource allocation path.

[0011] Further, the identification logic for dynamically tracking the task progress, execution status, and resource consumption according to the deep learning model to identify bottlenecks in the task execution process is as follows: Monitor the task progress, execution status, and resource consumption data according to the deep learning model and extract key features; Set a performance benchmark, compare the current state with the expected goal, and identify the deviation in the execution process; Determine the links that do not meet the set standards through threshold judgment; Sort the identified bottlenecks by priority.

[0012] Further, the specific process of generating optimization instructions is as follows: Based on the identified bottlenecks, analyze the influencing factors of task execution, including resource allocation and execution time; Convert the optimization plan into specific operation instructions, including resource reallocation, task scheduling, and priority adjustment; Set an execution time frame, feedback the generated optimization instructions to the deep learning model, and update the model parameters.

[0013] Furthermore, the specific process of dynamically adjusting the parameters and resource configuration rules of the deep learning model through the adaptive learning algorithm is as follows: Obtain the task execution data after executing the optimization instruction, covering the execution effect, resource usage, and completion timeliness; Analyze the difference between the task execution data and the optimization goal, and identify the key parameters affecting the model performance; Calculate the gradient of the key parameters and accordingly adjust the deep learning model parameters; Update the resource configuration rules, and feedback the adjusted parameters to the deep learning model to form a closed-loop feedback mechanism.

[0014] The intelligent collaborative office system for power enterprises based on artificial intelligence includes the following modules: business requirement identification module, resource matching and optimization module, bottleneck identification module, adaptive adjustment module; The business requirement identification module is used to identify the business requirement type, urgency, and task complexity from the request data received from the user terminal according to the deep learning model, analyze the business requirement type, urgency, and task complexity, generate a business priority index, classify the request according to the business priority index, and assign a priority; The resource matching and optimization module is used to match the associated tasks and resource requirements of the request based on the business priority index through the deep learning model, retrieve the historical data and knowledge base information related to the business requirement type, urgency, and task complexity, and analyze and optimize the required resource configuration path; The bottleneck identification module is used to dynamically track the task progress, execution status, and resource consumption according to the deep learning model, identify the bottlenecks in the task execution process, and generate optimization instructions; The adaptive adjustment module is used to dynamically adjust the parameters and resource configuration rules of the deep learning model based on the optimization instructions in the task execution process through the adaptive learning algorithm.

[0015] The present invention has the following beneficial effects: (1) For the intelligent collaborative office method for power enterprises based on artificial intelligence, by analyzing the request data of the user terminal through the deep learning model, it can efficiently classify business requirements, evaluate their urgency and complexity, and thus generate a business priority index. This accurate identification helps the enterprise quickly respond to customer needs, optimize task allocation, ensure that urgent and complex tasks are given priority, and thereby improve customer satisfaction and enterprise service quality. Based on the generated business priority index, the deep learning model can accurately match the associated tasks and resource requirements of the request. This process intelligently analyzes and optimizes the resource configuration path by retrieving historical data and knowledge base information, reduces the redundant use of manpower and equipment, ensures the reasonable allocation of resources at critical moments, improves work efficiency, and reduces the risk of delays caused by resource shortages.

[0016] (2) The intelligent collaborative office system for power enterprises based on artificial intelligence. The deep learning model monitors the progress, execution status, and resource consumption of tasks in real time, and through data analysis, it can promptly identify bottleneck links in the execution process. This dynamic monitoring helps managers quickly understand the project progress, implement targeted adjustment measures, ensure the smooth progress of tasks, and reduce the situations of project delays and cost overruns. After identifying the bottleneck, the system can generate optimization instructions and use the adaptive learning algorithm to dynamically adjust the parameters of the deep learning model. This adjustment ensures that the model can continuously adapt to new business requirements and environmental changes, improve the rationality of resource allocation rules, form a feedback loop, further optimize the system performance and response speed, and enhance the overall operation efficiency and flexibility of power enterprises.

[0017] Of course, it is not necessary for any product implementing the present invention to simultaneously achieve all the above-mentioned advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of the intelligent collaborative office method for power enterprises based on artificial intelligence of the present invention.

[0019] Figure 2 It is a schematic structural diagram of the intelligent collaborative office system for power enterprises based on artificial intelligence of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The embodiments of the present application solve the problems of low efficiency in processing complex data requirements, dynamic response, and resource allocation in traditional collaborative office methods through the intelligent collaborative office method and system for power enterprises based on artificial intelligence.

[0021] The general idea for the problems in the embodiments of the present application is as follows: Identify the business requirement type, urgency, and task complexity from the request data received from the user terminal according to the deep learning model, analyze the business requirement type, urgency, and task complexity, generate a business priority index, and classify and assign priorities to the requests according to the business priority index.

[0022] Based on the business priority index, match the associated tasks and resource requirements of the requests through the deep learning model, retrieve historical data and knowledge base information related to the business requirement type, urgency, and task complexity, and analyze and optimize the required resource allocation path.

[0023] Dynamically track the task progress, execution status, and resource consumption according to the deep learning model, identify bottlenecks in the task execution process, and generate optimization instructions.

[0024] Based on the optimization instructions in the task execution process, dynamically adjust the parameters of the deep learning model and the resource allocation rules through the adaptive learning algorithm.

[0025] Please refer to Figure 1 , an embodiment of the present invention provides a technical solution: an intelligent collaborative office method for power enterprises based on artificial intelligence, including the following steps: S1. Identify the business requirement type, urgency, and task complexity from the request data received from the user terminal according to the deep learning model, analyze the business requirement type, urgency, and task complexity, generate a business priority index, and classify and assign priorities to the requests according to the business priority index; S2. Based on the business priority index, match the associated tasks and resource requirements of the requests through the deep learning model, retrieve the historical data and knowledge base information related to the business requirement type, urgency, and task complexity, and analyze and optimize the required resource configuration path; S3. Dynamically track the task progress, execution status, and resource consumption according to the deep learning model, identify the bottlenecks in the task execution process, and generate optimization instructions; S4. Based on the optimization instructions during the task execution process, dynamically adjust the parameters and resource configuration rules of the deep learning model through the adaptive learning algorithm.

[0026] In this implementation scheme: S1. This step analyzes the request data submitted by the user terminal through a deep learning model to identify and classify business requirements. According to the urgency and complexity of the requirements, a business priority index is generated to determine the priority order for subsequent processing. Deep learning model: A machine learning model that simulates the structure of the human brain neural network and is trained with a large amount of data to extract features and patterns. S2. In this stage, according to the generated business priority index, the deep learning model matches the user requests with relevant task and resource requirements, retrieves historical data and knowledge base information, and analyzes and optimizes the resource allocation path. Historical data and knowledge base: Refers to the past operation data and knowledge accumulation of the enterprise, which can provide a basis for current decision-making. S3. This step monitors the progress, status, and resource consumption of task execution through a deep learning model, identifies bottlenecks that occur during the execution process, and generates corresponding optimization instructions. S4. According to the identified bottlenecks and the generated optimization instructions, an adaptive learning algorithm is used to dynamically adjust the parameters and resource allocation rules of the deep learning model to continuously optimize work efficiency. Deep learning model: A machine learning model based on a multi-layer neural network that can automatically extract features and learn complex patterns from a large amount of data. Commonly used in fields such as image recognition and natural language processing. Business priority index: A quantitative indicator used to evaluate and rank the priorities of different business requirements, usually considering factors such as urgency, resource requirements, and potential impact. Resource allocation path: Refers to the specific plan for the allocation and use of resources (such as human and material resources) during task execution. Optimization instructions: Specific operation suggestions generated based on data analysis, aiming to improve the efficiency and effect of task execution. Bottleneck analysis: Identifying and evaluating the links that limit performance or efficiency in the production or service process, and improving the overall process efficiency by solving bottleneck problems. Adaptive learning algorithm: Refers to a class of machine learning algorithms that can self-adjust during the process of continuously obtaining new data to improve the prediction accuracy and adaptability of the model.

[0027] Specifically, the specific process of analyzing the business requirement type, urgency, and task complexity to generate the business priority index is as follows: Parse the user request data according to the deep learning model, and extract the features of business requirement type, urgency, and task complexity; perform standardization processing on the extracted features, assign weights to different features through a weighting algorithm, and perform comprehensive operations to generate the business priority index.

[0028] In this implementation scheme, data parsing: Use the deep learning model to analyze the user request data and extract the following features: business requirement type (T), urgency (E), task complexity (C); feature standardization: Perform standardization processing on the extracted features to ensure that the features are compared under the same dimension. The standardization formula is: ; where is the original feature value, The mean value of the feature is the standard deviation of the feature. Weights are assigned to different features through a weighting algorithm to generate a business priority index. After setting the weights, the calculation formula for the business priority index ( ) is as follows: ; : The business priority index, which represents the priority of a task or request. The higher the value, the higher the priority; : The feature values of the business requirement type, urgency, and task complexity after standardization, corresponding to the original features extracted respectively. : The weight coefficients corresponding to the business requirement type, urgency, and task complexity, indicating the importance of each feature in the priority calculation. Their value range is from 0 to 1, and they need to satisfy . The normalization factor, which is used to adjust the proportion of each part in the formula so that the final priority index is within a reasonable range, usually : Resource availability, which represents the quantity or quality of resources currently available for a task. The value range is from 0 to 1, where 0 means no available resources and 1 means sufficient resources. : Historical completion efficiency, which represents the efficiency of executing similar tasks in the past. Usually, it is the ratio of the completion time to the expected time. A value greater than 1 means the execution efficiency is lower than expected, and a value less than 1 means it is better than expected. : The adjustment coefficient, which is used to adjust the influence degree of resource availability and historical efficiency on the priority. It is dynamically set according to actual requirements. : The constant correction term, which is used to compensate for the priority deviation caused by model limitations or external factors. It can be set according to specific application scenarios to ensure the rationality and accuracy of the business priority index.

[0029] Specifically, the specific process of classifying requests and assigning priorities according to the business priority index is as follows: Set classification thresholds according to the business priority index to divide the request levels; Compare the request data with the classification thresholds to determine the priority category of the request; Generate a priority identifier according to the priority category and assign the request to the corresponding processing queue.

[0030] In this implementation plan, the process is mainly divided into three steps: setting classification thresholds, comparing request data with classification thresholds, and generating priority identifiers and allocating requests to processing queues. Step 1: Set classification thresholds. According to the distribution of business priority indices, set classification thresholds to divide the priority levels of requests. According to historical data or real-time feedback, there is the fixed threshold method: set fixed priority thresholds based on experience or industry standards. For example: high priority threshold: P≥0.75, medium priority threshold: 0.50≤P<0.75, low priority threshold: P<0.50. Compare the request data with the classification thresholds. Compare the calculated business priority index (P) with the set classification thresholds to determine the priority category of each request. The specific comparison process is as follows: For the priority index of each request, compare it with the set thresholds in turn: If P≥0.75, the request category is high priority. If 0.50≤P<0.75, the request category is medium priority. If P<0.50, the request category is low priority. Through this comparison, the urgency of request processing can be accurately judged, facilitating subsequent task allocation. Generate priority identifiers and allocate requests to processing queues. According to the determined priority category, generate corresponding priority identifiers for each request and allocate the requests to the corresponding processing queues: high priority requests are identified as "high"; medium priority requests are identified as "medium"; low priority requests are identified as "low". High priority requests will be immediately placed in the "high priority processing queue" for priority processing. Medium priority requests are placed in the "medium priority processing queue" and processed in order. Low priority requests will be placed in the "low priority processing queue" and processed when resources are idle.

[0031] Specifically, based on the business priority index, the specific process of matching the associated tasks and resource requirements of the request through a deep learning model is as follows: Input the business priority index into the deep learning model to identify the associated tasks and required resources of the request; Retrieve resource information related to business requirement types, urgency, and task complexity from historical data and the knowledge base; According to the retrieval results and request characteristics, conduct resource requirement analysis and match the optimal resource allocation path.

[0032] In this implementation plan, the process is mainly divided into the following four steps: input the business priority index, identify the associated tasks and required resources of the request, retrieve resource information, and conduct resource demand analysis and match the optimal resource allocation path. Step 1: Input the business priority index into the deep learning model. The calculated business priority index (P) is used as input data and passed to the deep learning model (CNN model). The model processes the input data through forward propagation and outputs the tasks and resource requirements related to the request. At this time, the input data structure may include the following information: Request feature vector: It contains feature data, such as the type of business requirements, the degree of urgency (e.g., the set value ranges from 1 to 5, where 1 represents a low degree of urgency and 5 represents a high degree of urgency), and the task complexity (e.g., simple, medium, complex). Step 2: Identify the associated tasks and required resources of the request. The model processes the input data to identify the specific tasks and corresponding resources required by the request. Specifically, it includes: Task identification: The model determines the specific tasks involved in the request based on the patterns learned from historical data. For example, for a power failure handling request, the model may identify "fault detection" and "on-site repair" as associated tasks. Resource requirement identification: Based on the identified tasks, the model outputs the specific resource types and quantities required. For instance, it is identified that the repair task requires 2 technicians, 1 maintenance equipment, and corresponding safety equipment. Step 3: Retrieve resource information. After identifying the tasks and resource requirements of the request, relevant resource information is retrieved from the enterprise's historical database and knowledge base. The specific process includes: Historical data analysis: By analyzing the processing records of previous similar requests (e.g., finding out the average time required to complete the fault detection task and the resource allocation according to historical records), it is determined which resources are most effective in similar situations. Knowledge base query: Extract the best practices and resource allocation suggestions related to the task type, degree of urgency, and complexity from the knowledge base. For example, for a complex fault handling task, the knowledge base may store a recommended resource allocation list for specific equipment failures. Step 4: Conduct resource demand analysis and match the optimal resource allocation path. Based on the request features, associated tasks, and retrieved resource information, resource demand analysis is conducted and the optimal resource allocation path is matched. The specific process is as follows: Demand analysis: Using the results of historical data analysis, the specific resource requirements of the request are evaluated, and the quantity of resources required to complete the task and their corresponding configurations are clarified. For example, if historical data shows that the "fault detection" task generally takes 3 hours and requires 1 experienced technician, the system takes this information into consideration.

[0033] Path matching: Using an optimization algorithm (linear programming), comparing the task and resource requirements, the optimal resource allocation path is determined. At this time, the system combines the real-time available resources to generate an optimal resource scheduling list. For example, if two technicians are available at the same time, the system will preferentially select the experienced technician for fault detection and allocate the corresponding equipment.

[0034] Specifically, the specific process of analyzing and optimizing the required resource allocation path is as follows: According to the business priority index of the request, an optimization model of the resource allocation path is established; resource allocation data is obtained, including manpower, power equipment, and response time; the performance of the resource allocation path is evaluated through a multi-objective optimization algorithm, and the resource allocation path is adjusted.

[0035] In this implementation plan, this process mainly includes four steps: establishing an optimization model of the resource allocation path, obtaining resource allocation data, performance evaluation, and adjusting the resource allocation path. Step 1: Establishing the construction of an optimization model of the resource allocation path according to the business priority index of the request: According to the business priority index of the request ( ), a mathematical optimization model is constructed. This model can adopt the form of linear programming or integer programming, and its goal is to minimize the resource usage cost while maximizing the efficiency of task execution. The basic structure of the model is as follows: ; where: is the total cost; indicates that the goal is to minimize the total resource usage cost C; is the resource usage cost of the i-th task; is the allocation amount of resources required for the i-th task; subject to means satisfying the following constraints, here it refers to that for each task i, the allocation amount of resources must be no less than the demand ; The contribution coefficient of the i-th task to the j-th resource; is the task 's demand; $x_{ij}$ is the allocation volume of the $j$-th type of resource; $m$ is the total number of tasks; $n$ is the total number of resources. Objective function: According to business requirements and resource availability, set an appropriate objective function. For example, minimize response time and total resource consumption as much as possible. Step 2: Data collection: Extract relevant resource allocation data from the enterprise internal system and external databases, including the following aspects: Human resources: Obtain the number of available technicians, skill levels, and work time arrangement information. Power equipment: Collect the availability, processing capacity (such as equipment load, response time, etc.) and maintenance status of the equipment. Response time: Analyze the average response time of specific tasks based on historical data. Data standardization: To ensure the compatibility of different types of data, standardize the obtained data for subsequent analysis. The standardization method uses Z-score standardization. Step 3: Use a multi-objective optimization algorithm to evaluate the performance of the resource allocation path to ensure finding the best balance among multiple objectives. The multi-objective optimization algorithm aims to optimize multiple objectives simultaneously, minimize costs, maximize efficiency, and shorten response time. This algorithm allows evaluating the advantages and disadvantages of different resource allocations and generating a set of feasible solutions. Step 4: Path adjustment: Adjust the resource allocation path according to the output results of the multi-objective optimization algorithm. This may include: Resource reallocation: Adjust the resource allocation required for each task according to the optimization results. For example, transfer the technicians of a certain task from a secondary task to a high-priority request. Time adjustment: Optimize the execution order of tasks to reduce the overall response time. For example, arrange high-urgency tasks to be executed first. Iterative optimization: Continuously iterate and optimize the resource allocation path according to the actual execution feedback and performance evaluation results to continuously improve efficiency and response speed.

[0036] Specifically, the identification logic for dynamically tracking the task progress, execution status, and resource consumption according to the deep learning model and identifying the bottlenecks in the task execution process is as follows: Monitor the task progress, execution status, and resource consumption data according to the deep learning model, and extract key features; Set performance benchmarks, compare the current state with the expected goals, and identify the deviations in the execution process; Determine the links that do not meet the set standards through threshold judgment; Prioritize the identified bottlenecks.

[0037] In this implementation plan, in the intelligent collaborative office system of power enterprises, the specific logic for dynamically tracking task progress, execution status, and resource consumption is as follows: The system uses a deep learning model to monitor the task progress, execution status, and resource consumption in real time. The data sources for monitoring include: Task progress: Records the percentage of the task completed and the achievement of milestones at each stage. Execution status: The current status of the task (e.g., in progress, paused, completed, delayed). Resource consumption: Involves the usage of personnel, equipment, and resources such as time and electricity consumed. The purpose of extracting key features is to understand the actual execution of the task for subsequent analysis. Next, the system sets performance benchmarks to compare the current state with the expected goals. The performance benchmarks can include: Expected progress goal: The set task progress requirement, such as the percentage of completion that the task should reach at a specific time point. Expected status requirement: The specified task execution status, e.g., the expected progress of the task. Expected resource usage: The maximum amount of resources expected to complete the task, including time and equipment usage limits. By comparing the actual monitoring data with these expected goals, the system can identify the deviations that occur during task execution. Threshold judgment and bottleneck determination, the system sets thresholds to determine which links do not meet the set standards. For example: Behind schedule: If the current progress is significantly lower than the expected goal, the task is marked as a progress bottleneck. Status problem: If the execution status of the task fails to proceed according to the predetermined time node, it is marked as a status bottleneck. Resource overrun: If the actual resource consumption exceeds the expected upper limit, the system marks this link as a resource bottleneck. The identification of these bottlenecks helps to take timely measures for adjustment. Bottleneck priority ranking, finally, the system ranks the identified bottlenecks according to the following factors: Severity: Evaluates the degree of task deviation, and the links with larger deviations in progress and resource consumption have higher priorities. Scope of influence: Analyzes the impact of the bottleneck on the overall project progress, and the links with greater impact are given priority for processing. Difficulty of solution: Considers the resources and time required to fix the bottleneck, and the bottlenecks that are easier to solve have higher priorities.

[0038] Specifically, the specific process of generating optimization instructions is as follows: Based on the identified bottlenecks, analyze the influencing factors of task execution, including resource allocation and execution time; convert the optimization plan into specific operation instructions, including resource reconfiguration, task scheduling, and priority adjustment; set an execution time frame, and feedback the generated optimization instructions to the deep learning model to update the model parameters.

[0039] In this implementation plan, in the intelligent collaborative office system, the specific process of generating optimization instructions is as follows: Bottleneck Identification and Factor Analysis: After identifying the bottlenecks in the task execution process, the system first conducts in-depth analysis of these bottlenecks, mainly including the following two aspects: Resource Allocation: Check the current resource configuration, including human resources, equipment usage, and budget allocation, etc., and evaluate whether it is reasonable and how to optimize it. For example, if the execution of a certain task is overly dependent on a single resource, the system will consider increasing or reallocating that resource to alleviate the bottleneck. Execution Time: Analyze the time management of tasks, including the comparison between the actual execution time and the expected time of tasks. Through monitoring data, the system can identify the specific links of delays and the reasons for the delays (such as resource shortages, task complexity, etc.). Transformation of Optimization Solutions into Operational Instructions: Once the influencing factors are analyzed, the system will then specify the optimization solutions into operational instructions, including but not limited to the following: Resource Reconfiguration: According to the bottleneck situation, the system may instruct to transfer some resources from low-priority tasks to high-priority tasks. For example, if the progress of a certain project is slow and the urgency is high, the system can recommend increasing manpower or equipment support. Task Scheduling: Optimize the time arrangement of tasks to improve the overall efficiency by adjusting the execution order and start time of each task. The system may propose to postpone some non-urgent tasks in order to concentrate resources on handling the current key tasks. Priority Adjustment: According to the business priority index and the results of bottleneck analysis, the system will adjust the priorities of tasks to ensure that the most important tasks can obtain resources and support first. Setting of Execution Time Frame: After generating the optimization instructions, the system will set an execution time frame for each operation instruction to ensure that various optimization measures can be implemented in a timely manner. The time frame includes: Specific Start Time: Indicate when the optimization instruction should start to be implemented. Expected Completion Time: Estimate the implementation duration of each optimization measure to monitor the progress. Feedback of Optimization Instructions and Model Update: Finally, the generated optimization instructions are fed back to the deep learning model, and the model parameters are updated. This process includes: Encoding and Input of Optimization Instructions: Transform the optimization solution into a format that can be understood by the model and input it into the deep learning model for subsequent data training and optimization. Model Parameter Update: Adjust the model parameters according to the newly fed-back information to ensure that the model can better adapt to the real-time changing task execution environment and resource configuration requirements.

[0040] Specifically, the specific process of dynamically adjusting the parameters and resource configuration rules of the deep learning model through the adaptive learning algorithm is as follows: Obtain the task execution data after executing the optimization instructions, covering the execution effect, resource usage, and completion timeliness; Analyze the differences between the task execution data and the optimization objectives to identify the key parameters affecting the model performance; Calculate the gradients of the key parameters and accordingly adjust the deep learning model parameters; Update the resource configuration rules, and feed the adjusted parameters back to the deep learning model to form a closed-loop feedback mechanism.

[0041] In this implementation plan, in the intelligent collaborative office system, the specific process of dynamically adjusting the parameters and resource allocation rules of the deep learning model through the adaptive learning algorithm is as follows: Obtain task execution data: First, the system collects task execution data after executing the optimization instructions. These data mainly include: Execution effect: The completion quality and efficiency of the task, including whether the task is completed within the expected time and whether the task result meets the set standards. Resource usage: The actual usage of various resources (human resources, equipment, etc.), including the input of resources, usage frequency, and effectiveness in task execution. Completion timeliness: The time required to complete the task, compared with the preset completion time limit, to evaluate whether the task is delivered on time. Analyze the differences between task execution data and optimization goals: By analyzing the collected data, the system can identify the differences between task execution data and the predetermined optimization goals. This step mainly includes: Difference identification: Compare the actual execution effect, resource usage, and completion timeliness with the optimization goals to identify which aspects fail to meet expectations. For example, if the actual completion timeliness of a certain task far exceeds the expectation, it indicates that there is insufficient resource allocation or improper scheduling. Key parameter identification: Based on the difference analysis, the system identifies the key parameters that affect the model performance. These parameters may include task complexity, resource allocation ratio, the ability of the execution team, etc. Calculate the gradients of key parameters: After identifying the key parameters, the system will perform gradient calculation, and the specific steps are as follows: Gradient calculation: Use the optimization algorithm (stochastic gradient descent) to calculate the gradients of the key parameters with respect to the model loss function. This process helps the system understand how to adjust the parameters to better optimize task execution under the current configuration. Parameter update direction: Determine the adjustment direction and amplitude of the model parameters based on the calculated gradients to reduce the gap between the model output and the actual execution results. Adjust the parameters of the deep learning model: After calculating the gradients of the key parameters, the system will accordingly adjust the parameters of the deep learning model, and the specific process is as follows: Parameter adjustment: Update the model parameters based on the gradient information according to the set learning rate. The learning rate determines the amplitude of each adjustment, and a reasonable learning rate can effectively improve the convergence speed and stability of the model. Model retraining: After parameter adjustment, the model may need to be retrained to adapt to the new parameter configuration, thereby improving the prediction accuracy and execution efficiency. Update the resource allocation rules: After adjusting the parameters of the deep learning model, the system will next update the resource allocation rules to ensure the effective implementation of the optimization measures. This step includes: Resource allocation rule evaluation: Re-evaluate the existing resource allocation rules according to the newly adjusted model parameters, and analyze which rules need to be modified to improve the overall performance. Rule update: Update the resource allocation rules, integrate the adjusted parameters with the new configuration requirements to ensure that resources can be utilized more efficiently in subsequent task execution. Feedback to the deep learning model to form a closed-loop feedback mechanism: All adjustments and updates will be fed back to the deep learning model to form a closed-loop feedback mechanism to ensure that the system can continuously learn and optimize.Specifically include: Feedback mechanism: The execution data, model parameters, and resource allocation rules are fed back as inputs into the deep learning model, enabling it to learn from historical data and improve its own intelligence level. Continuous optimization: Through this feedback mechanism, the system can dynamically adjust itself to adapt to the changing task execution environment and management requirements, thereby improving the operation efficiency of power enterprises.

[0042] Please refer to Figure 2 , an intelligent collaborative office system for power enterprises based on artificial intelligence, including the following modules: business requirement identification module, resource matching and optimization module, bottleneck identification module, and adaptive adjustment module; The business requirement identification module is used to identify the business requirement type, urgency, and task complexity from the request data received from the user terminal according to the deep learning model, analyze the business requirement type, urgency, and task complexity, generate a business priority index, classify the requests according to the business priority index, and assign priorities; The resource matching and optimization module is used to match the associated tasks and resource requirements of the requests based on the business priority index through the deep learning model, retrieve the historical data and knowledge base information related to the business requirement type, urgency, and task complexity, and analyze and optimize the required resource allocation path; The bottleneck identification module is used to dynamically track the task progress, execution status, and resource consumption according to the deep learning model, identify the bottlenecks in the task execution process, and generate optimization instructions; The adaptive adjustment module is used to dynamically adjust the parameters and resource allocation rules of the deep learning model based on the optimization instructions in the task execution process through the adaptive learning algorithm.

[0043] In this implementation solution, there is a business requirement identification module which is mainly responsible for receiving request data from user terminals and using a deep learning model to parse and analyze the data. Its specific functions include: identifying the type of business requirement: determining the specific business area involved in the user request for targeted processing; evaluating the urgency: analyzing the urgency of the request to prioritize high-priority business requirements; analyzing the task complexity: evaluating the complexity of the request to help the system allocate appropriate resources and tasks; generating a business priority index: combining the above analysis results to generate a comprehensive business priority index, which is used to classify and prioritize requests to ensure that high-priority tasks are processed first. There is also a resource matching and optimization module which, based on the business priority index, uses a deep learning model for resource allocation and task matching. Its specific functions include: associating task and resource requirement matching: identifying relevant historical tasks and resource requirements according to the characteristics of the request; retrieving historical data and knowledge base information: extracting historical data related to the current request from the system's knowledge base for reference in resource allocation; analyzing and optimizing the resource allocation path: optimizing the resource allocation path through data analysis to achieve the best resource utilization and task execution effect. There is a bottleneck identification module which is responsible for dynamically monitoring key metrics during task execution and identifying possible bottlenecks. Its specific functions include: dynamically tracking task progress and execution status: monitoring the execution of tasks in real time to ensure timely problem discovery; resource consumption analysis: analyzing the resource consumption during task execution to identify resource shortages or unreasonable configurations; generating optimization instructions: after identifying bottlenecks, this module will generate targeted optimization instructions to guide subsequent resource adjustment and task rescheduling. There is an adaptive adjustment module which dynamically adjusts the deep learning model and resource allocation rules according to the optimization instructions during task execution. Its specific functions include: dynamically adjusting model parameters: using an adaptive learning algorithm to update the parameters of the deep learning model in real time to improve the model's prediction accuracy and task processing ability; updating resource allocation rules: adjusting resource allocation rules in a timely manner according to new task execution data and optimization instructions to ensure that the system can respond flexibly to different task requirements; forming a closed-loop feedback mechanism: through continuous feedback and adjustment, the system can achieve self-learning and optimization, improving the overall operation efficiency.

[0044] In summary, this application has at least the following effects: An intelligent collaborative office method and system for power enterprises based on artificial intelligence receive request data from user terminals through a deep learning model, identify the types of business requirements, urgency levels, and task complexities, generate business priority indices, classify and allocate priorities, match associated tasks and resource requirements based on business priorities through model matching, retrieve relevant historical data to optimize resource allocation paths, dynamically track task progress, execution status, and resource consumption, identify bottlenecks during execution, and generate optimization instructions. Finally, through an adaptive learning algorithm, dynamically adjust model parameters and resource allocation rules to form a closed-loop feedback mechanism. Effectively integrate information flow and resource allocation, improve the flexibility and response speed of collaborative office, and meet the development needs of smart grids and smart cities.

[0045] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, system, or computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0046] The present invention is described with reference to the flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0047] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are executed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the steps specified in one process or multiple processes and / or blocks Figure 1 one process or multiple processes and / or blocks Figure 1 steps for the functions specified in one block or multiple blocks.

[0049] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0050] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent collaborative office method for power enterprises based on artificial intelligence, characterized in that: The following steps are involved: S1. Identify the business requirement type, urgency and task complexity from the request data received from the user terminal according to the deep learning model, analyze the business requirement type, urgency and task complexity, generate a business priority index, and classify and prioritize the requests according to the business priority index; S2. Based on the business priority index, the deep learning model is used to match the associated tasks and resource requirements of the request, retrieve historical data and knowledge base information related to the business requirement type, urgency and task complexity, and analyze and optimize the required resource configuration path; S3. Dynamically track task progress, execution status, and resource consumption based on the deep learning model, identify bottlenecks in task execution, and generate optimization instructions; S4. Based on the optimization instructions during task execution, the parameters and resource configuration rules of the deep learning model are dynamically adjusted through an adaptive learning algorithm.

2. The intelligent collaborative office method for electric power enterprises based on artificial intelligence according to claim 1 is characterized by: The specific process of analyzing the business demand type, urgency and task complexity to generate the business priority index is as follows: Analyze user request data based on deep learning models to extract business demand type, urgency, and task complexity features; The extracted features are standardized, weights are assigned to different features through a weighted algorithm, and comprehensive calculations are performed to generate a business priority index.

3. The intelligent collaborative office method for electric power enterprises based on artificial intelligence according to claim 2 is characterized by: The specific process of classifying and prioritizing requests based on the business priority index is as follows: Set classification thresholds based on business priority index and classify requests; Compare request data with classification thresholds to determine the priority category of the request; Generate a priority ID based on the priority category and assign the request to the corresponding processing queue.

4. The intelligent collaborative office method for electric power enterprises based on artificial intelligence according to claim 3 is characterized by: Based on the business priority index, the specific process of matching the associated tasks and resource requirements of the request through the deep learning model is as follows: Input the business priority index into the deep learning model to identify the associated tasks and required resources of the request; Retrieve resource information related to business requirement type, urgency, and task complexity from historical data and knowledge bases; Based on the search results and request characteristics, perform resource demand analysis and match the optimal resource configuration path.

5. The intelligent collaborative office method for electric power enterprises based on artificial intelligence according to claim 4 is characterized by: The specific process of analyzing and optimizing the required resource configuration path is as follows: Establish an optimization model for resource allocation paths based on the requested business priority index; Obtain resource configuration data, including manpower, power equipment, and response time; The resource configuration path is evaluated for performance and adjusted through a multi-objective optimization algorithm.

6. The intelligent collaborative office method for electric power enterprises based on artificial intelligence according to claim 5 is characterized by: The deep learning model is used to dynamically track task progress, execution status, and resource consumption, and the identification logic of bottlenecks in the task execution process is as follows: Monitor task progress, execution status, and resource consumption data based on deep learning models and extract key features; Set performance benchmarks, compare current status with expected goals, and identify deviations in execution; Through threshold judgment, determine the links that do not meet the set standards; Prioritize the identified bottlenecks.

7. The intelligent collaborative office method for electric power enterprises based on artificial intelligence according to claim 6 is characterized by: The specific process of generating optimization instructions is as follows: Based on the identified bottlenecks, analyze the factors affecting task execution, including resource allocation and execution time; Convert optimization plans into specific operational instructions, including resource reconfiguration, task scheduling, and priority adjustment; Set the execution time frame, feed the generated optimization instructions back to the deep learning model, and update the model parameters.

8. The intelligent collaborative office method for electric power enterprises based on artificial intelligence according to claim 7 is characterized by: The specific process of dynamically adjusting the parameters and resource configuration rules of the deep learning model through the adaptive learning algorithm is as follows: Obtain task execution data after executing optimization instructions, including execution effect, resource usage, and completion time; Analyze the differences between task execution data and optimization goals, and identify key parameters that affect model performance; Calculate the gradients of key parameters and adjust the deep learning model parameters accordingly; Update resource configuration rules and feed the adjusted parameters back to the deep learning model to form a closed-loop feedback mechanism.

9. An intelligent collaborative office system for electric power enterprises based on artificial intelligence, applying an intelligent collaborative office method for electric power enterprises based on artificial intelligence as described in any one of claims 1 to 8, characterized in that: Includes the following modules: Business demand identification module, resource matching optimization module, bottleneck identification module, and adaptive adjustment module; The business demand identification module is used to identify the business demand type, urgency and task complexity from the request data received from the user terminal according to the deep learning model, analyze the business demand type, urgency and task complexity, generate a business priority index, and classify and prioritize the requests according to the business priority index; The resource matching optimization module is used to match the associated tasks and resource requirements of the request based on the business priority index through a deep learning model, retrieve historical data and knowledge base information related to the business requirement type, urgency and task complexity, and analyze and optimize the required resource configuration path; The bottleneck identification module is used to dynamically track task progress, execution status and resource consumption according to the deep learning model, identify bottlenecks in the task execution process, and generate optimization instructions; The adaptive adjustment module is used to dynamically adjust the parameters and resource configuration rules of the deep learning model through an adaptive learning algorithm based on the optimization instructions during the task execution process.

Images