Search

CN-121544056-B - Intelligent construction management system and method

CN121544056BCN 121544056 BCN121544056 BCN 121544056BCN-121544056-B

Abstract

The invention discloses an intelligent construction management system and method, which belong to the technical field of construction engineering management and comprise a construction task relation network for construction engineering, wherein the construction task relation network comprises construction tasks, an influence factor feature vector of the construction tasks is obtained to generate initial delay probability of the construction tasks, connection paths among the construction tasks are analyzed based on the construction task relation network, the number of paths, the length of the paths and the number of front construction tasks of the connection paths are obtained, a construction task influence analysis model is built to generate construction task influence factors, an iteration analysis model is built according to the initial delay probability of the construction tasks and the construction task influence factors to generate construction task comprehensive risk values, and the construction tasks are managed according to the construction task comprehensive risk values.

Inventors

  • MA XIAOYU

Assignees

  • 天河智建(天津)有限公司

Dates

Publication Date
20260508
Application Date
20260122

Claims (7)

  1. 1. The intelligent construction management method is characterized by comprising the following steps of: Constructing a construction task relation network of construction engineering, wherein the construction task relation network refers to a project plan quantification model based on a directed graph theory, specifically abstracts construction tasks into nodes, abstracts logical dependency relationships among the tasks into directed edges, and thus constructing a computable and analyzable complex network topological structure; acquiring an influence factor feature vector of a construction task, inputting the influence factor feature vector of the construction task into a machine learning model, and generating an initial delay probability of the construction task; Based on the construction task relation network, analyzing connection paths among construction tasks, and acquiring the number of paths, the length of the paths and the number of front construction tasks of the construction tasks; According to the number of paths, the length of the paths and the number of front construction tasks of the construction tasks, a construction task influence analysis model is built, and a construction task influence factor is generated; Establishing an iterative analysis model according to the initial delay probability of the construction task and the construction task influence factor to generate a construction task comprehensive risk value, wherein the initial delay probability of the construction task is the initial construction task comprehensive risk value of the iterative analysis model; managing the construction tasks according to the comprehensive risk values of the construction tasks; The generation mode of the building task comprehensive risk value specifically comprises the following steps: generating a comprehensive risk probability of no delay of the construction task according to the initial delay probability of the construction task and the influence factor of the construction task; establishing an iterative analysis model according to the construction task non-delay comprehensive risk probability to generate a construction task comprehensive risk value; The generation mode of the building task delay-free comprehensive risk probability specifically comprises the following steps: By the formula: ; Generating a comprehensive risk probability for construction tasks without delay ; In the formula (i) the formula (ii), Representing a construction task node The building task comprehensive risk value after the kth iteration, Representing a construction task node Is a pre-built task node of (a) Building task composite risk value after the kth round of iterations, Representing a construction task node Is a factor of the influence of the construction task, Represented is the propagation attenuation factor(s), Representing all pointing to construction task nodes Is a front construction task node set, m represents the front construction task node set The number of intermediate front-end building task nodes; The expression of the iterative analysis model is specifically: ; In the expression of the expression "a", Indicated are the comprehensive risk values of the construction tasks, The comprehensive risk probability that the construction task is not delayed is represented.
  2. 2. The intelligent construction management method according to claim 1, wherein the generating manner of the initial delay probability of the construction task specifically includes: By the formula: ; generating initial deferred probabilities for a build task ; In the formula (i) the formula (ii), Representing construction tasks The influencing factor feature vector at time t, Is a machine learning model.
  3. 3. The intelligent construction management method according to claim 1, wherein the generation mode of the construction task influence factor specifically includes the following steps: generating a construction task bridge factor according to the number and the length of the connecting paths; Generating PageRank values according to the number of the front construction tasks of the construction tasks; and building a construction task influence analysis model according to the construction task bridge factor and the PageRank value, and generating a construction task influence factor.
  4. 4. The intelligent construction management method according to claim 3, wherein the method for generating the construction task bridge factor specifically comprises: By the formula: ; generating construction task bridge factors ; In the formula (i) the formula (ii), Representing slave construction task nodes in a construction task relationship network To the construction task node Is provided for the total number of shortest paths, Represents the total number of shortest paths Intermediate construction task node Wherein, the limiting conditions of the formula are s not equal to t, s not equal to i and t not equal to i, and the limiting conditions refer to the fact that the building task nodes s, t and i in the building task relation network are not the same building task nodes.
  5. 5. The intelligent building management method according to claim 3, wherein the generating manner of the PageRank value specifically includes: By the formula: ; Generating PageRank values ; In the formula, d represents a damping coefficient, n represents the number of construction task nodes in the construction task relation network, Representing all pointing to construction task nodes Is used for building a task node aggregate in advance, Representing a collection of nodes of a pre-built task The j-th front building task node in the list, m represents the front building task node aggregate The number of intermediate front-end construction task nodes, Representing a collection of nodes of a pre-built task Middle front construction task node Is used for the purpose of determining the PageRank value of (C), Representing a collection of nodes of a pre-built task Middle front construction task node The outbound degree refers to the pre-construction task nodes in the construction task relation network The number of all directed edges that are scattered out.
  6. 6. The intelligent construction management method according to claim 3, wherein the expression of the construction task influence analysis model is specifically: ; In the expression of the expression "a", Represented is a construction task impact factor, Representing the bridge factor of the construction task Is used for the normalization of the values of (c), Representing PageRank values Is used for the normalization of the values of (c), 、 Are all weight coefficients, and 。
  7. 7. An intelligent construction management system for performing the intelligent construction management method of any one of claims 1-6, comprising in particular: The construction task relation network refers to a project plan quantization model based on a directed graph theory, specifically, abstracts construction tasks into nodes, abstracts logical dependency relationships among the tasks into directed edges, and thus, a computable and analyzable complex network topological structure is constructed; the initial delay probability analysis unit is used for acquiring influence factor feature vectors of the construction task, inputting the influence factor feature vectors of the construction task into the machine learning model and generating initial delay probability of the construction task; The data acquisition unit is used for analyzing connection paths among the construction tasks based on the construction task relation network and acquiring the number of paths, the length of the paths and the number of front construction tasks of the construction tasks; The influence analysis unit is used for building a construction task influence analysis model according to the number of paths of the connecting paths, the path length and the number of front construction tasks of the construction tasks and generating construction task influence factors; The risk comprehensive analysis unit is used for establishing an iterative analysis model according to the initial delay probability of the construction task and the construction task influence factor to generate a construction task comprehensive risk value, wherein the initial delay probability of the construction task is the initial construction task comprehensive risk value of the iterative analysis model; the management unit is used for managing the construction task according to the comprehensive risk value of the construction task; the risk comprehensive analysis unit specifically comprises: The non-delay probability analysis module is used for generating a non-delay comprehensive risk probability of the construction task according to the initial delay probability of the construction task and the influence factor of the construction task; The building task comprehensive risk value generation module is used for building an iteration analysis model according to the building task non-delay comprehensive risk probability and generating a building task comprehensive risk value.

Description

Intelligent construction management system and method Technical Field The invention belongs to the technical field of building engineering management, and particularly relates to an intelligent construction management system and method. Background As the construction industry has transformed to digital and intelligent, project management for large construction projects is facing increasingly complex challenges. The construction engineering generally comprises a large number of interrelated task links, strict logic dependency relationship exists among the tasks, and delay of any one task can generate chain reaction through the task dependency relationship so as to influence the progress of the whole project. In actual engineering management, the topology structure of a task network is complex and changeable, roles played by different tasks in the network are different, and part of tasks are not on a traditional critical path, but can bear a critical bridge function of connecting a plurality of sub-networks, and delay risks are easily ignored by the existing method. Currently, project management of construction projects mainly adopts traditional methods such as a critical path method, a plan review technology and the like. Some systems perform progress control through Gantt charts and milestone nodes, estimate the task construction period based on historical data, and other systems perform independent risk assessment on a single task by adopting a simple risk assessment matrix. In the aspect of informatization management, the prior art focuses on progress tracking and resource allocation, and lacks in-depth analysis on complex association relations between tasks. The critical path method only focuses on task sequences on the critical path, the structural importance of the tasks in the network is not fully considered, and task nodes which are not on the critical path but have important bridge functions cannot be identified, and once problems occur in the nodes, the connectivity of the whole task network can be interrupted. The existing risk assessment method is mostly based on independent analysis of a single task, and ignores linkage effects of risk propagation through task dependency, for example, delayed risks of a front task can be spread to a subsequent task along a directed edge to form cascade effects. Most management systems lack quantitative modeling capability for dynamic risk propagation processes, and cannot accurately predict the influence degree of local risks on the overall project progress, so that project managers cannot distinguish high-influence tasks from low-influence tasks, and cannot formulate targeted risk coping strategies. In addition, the existing method can not combine the topological characteristics of the task network with external influence factors, and can not realize dynamic tracking of a risk propagation path and iterative calculation of a comprehensive risk value, so that a risk assessment result has deviation from an actual engineering situation. Disclosure of Invention Aiming at the defects of the prior art, the invention provides an intelligent construction management system and method, which solve the problems. In order to achieve the purpose, the intelligent building management method is realized through the following technical scheme that the intelligent building management method specifically comprises the following steps: Constructing a construction task relation network of construction engineering, wherein the construction task relation network refers to a project plan quantification model based on a directed graph theory, specifically abstracts construction tasks into nodes, abstracts logical dependency relationships among the tasks into directed edges, and thus constructing a computable and analyzable complex network topological structure; acquiring an influence factor feature vector of a construction task, inputting the influence factor feature vector of the construction task into a machine learning model, and generating an initial delay probability of the construction task; Based on the construction task relation network, analyzing connection paths among construction tasks, and acquiring the number of paths, the length of the paths and the number of front construction tasks of the construction tasks; According to the number of paths, the length of the paths and the number of front construction tasks of the construction tasks, a construction task influence analysis model is built, and a construction task influence factor is generated; Establishing an iterative analysis model according to the initial delay probability of the construction task and the construction task influence factor to generate a construction task comprehensive risk value, wherein the initial delay probability of the construction task is the initial construction task comprehensive risk value of the iterative analysis model; And managing the construction tasks according to the comprehensive risk v