CN115796932A - Engineering cost prediction method and device, electronic equipment and storage medium - Google Patents
Engineering cost prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115796932A CN115796932A CN202211408235.5A CN202211408235A CN115796932A CN 115796932 A CN115796932 A CN 115796932A CN 202211408235 A CN202211408235 A CN 202211408235A CN 115796932 A CN115796932 A CN 115796932A
- Authority
- CN
- China
- Prior art keywords
- project
- similarity
- historical
- engineering
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a project cost prediction method, a project cost prediction device, electronic equipment and a storage medium, wherein a target project is subjected to project matching to obtain a plurality of similar historical projects, then similarity matrixes of the plurality of historical projects and the target project are calculated when each project characteristic parameter is taken as an index, and the calculated similarity matrixes are used for determining the project which is most similar to the target project cost from the plurality of historical projects; then, forecasting the target project cost by using the most similar historical characteristic parameters and historical cost of the historical project, so as to obtain the cost estimation value of the target project; therefore, when the construction cost is predicted, the construction cost is predicted without manpower or experience, so that the accuracy and the efficiency of prediction are improved, and the method is suitable for large-scale application and popularization.
Description
Technical Field
The invention belongs to the technical field of construction cost, and particularly relates to a construction cost prediction method, a construction cost prediction device, electronic equipment and a storage medium.
Background
The project cost refers to the construction cost of the project predicted or actually paid in the construction period, and the project cost is predicted, planned, controlled, accounted, analyzed and evaluated by comprehensively using knowledge and skills in the aspects of management, economics, engineering technology and the like, wherein the prediction or determination of the project cost and the construction content thereof is called project pricing according to procedures, methods and bases specified by laws, regulations, standards and the like, and the project pricing comprises project metering pricing standards related to the pricing content, the pricing method and the price standard, project pricing quota, project cost information and the like.
In the actual production engineering execution process, the engineering cost estimation is an important link of engineering supervision and project implementation; however, most of the current estimation of the total amount of the construction cost is manually estimated by workers according to experience, and the mode not only causes no unified standard for the estimation of the construction cost due to different personal experiences, but also has the problems of labor consumption and lower estimation accuracy; therefore, it is urgent to provide a construction cost method which does not depend on human subjective experience and has high estimation accuracy.
Disclosure of Invention
The invention aims to provide a project cost prediction method, a project cost prediction device, electronic equipment and a storage medium, which are used for solving the problems of time and labor consumption and low prediction accuracy in the prior art of adopting manual experience-based estimation.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, a method for predicting construction cost is provided, which includes:
acquiring an engineering type and engineering characteristic parameters of a target engineering, and matching a plurality of historical engineering similar to the target engineering from a historical engineering database based on the engineering type and the engineering characteristic parameters so as to form a similar engineering set by utilizing the plurality of historical engineering;
for the ith historical project in the multiple historical projects, combining the ith historical project with each similar project in the similar project set to obtain multiple similarity calculation project pairs when i is polled from 1 to n, wherein the initial value of i is 1, n is the total number of the historical projects, and i and n are positive integers;
calculating the similarity between each similarity calculation engineering pair and the target engineering by taking the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index, and constructing a similarity matrix between the plurality of historical engineering pairs and the target engineering by using the obtained plurality of similarities when the jth engineering characteristic parameter is taken as the similarity index;
adding 1 to j, and obtaining a similarity matrix between the plurality of historical projects and the target project when each project characteristic parameter is taken as a similarity index when j is equal to k, wherein k is the total number of the project characteristic parameters;
determining the most similar historical project of the target project from a plurality of historical projects based on the obtained similarity matrixes;
and acquiring the historical project cost and the historical project characteristic parameters of the most similar historical project, and calculating to obtain the cost predicted value of the target project based on the historical project characteristic parameters and the historical project cost.
Based on the disclosure, the invention firstly obtains the project type and the project characteristic parameters of the target project, and then matches a plurality of historical projects similar to the target project in the database based on the project type and the project characteristic parameters; the step is equivalent to screening out historical projects with the same project characteristic parameters as the target project; then, a similar project set can be formed by utilizing the screened multiple historical projects, and every two projects in each historical project and the similar project set are paired, so that a plurality of similarity calculation project pairs can be obtained; then, the invention uses the jth project characteristic parameter as the similarity index to calculate the similarity of each similarity calculation project pair relative to the target project, so as to form a similarity matrix between a plurality of historical projects and the target project by using a plurality of calculated similarities, and according to the method, the similarity matrix between a plurality of historical projects and the target project can be calculated when each project characteristic parameter is used as the similarity index; and finally, determining the historical project which is most similar to the target project cost from the plurality of historical projects through the obtained plurality of similarity matrixes, and predicting the cost of the target project by utilizing the project cost and the historical characteristic parameters of the most similar historical project.
Through the design, the target project is subjected to project matching to obtain a plurality of similar historical projects, then, similarity matrixes of the historical projects and the target project are calculated when each project characteristic parameter is taken as an index, wherein the calculated similarity matrixes are used for determining the project which is most similar to the target project cost from the historical projects; then, forecasting the target project cost by using the most similar historical characteristic parameters and historical cost of the historical project, so as to obtain the cost estimation value of the target project; therefore, when the construction cost is predicted, the construction cost prediction method does not need to use manpower and does not need to carry out construction cost prediction according to experience, not only improves the accuracy of prediction, but also improves the efficiency, and is suitable for large-scale application and popularization.
In one possible design, calculating the similarity between each similarity calculation engineering pair and the target engineering by using the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index includes:
for any similarity calculation engineering pair, acquiring a target historical engineering characteristic parameter of historical engineering in any similarity calculation engineering pair and a target engineering characteristic parameter of similar engineering in any similarity calculation engineering pair based on the jth engineering characteristic parameter, wherein the target historical engineering characteristic parameter and the target engineering characteristic parameter are the same as the jth engineering characteristic parameter;
calculating the absolute value of the difference between the jth engineering characteristic parameter and the target engineering parameter, and calculating the absolute value of the difference between the jth engineering characteristic parameter and the target historical engineering characteristic parameter to respectively obtain a first intermediate value and a second intermediate value;
summing the first intermediate value and the second intermediate value, and calculating a quotient of the first intermediate value and a result of the summing to use the quotient of the first intermediate value and the result of the summing as the similarity between the any one of the similarity calculation project pairs and the target project.
Based on the disclosure, the invention discloses a calculation process of the similarity between any similarity calculation engineering pair and a target engineering, namely, firstly, screening out a parameter which is the same as the jth engineering characteristic parameter from two projects of the similarity calculation engineering pair, and then, calculating the absolute value of the difference between the jth engineering characteristic parameter and the jth engineering characteristic parameter to obtain two intermediate values; and finally, calculating the similarity between any similarity calculation engineering pair and the target engineering by using the two intermediate values.
In one possible design, determining a most similar historical project of the target project from a plurality of historical projects based on the obtained plurality of similarity matrices, includes:
for an m-th similarity matrix, calculating a similarity value of each historical project relative to the target project when a designated characteristic parameter is used as a similarity index based on the m-th similarity matrix, wherein the designated characteristic parameter is a project characteristic parameter corresponding to the m-th similarity matrix, and m is a positive integer;
when m is polled from 1 to k, the similarity value of each historical project relative to the target project is obtained when each project characteristic parameter is taken as a similarity index;
for any historical project, when each project characteristic parameter of the historical project is used as a similarity index, summing the similarity values of the historical project relative to the target project to obtain the total similarity of the historical project relative to the target project;
and after the total similarity of all the historical projects relative to the target project is obtained, taking the historical project with the maximum total similarity as the most similar historical project of the target project.
Based on the disclosure, the invention discloses a historical project which is most similar to the target project cost is determined from a plurality of historical projects by utilizing a similarity matrix; specifically, any similarity matrix is equivalent to a plurality of historical projects, and on the basis of taking the specified characteristic parameters (namely, the project characteristic parameters corresponding to any similarity matrix) as similarity indexes, the similarity matrix and the target project are aggregated, so that each historical project can be obtained by using any similarity matrix, and when the specified characteristic parameters are the similarity indexes, the similarity matrix and the target project have similarity values; the method can calculate the similarity between each historical project and the target project when each project characteristic parameter is taken as the similarity index, and finally, for any historical project, the corresponding similarities are added when each project characteristic parameter is taken as the similarity index, so that the total similarity between any historical project and the target project can be obtained; and after the total similarity is obtained, the historical project with the maximum total similarity can be used as the most similar historical project.
In one possible design, each row vector in the mth similarity matrix corresponds to a historical project, wherein, when a similarity index is calculated based on the mth similarity matrix, a similarity value of each historical project with respect to the target project is calculated, including:
a. for each row vector in the m-th similarity matrix, screening out the minimum element value in each row vector to form a similarity vector by utilizing the screened-out minimum element value;
b. taking the maximum element value in the similarity vectors as a similarity calibration value, and performing similarity arrangement on the mth similarity matrix by using the similarity calibration value to obtain a similarity arrangement matrix, wherein each row vector in the similarity arrangement matrix corresponds to a historical project, the value of any element in the similarity arrangement matrix is 1 or 0, the number of elements with the median value of 1 in the last row vector in two adjacent rows of vectors is greater than the number of elements with the median value of 1 in the next row vector, and the more the number of elements with the median value of 1 in any row vector is, the higher the similarity of the historical project corresponding to any row vector and the target project is;
c. obtaining a similarity value between the historical project and the target project, which corresponds to the first row vector in the similarity arrangement matrix, based on the similarity arrangement matrix;
d. deleting a target vector from the mth similarity matrix to obtain an updated mth similarity matrix, wherein the target vector is a row vector of a first row vector in the similarity arrangement matrix corresponding to the historical project in the mth similarity matrix;
and repeating the steps a to d until the number of the row vectors in the m-th similarity matrix is equal to 1, and obtaining the similarity value of each historical project relative to the target project when the target characteristic parameter is taken as the similarity index.
In one possible design, taking a maximum element value in the similarity vector as a similarity calibration value, and performing similarity arrangement on the mth similarity matrix by using the similarity calibration value to obtain a similarity arrangement matrix, including:
for any row vector in the m-th similarity matrix, changing the element smaller than the similarity calibration value in the any row vector to 0, and changing the element larger than or equal to the similarity calibration value in the any row vector to 1, so as to obtain an initial similarity arrangement matrix after the change is finished;
and sequencing each row vector in the initial similarity arrangement matrix according to at least the number of target elements in sequence, so as to obtain the similarity arrangement matrix after sequencing is finished, wherein the target elements are elements with the value of 1.
In one possible design, calculating a predicted construction cost value of the target construction based on the historical construction characteristic parameters and the historical construction cost, including:
for the jth project characteristic parameter, screening out a historical project characteristic parameter corresponding to the jth project characteristic parameter from the historical project characteristic parameters of the most similar historical project to serve as a construction cost budget parameter;
calculating the quotient between the jth engineering characteristic parameter and the construction cost budget parameter, and multiplying the quotient between the jth engineering characteristic parameter and the construction cost budget parameter by the historical construction cost to obtain a construction cost budget value of the jth engineering characteristic parameter;
when j is polled from 1 to k, obtaining a cost budget value of each engineering characteristic parameter;
and calculating the average value of the cost precalculated values of the k engineering characteristic parameters to obtain the cost predicted value of the target engineering.
Based on the above disclosure, the invention discloses a specific process for predicting the cost of a target project based on the historical project characteristic parameters and the historical project cost of the most similar historical project, namely, for any project characteristic parameter, dividing any project characteristic parameter by the corresponding historical project characteristic parameter in the most similar historical project, and multiplying the result by the historical project cost to obtain the cost budget value of the target project based on any project characteristic parameter; based on the principle, the cost budget value of the target project on the basis of each project characteristic parameter can be calculated; and finally, adding all the cost precalculated values, and taking the average value to obtain the cost predicted value of the target project.
In one possible design, matching a plurality of historical projects similar to the target project from a historical project database based on the project type and the project characteristic parameters includes:
screening a plurality of pre-selected historical projects matched with the project types and the project characteristic parameters from the historical project database based on the project types and the project characteristic parameters;
acquiring historical engineering characteristic parameters of each preselected historical engineering, and constructing and obtaining an engineering characteristic parameter set by using the historical engineering characteristic parameters of each preselected historical engineering;
based on the engineering characteristic parameters, determining a first fuzzy subset of the target engineering relative to the engineering characteristic parameter set, and determining a second fuzzy subset of each preselected historical engineering relative to the engineering characteristic parameter set, wherein the first fuzzy subset and the second fuzzy subset both comprise s identical engineering parameters, s engineering parameters belong to the engineering characteristic parameters, and s is a positive integer greater than 1;
and calculating the similarity between the first fuzzy subset and each second fuzzy subset, and sorting the similarity according to the sequence from large to small, so as to take the preselected historical project corresponding to the second fuzzy subset t before the similarity sorting as the historical project similar to the target project, wherein t is a positive integer and is greater than or equal to 3.
In a second aspect, there is provided a construction cost prediction apparatus, including:
the historical project matching unit is used for acquiring the project type and the project characteristic parameters of a target project, and matching a plurality of historical projects similar to the target project from a historical project database based on the project type and the project characteristic parameters so as to form a similar project set by utilizing the plurality of historical projects;
the engineering combination unit is used for combining the ith historical engineering with each similar engineering in the similar engineering set for the ith historical engineering in the multiple historical engineering so as to obtain multiple similarity calculation engineering pairs when i is polled from 1 to n, wherein the initial value of i is 1, n is the total number of the historical engineering, and i and n are both positive integers;
the similarity calculation unit is used for calculating the similarity between each similarity calculation engineering pair and the target engineering by taking the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index, and constructing a similarity matrix between the historical engineering pairs and the target engineering by using the obtained multiple similarities when the jth engineering characteristic parameter is taken as the similarity index;
the similarity calculation unit is used for adding 1 to j until j is equal to k, and obtaining a similarity matrix between the plurality of historical projects and the target project when each project characteristic parameter is taken as a similarity index, wherein k is the total number of the project characteristic parameters;
the similarity calculation unit is used for determining the most similar historical project of the target project from a plurality of historical projects based on the obtained similarity matrixes;
and the construction cost prediction unit is used for acquiring the historical construction cost and the historical construction characteristic parameters of the most similar historical engineering, and calculating to obtain the construction cost prediction value of the target engineering based on the historical construction characteristic parameters and the historical construction cost.
In a third aspect, another construction cost prediction apparatus is provided, which takes an apparatus as an electronic device as an example, and includes a memory, a processor and a transceiver, which are connected in communication in sequence, where the memory is used for storing a computer program, the transceiver is used for sending and receiving messages, and the processor is used for reading the computer program and executing the construction cost prediction method as may be designed in any one of the first aspect or the first aspect.
In a fourth aspect, there is provided a storage medium having stored thereon instructions for executing the project cost prediction method according to the first aspect or any one of the possible designs of the first aspect when the instructions are executed on a computer.
In a fifth aspect, there is provided a computer program product comprising instructions which, when executed on a computer, cause the computer to perform the method of project cost prediction as described in the first aspect or any one of the possible designs of the first aspect.
Has the beneficial effects that:
(1) The method comprises the steps of firstly carrying out project matching on a target project to obtain a plurality of similar historical projects, then calculating similarity matrixes of the plurality of historical projects and the target project when each project characteristic parameter is taken as an index, wherein the calculated similarity matrixes are used for determining the project which is most similar to the target project cost from the plurality of historical projects; then, forecasting the target project cost by using the most similar historical characteristic parameters and historical cost of the historical project, so as to obtain the cost estimation value of the target project; therefore, when the construction cost is predicted, the construction cost is predicted without manpower or experience, so that the accuracy and the efficiency of prediction are improved, and the method is suitable for large-scale application and popularization.
Drawings
FIG. 1 is a schematic flow chart illustrating steps of a construction cost prediction method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a construction cost prediction apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly described below with reference to the accompanying drawings and the embodiments or the description of the prior art, it is obvious that the following description of the structure of the drawings is only some embodiments of the present invention, and it is also possible for those skilled in the art to obtain other drawings based on the drawings without creative efforts. It should be noted that the description of the embodiments is provided to help understanding of the present invention, and the present invention is not limited thereto.
It will be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments of the present invention.
It should be understood that, for the term "and/or" as may appear herein, it is merely an associative relationship that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists alone, B exists alone, and A and B exist at the same time; for the term "/and" as may appear herein, which describes another associative object relationship, it means that two relationships may exist, e.g., a/and B, may mean: a exists independently, and A and B exist independently; in addition, with respect to the character "/" which may appear herein, it generally means that the former and latter associated objects are in an "or" relationship.
Example (b):
referring to fig. 1, in the engineering cost prediction method provided in this embodiment, a plurality of historical projects similar to a target project are determined, and then, a similarity matrix between the plurality of historical projects and the target project when each engineering characteristic parameter is used as a similarity index is calculated based on the engineering characteristic parameters in the target project; then, determining a historical project which is most similar to the target project cost from the plurality of historical projects based on the similarity matrix, and finally, estimating the target project cost based on the determined historical project cost; therefore, the cost is predicted without manual operation, so that the accuracy and the efficiency of prediction are improved, and the method is suitable for large-scale application and popularization; in this embodiment, the method may be, but is not limited to, operated on a project cost prediction end side, where the project cost prediction end side may be, but is not limited to, a Personal Computer (PC), a tablet PC, a smart phone, and/or a Personal Digital Assistant (PDA), and it is understood that the foregoing execution subject does not constitute a limitation to the embodiment of the present application, and accordingly, the operation steps of the method may be, but are not limited to, as shown in the following steps S1 to S6.
S1, acquiring an engineering type and engineering characteristic parameters of a target engineering, and matching a plurality of historical engineering similar to the target engineering from a historical engineering database based on the engineering type and the engineering characteristic parameters to form a similar engineering set by using the plurality of historical engineering; in specific application, the project type and the project characteristic parameters may be extracted based on project information of a target project, where the project information may include, but is not limited to: project names, project addresses, project types (such as bridges, roads, tunnels, houses and the like), basic project parameters (such as length, total building area, width, floor height, single-layer building area, construction period and the like), construction standards and the like, so that the project types and the project characteristic parameters can be extracted and obtained on the basis of the project information; optionally, the project information may be subjected to character recognition by using an OCR (optical character recognition) character recognition algorithm, so as to extract the information from the project information; further, taking the engineering type as a tunnel as an example, the engineering characteristic parameters may include, but are not limited to, length, width, height, and construction period; of course, the corresponding engineering characteristic parameters of different engineering types are different, and may be selected from the engineering basic parameters according to the actual application, and the method is not limited to the foregoing examples.
After the project type and the project characteristic parameters are obtained, determining the historical project similar to the target project by utilizing the project type and the project characteristic parameters; optionally, a large amount of historical projects are stored in the historical project database by way of example, where each historical project includes a corresponding project type, a historical project characteristic parameter, and historical project cost detailed information (including total historical project cost, unit cost, such as construction cost per day, cost per meter, etc.), etc., so that project matching can be performed in the database based on the aforementioned search condition; specifically, the determination process of history engineering can be, but is not limited to, as shown in the following steps S11 to S14.
S11, screening a plurality of pre-selected historical projects matched with the project types and the project characteristic parameters from the historical project database based on the project types and the project characteristic parameters; when the method is applied specifically, historical projects of the same type as a target project can be screened out from a historical project database according to the project type, and then the historical projects containing the same project characteristic parameters as the target project are determined from the screened out historical projects so as to serve as pre-selected historical projects; as on the basis of the foregoing example, the project characteristic parameters of the target project include length (1000 m), width (10 m), height (5 m) and construction period (200 days), then historical projects with length of 1000m, width of 10m, height of 5m and construction period of 20 days can be matched out in the same tunnel project in the database as the preselected historical project; of course, in order to ensure the comprehensiveness of data crawling, the parameters can be set as parameter ranges, and the historical projects meeting the ranges can be used as the pre-selected historical projects, for example, the historical projects with the length of 900-1100m, the height of 9-12m, the width of 8-13m and the construction period of 190-220 days can be used as the pre-selected historical projects; in addition, when the project type is screened, the geological condition can be used as the screening condition, namely the geological condition and the index of the same project type are used for primary screening, and then the parameter screening is carried out in the history project of the primary screening.
After the preselected historical project is obtained, matching of similar projects can be performed in the preselected historical project, specifically, but not limited to, matching of similar projects corresponding to the target project can be achieved by using a fuzzy mathematics method, wherein the matching process is shown in the following steps S12 to S14.
S12, acquiring historical engineering characteristic parameters of each pre-selected historical engineering, and constructing to obtain an engineering characteristic parameter set by using the historical engineering characteristic parameters of each pre-selected historical engineering; in a specific application, the step S12 is equivalent to forming an engineering feature parameter set by using the historical engineering feature parameters of all the preselected historical projects, for example, if 5 preselected historical projects are assumed, each preselected historical project has 10 engineering feature parameters (including 5 engineering feature parameters identical to the target project, and the repeated statistics is only once), then the engineering feature set has 30 elements in total; of course, the principle of constructing the engineering characteristic parameter set for different numbers of preselected historical engineering is consistent with the foregoing examples, and will not be described herein again.
After the set of engineering characteristic parameters is obtained, fuzzy subsets of the target engineering and each of the preselected historical engineering may be selected by using a fuzzy mathematics method, so as to perform similarity calculation based on the determined fuzzy subsets, wherein the determination process of the fuzzy subsets is shown in step S13 below.
S13, determining a first fuzzy subset of the target project relative to the project characteristic parameter set and a second fuzzy subset of each preselected historical project relative to the project characteristic parameter set based on the project characteristic parameters, wherein the first fuzzy subset and the second fuzzy subset both comprise s identical project parameters, the s project parameters belong to the project characteristic parameters, and s is a positive integer greater than 1; in specific application, the engineering characteristic parameters are used as fuzzy reasoning rules, and only the historical engineering characteristic parameters which are the same as the engineering characteristic parameters are selected from the engineering characteristic parameter set, so that each fuzzy subset is formed, namely, elements (namely the engineering parameters) contained in the first fuzzy subset and the second fuzzy subset are the engineering characteristic parameters; however, because the proportion of the elements in the target project and each pre-selected historical project is different, the membership degree of each element (i.e. the project parameter) in different fuzzy subsets is different; in this way, the similarity between the first fuzzy subset and each second fuzzy subset is calculated based on the characteristic that each fuzzy subset has the same engineering parameter but each engineering parameter has different membership degrees; alternatively, the similarity calculation process is as shown in step S14 described below.
S14, calculating the similarity between the first fuzzy subset and each second fuzzy subset, and sequencing the first fuzzy subset and each second fuzzy subset from big to small to take the preselected historical engineering corresponding to the second fuzzy subset t before the similarity sequencing as the historical engineering similar to the target engineering, wherein t is a positive integer and is more than or equal to 3; in a specific application, it is described that the elements in the first fuzzy subset and the second fuzzy subset are the same, but the membership degree of each element is different, so that the membership degree of each element in each fuzzy subset needs to be determined first, and then the similarity between the first fuzzy subset and each second fuzzy subset can be calculated based on the membership degree of each element in each fuzzy subset; optionally, for example, the membership degree of each engineering parameter in the first fuzzy subset and each second fuzzy subset may be determined by, but is not limited to, a binary contrast sorting method, and the principle of the method is as follows: determining a comparison standard according to the construction cost corresponding to each element in the engineering characteristic parameter set (the element corresponds to an engineering parameter (actually, the engineering characteristic parameter), and each engineering parameter can represent building information of an engineering, such as width, length and the like, so that each engineering characteristic parameter corresponds to a construction cost, then preferentially taking the membership degree of the engineering parameter with the highest construction cost as 1, taking the lowest construction value as 0, and taking the construction cost as the engineering parameter between 0 and 1, namely, obtaining the corresponding membership degree by utilizing an interpolation method; thus, after the membership degree of each element in the engineering characteristic parameter set is obtained, the membership degree of each element in the first fuzzy subset and each second fuzzy subset is obtained.
In this embodiment, after the membership degrees of the elements in the fuzzy subsets are obtained, the membership degrees can be used to calculate the similarity between the fuzzy subsets; specifically, the similarity may be calculated by, but not limited to, the following formula (1):
in the above formula (1), R (Y, Y') is the similarity between any of the second fuzzy subsets and the first fuzzy subset, and Y (v) h ) For the h engineering parameter v in the first fuzzy subset h Degree of membership, Y '(v' h ) Is the h engineering parameter v 'in any second fuzzy subset' h The value of the membership degree, the lambda represents the minimum value, the V represents the maximum value, and H is the total number of the process parameters in any second fuzzy subset.
After the similarity between the first fuzzy subset and the second fuzzy subset of each preselection historical project is calculated based on the formula (1), the similarity can be ranked from high to low, and finally, the preselection historical project corresponding to the second fuzzy subset t bits before the similarity ranking can be taken as the historical project similar to the target project.
After a plurality of historical projects similar to the target project are matched in the historical project database, the historical project with the most similar construction cost to the target project can be determined again in the plurality of historical projects, so that the construction cost of the target project can be predicted based on the historical project with the most similar construction cost; specifically, each project characteristic parameter is used as a similarity index to calculate similarity matrixes of a plurality of historical projects and a target project, and then the historical project which is most similar to the target project cost is determined based on the similarity matrixes; specifically, the calculation process of the similarity matrix may be, but is not limited to, as shown in the following step S2 and step S3.
S2, for the ith historical project in the multiple historical projects, combining the ith historical project with each similar project in the similar project set to obtain multiple similarity calculation project pairs when i is polled from 1 to n, wherein the initial value of i is 1, n is the total number of the historical projects, and i and n are positive integers; when the method is applied specifically, every two of each historical project in a plurality of historical projects and similar projects in a similar project set are combined, so that a plurality of similarity calculation project pairs are obtained; if the total number of the historical projects is 4, and similarly, the similar project set also comprises 4 historical projects, then for the first historical project, 4 similarity calculation project pairs are obtained by combination, and according to the principle, after the 4 historical projects are respectively combined with each similar project in the similar project set, 16 similarity calculation project pairs can be obtained; of course, the combination principle of different quantities of historical engineering is the same as that of the previous example, and is not described herein again.
After obtaining the plurality of similarity calculation engineering pairs, the similarity of each similarity calculation engineering pair with respect to the target engineering may be calculated by using any engineering characteristic parameter as a similarity index, and then a similarity matrix may be formed by using the calculated plurality of similarities, where the specific calculation process may be, but is not limited to, as shown in the following step S3.
S3, taking the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index, calculating the similarity between each similarity calculation engineering pair and the target engineering, and constructing a similarity matrix between the plurality of historical engineering pairs and the target engineering when the jth engineering characteristic parameter is the similarity index by using the obtained plurality of similarities; in specific application, on the basis of the foregoing example, it is equivalent to calculate 16 similarities, and a similarity matrix can be constructed by using 16 similarities; optionally, since the similarity calculation process of each similarity calculation engineering pair is the same as that of the target engineering, the following specific description of the similarity calculation is given by taking any one of the similarity calculation engineering pairs as an example, and the process may be, but is not limited to, as shown in steps S31 to S33 below.
S31, for any similarity calculation engineering pair, acquiring a target historical engineering characteristic parameter of historical engineering in any similarity calculation engineering pair and a target engineering characteristic parameter of similar engineering in any similarity calculation engineering pair based on the jth engineering characteristic parameter, wherein the target historical engineering characteristic parameter and the target engineering characteristic parameter are the same as the jth engineering characteristic parameter; in specific application, a parameter which is the same as the jth engineering characteristic parameter is screened out from the parameters of two projects of any similarity calculation project pair, and meanwhile, the similar engineering essence in the similar engineering set is historical engineering, so that the historical engineering characteristic parameter which is the same as the jth engineering characteristic parameter is screened out from the historical engineering characteristic parameters corresponding to the two historical projects of any similarity calculation project pair; if the jth engineering characteristic parameter is the length (1000 m), the length is screened out from the two historical engineering.
After obtaining the parameters of the two projects in any similarity calculation project pair, which are the same as the jth project characteristic parameter, the similarity calculation can be realized by combining the jth project characteristic parameter, wherein the specific calculation method is shown in the following steps S32 and S33.
S32, calculating an absolute value of a difference value between the jth engineering characteristic parameter and the target engineering parameter, and calculating an absolute value of a difference value between the jth engineering characteristic parameter and the target historical engineering characteristic parameter to respectively obtain a first intermediate value and a second intermediate value.
S33, summing the first intermediate value and the second intermediate value, and calculating a quotient of the first intermediate value and a summing result so as to take the quotient of the first intermediate value and the summing result as the similarity between the any similarity calculation engineering pair and the target engineering; in specific implementation, the foregoing steps S32 and S33 are summarized by a formula as follows:
in the above formula (2), S represents the similarity between any similarity calculation project pair and the target project, and f o Is the jth engineering characteristic parameter, f 2 Calculating target engineering parameters of similar engineering in engineering for any similarity, f 1 And calculating target historical engineering characteristic parameters of historical engineering in the engineering according to any similarity.
The following equation (2) is described as an example, assuming that the jth engineering characteristic parameter is length and has a value of 1000m, and any similarity calculation engineering pair is a first similarity calculation engineering pair, which includes a first historical engineering and a first similar engineering, wherein the target engineering parameter of the first similar engineering is 900m, and the target historical engineering characteristic parameter of the first historical engineering is 1050m, then the similarity between the first similarity calculation engineering pair and the target engineering is: 100/(100 + 50) =0.667; of course, the similarity calculation method between the remaining different similarity calculation engineering pairs and the target engineering is the same as the foregoing example, and is not described herein again.
After the similarity between each similarity calculation engineering pair and the target engineering is calculated according to the method, a similarity matrix can be constructed by utilizing each similarity; in a specific application, since the above description is performed by combining from the first historical project, the similarity matrix may be constructed according to the combination order of the similarity calculation project pairs, and if the first similarity calculation project pair is obtained by combining the first historical project and the first similar project, the corresponding similarity is taken as an element in the first row and the first column of the matrix, and similarly, the second similarity calculation project pair is obtained by combining the first historical project and the second similar project, and the corresponding similarity is taken as an element in the first row and the second column of the matrix; in this way, the similarity of the engineering pair calculated by combining the first historical engineering and each similar engineering is substantially the first row element of the matrix, and similarly, the similarity of the engineering pair combined by the second historical engineering and each similar engineering is used as the second row element of the matrix, so that the similarity matrix can be constructed by using each similarity.
After the similarity matrixes between the plurality of historical projects and the target project are obtained by calculation when the jth project characteristic parameter is taken as the similarity index, the similarity matrixes between the plurality of historical projects and the target project when the rest of the project characteristic parameters are taken as the similarity index can be calculated by the method, wherein the cyclic calculation process is shown as the following step S4.
S4, adding 1 to j until j is equal to k, and obtaining a similarity matrix between the plurality of historical projects and the target project when each project characteristic parameter is taken as a similarity index, wherein k is the total number of the project characteristic parameters; when the method is applied specifically, each project characteristic parameter corresponds to a similarity matrix, so that after a plurality of similarity matrices are obtained, the most similar historical project to the target project cost can be determined from a plurality of historical projects by using the similarity matrices; the specific determination process is shown in step S5 below.
S5, determining the most similar historical project of the target project from a plurality of historical projects based on the obtained plurality of similarity matrixes; in specific application, in the embodiment, a plurality of similarity matrixes are used to obtain the total similarity of each historical project relative to the target project, and then the historical project with the highest total similarity is used as the project with the highest cost similar to the target project, wherein the foregoing process may be, but is not limited to, as shown in the following steps S51 to S54.
S51, for an mth similarity matrix, calculating a similarity value of each historical project relative to the target project when an appointed characteristic parameter is used as a similarity index based on the mth similarity matrix, wherein the appointed characteristic parameter is a project characteristic parameter corresponding to the mth similarity matrix, and m is a positive integer; in specific application, it has been described in the description of the construction process of the similarity matrix that the first row corresponds to the engineering pair obtained by combining the first historical engineering and the similar engineering, and the second row corresponds to the engineering pair obtained by combining the second historical engineering and the similar engineering, so that each row vector in the mth similarity matrix corresponds to one historical engineering, and therefore, the similarity of each row can be sorted by using the value of each element in the similarity matrix, so that each historical engineering is obtained according to the sorting order, and when the specified characteristic parameter is used as the similarity index, the similarity with the target engineering is obtained; specifically, the sorting procedure of each row vector in the m-th similarity matrix may be, but is not limited to, as shown in the following steps a to e.
a. For each row vector in the m-th similarity matrix, screening out the minimum element value in each row vector to form a similarity vector by utilizing the screened-out minimum element value; in specific implementation, the minimum value of each row in the mth similarity matrix is screened out, so that a similarity vector is formed; after the similarity vectors are obtained, similarity calibration values for sorting the vectors in the similarity matrix may be determined based on the similarity vectors, as shown in step b below.
b. Taking the maximum element value in the similarity vectors as a similarity calibration value, and performing similarity arrangement on the mth similarity matrix by using the similarity calibration value to obtain a similarity arrangement matrix, wherein each row vector in the similarity arrangement matrix corresponds to a historical project, the value of any element in the similarity arrangement matrix is 1 or 0, the number of elements with the median value of 1 in the last row vector in two adjacent rows of vectors is greater than the number of elements with the median value of 1 in the next row vector, and the more the number of elements with the median value of 1 in any row vector is, the higher the similarity of the historical project corresponding to any row vector and the target project is; in specific application, the specific construction process of the similarity arrangement matrix is as follows: firstly, for any row vector in the m-th similarity matrix, changing the element in the any row vector, which is smaller than the similarity calibration value, into 0, and changing the element in the any row vector, which is greater than or equal to the similarity calibration value, into 1, so as to obtain an initial similarity arrangement matrix after the change is finished; and secondly, sequencing each row vector in the initial similarity arrangement matrix according to at least the sequence of the number of target elements, so as to obtain the similarity arrangement matrix after sequencing is finished, wherein the target elements are elements with the value of 1.
The foregoing steps a and b are illustrated below as an example:
assuming that there are 4 historical projects, the project characteristic parameter corresponding to the mth similarity matrix is length, and the matrix is expressed as:
wherein, 0.667 is the similarity calculation engineering pair obtained by combining the first historical engineering and the first similar engineering, and the similarity with the target engineering, and similarly, 0.6 is the similarity calculation engineering pair obtained by combining the first historical engineering and the second similar engineering, and the similarity with the target engineering; thus, the first row corresponds to a first history project, the second row corresponds to a second history project, the third row corresponds to a third history project, and the fourth row corresponds to a fourth history project.
According to the steps, the minimum value of each row in the matrix is screened out to form a similarity vector, wherein the minimum value of each row is as follows: 0.6,0.23,0.32,0.222, and therefore the similarity vectors are {0.6,0.23,0.32,0.222}, and then the maximum value is selected from the similarity vectors as the similarity scaling value, i.e. the similarity scaling value is 0.6, so that the elements greater than or equal to 0.6 in the matrix are changed to 1, and the elements less than 0.6 are changed to 0, and then the initial similarity permutation matrix W' is obtained as:
then, for each row vector of the initial similarity array matrix, sorting the row vectors according to at least a sequence of the number of target elements (element value is 1), that is, the first row contains the largest number of target elements (i.e., element 1), and the first row is arranged in the first row, and the second row contains 2 target elements, and the second row is arranged in the second row, according to this principle, the rows in the initial similarity array matrix can be sorted, so as to obtain a similarity array matrix, wherein a similarity array matrix W ″ obtained by sorting the initial similarity array matrix W' is:
thus, the similarity sorting of the mth similarity matrix can be completed, and a corresponding similarity arrangement matrix is obtained; after the similarity ranking matrix is obtained, the similarity ranking matrix can be used to calculate the similarity value between the historical project corresponding to the first row vector in the similarity ranking matrix and the target project, as shown in step c below.
c. Obtaining a similarity value between the historical project and the target project, which corresponds to the first row vector in the similarity arrangement matrix, based on the similarity arrangement matrix; in specific application, it has been described above that, in the similarity arrangement matrix, the greater the number of target elements contained in any row vector, the higher the similarity between the history project and the target project corresponding to any row vector, and therefore, based on the similarity arrangement matrix W ″, it can be known that the most target elements exist in the first row vector, and therefore, the highest similarity between the history project (i.e., the first history project) and the target project corresponding to the first row vector is obtained, and the first history project is sorted first, at this time, the first history project can be obtained based on the first sorted, and when the project characteristic parameter, which is the length, is used as the similarity index, the similarity value with respect to the target project is obtained; optionally, a similarity mapping table is arranged at the engineering cost prediction end, where a similarity value corresponding to each similarity ranking is recorded in the table, and if the similarity value corresponding to the first similarity ranking is 5, the similarity value corresponding to the second similarity ranking is 4, and the similarity values are sequentially decreased; thus, the similarity value corresponding to the similarity ranking first can be found in the similarity mapping table.
And d, after the historical engineering corresponding to the first row vector is obtained and the similarity value of the target engineering is obtained by taking the specified characteristic parameter as a similarity index, calculating the similarity values of the rest historical engineering and the target engineering, and performing the following steps d-e.
d. And deleting a target vector from the mth similarity matrix to obtain an updated mth similarity matrix, wherein the target vector is a row vector of the first row vector in the similarity arrangement matrix corresponding to the historical project in the mth similarity matrix.
e. Repeating the steps a-d until the number of the row vectors in the mth similarity matrix is equal to 2, and obtaining the similarity value of each historical project relative to the target project when the target characteristic parameter is taken as a similarity index; in specific applications, the foregoing cycle is also specifically illustrated by taking the foregoing example as an example:
specifically, if the history project corresponding to the first row vector is the first history project, the first row in the mth similarity matrix is deleted, and at this time, the updated mth similarity matrix is W':
at this time, according to the same principle as the above, the minimum value of each row is selected to form a similarity vector, i.e. the similarity vector is {0.23,0.32,0.222}, and then the maximum value is selected from the similarity vectors as a similarity calibration value, i.e. 0.32 is used as the similarity calibration value, at this time, the obtained initial similarity permutation matrix is:
at this time, the initial similarity array matrix is sorted, and the obtained similarity array matrix is:
from the similarity arrangement matrix, the second row in the initial similarity arrangement matrix corresponds to the historical project with the highest similarity to the target project, and the historical project corresponding to the second row is the third historical project, so after the first historical project is sorted, the similarity arrangement of the third historical project and the target project is the second place, and the corresponding similarity value is 4.
Similarly, deleting the target vector in the mth similarity matrix, wherein the target vector is a row vector corresponding to the third historical project, and the updated mth similarity matrix is changed to:
similarly, the minimum value of each row is selected from the matrix to form a similarity vector, i.e., the similarity vector is
{0.23,0.222}, and then selecting the maximum value from the similarity vectors as the similarity calibration value, i.e. 0.23 as the similarity calibration value, where the obtained initial similarity array matrix is:
then, sorting the row vectors to obtain a similarity arrangement matrix as follows:
as can be seen from the similarity arrangement matrix, the target elements in the first row are the most, and the similarity between the corresponding historical projects and the target projects is the greatest, wherein in the similarity arrangement matrix, the historical project corresponding to the first row vector is the second historical project, and the historical project corresponding to the second row vector is the fourth historical project, so that the similarity between the second historical project and the target projects is ranked as the third, and the similarity between the fourth historical project and the target projects is ranked as the fourth; thus, the similarity between the target project and the two is respectively: 3 and 2; in summary, when the length is used as the similarity index, the similarity ranks of the 4 historical projects and the target project are respectively as follows: the corresponding similarity values of the first historical project, the third historical project, the second historical project and the fourth historical project are 5, 4, 3 and 2.
In this embodiment, if the number of target elements in two row vectors is the same in the similarity arrangement matrix, the two row vectors are not sorted sequentially, and the similarity between the historical engineering and the target engineering corresponding to the two row vectors is: the two sequencing positions correspond to the mean value of the similarity values; if the number of target elements in the first two row vectors in the similarity arrangement matrix is the same, and the historical project corresponding to the first row vector is the first historical project, and the historical project corresponding to the second row vector is the third historical project, then the first historical project and the second historical project are sorted into the first and the second, and the similarity value is: (5 + 4)/2 =4.5, at this time, the row vectors corresponding to the first historical project and the second historical project may be deleted from the m-th similarity matrix.
In this way, the similarity between each historical project and the target project can be calculated by the same method as described above when each project characteristic parameter is taken as the similarity index, wherein the loop process is as shown in the following step S52.
S52, when m is polled from 1 to k, obtaining similarity values of each historical project relative to the target project when each project characteristic parameter is taken as a similarity index; when the method is applied specifically, when each project characteristic parameter is used as a similarity index, the similarity value of each historical project and the target project is obtained through calculation, then any historical project can be added to the similarity value of the target project when each project characteristic parameter is used as the similarity index, and therefore the total similarity of any historical project relative to the target project is obtained; the overall similarity calculation process is shown in step S53 below.
S53, for any historical project, when each project characteristic parameter is taken as a similarity index, summing the similarity values of the historical project relative to the target project to obtain the total similarity of the historical project relative to the target project; in specific application, step S53 is described as an example, and it is assumed that the similarity between the first historical project and the target project is 5 when the engineering characteristic parameter of the length is used as the similarity index, and the similarity between the first historical project and the target project is 3 when the engineering characteristic parameter of the width is used as the similarity index; when the height engineering characteristic parameter is taken as a similarity index, the similarity with the target engineering is 4; when the project characteristic parameter of the construction period is used as a similarity index, the similarity with the target project is 2; then the total similarity between the first historical project and the target project is: 5+3+4+2=14; of course, the total similarity calculation process of the rest of historical projects and the target project is the same as the foregoing example, and is not described herein again; after the total similarity between each historical project and the target project is obtained, the historical project which is most similar to the target project cost can be determined from the plurality of historical projects based on the total similarity, as shown in the following step S54.
S54, after the total similarity of all historical projects relative to the target project is obtained, taking the historical project with the maximum total similarity as the most similar historical project of the target project; after determining the most similar historical project to the target project based on the total similarity, predicting the target project cost by using the historical project cost and the historical project characteristic parameters of the most similar historical project; the prediction process is shown in step S6 below.
S6, acquiring historical construction cost and historical construction characteristic parameters of the most similar historical construction, and calculating to obtain a construction cost predicted value of the target construction based on the historical construction characteristic parameters and the historical construction cost; in specific application, the construction cost of each project characteristic parameter is calculated based on the historical construction cost and the historical construction characteristic parameters of the most similar historical project, and then the construction costs of all the project characteristic parameters are used to obtain the construction cost predicted value of the target project, wherein the specific calculation process can be, but is not limited to, as shown in the following steps S61-S64.
S61, for the jth project characteristic parameter, screening out a historical project characteristic parameter corresponding to the jth project characteristic parameter from the historical project characteristic parameters of the most similar historical project to serve as a cost budget parameter.
S62, calculating a quotient between the jth project characteristic parameter and the cost budget parameter, and multiplying the historical project cost by the quotient between the jth project characteristic parameter and the cost budget parameter to obtain a cost budget value of the jth project characteristic parameter.
And S63, when j is polled from 1 to k, obtaining a cost precalculated value of each engineering characteristic parameter.
And S64, solving the average value of the cost budget values of the k engineering characteristic parameters to obtain the cost prediction value of the target engineering.
In specific applications, the foregoing steps S61 to S64 are described as an example:
assuming that 4 engineering characteristic parameters are present, namely length, width, height and construction period, wherein taking length as an example, the length of a target engineering is divided by the length in the most similar historical engineering, and then multiplied by the historical engineering cost of the most similar historical engineering, so as to obtain a cost precalculated value of the target engineering under the engineering characteristic parameter of length; if the length of the target project is 1000, the length of the most similar historical project is 1050 and the historical manufacturing cost is 150 ten thousand yuan, then (1000/1050) × 150=142.857 ten thousand yuan; similarly, the cost budget value of the target project under the other project characteristic parameters can also be calculated by adopting the example method; and finally, taking the average value of the 4 cost precalculated values to be used as the cost predicted value of the target project.
Therefore, through the engineering cost prediction method described in detail in the steps S1 to S6, when the engineering cost is predicted, the invention does not need to use manpower and predict the cost according to experience, thereby not only improving the accuracy of prediction, but also improving the efficiency, and being suitable for large-scale application and popularization.
As shown in fig. 2, a second aspect of this embodiment provides a hardware device for implementing the engineering cost prediction method in the first aspect of this embodiment, including:
the historical project matching unit is used for obtaining the project type and the project characteristic parameters of the target project, matching a plurality of historical projects similar to the target project from a historical project database based on the project type and the project characteristic parameters, and forming a similar project set by using the historical projects.
And the project combination unit is used for combining the ith historical project with each similar project in the similar project set in the ith historical project in the multiple historical projects so as to obtain multiple similarity calculation project pairs when i is polled from 1 to n, wherein the initial value of i is 1, n is the total number of the historical projects, and i and n are positive integers.
And the similarity calculation unit is used for calculating the similarity between each similarity calculation engineering pair and the target engineering by taking the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index, and constructing a similarity matrix between the historical engineering pairs and the target engineering by using the obtained multiple similarities when the jth engineering characteristic parameter is taken as the similarity index.
And the similarity calculation unit is used for adding 1 to j until j is equal to k, so as to obtain a similarity matrix between the plurality of historical projects and the target project when each project characteristic parameter is taken as a similarity index, wherein k is the total number of the project characteristic parameters.
And the similarity calculation unit is used for determining the most similar historical project of the target project from a plurality of historical projects based on the obtained similarity matrixes.
And the construction cost prediction unit is used for acquiring the historical construction cost and the historical construction characteristic parameters of the most similar historical engineering, and calculating to obtain the construction cost prediction value of the target engineering based on the historical construction characteristic parameters and the historical construction cost.
For the working process, the working details, and the technical effects of the apparatus provided in this embodiment, reference may be made to the first aspect of the embodiment, which is not described herein again.
As shown in fig. 3, a third aspect of the present embodiment provides another engineering cost prediction apparatus, taking an apparatus as an electronic device as an example, including: a memory, a processor and a transceiver, communicatively coupled in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive messages, and the processor is configured to read the computer program and execute the method of construction cost prediction according to the first aspect of the embodiments.
For example, the Memory may include, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Flash Memory (Flash Memory), a First In First Out (FIFO), a First In Last Out (FILO), and/or a First In Last Out (FILO); in particular, the processor may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on. The processor may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array), and meanwhile, the processor may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a CPU (Central Processing Unit); a coprocessor is a low power processor for processing data in a standby state.
In some embodiments, the processor may be integrated with a GPU (Graphics Processing Unit) which is responsible for rendering and drawing contents required to be displayed on the display screen, for example, the processor may not be limited to a processor adopting a model STM32F105 series microprocessor, a Reduced Instruction Set Computer (RISC) microprocessor, an X86 or other architecture processor or an embedded neural Network Processor (NPU); the transceiver may be, but is not limited to, a wireless fidelity (WIFI) wireless transceiver, a bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee wireless transceiver (ieee802.15.4 standard-based low power local area network protocol), a 3G transceiver, a 4G transceiver, and/or a 5G transceiver, etc. In addition, the device may also include, but is not limited to, a power module, a display screen, and other necessary components.
For the working process, the working details, and the technical effects of the electronic device provided in this embodiment, reference may be made to the first aspect of the embodiment, which is not described herein again.
A fourth aspect of the present embodiment provides a storage medium storing instructions including the construction cost prediction method according to the first aspect of the present embodiment, that is, the storage medium stores instructions that, when executed on a computer, perform the construction cost prediction method according to the first aspect.
The storage medium refers to a carrier for storing data, and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash Memory, a flash disk and/or a Memory Stick (Memory Stick), etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, the working details, and the technical effects of the storage medium provided in this embodiment, reference may be made to the first aspect of the embodiment, which is not described herein again.
A fifth aspect of the present embodiments provides a computer program product comprising instructions which, when executed on a computer, cause the computer to perform the method for project cost prediction according to the first aspect of the embodiments, wherein the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
Finally, it should be noted that: the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A project cost prediction method is characterized by comprising the following steps:
acquiring an engineering type and an engineering characteristic parameter of a target engineering, and matching a plurality of historical engineering similar to the target engineering from a historical engineering database based on the engineering type and the engineering characteristic parameter so as to form a similar engineering set by using the plurality of historical engineering;
for the ith historical project in the multiple historical projects, combining the ith historical project with each similar project in the similar project set to obtain multiple similarity calculation project pairs when i is polled from 1 to n, wherein the initial value of i is 1, n is the total number of the historical projects, and i and n are positive integers;
calculating the similarity between each similarity calculation engineering pair and the target engineering by taking the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index, and constructing a similarity matrix between the plurality of historical engineering pairs and the target engineering by using the obtained plurality of similarities when the jth engineering characteristic parameter is taken as the similarity index;
adding j to 1 by self until j is equal to k, and obtaining a similarity matrix between the plurality of historical projects and the target project when each project characteristic parameter is taken as a similarity index, wherein k is the total number of the project characteristic parameters;
determining the most similar historical project of the target project from a plurality of historical projects based on the obtained similarity matrixes;
and acquiring the historical project cost and the historical project characteristic parameters of the most similar historical project, and calculating to obtain the cost predicted value of the target project based on the historical project characteristic parameters and the historical project cost.
2. The method according to claim 1, wherein calculating the similarity between each similarity calculation project pair and the target project by taking the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index comprises:
for any similarity calculation engineering pair, acquiring a target historical engineering characteristic parameter of historical engineering in any similarity calculation engineering pair and a target engineering characteristic parameter of similar engineering in any similarity calculation engineering pair based on the jth engineering characteristic parameter, wherein the target historical engineering characteristic parameter and the target engineering characteristic parameter are the same as the jth engineering characteristic parameter;
calculating the absolute value of the difference between the jth engineering characteristic parameter and the target engineering parameter, and calculating the absolute value of the difference between the jth engineering characteristic parameter and the target historical engineering characteristic parameter to respectively obtain a first intermediate value and a second intermediate value;
summing the first intermediate value and the second intermediate value, and calculating a quotient of the first intermediate value and a result of the summing to use the quotient of the first intermediate value and the result of the summing as the similarity between the any one of the similarity calculation project pairs and the target project.
3. The method of claim 1, wherein determining a most similar historical project of the target project from a plurality of historical projects based on the obtained plurality of similarity matrices comprises:
for an mth similarity matrix, calculating a similarity value of each historical project relative to the target project when a specified characteristic parameter is taken as a similarity index based on the mth similarity matrix, wherein the specified characteristic parameter is a project characteristic parameter corresponding to the mth similarity matrix, and m is a positive integer;
when m is polled from 1 to k, obtaining the similarity value of each historical project relative to the target project when each project characteristic parameter is taken as a similarity index;
for any historical project, when each project characteristic parameter of the historical project is used as a similarity index, summing similarity values of the historical project relative to the target project to obtain the total similarity of the historical project relative to the target project;
and after the total similarity of all historical projects relative to the target project is obtained, taking the historical project with the maximum total similarity as the most similar historical project of the target project.
4. The method according to claim 3, wherein each row vector in the mth similarity matrix corresponds to a historical project, and wherein calculating a similarity value of each historical project with respect to the target project when the target feature parameter is used as a similarity index based on the mth similarity matrix comprises:
a. for each row vector in the m-th similarity matrix, screening out the minimum element value in each row vector to form a similarity vector by utilizing the screened-out minimum element value;
b. taking the maximum element value in the similarity vectors as a similarity calibration value, and performing similarity arrangement on the mth similarity matrix by using the similarity calibration value to obtain a similarity arrangement matrix, wherein each row vector in the similarity arrangement matrix corresponds to a historical project, the value of any element in the similarity arrangement matrix is 1 or 0, the number of elements with the median value of 1 in the last row vector in two adjacent rows of vectors is greater than the number of elements with the median value of 1 in the next row vector, and the more the number of elements with the median value of 1 in any row vector is, the higher the similarity of the historical project corresponding to any row vector and the target project is;
c. obtaining a similarity value between the historical project and the target project, which corresponds to the first row vector in the similarity arrangement matrix, based on the similarity arrangement matrix;
d. deleting a target vector from the mth similarity matrix to obtain an updated mth similarity matrix, wherein the target vector is a row vector of a first row vector in the similarity arrangement matrix corresponding to the historical project in the mth similarity matrix;
and repeating the steps a to d until the number of the row vectors in the m-th similarity matrix is equal to 1, and obtaining the similarity value of each historical project relative to the target project when the target characteristic parameter is taken as the similarity index.
5. The method according to claim 4, wherein the step of using the largest element value in the similarity vector as a similarity calibration value and using the similarity calibration value to perform similarity arrangement on the mth similarity matrix to obtain a similarity arrangement matrix comprises:
for any row vector in the m-th similarity matrix, changing the element smaller than the similarity calibration value in the any row vector to 0, and changing the element larger than or equal to the similarity calibration value in the any row vector to 1, so as to obtain an initial similarity arrangement matrix after the change is finished;
and sequencing each row vector in the initial similarity array matrix according to at least the sequence of the number of target elements, so as to obtain the similarity array matrix after sequencing is finished, wherein the target elements are elements with the value of 1.
6. The method of claim 1, wherein calculating a predicted construction cost value of the target construction based on the historical construction characteristic parameters and the historical construction cost comprises:
for the jth project characteristic parameter, screening out a historical project characteristic parameter corresponding to the jth project characteristic parameter from the historical project characteristic parameters of the most similar historical project to serve as a construction cost budget parameter;
calculating the quotient between the jth engineering characteristic parameter and the construction cost budget parameter, and multiplying the quotient between the jth engineering characteristic parameter and the construction cost budget parameter by the historical construction cost to obtain a construction cost budget value of the jth engineering characteristic parameter;
when j is polled from 1 to k, obtaining a cost budget value of each engineering characteristic parameter;
and solving the average value of the cost budget values of the k engineering characteristic parameters to obtain the cost prediction value of the target engineering.
7. The method of claim 1, wherein matching a plurality of historical projects from a historical project database that are similar to the target project based on the project type and the project characterization parameters comprises:
screening a plurality of pre-selected historical projects matched with the project types and the project characteristic parameters from the historical project database based on the project types and the project characteristic parameters;
acquiring historical engineering characteristic parameters of each pre-selected historical engineering, and constructing to obtain an engineering characteristic parameter set by using the historical engineering characteristic parameters of each pre-selected historical engineering;
determining a first fuzzy subset of the target project relative to the project characteristic parameter set and a second fuzzy subset of each preselected historical project relative to the project characteristic parameter set based on the project characteristic parameters, wherein the first fuzzy subset and the second fuzzy subset both comprise s identical project parameters, the s project parameters belong to the project characteristic parameters, and s is a positive integer greater than 1;
and calculating the similarity between the first fuzzy subset and each second fuzzy subset, and sorting the similarity according to the sequence from large to small, so as to take the preselected historical project corresponding to the second fuzzy subset t before the similarity sorting as the historical project similar to the target project, wherein t is a positive integer and is greater than or equal to 3.
8. A construction cost prediction apparatus, comprising:
the historical project matching unit is used for acquiring the project type and the project characteristic parameters of a target project, and matching a plurality of historical projects similar to the target project from a historical project database based on the project type and the project characteristic parameters so as to form a similar project set by utilizing the plurality of historical projects;
the project combination unit is used for combining the ith historical project with each similar project in the similar project set for the ith historical project in the multiple historical projects so as to obtain multiple similarity calculation project pairs when i is polled from 1 to n, wherein the initial value of i is 1, n is the total number of the historical projects, and i and n are positive integers;
the similarity calculation unit is used for calculating the similarity between each similarity calculation engineering pair and the target engineering by taking the jth engineering characteristic parameter in the engineering characteristic parameters as a similarity index, and constructing a similarity matrix between the historical engineering pairs and the target engineering by using the obtained multiple similarities when the jth engineering characteristic parameter is taken as the similarity index;
the similarity calculation unit is used for adding 1 to j until j is equal to k, and obtaining a similarity matrix between the plurality of historical projects and the target project when each project characteristic parameter is taken as a similarity index, wherein k is the total number of the project characteristic parameters;
the similarity calculation unit is used for determining the most similar historical project of the target project from a plurality of historical projects based on the obtained similarity matrixes;
and the construction cost prediction unit is used for acquiring the historical construction cost and the historical construction characteristic parameters of the most similar historical engineering, and calculating to obtain the construction cost prediction value of the target engineering based on the historical construction characteristic parameters and the historical construction cost.
9. An electronic device, comprising: a memory, a processor and a transceiver, communicatively connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive messages, and the processor is configured to read the computer program and execute the construction cost prediction method according to any one of claims 1 to 7.
10. A storage medium having stored thereon instructions which, when executed on a computer, carry out the project cost prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211408235.5A CN115796932B (en) | 2022-11-10 | 2022-11-10 | Project cost prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211408235.5A CN115796932B (en) | 2022-11-10 | 2022-11-10 | Project cost prediction method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115796932A true CN115796932A (en) | 2023-03-14 |
| CN115796932B CN115796932B (en) | 2023-10-03 |
Family
ID=85436757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211408235.5A Active CN115796932B (en) | 2022-11-10 | 2022-11-10 | Project cost prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115796932B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114922A (en) * | 2023-10-24 | 2023-11-24 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
| CN117273394A (en) * | 2023-11-17 | 2023-12-22 | 中铁四局集团有限公司 | Intelligent equipment selection allocation analysis management method based on big data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110108127A (en) * | 2010-03-26 | 2011-10-05 | (주)한미글로벌건축사사무소 | Cost estimating model and method for building projects in planning phase using cbr and ga |
| US20160224896A1 (en) * | 2015-02-03 | 2016-08-04 | International Business Machines Corporation | Group generation using sets of metrics and predicted success values |
| CN105976077A (en) * | 2016-03-04 | 2016-09-28 | 国家电网公司 | Power transmission and transformation project cost dynamic control target calculating system and calculating method |
| CN106600464A (en) * | 2016-12-22 | 2017-04-26 | 重庆电力设计院 | Power grid construction new project cost rapid estimation method based on fuzzy mathematics |
| CN107958043A (en) * | 2017-11-24 | 2018-04-24 | 中科院合肥技术创新工程院 | A kind of electricity power engineering budget inventory automatic generation method |
| CN107967522A (en) * | 2017-11-24 | 2018-04-27 | 国网内蒙古东部电力有限公司 | A kind of power grid technological transformation overhaul engineering Cost Management System and its control method |
| US20180375334A1 (en) * | 2017-06-26 | 2018-12-27 | Tsinghua University | Method and apparatus for photovoltaic power forecast based on numerical weather prediction |
| CN110163476A (en) * | 2019-04-15 | 2019-08-23 | 重庆金融资产交易所有限责任公司 | Project intelligent recommendation method, electronic device and storage medium |
| WO2020257993A1 (en) * | 2019-06-24 | 2020-12-30 | 深圳市欢太科技有限公司 | Content pushing method and apparatus, server, and storage medium |
| CN112508512A (en) * | 2020-11-26 | 2021-03-16 | 国网河北省电力有限公司经济技术研究院 | Power grid engineering cost data management method and device and terminal equipment |
-
2022
- 2022-11-10 CN CN202211408235.5A patent/CN115796932B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110108127A (en) * | 2010-03-26 | 2011-10-05 | (주)한미글로벌건축사사무소 | Cost estimating model and method for building projects in planning phase using cbr and ga |
| US20160224896A1 (en) * | 2015-02-03 | 2016-08-04 | International Business Machines Corporation | Group generation using sets of metrics and predicted success values |
| CN105976077A (en) * | 2016-03-04 | 2016-09-28 | 国家电网公司 | Power transmission and transformation project cost dynamic control target calculating system and calculating method |
| CN106600464A (en) * | 2016-12-22 | 2017-04-26 | 重庆电力设计院 | Power grid construction new project cost rapid estimation method based on fuzzy mathematics |
| US20180375334A1 (en) * | 2017-06-26 | 2018-12-27 | Tsinghua University | Method and apparatus for photovoltaic power forecast based on numerical weather prediction |
| CN107958043A (en) * | 2017-11-24 | 2018-04-24 | 中科院合肥技术创新工程院 | A kind of electricity power engineering budget inventory automatic generation method |
| CN107967522A (en) * | 2017-11-24 | 2018-04-27 | 国网内蒙古东部电力有限公司 | A kind of power grid technological transformation overhaul engineering Cost Management System and its control method |
| CN110163476A (en) * | 2019-04-15 | 2019-08-23 | 重庆金融资产交易所有限责任公司 | Project intelligent recommendation method, electronic device and storage medium |
| WO2020257993A1 (en) * | 2019-06-24 | 2020-12-30 | 深圳市欢太科技有限公司 | Content pushing method and apparatus, server, and storage medium |
| CN112508512A (en) * | 2020-11-26 | 2021-03-16 | 国网河北省电力有限公司经济技术研究院 | Power grid engineering cost data management method and device and terminal equipment |
Non-Patent Citations (2)
| Title |
|---|
| 易欣;: "基于Vague集贴近度的工程项目投资快速估算方法", 华东交通大学学报, no. 03, pages 11 - 15 * |
| 李佳;徐振东;刘建军;: "模糊数学法在园林工程快速报价中的应用", 黑龙江农业科学, no. 09, pages 122 - 125 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114922A (en) * | 2023-10-24 | 2023-11-24 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
| CN117114922B (en) * | 2023-10-24 | 2024-01-26 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
| CN117273394A (en) * | 2023-11-17 | 2023-12-22 | 中铁四局集团有限公司 | Intelligent equipment selection allocation analysis management method based on big data |
| CN117273394B (en) * | 2023-11-17 | 2024-02-06 | 中铁四局集团有限公司 | Intelligent equipment selection allocation analysis management method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115796932B (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115796932B (en) | Project cost prediction method and device, electronic equipment and storage medium | |
| Wu et al. | Several variants of simulated annealing hyper-heuristic for a single-machine scheduling with two-scenario-based dependent processing times | |
| Wang et al. | Modified backtracking search optimization algorithm inspired by simulated annealing for constrained engineering optimization problems | |
| CN113052214B (en) | Heat exchange station ultra-short-term heat load prediction method based on long-short-term time sequence network | |
| CN116845889B (en) | Hierarchical hypergraph neural network-based power load prediction method | |
| CN115759413A (en) | Meteorological prediction method and device, storage medium and electronic equipment | |
| CN115185804A (en) | Server performance prediction method, system, terminal and storage medium | |
| CN109934368A (en) | Order quantity and order state prediction method, device and system | |
| Vincent et al. | Simulated annealing with reinforcement learning for the set team orienteering problem with time windows | |
| CN115619423A (en) | Engineering three-dimensional model-based bid and offer prediction method and device and storage medium | |
| CN114971053A (en) | Training method and device for online prediction model of network line loss rate of low-voltage transformer area | |
| CN112070200A (en) | Harmonic group optimization method and application thereof | |
| Tai et al. | ILSGVCP: An improved local search algorithm for generalized vertex cover problem | |
| CN116191398A (en) | Load prediction method, load prediction device, computer equipment and storage medium | |
| US20230334360A1 (en) | Model-independent feature selection | |
| CN112000673B (en) | Method and device for inquiring transaction elements by quantum circuit | |
| CN112132614B (en) | Method and device for preference prediction demonstration by quantum circuit | |
| CN115034812A (en) | Steel industry sales prediction method and device based on big data | |
| Makropoulos et al. | A multi-objective evolutionary programming approach to the ‘object location’spatial analysis and optimisation problem within the urban water management domain | |
| CN114117323A (en) | Water resource system optimal configuration method, device and equipment | |
| CN113935407A (en) | Abnormal behavior recognition model determining method and device | |
| CN107016564A (en) | It is a kind of enter row index prediction method and apparatus | |
| CN111444388A (en) | Video tag sorting method based on random walk | |
| CN116596170B (en) | Intelligent prediction method for delivery time based on space-time attention mechanism | |
| CN109921957B (en) | Computer room end-to-end capacity management method, electronic device and storage medium |
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 |