ESTIMATING SYSTEM AND STORAGE MEDIUM

The system efficiently categorizes projects and applies tailored models for cost estimation, addressing the challenge of incomplete specification data in initial project planning by ensuring accurate and rapid cost calculations.

DE102024201802A1Pending Publication Date: 2024-12-05KK TOSHIBA
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
DE102024201802
Authority / Receiving Office
DE · DE
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-29
Filing Date
2024-02-27
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Existing estimate capture systems struggle to accurately and efficiently calculate cost estimates for projects with incomplete or vague specification information, particularly in the initial stages of project planning, leading to variability in estimates and increased calculation time.

Method used

A system that clusters previous projects based on specification information, generates two types of models (first and second models) for each cluster, and selects the appropriate model for estimating cost based on the specification information of the estimation object project, allowing for efficient and accurate cost estimation even with incomplete data.

Benefits of technology

Enables quick and precise cost estimation by categorizing projects into similar groups and applying the most suitable model, reducing the need for extensive specification information and minimizing estimation variability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

An estimate acquisition system comprises a clustering part, a preprocessing part, a model equation generation part, a cluster labeling part, and a model equation application part. The clustering part groups previous projects into clusters based on specification information relating to those previous projects. The model equation generation part creates a primary model and a secondary model for each cluster. Each piece of information about previous projects includes specification information and information about a cost value containing estimate items. The cluster labeling part determines a cluster among the clusters based on specification information from an estimate object project.The model equation application part is configured to select either the first model or the second model for the cluster determined by the cluster label part and, based on the selected model, calculates a value that relates to an estimate item of the estimate object project.
Need to check novelty before this filing date? Find Prior Art

Description

AREA

[0001] The embodiments described herein generally relate to an estimation acquisition system and a storage medium. BACKGROUND

[0002] A cost estimate is presented to a customer when they receive an order for a product, system, or similar project. For a large project, such as a solar power plant, a rough cost estimate is presented to the customer during the initial study phase to investigate the company's profitability. Estimation systems that use arithmetic processors such as computers and the like have been proposed for calculating such estimates.

[0003] For example, Reference 1 (JP 2015-099476 A (Kokai)) describes a method for calculating a cost estimate by extracting actual construction results of similar projects from a database of actual construction results using text mining based on specification information of a project that is the subject of the cost estimate, performing multiple regression analysis on the extracted actual construction results to determine a function that includes the specification information as explanatory variables and the working hours of the cost estimate items as the target variable, and multiplying the working hours obtained from the function by a predefined rate.

[0004] For example, Patent Literature 2 (JP 2019-101681 A (Kokai)) is an estimation acquisition device that calculates an estimate by clustering previously used member models, generates an estimation model including the specification information as explanatory variables and the estimation result as the target variable for each cluster, determines a cluster to which a project similar to the estimation project belongs based on the member models used by the estimation object, and inputs the specification information into a model equation of the designated cluster. BRIEF DESCRIPTION OF THE DRAWINGS Fig. 1 is a schematic block diagram illustrating an estimation detection system according to an embodiment; Fig. 2 is a schematic conceptual view describing project information; Fig. 3 is a flowchart illustrating a processing procedure of an estimation detection system according to the embodiment; Fig. 4 is an explanatory drawing illustrating the processing of the estimation detection system according to the embodiment; Fig. 5 is an explanatory drawing illustrating the processing of the estimation detection system according to the embodiment; and Fig. 6 is an explanatory drawing illustrating the processing of the estimation detection system according to the embodiment. DETAILED DESCRIPTION

[0005] An estimation acquisition system according to an embodiment includes a clustering part, a preprocessing part, a model equation generation part, a cluster designation part, and a model equation application part. The clustering part clusters a plurality of previous projects into a plurality of clusters based on specification information related to the plurality of previous projects. The preprocessing part performs preprocessing on a plurality of predecessor project information related to the plurality of previous projects. The model equation generation part generates a first model and a second model for each of the plurality of clusters based on the plurality of information about previous projects on which the preprocessing has been performed.Each of the plurality of predecessor project information includes the specification information and information about a cost value including a plurality of estimate items. The first model represents a correlation between the specification information and a cost-related value. The second model represents a cost structure corresponding to a relationship between values ​​related to the plurality of estimate items. The cluster designation part determines, based on specification information of an estimate object project, a cluster among the plurality of clusters to which a previous project similar to the estimate object project belongs. The model equation application part is configured to select either the first model or the second model for the cluster designated by the cluster designation part based on the specification information of the estimate object project.The model equation application part is configured to calculate a value based on the selected model that relates to an estimate item of the estimate object project.

[0006] Various embodiments are described below with reference to the accompanying drawings.

[0007] The drawings are schematic and conceptual, are not necessarily the same as the actual configurations.

[0008] In the description and drawings, components similar to those previously described or shown in a preceding drawing are designated by like reference numerals, and a detailed description is omitted where appropriate.

[0009] Fig. 1 is a schematic block diagram illustrating a system for collecting estimates according to one embodiment.

[0010] As in Fig. 1, the estimation acquisition system 100 includes an input device 11, an output device 12, an arithmetic device 20, and a storage device 30.

[0011] The storage device 30 stores multiple sets of predecessor project information 31 relating to multiple previous projects. A "project" refers, for example, to the manufacture or construction of a product. The term "project" may also include the provision of products and / or services. The storage device 30 also stores cluster information 32 in which the multiple previous projects are classified into multiple clusters, and model equation information 33 of model equations that model the costs incurred for each of the multiple previous projects.

[0012] Specifically, the storage device 30 is, for example, a storage device such as ROM (Read Only Memory) and / or RAM (Random Access Memory). In particular, the storage device 30 may include a non-volatile memory such as DRAM (Dynamic Random Access Memory), SRAM (Static Random Access Memory), EEPROM (registered trademark) (Electrically Erasable Programmable Read Only Memory), flash memory, etc. The storage device 30 may include a computer-readable storage medium. For example, the storage device 30 also stores an estimation acquisition program executed by the estimation acquisition system 100 (a calculation part).

[0013] The arithmetic device 20 is configured to communicate with the storage device 30. The arithmetic device 20 includes a calculation part 27 and a display part 26. The calculation part 27 includes a functional block (a clustering part 21, a preprocessing part 22, a model equation generation part 23, a cluster designation part 24, and a model equation application part 25) that performs the processing described below. As a result, the calculation part 27 estimates the cost value incurred by the estimation object project based on the predecessor project information 31, the cluster information 32, and the model equation information 33 stored in the storage device 30.

[0014] The clustering part 21 clusters the specification information of the previous projects. The preprocessing part 22 performs preprocessing of the actual result information of the previous projects. The model equation generation part 23 generates, for each cluster classified by the clustering part 21, a model (a second model, described below) that represents the cost structure of all estimated items based on the actual result information for which the preprocessing part 22 has performed preprocessing, and a model (a first model, described below) that outputs an estimation result for an input of the specification information of the previous projects. The cluster designation part 24 designates, based on the specification information of the estimation object project, a cluster among the clusters classified by the clustering part 21 to which a project similar to the estimation object project belongs.The model equation application part 25 selects a model equation that matches the specification information of the estimation object project from the model equations generated by the model equation generation part 23 for the clusters designated by the cluster designation part 24, and calculates an estimate by inputting the specification information of the estimation object project. The display part 26 displays the estimation result calculated by the model equation application part 25.

[0015] Specifically, the calculation part 27 is, for example, an arithmetic circuit including a CPU (central processing unit), etc. The calculation part 27 may include controllers that control the functions of the estimation acquisition system 100. The calculation part 27 may be configured to read the estimation acquisition program stored in the storage device 30 and use software to perform various processing described below. The display part 26 is a display device (e.g., a liquid crystal display, an organic EL display, etc.) that displays the estimation results of the calculation part 27.

[0016] The input device 11 and the output device 12 are configured to communicate with the arithmetic device 20 and the storage device 30. The input device 11 is an input part that inputs various information, such as the predecessor project information, the estimation object project information, etc., into the estimation acquisition system 100. Specifically, the input device 11 is, for example, a sensor such as a touch panel or the like, a user interface such as a mouse, a keyboard, etc. Or, the input device 11 may be a communication module and / or an input terminal for receiving information from an external storage device and / or network. The output device 12 outputs the estimation result to the outside. The output device 12 may be, for example, a communication module or an output terminal that transmits the estimation result to an external device and / or network.

[0017] Fig. Figure 2 is a schematic conceptual view describing project information.

[0018] In this example, the installation (construction) of a solar power generation system is assumed to be a previous project P. The example of Fig. 2 shows a first previous project P1, a second previous project P2, and a third previous project P3 as multiple previous projects P. The previous project information stored in the storage device 30 is information related to the previous projects P. For example, the multiple sets of predecessor project information include first predecessor project information related to the first previous project P1, second predecessor project information related to the second previous project P2, and third predecessor project information related to the third previous project P3.

[0019] The predecessor project information of each previous project P includes the specification information SI and the cost value information CI. For example, the first information relating to the first previous project P1 includes the first specification information SI1 and the cost value information CI1 of the first previous project. Similarly, the information relating to the second previous project includes the second specification information SI2 and the cost value information CI2 of the second previous project. The information relating to the third previous project includes the third specification information SI3 and the cost value information CI3 of the third previous project.

[0020] For example, the specification information of a project is information about the required specifications of that project. For example, the first specification information SI1, contained in the first predecessor project information, represents the required specifications of the first previous project P1. The specification information SI contains information about multiple specification elements (N required specification elements). Fig. Figure 2 illustrates three specification items as multiple specification items, namely the installation location where the solar power generation system is installed, the snowfall amount (e.g., the average snowfall amount per specified period) at the location where the solar power generation system is installed, and the soil hardness of the location where the solar power generation system is installed. According to the embodiment, the number (N) of specification items included in the specification information SI of the predecessor project information is not limited to three but can be arbitrary.

[0021] The information of each specification item can be expressed by a parameter (a numerical value). For example, if the specification is the installation location, the parameters of the installation location can be defined as discrete values, such as 1 for a plain, 2 for a golf course, and 3 for a mountainous region. If the specification is the amount of snow, the parameters can be continuous values ​​such as snow depth (cm). Or the amount of snowfall can be defined as a discrete value, such as 1 for a low amount of snowfall and 2 for a high amount of snowfall. The information of each specification item can be input as numerical values, or the required information can be extracted and quantified by the calculation part 27.

[0022] The specification information SI of the previous project P is thus expressed by a combination of the N parameters (the specification values) corresponding to the N prescribed specification items. This means that the specification information SI of the previous project P is data corresponding to points in n-dimensional space.

[0023] The information CI of the cost value of a previous project P is the value (the actual result value) of the costs actually incurred in the one previous project P. The cost value is the value to be estimated for the estimation object project and is, for example, the effort (the monetary amount). However, the embodiment can estimate not only the effort, but also the period, the amounts of other items, etc. It is sufficient if the cost (the estimated item) is correlated with the specification information and has a value that changes with the specification information.

[0024] The cost includes several items (hereinafter referred to as "estimated items") that are to be estimated for the estimation object project. The cost value information contains the information about the value of each estimated item. The values ​​of the estimated items are, for example, a breakdown of the cost value. In the cost value information CI of the previous project P, the value of each estimated item is the value (the actual result value) that was actually spent for the estimated item.

[0025] In the example of Fig. For example, in Figure 2, estimate 1 represents the cost of specific equipment, estimate 2 represents the cost of developing the site, estimate 3 represents the cost of foundation work, and estimate 4 represents the cost of framing. The estimates are not limited to those described above, but can also be costs for specific materials and / or processing and can be determined accordingly depending on the project. The number of estimates is not limited to four and can be n (where n is not less than 2).

[0026] Fig. 3 is a flowchart illustrating a processing procedure of an estimation detection system according to the embodiment. Fig. 4 to 6 are explanatory drawings illustrating the processing of the estimation detection system according to the embodiment.

[0027] For example, as a prerequisite for starting the processing process, all the specification information (the information of all specification items) and the actual result values ​​(the values ​​of all estimate items) of the previous projects P are stored in the storage device 30 (the predecessor project information) in a completed state.

[0028] In step S101, as in Fig. As illustrated in Figure 3, the specification information (e.g., the information of N specification items) required for generating model equations is extracted from all specification information of the predecessor project information. For example, it is assumed that the specification information required for model equation generation is predefined. The predecessor project information from which the specification information is extracted can be selected by a user, taking into account the implementation period of the previous projects, etc.

[0029] Subsequently, clustering part 21 performs a clustering based on one or more types of specification information (specification elements) of the selected previous projects. For example, in the Fig. In step S102 shown in Figure 3, the previous projects are clustered based on the specification information extracted from the selected predecessor project information. The user can select a known algorithm for clustering, such as the k-means algorithm, the Ward method, etc. The user can select any number of clusters. The number of clusters can also be determined by considering the results of a known technique such as the elbow method, etc. The number of clusters can be automatically determined using a known method such as the x-means algorithm, etc. The information obtained by clustering (the cluster information 32) about the number of clusters, the cluster to which each project belongs, etc. is stored in the storage device 30.The actual result values ​​of the projects belonging to each cluster are retrieved from the storage device 30 (the predecessor project information 31).

[0030] For example, as in Fig. As shown in Figure 4, the clustering part 21 clusters the multiple preceding projects P into multiple clusters Ck based on the specification information SI related to the multiple preceding projects P. That is, the clustering part 21 clusters the multiple preceding projects P into the multiple clusters Ck based on at least part of the information of all specification items (the information of not less than one (e.g., N) specification items). k is an integer from 1 to K, which represents the cluster number. That is, the multiple clusters Ck include the first to K-th clusters C1 to CK.

[0031] The multiple previous projects P are divided into the clusters Ck. In other words, the multiple previous projects P include the m k -th previous project P k m k , which belongs to cluster Ck. m k is an integer from 1 to M k , which represents the numbers of the previous projects P belonging to the k-th cluster Ck.

[0032] Specifically, the first to M1-th previous projects P11 to P1M1 are classified into a first cluster C1 (Group A). ​​Similarly, the first to M2-th previous projects P21 to P2M2 are classified into a second cluster C2 (Group B). Similarly, the first to M K -th previous projects P K 1 to P K M K classified into the K-th cluster CK (a group C).

[0033] Subsequently, the preprocessing part 22 uses, for example, the parameter that has the greatest impact on cost fluctuation to normalize the actual result information of the selected previous projects, calculates the average value and standard deviation of the actual result values ​​of each estimated item for each cluster classified by the clustering part 21, and sorts the estimated items according to the average value. Fig. For example, in step S103 illustrated in Figure 3, the parameter that has the greatest impact on cost variability is used to normalize the actual profit values ​​of the projects' estimated items. For example, in a solar power generation business, the generation capacity, which indicates the scale of power generation, has the greatest impact on cost variability, and therefore the actual profit value is normalized based on the generation capacity. For each cluster, the normalized actual profit values ​​of the projects are used to calculate an average value µ and a standard deviation σ for each estimated item. The estimated items are then sorted in ascending or descending order according to the average value µ for each cluster.

[0034] In other words, the preprocessing part 22 uses, for example, a reference value based on the information about previous projects to normalize the cost value (the values ​​of the estimated items) of the information about each previous project. The reference values ​​may be index values ​​indicating the magnitude of the cost values ​​of the previous projects P. For example, the reference values ​​may be based on information from at least one specification item of the specification information SI of the previous projects P. Specifically, in each previous project P, as described above, the generation power (watts) may be used as a reference value. For example, the values ​​of the estimated items of a previous project P are normalized by dividing the values ​​(the actual result values) of the estimated items of the one previous project P by the generation capacity (the reference value) of the one previous project P.

[0035] Or the reference values ​​can be based on the cost values ​​of previous projects P. For example, for each previous project, the value of the estimated item with the largest value among the multiple estimated items can be used as the reference value. Or, for example, for each previous project P, the value of a prescribed estimated item can be used as the reference value.

[0036] More specific, for example as in Fig. 4, the values ​​of the estimated items of the first previous project P11 of the first cluster C1 are normalized using a first reference value (e.g., by dividing by the first reference value). The first reference value is based on the first predecessor project information of the first previous project P11 and is based, for example, on the parameters of the specification elements of the first predecessor project information or the cost value information CI1 of the first predecessor project information.

[0037] Similarly, the values ​​of the estimated elements of the second to Mth previous projects P12 to P1M1 of the first cluster C1 are normalized using the second to Mth reference values, respectively. The second to Mth reference values ​​are based on the information about the previous projects of the second to Mth previous projects P12 to P1M1, respectively.

[0038] Similar to the first cluster C1, for the previous projects P classified in the second to K-th clusters C2 to CK, the preprocessing part 22 also uses reference values ​​based on the predecessor project information of the previous projects P to normalize the values ​​of the estimated items.

[0039] Normalization may also use a method other than dividing values ​​by reference values. For example, normalization can be performed in each previous project P by setting the maximum value of the multiple estimate item values ​​to 1 and the minimum value of the multiple estimate item values ​​to 0, or by setting the average value of the multiple estimate items to 0 and the standard deviation of the multiple estimate items to 1. According to the embodiment, preprocessing such as normalization and the like do not always need to be performed and can be omitted or performed as needed.

[0040] To continue with the description of the processing of the first cluster C1, which is Fig. 4 as an example, the preprocessing part 22 calculates the average value of the first estimated items of M1 previous projects P included in the first cluster C1 (i.e., the average value of the normalized value of the estimated item 1 of the first previous project P11, the normalized value of the estimated item 1 of the second previous project P12, ..., and the normalized value of the estimated item 1 of the M1-th previous project P1M1). The preprocessing part 22 also calculates the standard deviation of the first estimated items of the M1 previous projects P included in the first cluster C1. Similarly, the preprocessing part 22 calculates the average value and standard deviation of each of the second to n-th estimated items of the first cluster C1.

[0041] The preprocessing part 22 also performs a sorting for the first cluster C1, in which the multiple estimate items are sorted according to the calculated average value in descending (or ascending) order. In the diagram Gr2, which is shown on the right side of Fig. 4, for example, the plurality of estimate items are arranged from the left side of the diagram in ascending order of the normalized actual result value (the average value of the normalized values ​​of the estimate item).

[0042] In other words, sorting assigns a number (numerical value) from 1 to n to each of the multiple estimate items in descending (or ascending) order of the average value. For example, in the first cluster C1, the numerical values ​​from 1 to n are assigned to the estimate items in descending (or ascending) order of the average value, so that the estimate item with the largest average value among the multiple estimate items is set to 1, the estimate item with the second largest average value is set to 2, ......, and the estimate item with the nth largest average value is set to n. During sorting, each estimate item is assigned a numerical value from 1 to n, which indicates the order of the size (smallness) of the average value of each estimate item.

[0043] For example, as shown in diagram Gr2 in Fig. As illustrated in Figure 4, an estimation model M102 representing the cost structure is generated from a diagram in which the average values ​​of the estimated items are plotted in sorted order. The order of the model equation representing the cost structure can be reduced by sorting the average values ​​of the estimated items.

[0044] The preprocessing part 22 also performs similar processing for the second to Kth clusters. Namely, the preprocessing part 22 calculates, for each of the plurality of clusters Ck, the average value and standard deviation of the values ​​related to each of the plurality of estimate items for the plurality of previous projects P, and sorts the plurality of estimate items by the average values.

[0045] Thus, the preprocessing part 22 calculates for the clusters Ck the average value and the standard deviation of the normalized value of the first estimate item for the several previous projects P (the first to M k -th previous projects P k 1 to P k M k ), the average value and the standard deviation of the normalized value of the second estimated item for the plurality of previous projects P, ..., and the average value and the standard deviation of the normalized value of the nth estimated item for the plurality of previous projects P. For the clusters Ck, the preprocessing part 22 performs sorting in which each of the plurality of estimated items is assigned a number from 1 to n in descending (or ascending) order of the average value.

[0046] Subsequently, the model equation generation part 23 generates model equations for each cluster classified by the clustering part 21, in which the specification information is used as the explanatory variable for each estimation item and the estimation result is used as the target variable. For example, in the Fig. 3, no less than one set of specification information (a specification item) influencing cost fluctuation is defined for each estimation point. The defined specification information and the normalized actual result value are recorded for each estimated item of the projects included in the clusters; and an estimation model M101 is created to estimate the cost of each estimated item by performing a multiple regression analysis with the normalized actual result value as the target variable and the specification information as the explanatory variables (see Fig. 4).

[0047] In other words, for example, the model equation generation part 23 generates a first model M1 (e.g., the multiple estimation models M101) for each of the plurality of clusters Ck based on the multiple sets of previous project information related to the plurality of previous projects P. The first model M1 of one cluster Ck is a model representing the correlation between the specification information of the previous projects P of the one cluster Ck and the cost-related value. In other words, for example, the first model M1 of the first cluster C1 represents the correlation between the specification information of the plurality of previous projects P of the first cluster C1 and the value related to the cost of the plurality of previous projects P of the first cluster C1. The first model M1 receives the input of the specification information and outputs the cost-related value as the estimation result.

[0048] According to the embodiment, "the cost-related value" (the value related to the estimated item) is the cost value (the value of the estimated item), such as the amount of money, the period, etc., which is the final cost estimate object, and is the value after the prescribed conversion processing is performed. In the example, "the value related to cost" is the normalized cost value as described above. However, if conversion processing such as normalization or the like is omitted, the cost-related value may be the cost value that is not subjected to any conversion such as normalization, etc.

[0049] Specifically, in the example of Fig. 4 the first model M1 (the multiple estimation models M101) n estimation models, ie, the first to nth estimation models M1011 to M101n. The first to nth estimation models M1011 to M101n correspond to the first (estimate item 1) to nth (estimate item n) estimation items, respectively.

[0050] As in Fig. 4, the first estimation model M1011 represents a correlation between at least a part of the information (the so-called first specification part) among the N specification items and the value (the normalized actual result value) related to the first estimation item for the several previous projects P. In the example of Fig. 4, the first specification part is a specification element. A specification value V1 is the value of the parameter of one specification item. The first estimation model M1011 represents the correlation between the specification value V1 and the value related to the first estimate item for the several previous projects P.

[0051] Similarly, the n-th estimation model M101n represents the correlation between at least one piece of information (the n-th specification part) among the N specification items and the value (the normalized actual result value) related to the n-th estimate item for the several previous projects P. In the example of Fig. 4, the nth specification part consists of two specification elements. The specification value VN-1 and the specification value VN are the values ​​of the parameters of the two specification elements, respectively. The nth estimation model M101n represents the correlation between the two specification values ​​VN-1 and VN and the value related to the nth estimation item for the multiple previous projects P.

[0052] For example, the j-th estimation model M101j (j is an integer from 1 to n) of the k-th cluster can be represented by a model equation like the following Ykj=akj1xkj1+akj2xkj2+…

[0053] Here is Y kj the value that refers to the jth estimated item. x kj1 , x kj2 , ..., are the specification values ​​of the specification items contained in the j-th specification part (at least part of the N specification items). a kj1 , a kj2, ..., are constants. The specification items included in the j-th specification part are determined from the N specification items accordingly. The number of specification items included in the j-th specification part is a suitable number from 1 to N. Any estimation model can be derived through machine learning methods such as supervised learning. The model equation is not limited to a linear polynomial, but can be, for example, a second- or higher-order model equation.

[0054] For each cluster classified by the clustering part 21, the model equation generation part 23 plots the average values ​​of the estimated items on a graph in the sorted order and generates a model equation that represents the cost structure of the cluster through regression analysis. For example, in the Fig. 3, the values ​​of the average value µ of the normalized actual result values ​​determined for each estimated item of each cluster in step S103 are plotted on a graph in the sorted order, and the estimation model M102 representing the cost structure of the cluster is generated by regression analysis using the average value µ of the actual result value as the target variable and the estimated item as the explanatory variables (see Fig. 4). The order of the estimation model generated by sorting the estimate items by the average value µ may be lower than before sorting.

[0055] In other words, the model equation generation part 23 generates, for example, the second model (the estimation model M102) for each of the plurality of clusters Ck based on the plurality of predecessor project information related to the plurality of previous projects P. The estimation model M102 of one cluster Ck represents the cost structure of the plurality of previous projects P belonging to the one cluster Ck. For example, for the first cluster C1, the second model represents the cost structure of the plurality of previous projects P of the first cluster C1. The cost structure is the relationship between the values ​​related to the various estimation items.

[0056] In other words, for example, as in the Fig. 4, the estimation model M102 for the first cluster C1 shows the correlation between the numerical values ​​(the number indicates the order of magnitude) assigned to the multiple estimation items by the sorting described above for the first cluster C1 and the average value of the values ​​with respect to the multiple estimation items for the first cluster C1.

[0057] The estimation model M102 of the k-th cluster can be exemplified by a model equation like the following Yk=αkx2+βkX+γk x is the numerical value assigned to the estimated item by the sorting. y k is the value (the average value) that refers to the x-th estimated item. α k ,β k and γ kare constants. The estimation model can be derived using machine learning, e.g., supervised learning. The model equation is not limited to a quadratic equation and can, for example, be a first-, third-, or higher-order model equation.

[0058] The cluster designation part 24 performs clustering based on one or more types of specification information (specification items) of the estimation object project and determines the cluster to which the estimation object project belongs based on the clusters clustered by the clustering part 21. Specifically, for example, in the Fig. In step S105 shown in FIG. 3, clustering is performed using the specification information of the estimation object project, and the cluster to which the estimation object project belongs is determined. For example, the user uses the input device 11 to input the specification information of the estimation object project. The input specification information of the estimation object project may be insufficient for the specification information extracted in step S102. If the specification information is insufficient, a preset (default) value may be adjusted to the insufficient specification information; and clustering may be performed using the value.

[0059] In other words, the specification information of the estimation object project contains information about at least some of the specification items among the N prescribed specification items. The specification information of the estimation object project may contain information about all N specification items, similar to the project P described above, or it may only contain information about some of the specification items among the N specification items. Thus, the specification information of the estimation object project may be insufficient information, not containing information about some of the specification items among the N specification items.

[0060] As in Fig. As illustrated in Figure 5, the cluster designation part 24 calculates, for example, distances Lk (e.g., Euclidean distances) between the centroids of the clusters Ck and a point EP representing the specification information of the estimation object project in the n-dimensional space formed by the n specification items. In other words, the cluster designation part 24 calculates a distance L1 between the point EP and the centroid of the first cluster C1, a distance L2 between the point EP and the centroid of the second cluster C2, ..., and a distance LK between the point EP and the centroid of the K-th cluster CK. Then, the cluster designation part 24 designates the cluster Ck whose centroid has the closest distance to the point EP.

[0061] Thus, based on the specification information of the estimation object project, the cluster designation part 24 determines the cluster (the cluster to which the estimation object project belongs) among the plurality of clusters Ck as the cluster to which a previous project similar to the estimation object project belongs.

[0062] Based on the specification information of the estimation object project, the model equation application part 25 calculates the estimation by selecting and applying a suitable model from the model equations generated by the model equation generation part 23. Specifically, for example, in the Fig. In step S106 shown in Figure 3, the estimate is calculated by applying the model equation generated in step S104 to the specification information of the estimation object project inputted in step S105. The determination of the model equation to be applied is performed for each estimation object. For example, if the specification information inputted in step S105 satisfies the explanatory variables of the estimation model M101 generated in step S104, the estimate is calculated by applying the estimation model M101. For example, if the specification information inputted in step S105 does not satisfy the explanatory variables generated in step S104, the estimate is calculated by applying the estimation model M102.

[0063] Thus, the model equation application part 25 selects one of the first models (the estimation model M101) or the second model (the estimation model M102) for the cluster designated by the cluster designation part 24 based on the specification information of the estimation object project, and calculates the value related to the estimation item of the estimation object project based on the selected model.

[0064] In other words, the model equation application part 25 performs the processing of calculating the value related to one estimated item among the first to nth estimated items based on either the estimation model M101 (the first model) or the estimation model M102 corresponding to the one estimated item. The model equation application part 25 performs this processing for each of the plurality of estimated items.

[0065] Fig. Figure 6 shows the calculation of values ​​related to the estimated items b1 to b10 by the model equation application part 25. Each of the estimated items b1 to b10 is one of the first to n-th estimated items, respectively.

[0066] In Fig. In Figure 6, the bars with dot hatching indicate that the value of the estimated items is calculated based on the M101 estimation model. The bars with diagonal hatching indicate that the value of the estimated items is calculated based on the M102 estimation model.

[0067] For example, the estimation model M101 corresponding to the estimation item b1 is a model that estimates the value with respect to the estimation item b1 by using the information from at least a part of the N specification items (called the specification part of the estimation item b1) as input. The example in Fig. Figure 6 shows that the specification information of the estimation object contains the information about all specification elements contained in the specification part of the estimation item b1. In other words, the specification information of the estimation object project satisfies the explanatory variables of the estimation model M101 corresponding to the estimation item b1. In such a case, as shown in Fig. 6, the value relating to the estimated item b1 is estimated on the basis of the estimation model M101.

[0068] For example, the estimation model M101 corresponding to the estimation item b4 is a model that estimates the value with respect to the estimation item b4 by using the information from at least a part of the N specification items (called the specification part of the estimation item b4) as input. The example in Fig. Figure 6 shows that the specification information of the estimation object project does not contain information related to at least some of the specification elements contained in the specification part of the estimation item b4. In other words, the specification information of the estimation object project does not satisfy the explanatory variables of the estimation model M101 corresponding to the estimation item b4. In such a case, as shown in Fig. As illustrated in Figure 6, the value related to the estimated item b4 is estimated based on the estimation model M102. For example, the numerical value (the number indicating the order of magnitude) assigned to the estimated item b4 in the sorting described above is applied to the model equation of the estimation model M102.

[0069] Thus, for example, the first estimation model M1011 represents the correlation between the first specification part, which represents at least part of the N specification items, and the value related to the first estimation item for the plurality of previous projects. When the specification information of the estimation object project includes all the specification items included in the first specification part, the model equation application part 25 selects the first estimation model M1011 and estimates the value related to the first estimation item of the estimation object project by applying the specification information of the estimation project to the first estimation model M1011.On the other hand, when the specification information of the estimation object project does not include at least part of the specification items included in the first specification part, the model equation application part 25 selects the estimation model M102 (the second model) and estimates the value related to the first estimation item of the estimation object project based on the estimation model M102.

[0070] The thus estimated value is a value to which the prescribed conversion processing (e.g., the normalization described above) is applied. In step S106, the value to which the prescribed conversion processing is applied may be appropriately reverse-converted to calculate the final value of the monetary amount, etc. For example, when the preprocessing part 22 uses the generation capacity for normalization as described above, the estimated value (the normalized value) may be multiplied by the generation capacity of the estimation object project.

[0071] The effects of the estimation detection system according to the present embodiment will now be described.

[0072] According to the embodiment described above, two models, i.e., the first and the second models, are created for each cluster. Then, one of the first or second models is selected for the cluster to which a previous project similar to the estimation object project belongs, based on the specification information of the estimation object project; and the value related to the estimation item is calculated based on the selected model. Since the estimation result can be obtained by calculating the estimation based on the first or second model, the estimation can be easily acquired. For example, the estimation result can be obtained even when it is difficult to estimate using the other model. For example, the estimation result can be obtained according to the specification information of the estimation object project, etc., by selecting a more appropriate model.

[0073] For example, there are cases where estimation is performed at the initial stage of researching a product or equipment when the specifications are vague. In such a case, the estimation is performed based on the experience and knowledge of the estimation personnel, which may result in inconsistencies in the estimation results among personnel or a significant time-consuming estimation calculation when the estimation conditions are complex. Therefore, an estimation calculation system of a reference example was proposed, using an arithmetic processor such as a computer or the like.In the estimation calculation system of the reference example, similar previous actual result information is acquired based on the specification information of the estimation object project; a model equation with the specification information as explanatory variables is generated based on the acquired actual result information; and the estimate is calculated by inputting the specification information of the estimation object into the model equation. However, it is difficult to calculate the estimate if the input specification information of the estimation object project does not correspond to the specification information used as explanatory variables of the model.

[0074] In contrast, according to the embodiment, for example, the projects are divided into multiple clusters based on the specification information; and for each cluster, a model equation (the estimation model M101) that estimates the cost of each estimation object and a model equation (the estimation model M102) that represents the cost structure of all estimation objects in the cluster are created. A cluster to which a similar project belongs is determined based on the specification information of the estimation object project; if the specification information of the estimation object project satisfies the explanatory variables of the estimation model M101, the model equation of the estimation model M101 is applied; and if the specification information of the estimation object project is insufficient, the model equation of the estimation model M102 is applied.This makes quantitative and efficient estimation possible, for example, even when specification information is insufficient during the estimation phase. For example, even when specification information is insufficient, a quantitative rough estimate can be calculated based on previous actual results, reducing the workload required to calculate the estimate.

[0075] According to the embodiment, the preprocessing part 22 normalizes the cost value of each of the multiple sets of previous project information based on each of the multiple sets of previous project information. As a result, for example, even if the scales of the multiple previous projects are different from each other, it is easy to treat the data of the multiple previous projects together; and models can be generated. Furthermore, the preprocessing part 22 sorts the various estimates by the average values ​​as described above. The order of the model equation can thereby be reduced.For example, the model equation generation part 23 generates the second model for each cluster Ck by plotting the relationship between the order of the multiple estimate items sorted by the preprocessing part 22 and the average values ​​of the values ​​associated with the multiple estimate items on a graph and performing regression analysis. This allows the order of the model equation to be reduced.

[0076] According to the embodiment, the estimation result is calculated by performing the model selection determination for each estimation item. In other words, for example, the model equation application part 25 selects one of the estimation models M101 or the estimation model M102 corresponding to one of the plurality of estimation items based on the specification information of the estimation object project. Then, the model equation application part 25 calculates the value related to one of the plurality of estimation items based on the selected model. The model equation application part 25 performs this processing for each estimation item. As a result, a more suitable model can be estimated for each estimation item.

[0077] According to the embodiment, for example, the estimation object project can be automatically classified into a group of similar projects by inputting the specification information of the estimation object project. For example, by switching the model equation applied according to the condition of the input specification information, the estimate can be calculated even if the specification information is insufficient in the initial estimation stage.

[0078] The example of Fig. Figure 6 shows when the specification information of the estimation object project satisfies the explanatory variables of the estimation model M101, which corresponds to the estimation item b6. The bar, which is separated by a single dashed line at the estimation item b6 in Fig. Figure 6 illustrates an estimate of the estimated item b6 calculated based on the estimation model M101 corresponding to the estimated item b6. If the estimate based on the estimation model M101 deviates from the cluster trend, the estimate can be adjusted as in the example of Fig. 6 can be treated as an outlier; and the estimated value can be calculated based on the estimation model M102.

[0079] For example, the estimated value based on the estimation model M101 is considered an outlier if the difference between the estimated value of the estimated item calculated based on the estimation model M102 and the estimated value of the estimated item calculated based on the estimation model M101 is greater than a prescribed value. The prescribed value can be determined, for example, based on the standard deviation σ, e.g., 3σ, of the estimated item calculated by the preprocessing part 22.

[0080] The confidence level of the estimation model M101 corresponding to the estimated item can be calculated based on the standard deviation σ and / or the sample size of the estimated items. For example, the confidence level increases as the standard deviation σ decreases, and the confidence level increases as the sample size increases. The confidence level can be appropriately used to determine outliers in the estimated item of the estimated items based on the estimation model M101. For example, the estimated value of the estimated item based on the estimation model M101 that has a confidence level below a prescribed value is determined as an outlier. If the estimated item based on the estimation model M101 is determined as an outlier, the estimated value based on the estimation model M102 can be used for the estimated item.

[0081] The components, such as the functional blocks, etc., described in the embodiment are designed functionally and may not always be physically configured as shown. Some or all of the multiple functional blocks may be combined as needed, or each functional block may be divided into multiple blocks. A portion of each functional block may be moved to another block. The components of the embodiment may be functionally or physically distributed or integrated as needed.

[0082] The embodiment may be an estimation acquisition program that, when executed by a computer, causes the computer to perform the estimation acquisition method described with reference to the above-described flowchart. The estimation acquisition system 100 performs the above-described processing based on the estimation acquisition program. However, all or part of the estimation acquisition method according to the embodiment may also be performed based on a hardware operation that does not require a program.

[0083] The program is not limited to a program configuration (a configuration located in the computer) that, when executed by the computer, causes the computer to perform the method described above, and may have the configuration of a computer-readable recording medium. For example, a CD-ROM (-R / -RW), a magneto-optical disk, an HD (hard disk), a DVD-ROM (-R / -RW / -RAM), an FD (Flexible Disk), a flash memory, other similar recording media, other various ROM, RAM, etc. can be used as the recording medium. The storage format can have any configuration as long as the recording medium can be read by a computer or an embedded system.A computer can perform operations similar to those of the above-described embodiment by reading a program from a recording medium and causing a CPU to execute the instructions described in the program based on the program. Of course, when the computer acquires or reads the program, the computer can also acquire or read the program over a network.

[0084] Part of the processing for realizing the embodiment may be performed by an OS (operating system) or database management software running on a computer or an embedded system based on instructions of a program installed from a recording medium in the computer or the embedded system, or by MW (middleware) running on a network, etc.

[0085] According to the embodiment, the recording medium is not limited to a recording medium independent of a computer or an embedded system, and includes a program that is transmitted via a LAN, the Internet, and so on, downloaded, and stored or temporarily stored on a recording medium. The recording medium is not limited to one recording medium; and the processing according to the embodiment, which is performed by multiple recording media, is also included in the recording medium according to the embodiment. The configuration of the recording medium can be any configuration.

[0086] The computer or embedded system according to the embodiment performs the processing according to the embodiment based on a program stored on a recording medium and may have any configuration such as a device consisting of a single personal computer, microcomputer, or the like, a system having a plurality of devices connected via a network, etc.

[0087] According to the embodiment, “computer” is not limited to a personal computer, but also includes a computing processor, microcomputer, etc. included in an information processing device, and generally refers to equipment or a device that can use a program to realize the functions according to the embodiment.

[0088] The embodiments may include the following configurations. Configuration 1

[0089] 1. A system for recording estimates, consisting of: a clustering part that groups a plurality of previous projects into a plurality of clusters based on specification information related to the plurality of previous projects; a preprocessing part that performs preprocessing of a plurality of predecessor project information related to the plurality of previous projects; a model equation generation part that generates a first model and a second model for each of the plurality of clusters based on the plurality of predecessor project information on which the preprocessing has been performed, wherein each of the plurality of predecessor project information includes the specification information and information about a cost value including a plurality of estimated items, wherein the first model represents a correlation between the specification information and a value related to the cost, wherein the second model represents a cost structure corresponding to a relationship between values ​​related to the plurality of estimated items; a cluster designation part that determines, based on specification information of an appraisal object project, a cluster among the plurality of clusters to which a previous project similar to the appraisal object project belongs; and a model equation application part that is configured to to select the first model or the second model for the cluster designated by the cluster designation part based on the specification information of the estimation object project, and Based on the selected model, a value is calculated that relates to an estimated item of the appraisal object project. Configuration 2

[0090] The system according to configuration 1, where the preprocessing part normalizes the cost values ​​of the plurality of predecessor project information based on the plurality of predecessor project information. Configuration 3

[0091] The system according to configuration 2, where the preprocessing part calculates for each of the plurality of clusters an average of values ​​relating to each of the plurality of estimate items for the plurality of previous projects, and the preprocessing part sorts the multitude of estimated items according to the average values. Configuration 4

[0092] The system according to configuration 3, where the model equation generation part generates the second model for each of the plurality of clusters based on a relationship between an order of the plurality of estimate items sorted by the preprocessing part, and the average values ​​of the values ​​relating to the plurality of estimated items. Configuration 5

[0093] The system according to one of the configurations 1 to 4, wherein the first model includes a plurality of estimation models, each of the plurality of estimation models represents a correlation between the specification information of the plurality of previous projects and values ​​each relating to the plurality of estimation items, and for each of the multitude of estimate items of the model equation application part based on the specification information of the appraisal object project, selects one of the second models or an appraisal model from the plurality of appraisal models that corresponds to one of the plurality of appraisal items, and Based on the selected model, a value is calculated that relates to one of the several estimated items of the appraisal object project. Configuration 6

[0094] The system according to configuration 5, where the specification information for each of the several previous projects contains information about several specification elements, the plurality of estimation models includes a first estimation model corresponding to a first estimation item, the first estimation model represents a correlation between a first specification part and a value relating to the first estimate item of the plurality of previous projects, wherein the first specification part is at least a part of the plurality of specification elements, if the specification information of the estimation object project contains all the specification elements contained in the first specification part, the model equation application part selects the first estimation model, and estimates a value that relates to the first estimate item of the estimate object project by applying the specification information of the estimate object project to the first estimate model, and if the specification information of the estimation object project does not contain at least part of the specification elements included in the first specification part, the model equation application part selects the second model, and estimates the value related to the first appraisal item of the appraisal object project based on the second model. Configuration 7

[0095] A storage medium, where the storage medium is computer-readable, the storage medium is configured to store a program for capturing estimates, the estimate capture program, when run by a computer, causes the computer to: to cluster a plurality of previous projects into a plurality of clusters based on specification information relating to the plurality of previous projects; to carry out pre-processing of a plurality of information about previous projects relating to the plurality of previous projects; generate a first model and a second model for each of the plurality of clusters based on the plurality of predecessor project information on which the preprocessing was performed, wherein each of the plurality of predecessor project information includes the specification information and information about a cost value including a plurality of estimated items, wherein the first model represents a correlation between the specification information and a value related to the cost, wherein the second model represents a cost structure corresponding to a relationship between values ​​related to the plurality of estimated items; to determine, based on specification information of an appraisal object project, a cluster from the plurality of clusters to which a previous project similar to the appraisal object project belongs; to select one of the first models or the second model for the designated cluster based on the specification information of the estimation object project and to calculate a value based on the selected model that relates to an estimated item of the appraisal object project.

[0096] According to embodiments, an estimate acquisition system and an estimate acquisition program can be provided with which an estimate can be easily acquired.

[0097] Although certain embodiments have been described, these embodiments have been presented only by way of example and are not intended to limit the scope of the inventions. Indeed, the novel embodiments described herein may be embodied in a variety of other forms; furthermore, various omissions, substitutions, and changes may be made in the form of the embodiments described herein without departing from the spirit of the inventions. The appended claims and their equivalents are intended to cover such forms or changes as fall within the scope and spirit of the invention. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] JP 2015-099476 A

[0003] JP 2019-101681 A

[0004]

Claims

[1] Estimate recording system, comprising: a clustering part that clusters a plurality of previous projects into a plurality of clusters based on specification information related to the plurality of previous projects; a preprocessing part that performs preprocessing of a plurality of predecessor project information related to the plurality of previous projects; a model equation generation part that generates a first model and a second model for each of the plurality of clusters based on the plurality of predecessor project information on which the preprocessing has been performed, wherein each of the plurality of predecessor project information includes the specification information and information about a cost value including a plurality of estimated items, wherein the first model represents a correlation between the specification information and a value related to the cost, wherein the second model represents a cost structure corresponding to a relationship between values ​​related to the plurality of estimated items; a cluster designation part that determines, based on specification information of an appraisal object project, a cluster among the plurality of clusters to which a previous project similar to the appraisal object project belongs; and a model equation application part that is configured to to select the first model or the second model for the cluster designated by the cluster designation part based on the specification information of the estimation object project, and Based on the selected model, a value is calculated that relates to an estimated item of the appraisal object project. [2] The system according to claim 1, wherein the preprocessing part normalizes the cost values ​​of the plurality of predecessor project information respectively based on the plurality of predecessor project information. [3] System according to claim 2, wherein the preprocessing part calculates for each of the plurality of clusters an average of values ​​relating to each of the plurality of estimate items for the plurality of previous projects, and the preprocessing part sorts the multitude of estimated items according to the average values. [4] System according to claim 3, wherein the model equation generation part generates the second model for each of the plurality of clusters based on a relationship between an order of the plurality of estimates sorted by the preprocessing part and the average values ​​of the values ​​that relate to the multitude of estimated items. [5] System according to claim 1, wherein the first model includes a plurality of estimation models, each of the plurality of estimation models represents a correlation between the specification information of the plurality of previous projects and values ​​each relating to the plurality of estimation items, and for each of the several estimated items of the model equation application part based on the specification information of the appraisal object project, selects one of the second models or an appraisal model from the plurality of appraisal models that corresponds to one of the plurality of appraisal items, and Based on the selected model, a value is calculated that relates to one of the numerous estimated items of the appraisal object project. [6] System according to claim 5, wherein the specification information for each of the multiple previous projects contains information on multiple specification items, the plurality of estimation models includes a first estimation model corresponding to a first estimation item, the first estimation model represents a correlation between a first specification part and a value relating to the first estimate item of the plurality of previous projects, wherein the first specification part is at least a part of the plurality of specification elements, if the specification information of the estimation object project contains all the specification elements contained in the first specification part, the model equation application part selects the first estimation model, and estimates a value that relates to the first estimate item of the estimate object project by applying the specification information of the estimate object project to the first estimate model, and if the specification information of the estimation object project does not contain at least part of the specification elements included in the first specification part, the model equation application part selects the second model, and estimates the value related to the first appraisal item of the appraisal object project based on the second model. [7] Storage medium, where the storage medium is computer-readable, the storage medium is configured to store a program for capturing estimates, the estimate capture program, when run by a computer, causes the computer to: to cluster a plurality of previous projects into a plurality of clusters based on specification information relating to the plurality of previous projects; to carry out pre-processing of a plurality of information about previous projects relating to the plurality of previous projects; generate a first model and a second model for each of the plurality of clusters based on the plurality of predecessor project information on which the preprocessing was performed, wherein each of the plurality of predecessor project information includes the specification information and information about a cost value including a plurality of estimated items, wherein the first model represents a correlation between the specification information and a value related to the cost, wherein the second model represents a cost structure corresponding to a relationship between values ​​related to the plurality of estimated items; to determine, based on specification information of an appraisal object project, a cluster from the plurality of clusters to which a previous project similar to the appraisal object project belongs; based on the specification information of the estimation object project of the first model or the second model for the designated cluster and to calculate a value based on the selected model that relates to an estimated item of the appraisal object project.

Citation Information

Patent Citations

  • Approximate estimate preparation system and approximate estimate preparation method

    JP2015099476A

  • Quotation acquisition device, quotation acquisition method, and program

    JP2019101681A

  • JP002015099476A

  • JP002019101681A