WBS list intelligent pushing and performance tracking method based on experience case correlation

Abstract

The application provides a WBS list intelligent pushing and performance tracking method based on experience system correlation, relates to the technical field of project management and intelligent algorithm, and comprises the following steps: constructing a multilevel three-dimensional WBS correlation library, building a correlation system of business blocks and WBS nodes based on unified coding rules, establishing a three-dimensional correlation relationship among resources, WBS and project scenarios, inputting multiple types of resources and binding WBS node information and correlation attributes, and realizing the configurability of correlation relationship and resource priority and the dynamic updating of the correlation library; the application solves the problems of WBS correlation resource fragmentation, low correlation degree and update lag in the prior art, realizes the deep binding of resources, WBS and project scenarios through a multilevel three-dimensional WBS correlation library construction mechanism, combines correlation strength quantitative calculation and dynamic updating capability, makes resource reuse more accurate and data support more solid, improves resource utilization efficiency, shortens resource retrieval time, and improves resource matching accuracy.

Description

Technical Field

[0001] This invention relates to the fields of project management and intelligent algorithm technology, and in particular to a method for intelligent push and performance tracking of WBS lists based on experience-based correlation. Background Technology

[0002] In current project management, Work Breakdown Structure (WBS) is widely used as a core tool to achieve refined management through hierarchical decomposition of project tasks. Current mainstream methods mostly adopt a single-dimensional WBS association model, relying on coding rules to build the correspondence between tasks and resources. Some systems build a basic association library, inputting historical cases, solution templates, and other resources to assist in checklist creation and task execution. Meanwhile, current checklist generation largely relies on manually selecting general templates and adjusting them according to project attributes to form project-specific checklists. Project performance tracking mainly focuses on task completion status statistics, with progress monitoring achieved through manual feedback or simple system records. In existing technologies, the WBS association mode has a single dimension, insufficient depth of association between resources and WBS nodes and project scenarios, fragmented resource distribution, lack of quantitative assessment of association strength, and lagging updates to the association database, making it impossible to synchronize new experience and technical standards in real time, resulting in weak data support for list generation. Furthermore, the list generation algorithm lacks a multi-factor collaborative screening mechanism, relying solely on single project attribute matching, and cannot combine historical experience weights to achieve personalized hierarchical list generation. Manual adjustments are costly and inefficient, making it difficult to balance standardization and personalization needs. Simultaneously, knowledge and task push are passive, requiring executors to actively search for required specifications and cases, which easily leads to untimely and incomplete information acquisition, increasing the error rate of task execution. In addition, project performance tracking is limited to alarms for existing problems, lacking forward-looking risk warning capabilities, unable to predict potential risks through micro-task data, and failing to support management decision-making. Finally, business plans are disconnected from knowledge accumulation; there are no mandatory knowledge association requirements after list task decomposition, and lessons learned cannot be effectively transformed into prevention and control basis for subsequent projects, resulting in a missing management loop. Therefore, this invention proposes an intelligent WBS list push and performance tracking method based on experience-based series association to solve the problems existing in the prior art. Summary of the Invention

[0003] To address the aforementioned issues, this invention proposes an intelligent push and performance tracking method for WBS lists based on empirical series association. This method solves the problems of fragmented WBS associated resources, low relevance, and delayed updates in existing technologies. Through a multi-level three-dimensional WBS association library construction mechanism, it achieves deep binding of resources, WBS, and project scenarios. Combined with quantitative calculation of association strength and dynamic update capabilities, it makes resource reuse more accurate, data support more robust, significantly improves resource utilization efficiency, shortens resource retrieval time, and enhances resource matching accuracy.

[0004] To achieve the objectives of this invention, the invention is implemented through the following technical solution: a WBS list intelligent push and performance tracking method based on experience-based correlation, comprising the following steps: S1: Construct a multi-level three-dimensional WBS association library, build an association system between business segments and WBS nodes based on unified coding rules, establish a three-dimensional association relationship between resources, WBS and project scenarios, input multiple types of resources and bind WBS node information and association attributes, realize the configurability of association relationships and resource priorities and dynamic updates of the association library. S2: Based on a dual-factor intelligent algorithm of attribute matching and weight assignment, combined with a general list library and a three-dimensional WBS association library, it generates a hierarchical list adapted to the project, and provides channels for secondary refinement and manual adjustment according to professional and time dimensions. S3: Build an integrated intelligent push engine for knowledge, requirements, and responsible persons for task flows, bind the list of tasks with the project plan to form a task flow, and push tasks and related knowledge packages and requirement packages to the responsible persons according to the personalized timing and content granularity. S4: Based on the list of fulfillment status, build a real-time monitoring and forward-looking early warning model for project health, collect micro-data on task fulfillment, analyze task completion trends and problem characteristics, and realize forward-looking early warning of potential project risks and linkage with the main fulfillment plan nodes; S5: Based on the completed data of the checklist, the business plan is intelligently split and the responsibility is bound, generating two types of core business plans and configuring the responsibility allocation mechanism, self-inspection process and evaluation feedback mechanism to form a closed loop of knowledge accumulation.

[0005] Further improvements are made in the following: In S1, the unified coding rule is a four-level coding rule, and the coding format is: XX-XX-XX-XX, where the first level is the business segment code (2 digits), the second level is the WBS level code (2 digits), the third level is the professional type code (2 digits), and the fourth level is the node sequence number code (2 digits); the business segments include project planning, scheme design, construction execution, quality inspection, safety control, progress coordination, acceptance and delivery, and operation and maintenance review, and each business segment corresponds to several levels of WBS nodes; the association attribute includes the association strength label, and the association strength is calculated by formula (1): (1) Where: Sij is the association strength between the i-th WBS node and the j-th resource, with a value ranging from [0,1], and the larger the value, the higher the association strength; α is the resource reuse weight coefficient, with a value ranging from [0.3,0.5]; Rij is the historical reuse rate of the j-th resource in the i-th type of WBS node, that is, the ratio of the number of times the resource is associated with the same type of WBS node in historical projects to the total number of times the same type of WBS node is associated with resources; β is the time decay weight coefficient, with a value ranging from [0.2,0.4]; Tj is the time effectiveness coefficient of the j-th resource. , where is the current time, resource update time, and resource validity period, and is 0 when the result is negative; γ is the scene matching weight coefficient, with a value range of [0.2, 0.3]; Fij is the matching degree between the j-th resource and the project scene corresponding to the i-th WBS node, with a value range of [0, 1], which is determined according to the overlap between the resource's applicable scene and the current project scene.

[0006] Further improvements are made in the following aspects: In S1, the various types of resources include historical experience cases, solution templates, technical standards, acceptance specifications, lessons learned from failures, tool lists, personnel configuration plans, and cost budget templates; the dynamic update is achieved by real-time monitoring of the new resource entry port, technical standard update channels, and project archive data. New resources automatically trigger association strength calculations and are updated to the corresponding WBS node. At the same time, it supports administrators to manually review the validity of new resources.

[0007] The further improvement lies in the following steps of the dual-factor intelligent algorithm for attribute matching and weight assignment in S2: S21: Attribute matching stage, extract project attribute parameters, including professional field, project scale, construction difficulty, schedule requirements, and quality level, and filter basic nodes from the general list library based on attribute similarity formula (2): (2) Where: Pk is the attribute similarity between the k-th general list node and the current project, with a value range of [0,1], and the smaller the value, the higher the matching degree; n is the number of project attribute parameters, n≥5; Wm is the weight of the m-th attribute parameter. The weighting of professional field and construction difficulty shall not be less than 0.5; Xkm is the m-th attribute parameter value corresponding to the k-th general list node; Xpm is the m-th attribute parameter value of the current project; S22: In the weight assignment stage, the empirical weight is calculated by combining historical project data. The empirical weight is calculated using formula (3): (3) Where: Wek is the experience weight of the k-th list node, with a value range of [0,1]. The larger the value, the higher the reference value of the corresponding resource or list node; δ is the similarity weight coefficient, with a value range of [0.4,0.6]; Spk is the overall similarity between the historical project and the current project, calculated based on the weighted average of multiple attribute parameters; Ehk is the performance effect coefficient of the k-th list node in the historical project, with a value range of [0,1], which is comprehensively evaluated based on the project schedule compliance rate, quality pass rate, and safety accident incidence rate. S23: Based on the attribute matching results and experience weights, break down and refine the special item list to form the final graded list.

[0008] Further improvements are made in S3, where personalized configuration includes push timing configuration and content granularity configuration: push timing includes 12-24 hours before the task plan starts, key nodes during task execution, task delay warnings, and before task acceptance; content granularity is divided into basic, professional, and precise levels according to the importance level of the task. The basic level only pushes the core task and acceptance criteria, the professional level adds technical specifications and solution templates, and the precise level additionally pushes historical cases and lessons learned from failures; the knowledge package includes mandatory reference specifications, relevant lessons learned from failures, available solution templates, and tool operation guides, and the requirements package includes acceptance criteria, filling format, time limit requirements, and quality control points.

[0009] Further improvements are made in S4, specifically the real-time monitoring and proactive early warning model for project health, which includes the following steps: S41: Collect micro-level data on task performance, including task completion status, completion quality evaluation, on-site anomaly information, and feedback from responsible persons; S42: Calculate the project health index and risk warning index. The risk warning index is calculated using formula (4): (4) Where: Rp is the project risk warning index, with a value range of [0,10]. A value ≥ 6 triggers a warning, and a value ≥ 8 triggers a high-level warning; m is the number of highly relevant task groups; Ci is the importance coefficient of the i-th task group. The milestone task group coefficient is no less than 0.3; Di is the delay risk coefficient of the i-th task group, with a value range of [0,1], determined according to the ratio of the average delay time of the task group to the planned time; Li is the impact range coefficient of the i-th task group, with a value range of [1,3], graded according to the number of subsequent tasks affected; Ki is the problem frequency coefficient of the i-th task group, with a value range of [0,1], which is the ratio of the number of high-frequency problems to the total number of tasks in the task group; Mi is the problem severity coefficient of the i-th task group, with a value range of [1,3], graded according to the impact of the problem on quality, safety, and schedule; S43: Trigger corresponding warnings based on the risk warning index and link them with the main project performance plan nodes to update the node completion probability.

[0010] Further improvements are made in the following ways: In S5, the two types of core business plans are the solution plan and the lesson-taking and risk point plan; the solution plan is associated with the corresponding WBS node, and it is mandatory to enter the standard specification number, reference lessons-taking and risk point, the person responsible for the solution preparation, and the review node. The system automatically fills in the standard specifications and lessons-taking and risk point associated with the corresponding WBS node as basic materials; the lesson-taking and risk point plan automatically generates a risk point analysis report based on the completed data of the list, which clarifies the risk point type, frequency of occurrence, degree of impact, and rectification measures; the responsibility allocation mechanism supports automatic allocation and self-acceptance. Automatic allocation is based on role permissions, historical responsible experience, and current workload to determine task priority. The task priority calculation formula (5) is as follows: (5) Where: Ptq is the priority of the q-th task, ranging from [1,5], with higher values ​​indicating higher priority; ε is the task importance weight coefficient, ranging from [0.4,0.6]; Itq is the importance level of the q-th task itself, ranging from [1,5]; ζ is the user's historical experience weight coefficient, ranging from [0.2,0.3]; Huq is the user's historical experience value for the q-th type of task, ranging from [1,5], which is a weighted value of the quantity and quality of similar tasks handled in the past; η is the user's current load weight coefficient, ranging from [0.2,0.3]; Luq is the user's current load coefficient when executing the q-th task, ranging from [1,5], with higher values ​​indicating lower load; ε+ζ+η=1.

[0011] Further improvements are made in S5, where the self-inspection process requires the responsible person to upload execution evidence via the APP after completing the task. The system automatically compares the evidence with the acceptance standards in the requirement package, generates a preliminary evaluation, and then the final solution quality score is formed after review by the auditor. The score results are synchronized to the three-dimensional WBS association library to update the association strength and experience weight of the corresponding resources.

[0012] Further improvements are made in S2, where the hierarchical list includes a basic list, a special list, and a detailed list. The basic list is a core node list filtered after attribute matching. The special list includes a quality inspection station inspection list, a milestone node list, a critical and major project list, and a cross-operation coordination list. The detailed list is a list split according to professional and time dimensions.

[0013] Further improvements include data statistics and debriefing: real-time statistics on list generation efficiency, task completion rate, risk warning accuracy, knowledge reuse rate, business plan preparation time, etc., to form a debriefing report, providing data support for the optimization of the 3D WBS related library, algorithm parameter adjustment, and push strategy optimization.

[0014] The beneficial effects of this invention are as follows: 1. This invention addresses the problems of fragmented, low-relevance, and delayed updates of WBS-related resources in existing technologies. Through a multi-level three-dimensional WBS association library construction mechanism, it achieves deep binding of resources, WBS, and project scenarios. Combined with quantitative calculation of association strength and dynamic update capabilities, it makes resource reuse more accurate, data support more robust, significantly improves resource utilization efficiency, shortens resource retrieval time, and improves resource matching accuracy.

[0015] 2. This invention breaks through the limitations of traditional single-dimensional list generation algorithms. The dual-factor intelligent algorithm of attribute matching + weight assignment takes into account both the standardization and personalization needs of the list. Through multi-attribute similarity calculation and empirical weight quantification, it automatically generates hierarchical lists and supports secondary refinement, effectively reducing the cost of manual compilation. Compared with existing methods, it reduces the list compilation time and improves the adaptability of the list. At the same time, by introducing algorithm formulas, the list generation process becomes more scientific and repeatable.

[0016] 3. This invention uses an integrated intelligent push engine that combines knowledge, requirements, and responsible persons, along with personalized push timing and content granularity, to ensure that executors receive complete execution information at the right time. This effectively reduces the error rate caused by missing information. In practice, the task execution error rate has been reduced from 15%-20% in existing technologies to below 5%, improving the first-time pass rate of task acceptance.

[0017] 4. This invention upgrades project performance management from post-event remediation to proactive early warning. Based on micro-data of the performance list, it builds an early warning model that can not only alert to delayed tasks, but also predict potential milestone delays, quality and safety risks. It links with the main performance plan nodes to provide decision support, enabling project risk response time to be advanced by 24-48 hours and improving the success rate of risk control.

[0018] 5. This invention constructs a business system of task execution, knowledge accumulation, and closed-loop management. Through intelligent decomposition of business plans based on checklist operations and responsibility binding technology, it forces the association between knowledge and tasks. Combined with self-inspection processes and evaluation feedback mechanisms, it achieves effective accumulation and reuse of experience and lessons learned, promotes the upgrade of project management from task execution orientation to knowledge accumulation orientation, and reduces the time for business plan preparation, thereby significantly improving management efficiency. Attached Figure Description

[0019] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0020] To enhance understanding of the present invention, the present invention will be further described in detail below with reference to embodiments. These embodiments are only used to explain the present invention and do not constitute a limitation on the scope of protection of the present invention.

[0021] Example 1 according to Figure 1 As shown, this embodiment proposes an intelligent push and performance tracking method for WBS list based on experience series association, which is applied to a large blast furnace construction project in the metallurgical industry. The project's professional field is metallurgical construction, and the scale is a blast furnace with an annual output of 3 million tons. The construction is difficult and includes multiple critical engineering nodes (blast furnace foundation pouring, furnace body hoisting, and hot blast stove installation).

[0022] S1: A three-dimensional WBS (Worksheet on Structure) relational database is constructed using a four-level coding rule. The first-level codes 01-08 correspond to eight major business segments. Under the construction execution segment (code 03), the second-level code 02 corresponds to furnace installation, the third-level code 01 corresponds to mechanical engineering, and the fourth-level codes 01-10 correspond to various nodes in furnace hoisting. Input resources include historical cases of blast furnace hoisting (over 30), GB50205-2020 "Standard for Acceptance of Construction Quality of Steel Structures", lessons learned from hoisting failures (5 cases), and other relevant information. The association strength Sij between each resource and the hoisting node is calculated using formula (1), where α=0.4, β=0.3, γ=0.3, and for a certain historical hoisting case (resource j), Rij=0.8, Tj=0.9 (updated 3 months from the current time, valid for 1 year), and Fij=0.95 (adapted to large blast furnace scenarios). The calculated Sij=0.4×0.8+0.3×0.9+0.3×0.95=0.855, indicating a high association strength, and is therefore prioritized for push.

[0023] S2: Extract project attributes and filter the basic list using formula (2), n=5 (professional, scale, difficulty, construction period, quality). In Wm, the weight of professional is 0.3, the weight of construction difficulty is 0.25, and the weight of other attributes is 0.15. Combine with historical data of similar blast furnace projects, calculate the experience weight Wek (δ=0.5, Spk=0.88, Ehk=0.92) using formula (3), and get Wek=0.5×0.88+0.5×0.92=0.9. Split the special list (list of critical and major projects, list of milestones), refine it according to mechanical profession and weekly dimension, and form a weekly progress list for furnace body hoisting.

[0024] S3: Configure the push timing to be 24 hours before hoisting and key processes during hoisting (fixing of hoisting points, lifting, and positioning), with the content granularity set to precision level; push knowledge packages (blast furnace hoisting cases, lessons learned from failures, GB50205 standard) and requirement packages (hoisting acceptance standards, test data reporting formats) to the person in charge of hoisting.

[0025] S4: Collect data from each hoisting node and calculate the risk warning index Rp (m=3 highly correlated task groups, Ci=0.4, Di=0.1, Li=2, Ki=0.05, Mi=1) using formula (4). Obtain the contribution of other task groups and no warning is given.

[0026] S5: Split into a hoisting scheme plan (associated with node 03-02-01-02, filled with GB50205 standard) and a risk point plan (early warning of hoisting deformation risk); calculate the task priority Ptq (ε=0.5, Itq=5, ζ=0.2, Huq=4.8, η=0.3, Luq=4.5) using formula (5), and get Ptq=0.5×5+0.2×4.8+0.3×4.5=4.81, with a priority level of 5; after completion, upload hoisting photos and test data, the system scores 8.5 points, and synchronously update the association strength Sij of the associated library resources.

[0027] Example 2 according to Figure 1 As shown, this embodiment proposes a WBS list intelligent push and performance tracking method based on experience series association, which is applied to the intelligent transformation project of a mechanical manufacturing workshop. The professional field is mechanical + automation, the scale is 10,000㎡ workshop, the construction difficulty is moderate, the construction period is 6 months, including electrical wiring, equipment installation, system debugging and other nodes.

[0028] In the three-dimensional WBS associated library, the associated resources of the automation debugging section (code 03-04-02) include PLC debugging cases, GB / T50055-2011 "General Electrical Equipment Power Distribution Design Specification", and lessons learned from debugging failures (program conflicts, unstable signals), etc.; the association strength Sij between the PLC debugging cases and the debugging nodes is calculated by formula (1) as 0.4×0.85+0.3×0.9+0.3×0.8=0.85.

[0029] During the list generation phase, the basic list (nodes with attribute similarity Pk≤0.2) is matched using formula (2), and the special lists (automation system debugging list and electrical acceptance list) are split; the experience weight Wek=0.5×0.82+0.5×0.88=0.85, and high-weight debugging cases are given priority. The push engine pushes precise content 18 hours before debugging, including PLC debugging steps, signal detection standards, and historical program conflict cases.

[0030] During the performance tracking, debugging data was collected, the risk warning index Rp=3.2, and there was no warning. After the business plan was split, the task priority Ptq was calculated by formula (5) and the responsible person was assigned. Ptq corresponds to priority level 4. After completion, the debugging record was uploaded, the system score was 9.0 points, and the reuse rate of the associated library resources was updated (corresponding to the calculation basis of Rij).

[0031] Example 3 according to Figure 1 As shown in the figure, this embodiment proposes a WBS list intelligent push and performance tracking method based on experience series association, which is applied to a building deep foundation pit support project. The professional field is civil engineering, the scale is a foundation pit with a depth of 15m, the construction difficulty is high, it is a high-risk project, and safety risks need to be strictly controlled.

[0032] In the 3D WBS association library, the deep foundation pit node association resources under the safety management and control module (code 05) include deep foundation pit support scheme templates, JGJ120-2012 "Technical Specification for Foundation Pit Support", foundation pit collapse lessons and cases, etc.; the association strength Sij=0.4×0.9+0.3×0.85+0.3×0.95=0.89.

[0033] When the list is generated, the special list mainly includes the list of critical and major projects and the safety inspection list, with an experience weight of Wek=0.5×0.86+0.5×0.8=0.83; the push timing is configured to 24 hours before support construction and 1 hour before construction every day, and the content includes the provisions of the regulations, collapse cases and support testing requirements.

[0034] During contract performance tracking, an abnormal slope displacement occurred at a certain node. Data was collected and the risk warning index Rp=6.8, triggering a medium-level warning and linking the milestone node to adjust the construction plan. After the business plan was broken down, the person in charge uploaded support photos and displacement detection data. The system scored 7.8 points and the correlation strength Sij of the lesson case was updated simultaneously.

[0035] Example 4 according to Figure 1 As shown, this embodiment proposes an intelligent push and performance tracking method for WBS list based on experience series association, which is applied to equipment maintenance projects in the chemical industry. The professional field is chemical machinery, the scale is the maintenance of 10 reactors, the construction period is 15 days, and it is necessary to balance maintenance quality and production progress.

[0036] In the 3D WBS associated library, the associated resources of the Operation and Maintenance Review section (code 08) include reactor overhaul cases, HG20580-2011 "Basic Specifications for Design of Steel Chemical Containers", overhaul progress coordination plan, etc.; the associated strength Sij=0.4×0.82+0.3×0.88+0.3×0.8=0.83.

[0037] When the checklist is generated, it is broken down into daily maintenance checklists based on time, and special checklists include equipment acceptance checklists and progress coordination checklists; the experience weight Wek = 0.5 × 0.78 + 0.5 × 0.85 = 0.815. The push engine pushes professional-level content before the start of each day's work, including the day's maintenance steps, acceptance standards, and progress coordination requirements.

[0038] During performance tracking, the risk warning index Rp=2.5, with no warning; after the business plan is broken down, the responsible person takes on the task, uploads the maintenance record after completion, the system score is 8.2 points, and updates the reuse rate (corresponding to Rij) and time validity coefficient (corresponding to Tj) of the associated library resources.

[0039] Example 5 according to Figure 1 As shown, this embodiment proposes an intelligent push and performance tracking method for WBS inventory based on experience series association. It is applied to a substation construction project in the power industry, with the professional field being electrical engineering, the scale being a 220kV substation, and the construction difficulty being moderate, including nodes such as transformer installation, cable laying, and secondary circuit commissioning.

[0040] In the 3D WBS associated library, the associated resources of the electrical professional node in the construction execution section (code 03) include transformer installation cases, GB50217-2018 "Design Standard for Cables in Power Engineering", lessons learned from secondary circuit commissioning failures, etc.; the associated strength Sij=0.4×0.88+0.3×0.92+0.3×0.85=0.879.

[0041] When the list is generated, the special list includes the electrical equipment quality inspection list and the milestone (transformer placement) list, and is further refined into primary circuit and secondary circuit lists according to electrical specialties; the experience weight Wek = 0.5 × 0.85 + 0.5 × 0.9 = 0.875. The push engine pushes precise content 20 hours before commissioning, including commissioning plans, standard clauses, and historical commissioning problem cases.

[0042] During performance tracking, the risk warning index Rp=4.1, with no warning; after the business plan is broken down, responsible persons are automatically assigned (Ptq corresponds to priority level 5). After completion, debugging data and acceptance reports are uploaded, the system score is 8.8 points, and the experience weight Wek of the associated library resources is updated synchronously.

[0043] Validation data: The overall system comprises five core steps: constructing a 3D WBS (Work Breakdown Structure) relational library, intelligent generation of tiered lists, integrated intelligent push notifications, project health early warning, and business plan decomposition and closed-loop management. These steps work in tandem to form a complete project management system. The construction of the 3D WBS relational library relies on a four-level unified coding rule to clarify the correspondence between each business segment and WBS nodes, input various types of resources and calculate association strength, and establish a dynamic update mechanism to ensure the timeliness and effectiveness of resources. Tiered list generation is achieved through a two-factor algorithm: first, a basic list is selected based on project attributes, and then specialized and detailed lists are decomposed using experience weights, balancing standardization and personalization. The integrated push notification engine configures the timing and content granularity of push notifications based on task importance and responsible person roles, achieving precise delivery. The project health early warning model collects micro-level performance data, calculates a risk warning index, triggers corresponding warnings, and links to the main plan. After business plan decomposition, a closed-loop knowledge accumulation system is formed through responsibility allocation, self-inspection processes, and evaluation feedback. The parameters of each algorithm formula can be dynamically adjusted according to industry type and project scale. For example, in high-risk industries such as metallurgy and chemical engineering, the weight of safety risk-related parameters can be increased; for small projects, some calculation steps can be simplified to improve operational efficiency. Through the above design, this method can be adapted to the project management needs of different industries and project sizes, and has strong versatility and practicality.

[0044] Based on the above embodiments and practical applications in similar projects, a statistical comparison of the core indicators of this method and existing technologies was conducted, and the results are as follows: Existing technologies averaged 80 hours for compiling a project list, while this method reduces this to 24 hours, improving efficiency by 70%; the existing technology averaged 62%, while this method improved it to 86.5%, an increase of 39.5%; the existing technology averaged 17.8%, while this method reduced it to 4.2%, a decrease of 76.4%; the accuracy rate of this method in predicting potential risks reached 89.3%, and compared to existing technologies (primarily post-event alerts), risk response was on average 36 hours earlier; the existing technology averaged 45%, while this method improved it to 78.2%, an increase of 73.8%; the existing technology averaged 35 hours, while this method reduced it to 10.5 hours, improving efficiency by 70%; the existing technology averaged 78.5%, while this method improved it to 92.3%, an increase of 17.6%. In summary, this method significantly improves the efficiency, accuracy, and risk control capabilities of project management through a collaborative design that integrates multi-level three-dimensional association, intelligent algorithms, precise push notifications, forward-looking early warnings, and closed-loop management, and has broad industry application value.

[0045] This WBS (Work Breakdown Structure) list intelligent push and performance tracking method based on experience-based correlation addresses the problems of fragmented WBS-related resources, low correlation, and delayed updates in existing technologies. Through a multi-level, three-dimensional WBS correlation library construction mechanism, it achieves deep binding between resources, WBS, and project scenarios. Combined with correlation strength quantification calculation and dynamic update capabilities, it makes resource reuse more accurate, data support more robust, significantly improves resource utilization efficiency, shortens resource retrieval time, and enhances resource matching accuracy. Furthermore, this invention breaks through the limitations of traditional single-dimensional list generation algorithms. The attribute matching + weight assignment dual-factor intelligent algorithm balances the standardization and personalization needs of the list. Through multi-attribute similarity calculation and experience weight quantification, it automatically generates hierarchical lists and supports secondary refinement, effectively reducing manual compilation costs. Compared to existing methods, it reduces list compilation time, improves list adaptability, and, through the introduction of algorithm formulas, makes the list generation process more scientific and repeatable. Meanwhile, this invention, through an integrated intelligent push engine that combines knowledge, requirements, and responsible parties, combined with personalized push timing and content granularity, ensures that executors receive complete execution information at the correct time, effectively reducing the error rate caused by missing information. In practice, the task execution error rate has been reduced from 15%-20% in existing technologies to below 5%, improving the first-time pass rate for task acceptance. Furthermore, this invention upgrades project performance management from post-event remediation to proactive early warning. Based on micro-data of checklist performance, it constructs an early warning model that not only alerts to delayed tasks but also predicts potential milestone delays, quality, and safety risks. It links with the main performance plan nodes to provide decision support, advancing project risk response time by 24-48 hours and improving risk control success rates. Finally, this invention constructs a business system of task execution, knowledge accumulation, and closed-loop management. Through intelligent decomposition of checklist-based work plans and responsibility binding technology, it forces knowledge and tasks to be associated. Combined with self-inspection processes and evaluation feedback mechanisms, it achieves effective accumulation and reuse of lessons learned, driving project management from task execution-oriented to knowledge accumulation-oriented, while reducing business plan preparation time and significantly improving management efficiency.

[0046] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent push and fulfillment tracking of WBS lists based on experience-based systematic association, characterized by: Includes the following steps: S1: Construct a multi-level three-dimensional WBS association library, build an association system between business segments and WBS nodes based on unified coding rules, establish a three-dimensional association relationship between resources, WBS and project scenarios, input multiple types of resources and bind WBS node information and association attributes, realize the configurability of association relationships and resource priorities and dynamic updates of the association library. S2: Based on a dual-factor intelligent algorithm of attribute matching and weight assignment, combined with a general list library and a three-dimensional WBS association library, it generates a hierarchical list adapted to the project, and provides channels for secondary refinement and manual adjustment according to professional and time dimensions. S3: Build an integrated intelligent push engine for knowledge, requirements, and responsible persons for task flows, bind the list of tasks with the project plan to form a task flow, and push tasks and related knowledge packages and requirement packages to the responsible persons according to the personalized timing and content granularity. S4: Based on the list of fulfillment status, build a real-time monitoring and forward-looking early warning model for project health, collect micro-data on task fulfillment, analyze task completion trends and problem characteristics, and realize forward-looking early warning of potential project risks and linkage with the main fulfillment plan nodes; S5: Based on the completed data of the checklist, the business plan is intelligently split and the responsibility is bound, generating two types of core business plans and configuring the responsibility allocation mechanism, self-inspection process and evaluation feedback mechanism to form a closed loop of knowledge accumulation.

2. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: In S1, the unified coding rule is a four-level coding rule, and the coding format is: XX-XX-XX-XX, where the first level is the business segment code (2 digits), the second level is the WBS level code (2 digits), the third level is the professional type code (2 digits), and the fourth level is the node sequence number code (2 digits); the business segments include project planning, scheme design, construction execution, quality inspection, safety control, progress coordination, acceptance and delivery, and operation and maintenance review, and each business segment corresponds to several levels of WBS nodes; the association attribute includes the association strength label, and the association strength is calculated by formula (1): （1） Where: Sij is the association strength between the i-th WBS node and the j-th resource, with a value ranging from [0,1], and the larger the value, the higher the association strength; α is the resource reuse weight coefficient, with a value ranging from [0.3,0.5]; Rij is the historical reuse rate of the j-th resource in the i-th type of WBS node, that is, the ratio of the number of times the resource is associated with the same type of WBS node in historical projects to the total number of times the same type of WBS node is associated with resources; β is the time decay weight coefficient, with a value ranging from [0.2,0.4]; Tj is the time effectiveness coefficient of the j-th resource. , where is the current time, resource update time, and resource validity period, and is 0 when the result is negative; γ is the scene matching weight coefficient, with a value range of [0.2, 0.3]; Fij is the matching degree between the j-th resource and the project scene corresponding to the i-th WBS node, with a value range of [0, 1], which is determined according to the overlap between the resource's applicable scene and the current project scene.

3. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: In S1, the various types of resources include historical experience cases, solution templates, technical standards, acceptance specifications, lessons learned from failures, tool lists, personnel configuration plans, and cost budget templates. The dynamic update is achieved by real-time monitoring of the new resource entry port, technical standard update channels, and project archive data. New resources automatically trigger association strength calculations and are updated to the corresponding WBS node. At the same time, it supports administrators to manually review the validity of new resources.

4. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: In S2, the dual-factor intelligent algorithm for attribute matching and weight assignment specifically includes the following steps: S21: Attribute matching stage, extract project attribute parameters, including professional field, project scale, construction difficulty, schedule requirements, and quality level, and filter basic nodes from the general list library based on attribute similarity formula (2): （2） Where: Pk is the attribute similarity between the k-th general list node and the current project, with a value range of [0,1], and the smaller the value, the higher the matching degree; n is the number of project attribute parameters, n≥5; Wm is the weight of the m-th attribute parameter. The weighting of professional field and construction difficulty shall not be less than 0.5; Xkm is the m-th attribute parameter value corresponding to the k-th general list node; Xpm is the m-th attribute parameter value of the current project; S22: In the weight assignment stage, the empirical weight is calculated by combining historical project data. The empirical weight is calculated using formula (3): （3） Where: Wek is the experience weight of the k-th list node, with a value range of [0,1]. The larger the value, the higher the reference value of the corresponding resource or list node; δ is the similarity weight coefficient, with a value range of [0.4,0.6]; Spk is the overall similarity between the historical project and the current project, calculated based on the weighted average of multiple attribute parameters; Ehk is the performance effect coefficient of the k-th list node in the historical project, with a value range of [0,1], which is comprehensively evaluated based on the project schedule compliance rate, quality pass rate, and safety accident incidence rate. S23: Based on the attribute matching results and experience weights, break down and refine the special item list to form the final graded list.

5. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: In S3, personalized configuration includes push timing configuration and content granularity configuration: push timing includes 12-24 hours before the task plan starts, key nodes during task execution, task delay warnings, and before task acceptance; content granularity is divided into basic, professional, and precise levels according to the importance level of the task. The basic level only pushes the core task and acceptance criteria, the professional level adds technical specifications and solution templates, and the precise level additionally pushes historical cases and lessons learned from failures; the knowledge package includes the standard clauses that must be referenced, relevant lessons learned from failures, available solution templates, and tool operation guides, and the requirements package includes acceptance criteria, filling format, time limit requirements, and quality control points.

6. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: The real-time monitoring and proactive early warning model for project health in S4 specifically includes the following steps: S41: Collect micro-level data on task performance, including task completion status, completion quality evaluation, on-site anomaly information, and feedback from responsible persons; S42: Calculate the project health index and risk warning index. The risk warning index is calculated using formula (4): （4） Where: Rp is the project risk warning index, with a value range of [0,10]. A value ≥ 6 triggers a warning, and a value ≥ 8 triggers a high-level warning; m is the number of highly relevant task groups; Ci is the importance coefficient of the i-th task group. The milestone task group coefficient is no less than 0.3; Di is the delay risk coefficient of the i-th task group, with a value range of [0,1], determined according to the ratio of the average delay time of the task group to the planned time; Li is the impact range coefficient of the i-th task group, with a value range of [1,3], graded according to the number of subsequent tasks affected; Ki is the problem frequency coefficient of the i-th task group, with a value range of [0,1], which is the ratio of the number of high-frequency problems to the total number of tasks in the task group; Mi is the problem severity coefficient of the i-th task group, with a value range of [1,3], graded according to the impact of the problem on quality, safety, and schedule; S43: Trigger corresponding warnings based on the risk warning index and link them with the main project performance plan nodes to update the node completion probability.

7. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: In S5, the two types of core business plans are solution plans and lessons learned including risk points plans. Solution plans are associated with corresponding WBS nodes and are required to enter standard specification numbers, reference lessons learned, solution preparation responsible persons, and review nodes. The system automatically fills in the standard specifications and lessons learned associated with the corresponding WBS nodes as basic materials. The lessons learned, including risk point plans, are based on the completed data from the checklist and automatically generate risk point analysis reports, which clearly define the types of risks, their frequency of occurrence, their impact, and corrective measures. The responsibility allocation mechanism supports automatic allocation and self-claiming. Automatic allocation determines task priority based on role permissions, historical responsibility experience, and current workload. The task priority calculation formula (5) is as follows: （5） Where: Ptq is the priority of the q-th task, ranging from [1,5], with higher values ​​indicating higher priority; ε is the task importance weight coefficient, ranging from [0.4,0.6]; Itq is the importance level of the q-th task itself, ranging from [1,5]; ζ is the user's historical experience weight coefficient, ranging from [0.2,0.3]; Huq is the user's historical experience value for the q-th type of task, ranging from [1,5], which is a weighted value of the quantity and quality of similar tasks handled in the past; η is the user's current load weight coefficient, ranging from [0.2,0.3]; Luq is the user's current load coefficient when executing the q-th task, ranging from [1,5], with higher values ​​indicating lower load; ε+ζ+η=1.

8. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: In S5, the self-inspection process requires the person in charge to upload execution evidence through the APP after the task is completed. The system automatically compares the evidence with the acceptance standards in the requirement package, generates a preliminary evaluation, and then the final solution quality score is formed after review by the auditor. The score results are synchronized to the three-dimensional WBS association library to update the association strength and experience weight of the corresponding resources.

9. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: In S2, the hierarchical list includes a basic list, a special list, and a detailed list. The basic list is a core node list filtered after attribute matching. The special list includes a quality inspection station inspection list, a milestone node list, a critical and major project list, and a cross-operation coordination list. The detailed list is a list that is broken down according to professional and time dimensions.

10. The method for intelligent push and fulfillment tracking of WBS list based on experience series association as described in claim 1, characterized in that: It also includes data statistics and debriefing: real-time statistics on list generation efficiency, task completion rate, risk warning accuracy, knowledge reuse rate, business plan preparation time, etc., to form a debriefing report, providing data support for the optimization of the three-dimensional WBS related library, algorithm parameter adjustment, and push strategy optimization.

Images