CN117952572A

CN117952572A - Construction job file information generation method based on big data analysis

Info

Publication number: CN117952572A
Application number: CN202410355717.1A
Authority: CN
Inventors: 严宇平; 王国瑞; 裴求根; 周昉昉; 陆宏治; 谢瀚阳
Original assignee: Guangdong Power Grid Co Ltd
Current assignee: Guangdong Power Grid Co Ltd
Priority date: 2024-03-27
Filing date: 2024-03-27
Publication date: 2024-04-30

Abstract

The application relates to a construction job file information generation method, a construction job file information generation device, a construction job file information generation computer device, a construction job file information generation storage medium and a construction job file information generation computer program product. The method comprises the following steps: acquiring engineering information of a plurality of sub-projects of a construction project and object qualification information of a plurality of construction execution objects; detecting matching degrees between the plurality of sub-projects and the plurality of construction execution objects according to the project information of the plurality of sub-projects and the object qualification information of the plurality of construction execution objects to obtain a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features; and generating scheduling information between the plurality of sub-projects and the plurality of construction execution objects according to the plurality of first matching degree features and the matching degree scores corresponding to the plurality of first matching degree features. By adopting the method, the scheduling information generation accuracy of the construction project can be improved.

Description

Construction job file information generation method based on big data analysis

Technical Field

The present application relates to the field of big data technology, and in particular, to a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for generating construction job file information based on big data analysis.

Background

At present, for large-scale construction projects, the whole construction project is generally split into a plurality of sub-projects and is sub-divided into different construction execution objects (construction execution objects) to be completed, so that the construction efficiency is improved and the resource allocation is optimized.

However, due to the collaborative cooperation involving a plurality of construction execution objects, it is generally required to generate construction job file information based on big data analysis through manual auditing, and a plurality of sub-projects are reasonably distributed to the plurality of construction execution objects by using the scheduling information, but auditing standards of different auditors are generally different, so that subjectivity is high, and therefore each sub-project cannot be accurately distributed to the most suitable construction execution object based on the scheduling information, and the accuracy of the scheduling information generation remains to be agreed.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a construction job file information generation method, apparatus, computer device, computer-readable storage medium, and computer program product based on big data analysis that can improve the accuracy of scheduling information generation of construction projects.

In a first aspect, the present application provides a construction job file information generation method based on big data analysis. The method comprises the following steps:

acquiring engineering information of a plurality of sub-projects of a construction project and object qualification information of a plurality of construction execution objects;

Detecting matching degrees between the plurality of sub-projects and the plurality of construction execution objects according to the project information of the plurality of sub-projects and the object qualification information of the plurality of construction execution objects to obtain a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features;

and generating scheduling information between the plurality of sub-projects and the plurality of construction execution objects according to the plurality of first matching degree features and the matching degree scores corresponding to the plurality of first matching degree features.

In one embodiment, the generating scheduling information between the multiple sub-projects and the multiple construction execution objects according to the multiple first matching degree features and the matching degree scores corresponding to the multiple first matching degree features includes:

Generating a plurality of coding features according to scheduling constraint information between the plurality of sub-projects and the plurality of construction execution objects, wherein the coding features are used for representing scheduling allocation information between the plurality of sub-projects and the plurality of construction execution objects; generating an adaptability value of each coding feature according to the matching degree scores; according to the fitness values of the plurality of coding features, performing iterative optimization on the plurality of first matching degree features by adopting a whale optimization algorithm to obtain a plurality of second matching degree features; and determining a target coding characteristic with the maximum fitness value in the plurality of coding characteristics according to the fitness values determined by the plurality of second matching degree characteristics, and generating scheduling information between the plurality of sub-projects and the plurality of construction execution objects according to the target coding characteristic.

In one embodiment, the performing iterative optimization on the first matching degree features by using a whale optimization algorithm according to the fitness values of the coding features to obtain second matching degree features includes:

The generation step is executed: generating a first random number; if the first random number is larger than a first preset threshold value, selecting a first matching degree feature with the largest fitness value as a first target matching degree feature; updating the first matching degree features according to the first target matching degree features and differences between the first target matching degree features and the first matching degree features aiming at each first matching degree feature; updating the fitness value of the plurality of coding features according to the updated plurality of first matching degree features; if the first random number is not greater than the first preset threshold value, randomly generating a first vector, a second random number corresponding to the first vector and a second vector corresponding to the second random number, wherein the first vector is used for representing iterative updating degrees of the plurality of first matching degree features; updating the plurality of first matching degree features according to the first vector, the second vector and the second random number, and updating the fitness values of the plurality of coding features according to the updated plurality of first matching degree features; if the updated first matching degree features do not meet the preset iteration update ending condition, returning to execute the generating step; and if the updated first matching degree features meet the preset iteration update ending condition, determining the updated first matching degree features as second matching degree features.

In one embodiment, the updating the plurality of first matching degree features according to the first vector, the second vector and the second random number includes:

If the second random number is larger than a second preset threshold value, for each first matching degree feature, randomly searching a second target matching degree feature from the plurality of first matching degree features; updating the first matching degree feature according to the first vector, the second target matching degree feature and the difference between the second target matching degree feature and the first matching degree feature; if the second random number is not greater than a second preset threshold value, selecting a first matching degree characteristic with the largest fitness value as a first target matching degree characteristic; for each matching degree feature, updating the first matching degree feature according to the first vector, the second vector, the first target matching degree feature and the difference between the first target matching degree feature and the first matching degree feature.

In one embodiment, the randomly generating the first vector includes:

Determining the current iterative optimization times of the first matching degree features, and acquiring the maximum iterative optimization times of the first matching degree features; and generating a first vector according to the first random number, the current iteration optimization times and the maximum iteration optimization times.

In one embodiment, the detecting, according to the project information of the multiple sub-projects and the object qualification information of the multiple construction execution objects, the matching degree between the multiple sub-projects and the multiple construction execution objects to obtain multiple first matching degree features and matching degree scores corresponding to the multiple first matching degree features includes:

Extracting the characteristics of the engineering information of the multiple sub-projects respectively to obtain the engineering information characteristics of the multiple sub-projects; extracting the characteristics of the object qualification information of the construction execution objects respectively to obtain the object qualification characteristics of the construction execution objects; carrying out feature fusion on the engineering information features of the multiple sub-projects and the object qualification features of the multiple construction execution objects to obtain multiple first matching degree features; and respectively predicting matching degree scores between the plurality of sub-projects and the plurality of construction execution objects according to the plurality of first matching degree features.

In one embodiment, the engineering information at least includes one of an engineering area, an engineering height, an engineering length, an engineering capacity, engineering budget information, and an engineering construction period; the object qualification information includes at least one of registered capital information, construction project experience information, the number of constructors, the number of construction equipment, the number of incidents, and the number of qualification certificates.

In a second aspect, the application further provides a construction job file information generation device based on big data analysis. The device comprises:

the acquisition module is used for acquiring engineering information of a plurality of sub-projects of the construction project and object qualification information of a plurality of construction execution objects;

The detection module is used for detecting the matching degree between the plurality of sub-projects and the plurality of construction execution objects according to the project information of the plurality of sub-projects and the object qualification information of the plurality of construction execution objects to obtain a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features;

And the generating module is used for generating scheduling information between the plurality of sub-projects and the plurality of construction execution objects according to the plurality of first matching degree features and the matching degree scores corresponding to the plurality of first matching degree features.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:

In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:

According to the construction job file information generation method, the device, the computer equipment, the computer storage medium and the computer program product based on big data analysis, firstly, the project information of a plurality of sub projects of a construction project and the object qualification information of a plurality of construction execution objects are obtained, and then the matching degree between the plurality of sub projects and the plurality of construction execution objects can be automatically detected according to the project information of the plurality of sub projects and the object qualification information of the plurality of construction execution objects, so that a plurality of first matching degree characteristics and matching degree scores corresponding to the plurality of first matching degree characteristics are obtained; and the scheduling information between a plurality of sub-projects and a plurality of construction execution objects can be accurately generated based on the matching degree scores corresponding to the plurality of first matching degrees and the plurality of first matching degree features, the construction operation file information based on big data analysis is not required to be generated in a manual auditing mode, the scheduling information generation mode is more objective and is not influenced by the supervisors of the auditing personnel, and therefore the accuracy of the scheduling information generation of the construction projects can be improved.

Drawings

FIG. 1 is a flow chart of a method for generating construction job file information based on big data analysis in an embodiment of the present application;

FIG. 2 is a flow chart of detecting matching between a plurality of sub-projects and a plurality of construction execution objects according to an embodiment of the present application;

FIG. 3 is a flow chart of generating scheduling information between a plurality of sub-projects and a plurality of construction execution objects according to an embodiment of the present application;

FIG. 4 is a block diagram of a construction job file information generating apparatus based on big data analysis in one embodiment of the present application;

Fig. 5 is an internal structural view of a computer device according to an embodiment of the present application.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

In one embodiment, as shown in fig. 1, a method for generating construction job file information based on big data analysis is provided, and this embodiment is exemplified by the application of the method to a terminal, it can be understood that the method can also be applied to a server, and can also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:

Step 202, acquiring engineering information of a plurality of sub-projects of a construction project and object qualification information of a plurality of construction execution objects.

The construction project can be divided into a plurality of sub-projects, the construction execution object can be the construction execution object of the construction project, and the number of the construction execution objects is usually a plurality of; the engineering information at least comprises one of engineering area, engineering height, engineering length, engineering capacity, engineering budget information and engineering construction period; the object qualification information includes at least one of registered capital information, construction project experience information, the number of constructors, the number of construction equipment, the number of incidents, and the number of qualification certificates.

And 204, detecting the matching degree between the plurality of sub-projects and the plurality of construction execution objects according to the project information of the plurality of sub-projects and the object qualification information of the plurality of construction execution objects to obtain a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features.

As an example, step 204 includes: respectively carrying out feature coding on engineering information of a plurality of sub-projects to obtain engineering information features corresponding to the plurality of sub-projects; performing feature coding on the plurality of object qualification information respectively to obtain object qualification features corresponding to a plurality of construction execution objects; and detecting the matching degree between the plurality of sub-projects and the plurality of construction execution objects according to the project information characteristics of the plurality of sub-projects and the object qualification characteristics of the plurality of construction execution objects, and obtaining a plurality of first matching degree characteristics and matching degree scores corresponding to the plurality of first matching degree characteristics.

The engineering information features and the object qualification features can be feature vectors, the first matching degree features can be obtained by combining the engineering information features and the object qualification features, and the matching degree scores can be obtained by predicting the features through first matching.

And 206, generating scheduling information between the multiple sub-projects and the multiple construction execution objects according to the multiple first matching degree features and the matching degree scores corresponding to the multiple first matching degree features.

As an example, step 206 includes: optimizing the first matching degree features by using a whale optimization algorithm according to matching degree scores corresponding to the first matching degree features to obtain second matching degree features; updating the matching degree score by fully connecting the plurality of second matching degree features; and generating scheduling information between the multiple sub-projects and the multiple construction execution objects according to the updated matching degree scores.

In the construction operation file information generation method based on big data analysis, firstly, the project information of a plurality of sub projects of a construction project and the object qualification information of a plurality of construction execution objects are obtained, and then according to the project information of the plurality of sub projects and the object qualification information of the plurality of construction execution objects, the matching degree between the plurality of sub projects and the plurality of construction execution objects can be automatically detected, so that a plurality of first matching degree characteristics and matching degree scores corresponding to the plurality of first matching degree characteristics are obtained; and the scheduling information between a plurality of sub-projects and a plurality of construction execution objects can be accurately generated based on the matching degree scores corresponding to the plurality of first matching degrees and the plurality of first matching degree features, the construction operation file information based on big data analysis is not required to be generated in a manual auditing mode, the scheduling information generation mode is more objective and is not influenced by the supervisors of the auditing personnel, and therefore the accuracy of the scheduling information generation of the construction projects can be improved.

In one embodiment, as shown in fig. 2, according to project information of a plurality of sub-projects and object qualification information of a plurality of construction execution objects, detecting matching degrees between the plurality of sub-projects and the plurality of construction execution objects, to obtain a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features, including:

And 302, respectively extracting the characteristics of the engineering information of the multiple sub-projects to obtain the engineering information characteristics of the multiple sub-projects.

In this embodiment, a matching degree evaluation model is provided, where the matching degree evaluation model is composed of a first coding layer, a second coding layer, a feature fusion layer, a hidden layer and a full connection layer.

As an example, step 302 includes: and respectively inputting the engineering information of the multiple sub-projects into the first coding layer, and respectively carrying out feature coding on the engineering information of the multiple sub-projects to obtain engineering information features of the multiple sub-projects.

And step 304, extracting the characteristics of the object qualification information of the plurality of construction execution objects to obtain the object qualification characteristics of the plurality of construction execution objects.

As an example, step 304 includes: and respectively inputting object qualification information of the construction execution objects into the second coding layer, and respectively performing feature coding on the object qualification information of the construction execution objects to obtain object qualification characteristics of the construction execution objects.

And 306, carrying out feature fusion on the engineering information features of the multiple sub-projects and the object qualification features of the multiple construction execution objects to obtain multiple first matching degree features.

As one example, step 306 includes: the method comprises the steps of carrying out feature fusion on engineering information features of a plurality of sub-projects and object qualification features of a plurality of construction execution objects by mixing the engineering information features of the plurality of sub-projects and the construction execution objects in pairs into a feature fusion layer, so as to obtain a plurality of fusion features, wherein the fusion mode can be splicing or weighted aggregation; and respectively mapping the fusion features into corresponding first matching degree features through the fusion feature input hiding layers.

As an example, the number of hidden layers may be one or more layers, e.g. the hidden layers may comprise a first hidden layer and a second hidden layer.

Step 308, predicting matching degree scores between every two of the plurality of sub-projects and the plurality of construction execution objects according to the plurality of first matching degree features.

As one example, step 308 includes: and inputting the plurality of first matching degree features into the full-connection layer, and respectively carrying out full connection on the plurality of first matching degree features to obtain matching degree scores between the plurality of sub-projects and the plurality of construction execution objects.

In this embodiment, feature extraction may be performed on engineering information of a plurality of sub-projects to generate a plurality of engineering information features, and feature extraction may be performed on object qualification information of a plurality of construction execution objects to generate a plurality of object qualification features, respectively; then fusing the engineering information features and the object qualification features to obtain a plurality of first matching degree features; and then, the first matching degree features are fully connected to obtain the first matching degree scores, so that the first matching degree features and the matching degree scores are automatically generated, manual intervention is not needed, and a foundation is laid for improving the accuracy of scheduling information generation.

In one embodiment, referring to fig. 3, generating scheduling information between a plurality of sub-projects and a plurality of construction execution objects according to a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features includes:

Step 402, generating a plurality of coding features according to scheduling constraint information between a plurality of sub-projects and a plurality of construction execution objects, wherein the coding features are used for representing scheduling allocation information between the plurality of sub-projects and the plurality of construction execution objects.

The scheduling constraint information may be constraint information for constraining the number of allocations between a plurality of sub-projects and a plurality of construction execution objects, for example, a first construction execution object may be allocated to each sub-project, a preset number of sub-projects may be allocated to at most one construction execution object, and the preset number may be set to 2; the coding feature is used for representing scheduling allocation information between a plurality of sub-projects and a plurality of construction execution objects, and is composed of a plurality of coding feature values, and each coding feature value is used for representing whether each sub-project is allocated to each construction execution object or whether each construction execution object is allocated to each sub-project.

As an example, the coding feature may be a coding matrix, which is expressed in the following form:

Wherein, For coding matrix,/>For coding eigenvalues in the coding matrix,/>Respectively, the 1 st construction execution object is allocated to the 1 st sub-project to the 1 st/>Distribution of sub-projects,/>Respectively represent that the 1 st sub-project is allocated to the 1 st construction execution object to the/>Distribution of individual construction execution objects,/>Representing the first of the coding matricesLine/>Coding feature values of columns and representing the/>Sub-engineering allocation to the/>And (3) the allocation situation of each construction execution object, wherein the coding characteristic value in the coding matrix is represented by 0 or 1, wherein 0 represents the construction execution object corresponding to the column of the coding characteristic value, which is not allocated to the sub-engineering corresponding to the row of the coding characteristic value, and 1 represents the construction execution object corresponding to the column of the coding characteristic value, which is allocated to the sub-engineering corresponding to the row of the coding characteristic value.

Step 404, generating fitness values of each coding feature according to the matching degree scores.

As an example, step 404 includes: for each coding feature, determining arrangement position information of each preset coding feature value in the coding feature; determining a plurality of target matching degree scores corresponding to the arrangement position information in the plurality of matching degree scores; and summing the multiple target matching degree scores to obtain the fitness value corresponding to the coding feature. For example, the coding feature is a coding matrix, and the arrangement position information may be the number of rows and columns where the preset coding feature value is located in the coding matrix.

As an example, the preset encoding feature value is used to indicate that the sub-project corresponding to the preset encoding feature value is allocated to the corresponding construction execution object, or used to indicate that the construction execution object corresponding to the preset encoding feature value is allocated to the corresponding sub-project, where the preset encoding feature value may be set to 1.

And step 406, performing iterative optimization on the first matching degree features by using a whale optimization algorithm according to the fitness values of the coding features to obtain second matching degree features.

As an example, step 406 includes: determining a maximum fitness value among a plurality of fitness values; and taking the first matching degree characteristic corresponding to the maximum fitness value as a target matching degree characteristic, and adopting a whale optimization algorithm to iteratively optimize the first matching degree characteristic to obtain a plurality of second matching degree characteristics.

And step 408, determining a target coding feature with the maximum fitness value in the plurality of coding features according to the fitness values determined by the plurality of second matching degree features, and generating scheduling information between a plurality of sub-projects and a plurality of construction execution objects according to the target coding feature.

As one example, step 408 includes: respectively carrying out full connection on the plurality of second matching degree features to obtain matching degree scores corresponding to the plurality of second matching degree features; aiming at each coding feature, according to the arrangement position information of each preset coding feature value in the coding features; re-determining a plurality of target matching degree scores corresponding to the arrangement position information in the matching degree scores corresponding to the plurality of second matching degree features; summing a plurality of target matching degree scores corresponding to the redetermined arrangement position information to obtain an adaptability value determined based on the second matching degree characteristics; and selecting the coding feature corresponding to the maximum adaptability value determined based on the second matching degree feature as a target coding feature, and generating scheduling information between a plurality of sub-projects and a plurality of construction execution objects according to the target coding feature.

In this embodiment, a plurality of coding features are generated according to scheduling constraint information between a plurality of sub-projects and a plurality of construction execution objects, where the coding features are used to characterize scheduling allocation information between the plurality of sub-projects and the plurality of construction execution objects, so that the plurality of coding features can be used as initial population individuals of a whale optimization algorithm, and thus fitness values of each initial population individual can be calculated according to a plurality of matching degree scores; according to the fitness value of each initial population individual, optimizing the first matching degree features by using a whale optimization algorithm to generate a plurality of second matching degree features with higher accuracy; and the scheduling information between the plurality of sub-projects and the plurality of construction execution objects is generated according to the target coding features, so that the scheduling information can be generated according to the second matching degree features with higher accuracy, and the scheduling information is generated with higher accuracy.

In one embodiment, according to fitness values of the plurality of coding features, iteratively optimizing the plurality of first matching features using a whale optimization algorithm to obtain a plurality of second matching features, including:

The generation step is executed: generating a first random number; if the first random number is larger than a first preset threshold value, selecting a first matching degree feature with the largest fitness value as a first target matching degree feature; updating the first matching degree features according to the first target matching degree features and the differences between the first target matching degree features and the matching degree features for each first matching degree feature; updating the fitness value of the plurality of coding features according to the updated plurality of first matching degree features; if the first random number is not greater than a first preset threshold value, randomly generating a first vector, a second random number corresponding to the first vector and a second vector corresponding to the second random number, wherein the first vector is used for representing iterative updating degrees of a plurality of first matching degree features; updating the plurality of first matching degree features according to the first vector, the second vector and the second random number, and updating the fitness values of the plurality of coding features according to the updated plurality of first matching degree features; if the updated first matching degree features do not meet the preset iteration update ending condition, returning to the execution generating step; and if the updated first matching degree features meet the preset iteration update ending condition, determining the updated first matching degree features as second matching degree features.

In this embodiment, in the process of iteratively optimizing the first matching degree feature based on the whale optimization algorithm, three ways exist for updating the first matching degree feature, which are respectively a "spiral attack" updating way, a "random search" updating way and a "surrounding prey" updating way.

Specifically, the generation step is performed: generating a first random number, wherein the first random number is within a preset value range, for example, the preset value range can be set to be 0 to 1; if the first random number is larger than a first preset threshold value, updating the first matching degree characteristic by adopting a spiral attack updating mode; generating a plurality of new matching degree scores by fully connecting the updated first matching degree features, and covering the matching degree scores before updating with the new matching degree scores; and recalculating the fitness values of the plurality of coding features according to the updated plurality of matching degree scores, and covering the fitness values before updating with the recalculated fitness values.

As an example, using a "spiral attack" update approach, updating the first matching degree feature includes:

for each first matching degree feature, selecting the first matching degree feature with the largest current fitness value as a first target matching degree feature, wherein when the preset value range is 0 to 1, a first preset threshold value can be set to be 0.5; and calculating the updated first matching degree characteristic according to the first target matching degree characteristic and the absolute value of the difference value between the first target matching degree characteristic and the first matching degree characteristic.

As an example, according to the first target matching degree feature, the absolute value of the difference between the first target matching degree feature and the first matching degree feature, the calculation formula of the updated first matching degree feature is as follows:

Wherein, For/>First/>, when updating the first matching degree feature for a second iterationFirst matching degree characteristics corresponding to the coding characteristics,/>For/>First target matching degree characteristics when the first matching degree characteristics are updated through iteration once,/>For/>First/>, when updating the first matching degree feature for a second iterationFirst matching degree characteristics corresponding to the coding characteristics,/>Is a natural constant,/>Is a constant value, and is used for the treatment of the skin,Is a random number between-1 and 1,/>As a cosine function.

Further, if the first random is not greater than a first preset threshold, randomly generating a first vector, and performing modulo operation on the first vector to obtain a second random number corresponding to the first vector; generating a second vector corresponding to the second random number by weighting the second random number, wherein the first vector is used for representing iterative updating degrees of a plurality of first matching degree features; updating the plurality of first matching degree features according to the first vector, the second vector and the second random number, and updating the fitness values of the plurality of coding features according to the updated plurality of first matching degree features; if the updated first matching degree features do not meet the preset iteration update ending condition, the generating step is executed in a returning mode, and iteration update of the next round is conducted on the first matching degree features; and if the updated first matching degree features meet the preset iteration update ending condition, determining the updated first matching degree features as second matching degree features.

As an example, the preset iteration update end condition may be that the maximum iteration optimization number is reached, or the updated first matching degree features continuously do not change during the preset iteration optimization number, for example, the change amounts of the first matching degree features continuously during the last three iteration optimizations are all smaller than a preset threshold, and then the updated first matching degree features are considered to continuously not change during the last three iteration optimizations.

In one embodiment, updating the plurality of first matching degree features based on the first vector, the second vector, and the second random number includes:

If the second random number is larger than a second preset threshold value, randomly searching a second target matching degree feature from a plurality of first matching degree features aiming at each first matching degree feature; updating the first matching degree feature according to the first vector, the second target matching degree feature and the difference between the second target matching degree feature and the first matching degree feature; if the second random number is not greater than a second preset threshold value, selecting a first matching degree characteristic with the largest fitness value as a first target matching degree characteristic; for each matching degree feature, updating the first matching degree feature according to the first vector, the second vector, the first target matching degree feature and the difference between the first target matching degree feature and the first matching degree feature.

Specifically, if the second random number is greater than a second preset threshold value, updating a plurality of first matching degree features in a random search mode; if the second random is not greater than the second preset threshold, updating the first matching degree features by adopting the direction of surrounding the prey.

Wherein updating the plurality of first matching degree features in a "random search" manner includes:

For each first matching degree feature, randomly selecting one first matching degree feature from a plurality of first matching degree features as a second target matching degree feature; weighting the second target matching degree feature according to the second vector, and weighting the difference absolute value of the first matching degree feature and the weighted second target matching degree feature according to the first vector to obtain a first weighting feature; and calculating the updated first matching degree characteristic according to the difference value between the second target matching degree characteristic and the first weighted characteristic, and covering the first matching degree characteristic before updating with the updated first matching degree characteristic.

As an example, the calculation formula for updating the plurality of first matching degree features in a "random search" manner is as follows:

Wherein, For/>First/>, when updating the first matching degree feature for a second iterationFirst matching degree characteristics corresponding to the coding characteristics,/>For/>Second target matching degree characteristic when first matching degree characteristic is updated by iterationFor/>First/>, when updating the first matching degree feature for a second iterationFirst matching degree characteristics corresponding to the coding characteristics,/>Is the first vector,/>Is the second vector.

Wherein updating the plurality of first fitness features with the direction of "surrounding the prey" comprises:

Selecting a first matching degree characteristic with the largest current fitness value as a first target matching degree characteristic; for each first matching degree feature, weighting the first target matching degree feature according to the second vector, and weighting the absolute value of the difference between the first matching degree feature and the weighted first target matching degree feature according to the first vector to obtain a second weighted feature; and calculating the updated first matching degree characteristic according to the difference value between the first target matching degree characteristic and the second weighted characteristic, and covering the first matching degree characteristic before updating with the updated first matching degree characteristic.

As an example, the calculation formula for updating the plurality of first matching degree features in a manner of "surrounding the prey" is as follows:

Wherein, For/>First/>, when updating the first matching degree feature for a second iterationFirst matching degree characteristics corresponding to the coding characteristics,/>For/>First target matching degree characteristics when the first matching degree characteristics are updated through iteration once,/>For/>First/>, when updating the first matching degree feature for a second iterationFirst matching degree characteristics corresponding to the coding characteristics,/>Is the first vector,/>Is the second vector.

In one embodiment, randomly generating the first vector includes:

Specifically, determining the current iterative optimization times of the first matching degree features, and acquiring the maximum iterative optimization times of the first matching degree features; and calculating the ratio between the current iteration optimization times and the maximum iteration optimization times, and generating a first vector according to the ratio and the first random number.

As an example, the calculation formula of the first vector is as follows:

Wherein, Is the first vector,/>Optimizing the number of times for the current iteration,/>For maximum iterative optimization times,/>Is a first random number.

As an example, the calculation formula of the second vector is as follows:

Wherein, Is the second vector,/>Is a second random number.

In this embodiment, based on a whale optimization algorithm, three update modes, namely a "spiral attack" update mode, a "random search" update mode and a "surrounding prey" update mode, are respectively set to perform further iterative optimization update on the plurality of first matching degree features, so that on one hand, the plurality of second matching degree features can be generated more accurately than the plurality of first matching degree features after the iterative update is completed, thereby generating a plurality of matching degree scores with better accuracy, on the other hand, the three update modes, namely the "spiral attack" update mode, the "random search" update mode and the "surrounding prey" update mode, perform further iterative optimization update on the plurality of first matching degree features, the update modes of the plurality of first matching degree features are more flexible and variable, are not easy to fall into local optimum, the plurality of first matching degree features can be converged more quickly, and the iterative optimization efficiency of the plurality of first matching degree features can be improved.

In one embodiment, first, project information of a plurality of sub-projects of a construction project and object qualification information of a plurality of construction execution objects are acquired; respectively carrying out feature coding on engineering information of a plurality of sub-projects to obtain engineering information features corresponding to the plurality of sub-projects; performing feature coding on the plurality of object qualification information respectively to obtain object qualification features corresponding to a plurality of construction execution objects; and detecting the matching degree between the plurality of sub-projects and the plurality of construction execution objects according to the project information characteristics of the plurality of sub-projects and the object qualification characteristics of the plurality of construction execution objects, and obtaining a plurality of first matching degree characteristics and matching degree scores corresponding to the plurality of first matching degree characteristics.

Further, generating a plurality of coding features according to scheduling constraint information between a plurality of sub-projects and a plurality of construction execution objects, wherein the coding features are used for representing scheduling allocation information between the plurality of sub-projects and the plurality of construction execution objects; for each coding feature, determining arrangement position information of each preset coding feature value in the coding feature; determining a plurality of target matching degree scores corresponding to the arrangement position information in the plurality of matching degree scores; and summing the multiple target matching degree scores to obtain the fitness value corresponding to the coding feature.

Further, the generating step is performed: generating a first random number, wherein the first random number is within a preset value range, for example, the preset value range can be set to be 0 to 1; if the first random number is greater than a first preset threshold, selecting a first matching degree feature with the largest current fitness value as a first target matching degree feature according to each first matching degree feature, wherein the first preset threshold can be set to be 0.5 when the preset value range is 0 to 1; calculating updated first matching degree features according to the first target matching degree features and the absolute value of the difference between the first target matching degree features and the first matching degree features; generating a plurality of new matching degree scores by fully connecting the updated first matching degree features, and covering the matching degree scores before updating with the new matching degree scores; and recalculating the fitness values of the plurality of coding features according to the updated plurality of matching degree scores, and covering the fitness values before updating with the recalculated fitness values.

Further, if the first random is not greater than a first preset threshold, randomly generating a first vector, and performing modulo operation on the first vector to obtain a second random number corresponding to the first vector; generating a second vector corresponding to the second random number by weighting the second random number, wherein the first vector is used for representing iterative updating degrees of a plurality of first matching degree features; if the second random number is larger than a second preset threshold, randomly selecting one first matching degree feature from a plurality of first matching degree features as a second target matching degree feature aiming at each first matching degree feature; weighting the second target matching degree feature according to the second vector, and weighting the difference absolute value of the first matching degree feature and the weighted second target matching degree feature according to the first vector to obtain a first weighting feature; and calculating the updated first matching degree characteristic according to the difference value between the second target matching degree characteristic and the first weighted characteristic, and covering the first matching degree characteristic before updating with the updated first matching degree characteristic.

Further, if the second random is not greater than a second preset threshold, selecting a first matching degree feature with the largest current fitness value as a first target matching degree feature; for each first matching degree feature, weighting the first target matching degree feature according to the second vector, and weighting the absolute value of the difference between the first matching degree feature and the weighted first target matching degree feature according to the first vector to obtain a second weighted feature; and calculating the updated first matching degree characteristic according to the difference value between the first target matching degree characteristic and the second weighted characteristic, and covering the first matching degree characteristic before updating with the updated first matching degree characteristic.

Further, updating the fitness value of the plurality of coding features according to the updated plurality of first matching degree features; if the updated first matching degree features do not meet the preset iteration update ending condition, returning to the execution generating step; if the updated first matching degree features meet the preset iteration update ending condition, determining the updated first matching degree features as second matching degree features; respectively carrying out full connection on the plurality of second matching degree features to obtain matching degree scores corresponding to the plurality of second matching degree features; aiming at each coding feature, according to the arrangement position information of each preset coding feature value in the coding features; re-determining a plurality of target matching degree scores corresponding to the arrangement position information in the matching degree scores corresponding to the plurality of second matching degree features; summing a plurality of target matching degree scores corresponding to the redetermined arrangement position information to obtain an adaptability value determined based on the second matching degree characteristics; and selecting the coding feature corresponding to the maximum adaptability value determined based on the second matching degree feature as a target coding feature, and generating scheduling information between a plurality of sub-projects and a plurality of construction execution objects according to the target coding feature.

The method and the system can be used for generating a plurality of second matching degree features with higher accuracy by combining a whale optimization algorithm based on the first matching degrees and matching degree scores corresponding to the first matching degree features, so that scheduling information among a plurality of sub-projects and a plurality of construction execution objects can be accurately generated according to the second matching degree features with higher accuracy, and the accuracy of scheduling information generation of construction projects can be improved.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a construction job file information generation device based on big data analysis, which is used for realizing the construction job file information generation method based on big data analysis. The implementation scheme of the device for solving the problem is similar to that described in the method, so the specific limitation in the embodiment of the device for generating the construction job file information based on big data analysis provided below can be referred to the limitation of the method for generating the construction job file information based on big data analysis hereinabove, and will not be repeated here.

In one embodiment, as shown in fig. 4, there is provided a construction job file information generating apparatus based on big data analysis, comprising: an acquisition module 502, a detection module 504, and a generation module 506, wherein:

The acquisition module is used for acquiring engineering information of a plurality of sub-projects of the construction project and object qualification information of a plurality of construction execution objects.

And the detection module is used for detecting the matching degree between the plurality of sub-projects and the plurality of construction execution objects according to the project information of the plurality of sub-projects and the object qualification information of the plurality of construction execution objects to obtain a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features.

In one embodiment, the generating module is further configured to:

In one embodiment, the detection module is further configured to:

Each module in the construction job file information generation apparatus based on big data analysis described above may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a construction job file information generation method based on big data analysis.

It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

In one embodiment, the processor when executing the computer program further performs the steps of:

In one embodiment, the engineering information includes at least one of an engineering area, an engineering height, an engineering length, an engineering capacity, engineering budget information, and an engineering construction cycle; the object qualification information includes at least one of registered capital information, construction project experience information, the number of constructors, the number of construction equipment, the number of incidents, and the number of qualification certificates.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of:

In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A construction job file information generation method based on big data analysis, the method comprising:

2. The method of claim 1, wherein the generating scheduling information between the plurality of sub-projects and the plurality of construction execution objects according to the plurality of first matching degree features and the matching degree scores corresponding to the plurality of first matching degree features comprises:

Generating a plurality of coding features according to scheduling constraint information between the plurality of sub-projects and the plurality of construction execution objects, wherein the coding features are used for representing scheduling allocation information between the plurality of sub-projects and the plurality of construction execution objects;

generating an adaptability value of each coding feature according to the matching degree scores;

according to the fitness values of the plurality of coding features, performing iterative optimization on the plurality of first matching degree features by adopting a whale optimization algorithm to obtain a plurality of second matching degree features;

And determining a target coding characteristic with the maximum fitness value in the plurality of coding characteristics according to the fitness values determined by the plurality of second matching degree characteristics, and generating scheduling information between the plurality of sub-projects and the plurality of construction execution objects according to the target coding characteristic.

3. The method of claim 2, wherein iteratively optimizing the first plurality of matching degree features using a whale optimization algorithm based on fitness values of the plurality of coding features to obtain a second plurality of matching degree features, comprises:

The generation step is executed: generating a first random number; if the first random number is larger than a first preset threshold value, selecting a first matching degree feature with the largest fitness value as a first target matching degree feature; updating the first matching degree features according to the first target matching degree features and differences between the first target matching degree features and the first matching degree features aiming at each first matching degree feature;

Updating the fitness value of the plurality of coding features according to the updated plurality of first matching degree features;

If the first random number is not greater than the first preset threshold value, randomly generating a first vector, a second random number corresponding to the first vector and a second vector corresponding to the second random number, wherein the first vector is used for representing iterative updating degrees of the plurality of first matching degree features;

Updating the plurality of first matching degree features according to the first vector, the second vector and the second random number, and updating the fitness values of the plurality of coding features according to the updated plurality of first matching degree features;

If the updated first matching degree features do not meet the preset iteration update ending condition, returning to execute the generating step; and if the updated first matching degree features meet the preset iteration update ending condition, determining the updated first matching degree features as second matching degree features.

4. A method according to claim 3, wherein said updating said plurality of first matching degree features based on said first vector, said second vector and said second random number comprises:

if the second random number is larger than a second preset threshold value, for each first matching degree feature, randomly searching a second target matching degree feature from the plurality of first matching degree features;

updating the first matching degree feature according to the first vector, the second target matching degree feature and the difference between the second target matching degree feature and the first matching degree feature;

if the second random number is not greater than a second preset threshold value, selecting a first matching degree characteristic with the largest fitness value as a first target matching degree characteristic;

for each matching degree feature, updating the first matching degree feature according to the first vector, the second vector, the first target matching degree feature and the difference between the first target matching degree feature and the first matching degree feature.

5. A method according to claim 3, wherein said randomly generating a first vector comprises:

determining the current iterative optimization times of the first matching degree features, and acquiring the maximum iterative optimization times of the first matching degree features;

and generating a first vector according to the first random number, the current iteration optimization times and the maximum iteration optimization times.

6. The method according to claim 1, wherein the detecting, according to the project information of the plurality of sub-projects and the object qualification information of the plurality of construction execution objects, the matching degree between the plurality of sub-projects and the plurality of construction execution objects to obtain a plurality of first matching degree features and matching degree scores corresponding to the plurality of first matching degree features includes:

Extracting the characteristics of the engineering information of the multiple sub-projects respectively to obtain the engineering information characteristics of the multiple sub-projects;

Extracting the characteristics of the object qualification information of the construction execution objects respectively to obtain the object qualification characteristics of the construction execution objects;

carrying out feature fusion on the engineering information features of the multiple sub-projects and the object qualification features of the multiple construction execution objects to obtain multiple first matching degree features;

and respectively predicting matching degree scores between the plurality of sub-projects and the plurality of construction execution objects according to the plurality of first matching degree features.

7. The method of claim 1, wherein the engineering information includes at least one of an engineering area, an engineering height, an engineering length, an engineering capacity, engineering budget information, and an engineering construction cycle; the object qualification information includes at least one of registered capital information, construction project experience information, the number of constructors, the number of construction equipment, the number of incidents, and the number of qualification certificates.

8. A construction job file information generation apparatus based on big data analysis, the apparatus comprising:

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.

10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.