CN115392808B - Building construction prediction progress and allocation system based on deep learning - Google Patents
Building construction prediction progress and allocation system based on deep learning Download PDFInfo
- Publication number
- CN115392808B CN115392808B CN202211341494.0A CN202211341494A CN115392808B CN 115392808 B CN115392808 B CN 115392808B CN 202211341494 A CN202211341494 A CN 202211341494A CN 115392808 B CN115392808 B CN 115392808B
- Authority
- CN
- China
- Prior art keywords
- building construction
- building
- house
- construction
- module
- 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.)
- Active
Links
- 238000009435 building construction Methods 0.000 title claims abstract description 169
- 238000013135 deep learning Methods 0.000 title claims abstract description 35
- 238000010276 construction Methods 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 28
- 239000000463 material Substances 0.000 claims abstract description 18
- 230000006870 function Effects 0.000 claims description 13
- 239000004566 building material Substances 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 239000004568 cement Substances 0.000 claims description 3
- 229910000831 Steel Inorganic materials 0.000 claims 1
- 238000004364 calculation method Methods 0.000 claims 1
- 239000010959 steel Substances 0.000 claims 1
- 238000012790 confirmation Methods 0.000 abstract description 3
- 239000004035 construction material Substances 0.000 description 3
- 229910001294 Reinforcing steel Inorganic materials 0.000 description 2
- 238000007792 addition Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06314—Calendaring for a resource
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of building construction prediction progress and allocation, and particularly relates to a building construction prediction progress and allocation system based on deep learning; the prepared material and manpower data are input to each house building department through a house building department data module and are transmitted to a house building prediction module; after the house is built for a period of time, the shot photo of the house under construction is collected through a picture collecting module and uploaded to a deep learning picture recognition platform; determining the data of the building construction completion degree according to the picture identification result and personnel; the data of the building construction completion degree is transmitted to a building construction allocation module; the method can effectively predict the completion degree of the building construction by the existing data without completely depending on the confirmation of the completion degree of the building construction by manpower; and a more accurate allocation mechanism is provided for the house construction, and the house construction can be allocated in more aspects when the difference between the prediction completion degree and the building construction completion degree is met.
Description
Technical Field
The invention belongs to the technical field of building construction prediction progress and allocation, and particularly relates to a building construction prediction progress and allocation system based on deep learning.
Background
The house construction is a project frequently encountered by construction units, but the house construction progress lacks an accurate prediction and allocation mechanism; the completion degree of house construction cannot be effectively predicted according to the existing data, and future projects are lack of grasp; high-tech application is not introduced in the house construction process, the completion degree is seriously determined by manpower, and an auxiliary mechanism is lacked; a detailed deployment mechanism cannot be performed based on the difference between the predicted completion and the actual completion.
On one hand, the existing data cannot be used for effectively predicting the completion degree of building construction on the one hand; the completion confirmation of the house construction is seriously depended on the manual work; not only can the building construction completion degree be predicted, but also the future building construction progress can not be planned for a long time; on the other hand, the house construction does not have a more precise allocation mechanism for the house construction, and when the difference between the prediction completion degree and the house construction is met, the house construction cannot be allocated in more aspects, and an elastic mechanism for the house construction is lacked.
Disclosure of Invention
The invention is based on the technical problems, and the system for predicting the building construction progress and allocating is used for providing a system for predicting the building construction progress and allocating based on deep learning;
the method not only can effectively predict the completion degree of the building construction by the existing data and does not completely depend on manual confirmation of the completion degree of the building construction, but also can provide a more accurate allocation mechanism for the building construction.
The invention is realized by the following steps:
the invention provides a building construction prediction progress and allocation system based on deep learning, which applies a picture collection module, a building construction department data module, a deep learning picture identification platform, a building construction prediction module and a building construction allocation module; characterized in that the method comprises the following steps:
step1, each house building department inputs prepared material and manpower data through a house building department data module;
step2: transmitting the data collected by the data module of the house building department to the house building prediction module;
step3, after the house is built for a period of time, the photo of the house under construction is collected through the picture collecting module and uploaded to the deep learning picture recognition platform;
step 4, transmitting the completion data to a house construction allocation module according to the picture identification result and the house construction;
and 5, carrying out house building material and manpower data allocation through a house building allocation module.
According to one implementation manner of the aspect of the invention, the specific operation method for inputting the prepared material and human data by each department of building construction in the step1 comprises the following steps:
various departments of building construction include: reinforcing steel bar department, human resource and cement department; marking phi for each department of building construction β Wherein β =0,1,2, · n; n is a positive integer and represents the maximum value of the value of beta in each department of building construction; prepared material and human data representation for building constructionThe required construction materials and the number of people who need to participate in the construction.
According to one possible implementation manner of the aspect of the present invention, the method for transmitting the data collected by the building construction department data module in the step2 to the building construction prediction module comprises:
calculating and analyzing the collected data through a building construction prediction module to obtain the required building construction completion degree according to the existing material and manpower data under the normal condition;
assuming that input data for each factor affecting house construction is set to x 1 ，x 2 ,x 3 ...x n (ii) a The weight of each influencing factor is set as a 1 ，a 2 ,a 3 ...a n (ii) a The estimated completion is set to y;
according to the mathematical formula:
an objective function:
the weight values are expressed as:
the house building prediction module mainly depends on the weight value of each factor influencing house building, the weight value is used as an independent variable, and the house building prediction result is a dependent variable; the existing completion degree representation occurring under similar conditions is based on historical experience data and the completion condition of building construction under the same condition, and new building construction is predicted; the two are rare in life based on the same situation, the similar situations are more, and the difference of the similar situations is not more than 5%;
different degrees of completeness are required, and the weight values are different;
predicting the final completion degree:
because each influence factor on the building construction is different, the corresponding percentage in the building construction is also different, although the historical experience can generate the percentage in the size range, the percentage of the maximum value is taken to ensure that the building construction is finished on time when the prediction condition of the building construction is realized in practice, and the influence on the building construction under the extreme condition is avoided; thus, in the building construction prediction module, the percentage of the maximum value of the input data for each factor affecting building construction has been previously defined based on prior historical empirical data.
According to an implementation manner of the aspect of the present invention, the method for collecting the photo of the building under construction in step3 and uploading the photo to the deep learning picture recognition platform includes:
after the house is built for a period of time, the shot photo of the house under construction is collected through a picture collecting module and uploaded to a deep learning picture recognition platform;
the house photos mainly comprise multi-angle shooting scenes and construction photos concentrated on the building construction surface;
step1: shooting pictures from multiple angles and uploading the pictures to a deep learning picture identification platform;
step2: identifying the uploaded photos according to the photos with different completion degrees of the house construction trained by the deep learning picture identification platform;
step3: identifying a degree of completion of building construction occurring;
the method comprises the following specific steps: dividing the picture into N x N pixels, each pixel representing a neuron, all the pixels being arranged in a row as a first layer of a neural network, i.e. an input layer, only the data of the input layer being known for generating a first layer of the hidden layer;
secondly, hiding the first layer of the layer for identifying edges or edges, that is, generating the edges or edges of the image after the pixels of the first layer are input, that is, only identifying the least important places of the image;
then, the first layer of the hidden layer is used as input for the second layer of the hidden layer, generating angles and contours, the second layer of the hidden layer generating more detailed image content;
finally, assuming a total of three hidden layers, the second layer of the hidden layers is used as input for the third layer of the hidden layers, resulting in a more detailed picture, such as a local feature of the building construction. The characteristic pictures are used as input of an output layer to generate a target image; basic knowledge such as a sensor, a loss function, a back propagation algorithm, a learning rate, a filter, gradient descent, forward propagation and the like is used in the construction of the whole network;
preliminarily performing machine learning on the building construction completion degree, and determining and changing the building construction by combining construction site professionals; if the current building construction completion is different from the data of the initial forecast, the current building construction completion needs to be transmitted to the building construction deployment module.
One way in which aspects of the invention can be achieved is characterized in that: the concrete operation method of the house building and allocation module in the step 5 comprises the following steps:
assuming that the difference between the actual completion degree value and the predicted completion degree value of the house construction is M in absolute value of the ratio of the actual completion degree value, y is the predicted completion degree,
the actual completion degree is; the number of deployments for building construction is i =1,2,3.. N;
input value, x, for allocation of factors affecting building construction i Values of actual factors occurring for building a house;
according to the numerical value determined by M, under the allocation of i influence factors, the values of the two sides are converged to achieve the similarity or the equality of the predicted completion value and the actual completion value of the building construction;
increasing the number of people or the number of materials under the condition of meeting the determined value of M, and the like, X i The value of (a) is constantly changing; as long as X i After the value of (c) is entered, the cumulative addition of the left-hand equations equals M, indicating thatThe allocation is carried out on each door of the house construction.
A cloud system predicts the completion degree of a house building prediction module according to data input by each department of the house building, and after the house building is carried out for a period of time, the completion degree recognition is carried out on the house building based on a deep learning picture recognition platform and the resource allocation is carried out through a house building allocation module; and predicting the progress and allocation of the house construction through cloud computing and analysis.
Based on any one of the aspects, the invention has the beneficial effects that:
1. the invention inputs prepared material and manpower data to each house building department through a house building department data module, and transmits the data to a house building prediction module; after the house is built for a period of time, the shot photo of the house under construction is collected through a picture collecting module and uploaded to a deep learning picture recognition platform; determining the data of the building construction completion degree according to the picture identification result and personnel; on one hand, the method can effectively predict the completion degree of building construction by the existing data; the completion degree of building construction is confirmed without completely depending on manpower; the method can not only predict the building construction completion degree, but also plan the building construction progress in the future.
2. According to the invention, the data of the building construction completion degree is transmitted to the building construction allocation module, and the building construction materials and the manpower data are allocated through the building construction allocation module; preliminarily performing machine learning on the building construction completion degree, and determining and changing the building construction by combining construction site professionals; if the building construction completion degree is different from the data of starting prediction, the building construction completion degree needs to be transmitted to a building construction allocation module; the house is built and a more accurate allocation mechanism is provided for the house, and the house can be allocated in more aspects when the difference between the predicted completion degree and the house is met.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a flow chart of the method steps of the present invention.
Detailed Description
While the foregoing is directed to embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.
With reference to fig. 1, a system for predicting progress and allocation of building construction based on deep learning applies a picture collection module, a data module of a building construction department, a deep learning picture recognition platform, a building construction prediction module, and a building construction allocation module; characterized in that the method comprises the following steps:
step1, each house building department inputs prepared material and manpower data through a house building department data module;
in a specific embodiment of the present invention, the specific operation method for inputting prepared material and human data by each department of building construction in step1 includes:
various departments of building construction include: reinforcing steel bar department, human resource and cement department; marking phi for each department of building construction β Wherein β =0,1,2, ·, n; n is a positive integer and represents the maximum value of the value of beta in each department of building construction; the prepared material and labor data represent the building materials required for the building construction and the number of people required to participate in the construction.
Step2: transmitting the data collected by the data module of the house building department to the house building prediction module;
in an embodiment of the present invention, the operation method of transmitting the data collected by the building construction department data module in the step2 to the building construction prediction module includes:
calculating and analyzing the collected data through a building construction prediction module to obtain the required building construction completion degree according to the existing material and manpower data under the normal condition;
assuming that input data for each factor affecting house construction is set to x 1 ，x 2 ,x 3 ...x n (ii) a The weight of each influencing factor is set as a 1 ，a 2 ,a 3 ...a n (ii) a The estimated completion is set to y;
according to the mathematical formula:
an objective function:
the weight values are expressed as:
the house building prediction module mainly depends on the weight value of each factor influencing house building, the weight value is used as an independent variable, and the house building prediction result is a dependent variable; the existing completion degree representation occurring under similar conditions is based on historical experience data and the completion condition of building construction under the same condition, and new building construction is predicted; the two are rare in life based on the same situation, the similar situations are more, and the difference of the similar situations is not more than 5%;
different degrees of completeness are required, and the weight values are different;
predicting the final completion degree:
because each influence factor on the building construction is different, the corresponding percentage in the building construction is also different, although the percentage in the large-small range can be generated in the historical experience, the percentage of the maximum value is taken to ensure that the building construction is completed on time when the prediction condition of the building construction is carried out in practice, and the influence on the building construction under the extreme condition is avoided; thus, in the building construction prediction module, the percentage of the maximum value of the input data for each factor affecting building construction has been previously defined based on prior historical empirical data.
Step3, after the house is built for a period of time, the photo of the house under construction is collected through the picture collecting module and uploaded to the deep learning picture recognition platform;
in a specific embodiment of the present invention, the method for collecting the photo of the building under construction by the photo collection module in step3 and uploading the photo to the deep learning photo recognition platform includes:
after the house is built for a period of time, the shot photo of the house under construction is collected through a picture collecting module and uploaded to a deep learning picture recognition platform;
the house photos mainly comprise multi-angle shooting scenes and construction photos concentrated on the building construction surface;
step1: shooting pictures from multiple angles and uploading the pictures to a deep learning picture identification platform;
step2: identifying the uploaded photos according to the photos with different completion degrees of the house construction trained by the deep learning picture identification platform;
step3: identifying a degree of completion of building construction occurring;
the method comprises the following specific steps: dividing the picture into N x N pixels, each pixel representing a neuron, all the pixels being arranged in a row as a first layer of a neural network, i.e. an input layer, only the data of the input layer being known for generating a first layer of the hidden layer;
secondly, hiding the first layer of the layer for identifying edges or edges, that is, generating the edges or edges of the image after the pixels of the first layer are input, that is, only identifying the least important places of the image;
then, the first layer of the hidden layer is used as input for the second layer of the hidden layer, generating angles and contours, the second layer of the hidden layer generating more detailed image content;
finally, assuming a total of three hidden layers, the second layer of the hidden layers is used as input for the third layer of the hidden layers, resulting in a more detailed picture, such as a local feature of the building construction. The characteristic pictures are used as input of an output layer to generate a target image; basic knowledge such as a sensor, a loss function, a back propagation algorithm, a learning rate, a filter, gradient descent, forward propagation and the like is used in the construction of the whole network;
preliminarily performing machine learning on the building construction completion degree, and determining and changing the building construction by combining construction site professionals; if the current building construction completion is different from the data of the initial forecast, the current building construction completion needs to be transmitted to the building construction deployment module.
Step 4, the data of the completion degree of the building construction is transmitted to a building construction allocation module according to the picture recognition result and the building construction;
and 5, carrying out house building material and manpower data allocation through a house building allocation module.
In an embodiment of the present invention, the specific operation method of the building construction deployment module in step 5 includes:
assuming that the absolute value of the ratio of the difference between the actual completion value of the house construction and the predicted completion value is M, y is the predicted completion,
the actual completion degree is; the allocation quantity for building construction is i =1,2,3.. N;
input value, x, for allocation of factors affecting building construction i Values of actual factors occurring for building a house;
according to the numerical value determined by M, under the allocation of i influence factors, the values of the two sides are converged to achieve the similarity or the equality of the predicted completion value and the actual completion value of the building construction;
increasing the number of people or the number of materials under the condition of meeting the determined value of M, and the like, wherein X is i The value of (a) is constantly changing; as long as X i When the values of (a) are entered, the left equation sums up cumulatively to equal M, indicating that the allocation of the building construction sections has been performed.
A cloud system predicts the completion degree of a house building prediction module according to data input by each department of the house building, and after the house building is carried out for a period of time, the completion degree recognition is carried out on the house building based on a deep learning picture recognition platform and the resource allocation is carried out through a house building allocation module; and predicting the progress and allocation of the building construction through cloud computing and analysis.
Example 2 assuming an actual completion value of 20%, a predicted completion value of 30%; the distance difference is between the predicted completion degree and the predicted completion degree, and the allocation is needed;
according to the mathematical formula:
m =50%, M being the difference between the actual completion value and the predicted completion value of the building construction, accounting for the absolute value of the ratio of the actual completion values; i.e. the progress that needs to be increased; then the above mathematical formula is substituted;
suppose that 50 persons are actually used for building a house;
calculate out
=25, so we need to increase the number of people to a value of 75 people to compensate for the predicted completion;
in real life, the construction progress of building construction is allocated with various numerical changes, such as the number of people, materials and the like; as long as the calculated and accumulated added value of the allocated value is equal to or approximately equal to the value of M, the allocation of the building construction is accurate;
the invention inputs prepared material and manpower data to each house building department through a house building department data module, and transmits the data to a house building prediction module; after the house is built for a period of time, the shot photo of the house under construction is collected through a picture collecting module and uploaded to a deep learning picture recognition platform; determining the data of the building construction completion degree according to the picture identification result and personnel; the data of the building construction completion degree is transmitted to a building construction allocation module, and the building construction materials and the manpower data are allocated through the building construction allocation module; preliminarily performing machine learning on the building construction completion degree, and determining and changing the building construction by combining construction site professionals; if the building construction completion degree is different from the data of starting prediction, the building construction completion degree needs to be transmitted to a building construction allocation module; on one hand, the method can effectively predict the completion degree of building construction by the existing data; the completion degree of building construction is confirmed without completely depending on manpower; not only can the building construction completion degree be predicted, but also the future building construction progress can be planned for a long time; the house is built and a more accurate allocation mechanism is provided for the house, and the house can be allocated in more aspects when the difference between the predicted completion degree and the house building is met.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (3)
1. A building construction prediction progress and deployment method based on deep learning is disclosed, which applies a picture collection module, a building construction department data module, a deep learning picture identification platform, a building construction prediction module and a building construction deployment module, and is characterized by comprising the following steps:
step1, each house building department inputs prepared material and manpower data through a house building department data module;
step2: transmitting the data collected by the data module of the house building department to a house building prediction module to obtain the house building prediction completion degree;
step3, collecting the shot photos of the house under construction through a picture collecting module, and uploading the photos to a deep learning picture recognition platform to obtain the actual building construction completion degree;
step 4, transmitting the predicted building construction completion degree and the actual building construction completion degree to a building construction allocation module;
step 5, carrying out house building material and manpower data allocation through a house building allocation module;
the concrete operation method for inputting prepared material and manpower data by each department of building construction in the step1 comprises the following steps:
each department of building construction comprises a steel bar department, a human resource department and a cement department; marking phi for each department of building construction β Wherein β =0,1,2, ·, n; n is a positive integer and represents the maximum value of the value of beta in each department of building construction; the prepared material and manpower data represent the building materials needed by the building construction and the number of people needing to participate in the construction;
the operation method for transmitting the data collected by the data module of the house building department in the step2 to the house building prediction module comprises the following steps:
the building construction prediction completion degree is obtained for the collected material and manpower data through a building construction prediction module;
assuming that input data for each factor affecting house construction is set to x 1 ，x 2 ,x 3 ...x n (ii) a The weight of each influencing factor is set as a 1 ，a 2 ,a 3 ...a n (ii) a The prediction completion degree is set as y;
according to the mathematical formula:
an objective function:
predicting the final completion degree:
the picture collecting module in the step3 collects the shot house pictures which are being constructed, and uploads the pictures to the deep learning picture recognition platform, and the operation method comprises the following steps:
the method comprises the steps that a shot house photo under construction is collected through a picture collecting module and uploaded to a deep learning picture recognition platform;
the house photos mainly comprise multi-angle shooting scenes and construction photos concentrated on the building construction surface;
step1: shooting pictures from multiple angles and uploading the pictures to a deep learning picture identification platform;
step2: identifying the uploaded photos according to the photos with different completion degrees of the house construction trained by the deep learning picture identification platform;
step3: identifying a degree of completion of building construction occurring;
preliminarily performing machine learning on the building construction completion degree, and determining the actual building construction completion degree by combining construction site professionals; if the actual building construction completion degree is different from the predicted building construction completion degree, the actual building construction completion degree and the predicted building construction completion degree need to be transmitted to the building construction allocation module.
2. The deep learning based house construction prediction progress and deployment method of claim 1, wherein: the concrete operation method of the house building and allocation module in the step 5 comprises the following steps:
under the condition of the allocation of the i influencing factors, the numerical values of the two sides are equal; y is the predicted completion, y '' is the actual completion; the number of deployments for building construction is i =1,2,3.. N;
input value, x, for allocation of factors affecting building construction i Values of actual factors occurring for building a house;
3. a cloud system, characterized in that: the completion degree prediction is carried out on a house building prediction module according to data input by each department for building, and the actual building completion degree is determined based on a deep learning picture recognition platform; performing the deep learning-based house construction prediction schedule and deployment method of any one of the above claims 1-2 by cloud computing and analyzing the house construction prediction schedule and deployment;
the cloud terminal realizes the building construction prediction progress and deployment method based on deep learning of any one of claims 1-2 on the prediction progress and deployment of building construction by means of a cloud terminal calculation and analysis service program under a network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211341494.0A CN115392808B (en) | 2022-10-31 | 2022-10-31 | Building construction prediction progress and allocation system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211341494.0A CN115392808B (en) | 2022-10-31 | 2022-10-31 | Building construction prediction progress and allocation system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115392808A CN115392808A (en) | 2022-11-25 |
| CN115392808B true CN115392808B (en) | 2023-01-13 |
Family
ID=84115310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211341494.0A Active CN115392808B (en) | 2022-10-31 | 2022-10-31 | Building construction prediction progress and allocation system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392808B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105933362A (en) * | 2016-07-13 | 2016-09-07 | 北京恒华伟业科技股份有限公司 | Project progress monitoring method, device, and system |
| CN107679310A (en) * | 2017-09-26 | 2018-02-09 | 华北电力大学 | The real-time progress 3 D stereo methods of exhibiting of engineering based on BIM and image congruencing technology |
| CN109472091A (en) * | 2018-11-13 | 2019-03-15 | 四川华芯项目管理有限公司 | A kind of assembled architecture construction and stage monitoring system and method for being on active service |
| CN112016908A (en) * | 2020-10-22 | 2020-12-01 | 广东恩胜科技有限公司 | BIM-based construction progress monitoring method and system, electronic equipment and storage medium |
| CN113609550A (en) * | 2021-07-05 | 2021-11-05 | 江苏徐工工程机械研究院有限公司 | BIM-based construction process planning management method and system |
| CN114580754A (en) * | 2022-03-09 | 2022-06-03 | 广州市建筑科学研究院集团有限公司 | Construction project progress management cooperative system and method based on machine learning |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4165284B2 (en) * | 2003-04-23 | 2008-10-15 | 株式会社日立プラントテクノロジー | Process progress management system |
| CN106484977A (en) * | 2016-09-28 | 2017-03-08 | 天津大学 | High arch dam construction progress self-adapting simulation analysis method |
| JP7555195B2 (en) * | 2020-03-27 | 2024-09-24 | 株式会社フジタ | Construction work management system and construction work management method |
| CN111476425A (en) * | 2020-04-15 | 2020-07-31 | 中道明华建设工程项目咨询有限责任公司 | Engineering project cost progress supervision system and method |
| CN113110313A (en) * | 2021-03-26 | 2021-07-13 | 广东建设职业技术学院 | Construction process control method based on digital twinning |
-
2022
- 2022-10-31 CN CN202211341494.0A patent/CN115392808B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105933362A (en) * | 2016-07-13 | 2016-09-07 | 北京恒华伟业科技股份有限公司 | Project progress monitoring method, device, and system |
| CN107679310A (en) * | 2017-09-26 | 2018-02-09 | 华北电力大学 | The real-time progress 3 D stereo methods of exhibiting of engineering based on BIM and image congruencing technology |
| CN109472091A (en) * | 2018-11-13 | 2019-03-15 | 四川华芯项目管理有限公司 | A kind of assembled architecture construction and stage monitoring system and method for being on active service |
| CN112016908A (en) * | 2020-10-22 | 2020-12-01 | 广东恩胜科技有限公司 | BIM-based construction progress monitoring method and system, electronic equipment and storage medium |
| CN113609550A (en) * | 2021-07-05 | 2021-11-05 | 江苏徐工工程机械研究院有限公司 | BIM-based construction process planning management method and system |
| CN114580754A (en) * | 2022-03-09 | 2022-06-03 | 广州市建筑科学研究院集团有限公司 | Construction project progress management cooperative system and method based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115392808A (en) | 2022-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Peng et al. | A self-learning dynamic path planning method for evacuation in large public buildings based on neural networks | |
| CN109523107A (en) | A kind of Construction Management System and method based on BIM | |
| CN104573359B (en) | A kind of mass-rent labeled data integration method of task based access control difficulty and mark person's ability | |
| JP2635087B2 (en) | Process control method | |
| WO2020056669A1 (en) | Control method and apparatus for unmanned aerial vehicle cruise based on prefabricated building platform | |
| CN107679310A (en) | The real-time progress 3 D stereo methods of exhibiting of engineering based on BIM and image congruencing technology | |
| El-Sawalhi et al. | A neural network model for building construction projects cost estimating | |
| JPH09244705A (en) | Device and method for supporting control model constitution | |
| CN112150031B (en) | Highway engineering construction progress management method and system based on big data | |
| CN115766501B (en) | Tunnel construction data management system and method based on big data | |
| CN113240249A (en) | Urban engineering quality intelligent evaluation method and system based on unmanned aerial vehicle augmented reality | |
| CN115392791B (en) | Smart city public facility management method, system and medium based on Internet of things | |
| CN111950195B (en) | Project progress prediction method based on portrait system and depth regression model | |
| CN115392808B (en) | Building construction prediction progress and allocation system based on deep learning | |
| CN116797157B (en) | River course treatment engineering cost management system based on artificial intelligence | |
| CN114742987B (en) | Automatic positioning control method and system for cutting of non-metallic materials | |
| CN107229970B (en) | The adaptive dynamic self study on-line monitoring system of shared direct drinking water quality | |
| CN113128788A (en) | Power emergency material conveying path optimization method and device and storage medium | |
| CN116385969A (en) | Personnel gathering detection system based on multi-camera cooperation and human feedback | |
| Fergusson et al. | Achieving industrial facility quality: Integration is key | |
| CN117114619A (en) | Project security management system based on big data analysis | |
| CN117093822B (en) | Industrial brain data analysis platform based on industrial knowledge graph | |
| KR101843286B1 (en) | Apparatus for prediction of process duration using artificail neural network and method thereof | |
| CN107894970A (en) | Terminal leaves the port the Forecasting Methodology and system of number | |
| CN115293465A (en) | Crowd density prediction method and system |
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 | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230630 Address after: Room 301, Building 1, No. 2, Shangqiao Industrial Road, Dongcheng Street, Dongguan City, Guangdong Province 523000 Patentee after: Guangdong Hongsheng Construction Labor Subcontracting Co.,Ltd. Address before: No. 9, Qingshi Road, Lvyuan District, Changchun, Jilin 130062 Patentee before: Changchun Longjia Network Technology Co.,Ltd. |