A data mining system and method based on Internet information

Abstract

The present invention provides a data mining system and method based on Internet information, and relates to the technical field of data mining. The system comprises: extracting data features by acquiring and preprocessing Internet information, classifying data features according to the data features and the data correlation of Internet information, and determining fixed data features and mobile data features; performing data similarity mining on Internet information according to the fixed data features and performing data transfer rate mining on Internet information according to the mobile data features, clustering and merging the data similarity mining results and the data transfer rate mining results according to the data correlation between the data features; constructing a data mining evaluation system, performing mining evaluation on the clustered and merged data mining results, and visually displaying the clustered and merged data mining results when the mining evaluation is qualified; and realizing efficient and high-quality data mining based on Internet information.

Description

Technical Field

[0001] The present invention relates to the technical field of data mining, and in particular to a data mining system and method based on Internet information. Background Art

[0002] With the continuous development of the Internet, Internet information is becoming more and more valuable, and data mining of Internet information is becoming more frequent and diverse. Internet information can be effectively utilized through data mining; however, due to the complex structure of Internet information and the large amount of data, the efficiency of data mining of Internet information is low; in addition, data mining of the same type of Internet information is prone to only mining this type of Internet information, and it is impossible to expand the mining of other types of Internet information, and data mining is not universal.

[0003] Therefore, the present invention provides a data mining system and method based on Internet information. Summary of the invention

[0004] The present invention provides a data mining system and method based on Internet information. The system acquires and preprocesses Internet information, extracts data features, classifies data features according to data features and data correlations of Internet information, and determines fixed data features and mobile data features. Data similarity mining is performed on Internet information according to the fixed data features, and data transfer rate mining is performed on Internet information according to the mobile data features. Data similarity mining results and data transfer rate mining results are clustered and merged according to data correlations between data features. A data mining evaluation system is constructed to perform mining evaluation on clustered and merged data mining results, and when the mining evaluation is qualified, the clustered and merged data mining results are visualized. High-efficiency and high-quality data mining based on Internet information is realized.

[0005] The present invention provides a data mining system based on Internet information, comprising:

[0006] The acquisition and processing module is used to acquire and pre-process Internet information, extract data features, classify data features according to the data relevance between the data features and the Internet information, and determine fixed data features and mobile data features;

[0007] A data mining module, used to perform data similarity mining on Internet information according to the fixed data features and data transfer rate mining on Internet information according to the mobile data features, and cluster and merge the data similarity mining results and the data transfer rate mining results according to the data correlation between the data features;

[0008] The evaluation and display module is used to construct a data mining evaluation system, conduct mining evaluation on the data mining results of cluster merging, and visualize the data mining results of cluster merging when the mining evaluation is qualified.

[0009] According to a data mining system based on Internet information provided by the present invention, the acquisition and processing module includes:

[0010] A data acquisition unit, used to set a data source and acquire Internet information;

[0011] A data processing unit is used to perform data cleaning and preprocessing on Internet information to remove erroneous data and abnormal data;

[0012] Perform data normalization on Internet information that has completed data cleaning and preprocessing;

[0013] The data storage unit is used to store the Internet information after the data normalization processing is completed.

[0014] According to a data mining system based on Internet information provided by the present invention, the acquisition and processing module includes:

[0015] A data feature extraction unit, used to extract data features from the stored Internet information according to a preset data feature extraction strategy to obtain data features;

[0016] A data feature relevance unit, used to determine the data relevance of data features and Internet information;

[0017] A data feature classification unit, used to classify the data features according to the data correlation between the data features and the Internet information, and determine the fixed data features and the mobile data features;

[0018] When the data relevance between the data feature and the Internet information is not less than the preset relevance, the corresponding data feature is determined to be a fixed data feature;

[0019] When the data correlation between the data feature and the Internet information is lower than the preset correlation and the data feature has a data correlation with other Internet information that is not lower than the preset correlation, the corresponding data feature is determined to be a mobile data feature.

[0020] According to a data mining system based on Internet information provided by the present invention, a data feature correlation unit includes:

[0021] The data feature correlation block is used to calibrate the main data features of Internet information, obtain historically stored Internet information, and determine the data correlation between the data features and the Internet information based on the number of occurrences of the data features in the historically stored Internet information, the number of occurrences of the main data features, and the number of simultaneous occurrences of the data features and the main data features.

[0022] According to a data mining system based on Internet information provided by the present invention, the data mining module includes:

[0023] A data similarity mining unit is used to obtain structural distribution data between fixed data features, the number of occurrences of fixed data features in Internet information, and to form a data similarity mining template;

[0024] Extracting a fixed number of Internet information features from Internet information, performing data similarity mining on the Internet information, and determining mining similarity between the Internet information and the data similarity mining template;

[0025] When the mining similarity is not lower than the preset similarity, it is determined that the data similarity mining is completed;

[0026] Otherwise, the fixed data features are deleted one by one from large to small according to the number of times they appear in the Internet information, and Internet information features are randomly selected for corresponding replacement, and the data similarity mining template is reconstructed;

[0027] A data transfer rate mining unit is used to obtain the feature transfer probability of mobile data features and the data similarity between the mobile data features and the Internet information features, perform data transfer rate mining on the Internet information, and determine the mining transfer rate of the mobile data features and the Internet information;

[0028] A mining cluster merging unit is used to obtain data correlation between data features, and determine a cluster merging rate for clustering and merging data similarity mining results and data transfer rate mining results in combination with mining similarity and mining transfer rate;

[0029] ;in, represents the cluster merging rate; Indicates when When a fixed data feature is not replaced by an Internet information feature, output 0, otherwise, output 1; Indicates The number of times a fixed data feature appears in Internet information; The total amount of data representing Internet information; Indicates The number of times a fixed data feature appears in various types of Internet information; Indicates The feature transition probability of each mobile data feature; Indicates feature vector of mobile data features; Indicates The feature vector of the Internet information feature corresponding to the mobile data feature; represents the average data correlation between fixed data features and Internet information features; represents the average data correlation between mobile data characteristics and Internet information characteristics; Indicates the number of fixed data features; Indicates the number of mobile data features;

[0030] When the cluster merging rate of cluster merging the data similarity mining results and the data transfer rate mining results is not lower than a preset cluster value, the data similarity mining results and the data transfer rate mining results are clustered and merged.

[0031] According to a data mining system based on Internet information provided by the present invention, the evaluation display module includes:

[0032] A data mining evaluation system unit is used to determine data mining evaluation indicators based on the data mining results of historically stored Internet information and to construct a data mining evaluation system, wherein the data mining evaluation indicators include: data mining precision evaluation indicators, data mining accuracy evaluation indicators and data mining efficiency evaluation indicators;

[0033] A mining evaluation unit, used to perform quantitative evaluation on the data mining results of cluster merging according to the data mining evaluation system to obtain a current quantitative score;

[0034] A quantitative scoring threshold is determined according to the data mining results of historically stored Internet information, and when the current quantitative scoring is not lower than the quantitative scoring threshold, it is determined that the mining evaluation of the cluster-merged data mining results is qualified.

[0035] According to a data mining system based on Internet information provided by the present invention, the evaluation display module includes:

[0036] A mining display unit, used for visually displaying the data mining results of the cluster merging that has passed the mining evaluation and the current quantitative score;

[0037] The iterative updating unit is used for periodically iteratively updating the data mining results of cluster merging and periodically iteratively updating the data mining evaluation system.

[0038] The present invention provides a data mining method based on Internet information, comprising:

[0039] Step 1: Obtain and preprocess Internet information, extract data features, classify data features according to the data relevance between the data features and Internet information, and determine fixed data features and mobile data features;

[0040] Step 2: performing data similarity mining on Internet information according to the fixed data features and performing data transfer rate mining on Internet information according to the mobile data features, and clustering and merging the data similarity mining results and the data transfer rate mining results according to the data correlation between the data features;

[0041] Step 3: Construct a data mining evaluation system to conduct mining evaluation on the data mining results of cluster merging, and visualize the data mining results of cluster merging when the mining evaluation is qualified.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The invention obtains and pre-processes Internet information, extracts data features, classifies data features according to the data features and the data correlation of Internet information, determines fixed data features and mobile data features; performs data similarity mining on Internet information according to the fixed data features and performs data transfer rate mining on Internet information according to the mobile data features, clusters and merges the data similarity mining results and the data transfer rate mining results according to the data correlation between data features; constructs a data mining evaluation system, performs mining evaluation on the clustered and merged data mining results, and visualizes the clustered and merged data mining results when the mining evaluation is qualified; thus, efficient and high-quality data mining based on Internet information is realized.

[0044] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0045] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0047] Figure 1 It is a structural schematic diagram of a data mining system based on Internet information provided by an embodiment of the present invention;

[0048] Figure 2 It is a flow chart of a data mining method based on Internet information provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention. Embodiment 1:

[0050] The embodiment of the present invention provides a data mining system based on Internet information, such as Figure 1 As shown, including:

[0051] The acquisition and processing module is used to acquire and pre-process Internet information, extract data features, classify data features according to the data relevance between the data features and the Internet information, and determine fixed data features and mobile data features;

[0052] A data mining module, used to perform data similarity mining on Internet information according to the fixed data features and data transfer rate mining on Internet information according to the mobile data features, and cluster and merge the data similarity mining results and the data transfer rate mining results according to the data correlation between the data features;

[0053] The evaluation and display module is used to construct a data mining evaluation system, conduct mining evaluation on the data mining results of cluster merging, and visualize the data mining results of cluster merging when the mining evaluation is qualified.

[0054] In this embodiment, fixed data features refer to data features used to analyze and mine the current category of Internet information.

[0055] In this embodiment, the mobile data features refer to data features used to analyze and mine other types of Internet information.

[0056] In this embodiment, data similarity mining refers to data mining of Internet information based on fixed data features, which is used to mine similar Internet information.

[0057] In this embodiment, data transfer rate mining refers to data mining based on mobile data characteristics, which is used to mine other types of Internet information and expand the mining results of this type of Internet information.

[0058] In this embodiment, cluster merging refers to summarizing the data similarity mining results and the data transfer rate mining results to achieve high-quality mining of Internet information.

[0059] In this embodiment, a data mining evaluation system is constructed to accurately analyze and evaluate data mining results, wherein the data mining evaluation system is constructed by data mining evaluation indicators, and the data mining evaluation indicators include: data mining precision evaluation indicators, data mining accuracy evaluation indicators and data mining efficiency evaluation indicators.

[0060] The working principle and beneficial effects of the above technical solution are: by acquiring and preprocessing Internet information, extracting data features, classifying data features according to the data correlation between data features and Internet information, and determining fixed data features and mobile data features; performing data similarity mining on Internet information according to the fixed data features and performing data transfer rate mining on Internet information according to the mobile data features, clustering and merging the data similarity mining results and the data transfer rate mining results according to the data correlation between data features; building a data mining evaluation system, performing mining evaluation on the clustered and merged data mining results, and visually displaying the clustered and merged data mining results when the mining evaluation is qualified; and realizing efficient and high-quality data mining based on Internet information. Embodiment 2:

[0061] The embodiment of the present invention provides a data mining system based on Internet information, a collection and processing module, including:

[0062] A data acquisition unit, used to set a data source and acquire Internet information;

[0063] A data processing unit is used to perform data cleaning and preprocessing on Internet information to remove erroneous data and abnormal data;

[0064] Perform data normalization on Internet information that has completed data cleaning and preprocessing;

[0065] The data storage unit is used to store the Internet information after the data normalization processing is completed.

[0066] In this embodiment, the Internet information that has completed the data normalization process is stored according to the Internet information category, wherein the Internet information category can be divided and determined according to the Internet information type, format and data source.

[0067] The working principle and beneficial effect of the above technical solution are: by acquiring and preprocessing Internet information, it is conducive to subsequent accurate data mining of Internet information, laying the foundation for data mining. Embodiment 3:

[0068] The embodiment of the present invention provides a data mining system based on Internet information, a collection and processing module, including:

[0069] A data feature extraction unit, used to extract data features from the stored Internet information according to a preset data feature extraction strategy to obtain data features;

[0070] A data feature relevance unit, used to determine the data relevance of data features and Internet information;

[0071] A data feature classification unit, used to classify the data features according to the data correlation between the data features and the Internet information, and determine the fixed data features and the mobile data features;

[0072] When the data relevance between the data feature and the Internet information is not less than the preset relevance, the corresponding data feature is determined to be a fixed data feature;

[0073] When the data correlation between the data feature and the Internet information is lower than the preset correlation and the data feature has a data correlation with other Internet information that is not lower than the preset correlation, the corresponding data feature is determined to be a mobile data feature.

[0074] In this embodiment, the preset data feature extraction strategy refers to a strategy for efficiently extracting data features, such as a word frequency-inverse word frequency data feature extraction strategy.

[0075] In this embodiment, when the data correlation between a data feature and Internet information is not lower than a preset correlation, the corresponding data feature is determined to be a fixed data feature, that is, the fixed data feature is stably correlated with the current Internet information and can be used for data mining of the current Internet information.

[0076] In this embodiment, the mobile data feature may appear in the current Internet information or in other Internet information, but is not stably related to the Internet information.

[0077] In this embodiment, the mobile data feature is used to perform data expansion mining on Internet information, that is, the current Internet information is linked with other Internet information through the mobile data feature, and then the correlation between the current Internet information and other Internet information is mined.

[0078] The working principle and beneficial effects of the above technical solution are: classifying data features according to their data correlation with Internet information, determining fixed data features and mobile data features, which is conducive to the subsequent high-quality data mining of Internet information. Embodiment 4:

[0079] The embodiment of the present invention provides a data mining system based on Internet information, a data feature correlation unit, including:

[0080] The data feature correlation block is used to calibrate the main data features of Internet information, obtain historically stored Internet information, and determine the data correlation between the data features and the Internet information based on the number of occurrences of the data features in the historically stored Internet information, the number of occurrences of the main data features, and the number of simultaneous occurrences of the data features and the main data features.

[0081] In this embodiment, the main data features of the Internet information, that is, the data features that are stably related to the Internet information, are used to represent the Internet information.

[0082] The working principle and beneficial effects of the above technical solution are: by calibrating the main data characteristics of Internet information and determining the data correlation between data characteristics and Internet information, it is conducive to the division of data characteristics and lays the foundation for subsequent data characteristics. Embodiment 5:

[0083] The embodiment of the present invention provides a data mining system based on Internet information, and a data mining module, including:

[0084] A data similarity mining unit is used to obtain structural distribution data between fixed data features, the number of occurrences of fixed data features in Internet information, and to form a data similarity mining template;

[0085] Extracting a fixed number of Internet information features from Internet information, performing data similarity mining on the Internet information, and determining mining similarity between the Internet information and the data similarity mining template;

[0086] When the mining similarity is not lower than the preset similarity, it is determined that the data similarity mining is completed;

[0087] Otherwise, the fixed data features are deleted one by one from large to small according to the number of times they appear in the Internet information, and Internet information features are randomly selected for corresponding replacement, and the data similarity mining template is reconstructed;

[0088] A data transfer rate mining unit is used to obtain the feature transfer probability of mobile data features and the data similarity between the mobile data features and the Internet information features, perform data transfer rate mining on the Internet information, and determine the mining transfer rate of the mobile data features and the Internet information;

[0089] A mining cluster merging unit is used to obtain data correlation between data features, and determine a cluster merging rate for clustering and merging data similarity mining results and data transfer rate mining results in combination with mining similarity and mining transfer rate;

[0090] ;in, represents the cluster merging rate; Indicates when When a fixed data feature is not replaced by an Internet information feature, output 0, otherwise, output 1; Indicates The number of times a fixed data feature appears in Internet information; The total amount of data representing Internet information; Indicates The number of times a fixed data feature appears in various types of Internet information; Indicates The feature transition probability of each mobile data feature; Indicates feature vector of mobile data features; Indicates The feature vector of the Internet information feature corresponding to the mobile data feature; represents the average data correlation between fixed data features and Internet information features; represents the average data correlation between mobile data characteristics and Internet information characteristics; Indicates the number of fixed data features; Indicates the number of mobile data features;

[0091] When the cluster merging rate of cluster merging the data similarity mining results and the data transfer rate mining results is not lower than a preset cluster value, the data similarity mining results and the data transfer rate mining results are clustered and merged.

[0092] In this embodiment, the data similarity mining template refers to a template for performing data similarity mining analysis on Internet information.

[0093] In this embodiment, mining similarity refers to the text similarity between Internet information and a data similarity mining template. The higher the mining similarity, the higher the data mining efficiency and the higher the mining quality of Internet information by the data similarity template constructed according to fixed data features.

[0094] In this embodiment, the feature transfer probability of the mobile data feature refers to the probability of the mobile data feature transferring from the current Internet information to other Internet information, and is used to indicate the possibility of supplementary mining of the current Internet information data by other Internet information.

[0095] In this embodiment, the cluster merging rate of clustering and merging the data similarity mining results and the data transfer rate mining results refers to the possibility of clustering and merging the data similarity mining results and the data transfer rate mining results.

[0096] In this embodiment, when the cluster merging rate of clustering and merging the data similarity mining results and the data transfer rate mining results is lower than the preset clustering value, it means that the data similarity mining is insufficient or the data transfer rate mining is insufficient, and data mining needs to be performed again.

[0097] The working principle and beneficial effect of the above technical solution are: by performing data similarity mining on Internet information according to the fixed data characteristics and performing data transfer rate mining on Internet information according to the mobile data characteristics, the data similarity mining results and the data transfer rate mining results are clustered and merged according to the data correlation between the data characteristics, thereby achieving efficient and high-quality data mining based on Internet information. Embodiment 6:

[0098] The embodiment of the present invention provides a data mining system based on Internet information, an evaluation display module, including:

[0099] A data mining evaluation system unit is used to determine data mining evaluation indicators based on the data mining results of historically stored Internet information and to construct a data mining evaluation system, wherein the data mining evaluation indicators include: data mining precision evaluation indicators, data mining accuracy evaluation indicators and data mining efficiency evaluation indicators;

[0100] A mining evaluation unit, used to perform quantitative evaluation on the data mining results of cluster merging according to the data mining evaluation system to obtain a current quantitative score;

[0101] A quantitative scoring threshold is determined according to the data mining results of historically stored Internet information, and when the current quantitative scoring is not lower than the quantitative scoring threshold, it is determined that the mining evaluation of the cluster-merged data mining results is qualified.

[0102] In this embodiment, the weights of the impact of the data mining evaluation indicators on the quantitative scores are different, and the weight settings can be changed according to needs.

[0103] In this embodiment, the quantitative score threshold is the lower limit of the quantitative score for judging whether the data mining result is qualified.

[0104] The working principle and beneficial effect of the above technical solution are: by constructing a data mining evaluation system, the data mining results of cluster merging are evaluated, which effectively ensures the quality and efficiency of data mining. Embodiment 7:

[0105] The embodiment of the present invention provides a data mining system based on Internet information, an evaluation display module, including:

[0106] A mining display unit, used for visually displaying the data mining results of the cluster merging that has passed the mining evaluation and the current quantitative score;

[0107] The iterative updating unit is used for periodically iteratively updating the data mining results of cluster merging and periodically iteratively updating the data mining evaluation system.

[0108] In this embodiment, the data mining results of cluster merging are updated iteratively and the data mining evaluation system is updated iteratively periodically, wherein the iteration period is determined according to the mining quantitative score.

[0109] The working principle and beneficial effect of the above technical solution are: by visually displaying the data mining results of merging the clusters after the mining evaluation is qualified, it is beneficial to make full use of the data mining results. Embodiment 8:

[0110] The embodiment of the present invention provides a data mining method based on Internet information, such as Figure 2 As shown, including:

[0111] Step 1: Obtain and preprocess Internet information, extract data features, classify data features according to the data relevance between the data features and Internet information, and determine fixed data features and mobile data features;

[0112] Step 2: performing data similarity mining on Internet information according to the fixed data features and performing data transfer rate mining on Internet information according to the mobile data features, and clustering and merging the data similarity mining results and the data transfer rate mining results according to the data correlation between the data features;

[0113] Step 3: Construct a data mining evaluation system to conduct mining evaluation on the data mining results of cluster merging, and visualize the data mining results of cluster merging when the mining evaluation is qualified.

[0114] The working principle and beneficial effects of the above technical solution are: by acquiring and preprocessing Internet information, extracting data features, classifying data features according to the data correlation between data features and Internet information, and determining fixed data features and mobile data features; performing data similarity mining on Internet information according to the fixed data features and performing data transfer rate mining on Internet information according to the mobile data features, clustering and merging the data similarity mining results and the data transfer rate mining results according to the data correlation between data features; building a data mining evaluation system, performing mining evaluation on the clustered and merged data mining results, and visually displaying the clustered and merged data mining results when the mining evaluation is qualified; and realizing efficient and high-quality data mining based on Internet information.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data mining system based on Internet information, characterized in that: include: The acquisition and processing module is used to acquire and pre-process Internet information, extract data features, classify data features according to the data relevance between the data features and the Internet information, and determine fixed data features and mobile data features; A data mining module, used to perform data similarity mining on Internet information according to the fixed data features and data transfer rate mining on Internet information according to the mobile data features, and cluster and merge the data similarity mining results and the data transfer rate mining results according to the data correlation between the data features; An evaluation and display module is used to build a data mining evaluation system, conduct mining evaluation on the data mining results of cluster merging, and visualize the data mining results of cluster merging when the mining evaluation is qualified; Data mining modules, including: A data similarity mining unit is used to obtain structural distribution data between fixed data features, the number of occurrences of fixed data features in Internet information, and to form a data similarity mining template; Extracting a fixed number of Internet information features from Internet information, performing data similarity mining on the Internet information, and determining mining similarity between the Internet information and the data similarity mining template; When the mining similarity is not lower than the preset similarity, it is determined that the data similarity mining is completed; Otherwise, the fixed data features are deleted one by one from large to small according to the number of times they appear in the Internet information, and Internet information features are randomly selected for corresponding replacement, and the data similarity mining template is reconstructed; A data transfer rate mining unit is used to obtain the feature transfer probability of mobile data features and the data similarity between the mobile data features and the Internet information features, perform data transfer rate mining on the Internet information, and determine the mining transfer rate of the mobile data features and the Internet information; A mining cluster merging unit is used to obtain data correlation between data features, and determine a cluster merging rate for clustering and merging data similarity mining results and data transfer rate mining results in combination with mining similarity and mining transfer rate; ;in, represents the cluster merging rate; Indicates when When a fixed data feature is not replaced by an Internet information feature, output 0, otherwise, output 1; Indicates The number of times a fixed data feature appears in Internet information; The total amount of data representing Internet information; Indicates The number of times a fixed data feature appears in various types of Internet information; Indicates The feature transition probability of each mobile data feature; Indicates feature vector of mobile data features; Indicates The feature vector of the Internet information feature corresponding to the mobile data feature; represents the average data correlation between fixed data features and Internet information features; represents the average data correlation between mobile data characteristics and Internet information characteristics; Indicates the number of fixed data features; Indicates the number of mobile data features; When the cluster merging rate of clustering and merging the data similarity mining results and the data transfer rate mining results is not lower than a preset clustering value, the data similarity mining results and the data transfer rate mining results are clustered and merged.

2. A data mining system based on Internet information according to claim 1, characterized in that: Acquisition and processing module, including: A data acquisition unit, used to set a data source and acquire Internet information; A data processing unit is used to perform data cleaning and preprocessing on Internet information to remove erroneous data and abnormal data; Perform data normalization on Internet information that has completed data cleaning and preprocessing; The data storage unit is used to store the Internet information after the data normalization processing is completed.

3. A data mining system based on Internet information according to claim 2, characterized in that: Acquisition and processing module, including: A data feature extraction unit, used to extract data features from the stored Internet information according to a preset data feature extraction strategy to obtain data features; A data feature relevance unit, used to determine the data relevance of data features and Internet information; A data feature classification unit, used to classify the data features according to the data correlation between the data features and the Internet information, and determine the fixed data features and the mobile data features; When the data relevance between the data feature and the Internet information is not less than the preset relevance, the corresponding data feature is determined to be a fixed data feature; When the data correlation between the data feature and the Internet information is lower than the preset correlation and the data feature has a data correlation with other Internet information that is not lower than the preset correlation, the corresponding data feature is determined to be a mobile data feature.

4. A data mining system based on Internet information according to claim 3, characterized in that: Data feature correlation unit, including: The data feature correlation block is used to calibrate the main data features of Internet information, obtain historically stored Internet information, and determine the data correlation between the data features and the Internet information based on the number of occurrences of the data features in the historically stored Internet information, the number of occurrences of the main data features, and the number of simultaneous occurrences of the data features and the main data features.

5. The data mining system based on Internet information according to claim 1, characterized in that: Evaluation display module, including: A data mining evaluation system unit is used to determine data mining evaluation indicators based on the data mining results of historically stored Internet information and to construct a data mining evaluation system, wherein the data mining evaluation indicators include: data mining precision evaluation indicators, data mining accuracy evaluation indicators and data mining efficiency evaluation indicators; A mining evaluation unit, used to perform quantitative evaluation on the data mining results of cluster merging according to the data mining evaluation system to obtain a current quantitative score; A quantitative scoring threshold is determined according to the data mining results of historically stored Internet information, and when the current quantitative scoring is not lower than the quantitative scoring threshold, it is determined that the mining evaluation of the cluster-merged data mining results is qualified.

6. A data mining system based on Internet information according to claim 5, characterized in that: Evaluation display module, including: A mining display unit, used for visually displaying the data mining results of the cluster merging that has passed the mining evaluation and the current quantitative score; The iterative updating unit is used for periodically iteratively updating the data mining results of cluster merging and periodically iteratively updating the data mining evaluation system.

7. A data mining method based on Internet information, using the data mining system according to claim 1, characterized in that: include: Step 1: Obtain and preprocess Internet information, extract data features, classify data features according to the data relevance between the data features and Internet information, and determine fixed data features and mobile data features; Step 2: performing data similarity mining on Internet information according to the fixed data features and performing data transfer rate mining on Internet information according to the mobile data features, and clustering and merging the data similarity mining results and the data transfer rate mining results according to the data correlation between the data features; Step 3: Construct a data mining evaluation system to conduct mining evaluation on the data mining results of cluster merging, and visualize the data mining results of cluster merging when the mining evaluation is qualified.

Images