An information collection and analysis method based on an intelligent manufacturing platform

Abstract

This invention provides a method for information collection and analysis based on an intelligent manufacturing platform. It includes: collecting first business data from the intelligent manufacturing platform using its default search engine; collecting sub-business data corresponding to the business types involved in the intelligent manufacturing platform using a type-specific search engine, and synthesizing this data to obtain second business data; performing a first analysis on the log information of the intelligent manufacturing platform based on the first business data, and a second analysis on the log information based on the second business data; and obtaining common optimization data and special optimization data based on the first and second analysis results, and then summarizing and storing these data. By using both the default search engine and the type-specific search engine to collect information from the intelligent manufacturing platform, the accuracy of information collection can be maximized, resulting in more detailed data analysis.

Description

Technical Field

[0001] This invention relates to the field of information collection and analysis, and in particular to an information collection and analysis method based on an intelligent manufacturing platform. Background Technology

[0002] Currently, with the rapid development of internet and streaming media technologies, users have higher requirements for precise services such as web pages, downloads, and streaming video.

[0003] However, existing technologies have relatively limited data collection methods and cannot accurately collect and analyze information.

[0004] Therefore, this invention provides an information collection and analysis method based on an intelligent manufacturing platform. Summary of the Invention

[0005] This invention provides an information collection and analysis method based on an intelligent manufacturing platform. It collects information from the intelligent manufacturing platform by using both a default search engine and a type search engine, which can maximize the accuracy of information collection and make data analysis more detailed.

[0006] This invention provides an information collection and analysis method based on an intelligent manufacturing platform, including:

[0007] Step 1: Collect the first business data of the intelligent manufacturing platform based on the default search engine of the intelligent manufacturing platform;

[0008] Step 2: Collect sub-business data corresponding to the business types involved in the intelligent manufacturing platform using the corresponding search engine, and synthesize them to obtain the second business data;

[0009] Step 3: Perform a first analysis on the log information recorded by the intelligent manufacturing platform based on the first business data, and perform a second analysis on the log information recorded by the intelligent manufacturing platform based on the second business data;

[0010] Step 4: Based on the results of the first and second analyses, obtain common optimization data and special optimization data, and summarize and store them.

[0011] In one possible implementation, the first business data of the intelligent manufacturing platform is collected based on the platform's default search engine, including:

[0012] Step 11: Capture the current business set of the intelligent manufacturing platform and match it with the default search engine from the engine database;

[0013] Step 12: Based on the default search engine, collect information from the intelligent manufacturing platform to obtain the first business data.

[0014] In one possible implementation, a type search engine matching the business type involved in the intelligent manufacturing platform collects sub-business data corresponding to the business type, and synthesizes this data to obtain second business data, including:

[0015] Step 21: Obtain the type of business information required for each current business search in the current business set;

[0016] Step 22: Construct a comprehensive type model based on the business information type, and simultaneously use the type search engine of the intelligent manufacturing platform to classify and search for available information based on the comprehensive type model;

[0017] Step 23: Based on the category search results, determine several sub-business information items that match the business information type from all available information on the intelligent manufacturing platform;

[0018] Step 24: Sort the sub-business information according to the degree of type matching between the information type and the business information type in the type integration model, and obtain the second business data.

[0019] In one possible implementation, a first analysis is performed on the log information recorded by the intelligent manufacturing platform based on the first business data, including:

[0020] Step 31: Perform data preprocessing on the acquired first business data to obtain the first standard business data that matches the intelligent manufacturing platform, and at the same time, acquire the corresponding first historical standard data;

[0021] Step 32: Obtain the first log information related to the first business data on the intelligent manufacturing platform;

[0022] Step 33: Perform a first optimization on the first standard business data based on the first log information;

[0023] Step 34: Construct a data analysis model based on the first historical standard data, and transfer the first optimized data to the data analysis model for a second optimization;

[0024] Step 35: Compare the second optimized data with the preset data analysis table to obtain the first analysis result.

[0025] In one possible implementation, a second analysis is performed on the log information recorded by the intelligent manufacturing platform based on the second business data, including:

[0026] Step 01: Based on the acquired second business data, perform data preprocessing to obtain second standard business data that matches the intelligent manufacturing platform;

[0027] Step 02: Obtain the second log information related to the second business data on the intelligent manufacturing platform;

[0028] Step 03: Optimize the second standard business data based on the second log information;

[0029] Step 04: Perform cluster analysis on the optimized second standard business data;

[0030] Step 05: Compare the cluster data after cluster analysis with the preset analysis table to obtain the corresponding second analysis results.

[0031] In one possible implementation, the clustered data is compared with a pre-defined analysis table to obtain the corresponding second analysis results, including:

[0032] Step 051: Obtain the cluster data of the second standard business data after cluster analysis and the category number corresponding to each cluster data;

[0033] Step 052: Based on the category number, filter the category standard data and corresponding data analysis results in the first database to form a preset analysis table;

[0034] The analysis table includes category number, category standard data, and analysis of the differences between the standard data of each category and different data, as well as the possible reasons for the differences;

[0035] Step 053: Based on the same category number, compare the difference between the second standard business data and the category standard data corresponding to the same category number, and construct the corresponding data difference table;

[0036] Step 054: Based on the difference in the data difference table, filter the difference analysis and possible causes of the difference for the same category number in the preset analysis table;

[0037] Step 055: Based on the possible causes of the difference, obtain the impact of other data corresponding to each possible cause of the difference, collect the basic data information of other data in the class data for comparison, and determine the degree of possibility corresponding to each possible cause of the difference based on the comparison results;

[0038] Step 056: Compare the probability of all possible causes with the probability of the preset standard;

[0039] If the probability of a possible cause is higher than the preset standard probability, then the possible cause is retained.

[0040] If the probability of a possible cause is not higher than the preset standard probability, then the possible cause is eliminated.

[0041] Based on the remaining possible causes, construct a sequence of probabilities according to the probability of each possible cause.

[0042] Based on the comparison of the remaining possible causes corresponding to the possible degree sequence, duplicate causes are eliminated to obtain the first comprehensive cause group;

[0043] Based on the first comprehensive cause group, extract the primary cause keywords for each group of causes;

[0044] Based on the comparison of the first reason keywords, duplicate reasons in the first reason keywords are eliminated to obtain the second reason keywords;

[0045] Based on the second reason keyword, match the possible reasons corresponding to the keyword, and perform comprehensive processing based on the possible reasons to construct the first comprehensive difference reason;

[0046] Based on the first comprehensive difference cause, difference analysis, and second standard business data, the corresponding second analysis result is obtained.

[0047] In one possible implementation, based on the first and second analysis results, common optimization data and specific optimization data are obtained, summarized, and stored, including:

[0048] Step 41: Based on the first analysis result, extract the data in the first standard business data that falls within the standard range corresponding to the preset data analysis table as the first common data. At the same time, extract the data in the first standard business data that does not fall within the standard range corresponding to the preset data analysis table as the first special data.

[0049] Among them, the first public data and the first special data constitute the first standard business data;

[0050] Step 42: Obtain the second public data and the second special data based on the second analysis results;

[0051] Step 43: Compare the first public data with the second public data to determine the degree of data overlap between the first public data and the second public data based on the same sub-business;

[0052] Step 44: Obtain the sub-service data with a data overlap greater than a preset overlap as the main common optimization data, and take the remaining data after removing the main common optimization data from the first common data and the second common data as the secondary optimization data;

[0053] At the same time, the first special data and the second special data are used as special optimization data;

[0054] Step 45: Summarize and store the main optimization data, secondary optimization data, and special optimization data.

[0055] In one possible implementation, the first public data is compared with the second public data to determine the degree of data overlap based on the same sub-business in the first public data and the second public data, including:

[0056] Step 431: Extract the first public data keywords and second public data keywords corresponding to the same sub-business from the first public data and the second public data;

[0057] Step 432: Compare all first public data keywords with all second public data keywords under the same sub-business;

[0058] Step 433: Based on the comparison results, determine the keyword overlap for sub-businesses;

[0059] Step 434: Based on the keyword overlap, determine the degree of data overlap between the first public data and the second public data under the same sub-business;

[0060] Step 435: Input the obtained data overlap under the same sub-business into the data filling table to obtain the data overlap table.

[0061] In one possible implementation, determining the data overlap between the first public data and the second public data based on the keyword overlap includes:

[0062] Based on the first and second public data keywords under the same sub-business, filter overlapping keywords as well as the first and second independent keywords;

[0063] Based on the first occurrence position of the first public data keyword, an initial weight is assigned to each overlapping keyword;

[0064] Based on the second occurrence position of the overlapping keywords according to the second public data keywords, a second weight is assigned to each overlapping keyword;

[0065] The average weight of the first and second weights of the same overlapping keywords is used as the third weight;

[0066] Obtain the third occurrence position of each first independent keyword based on the first public data keyword, and assign a fourth weight to each first independent keyword;

[0067] Obtain the fourth occurrence position of each second independent keyword based on the second public data keyword, and assign a fifth weight to each second independent keyword;

[0068] Based on the first difference between the cumulative sum of the first weight and the cumulative sum of the third weight, the fourth weight is adjusted to obtain the sixth weight.

[0069] Based on the second difference between the cumulative sum of the second weight and the cumulative sum of the third weight, the fifth weight is adjusted a second time to obtain the seventh weight;

[0070] Based on the final weight of each keyword and the allowed overlap value of the keyword itself, the data overlap degree under the corresponding sub-business is obtained.

[0071] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0072] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0073] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0074] Figure 1 This is a flowchart of an information collection and analysis method based on an intelligent manufacturing platform according to an embodiment of the present invention;

[0075] Figure 2 This is another flowchart of an information collection and analysis method based on an intelligent manufacturing platform according to an embodiment of the present invention;

[0076] Figure 3 This is a flowchart illustrating the determination of data overlap in an information collection and analysis method based on an intelligent manufacturing platform, as described in an embodiment of the present invention. Detailed Implementation

[0077] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0078] Example 1:

[0079] This invention provides an information collection and analysis method based on an intelligent manufacturing platform, such as... Figure 1 As shown, it includes:

[0080] Step 1: Collect the first business data of the intelligent manufacturing platform based on the default search engine of the intelligent manufacturing platform;

[0081] Step 2: Collect sub-business data corresponding to the business types involved in the intelligent manufacturing platform using the corresponding search engine, and synthesize them to obtain the second business data;

[0082] Step 3: Perform a first analysis on the log information recorded by the intelligent manufacturing platform based on the first business data, and perform a second analysis on the log information recorded by the intelligent manufacturing platform based on the second business data;

[0083] Step 4: Based on the results of the first and second analyses, obtain common optimization data and special optimization data, and summarize and store them.

[0084] In this embodiment, the default search engine refers to the search engine corresponding to the business information required by the current intelligent manufacturing platform. Generally, the default search engine is used to search on the platform, and the search includes searching for different types of information.

[0085] In this embodiment, the first business data refers to the business data searched in the available information corresponding to the intelligent manufacturing platform based on the search method of the default search engine.

[0086] In this embodiment, the business type refers to the type of business information, such as the corresponding format type, data type, task type, etc.

[0087] In this embodiment, the type search engine refers to a search engine that searches for information based on the type of business information.

[0088] In this embodiment, the second business data refers to the business data searched in the available information corresponding to the intelligent manufacturing platform using a type-based search engine.

[0089] The difference between the first and second business data is due to the different engines used. The default search engine directly collects information of multiple types, while the type search engine directly collects information of matching types. During the collection process, the different functions of the engines may result in the same or different information being collected.

[0090] In this embodiment, the first analysis and the second analysis refer to performing data analysis on the first business data and the second business data in different ways based on the first log information and the second log information. For example, the first business data is analyzed by building a model using historical business data, and the second business data is analyzed by clustering analysis.

[0091] In this embodiment, the common optimized data refers to the data in the first business data and the second business data where the data overlap is higher than the preset overlap.

[0092] In this embodiment, special optimization data refers to the data in the first business data and the second business data excluding the common optimization data, wherein the special optimization data consists of the first special data and the second special data.

[0093] In this embodiment, common optimization data and special optimization data are obtained by judging the data overlap between the first business data and the second business data, thereby achieving accurate data classification and accurate collection of the required business data.

[0094] The beneficial effects of the above technical solution are: by using both the default search engine and the type search engine to collect information from the intelligent manufacturing platform, the accuracy of information collection can be maximized, thereby making the data analysis more detailed.

[0095] Example 2:

[0096] Based on Example 1, and using the default search engine of the intelligent manufacturing platform, the first business data of the intelligent manufacturing platform is collected, including:

[0097] Step 11: Capture the current business set of the intelligent manufacturing platform and match it with the default search engine from the engine database;

[0098] Step 12: Based on the default search engine, collect information from the intelligent manufacturing platform to obtain the first business data.

[0099] In this embodiment, the engine database refers to a database that stores all search engines, including direct search engines and type search engines. The direct search engine is the default search engine corresponding to the intelligent manufacturing platform.

[0100] In this embodiment, the default search engine refers to the direct search engine corresponding to the business information required by the current intelligent manufacturing platform.

[0101] In this embodiment, the first business data refers to the business data searched in the available information corresponding to the intelligent manufacturing platform based on the search method of the default search engine.

[0102] The beneficial effects of the above technical solution are: by using the default search engine of the intelligent manufacturing platform, the first business data is collected from the intelligent manufacturing platform and then comprehensively analyzed with the second business data, which can maximize the accuracy of the collected data.

[0103] Example 3:

[0104] Based on Example 2, according to the type search engine matching the business types involved in the intelligent manufacturing platform, sub-business data of the corresponding business types are collected, and the second business data is obtained by combining them, such as... Figure 2 As shown, it includes:

[0105] Step 21: Obtain the type of business information required for each current business search in the current business set;

[0106] Step 22: Construct a comprehensive type model based on the business information type, and simultaneously use the type search engine of the intelligent manufacturing platform to classify and search for available information based on the comprehensive type model;

[0107] Step 23: Based on the category search results, determine several sub-business information items that match the business information type from all available information on the intelligent manufacturing platform;

[0108] Step 24: Sort the sub-business information according to the degree of type matching between the information type and the business information type in the type integration model, and obtain the second business data.

[0109] In this embodiment, the business information type is determined based on multiple corresponding types. For example, according to the application department, the information can be divided into industrial information, agricultural information, military information, political information, scientific and technological information, cultural information, economic information, market information and management information, etc.; according to the status, the information can be divided into objective information and subjective information.

[0110] In this embodiment, the type integration model refers to the model constructed based on all information types of business information.

[0111] In this embodiment, the type search engine refers to a search engine that searches for information based on the type of business information.

[0112] In this embodiment, the category search is based on the type of business information search engine.

[0113] In this embodiment, the second business data refers to the business data searched in the available information corresponding to the intelligent manufacturing platform using a type-based search engine.

[0114] The beneficial effects of the above technical solution are: by collecting data through a type search engine obtained by matching the business types involved in the intelligent manufacturing platform, second business data is obtained, and then combined with the first business data for comprehensive analysis, which can maximize the accuracy of the collected data.

[0115] Example 4:

[0116] Based on Embodiment 3, a first analysis is performed on the log information recorded by the intelligent manufacturing platform based on the first business data, including:

[0117] Step 31: Perform data preprocessing on the acquired first business data to obtain the first standard business data that matches the intelligent manufacturing platform, and at the same time, acquire the corresponding first historical standard data;

[0118] Step 32: Obtain the first log information related to the first business data on the intelligent manufacturing platform;

[0119] Step 33: Perform a first optimization on the first standard business data based on the first log information;

[0120] Step 34: Construct a data analysis model based on the first historical standard data, and transfer the first optimized data to the data analysis model for a second optimization;

[0121] Step 35: Compare the second optimized data with the preset data analysis table to obtain the first analysis result.

[0122] In this embodiment, data preprocessing is performed on the first business data to standardize all data information.

[0123] In this embodiment, the first standard business data refers to the first business data after standardization processing.

[0124] In this embodiment, the first historical standard business data refers to the historical standard business data that is consistent with the data form of the first standard data among the historical business data filtered in the intelligent manufacturing platform based on the data form of the first standard data.

[0125] In this embodiment, the first log information refers to the corresponding situation of the data in the intelligent manufacturing platform during the actual operation of the data based on the first standard business data.

[0126] In this embodiment, the first optimization refers to performing data optimization processing on the first standard business data based on the first log information. For example, judging whether the first standard business data information is accurate based on the content of the first log information. If there is an information error, the information is adjusted based on the log information to complete the data optimization.

[0127] In this embodiment, the second optimization refers to the data optimization processing of the first standard business data by the data analysis model built based on the first historical standard business data. For example, based on the data information optimized in the first optimization, the data is substituted into the data analysis model built based on the first historical standard data to make a judgment, check whether there is a discrete state of data information, remove the discrete data, and supplement it with the corresponding average data to achieve the second optimization of the data information.

[0128] In this embodiment, the preset data analysis table is selected from the large database based on the data after two optimizations. The data analysis table includes the corresponding data of the intelligent manufacturing platform, the standard data under the standard state, and the different analysis results corresponding to the different data differences between the corresponding data and the standard data.

[0129] In this embodiment, the first analysis result refers to the data analysis result obtained by comparing the data after two data optimizations with the preset analysis table.

[0130] The beneficial effects of the above technical solution are: by optimizing the first business information through the first log information, the obtained data information can be more accurate, thereby achieving more accurate analysis and optimization with the second business data, and obtaining more detailed data analysis results.

[0131] Example 5:

[0132] Based on Example 3, a second analysis is performed on the log information of the intelligent manufacturing platform based on the second business data, including:

[0133] Step 01: Based on the acquired second business data, perform data preprocessing to obtain second standard business data that matches the intelligent manufacturing platform;

[0134] Step 02: Obtain the second log information related to the second business data on the intelligent manufacturing platform;

[0135] Step 03: Optimize the second standard business data based on the second log information;

[0136] Step 04: Perform cluster analysis on the optimized second standard business data;

[0137] Step 05: Compare the cluster data after cluster analysis with the preset analysis table to obtain the corresponding second analysis results.

[0138] In this embodiment, data preprocessing is performed on the second business data to standardize all data information.

[0139] In this embodiment, the second standard business data refers to the second business data after standardization processing.

[0140] In this embodiment, the second log information refers to the corresponding situation of the data in the intelligent manufacturing platform during the actual operation of the data based on the second standard business data.

[0141] In this embodiment, data optimization refers to performing data optimization processing on the second standard business data based on the second log information. For example, the accuracy of the second standard business data information is determined based on the content of the second log information. If there is an information error, the information is adjusted based on the log information to complete the data optimization.

[0142] In this embodiment, cluster analysis needs to ensure that the intra-class gap is minimized and the inter-class gap is maximized among the different types of sub-business information contained in the second standard business data. The values ​​of minimizing the intra-class gap and maximizing the inter-class gap should also meet the preset gap threshold.

[0143] In this embodiment, the preset analysis table refers to the data analysis table that is selected from the large database after the clustering analysis of the class data.

[0144] In this embodiment, the second analysis result refers to the data analysis result obtained by comparing the cluster data after cluster analysis with the preset analysis table. For example, the cluster data obtained after cluster analysis is compared with the preset standard cluster data in the preset analysis table, and the difference in the obtained data is analyzed. The reasons for the difference between the cluster data and the standard cluster data under different difference conditions, as well as the difference value, are analyzed.

[0145] The beneficial effects of the above technical solution are: by optimizing the second business information through the second log information, the obtained data information can be more accurate, and by using the cluster analysis method, more accurate analysis and optimization can be achieved with the first business data, resulting in more detailed data analysis results.

[0146] Example 6:

[0147] Based on Example 5, the clustered data is compared with a preset analysis table to obtain the corresponding second analysis results, including:

[0148] Step 051: Obtain the cluster data of the second standard business data after cluster analysis and the category number corresponding to each cluster data;

[0149] Step 052: Based on the category number, filter the category standard data and corresponding data analysis results in the first database to form a preset analysis table;

[0150] The analysis table includes category number, category standard data, and analysis of the differences between the standard data of each category and different data, as well as the possible reasons for the differences;

[0151] Step 053: Based on the same category number, compare the difference between the second standard business data and the category standard data corresponding to the same category number, and construct the corresponding data difference table;

[0152] Step 054: Based on the difference in the data difference table, filter the difference analysis and possible causes of the difference for the same category number in the preset analysis table;

[0153] Step 055: Based on the possible causes of the difference, obtain the impact of other data corresponding to each possible cause of the difference, collect the basic data information of other data in the class data for comparison, and determine the degree of possibility corresponding to each possible cause of the difference based on the comparison results;

[0154] Step 056: Compare the probability of all possible causes with the probability of the preset standard;

[0155] If the probability of a possible cause is higher than the preset standard probability, then the possible cause is retained.

[0156] If the probability of a possible cause is not higher than the preset standard probability, then the possible cause is eliminated.

[0157] Based on the remaining possible causes, construct a sequence of probabilities according to the probability of each possible cause.

[0158] Based on the comparison of the remaining possible causes corresponding to the possible degree sequence, duplicate causes are eliminated to obtain the first comprehensive cause group;

[0159] Based on the first comprehensive cause group, extract the primary cause keywords for each group of causes;

[0160] Based on the comparison of the first reason keywords, duplicate reasons in the first reason keywords are eliminated to obtain the second reason keywords;

[0161] Based on the second reason keyword, match the possible reasons corresponding to the keyword, and perform comprehensive processing based on the possible reasons to construct the first comprehensive difference reason;

[0162] Based on the first comprehensive difference cause, difference analysis, and second standard business data, the corresponding second analysis result is obtained.

[0163] In this embodiment, the second standard business data refers to the second business data after standardization processing.

[0164] In this embodiment, "class data" refers to the data obtained by classifying the second standard business data using a clustering analysis method.

[0165] In this embodiment, the category number refers to the number corresponding to each group of category data in the second standard business data.

[0166] In this embodiment, the first database contains category standard data corresponding to all business data of the current intelligent manufacturing platform, as well as data difference analysis between each category standard data and different data.

[0167] In this embodiment, the preset analysis table includes category number, category standard data, and analysis of the differences between the standard data of each category and different data, as well as the possible reasons for the differences.

[0168] In this embodiment, the data difference table is constructed based on the difference between the class data corresponding to the same category number and the category standard data. For example, in the current intelligent manufacturing platform, a certain category number is 011, and the corresponding class data is the order status in the order data. The order status includes orders that are pending shipment, pending payment, shipped, and refunded / after-sales orders. The category standard data is pending shipment, so the difference is 0 when the class data is pending shipment, 1 when the class data is pending payment, 2 when the class data is shipped, and 3 when the class data is refunded / after-sales orders.

[0169] In this embodiment, the difference analysis refers to the judgment based on the difference in the data difference table. For example, if a certain category number is 011 and the difference in the difference table is 1, the possible difference situations may include: the user forgot to pay, the user failed to pay, etc.

[0170] In this embodiment, the possible reasons for the difference are based on all possible reasons corresponding to the current difference result. For example, if a certain category number is 011 and the difference in the difference table is 1, then the possible reasons for the payment failure are insufficient balance of the current payment method or network lag during payment.

[0171] In this embodiment, the probability of the possible causes of the difference will vary depending on the user's actual situation. For example, if a certain category number is 011 and the difference in the difference table is 1, it is determined that the user's payment failed based on the difference analysis. If the network at the user's location is good, the probability of network lag is 0.1. If the user's current payment method has a low transaction volume, the probability of insufficient balance is 0.8.

[0172] In this embodiment, the degree of probability of the preset standard refers to the degree of probability of the preset standard obtained by analyzing the business data of the current intelligent manufacturing platform.

[0173] In this embodiment, the first comprehensive cause group refers to the cause group consisting of causes whose probability is higher than the preset standard probability included in the possible causes of the difference.

[0174] In this embodiment, the first reason keyword refers to the reason keyword included in each remaining possible reason. For example, the first reason keyword for insufficient balance in the current payment method is balance.

[0175] In this embodiment, the second reason keyword refers to the reason keyword obtained after removing duplicate reasons from the first reason keyword.

[0176] In this embodiment, the first comprehensive difference reason refers to the comprehensive reason obtained by combining and modifying all the second reason keywords.

[0177] In this embodiment, the second analysis result is obtained based on the first comprehensive reasons for the difference, the difference analysis, and the second standard business data.

[0178] The beneficial effects of the above technical solution are: by performing multiple analyses on the data after cluster analysis, deleting the corresponding duplicate and invalid data reasons, and comprehensively analyzing the remaining reasons to obtain the second analysis result, the obtained data information can be more accurate, thereby achieving more accurate analysis and optimization with the first business data, and obtaining more detailed data analysis results.

[0179] Example 7:

[0180] Based on Example 5, common optimization data and specific optimization data are obtained based on the first analysis results and the second analysis results, and then summarized and stored, including:

[0181] Step 41: Based on the first analysis result, extract the data in the first standard business data that falls within the standard range corresponding to the preset data analysis table as the first common data. At the same time, extract the data in the first standard business data that does not fall within the standard range corresponding to the preset data analysis table as the first special data.

[0182] Among them, the first public data and the first special data constitute the first standard business data;

[0183] Step 42: Obtain the second public data and the second special data based on the second analysis results;

[0184] Step 43: Compare the first public data with the second public data to determine the degree of data overlap between the first public data and the second public data based on the same sub-business;

[0185] Step 44: Obtain the sub-service data with a data overlap greater than a preset overlap as the main common optimization data, and take the remaining data after removing the main common optimization data from the first common data and the second common data as the secondary optimization data;

[0186] At the same time, the first special data and the second special data are used as special optimization data;

[0187] Step 45: Summarize and store the main optimization data, secondary optimization data, and special optimization data.

[0188] In this embodiment, the first public data and the second public data refer to the data in the first standard business data that falls within the standard range corresponding to the preset data analysis table, extracted based on the first analysis result, and the data in the second standard business data that falls within the standard range corresponding to the preset data analysis table, extracted based on the second analysis result.

[0189] In this embodiment, the first special data and the second special data refer to the data in the first standard business data extracted based on the first analysis result that is not within the standard range corresponding to the preset data analysis table, and the data in the second standard business data extracted based on the second analysis result that is not within the standard range corresponding to the preset data analysis table.

[0190] In this embodiment, the first public data and the first special data constitute the first standard business data, and the second public data and the second special data constitute the second standard business data.

[0191] In this embodiment, data overlap refers to the degree of overlap between the corresponding data of the first public data and the second public data.

[0192] In this embodiment, the preset overlap degree is the information overlap degree preset based on the platform characteristics and information features of the current intelligent manufacturing platform.

[0193] In this embodiment, the main common optimized data refers to the data that exists in both the first common data and the second common data, where the overlap between the data in the first common data and the second common data is higher than the preset overlap.

[0194] In this embodiment, secondary common optimization data refers to the remaining data after removing primary common optimization data from the first common data and the second common data.

[0195] In this embodiment, the first special data and the second special data are used as special optimization data.

[0196] In this embodiment, data aggregation refers to classifying and summarizing data information according to primary optimization data, secondary optimization data, and special optimization data.

[0197] In this embodiment, data storage refers to storing the summarized data based on the data aggregation results.

[0198] The beneficial effects of the above technical solution are: by obtaining public optimization data and special optimization data through the first analysis results and the second analysis results, more accurate summarization and storage can be carried out, and the accurate collection of information can be maximized.

[0199] Example 8:

[0200] Based on Example 7, the first public data and the second public data are compared to determine the degree of data overlap between the first public data and the second public data based on the same sub-service, such as... Figure 3 As shown, it includes:

[0201] Step 431: Extract the first public data keywords and second public data keywords corresponding to the same sub-business from the first public data and the second public data;

[0202] Step 432: Compare all first public data keywords with all second public data keywords under the same sub-business;

[0203] Step 433: Based on the comparison results, determine the keyword overlap for sub-businesses;

[0204] Step 434: Based on the keyword overlap, determine the degree of data overlap between the first public data and the second public data under the same sub-business;

[0205] Step 435: Input the obtained data overlap under the same sub-business into the data filling table to obtain the data overlap table.

[0206] In this embodiment, the first public data keyword and the second public data keyword are information data keywords based on the same sub-business information in the first public data and the second public data.

[0207] In this embodiment, keyword overlap refers to the overlap between the first public data keyword and the second public data keyword corresponding to the same sub-business information.

[0208] In this embodiment, data overlap refers to the degree of overlap corresponding to keyword overlap.

[0209] The beneficial effects of the above technical solution are: by obtaining the overlap between the first and second public data through the first and second analysis results, more accurate summarization and storage can be carried out, and the accurate collection of information can be achieved to a greater extent.

[0210] Example 9:

[0211] Based on Example 8, and based on the keyword overlap, the degree of data overlap between the first public data and the second public data under the same sub-business is determined, including:

[0212] Based on the first and second public data keywords under the same sub-business, filter overlapping keywords as well as the first and second independent keywords;

[0213] Based on the first occurrence position of the first public data keyword, an initial weight is assigned to each overlapping keyword;

[0214] Based on the second occurrence position of the overlapping keywords according to the second public data keywords, a second weight is assigned to each overlapping keyword;

[0215] The average weight of the first and second weights of the same overlapping keywords is used as the third weight;

[0216] Obtain the third occurrence position of each first independent keyword based on the first public data keyword, and assign a fourth weight to each first independent keyword;

[0217] Obtain the fourth occurrence position of each second independent keyword based on the second public data keyword, and assign a fifth weight to each second independent keyword;

[0218] Based on the first difference between the cumulative sum of the first weight and the cumulative sum of the third weight, the fourth weight is adjusted to obtain the sixth weight.

[0219] Based on the second difference between the cumulative sum of the second weight and the cumulative sum of the third weight, the fifth weight is adjusted a second time to obtain the seventh weight;

[0220] Based on the final weight of each keyword and the allowed overlap value of the keyword itself, the data overlap degree under the corresponding sub-business is obtained.

[0221] In this embodiment, the first public data keywords are: words 01, 02, 03, 04, 05, and 06; the second public data keywords are: words 01, 03, 04, 07, 08, and 02; the overlapping keywords are: 01, 02, 03, and 04; the first independent keywords are: 05 and 06; and the second independent keywords are: 07 and 08.

[0222] In this embodiment, the appearance position refers to the appearance order, and different appearance orders correspond to different weights. The weight is obtained based on the position-weight mapping table, which contains different combinations of appearance positions and the weights matched with the appearance positions. Therefore, the corresponding first weight, second weight, fourth weight and fifth weight can be obtained, and the sum of all weights is 1.

[0223] In this embodiment, if the first difference is greater than 0, the fourth weight is adjusted to be larger; if the first difference is less than 0, the fourth weight is adjusted to be smaller. The adjustment principle of the second difference is similar to that of the first difference.

[0224] In this embodiment, when the first difference is greater than 0:

[0225] Where represents the cumulative sum of the first weight; sum3 represents the cumulative sum of the third weight; and represents the number of overlapping keywords.

[0226] When the first difference is less than or equal to 0:

[0227] Where represents the cumulative sum of the first weight; sum3 represents the cumulative sum of the third weight; and represents the number of overlapping keywords.

[0228] In this embodiment, the data overlap is the sum of all the products obtained by multiplying the final weight of each keyword by the allowed overlap value.

[0229] The beneficial effects of the above technical solution are: by determining the degree of data overlap between the first public data and the second public data based on the same sub-business through keyword overlap, the analysis of data information can be more detailed and accurate.

[0230] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An information collection and analysis method based on an intelligent manufacturing platform, characterized in that, include: Step 1: Collect the first business data of the intelligent manufacturing platform based on the default search engine of the intelligent manufacturing platform; Step 2: Collect sub-business data corresponding to the business types involved in the intelligent manufacturing platform using the corresponding search engine, and synthesize them to obtain the second business data; Step 3: Perform a first analysis on the log information recorded by the intelligent manufacturing platform based on the first business data, and perform a second analysis on the log information recorded by the intelligent manufacturing platform based on the second business data; Step 4: Based on the results of the first and second analyses, obtain common optimization data and special optimization data, and summarize and store them; A first analysis is performed on the log information recorded by the intelligent manufacturing platform based on the first business data, including: Step 31: Perform data preprocessing on the acquired first business data to obtain the first standard business data that matches the intelligent manufacturing platform, and at the same time, acquire the corresponding first historical standard data; Step 32: Obtain the first log information related to the first business data on the intelligent manufacturing platform; Step 33: Perform a first optimization on the first standard business data based on the first log information; Step 34: Construct a data analysis model based on the first historical standard data, and transfer the first optimized data to the data analysis model for a second optimization; Step 35: Compare the second optimized data with the preset data analysis table to obtain the first analysis result; A second analysis is performed on the log information of the intelligent manufacturing platform based on the second business data, including: Step 01: Based on the acquired second business data, perform data preprocessing to obtain second standard business data that matches the intelligent manufacturing platform; Step 02: Obtain the second log information related to the second business data on the intelligent manufacturing platform; Step 03: Optimize the second standard business data based on the second log information; Step 04: Perform cluster analysis on the optimized second standard business data; Step 05: Compare the cluster data after cluster analysis with the preset analysis table to obtain the corresponding second analysis results; Based on the results of the first and second analyses, common optimization data and specific optimization data are obtained, summarized, and stored, including: Step 41: Based on the first analysis result, extract the data in the first standard business data that falls within the standard range corresponding to the preset data analysis table as the first common data. At the same time, extract the data in the first standard business data that does not fall within the standard range corresponding to the preset data analysis table as the first special data. Among them, the first public data and the first special data constitute the first standard business data; Step 42: Obtain the second public data and the second special data based on the second analysis results; Step 43: Compare the first public data with the second public data to determine the degree of data overlap between the first public data and the second public data based on the same sub-business; Step 44: Obtain the sub-service data with a data overlap greater than a preset overlap as the main common optimization data, and take the remaining data after removing the main common optimization data from the first common data and the second common data as the secondary optimization data; At the same time, the first special data and the second special data are used as special optimization data; Step 45: Summarize and store the main optimization data, secondary optimization data, and special optimization data.

2. The information collection and analysis method based on an intelligent manufacturing platform as described in claim 1, characterized in that, Based on the default search engine of the intelligent manufacturing platform, the first business data of the intelligent manufacturing platform is collected, including: Step 11: Capture the current business set of the intelligent manufacturing platform and match it with the default search engine from the engine database; Step 12: Based on the default search engine, collect information from the intelligent manufacturing platform to obtain the first business data.

3. The information collection and analysis method based on an intelligent manufacturing platform as described in claim 2, characterized in that, According to the type search engine matching the business types involved in the intelligent manufacturing platform, sub-business data of the corresponding business types are collected, and the second business data is obtained by combining them, including: Step 21: Obtain the type of business information required for each current business search in the current business set; Step 22: Construct a comprehensive type model based on the business information type, and simultaneously use the type search engine of the intelligent manufacturing platform to classify and search for available information based on the comprehensive type model; Step 23: Based on the category search results, determine several sub-business information items that match the business information type from all available information on the intelligent manufacturing platform; Step 24: Sort the sub-business information according to the degree of type matching between the information type and the business information type in the type integration model, and obtain the second business data.

4. The information collection and analysis method based on an intelligent manufacturing platform as described in claim 1, characterized in that, The cluster data obtained from the clustering analysis are compared with the preset analysis table to obtain the corresponding second analysis results, including: Step 051: Obtain the cluster data of the second standard business data after cluster analysis and the category number corresponding to each cluster data; Step 052: Based on the category number, filter the category standard data and corresponding data analysis results in the first database to form a preset analysis table; The analysis table includes category number, category standard data, and analysis of the differences between the standard data of each category and different data, as well as the possible reasons for the differences; Step 053: Based on the same category number, compare the difference between the second standard business data and the category standard data corresponding to the same category number, and construct the corresponding data difference table; Step 054: Based on the difference in the data difference table, filter the difference analysis and possible causes of the difference for the same category number in the preset analysis table; Step 055: Based on the possible causes of the difference, obtain the impact of other data corresponding to each possible cause of the difference, collect the basic data information of other data in the class data for comparison, and determine the degree of possibility corresponding to each possible cause of the difference based on the comparison results; Step 056: Compare the probability of all possible causes with the probability of the preset standard; If the probability of a possible cause is higher than the preset standard probability, then the possible cause is retained. If the probability of a possible cause is not higher than the preset standard probability, then the possible cause is eliminated. Based on the remaining possible causes, construct a sequence of probabilities according to the probability of each possible cause. Based on the comparison of the remaining possible causes corresponding to the possible degree sequence, duplicate causes are eliminated to obtain the first comprehensive cause group; Based on the first comprehensive cause group, extract the primary cause keywords for each group of causes; Based on the comparison of the first reason keywords, duplicate reasons in the first reason keywords are eliminated to obtain the second reason keywords; Based on the second reason keyword, match the possible reasons corresponding to the keyword, and perform comprehensive processing based on the possible reasons to construct the first comprehensive difference reason; Based on the first comprehensive difference cause, difference analysis, and second standard business data, the corresponding second analysis result is obtained.

5. The information collection and analysis method based on an intelligent manufacturing platform as described in claim 1, characterized in that, The first public data is compared with the second public data to determine the degree of data overlap between the first public data and the second public data based on the same sub-business, including: Step 431: Extract the first public data keywords and second public data keywords corresponding to the same sub-business from the first public data and the second public data; Step 432: Compare all first public data keywords with all second public data keywords under the same sub-business; Step 433: Based on the comparison results, determine the keyword overlap for sub-businesses; Step 434: Based on the keyword overlap, determine the degree of data overlap between the first public data and the second public data under the same sub-business; Step 435: Input the obtained data overlap under the same sub-business into the data filling table to obtain the data overlap table.

6. The information collection and analysis method based on an intelligent manufacturing platform as described in claim 5, characterized in that, Based on the keyword overlap, the degree of data overlap between the first public data and the second public data under the same sub-business is determined, including: Based on the first and second public data keywords under the same sub-business, filter overlapping keywords as well as the first and second independent keywords; Based on the first occurrence position of the first public data keyword, an initial weight is assigned to each overlapping keyword; Based on the second occurrence position of the overlapping keywords according to the second public data keywords, a second weight is assigned to each overlapping keyword; The average weight of the first and second weights of the same overlapping keywords is used as the third weight; Obtain the third occurrence position of each first independent keyword based on the first public data keyword, and assign a fourth weight to each first independent keyword; Obtain the fourth occurrence position of each second independent keyword based on the second public data keyword, and assign a fifth weight to each second independent keyword; Based on the first difference between the cumulative sum of the first weight and the cumulative sum of the third weight, the fourth weight is adjusted to obtain the sixth weight. Based on the second difference between the cumulative sum of the second weight and the cumulative sum of the third weight, the fifth weight is adjusted a second time to obtain the seventh weight; Based on the final weight of each keyword and the allowed overlap value of the keyword itself, the data overlap degree under the corresponding sub-business is obtained.

Images