The Application Of The Data Mining Technology In The Information System Of Population

Since the basic information management system of population was built in middle period of the eighties, there have already. 10 6,800 million demographic data been included in computer management, accounts for 86% of total population. In the face of so enormous data amount, and can not get effective use,a lot of advanced research approaches and data processing methods can't be applied to population research .In recent years, the information technology of the network and computer technology are developed rapidly, data analysis of technology offering the unprecedented facility for development, use of demographic data, share with population constant innovation. Fast-moving forms of people require the research results socialized accelerating of population, making the demographic renewal of knowledge accelerate too. However, we utilize degree of modernized technology still far from enough at present, especially the resource-sharing degree of our domestic people's educational circles is still quite low, it is quite backward too to share the way, Such backward situation needs changing fast badly, otherwise it is wasted that the one that will cause population resources of our country is enormous, people's theoretical research and real work disconnect seriously, development restraining the people of our country from studying seriously. In the face of this current situation, we should fully utilize the modernized information technology and treatment technology, with maximum development and use demographic data resource, socialization of the research results of population in advance at the fastest speed. The application study of data mining on people's information of technology, it is still the blank to be domestic at present. Because the technology that the data mining is applied to such fields as the finance, market industry, project and scientific research, products manufacturing industry, administration of justice, etc. mainly at present, So technology of data mining is introduced to the demographic field to collect in the research field of population, and for widening the application that the data mining, widen the thinking that people study, significant This text based on the compiling relevant materials extensively, have described the current situation which people study at present at first, have announced people study the existing problem, And then introduced relevant knowledge that the technology of data mining and use the current situation, have expounded the fact the data mining applied to people study the great realistic meaning. Secondly, Based on the induced attributes and relationship among the induced attributes of the population's information system, the tasks of the statistical analysis and the data mining, and the function for data mining is determined. Then carry on the pretreatment to the data, It is mainly to the data of omitting, the noise data are dealt with, and change and deal with the corresponding data according to the task that the data mining, it is that the following modeling work is ready. It is the type modeling of change of population to choose to utilize the decision tree finally, and set up the method and introduced the detailed one to decision tree .SAS is chosen as tool of data mining, and use the tree algorithm modeling of decision, find the classification of the type of change of population and mode of the law, And has explained the result. This text includes five chapter contents altogether. Chapter one: Introduction. This chapter studies the current situation to describe on the people at present at first, find the problem existing in people study at present. Embodied in mainly, in the face of huge demographic data resources, and can not get effective use, a lot of advanced research approaches and data processing methods can't be applied to people and studied either, people's theoretical research and real work disconnect seriously, Such backward situation needs changing fast badly, Will cause of our country population resource enormous to waste, restrain of our country development that population study from seriously. And then introduced the technology of data mining, foundational knowledge of the data mining and application that the data mining have been explained mainly, and has proved the data mining technology to apply in the feasibility of the research field of population and great meaning Chapter two: Confirmation of the task of data mining. This chapter has induced attributes to the demographic data at first, deleted the redundant attributeamong the systems mainly by utilizing attribute generalization and the method of attribute deleting. Under the foundation of the induced attributes, utilizing the data cube to confirm the statistical analysis task, then combine 0-1 between induced attributes and differentiate matrix according to relevant knowledge that people study, we confirmed the task of data mining to the demographic data; And the function of data mining has carried on the detailed classification, we confirmed finally the function of data mining to the data of the demographic data. Chapter three: Pretreatment of the data. This chapter is on the basis of induced attributes above, carrying on the pretreatment to the demographic data further. It is the data that are washed at first, mainly fill in and omit the data, level and smooth noise data, and correct the inconsistent data course, There are the treating method used that neglecting this record, filling in the omitting value by hand, utilizing defaulting value to fill in the omitting value, utilizing mean value to fill in the omitting value, utilizing generic mean value to fill in the omitting value, utilizing the most possible value to fill in the omitting value. Then the data are changed and deal with. We change and deal with left demographic data, deal with levelly and smoothly, total and deal with, standardize, construct. Chapter four: Data mining law of change of population based on decision tree. This chapter has stated the basic conception of the tree, explained the basic theories and algorithm of the decision tree, summarized some branch standards and beta pruning methods used during the process of constructing the decision tree, proved especially course of growth course of decision tree, beta pruning course of the tree and optimum tree, and the algorithm of the decision tree, and set up the data database for data mining in demographic data of utilizing SAS and, and then the operation of the model and result analysis, used the decision tree module to construct models to the behavior of change of population, and drawn the rule and mode which describe the characteristic of change of population. We explained and analyzed the result-combined people's knowledge. Chapter five: Summary. Innovation of this text: The data mining technology is applied to population...