JP7014582B2 - Quotation acquisition device, quotation acquisition method and program - Google Patents

Description

The present invention relates to a quotation acquisition device, a quotation acquisition method and a program.

Regarding the estimation of construction work, etc., a method of estimating using CAD data (see Patent Documents 1 and 2) and similar cases from the past cases are extracted based on the specification information, and the estimation is made based on the extracted similar cases. (Patent Document 3) has been proposed.

Japanese Unexamined Patent Publication No. 9-171519 Japanese Unexamined Patent Publication No. 2007-34346 Japanese Unexamined Patent Publication No. 2015-99476

The method using CAD data cannot be applied unless the design stage is as detailed as creating a design drawing by CAD. In addition, it takes time to estimate because it takes time to create a design drawing by CAD.
Further, in the method of extracting similar cases from past cases, it is expected that the estimation accuracy will increase as the number of past cases increases, while the search time for extracting similar cases will become longer as the number of past cases increases.
If it is possible to make an estimate without the need for CAD data and without having to search past cases after obtaining the specifications to be estimated, it will be possible to make an estimate at a relatively early stage and relatively quickly and accurately. Be expected.

The present disclosure provides an estimate acquisition device, an estimate acquisition method, and a program that do not require CAD data and can make an estimate without having to search past cases after obtaining the specifications to be estimated.

According to some aspects of the present disclosure, the estimate acquisition device includes a clustering unit that performs clustering of the types of members used in a project into one group according to a predetermined standard, and a past. For each cluster in which the model of the member used in the project is clustered by the clustering unit , the number of members classified in the cluster and the correlation with the input of the specification information indicating the required specifications in the project to be estimated It is used for the model construction unit that builds an estimation model that outputs a certain value as an estimation value by supervised learning using the required specifications in the past project and the actual value of the estimation target in the project, and the project to be estimated. For each cluster in which the member type is clustered by the clustering unit, the model specifying unit that specifies the estimation model corresponding to the cluster among the estimation models and the estimation model specified by the model specifying unit for each cluster are assigned to each of the estimation models. It is provided with an estimate acquisition unit for inputting specification information indicating the required specifications in the project to be estimated and acquiring an estimate for each cluster .

According to some aspects of the present disclosure, the estimation acquisition method is a clustering in which a computer groups a plurality of member types into one group according to a predetermined standard with respect to the member types used in past projects. For each cluster that has been performed, in response to the input of specification information indicating the required specifications in the project to be estimated, an estimation model that outputs a value that correlates with the quantity of parts classified in that cluster as an estimated value has been created in the past. It is constructed by supervised learning using the required specifications in the project and the actual value of the estimation target in the project, and the estimation is performed for each cluster in which the computer clusters the types of the members used in the estimation target project. Among the models, the estimation model corresponding to the cluster is specified, and the computer inputs the specification information indicating the required specifications in the project to be estimated into each of the estimation models specified for each cluster, and the cluster . Includes getting an estimate for each .

According to some aspects of the present disclosure, the program clustered the computer with the member types used in past projects , grouping multiple member types into a group according to predetermined criteria . For each cluster, an estimation model that outputs a value that correlates with the quantity of parts classified in the cluster as an estimated value for the input of specification information indicating the required specifications in the project to be estimated is provided in the past project. For each cluster that is constructed by supervised learning using the required specifications and the actual value of the estimation target in the project, and the model of the member used in the estimation target project is clustered, the cluster is included in the estimation model. Specifying the corresponding estimation model and inputting the specification information indicating the required specifications in the project to be estimated into each of the estimation models specified for each cluster to obtain the estimation for each cluster . It is a program to be executed.

According to the above-mentioned estimate acquisition device, estimate acquisition method and program, it is possible to make an accurate estimate without requiring CAD data and without having to search past cases after obtaining the specifications to be estimated.

It is a schematic block diagram which shows the functional structure of the estimate acquisition apparatus which concerns on embodiment. It is a figure which shows the example of the clustering performed by the clustering part which concerns on the same embodiment. It is a figure which shows the example of the model when the number of data is small. It is a figure which shows the example of the model which the model building part builds when the number of data is relatively large in the same embodiment. It is a figure which shows the example of the flow of the estimate using the estimate acquisition apparatus which concerns on the same embodiment. It is a flowchart which shows the example of the processing procedure which the estimate acquisition apparatus which concerns on the same embodiment generates an estimate model. It is a flowchart which shows the example of the processing procedure which the estimate acquisition apparatus which concerns on the same embodiment makes an estimate.

Hereinafter, some embodiments of the present disclosure will be described, but the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential to the means of solving the invention.
FIG. 1 is a schematic block diagram showing a functional configuration of an estimate acquisition device according to some embodiments of the present disclosure. As shown in FIG. 1, the estimate acquisition device 100 includes an input unit 110, an output unit 120, a storage unit 180, and a control unit 190. The control unit 190 includes a clustering unit 191, a model construction unit 192, a model identification unit 193, and an estimate acquisition unit 194.

The estimate acquisition device 100 is an device that estimates a project using members having a plurality of model numbers. A project that uses parts here is to make things using parts, such as construction, construction, or manufacturing.
Further, the target to be estimated by the estimate acquisition device 100 may be a value that correlates with the number of members. For example, the member may be a cable, and the estimate acquisition device 100 may estimate the cable length required for the project, or estimate the quantity of the member itself. Alternatively, the estimate acquisition device 100 may estimate the amount of money (material cost) of the member. Alternatively, the estimate acquisition device 100 may estimate the work cost for installing the member in addition to or instead of the amount of the member.
The estimate acquisition device 100 is configured by using a computer such as a personal computer (PC) or a workstation (Workstation), for example.

The input unit 110 receives data input. The input unit 110 may be configured by using a communication circuit. Alternatively, the input unit 110 may be configured by using an interface that receives a connection from a device such as a storage device such as a USB port. Alternatively, the input unit 110 may be configured by using an input device such as a keyboard and a mouse. Alternatively, the input unit 110 may be configured by using a combination of these.

The output unit 120 outputs data such as an estimation result. The output unit 120 may be configured by using a communication circuit. Alternatively, the output unit 120 may be configured by using an interface that receives a connection from a device such as a storage device such as a USB port. Alternatively, the output unit 120 may be configured by using a display screen such as a liquid crystal panel or an LED (Light Emitting Diode) panel. Alternatively, the output unit 120 may be configured by using a combination of these.

The storage unit 180 stores various data. In particular, the storage unit 180 stores the specifications of past projects and the actual values to be estimated. Further, the storage unit 180 stores the model constructed by the model construction unit 192.
The control unit 190 controls each unit of the quotation acquisition device 100 to perform various processes. The control unit 190 is configured by a CPU (Central Processing Unit) included in the estimate acquisition device 100 reading a program from the storage unit 180 and executing the program.

The clustering unit 191 clusters the types of members used in the project. Specifically, the clustering unit 191 groups the types of a plurality of members into one group according to a predetermined standard.
As a method for clustering by the clustering unit 191, a known machine learning method such as k-means can be used.

FIG. 2 is a diagram showing an example of clustering performed by the clustering unit 191. FIG. 2 shows an example in which the clustering unit 191 performs clustering based on the place where the member is used. The rows in FIG. 2 are associated with the model of the member (specifically, the model number), and the columns are associated with the place of use of the member.
For example, the project to be estimated is a new project of AGT (Automated Guideway Transit, a transportation system that runs on a dedicated track with rubber tires), the member is a cable, and the clustering unit 191 uses the equipment to which the cable is connected. You may try to perform clustering as. In this case, the end positions of both ends of the cable can be used as the place of use, such as high voltage room (high voltage power supply room) -guideway (guide rail), high voltage room-high voltage room of another station.

In the example of FIG. 2, the clustering unit 191 classifies the types of members used in the locations P3, 4, 10 and 11 into cluster 1. Further, the clustering unit 191 classifies the types of the members used in the places P4, 6 to 8 and 10 into the cluster 2. In this way, the clustering unit 191 clusters the types of the members according to the place where the members are used.

However, the standard for the clustering unit 191 to cluster the model of the member is not limited to the place where the member is used. For example, the clustering unit 191 may perform clustering of the model number of the member based on any one of the use of the member, the size of the member (for example, the diameter of the cable), the correlation between the member and the explanatory variable, or a combination thereof. good.
The explanatory variables referred to here are inputs (arguments) to the model constructed by the model construction unit 192.

The model construction unit 192 constructs an estimation model that outputs an estimate for input of specification information for each cluster in which the clustering unit 191 clusters the types of members used in the past projects. The specification information referred to here is information indicating the required specifications in the project to be estimated.
A known learning algorithm such as multiple regression or Ridge regression can be used by the model building unit 192 to build the estimation model.
When the model building unit 192 builds a model using multiple regression or Ridge regression, the model is expressed as Eq. (1).

Here, w ₁ , w ₂ , w ₃ , ... w _N , w ₀ are constants defined as regression coefficients. N is a positive integer. x ₁ , x ₂ , x ₃ , ... x _N are explanatory variables (that is, input parameters to the model). w is a vector indicating w ₁ , w ₂ , w ₃ , ... w _N , w ₀ . x is a vector dull indicating x ₁ , x ₂ , x ₃ , ... x _{N. ya} indicates an estimated value. The subscript a indicates that it is an estimated value.

In the case of multiple regression, the regression coefficient is determined by the least squares method so as to minimize the error E (w) shown in the equation (2).

Here, y is the true value of the estimation target.
On the other hand, in Ridge regression, the regression coefficient is determined so as to minimize the error E (w) shown in the equation (3).

Comparing the equation (3) with the equation (2), a penalty term − (λ / 2) || w || ² is provided on the right side. Here, λ is a predetermined constant. || W || indicates the eigenvalue of the vector w.
This penalty term can suppress overfitting.

When the member is a cable, the model building unit 192 may build a model including the distance between the equipment to which the cable is connected, such as the distance between stations, as an input. It is considered that there is a correlation between the distance between the equipment and the cable length, and in this respect, the model building unit 192 is expected to build a highly accurate model.

Further, the model construction unit 192 may output the estimate as a probability distribution. Here, it is conceivable that the value to be estimated is not uniquely determined and there are fluctuation factors. By outputting the estimate as a probability distribution, the model construction unit 192 can present an estimate that reflects the fluctuation range due to fluctuation factors.
An estimation model that outputs an estimation with a probability distribution can be obtained, for example, by the model construction unit 192 performing machine learning using a Gaussian process or Bayesian linear regression.

The members are also clustered by the clustering unit 191 clustering the types of the members. The clustering unit 191 clusters the members by clustering the types of the members, and the model building unit 192 constructs a model (estimation model) for each clustered member, so that the model building unit 192 has more data. You can build a model based on. This point will be described with reference to FIGS. 3 and 4.

FIG. 3 is a diagram showing an example of a model when the number of data is small. The horizontal axis of the graph in FIG. 3 shows explanatory variables, and the vertical axis shows estimated values. The explanatory variables are the inputs to the estimation model (the model that outputs the estimates), and the estimated values are the outputs of the estimation model.
Points P21 to P24 indicate the relationship between the explanatory variables and the actual value of the estimation target for the member of the same model number (for example, the actual value of the quantity using the member) in different projects.

Lines L11 to L13 show examples of model candidates obtained based on points P21 to P24. The line L11 shows an example of a model in which the points P21 to P23 are approximated by a straight line, with the exception of the point P24. Line L12 shows an example of a model in which points P21 to P24 are approximated by a straight line. Line L13 shows an example of a model in which points P21 to P24 are approximated by a curve.
When the number of data is small, it is difficult to determine what kind of model is appropriate, and it is possible that the accuracy of the model is low due to the small amount of data.

FIG. 4 is a diagram showing an example of a model constructed by the model construction unit 192 when the number of data is relatively large. The horizontal axis of the graph of FIG. 4 shows explanatory variables, and the vertical axis shows estimated values. The explanatory variables are inputs to the estimation model constructed by the model construction unit 192, and the estimation values are outputs of the estimation model.
Points P21 to P24 are the same as in the case of FIG. The points P31 to P34 are the same as the points P21 to P24, but the model numbers of the members are different between the points P21 to P24 and the points P31 to P34. The members of points P21 to P24 and the members of points P31 to P34 are classified into the same cluster by the clustering of the clustering unit 191.

The line L21 shows an example of a model candidate generated by the model building unit 192 based on the points P21 to P24 and P31 to P34. The line L21 shows an example of a model in which points P21 to P23 and P31 to P34 are approximated by a straight line, with the exception of the point P24.
Due to the clustering performed by the clustering unit 191, the number of data for constructing the model is larger than that in the case where the model building unit 192 constructs the model for each model number of the member. As a result, it is expected that the model building unit 192 can build a more accurate model.
Further, by constructing the model for each cluster by the model constructing unit 192, the number of models can be reduced as compared with the case where the model is constructed for each model number of the member. As a result, the load of model construction and the load of model maintenance can be reduced.

The model construction unit 192 may calculate the reliability of the estimation model for each estimation model.
For example, the model construction unit 192 calculates the reliability reliability (c) based on the equation (4).

Here, c indicates a cluster.
rn ( _c ) is expressed as in the equation (5).

Here, N (c) indicates the total number of data that can belong to the cluster c. n (c) indicates the number of valid data in N (c). For example, let N (c) be the number of projects × the number of cable types belonging to the cluster c. Of these, the number of data for which the cable length is actually shown is defined as n (c).
Weighting is performed by the number of data using r _n (c). In particular, the larger the number of data, the higher the reliability. That is, the model construction unit 192 calculates the reliability of each estimation model as the number of projects having members belonging to the cluster corresponding to the estimation model among the past projects increases.
Further, r _σ (c) is an evaluation value of the degree of variation in the estimation, and is expressed as in the equation (6).

Here, 3σ is expressed by the equation (7).

_em is an error of the true value with respect to the estimated value, and is expressed by the equation (8).

_ypre indicates an estimated value of the estimate. y _act indicates the true value of the estimate.
For example, when r _σ (c) = 30, it indicates that the true value is within the range of ± 30% of the estimated value.
r _σ (c) is weighted according to the degree of variation in the estimation using. The model construction unit 192 calculates the reliability of each estimation model as the degree of variation in the estimation target values obtained from the execution results of past projects for the members belonging to the cluster corresponding to the estimation model is smaller.

The model specifying unit 193 specifies an estimation model corresponding to the cluster from the estimation model constructed by the model construction unit 192 for each cluster in which the model of the member used for the project to be estimated is clustered by the clustering unit 191.
The estimate acquisition unit 194 inputs an explanatory variable (specification information) in the project to be estimated into each of the estimation models specified by the model identification unit 193 to acquire an estimate.
The quotation acquisition unit 194 may acquire a quotation including a margin for the accuracy of the quotation.

Next, the operation of the estimate acquisition device 100 will be described with reference to FIGS. 5 to 7.
FIG. 5 is a diagram showing an example of an estimation flow using the estimation acquisition device 100.
In the flow of FIG. 5, the customer requests a quotation from the company that is a candidate for order (sequence S111). When requesting a quotation, the customer shows the required specifications to the candidate company by drawing. The candidate company receives the required specifications in drawings or the like (sequence S121).

The company that is a candidate for an order requests a quotation from each section related to the project for which a quotation is requested (sequence S122). Each section that receives the request organizes the conditions of the equipment of the target project (sequence S123), and makes an estimate using the estimate acquisition device 100 (sequence S124). Each section evaluates the estimate obtained by using the estimate acquisition device 100 (sequence S125). Here, if it is determined that the accuracy of the estimation is not good, the estimation acquisition device 100 may be made to perform the estimation again.
As a result of the evaluation, if it is judged that the quotation can be used, each section will prepare a quotation. (Sequence S126).

After each related section prepares a quotation, each section gathers to hold a review meeting (Sequence S127). If a defect is found at the review meeting, the relevant section will bring back the quotation and prepare the quotation again.
If the review meeting decides to adopt the quotation of each section, the approval authority will approve it (sequence S128) and answer the quotation to the customer (sequence S129).
The customer receives a quotation from a candidate company (sequence S131).

FIG. 6 is a flowchart showing an example of a processing procedure in which the quotation acquisition device 100 generates a quotation model. The estimate acquisition device 100 performs the process of FIG. 6 in advance to generate an estimate model.
In the process of FIG. 6, the input unit 110 acquires the data of the past project (step S211). The clustering unit 191 clusters the member types with respect to the past project data acquired by the input unit 110 (step S212).

Next, the control unit 190 starts a loop A for processing for each cluster (step S221).
In the process of loop A, the model building unit 192 builds an estimation model for each cluster (step S222), and the model building unit 192 calculates the reliability of the estimation model built in step S222 (sequence S223).

Next, the control unit 190 performs the termination processing of the loop A (step S224). Specifically, the control unit 190 determines whether or not the processing of the loop A has been completed for all the clusters. If it is determined that there is an unprocessed cluster, the process returns to step S221, and the unprocessed cluster is processed in loop A. On the other hand, when it is determined that the processing of loop A is completed for all the clusters, the processing of FIG. 6 is terminated.

FIG. 7 is a flowchart showing an example of a processing procedure in which the quotation acquisition device 100 makes an estimate. The estimate acquisition device 100 performs the process of FIG. 7, for example, in the sequence S124 of FIG.
In the process of FIG. 7, the input unit 110 acquires the data of the project to be estimated (step S311). The clustering unit 191 clusters the member types with respect to the project data to be estimated acquired by the input unit 110 (step S312).

Next, the control unit 190 starts a loop B for processing for each cluster (step S321).
In the processing of the loop B, the model specifying unit 193 specifies the estimation model corresponding to the cluster to be processed in the loop B (step S322). The estimate acquisition unit 194 calculates (acquires) an estimate using the estimate model calculated by the model identification unit 193 (step S323). In the example of FIG. 7, the estimate acquisition unit 194 acquires an estimate of the length of the cable which is a member.
Next, the estimate acquisition unit 194 calculates (acquires) the estimated amount for each cluster based on the cable length obtained in step S323 (step S324).

Next, the control unit 190 performs the termination processing of the loop B (step S325). Specifically, the control unit 190 determines whether or not the processing of the loop B has been completed for all the clusters. If it is determined that there is an unprocessed cluster, the process returns to step S321 and the loop B is processed for the unprocessed cluster. On the other hand, if it is determined that the processing of the loop B has been completed for all the clusters, the loop B is terminated and the process proceeds to step S331.

When the loop B is terminated, the estimate acquisition unit 194 totals the estimated amounts for each cluster obtained in step S324 to calculate (acquire) the total estimated amount (step S331). The output unit 120 outputs the reliability of the estimate and the estimate model according to the control of the estimate acquisition device 100 (S332).
After step S332, the process of FIG. 7 is terminated.

As described above, the clustering unit 191 clusters the types of members used in the project. The model construction unit 192 constructs an estimation model that outputs an estimate for input of specification information for each cluster in which the clustering unit 191 clusters the types of members used in the past projects. The model specifying unit 193 specifies an estimation model corresponding to the cluster from the estimation model constructed by the model construction unit 192 for each cluster in which the model of the member used for the project to be estimated is clustered by the clustering unit 191. The estimate acquisition unit 194 inputs the specification information in the project to be estimated into each of the estimation models specified by the model identification unit 193 and acquires an estimate.

The estimate acquisition device 100 can build a model in advance using the data of the past project. Then, the estimate acquisition device 100 can acquire an estimate using this model. By using the model, the estimate acquisition device 100 can make an estimate without requiring CAD data and without having to search past cases after obtaining the specifications to be estimated.

Further, by constructing the model for each cluster of the model of the member by the model construction unit 192, more data for model construction can be obtained than in the case of constructing the model for each model. In this respect, the model building unit 192 can build a highly reliable model.
Further, since the model building unit 192 builds a model for each cluster of member types, the number of models is smaller than that for building a model for each type. In this respect, the load of building the model and the load of maintaining the model can be reduced.

Further, the model construction unit 192 calculates the reliability of the estimation model for each estimation model.
When the user obtains the quotation from the quotation acquisition device 100, the user can refer to the reliability and refer to whether or not to review the quotation. Further, the user can refer to the reliability as a reference as to whether or not to tune the model constructed by the model construction unit 192.

Further, the model construction unit 192 calculates the reliability for each estimation model as the degree of variation in the estimation target values obtained from the execution results of past projects for the members belonging to the cluster corresponding to the estimation model is smaller. ..
According to the model construction unit 192, it is considered that the smaller the variation in the estimation, the higher the reliability, and in this respect, an appropriate reliability can be obtained.

Further, the model construction unit 192 calculates the reliability higher for each estimation model as the number of projects having the member belonging to the cluster corresponding to the estimation model among the past projects is larger.
According to the model construction unit 192, it is considered that the higher the number of data used for model construction, the higher the reliability, and in this respect, appropriate reliability can be obtained.

Further, the clustering unit 191 performs clustering based on the place where the member is used.
As a result, the model building unit 192 can build a highly accurate model when there is a correlation between the place where the member is used and the value to be estimated.

The member is a cable. The clustering unit 191 performs clustering using the equipment to which the cable is connected as the place of use. The model building unit builds a model that includes the distance between the equipment as an input.
It is considered that there is a correlation between the distance between the equipment and the cable length, and in this respect, the model building unit 192 can build a highly accurate model.

Further, the model construction unit 192 constructs a model that outputs an estimate with a probability distribution.
The estimate acquisition unit 194 can use this model to present the uncertainty of the estimate according to the estimate.

In addition, the quotation acquisition unit 194 acquires a quotation including a margin.
As a result, according to the estimate acquisition device 100, it is possible to reduce the possibility that the estimate will be short-circuited (the estimated value is lower than the actual value).

A program for realizing all or part of the functions of the control unit 190 is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into the computer system and executed. May be processed. The term "computer system" as used herein includes hardware such as an OS and peripheral devices.
Further, the "computer system" includes the homepage providing environment (or display environment) if the WWW system is used.
Further, the "computer-readable recording medium" refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, or a CD-ROM, and a storage device such as a hard disk built in a computer system. Further, the above-mentioned program may be for realizing a part of the above-mentioned functions, and may be further realized for realizing the above-mentioned functions in combination with a program already recorded in the computer system.

Although the present embodiment has been described in detail with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like within a range not deviating from the gist of this disclosure are also included.

100 Estimate acquisition device 110 Input unit 120 Output unit 180 Storage unit 190 Control unit 191 Clustering unit 192 Model construction unit 193 Model identification unit 194 Estimate acquisition unit

Claims (10)

A clustering unit that performs clustering that groups the types of multiple members into one group according to a predetermined standard for the types of members used in the project.
For each cluster in which the type of member used in the past project is clustered by the clustering unit , the number of members classified into that cluster and the correlation with the input of the specification information indicating the required specifications in the project to be estimated . A model construction unit that builds an estimation model that outputs a certain value as an estimation value by supervised learning using the required specifications in the past project and the actual value of the estimation target in the project .
For each cluster in which the clustering unit clusters the model of the member used in the project to be estimated, the model specifying unit that specifies the estimation model corresponding to the cluster among the estimation models, and the model specifying unit.
An estimate acquisition unit that inputs specification information indicating the required specifications in the project to be estimated into each of the estimation models specified by the model identification unit for each cluster and acquires an estimate for each cluster .
Equipped with a quote acquisition device. The model building unit calculates the reliability of the estimation model for each estimation model.
The estimate acquisition device according to claim 1. The model building unit increases the reliability of the member belonging to the cluster corresponding to the estimation model as the degree of variation in the estimation target value obtained from the execution result of the past project is smaller for each estimation model. calculate,
The estimate acquisition device according to claim 2. The model building unit calculates the reliability higher for each estimation model as the number of projects having the member belonging to the cluster corresponding to the estimation model among the past projects increases.
The estimate acquisition device according to claim 2 or 3. The clustering unit performs clustering based on the place where the member is used.
The estimate acquisition device according to any one of claims 1 to 4. The member is a cable
The clustering unit performs the clustering using the equipment to which the cable is connected as the place of use.
The model building unit builds the model including the distance between the facilities as an input.
The estimate acquisition device according to claim 5. The model building unit outputs the estimate as a probability distribution.
The estimate acquisition device according to any one of claims 1 to 6. The quotation acquisition unit acquires a quotation including a margin.
The estimate acquisition device according to any one of claims 1 to 7. A specification that indicates the required specifications in the project to be estimated for each cluster in which the computer has performed clustering in which the types of multiple members are grouped into one group according to a predetermined standard with respect to the model of the member used in the past project. For the input of information, the estimation model that outputs the value that correlates with the quantity of the parts classified in the cluster as the estimated value, the required specifications in the past project and the actual value of the estimation target in the project. Building by using supervised learning and
The computer identifies the estimation model corresponding to the cluster among the estimation models for each cluster in which the types of the members used in the project to be estimated are clustered.
The computer inputs specification information indicating the required specifications in the project to be estimated into each of the estimation models specified for each cluster, and obtains an estimate for each cluster .
How to get a quote, including. On the computer
Input of specification information indicating the required specifications in the project to be estimated for each cluster in which the types of multiple members are grouped into one group according to a predetermined standard for the model of the member used in the past project. On the other hand, a teacher using an estimation model that outputs a value that correlates with the quantity of parts classified in the cluster as an estimated value , using the required specifications in the past project and the actual value of the estimation target in the project. Building by learning with existence
For each cluster in which the types of members used in the project to be estimated are clustered, the estimation model corresponding to the cluster is specified from the estimation models.
To obtain an estimate for each cluster by inputting specification information indicating the required specifications in the project to be estimated into each of the estimation models specified for each cluster.
A program to execute.

Images