Design And Research Of Project Cost Database Based On Data Mining

The development of informationization and cost reform promotes the accumulation of engineering cost data,which makes it an inevitable trend to realize the sustainable development in the field of engineering cost.The engineering cost database has also attracted the attention of many cost consulting enterprises.However,through the investigation,it is found that the vast majority of cost consulting enterprises have not established their own cost database,but still rely on the accumulation of human experience and the tabular storage and archiving of ordinary computers.This traditional tabular data accumulation method is not conducive to investigation and use,can not activate data assets,resulting in low data value.As a result,cost consulting enterprises do not set up their own project cost database,the main reasons are three aspects: first,because the original cost data abundant,various forms,resulting in high data noise,data system is not clear;second,because the data formed by cost consulting enterprises are often stored in different excel tables,unable to achieve data integration and comparison,backward data storage and processing methods lead to the lack of systematic scheme for in-depth analysis of data in cost consulting enterprises;Third,even if the database is used,it is difficult to give full play to the value of historical data to provide reference for new projects because of the low level of information.Based on the above problems,this paper carries out the following three aspects of research.First,The design of structured database form is completed based on primitiveness mining.Firstly,the index system of primitive mining is obtained by practical application research and information precipitation method,and then the characteristic factors affecting the project cost index are selected according to the analysis of primary and secondary factors and literature analysis.Based on AHP,the important feature factor set of engineering cost index is established,and a structured database form is established to provide the data basis for the analysis and prediction of the subsequent database.Second,The function of database analysis is designed based on descriptive mining.Firstly,the input and output parameterized tables are designed to realize the function of economic description,and the charts are designed to realize the function of database visual.Third,the prediction function of database is designed based on predictive mining.Firstly,through the literature study of the advantages and disadvantages of various prediction methods,the applicability of case reasoning technology as a database prediction system.Then the predictive mining model is established by using the case reasoning system for reference,the implementation steps are clarified,and the case is used for empirical analysis to ensure that the prediction model is scientific and reasonable,and the prediction function of the database has the possibility of realization.In summary,based on data mining technology,this paper basically realizes the identification according to the rules,arranges the original cost information,and establishes the structured database form by various research methods.