A method, device and medium for managing and controlling online nodes of the entire enterprise based on a digital intelligence and electrical platform

Abstract

The present invention discloses a method, device and medium for managing and controlling online nodes of the whole enterprise based on a digital and intelligent power platform, which relates to the technical field of online node management and control of the whole enterprise, and includes the following steps: obtaining work node evaluation data and push information evaluation data; constructing a push priority evaluation model based on the bp neural network according to the work node evaluation data and the push information evaluation data, and generating push information priority; generating a push information sorting table according to the push information priority, and pushing work node information based on the push information sorting table; obtaining the enterprise work plan, establishing a three-color progress evaluation mechanism, the three colors including green, yellow and red; adjusting the push order of work node information according to the three-color progress evaluation mechanism. This application solves the problem that label information notes and push functions will generate information overload, which makes it difficult to effectively filter out the content that really needs attention.

Description

Technical Field

[0001] The present invention relates to the technical field of online node control for enterprise-wide services. More specifically, the present invention relates to a method, device and medium for online node control for enterprise-wide services based on a digital intelligence integrated power platform. Background Art

[0002] The existing enterprise-wide online node control methods, devices and media based on the Digital Intelligence and Power Integration Platform are based on the "Digital Intelligence and Power Integration" platform to build a key enterprise-wide online node control system module to form a digital control handle. Classify and refine common work progress nodes, summarize and input work node information, and realize standardized control. Realize the visual display of processes and nodes, and promote the transformation of key work management into work orders.

[0003] Establish a "like" evaluation mechanism for management. Learn from the market-oriented marketing model to formulate a management evaluation strategy, and achieve a "short, flat and fast" evaluation of task nodes through likes. The "evaluation" function can provide specific evaluations. Set up functions such as attention, collection, pinning, and forwarding for work nodes to assist management in focusing on core work. Setting label information notes and push functions based on node work content can effectively support the timely communication of work requirements.

[0004] Implement accompanying control of all links according to the work plan. Establish a three-color evaluation mechanism for work progress, where on-time completion is recorded as a green card, overtime completion is recorded as a yellow card, and overtime again after being urged is recorded as a red card. The evaluation results can be used as an important basis for assessment or supervision. Implement the on-site verification mechanism for work nodes, formulate evaluation standards around progress, personnel performance, work quality, etc., and focus on the lagging or ahead of schedule of tasks, the consistency of on-site progress of tasks with the system, the implementation of coordinated issues, and the performance of responsibilities of the responsible personnel. Strengthen the scientific nature of the task process, and correct problems in a timely manner when they are discovered.

[0005] For example, the intelligent node management and control service system announced in the invention patent with announcement number CN117938636B provides a dynamic generation mechanism for distributed centerless node resource identifiers. The resource identifiers are globally unique, understandable, machine-readable, and extensible, and support full network synchronization. It supports real-time monitoring of node resource status, and achieves effective monitoring of training resources by dynamically acquiring status information of infrastructure, experimental platforms, and training resources. It provides operation diagnosis and fault location capabilities, and can quickly diagnose and locate faults based on abnormal alarm information of monitored resources, thereby achieving multi-dimensional control of training resources. It provides remote process call function, and realizes one-click sending and return status remote asynchronous calls of commands such as remote resource deployment, start and stop control, and resource recovery, providing strong support for the rapid construction of an integrated training simulation experiment operation environment, and providing accurate, efficient, and real-time technical guarantees for training simulation experiments.

[0006] For example, a node control method and system announced by the invention patent with announcement number CN112187532A, through a management platform, tenant nodes and routers, the management platform is connected to the management network, the router corresponds to the tenant network one by one, each tenant network contains multiple tenant nodes, and each tenant node establishes a communication connection with the network platform through the tenant network, the router corresponding to the tenant network and the management network; the method includes: the management platform obtains an operation command, determines that the tenant node corresponding to the operation command is the target node; the management platform searches for the communication connection corresponding to the target node, and writes the operation command into the communication connection corresponding to the target node; the target node obtains the operation command from the corresponding communication connection, executes the operation command, and returns the result of executing the operation command to the management platform. This application can greatly reduce the occupation of the IP resources of the management network and increase the number of tenant nodes that can be controlled.

[0007] The above disclosed technical solutions have at least the following technical problems:

[0008] Although the likes evaluation method in the process of online node management and control of the enterprise business is simple, it may not reflect the true quality of task completion. Likes may be more inclined to personal preferences or prejudices rather than objective standards;

[0009] In addition, the tag information annotation and push functions may cause information overload, making it difficult to effectively filter out the content that really needs attention. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0010] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method, device and medium for online node management of enterprise-wide business based on a digital and intelligent integrated power platform, which solves the problem of information overload caused by label information annotation and push functions, making it difficult to effectively screen out the content that really needs attention, through information push evaluation of online nodes of enterprise-wide business.

[0011] To achieve the above object, the present invention provides the following technical solutions:

[0012] The method for online node management and control of enterprise-wide business based on the digital and intelligent power integration platform includes the following steps: classify and refine common work nodes for the entire enterprise, and summarize and enter work node information; set labels, information notes and push functions for work nodes based on the digital and intelligent power integration platform; obtain work node evaluation data and push information evaluation data; build a push priority evaluation model based on the bp neural network according to the work node evaluation data and the push information evaluation data, and generate push information priority; generate a push information ranking table according to the push information priority, and push work node information based on the push information ranking table; obtain the enterprise work plan, and establish a three-color progress evaluation mechanism, wherein the three colors include green, yellow and red; and adjust the push order of work node information according to the three-color progress evaluation mechanism.

[0013] In a preferred embodiment, the digital intelligence and electrical integration platform is used to set labels, information notes and push functions for working nodes, specifically: based on NLP, key features of working nodes are extracted and labels are generated; based on a predefined label library, working nodes are classified and identified; the labels in the label library include task type, priority, time sensitivity and custom labels related to enterprise-specific business; based on an automated algorithm, labels are automatically matched and assigned according to the attributes and historical data of the nodes.

[0014] In a preferred embodiment, the working node evaluation data includes a working node timeliness influence coefficient; the push information evaluation data includes a push information entropy influence coefficient and a push information interactivity influence coefficient.

[0015] In a preferred embodiment, the specific method for obtaining the timeliness impact coefficient of the work node is as follows: obtain the historical key time points of each work node, the historical key time points include the planned start time, the planned completion time and the actual completion time; calculate the time deviation and the remaining time according to the historical key time points; build a task dependency graph based on each work node, and record the predecessor task and the successor task of each work node, and use a directed graph to represent the task dependency relationship; determine the node influence range based on the edges and nodes in the task dependency graph, and obtain the node influence weight; calculate the node delay impact coefficient based on the node influence weight; based on the delay impact coefficient of each node on the directed graph path after a specific node in the task dependency graph, summarize each delay impact coefficient and calculate the node importance; calculate the work node timeliness impact coefficient based on the node importance, time deviation and remaining time based on the preset work node timeliness impact coefficient calculation formula.

[0016] In a preferred embodiment, the specific method for obtaining the information entropy influence coefficient of the push information is as follows: collect all push text data of the information to be pushed, and simplify the text data; calculate the push word frequency probability of the push text data based on a preset word frequency model; calculate the information entropy of the push text data based on the push word frequency probability; calculate the information entropy influence coefficient of the push information by combining the information entropy of the push text data with the preset enterprise special word weights.

[0017] In a preferred embodiment, the specific method for obtaining the push information interactivity influence coefficient is as follows: based on historical interaction event types, an information interaction set is obtained, wherein the information interaction set includes various push information and their interaction events and event results; a preset interaction score is assigned to various interaction event types in the information interaction set; a regression model is constructed based on the information interaction set and the corresponding interaction scores to generate the push information interactivity influence coefficient.

[0018] A device for a method for controlling online nodes of the entire enterprise's business based on a digital and intelligent power integration platform, characterized in that it includes a node division module, an information push module, a push detailed analysis module, an information priority analysis module, an information sorting module, a three-color evaluation module and a secondary push module; the node division module is used to classify and refine common working nodes of the entire enterprise, and summarize and enter working node information; the information push module is used to set labels, information notes and push functions for working nodes based on the digital and intelligent power integration platform; the push detailed analysis module is used to obtain working node evaluation data and push information evaluation data; the information priority analysis module is used to construct a push priority evaluation model based on the bp neural network according to the working node evaluation data and the push information evaluation data, and generate push information priority; the information sorting module is used to generate a push information sorting table according to the push information priority, and push the working node information based on the push information sorting table; the three-color evaluation module is used to obtain the enterprise work plan and establish a three-color progress evaluation mechanism, wherein the three colors include green, yellow and red; the secondary push module is used to adjust the push order of working node information according to the three-color progress evaluation mechanism.

[0019] A computer-readable storage medium stores a computer program, characterized in that when the computer program is executed by a processor, a method for online node management and control of the entire enterprise's business based on a digital and intelligent power integration platform is implemented.

[0020] The technical effects and advantages of the enterprise-wide business online node management method, device and medium based on the digital intelligence power integration platform of the present invention are as follows:

[0021] 1. The present invention classifies and refines the common work nodes of the entire enterprise, and performs intelligent label setting, information annotation and push function configuration on the digital intelligence platform, which significantly improves the efficiency of work node management and information push. By classifying the strategic impact, time sensitivity, risk level and other characteristics of the nodes in detail, as well as label generation and annotation optimization based on NLP and automated algorithms, the system ensures the accuracy and timeliness of information transmission. In addition, the push information is dynamically evaluated using the timeliness impact coefficient, information entropy impact coefficient and interactivity impact coefficient, which supports the intelligent adjustment and priority optimization of information push, effectively reduces information overload, improves decision-making quality, optimizes resource allocation, and enhances project management effectiveness.

[0022] 2. The present invention significantly improves the efficiency and accuracy of information push by constructing a push priority evaluation model based on the BP neural network. First, the technology comprehensively evaluates the priority of each node information by comprehensively considering the timeliness influence coefficient of the work node, the information entropy influence coefficient of the push information, and the interactivity influence coefficient of the push information, thereby ensuring that the most urgent and complex information can be processed first. Secondly, the generation of the push information sorting table and the adjustment of the information push order enable high-priority information to be communicated in a timely manner under limited load, effectively avoiding information overload and delays. The three-color progress evaluation mechanism further optimizes the push strategy, and by classifying the status of the work nodes, ensures that the information of the red card nodes is pushed first, which promotes the control and management of the project progress. Overall, these measures not only improve the efficiency and accuracy of information processing, but also optimize resource allocation, enhance the relevance and real-time nature of information transmission, and ultimately achieve effective management and scheduling of enterprise work nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a structural schematic diagram of a method for online node management and control of enterprise-wide services based on a digital intelligence and electrical platform according to the present invention.

[0024] Figure 2 This is a structural schematic diagram of an enterprise-wide business online node management and control device based on a digital intelligence and electrical platform according to the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1, Figure 1The present invention provides a method for managing and controlling enterprise-wide business online nodes based on a digital intelligence and electrical platform, comprising the following steps:

[0027] S1, classify and refine the common work nodes of the entire enterprise, and summarize and enter the work node information.

[0028] In this embodiment, the classification and extraction of enterprise-wide common work nodes is specifically as follows:

[0029] The core of classification and refinement is to clarify the characteristics and management requirements of each work node, ensuring that different types of nodes are properly handled during the entire management and control process;

[0030] First, the work nodes must be classified according to the degree of impact of the task on the enterprise's strategic goals; the nodes that have a direct impact on the enterprise's strategic goals are classified as strategic core nodes; these nodes play a decisive role in the realization of the overall goals of the enterprise, so it is necessary to ensure that the information of these nodes has the highest priority in the system, ensuring that the management can follow up and handle it in a timely manner;

[0031] Secondly, work nodes need to be classified according to their time sensitivity. Emergency nodes are the ones that need to be processed with the highest priority because they have a strict deadline for completion. Once delayed, subsequent tasks may not be carried out on time.

[0032] Next, the classification of work nodes should also take into account their risk level; for high-risk nodes, the system must prioritize the push of relevant information; such nodes usually involve tasks that are technically difficult or may have major consequences, so once a problem is discovered, the company must take immediate action to prevent the risk from expanding or getting out of control;

[0033] In addition, the classification work should also cover the cross-departmental collaboration needs of task nodes; nodes involving collaboration among multiple departments require special attention; the successful completion of such nodes often determines the progress and quality of the entire project. Therefore, the system should ensure that information push for such nodes is prioritized to ensure smooth coordination between departments;

[0034] Finally, classification and refinement must also be based on the completion and historical performance of the nodes. For nodes with high completion that are close to completion, the system can appropriately lower the priority of their information push. For nodes with poor historical performance and low completion, the system must increase their push priority to encourage management to pay more attention and invest resources to ensure that the task is completed within the specified time.

[0035] It should be noted that in the process of node classification, in-depth analysis is required based on the different actual needs of the enterprise; the business characteristics, strategic goals, project complexity, cross-departmental collaboration needs and risk management requirements of each enterprise are different. Through a comprehensive analysis of these actual needs, the rationality and scientificity of node classification can be ensured.

[0036] S2, based on the digital and intelligent power platform, sets labels, information notes and push functions for working nodes.

[0037] In this embodiment, the setting of labels, information notes and push functions for working nodes based on the digital intelligence power integration platform is specifically as follows:

[0038] Extract key features of working nodes based on NLP and generate labels;

[0039] Classify and identify working nodes based on a predefined tag library;

[0040] The tags in the tag library include task type, priority, time sensitivity, and custom tags related to the company's specific business;

[0041] Based on automated algorithms, labels are automatically matched and assigned according to node attributes and historical data.

[0042] The information note function is based on structured data input and natural language generation technology. In work nodes, note information is usually used to record specific requirements, progress or problems of the task. In order to ensure the uniformity and traceability of information, the system uses structured data input methods, such as preset templates and options, to reduce the randomness of manual input. At the same time, the system also applies natural language generation technology to automatically generate concise note suggestions based on existing task data and progress, to assist users in filling out and improve efficiency.

[0043] The push function relies on intelligent push algorithms and real-time communication technology. The intelligent push algorithm determines the time and object of information push based on the priority rules set in advance and the real-time status of the nodes.

[0044] The algorithm uses a model based on BP neural network, which can predict and optimize the effect of information push by training a large amount of historical data; real-time communication technology ensures that the push information can be conveyed to relevant personnel immediately, which is achieved through an integrated enterprise communication platform, such as instant messaging, email or internal enterprise notification system; the system will also automatically record the receipt and response status when pushing, to ensure closed-loop management of information.

[0045] S3, obtains working node evaluation data and push information evaluation data.

[0046] In this embodiment, the working node evaluation data includes the working node timeliness influence coefficient; the push information evaluation data includes the push information information entropy influence coefficient and the push information interactivity influence coefficient.

[0047] The timeliness impact coefficient of a work node is used to evaluate the urgency of a work node and its impact on the priority of pushed information. The timeliness impact coefficient of a work node quantifies the timeliness requirements of a node by analyzing the deviation between the actual progress of the node and the scheduled schedule, combined with the node's deadline and the importance of the task. Specifically, the timeliness impact coefficient takes into account the remaining time before the node's completion deadline, the degree of progress lag, and the impact on subsequent tasks; if a node's completion deadline is approaching and the progress lag is serious, its timeliness impact coefficient is high, indicating that the push information of this node should be given priority; this coefficient ensures that the key information pushed can be communicated to relevant personnel in a timely manner, thereby effectively supporting the smooth advancement of tasks and the timely completion of projects.

[0048] Analyzing the timeliness impact coefficient of work nodes has the following advantages for analyzing and evaluating the priority of push information:

[0049] Improve task response speed: By measuring the timeliness impact coefficient of nodes, the most urgent tasks and nodes can be identified, ensuring that the push information of these nodes is processed first; this prioritization helps to speed up the response to critical tasks and reduce delays;

[0050] Optimize resource allocation: The timeliness impact coefficient helps determine which work nodes are critical to the overall project progress; prioritizing the push of information on these nodes can ensure that resources and attention are focused on the parts that are critical to project completion, thereby improving resource utilization efficiency;

[0051] Enhanced project management: Understanding the timeliness impact coefficient of nodes can provide project managers with clearer task priority sorting, helping them to track and adjust progress more effectively, and ensure that the project proceeds according to the established schedule;

[0052] Reduce risk: By prioritizing those nodes with a higher timeliness impact coefficient, the risk of delays can be reduced; this early warning mechanism can identify potential problems in a timely manner, take measures to intervene, and reduce the risk of project failure;

[0053] Improve the relevance of information delivery: The timeliness impact coefficient can ensure that the pushed information matches the actual urgency of the task, making the information delivery more in line with actual needs; this targeted push improves the relevance and practicality of information, and enhances users' attention and response to information;

[0054] Support dynamic adjustment: The timeliness impact coefficient can be updated in real time as the project progresses, thereby supporting dynamic adjustment of push strategies; as the task priority changes, the priority of push information can be adjusted in time to ensure that information push always meets current actual needs.

[0055] The specific method for obtaining the timeliness influence coefficient of the working node is as follows:

[0056] Obtain the historical key time points of each work node, including the planned start time, planned completion time, and actual completion time;

[0057] Calculate time deviation and remaining time based on historical key time points;

[0058] Build a task dependency graph based on each work node, record the predecessor and successor tasks of each work node, and use a directed graph to represent the task dependency relationship;

[0059] Determine the node influence range based on the edges and nodes in the task dependency graph and obtain the node influence weight;

[0060] Calculate the node delay impact coefficient based on the node impact weight;

[0061] Based on the delay impact coefficient of each node on the directed graph path after a specific node in the task dependency graph, each delay impact coefficient is summarized to calculate the node importance;

[0062] According to the node importance, time deviation and remaining time, the working node timeliness impact coefficient is calculated based on the preset working node timeliness impact coefficient calculation formula.

[0063] The specific calculation formula of the node importance is as follows:

[0064]

[0065] The specific method for obtaining the timeliness influence coefficient of the working node is as follows:

[0066]

[0067] In the formula, is the timeliness influence coefficient of the working node, is the time deviation, For the remaining time, is the importance of the i-th node, is the number of the subsequent path node of node i in the directed graph, p is the total number of subsequent path nodes of node i in the directed graph, is the jth node, is the node influence weight of the j-th node.

[0068] It should be noted that the time deviation indicates the degree of deviation of the actual progress of the node from the plan. When the time deviation is a positive value, it means that the node progress is lagging behind; when it is a negative value, it means that the node progress is ahead of schedule.

[0069] The information entropy impact coefficient of pushed information is an indicator that quantifies the complexity and uncertainty of the pushed information content. Information entropy is an important concept in information theory, which is used to measure the randomness and information content of information. In the pushed information, the information entropy impact coefficient reflects the richness and information content of the information by calculating the entropy value of the information content. Specifically, the higher the information entropy, the more complex the information content, the greater the uncertainty, and the higher the degree of processing and attention required. This coefficient helps determine which information should be pushed to relevant personnel first due to its higher uncertainty and information content, thereby improving the efficiency and accuracy of information transmission.

[0070] Analyzing the information entropy impact coefficient of push information has the following advantages for analyzing and evaluating the priority of push information:

[0071] Quantifying information complexity: The information entropy impact coefficient can quantify the complexity and amount of information pushed; high information entropy indicates that the information content is complex and has high uncertainty, and needs to be processed first to ensure a comprehensive understanding of the information; this helps identify the content that needs to be focused on, thereby improving processing efficiency;

[0072] Improve the accuracy of information processing: By measuring information entropy, it is possible to determine which pushed information contains more valid data and detailed content; information with high information entropy may contain key details and implicit information. Prioritizing the push of such information can reduce omissions and misunderstandings and improve the accuracy of information processing;

[0073] Optimize information priority sorting: The information entropy impact coefficient sets a priority sorting standard for push information based on content complexity; content with high information entropy is prioritized in sorting, ensuring that complex and important information can be conveyed to relevant personnel in the shortest time, improving the management efficiency of the overall information flow;

[0074] Enhance the relevance of information delivery: The information entropy impact coefficient helps identify information that requires more attention due to its complexity and large data volume; this method ensures that the information pushed not only meets actual needs, but also can meet users' needs for information in a targeted manner, thereby improving the relevance of information delivery;

[0075] Support dynamic priority adjustment: In a dynamic environment, the complexity and importance of information may change; the information entropy impact coefficient can reflect these changes in real time, support dynamic adjustment of the priority of pushed information according to actual conditions, and ensure that information push always meets the latest business needs;

[0076] Reduce the risk of information overload: By giving priority to pushing content with high information entropy, you can effectively reduce the interference of low-priority, repetitive information and reduce the risk of information overload; this can help users focus on the most valuable and most important information, thereby improving the quality of decision-making.

[0077] The specific method for obtaining the information entropy influence coefficient of the push information is as follows:

[0078] Collect all the push text data of the information to be pushed and simplify the text data;

[0079] Calculate the push word frequency probability of the push text data based on a preset word frequency model;

[0080] Calculate the information entropy of the pushed text data based on the pushed word frequency probability;

[0081] The information entropy of the pushed text data is combined with the preset enterprise special word weights to calculate the information entropy influence coefficient of the pushed information.

[0082] The specific calculation formula of the preset word frequency model is as follows:

[0083]

[0084] The specific calculation formula of the push information entropy influence coefficient is as follows:

[0085]

[0086] In the formula, is the probability of the word in the kth push information, M is the total number of words in the push information, is the vocabulary probability, is the information entropy influence coefficient of the pushed information, It is the weight of special words for enterprises.

[0087] The interactive impact coefficient of push information is an indicator that measures the frequency and depth of interaction between push information and recipients; this coefficient reflects the actual influence and interactive value of information by analyzing the recipient's feedback, response and further interactive behavior (such as comments, likes, sharing, etc.) to the information. A higher interactive impact coefficient indicates that the information has triggered more user participation and interaction, which means that it is more important and urgent. Therefore, the interactive impact coefficient of push information helps prioritize the information that can effectively trigger user actions, thereby improving the effectiveness and response speed of information delivery.

[0088] Analyzing the interaction impact coefficient of push information has the following advantages for analyzing and evaluating the priority of push information:

[0089] Improve interaction effect: The interaction impact coefficient can identify the most attractive and influential information to users by measuring the user feedback and interaction volume triggered by the information. Prioritizing the push of highly interactive information helps to improve the participation and actual application effect of the information.

[0090] Enhance information relevance: High interactivity usually indicates that information is more relevant and useful to users. By analyzing the interactivity, we can prioritize the information that is more likely to attract users' attention, thereby ensuring the relevance and effectiveness of information delivery.

[0091] Optimize resource allocation: The interaction impact coefficient can help identify which information can effectively trigger user responses and actions. In this way, push resources can be reasonably allocated, and more energy can be focused on information that can generate high user interaction, thereby improving resource utilization efficiency.

[0092] Real-time priority adjustment: The interaction coefficient provides a basis for dynamic priority adjustment. As user behavior changes, the interactivity of information will also change. Timely updating of the interaction coefficient can dynamically adjust the push priority to ensure the real-time and flexibility of the push strategy.

[0093] Improve decision-making quality: By comprehensively analyzing the interactivity of information, the importance and urgency of information can be more accurately assessed. Using interactivity as one of the evaluation criteria can improve the accuracy of data-driven decision-making and ensure that the most valuable information for the business or users is pushed first.

[0094] Reduce information redundancy: Analyzing the interactivity of information can help identify which information has been widely interacted with, thereby reducing the push of repeated or low-interaction information, reducing the risk of information redundancy, and improving the clarity and pertinence of information delivery.

[0095] The specific method for obtaining the push information interaction influence coefficient is as follows:

[0096] Based on the historical interaction event types, an information interaction set is obtained, wherein the information interaction set includes various push information and interaction events and event results thereof;

[0097] Assigning preset interaction scores to various types of interaction events in the information interaction set;

[0098] A regression model is constructed based on the information interaction set and the corresponding interaction score to generate the push information interaction influence coefficient.

[0099] The specific calculation formula of the push information interaction influence coefficient is as follows:

[0100]

[0101] In the formula, is the interaction influence coefficient of push information, … is the preset interaction score corresponding to the interaction event, … is the proportion of interaction events in all interaction events, is the type of interaction event, n is the number of the interaction event, and e is a natural number.

[0102] This embodiment significantly improves the efficiency of work node management and information push by classifying and refining common work nodes for the entire enterprise, and performing intelligent label setting, information annotation and push function configuration on the Digital Intelligence and Power Integration Platform. By classifying the strategic impact, time sensitivity, risk level and other characteristics of the nodes in detail, as well as label generation and annotation optimization based on NLP and automated algorithms, the system ensures the accuracy and timeliness of information transmission. In addition, the push information is dynamically evaluated using the timeliness impact coefficient, information entropy impact coefficient and interactivity impact coefficient, which supports the intelligent adjustment and priority optimization of information push, effectively reduces information overload, improves decision-making quality, optimizes resource allocation, and enhances project management effectiveness.

[0103] Embodiment 2, S4, builds a push priority evaluation model based on the bp neural network according to the working node evaluation data and the push information evaluation data, and generates the push information priority.

[0104] In this embodiment, a push priority evaluation model is constructed based on the bp neural network according to the working node evaluation data and the push information evaluation data to generate the push information priority, specifically:

[0105] The acquired working node timeliness influence coefficient, push information entropy influence coefficient and push information interactivity influence coefficient are used to establish a push priority evaluation model to generate push information priority;

[0106] The calculation formula of the push information priority is as follows:

[0107]

[0108] In the formula, TS is the priority of push information, is the preset proportional coefficient of the working node timeliness impact coefficient, is the information entropy influence coefficient of the pushed information, It is the preset proportional coefficient of the interaction influence coefficient of the pushed information. is the timeliness influence coefficient of the working node, is the information entropy influence coefficient of the pushed information, It is the interaction influence coefficient of pushed information.

[0109] S5, generating a push information sorting table according to the push information priority, and pushing the working node information based on the push information sorting table.

[0110] In this embodiment, the push information sorting table is specifically:

[0111] The push information of each node is sorted in descending order based on the corresponding push information priority, and the working node information is pushed from top to bottom under limited information load according to the push information sorting table.

[0112] S6, obtain the enterprise work plan and establish a three-color progress evaluation mechanism, where the three colors include green, yellow and red.

[0113] In this embodiment, the enterprise work plan is obtained and a three-color progress evaluation mechanism is established, specifically:

[0114] Establish a three-color evaluation mechanism for work progress, where on-time completion is recorded as a green card, overdue completion is recorded as a yellow card, and overdue again after being urged is recorded as a red card.

[0115] S7, adjust the order of pushing work node information according to the three-color progress evaluation mechanism.

[0116] In this embodiment, the order of pushing the work node information is adjusted according to the three-color progress evaluation mechanism, specifically:

[0117] Adjust the order of information push according to the priority of each node; give priority to pushing red card node information, followed by yellow card node information, and finally green card node information. The order of information push is executed according to the push information sorting table based on the three-color evaluation mechanism.

[0118] This embodiment significantly improves the efficiency and accuracy of information push by constructing a push priority evaluation model based on the BP neural network. First, the technology comprehensively evaluates the priority of each node information by comprehensively considering the timeliness influence coefficient of the work node, the information entropy influence coefficient of the push information, and the interaction influence coefficient of the push information, thereby ensuring that the most urgent and complex information can be processed first. Secondly, the generation of the push information sorting table and the adjustment of the information push order enable high-priority information to be conveyed in a timely manner under limited load, effectively avoiding information overload and delay. The three-color progress evaluation mechanism further optimizes the push strategy, and by classifying the status of the work node, ensures that the information of the red card node is pushed first, which promotes the control and management of the project progress. Overall, these measures not only improve the efficiency and accuracy of information processing, but also optimize resource allocation, enhance the relevance and real-time nature of information transmission, and ultimately achieve effective management and scheduling of enterprise work nodes.

[0119] Embodiment 3, Figure 2 It is an online node management and control method for the entire enterprise's business based on the digital and intelligent integrated power platform, including a node division module, an information push module, a push detailed analysis module, an information priority analysis module, an information sorting module, a three-color evaluation module and a secondary push module.

[0120] The node division module is used to classify and refine the common work nodes of the entire enterprise and summarize and enter the work node information;

[0121] The information push module is used to set labels, information notes and push functions for working nodes based on the digital and intelligent power platform;

[0122] Push detailed analysis module, used to obtain work node evaluation data and push information evaluation data;

[0123] The information priority analysis module is used to build a push priority evaluation model based on the BP neural network according to the work node evaluation data and the push information evaluation data, and generate the push information priority;

[0124] An information sorting module is used to generate a push information sorting table according to the push information priority, and push the work node information based on the push information sorting table;

[0125] A three-color evaluation module is used to obtain the enterprise work plan and establish a three-color progress evaluation mechanism, wherein the three colors include green, yellow and red;

[0126] The secondary push module is used to adjust the push order of work node information according to the three-color progress evaluation mechanism.

[0127] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0128] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0129] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0130] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0131] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0132] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The enterprise-wide online node management and control method based on the digital intelligence power platform is characterized by: The steps include: Classify and refine common work nodes across the enterprise, and summarize and enter work node information; Based on the Digital Intelligence Power Integration Platform, set labels, information notes and push functions for working nodes; Obtain work node evaluation data and push information evaluation data; The working node evaluation data includes a working node timeliness impact coefficient; The specific method for obtaining the timeliness influence coefficient of the working node is as follows: Obtain the historical key time points of each work node, including the planned start time, planned completion time, and actual completion time; Calculate time deviation and remaining time based on historical key time points; Build a task dependency graph based on each work node, record the predecessor and successor tasks of each work node, and use a directed graph to represent the task dependency relationship; Determine the node influence range based on the edges and nodes in the task dependency graph and obtain the node influence weight; Calculate the node delay impact coefficient based on the node impact weight; Based on the delay impact coefficient of each node on the directed graph path after a specific node in the task dependency graph, each delay impact coefficient is summarized to calculate the node importance; According to the node importance, time deviation and remaining time, the work node timeliness impact coefficient is calculated based on the preset work node timeliness impact coefficient calculation formula; The specific calculation formula of the node importance is as follows: The specific calculation formula of the working node timeliness influence coefficient is as follows: In the formula, is the timeliness impact coefficient of the working node, is the time deviation, For the remaining time, is the importance of the i-th node, is the number of the subsequent path node of node i in the directed graph, p is the total number of subsequent path nodes of node i in the directed graph, is the jth node, is the node influence weight of the j-th node; According to the work node evaluation data and the push information evaluation data, a push priority evaluation model is built based on the bp neural network to generate the push information priority; Generate a push information sorting table according to the push information priority, and push the work node information based on the push information sorting table; Obtain the enterprise work plan and establish a three-color progress evaluation mechanism, the three colors include green, yellow and red; Adjust the order of pushing work node information according to the three-color progress evaluation mechanism.

2. The method for managing and controlling enterprise-wide business online nodes based on the digital intelligence power integration platform according to claim 1 is characterized in that: The digital intelligence power integration platform is based on setting labels, information notes and push functions for working nodes, specifically: Extract key features of working nodes based on NLP and generate labels; Classify and identify working nodes based on a predefined tag library; The tags in the tag library include task type, priority, time sensitivity, and custom tags related to the company's specific business; Based on automated algorithms, labels are automatically matched and assigned according to node attributes and historical data.

3. The method for managing and controlling enterprise-wide business online nodes based on the digital intelligence power integration platform according to claim 2 is characterized in that: The push information evaluation data includes a push information entropy influence coefficient and a push information interactivity influence coefficient.

4. The method for managing and controlling enterprise-wide business online nodes based on the digital intelligence power integration platform according to claim 3 is characterized in that: The specific method for obtaining the information entropy influence coefficient of the push information is as follows: Collect all the push text data of the information to be pushed and simplify the text data; Calculate the push word frequency probability of the push text data based on a preset word frequency model; Calculate the information entropy of the pushed text data based on the pushed word frequency probability; The information entropy of the pushed text data is combined with the preset enterprise special word weights to calculate the information entropy influence coefficient of the pushed information.

5. The method for managing and controlling enterprise-wide business online nodes based on the digital intelligence power integration platform according to claim 4 is characterized in that: The specific method for obtaining the push information interaction influence coefficient is as follows: Based on the historical interaction event types, an information interaction set is obtained, wherein the information interaction set includes various push information and interaction events and event results thereof; Assigning preset interaction scores to various types of interaction events in the information interaction set; A regression model is constructed based on the information interaction set and the corresponding interaction score to generate the push information interaction influence coefficient.

6. The method for managing and controlling enterprise-wide business online nodes based on the digital intelligence power integration platform according to claim 5 is characterized in that: The specific calculation formula of the preset word frequency model is as follows: The specific calculation formula of the push information entropy influence coefficient is as follows: In the formula, is the probability of the word in the kth push information, M is the total number of words in the push information, is the vocabulary probability, is the information entropy influence coefficient of the pushed information, It is the weight of special words for enterprises.

7. A device using the method for managing and controlling enterprise-wide business online nodes based on a digital intelligence and electrical platform as described in any one of claims 1 to 6, characterized in that: It includes node division module, information push module, push detailed analysis module, information priority analysis module, information sorting module, three-color evaluation module and secondary push module; The node division module is used to classify and refine the common work nodes of the entire enterprise and summarize and enter the work node information; The information push module is used to set labels, information notes and push functions for working nodes based on the digital and intelligent power platform; Push detailed analysis module, used to obtain work node evaluation data and push information evaluation data; The information priority analysis module is used to build a push priority evaluation model based on the BP neural network according to the work node evaluation data and the push information evaluation data, and generate the push information priority; An information sorting module is used to generate a push information sorting table according to the push information priority, and push the work node information based on the push information sorting table; A three-color evaluation module is used to obtain the enterprise work plan and establish a three-color progress evaluation mechanism, wherein the three colors include green, yellow and red; The secondary push module is used to adjust the push order of work node information according to the three-color progress evaluation mechanism.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the method for online node management and control of the entire enterprise's business based on the digital and intelligent power integration platform as described in any one of claims 1 to 6.

Images