CN112200532A - Method and system for intelligently calculating construction period and computer readable medium - Google Patents
Method and system for intelligently calculating construction period and computer readable medium Download PDFInfo
- Publication number
- CN112200532A CN112200532A CN202010973483.9A CN202010973483A CN112200532A CN 112200532 A CN112200532 A CN 112200532A CN 202010973483 A CN202010973483 A CN 202010973483A CN 112200532 A CN112200532 A CN 112200532A
- Authority
- CN
- China
- Prior art keywords
- calculation
- project
- module
- calculation model
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000010276 construction Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004364 calculation method Methods 0.000 claims abstract description 265
- 238000013135 deep learning Methods 0.000 claims abstract description 36
- 238000000354 decomposition reaction Methods 0.000 claims description 31
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000013500 data storage Methods 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000009430 construction management Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Geometry (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Structural Engineering (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Civil Engineering (AREA)
- Mathematical Analysis (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Architecture (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a system for intelligently calculating a construction period and a computer readable medium, and belongs to the following steps: firstly, establishing a database; secondly, importing data; thirdly, deep learning; fourthly, correcting the calculation model; fifthly, confirming a calculation model; sixthly, recording the project; seventhly, decomposing the items; eighthly, importing a building model; ninthly, task calculation; and displaying graphs, performing deep learning training on the calculation model by the system, and calculating project information by using the usable model to obtain the construction period of each subtask and the total construction period.
Description
Technical Field
The invention relates to the technical field of construction management systems, in particular to a construction period intelligent calculation method and system and a computer readable medium.
Background
At present, the construction period is generally calculated by a construction project management system, but when a project is built, a large project often comprises countless small projects, and the construction period of all the small projects needs to be determined so as to finally determine the construction period of the large project. The construction project management system generally estimates the construction period by the user according to experience and inputs the construction period into each sub-project, and the system arranges and calculates the construction period and the construction resources of a large project and then manually distributes the construction resources.
The existing construction project management system comprises the following editing steps: defining information of a project, carrying out WBS decomposition on the project, filling an estimated construction period for all subtasks, setting a task chain relation, establishing a resource table, allocating resources to each task of the project, and adjusting and optimizing a project plan.
The above prior art solutions have the following drawbacks: when the existing construction management system edits the construction schedule, the total schedule can be formed only after the construction period is artificially estimated and resources are artificially allocated. Limited by practical experience, lack of accuracy and waste of time.
Disclosure of Invention
In order to automatically obtain the information and the construction period of the sub-project, the application provides a construction period intelligent calculation method.
The technical scheme provided by the application is as follows:
a construction period intelligent calculation method comprises the following steps:
firstly, establishing a database: establishing a calculation model and a database, and storing the calculation model into the database;
secondly, data import: importing the engineering data with the result into a database;
thirdly, deep learning: the calculation model carries out simulation calculation according to the engineering data, a nonlinear fitting method is used for carrying out operation training on the calculation model, and deviation values of the finally obtained calculation results of the calculation model and historical data results are recorded;
fourthly, correcting the calculation model: if the deviation value of the calculation result and the historical data result is larger than the set range, modifying the calculation model, and repeating the third step;
fifthly, confirming a calculation model: if the deviation value of the calculation result and the historical data result is smaller than the set range, confirming the calculation model;
sixthly, entry of items: defining project information and inputting the project information into a server;
seventhly, item decomposition: the server carries out WBS decomposition on the project to obtain a plurality of subtasks;
eighthly, importing a building model: building a building information model and importing the building information model into a server, and confirming the specific drawing workload of each subtask by the server according to a building information calculation model;
ninthly, task calculation: substituting the engineering information of the subtasks and the workload of the specific drawing into the confirmed calculation model to obtain the construction period of each subtask and form a subtask engineering report with the project information of the subtasks;
tenthly, displaying a graph: and integrating all the subtask project reports, calculating the total project period and displaying the formed total project report to a user.
By adopting the scheme, WBS decomposition is carried out on the total project information to obtain a plurality of blank subtasks, a user establishes a building information model, the system fills information into the subtasks through the building information model, all required information of each subtask is calculated through the calculation model, and finally a total project report is generated through total calculation for the user to use. The calculation model with the minimum calculation result deviation value is obtained by continuously carrying out deep learning training on the calculation model, the calculation model can keep up with changes, the construction period of the finally calculated subtask and the construction period of the total project are accurate, the automation degree of the calculation process is high, the problem that a user can only estimate the construction period of the subentry project by experience is solved, the user only needs to input the building information model, the system can automatically calculate the construction period and the total construction period of each subtask, the labor is effectively saved, the requirement on the technology of an engineer is lowered, the calculation result is accurate, and the error is small.
Preferably, the step three is specifically configured as follows:
and thirdly, filling the engineering data into the calculation model to obtain a calculation result, comparing the calculation result with the historical data result to obtain a deviation value, and revising the calculation model according to a gradient descent algorithm until the deviation values obtained when the calculation model calculates different historical data are balanced.
By adopting the scheme, the calculation model of the engineering construction period belongs to nonlinear change, so the error of deep learning and training of the calculation model by using a nonlinear fitting method is lower, and the calculation model can be gradually improved by a gradient descent algorithm.
Preferably, the second and third steps further comprise:
secondly, the server is provided with a business database and an original database, the business database and the original database both store engineering data, and the data of the original database is called when the calculation model carries out deep learning;
and thirdly, when the original database receives new engineering data, judging whether the new engineering data conform to a reasonable data range, and if not, prompting a user to correct the new engineering data.
By adopting the scheme, when the server trains the calculation model by using the engineering data, the server can carry out data cleaning on the received engineering data and judge whether the data is abnormal data, so that the possibility of inputting wrong engineering data by a user can be effectively reduced.
Preferably, the step one is specifically configured as follows:
the method comprises the steps that a, a server inputs engineering quantity, available machinery, available manpower, efficiency influence factors and time influence factors into a calculation model, the calculation model calculates weighted workload according to the engineering quantity, the calculation model calculates working efficiency according to the available machinery and the available manpower, the calculation model corrects the working efficiency according to the efficiency influence factors, the calculation model corrects the working time according to the weighted workload, the working efficiency and the efficiency, the calculation model corrects the working time according to the time influence factors, and the calculation model corrects the time consumed by a calculation process according to the working time and the time.
By adopting the scheme, the system is accurate in calculation, the interference of the efficiency influence factors and the time influence factors can be accurately eliminated, and the final construction period is accurate in calculation.
In order to automatically obtain the information and the construction period of the sub-project, the application provides a system for intelligently calculating the construction period.
The technical scheme provided by the application is as follows:
a system for intelligently calculating a construction period comprises a data acquisition end and a server;
the data acquisition end acquires engineering information and sends the engineering information to the server;
the server comprises a total storage module, a data acquisition module, a deep learning module, a project decomposition module, a project calculation module and a chart display module;
the total storage module receives and stores the input information, and the calculation model is stored in the total storage module;
the data acquisition module receives the engineering information transmitted by the data acquisition end and sends the engineering information to the main storage module for storage, and the data acquisition module sends the complete engineering information to the deep learning module;
the deep learning module calls a calculation model stored by the main storage module, the deep learning module introduces engineering information into the calculation model for calculation, the calculation model is operated and trained by a nonlinear fitting method, the deviation value of the finally obtained calculation result of the calculation model and the historical data result is recorded, the recorded deviation value is compared with a set range, if the deviation is larger than the set range, the calculation model is modified according to the result, and if the deviation is smaller than the set range, the calculation model is transmitted to the main storage module and covers the original calculation model;
the project decomposition module (24) calls the engineering information stored by the main storage module, WBS decomposition is carried out on the engineering information, a plurality of blank subtask items are obtained, the project decomposition module establishes a corresponding building information model according to the engineering information, the specific drawing workload is confirmed through the building information calculation model, the project decomposition module adds the building information model information and the specific drawing workload into the corresponding subtask items, and the project decomposition module transmits the subtask items to the project calculation module;
the project calculation module calls a calculation model stored in the total storage module according to the received subtask items, the project calculation module calculates the process time consumption of the corresponding subtask items by using the corresponding calculation model, the project calculation module calculates the total process construction period according to the process time consumption of all the subtask items, and the project calculation module transmits the information of the subtask items, the process time consumption and the total process construction period to the chart display module;
the chart display module stores a chart template, fills the chart template according to the received information and generates an engineering chart, and the chart display module (26) transmits the engineering chart to the main storage module for storage and displays the engineering chart.
By adopting the scheme, WBS decomposition is carried out on the total project information to obtain a plurality of blank subtasks, a user establishes a building information model, the system fills information into the subtasks through the building information model, all required information of each subtask is calculated through the calculation model, and finally a total project report is generated through total calculation for the user to use. The calculation model with the minimum calculation result deviation value is obtained by continuously carrying out deep learning training on the calculation model, the calculation model can keep up with changes, the construction period of the finally calculated subtask and the construction period of the total project are accurate, the automation degree of the calculation process is high, the problem that a user can only estimate the construction period of the subentry project by experience is solved, the user only needs to input the building information model, the system can automatically calculate the construction period and the total construction period of each subtask, the labor is effectively saved, the requirement on the technology of an engineer is lowered, the calculation result is accurate, and the error is small.
Preferably, the deep learning module calls a calculation model stored in the main storage module, the deep learning module introduces engineering information into the calculation model for calculation, the calculation result is compared with the historical data result to obtain a deviation value, the calculation model is revised according to a gradient descent algorithm until the deviation values obtained when the calculation model calculates different historical data are balanced, if the balanced deviation is larger than a set range, the calculation model is revised according to the result, and if the deviation is smaller than the set range, the calculation model is transmitted to the main storage module and covers the original calculation model.
By adopting the scheme, the calculation model of the engineering construction period belongs to nonlinear change, so the error of deep learning and training of the calculation model by using a nonlinear fitting method is lower, and the calculation model can be gradually improved by a gradient descent algorithm.
Preferably, the total data storage module includes an original database and a service database, the total data storage module stores a data judgment range, the original database judges whether the item information is within the data judgment range when receiving the item information, if so, the item information is stored, and if not, a warning is given.
By adopting the scheme, when the server trains the calculation model by using the engineering data, the server can carry out data cleaning on the received engineering data and judge whether the data is abnormal data, so that the possibility of inputting wrong engineering data by a user can be effectively reduced.
Preferably, the project calculation module analyzes the project amount, the available machines, the available workers, the efficiency influence factors and the time influence factors in the project information, the project calculation module calculates the weighted workload according to the project amount, the project calculation module calculates the work efficiency according to the available machines and the available workers, the project calculation module calculates efficiency correction according to the efficiency influence factors, the project calculation module calculates the work time according to the weighted workload, the work efficiency and the efficiency correction, the project calculation module calculates time correction according to the time influence factors, and the project calculation module corrects the time consumed by the calculation process according to the work time and the time.
By adopting the scheme, the system is accurate in calculation, the interference of the efficiency influence factors and the time influence factors can be accurately eliminated, and the final construction period is accurate in calculation.
Preferably, the engineering chart of the chart display module displays engineering quantity, available machinery, available labor, efficiency influence factors, time influence factors, work efficiency, work time, process time consumption and total engineering construction period, the content of the engineering chart is modified according to the received information, and when the engineering chart is modified, the chart display module sends the project information in the modified engineering chart to the project calculation module for recalculation.
By adopting the scheme, a user can modify the project information through the system, the system automatically recalculates, and the user can conveniently designate the optimal construction scheme.
In order to automatically obtain the information and the construction period of the sub-project, the application provides a system for intelligently calculating the construction period.
The technical scheme provided by the application is as follows:
a computer-readable medium, characterized in that: a computer program which can be loaded by a processor and which executes the method according to any of claims 1 to 4.
By adopting the scheme, the information of the subtasks can be obtained by carrying out WBS decomposition on the total project information, the calculation model with the minimum calculation result deviation value is obtained by continuously carrying out deep learning training on the calculation model, the calculation model can be ensured to keep up with the change, the final calculation time limit of the subtasks and the final calculation time limit of the total project are accurate, the automation degree of the calculation process is high, the problem that a user can only estimate the time limit of the subtasks by experience is solved, the user only needs to input the building information model, the system can automatically calculate the time limit and the total time limit of each subtask, the labor is effectively saved, the requirements on the engineer technology are reduced, the calculation result is accurate, and the error is small.
In conclusion, the invention has the following beneficial effects:
1. the calculated construction period of the subtasks and the construction period of the total project are accurate, the automation degree of the calculation process is high, the problem that a user can only estimate the construction period of the subtasks by experience is solved, the user only needs to input the building information model, the system can automatically calculate the construction period and the total construction period of each subtask, manpower is effectively saved, the requirements on the technology of engineers are reduced, the calculation result is accurate, and the error is small.
Drawings
FIG. 1 is a system block diagram of an embodiment of a system for intelligent construction period calculation according to the present application;
FIG. 2 is a system block diagram of a server of an embodiment of a system for intelligent construction period calculation of the present application;
FIG. 3 is a block diagram of the overall storage module of an embodiment of a system for intelligent construction period calculation of the present application.
In the figure, 1, a data acquisition end; 2. a server; 21. a total storage module; 211. an original database; 212. a service database; 213. a model storage database; 22. a data acquisition module; 23. a deep learning module; 24. a project decomposition module; 25. a project calculation module; 26. and a chart display module.
Detailed Description
The present application is described in further detail below with reference to figures 1-3.
Example (b): the embodiment of the application discloses a construction period intelligent calculation method, which comprises the following specific steps:
step one, establishing a database: establishing a calculation model and a server 2, setting a service database 212 and an original database 211 in the server 2, and storing the calculation model in the service database 212 and the original database 211. The server 2 inputs the engineering quantity, the available machinery, the available manpower, the efficiency influence factors and the time influence factors into a calculation model, the calculation model calculates the weighted workload according to the engineering quantity, the calculation model calculates the working efficiency according to the available machinery and the available manpower, the calculation model corrects the working efficiency according to the efficiency influence factors, the calculation model corrects the working time according to the weighted workload, the working efficiency and the efficiency, the calculation model corrects the working time according to the time influence factors, and the calculation model corrects the time consumed by the calculation process according to the working time and the time. The efficiency correction is a known item which has influence on the efficiency in the construction process, and the time correction is a known factor such as the transportation time of a machine and the like of a special work pause which occurs in the construction process. The system is accurate in calculation, interference of efficiency influence factors and time influence factors can be accurately eliminated, and the final construction period is accurate in calculation.
Step two, data import: the user collects the engineering related data through the collection terminal and sends the engineering related data to the service database 212 and the original database 211 for storage.
Step three, deep learning: and calling data of the original database 211 when the calculation model performs deep learning, judging whether the new engineering data accords with a reasonable data range or not when the original database 211 receives the new engineering data, and prompting a user to correct if the new engineering data does not accord with the reasonable data range. And filling the engineering related data into the calculation model, and performing operation training on the calculation model by using a nonlinear fitting method. The nonlinear fitting training method is to fill the engineering data into the calculation model to obtain a calculation result, compare the calculation result with the historical data result to obtain a deviation value, and revise the calculation model according to a gradient descent algorithm until the deviation values obtained by the calculation model when calculating different historical data are balanced. When the server 2 trains the calculation model by using the engineering data, the received engineering data is subjected to data cleaning, whether the data is abnormal data or not is judged, and the possibility that a user inputs wrong engineering data can be effectively reduced. The calculation model of the engineering construction period belongs to nonlinear change, so the error of deep learning training of the calculation model by using a nonlinear fitting method is lower.
Step four, calculating model correction: and if the deviation value of the calculation result and the historical data result is larger than the set range, modifying the calculation model, and repeating the third step.
Step five, confirming a calculation model: and if the deviation value of the calculation result and the historical data result is smaller than the set range, confirming the calculation model. And step one to step five form a feedforward neural network, and the feedforward neural network is suitable for deep learning training.
Step six, entry of items: defines project information and enters the project information into the server 2.
Step seven, item decomposition: the server 2 performs WBS decomposition on the project to obtain a plurality of subtasks.
Step eight, importing a building model: and establishing a building information model and importing the building information model into the server 2, wherein the building information model comprises all information related to the subtasks and is formed in a fixed format. And the server 2 confirms the specific drawing workload of each subtask according to the building information calculation model.
Step nine, task calculation: and substituting the engineering information of the subtasks and the workload of the specific drawing into the confirmed calculation model to obtain the construction period of each subtask and form a subtask engineering report with the project information of the subtasks.
Step ten, displaying a graph: and integrating all the subtask project reports, calculating the total project period and displaying the formed total project report to a user. The user can modify the project information of the server 2 according to the project report, and the server 2 recalculates the project period.
The WBS decomposition is carried out on the total project information to obtain the information of the subtasks, the calculation model with the minimum calculation result deviation value is obtained by continuously carrying out deep learning training on the calculation model, the calculation model can be ensured to keep up with the change, the final calculation sub-task construction period and the final calculation total project construction period are accurate, the automation degree of the calculation process is high, the problem that a user can only estimate the sub-project construction period through experience is solved, the user only needs to input the building information model, the system can automatically calculate the construction period and the total construction period of each sub-task, the manpower is effectively saved, the requirements for the engineer technology are reduced, the calculation result is accurate, and the error is small.
Example (b): the embodiment of the application discloses system for intelligently calculating construction period, as shown in fig. 1 and 2, comprises a plurality of data acquisition terminals 1 and a server 2, wherein the data acquisition terminals 1 transmit data to the server 2. The server 2 includes a total storage module 21, a data collection module 22, a deep learning module 23, an item decomposition module 24, an item calculation module 25, and a graph display module 26.
As shown in fig. 2 and 3, the total storage module 21 receives and stores the input information, the total data storage module includes an original database 211, a business database 212, and a model storage database 213, and the model storage database 213 stores calculation models. The data acquisition module 22 receives the engineering information transmitted by the data acquisition terminal 1 and sends the engineering information to the main storage module 21 for storage, and the data acquisition module 22 sends the complete engineering information to the deep learning module 23. The total data storage module stores a data judgment range, judges whether the project information is in the data judgment range when the original database 211 receives the project information, stores the project information if the project information is in the data judgment range, and sends out a warning if the project information is not in the data judgment range. When the server 2 trains the calculation model by using the engineering data, the received engineering data is subjected to data cleaning, whether the data is abnormal data or not is judged, and the possibility that a user inputs wrong engineering data can be effectively reduced.
As shown in fig. 2 and fig. 3, the deep learning module 23 calls the calculation model stored in the model storage database 213, the deep learning module 23 matches the engineering information with the corresponding calculation model, and the deep learning module 23 imports the corresponding engineering information into the corresponding calculation model for calculation. And (3) performing operation training on the calculation model by using a nonlinear fitting method, recording the deviation value of the finally obtained calculation result of the calculation model and the historical data result, comparing the recorded deviation value with a set range, modifying the calculation model according to the result if the deviation is greater than the set range, transmitting the calculation model to a total storage module (21) if the deviation is less than the set range, covering the original calculation model, transmitting the calculation model to a model storage database 213 and covering the original calculation model if the deviation is less than the set range. The calculation model of the engineering construction period belongs to nonlinear change, so the error of deep learning training of the calculation model by using a nonlinear fitting method is lower.
As shown in fig. 2 and 3, the project decomposition module 24 calls the project information stored in the original database 211, performs WBS decomposition on the project information to obtain a plurality of blank subtask items, the project decomposition module 24 establishes a corresponding building information model according to the project information, and determines the specific drawing workload through the building information calculation model, the project decomposition module 24 adds the building information model and the specific drawing workload to the corresponding subtask items, and the project decomposition module 24 transmits the subtask items to the project calculation module 25.
As shown in fig. 2 and 3, the project calculation module 25 calls the calculation model stored in the total storage module 21 according to the received subtask information. The project calculation module 25 analyzes the project amount, available machines, available labor, efficiency influencing factors and time influencing factors in the project information, wherein the efficiency influencing factors are known items which influence the efficiency in the construction process, and the time influencing factors are known factors such as the transportation time of the machine and the like which occur in the construction process. The project calculation module 25 calculates weighted workload according to the project amount, the project calculation module 25 calculates work efficiency according to available machines and available workers, the project calculation module 25 corrects the work efficiency according to the efficiency influence factor, the project calculation module 25 calculates work time according to the weighted workload, the work efficiency and the efficiency correction, the project calculation module 25 calculates time correction according to the time influence factor, and the project calculation module 25 corrects the time consumed by the calculation process according to the work time and the time. The project calculation module 25 calculates the total project period according to the process time consumption of all the subtask information, and the project calculation module 25 transmits the information of the subtask items, the process time consumption and the total project period to the chart display module 26.
As shown in fig. 2 and 3, the chart display module 26 stores a chart template based on a gantt chart, the chart display module 26 fills the chart template according to the received information to generate an engineering chart, and the chart display module 26 transmits the engineering chart to the service database 212 for storage and displays the engineering chart. The project chart of the chart display module 26 displays the project amount, the available machines, the available workers, the efficiency influence factors, the time influence factors, the work efficiency, the work time, the process time consumption and the total project period, the content of the project chart is modified according to the received information, and when the project chart is modified, the chart display module 26 sends the project information in the modified project chart to the project calculation module 25 for recalculation. The user can modify the project information through the system, and the system automatically recalculates, so that the user can conveniently specify the optimal construction scheme.
The implementation principle of the system for intelligently calculating the construction period in the embodiment of the application is as follows: WBS decomposition is carried out on the total project information to obtain a plurality of blank subtasks, a user establishes a project model, the system fills information into the subtasks through the project model, all required information of each subtask is calculated through a calculation model, and finally a total project report is generated through total calculation for the user to use. The calculation model with the minimum calculation result deviation value is obtained by continuously carrying out deep learning training on the calculation model, the calculation model can keep up with changes, the construction period of the finally calculated subtask and the construction period of the total project are accurate, the automation degree of the calculation process is high, the problem that a user can only estimate the construction period of the subentry project by experience is solved, the user only needs to input the building information model, the system can automatically calculate the construction period and the total construction period of each subtask, the labor is effectively saved, the requirement on the technology of an engineer is lowered, the calculation result is accurate, and the error is small.
Example (b): an embodiment of the present application discloses a computer-readable storage medium, which includes, for example: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk. The computer readable storage medium is capable of being loaded by a processor and executing the embodiments as follows: a computer program for a method of intelligently calculating a construction period.
The embodiments of the present invention are preferred embodiments of the present invention, and the scope of the present invention is not limited by these embodiments, so: all equivalent changes made according to the structure, shape and principle of the invention are covered by the protection scope of the invention.
Claims (10)
1. A construction period intelligent calculation method is characterized by comprising the following steps: the method comprises the following steps:
firstly, establishing a database: establishing a calculation model and a database, and storing the calculation model into the database;
secondly, data import: importing the engineering data with the result into a database;
thirdly, deep learning: the calculation model carries out simulation calculation according to the engineering data, a nonlinear fitting method is used for carrying out operation training on the calculation model, and deviation values of the finally obtained calculation results of the calculation model and historical data results are recorded;
fourthly, correcting the calculation model: if the deviation value of the calculation result and the historical data result is larger than the set range, modifying the calculation model, and repeating the third step;
fifthly, confirming a calculation model: if the deviation value of the calculation result and the historical data result is smaller than the set range, confirming the calculation model;
sixthly, entry of items: defining project information and inputting the project information into the server (2);
seventhly, item decomposition: the server (2) carries out WBS decomposition on the project to obtain a plurality of subtasks;
eighthly, importing a building model: building a building information model and importing the building information model into the server (2), and the server (2) confirms the specific drawing workload of each subtask according to the building information calculation model;
ninthly, task calculation: substituting the engineering information of the subtasks and the workload of the specific drawing into the confirmed calculation model to obtain the construction period of each subtask and form a subtask engineering report with the project information of the subtasks;
tenthly, displaying a graph: and integrating all the subtask project reports, calculating the total project period and displaying the formed total project report to a user.
2. The method for intelligently calculating the construction period according to claim 1, wherein the third step is specifically set as:
and thirdly, filling the engineering data into the calculation model to obtain a calculation result, comparing the calculation result with the historical data result to obtain a deviation value, and revising the calculation model according to a gradient descent algorithm until the deviation values obtained when the calculation model calculates different historical data are balanced.
3. The method for intelligently calculating the construction period according to claim 2, wherein the second and third steps further comprise:
the server (2) is provided with a business database (212) and an original database (211), and both the business database (212) and the original database (211) store engineering data;
and thirdly, calling data of the original database (211) when the calculation model carries out deep learning, judging whether the new engineering data conform to a reasonable data range or not when the original database (211) receives the new engineering data, and prompting a user to correct if the new engineering data do not conform to the reasonable data range.
4. The method for intelligently calculating the construction period as claimed in claim 1, wherein the step one is specifically configured as:
the method comprises the steps that a, a server (2) inputs engineering quantity, available machinery, available manpower, efficiency influence factors and time influence factors into a calculation model, the calculation model calculates weighted workload according to the engineering quantity, the calculation model calculates working efficiency according to the available machinery and the available manpower, the calculation model corrects the working efficiency according to the efficiency influence factors, the calculation model calculates working time according to the weighted workload, the working efficiency and the efficiency correction, the calculation model calculates time correction according to the time influence factors, and the calculation model corrects the consumed time of a calculation process according to the working time and the time.
5. The utility model provides a system for construction period intelligence calculation which characterized in that: comprises a data acquisition end (1) and a server (2);
the data acquisition terminal (1) acquires engineering information and sends the engineering information to the server (2);
the server (2) comprises a total storage module (21), a data acquisition module (22), a deep learning module (23), a project decomposition module (24), a project calculation module (25) and a chart display module (26);
the total storage module (21) receives and stores the input information, and the calculation model is stored in the total storage module (21);
the data acquisition module (22) receives the engineering information transmitted by the data acquisition end (1) and sends the engineering information to the main storage module (21) for storage, and the data acquisition module (22) sends the complete engineering information to the deep learning module (23);
the deep learning module (23) calls a calculation model stored by the main storage module (21), the deep learning module (23) introduces engineering information into the calculation model for calculation, a nonlinear fitting method is used for carrying out operation training on the calculation model, deviation values of calculation results of the finally obtained calculation model and historical data results are recorded, the recorded deviation values are compared with a set range, if the deviation is larger than the set range, the calculation model is modified according to the result, and if the deviation is smaller than the set range, the calculation model is transmitted to the main storage module (21) and covers the original calculation model;
the project decomposition module (24) calls the engineering information stored by the main storage module (21), WBS decomposition is carried out on the engineering information, a plurality of blank subtask items are obtained, the project decomposition module (24) establishes a corresponding building information model according to the engineering information, specific drawing workload is confirmed through a building information calculation model, the project decomposition module (24) adds the building information model information and the specific drawing workload into the corresponding subtask items, and the project decomposition module (24) transmits the subtask items to the project calculation module (25);
the project calculation module (25) calls the calculation model stored in the total storage module (21) according to the received subtask items, the project calculation module (25) calculates the process time consumption of the corresponding subtask items by using the corresponding calculation model, the project calculation module (25) calculates the total process construction period according to the process time consumption of all the subtask items, and the project calculation module (25) transmits the information, the process time consumption and the total process construction period of the subtask items to the chart display module (26);
the chart display module (26) stores a chart template, the chart display module (26) fills the chart template according to the received information and generates an engineering chart, and the chart display module (26) transmits the engineering chart to the main storage module (21) for storage and displays the engineering chart.
6. The system for intelligently calculating the construction period according to claim 5, wherein: the deep learning module (23) calls the calculation model stored in the main storage module (21), the deep learning module (23) introduces engineering information into the calculation model for calculation, the calculation result is compared with the historical data result to obtain a deviation value, the calculation model is revised according to a gradient descent algorithm until the deviation values obtained by the calculation model in calculating different historical data are balanced, if the balanced deviation is larger than a set range, the calculation model is revised according to the result, and if the deviation is smaller than the set range, the calculation model is transmitted to the main storage module (21) and covers the original calculation model.
7. The system for intelligently calculating the construction period according to claim 5, wherein: the total data storage module comprises an original database (211) and a business database (212), the total data storage module stores a data judgment range, the original database (211) judges whether the project information is in the data judgment range when receiving the project information, if so, the project information is stored, and if not, a warning is sent out.
8. The system for intelligently calculating the construction period according to claim 5, wherein: the project calculation module (25) analyzes the project amount, the available machines, the available manual work, the efficiency influence factors and the time influence factors in the project information, the project calculation module (25) calculates the weighted workload according to the project amount, the project calculation module (25) calculates the work efficiency according to the available machines and the available manual work, the project calculation module (25) corrects the work efficiency according to the efficiency influence factors, the project calculation module (25) calculates the work time according to the weighted workload, the work efficiency and the efficiency correction, the project calculation module (25) calculates the time correction according to the time influence factors, and the project calculation module (25) corrects the time consumed by the calculation process according to the work time and the time.
9. The system for intelligently calculating the construction period according to claim 8, wherein: the project chart of the chart display module (26) displays the project amount, the available machines, the available manpower, the efficiency influence factors, the time influence factors, the work efficiency, the work time, the process time consumption and the total project period, the content of the project chart is modified according to the received information, and when the project chart is modified, the chart display module (26) sends the project information in the modified project chart to the project calculation module (25) for recalculation.
10. A computer-readable medium, characterized in that: a computer program which can be loaded by a processor and which executes the method according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010973483.9A CN112200532B (en) | 2020-09-16 | 2020-09-16 | Method and system for intelligent calculation of construction period and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010973483.9A CN112200532B (en) | 2020-09-16 | 2020-09-16 | Method and system for intelligent calculation of construction period and computer readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112200532A true CN112200532A (en) | 2021-01-08 |
| CN112200532B CN112200532B (en) | 2024-07-19 |
Family
ID=74016389
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010973483.9A Active CN112200532B (en) | 2020-09-16 | 2020-09-16 | Method and system for intelligent calculation of construction period and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200532B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095786A (en) * | 2021-04-20 | 2021-07-09 | 广联达科技股份有限公司 | Delay prediction method and prediction device for construction project |
| CN113298363A (en) * | 2021-05-11 | 2021-08-24 | 福建万川信息科技股份有限公司 | Insurance bond and contract performing engineering risk prediction method |
| CN113869684A (en) * | 2021-09-17 | 2021-12-31 | 湖南方圆工程咨询监理有限公司 | BIM-based project progress management method, device and system |
| CN114969901A (en) * | 2022-05-10 | 2022-08-30 | 深圳采骏绿碳供应链有限公司 | Building equipment and building information model matching method and device |
| CN115357995A (en) * | 2022-10-21 | 2022-11-18 | 深圳市地铁集团有限公司 | Inter-city railway cloud model data fusion calculation method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130335413A1 (en) * | 2012-06-13 | 2013-12-19 | National Chiao Tung University | System and method for estimating construction duration |
| US20170249574A1 (en) * | 2016-02-26 | 2017-08-31 | A2PS Consulting and Software LLC | System for monitoring of workflows capable of automatic task allocation and monitoring of resources |
| CN109784781A (en) * | 2019-03-04 | 2019-05-21 | 中铁隧道局集团有限公司 | A kind of project management system served as theme with project progress, method and storage medium |
| CN110619143A (en) * | 2019-08-05 | 2019-12-27 | 中铁隧道局集团有限公司 | Drilling and blasting method tunnel construction simulation system established by taking time-cost as evaluation model |
| CN110956507A (en) * | 2019-12-16 | 2020-04-03 | 广州合道信息科技有限公司 | Method and device for calculating full-period node construction period, computer equipment and storage medium |
| CN111178605A (en) * | 2019-12-19 | 2020-05-19 | 国网浙江省电力有限公司丽水供电公司 | Distribution network engineering project construction period prediction method based on feature selection |
| CN111311090A (en) * | 2020-02-13 | 2020-06-19 | 北京轩宇信息技术有限公司 | Intelligent scheduling method and device based on big data calculation and analysis |
| CN111506876A (en) * | 2020-04-02 | 2020-08-07 | 沈阳数云科技有限公司 | Data prediction analysis method, system, equipment and readable storage medium |
| CN111598379A (en) * | 2020-03-31 | 2020-08-28 | 中铁建华南建设有限公司 | Project management method, platform, device, computer equipment and storage medium |
-
2020
- 2020-09-16 CN CN202010973483.9A patent/CN112200532B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130335413A1 (en) * | 2012-06-13 | 2013-12-19 | National Chiao Tung University | System and method for estimating construction duration |
| US20170249574A1 (en) * | 2016-02-26 | 2017-08-31 | A2PS Consulting and Software LLC | System for monitoring of workflows capable of automatic task allocation and monitoring of resources |
| CN109784781A (en) * | 2019-03-04 | 2019-05-21 | 中铁隧道局集团有限公司 | A kind of project management system served as theme with project progress, method and storage medium |
| CN110619143A (en) * | 2019-08-05 | 2019-12-27 | 中铁隧道局集团有限公司 | Drilling and blasting method tunnel construction simulation system established by taking time-cost as evaluation model |
| CN110956507A (en) * | 2019-12-16 | 2020-04-03 | 广州合道信息科技有限公司 | Method and device for calculating full-period node construction period, computer equipment and storage medium |
| CN111178605A (en) * | 2019-12-19 | 2020-05-19 | 国网浙江省电力有限公司丽水供电公司 | Distribution network engineering project construction period prediction method based on feature selection |
| CN111311090A (en) * | 2020-02-13 | 2020-06-19 | 北京轩宇信息技术有限公司 | Intelligent scheduling method and device based on big data calculation and analysis |
| CN111598379A (en) * | 2020-03-31 | 2020-08-28 | 中铁建华南建设有限公司 | Project management method, platform, device, computer equipment and storage medium |
| CN111506876A (en) * | 2020-04-02 | 2020-08-07 | 沈阳数云科技有限公司 | Data prediction analysis method, system, equipment and readable storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095786A (en) * | 2021-04-20 | 2021-07-09 | 广联达科技股份有限公司 | Delay prediction method and prediction device for construction project |
| CN113298363A (en) * | 2021-05-11 | 2021-08-24 | 福建万川信息科技股份有限公司 | Insurance bond and contract performing engineering risk prediction method |
| CN113869684A (en) * | 2021-09-17 | 2021-12-31 | 湖南方圆工程咨询监理有限公司 | BIM-based project progress management method, device and system |
| CN114969901A (en) * | 2022-05-10 | 2022-08-30 | 深圳采骏绿碳供应链有限公司 | Building equipment and building information model matching method and device |
| CN115357995A (en) * | 2022-10-21 | 2022-11-18 | 深圳市地铁集团有限公司 | Inter-city railway cloud model data fusion calculation method and device |
| CN115357995B (en) * | 2022-10-21 | 2023-04-07 | 深圳市地铁集团有限公司 | Inter-city railway cloud model data fusion calculation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112200532B (en) | 2024-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200532B (en) | Method and system for intelligent calculation of construction period and computer readable medium | |
| CN107464025B (en) | Supply chain demand prediction and intelligent decision method based on big data | |
| CN110046865B (en) | Distributed inventory scheduling method | |
| US8670962B2 (en) | Process simulation utilizing component-specific consumption data | |
| CN106681291A (en) | Production scheduling method and system | |
| CN101261695A (en) | A real time dynamic re-dispatching method for production dispatching system in process industry | |
| CN110880097B (en) | Project progress simulation display method and device | |
| Schuh et al. | Methodology for the evaluation of forecast reliability of production planning systems | |
| CN103500375A (en) | EM-Plant-based MES (Manufacturing Execution Systems) dispatching control method | |
| CN112541749A (en) | Construction progress management system based on BIM technology | |
| CN107516149B (en) | Enterprise supply chain management system | |
| KR20220115357A (en) | A method and apparatus for generating future demand forecast data based on attention mechanism | |
| Chen | Integrated optimization model for production planning and scheduling with logistics constraints | |
| CN115965154A (en) | Knowledge graph-based digital twin machining process scheduling method | |
| CN114881301A (en) | Simulation scheduling method and system for production line, terminal device and storage medium | |
| CN116630082A (en) | Method and device for allocating production resources, electronic equipment and storage medium | |
| CN101261694A (en) | A simulation validation method for virtualization dispatching optimization in process industry | |
| KR20120133362A (en) | Optimized production scheduling system using loading simulation engine with dynamic feedback scheduling algorithm | |
| CN115545329A (en) | Integrated dynamic scheduling method suitable for clothing manufacturing production line | |
| CN115374641A (en) | Visual editing method suitable for production scheduling of three-dimensional virtual factory | |
| Mei et al. | A computing model: the closed-loop optimal control for large-scale one-of-a-kind production based on multilevel hierarchical PERT-Petri net | |
| CN113031556A (en) | Multisource industrial data acquisition system based on network collaborative manufacturing | |
| Kim et al. | Computational shipyard dynamics | |
| CN109032075A (en) | A kind of intelligence steel construction stock method and system | |
| CN114896678B (en) | Construction method and system of engineering construction BIM model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |