A BI business opportunity mining management system and method based on big data

Abstract

The present invention relates to the technical field of BI business opportunity mining, and in particular to a BI business opportunity mining management system and method based on big data, the BI business opportunity mining management system comprises a data mining module for obtaining massive enterprise information data from an enterprise information database; a data cleaning module connected to the data mining module for cleaning the acquired massive enterprise information data; a data storage module connected to the data cleaning module for storing the massive enterprise information data after data cleaning and storing the massive enterprise information data in different data pools; a data analysis module connected to the data storage module for determining a strategy for constructing a fuzzy target data pool; a data processing module connected to the data analysis module for determining an adjustment method for the fuzzy target data pool; and a data optimization module connected to the data processing module for determining an optimization method for the fuzzy target data pool. The present invention improves the accuracy and efficiency of business opportunity mining.

Description

Technical Field

[0001] The present invention relates to the technical field of BI business opportunity mining, and in particular to a BI business opportunity mining management system and method based on big data. Background Art

[0002] With the rapid development of technologies such as the Internet, mobile Internet, and the Internet of Things, the amount of global data is growing explosively. The emergence of big data technology has made it possible for enterprises to process and analyze massive amounts of data. As a management and decision support tool, BI systems help enterprises gain valuable insights by collecting, integrating, and analyzing internal enterprise data. However, with the surge in data volume, traditional BI systems have gradually shown their limitations in processing large-scale and complex data.

[0003] Chinese patent application publication number: CN115760302A discloses a business management method and system based on data mining technology, including collecting real-time image data of unmanned supermarkets; parsing real-time image data, obtaining original data of on-site behavior characteristics associated with current user information through action recognition models; obtaining user checkout instructions and identifying current user information; retrieving user demand portraits from consumer big data servers based on current user information; correcting original data of on-site behavior characteristics in combination with user demand portraits to obtain credible behavior characteristics; generating product recommendation and purchase plans in combination with unmanned supermarket product promotion libraries, user demand portraits and credible behavior characteristics; and displaying product recommendation and purchase plans in unmanned supermarket settlement sales terminals. However, the following problems exist in the prior art:

[0004] The system lacks business intelligence technology and has low accuracy in mining business opportunities, which leads to low efficiency in mining business opportunities. Summary of the invention

[0005] To this end, the present invention provides a BI business opportunity mining management system and method based on big data, so as to overcome the problems of low accuracy and low efficiency in BI business opportunity mining in the prior art.

[0006] To achieve the above objectives, the present invention provides a BI business opportunity mining management system and method based on big data, including:

[0007] Data mining module, used to obtain massive enterprise information data from the enterprise information database;

[0008] A data cleaning module, which is connected to the data mining module and is used to determine the eligibility of a single data volume based on the frequency of occurrence of the single data volume in the massive enterprise information data;

[0009] A data storage module connected to the data cleaning module is used to determine that the clustering is unqualified when the characteristic evaluation value of the data volume is greater than the preset characteristic evaluation value under the condition that the single data is qualified, and store the data volume into the fuzzy target data pool;

[0010] A data analysis module, which is connected to the data storage module, is used to determine the eligibility of the data volume of the fuzzy target data pool according to the comparison result of the coincidence evaluation value and the preset coincidence evaluation value under the condition of unqualified clustering, and to determine the strategy of comparing the data volume of the fuzzy target data pool with the data volume of the fuzzy target data pool of the same type of small and micro-sized enterprises or the data volume of the fuzzy target data pool of the same type of large and medium-sized enterprises according to the evaluation value of the uniformity of the distribution of the data volume of the fuzzy target data pool;

[0011] A data processing module, which is connected to the data analysis module, and is used to determine the adjustment of the data volume of the fuzzy target data pool according to the difference between the preset coincidence evaluation value and the coincidence evaluation value under the condition that the data volume of the fuzzy target data pool is unqualified, and to determine the adjustment of the data volume of the fuzzy target database according to the management evaluation value or the comprehensive evaluation value based on the strategy of comparing the data volume of the fuzzy target data pool with the data volume of the fuzzy target data pool of the same type of small and micro-sized enterprises or the data volume of the fuzzy target data pool of the same type of large and medium-sized enterprises;

[0012] The data optimization module is connected to the data processing module and is used to determine the optimization of the data volume of the fuzzy target database according to the comparison object based on the data processing module performing a data volume comparison of its own historical fuzzy target data pool or a data volume comparison of an external fuzzy target data pool.

[0013] Furthermore, under the condition that the data mining module obtains massive enterprise information data, the data analysis module determines that a single data amount is qualified based on the frequency of occurrence of the single data amount being less than or equal to a preset frequency, determines that clustering is unqualified based on the comparison result that the characteristic evaluation value of the data amount is greater than a preset characteristic evaluation value, and determines that the data amount in the fuzzy target data pool is unqualified based on the fact that the overlap evaluation value between the data amount in the fuzzy target data pool and the data amount in its own historical fuzzy target data pool is less than or equal to a preset overlap evaluation value.

[0014] Furthermore, under the condition that the data amount in the fuzzy target data pool is determined to be unqualified, the data processing module determines to update the data amount in the fuzzy target data pool to a corresponding value using a first preset update adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is less than or equal to a first preset ratio.

[0015] Furthermore, under the condition that the data amount in the fuzzy target data pool is determined to be unqualified, the data processing module determines to update the data amount in the fuzzy target data pool to a corresponding value using a second preset update adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is greater than a first preset ratio.

[0016] Furthermore, under the condition that the data amount in the fuzzy target data pool is determined to be unqualified, the data processing module determines that the data amount in the fuzzy target data pool shall be reduced to a corresponding value using a first preset deletion adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is less than or equal to a second preset ratio.

[0017] Furthermore, under the condition that the data amount in the fuzzy target data pool is determined to be unqualified, the data processing module determines that the data amount in the fuzzy target data pool shall be reduced to a corresponding value using a second preset deletion adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is greater than a second preset ratio.

[0018] Furthermore, under the condition that the data volume of the fuzzy target data pool is determined to be unqualified, the data processing module determines a strategy for comparing the data volume of the fuzzy target data pool with the data volume of the same type of small and micro enterprises based on the comparison result that the distribution uniformity evaluation value of the fuzzy target data pool is less than or equal to the preset distribution uniformity evaluation value, and determines to update the data volume of the fuzzy target data pool with the management adjustment coefficient based on the comparison result that the management evaluation value is less than or equal to the preset management evaluation value.

[0019] Furthermore, under the condition that the data volume of the fuzzy target data pool is determined to be unqualified, the data processing module determines a strategy for comparing the data volume of the fuzzy target data pool with that of similar large and medium-sized enterprises based on the comparison result that the distribution uniformity evaluation value of the fuzzy target data pool is greater than a preset distribution uniformity evaluation value, and determines to reduce the data volume of the fuzzy target data pool by a deletion adjustment coefficient based on the comprehensive evaluation value being less than or equal to a preset comprehensive evaluation value.

[0020] Furthermore, under the condition that the data processing module determines the corresponding comparison strategy, if the comparison strategy is to compare the data volume of the fuzzy target data pool with the data volume of its own historical fuzzy target data pool, the data optimization module determines to supplement the data volume from the target data pool to the fuzzy target data pool; if the comparison strategy is to compare the data volume of the fuzzy target data pool with the data volume of an external fuzzy target data pool, then it determines to supplement the data volume from the external target data pool to the fuzzy target data pool.

[0021] Another aspect of the present invention further provides a BI business opportunity mining method based on big data, comprising:

[0022] Step S1, obtaining massive enterprise information data from an external enterprise information database and an internal enterprise information database by data crawling;

[0023] Step S2, determining the eligibility of a single data according to the comparison result of the frequency of occurrence of the single data in the massive enterprise information data with the preset frequency;

[0024] Step S3, under the condition that the single data is determined to be qualified, the single data is stored in the data lake, and a number of data in the data lake are clustered, and the qualified clustering data is stored in the target data pool according to the clustering eligibility, and the unqualified clustering data is stored in the fuzzy target data pool;

[0025] Step S4, determining the eligibility of the data volume of the fuzzy target data pool, the strategy for comparing the data volume of the fuzzy data pool with the data volume of the same type and different scale enterprises, and the adjustment method for updating the data volume according to the comparison result of the coincidence evaluation value of the data volume of the fuzzy target data pool and the preset coincidence value;

[0026] Step S5, determining an optimization method for the data volume of the fuzzy target data pool according to the comparison result, so as to supplement the data volume from the target data pool or the external target data pool to the fuzzy target data pool.

[0027] Compared with the prior art, the beneficial effect of the present invention lies in that the present invention determines the eligibility of a single data volume according to the comparison result of the frequency of occurrence of the single data volume with the preset frequency through the data cleaning module, thereby improving the accuracy and reliability of the overall data set, thereby improving the accuracy of the management system.

[0028] Furthermore, the present invention performs cluster analysis on several individual data volumes through the data lake of the data storage module, and determines the clustering eligibility by comparing the characteristic evaluation value with the preset characteristic evaluation value, thereby reducing the influence of human intervention and subjective judgment, thereby improving the accuracy and efficiency of management system evaluation.

[0029] Furthermore, the present invention classifies information data and stores them into different data pools according to clustering eligibility through the data storage module. After the data storage module stores the data that does not meet the clustering criteria into the fuzzy target data pool, the data analysis module adjusts the data volume of the fuzzy target data pool to make data analysis more accurate, thereby improving the accuracy of the management system.

[0030] Furthermore, the present invention classifies information data and stores them into different data pools according to clustering eligibility through the data storage module. After the data storage module stores the data that does not meet the clustering requirements into the fuzzy target data pool through the data analysis module, the subsequent analysis strategy is determined based on the comparison result between the data volume distribution uniformity evaluation value of the fuzzy target data pool and the preset distribution uniformity evaluation value, so as to make data analysis more efficient, thereby improving the efficiency of the management system.

[0031] Furthermore, under the condition that the data analysis module of the present invention determines the correlation with the data volume comparison of the same type of small and micro fuzzy data pool, the data processing module will perform further adjustment operations, and specifically determine the adjustment mode according to the comparison result between the management evaluation value and the preset management evaluation value, thereby improving the accuracy of the management system.

[0032] Furthermore, under the condition that the data analysis module determines the correlation with the data volume comparison of the large and medium-sized fuzzy target data pool of the same type, the data processing module will further determine the adjustment mode according to the comparison result of the comprehensive evaluation value with the preset comprehensive evaluation value, which helps to reduce data redundancy and outdated information, thereby improving the accuracy and efficiency of the management system.

[0033] Furthermore, after receiving the comparison result from the data processing module, the data optimization module of the present invention determines a corresponding optimization method according to the specific object of comparison, thereby improving the accuracy and efficiency of the management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a schematic diagram of module connections of a BI business opportunity mining management system based on big data according to an embodiment of the present invention;

[0035] Figure 2 A flow chart for determining cluster eligibility for an embodiment of the present invention;

[0036] Figure 3 A flow chart for determining eligibility of data volume in a fuzzy target data pool according to an embodiment of the present invention;

[0037] Figure 4 The figure is a flow chart of a BI business opportunity mining method based on big data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0040] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0041] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0042] See also Figure 1-Figure 4 As shown, Figure 1 This is a schematic diagram of module connections of a BI business opportunity mining management system based on big data according to an embodiment of the present invention; Figure 2 A flow chart for determining cluster eligibility for an embodiment of the present invention; Figure 3 A flow chart for determining eligibility of data volume in a fuzzy target data pool according to an embodiment of the present invention; Figure 4 The figure is a flow chart of a BI business opportunity mining method based on big data according to an embodiment of the present invention.

[0043] The embodiment of the present invention is used for a BI business opportunity mining management system based on big data, including:

[0044] Data mining module, used to obtain massive enterprise information data from the enterprise information database;

[0045] A data cleaning module, which is connected to the data mining module and is used to clean the massive enterprise information data acquired by the data mining module;

[0046] A data storage module, which is connected to the data cleaning module and is used to store the massive enterprise information data cleaned by the data cleaning module and store the massive enterprise information data into different data pools;

[0047] A data analysis module, which is connected to the data storage module and is used to determine a strategy for constructing a fuzzy target data pool;

[0048] A data processing module, which is connected to the data analysis module and is used to determine the adjustment method of the fuzzy target data pool;

[0049] The data optimization module is connected to the data processing module and is used to determine the optimization method of the fuzzy target data pool.

[0050] Specifically, the data mining module obtains massive amounts of enterprise information data from external enterprise information databases and internal enterprise information databases by means of data crawling.

[0051] Specifically, the data cleaning module determines the eligibility of a single data according to the comparison result between the frequency of occurrence of a single data in the massive enterprise information data and the preset frequency under the condition that the data mining module obtains the massive enterprise information data;

[0052] If the frequency of occurrence of the single data is less than or equal to the preset frequency, the single data is determined to be qualified;

[0053] If the frequency of occurrence of the single data is greater than the preset frequency, the single data is determined to be unqualified.

[0054] In the embodiment of the present invention, the preset frequency value is 5 times, but the above value is not limited to this. Technical personnel in this field can also adjust the value according to actual needs. This value is in actual application. It allows a single data in massive enterprise information data to have multiple different application scenarios. For example, enterprise sales data is used by multiple departments to analyze future plans, historical sales summary, financial accounting, market research and advertising.

[0055] Specifically, the data storage module stores the single data into the data lake of the data storage module when the data cleaning module determines that the single data in the massive enterprise information data is qualified; the data storage module removes the single data when the data cleaning module determines that the single data in the massive enterprise information data is unqualified.

[0056] Specifically, the present invention determines the eligibility of individual data according to the comparison result of the frequency of occurrence of the individual data with the preset frequency through the data cleaning module, thereby improving the accuracy and reliability of the overall data set, thereby improving the accuracy of the management system.

[0057] Specifically, the data lake of the data storage module clusters a number of data and determines clustering eligibility based on a comparison result between the characteristic evaluation value of the data and a preset characteristic evaluation value of 0.85;

[0058] If the characteristic evaluation value is less than or equal to the preset characteristic evaluation value, the clustering is determined to be qualified;

[0059] If the characteristic evaluation value is greater than the preset characteristic evaluation value, it is determined that the clustering is unqualified.

[0060] In the embodiment of the present invention, the preset characteristic evaluation value is 0.85, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0061] Specifically, the present invention performs cluster analysis on a number of data through the data lake of the data storage module, and determines the clustering eligibility by comparing the characteristic evaluation value with the preset characteristic evaluation value, thereby reducing the influence of manual intervention and subjective judgment, thereby improving the accuracy and efficiency of management system evaluation.

[0062] Specifically, the data storage module calculates the characteristic evaluation value according to the following formula, setting:

[0063]

[0064] Among them, Q represents the characteristic evaluation value, ai represents the distance from the i-th data to the center point of the cluster to which it belongs, bi represents the distance from the i-th data to the center point that is most adjacent to it but does not belong to the same cluster, and n represents all data points.

[0065] Specifically, the data storage module stores the data into different data pools according to clustering eligibility. If the clustering is qualified, the data is stored in the target data pool; if the clustering is unqualified, the data is stored in the fuzzy target data pool.

[0066] Specifically, the data analysis module determines the eligibility of the data volume in the fuzzy target data pool according to the comparison result between the coincidence evaluation value of the data volume in the fuzzy target data pool and the data volume in its own historical fuzzy target data pool and the preset coincidence evaluation value of 0.8, under the condition that the data storage module stores the data that fails to be clustered into the fuzzy target data pool;

[0067] If the overlap evaluation value is less than or equal to the preset overlap evaluation value, it is determined that the data volume of the fuzzy target data pool is unqualified;

[0068] If the overlap evaluation value is greater than the preset overlap evaluation value, it is determined that the fuzzy target data pool is qualified;

[0069] The overlap evaluation value is an overlap evaluation value of the data volume of the fuzzy target data pool and the data volume of its own historical fuzzy target data pool.

[0070] In the embodiment of the present invention, the preset coincidence evaluation value is 0.8, and the preset coincidence evaluation value is obtained by taking the average value of several qualified historical coincidence evaluation values ​​in the fuzzy target data pool, but the above value is not limited to this, and technical personnel in this field can also adjust the value according to actual needs.

[0071] Specifically, the data processing module calculates the overlap evaluation value according to the following formula:

[0072]

[0073] Among them, P represents the overlap evaluation value, Nc represents the data volume of the overlapping fuzzy target data pool, N represents the data volume of the current fuzzy target data pool, and Nh represents the data volume of its own historical fuzzy target data pool.

[0074] Specifically, the data processing module determines, under the condition that the data volume of the fuzzy target data pool is unqualified, a method for adjusting the data volume of the fuzzy target data pool according to a comparison result between the preset coincidence evaluation value and the difference between the coincidence evaluation value and the preset difference value 0.2;

[0075] If the difference is less than or equal to the preset difference, determining the amount of data to update the fuzzy target data pool;

[0076] If the difference is greater than the preset difference, determining to delete the data amount of the fuzzy target data pool;

[0077] The difference value is the difference between the preset coincidence evaluation value and the coincidence evaluation value.

[0078] In an embodiment of the present invention, the preset difference value is 0.2, and the preset difference value is obtained by taking the average value of the difference between several historical preset coincidence evaluation values ​​and the coincidence evaluation value, but the above value is not limited to this, and technical personnel in this field can also adjust the value according to actual needs.

[0079] Specifically, the present invention classifies information data into different data pools according to clustering eligibility through the data storage module, and adjusts the data volume of the fuzzy target data pool after the data storage module stores the data that does not meet the clustering requirements into the fuzzy target data pool through the data analysis module, so as to make the data analysis more accurate, thereby improving the accuracy of the management system.

[0080] Specifically, the data processing module determines the amount of data to update the fuzzy target data pool according to a comparison result of the ratio of the difference value to the preset difference value and the first preset ratio of 0.8;

[0081] If the ratio is less than or equal to the first preset ratio, it is determined to update the data volume of the fuzzy target data pool to a corresponding value using the first preset update adjustment coefficient;

[0082] If the ratio is greater than the first preset ratio, it is determined to update the data volume of the fuzzy target data pool to a corresponding value using a second preset update adjustment coefficient;

[0083] The ratio is the ratio of the difference to a preset difference.

[0084] In the embodiment of the present invention, the preset ratio is 0.8, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0085] In an embodiment of the present invention, the data volume of the updated fuzzy label database is set to Nz, and Nz=N×Ti is set, wherein N represents the data volume of the fuzzy target data pool, Ti represents the i-th preset update adjustment coefficient, i takes a value of 1 or 2, T1 is the first preset update adjustment coefficient, and T2 is the second preset update adjustment coefficient.

[0086] Specifically, after determining the strategy for updating the data volume of the fuzzy target data pool, the data processing module determines how to update the data volume of the fuzzy target data pool based on the comparison result of the ratio of the difference to the preset difference and the first preset ratio, thereby improving the accuracy of the management system.

[0087] Specifically, the data processing module determines the amount of data to be deleted from the fuzzy target data pool according to the comparison result of the ratio of the difference value to the preset difference value and the second preset ratio of 1.2;

[0088] If the ratio is less than or equal to the second preset ratio, it is determined to reduce the data volume of the fuzzy target data pool to a corresponding value using the first preset deletion adjustment coefficient;

[0089] If the ratio is greater than a second preset ratio, it is determined to reduce the amount of data in the fuzzy target data pool to a corresponding value using a second preset deletion adjustment coefficient;

[0090] The ratio is the ratio of the difference to a preset difference.

[0091] In the embodiment of the present invention, the preset ratio is 1.2, but the above value is not limited thereto, and those skilled in the art may also adjust the value according to actual needs.

[0092] In an embodiment of the present invention, the data volume of the updated fuzzy label database is set to Ns, and Ns=N×Ki is set, wherein N represents the data volume of the fuzzy target database, Ki represents the i-th preset deletion adjustment coefficient, i takes a value of 1 or 2, T1 is the first preset deletion adjustment coefficient, and T2 is the second preset deletion adjustment coefficient.

[0093] Specifically, after determining the strategy for reducing the data volume of the fuzzy target data pool, the data processing module determines how to reduce the data volume of the fuzzy target data pool based on the comparison result of the ratio of the difference with the preset difference and the second preset ratio, thereby improving the accuracy of the management system.

[0094] Specifically, the data analysis module determines the strategy of comparing the data volume of the fuzzy target data pool with the data volume of the same type but different scale fuzzy target data pools according to the comparison result of the data volume distribution uniformity evaluation value of the fuzzy target data pool and the preset distribution uniformity evaluation value of 0.82 under the condition that the data storage module stores the data volume that fails to meet the clustering requirements into the fuzzy target data pool;

[0095] If the data volume distribution uniformity evaluation value of the fuzzy target data pool is less than or equal to the preset distribution uniformity evaluation value, a strategy for comparing the data volume with the fuzzy target data pool of small and micro enterprises of the same type is determined;

[0096] If the data volume distribution uniformity evaluation value of the fuzzy target data pool is greater than the preset distribution uniformity evaluation value, a strategy for comparing the data volume with the fuzzy target data pools of large and medium-sized enterprises of the same type is determined.

[0097] In the embodiment of the present invention, the preset distribution uniformity evaluation value is 0.82. The preset distribution uniformity evaluation value is obtained by taking the average of several historical distribution uniformity evaluation values, but the above value is not limited to this. Technical personnel in this field can also adjust the value according to actual needs.

[0098] In the embodiment of the present invention, the correlation is determined based on the same semantic expression between the fuzzy target data pool and the fuzzy target data pools of the same type but different sizes.

[0099] Specifically, the data processing module calculates the distribution uniformity evaluation value according to the following formula, setting:

[0100]

[0101] Among them, U represents the uniformity evaluation value, n represents that the fuzzy target data pool is divided into n intervals, Ci represents the data volume of the i-th interval, and E represents the average expected data volume of each interval.

[0102] Specifically, the present invention classifies information data into different data pools according to clustering eligibility through the data storage module, and after the data storage module stores the data that does not meet the clustering requirements into the fuzzy target data pool, the subsequent analysis strategy is determined according to the comparison result between the data volume distribution uniformity evaluation value of the fuzzy target data pool and the preset distribution uniformity evaluation value, so as to make data analysis more efficient, thereby improving the efficiency of the management system.

[0103] Specifically, the data processing module determines the mode for adjusting the data volume of the fuzzy target data pool according to the comparison result of the management evaluation value with the preset management evaluation value, under the condition that the data analysis module determines the correlation with the data volume comparison of the fuzzy target data pool of small and micro enterprises of the same type;

[0104] If the management evaluation value is less than or equal to the preset management evaluation value, it is determined to update the data volume of the fuzzy target data pool with the management adjustment coefficient F;

[0105] If the management evaluation value is greater than the preset management evaluation value, it is determined that there is no need to adjust the data volume of the fuzzy target data pool.

[0106] In the embodiment of the present invention, the data volume of the updated fuzzy target data pool is set to Ng, and Ng=N×F is set, wherein N represents the data volume of the fuzzy target data pool, and F represents the management adjustment coefficient.

[0107] In the embodiment of the present invention, the preset enterprise management evaluation value is 0.9, and the preset enterprise management evaluation value is obtained by averaging several historical enterprise management evaluation values, but the above value is not limited to this, and technical personnel in this field can also adjust the value according to actual needs.

[0108] Specifically, the data processing module calculates the management evaluation value according to the following formula:

[0109]

[0110] Among them, L represents the management evaluation value, H represents the enterprise sales, Hi represents the sales of the i-th small and micro-enterprise of the same type, B represents the number of customers, Bi represents the number of customers of the i-th small and micro-enterprise of the same type, D represents the number of employees, and Di represents the number of employees of the i-th small and micro-enterprise of the same type.

[0111] In the embodiment of the present invention, the enterprise sales volume is the total revenue obtained by the enterprise through the sale of products, the number of customers is the total number of customers that have business dealings or established relationships with the enterprise, and the number of employees is the total number of people working in the enterprise.

[0112] Specifically, the data processing module determines the management adjustment coefficient F according to the difference between the management evaluation value and the preset management evaluation value and the preset difference.

[0113] Specifically, the data processing module calculates the management adjustment coefficient according to the following formula and sets:

[0114]

[0115] Wherein, F represents the management adjustment coefficient, ΔL represents the difference between the management evaluation value and the preset management evaluation value, and ΔL0 represents the preset difference.

[0116] Specifically, under the condition that the data analysis module of the present invention determines the correlation with the data volume comparison in the fuzzy data pool of small and micro enterprises of the same type, the data processing module will perform further adjustment operations, and determine the adjustment mode specifically according to the comparison result between the management evaluation value and the preset management evaluation value, thereby improving the accuracy of the management system.

[0117] Specifically, the data processing module determines the mode for adjusting the data volume of the fuzzy target data pool according to the comparison result between the comprehensive evaluation value and the preset comprehensive evaluation value under the condition that the data analysis module determines the correlation with the large and medium-sized enterprises of the same type;

[0118] If the comprehensive evaluation value is less than or equal to the preset comprehensive evaluation value, it is determined to reduce the amount of data in the fuzzy target data pool by using the deletion adjustment coefficient G;

[0119] If the comprehensive evaluation value is greater than the preset comprehensive evaluation value, there is no need to adjust the data volume of the fuzzy target data pool.

[0120] The data volume of the fuzzy target data pool is set to Nv, and Ng=N×G is set, where N represents the data volume of the fuzzy target data pool, and G represents the deletion adjustment coefficient.

[0121] In the embodiment of the present invention, the preset enterprise comprehensive evaluation value is 0.88, and the preset enterprise comprehensive evaluation value is obtained by averaging several historical comprehensive evaluation values, but the above value is not limited to this, and technical personnel in this field can also adjust the value according to actual needs.

[0122] Specifically, the data processing module calculates the comprehensive evaluation value according to the following formula:

[0123]

[0124] Among them, K represents the comprehensive evaluation value, S represents the R&D investment of the enterprise, Si represents the R&D investment of the i-th large and medium-sized enterprise of the same type, M represents the market size, Mi represents the market size of the i-th large and medium-sized enterprise of the same type, R represents the number of enterprise partners, and Ri represents the number of partners of the i-th large and medium-sized enterprise of the same type.

[0125] In the embodiment of the present invention, the enterprise market size is the share of the enterprise in the industry, the enterprise R&D investment is the total expenditure incurred by the enterprise in research and development activities, and the number of partners is the number of other enterprises, institutions or individuals that have established cooperative relations with the enterprise.

[0126] Specifically, the data processing module determines the deletion adjustment coefficient G according to the difference between the comprehensive evaluation value and the preset comprehensive evaluation value and the preset difference.

[0127] Specifically, the data processing module calculates the deletion adjustment coefficient according to the following formula and sets:

[0128]

[0129] Wherein, G represents the deletion adjustment coefficient, ΔK represents the difference between the comprehensive evaluation value and the preset comprehensive evaluation value, and ΔK0 represents the preset difference.

[0130] Specifically, under the condition that the data analysis module determines the correlation with the data volume comparison of the fuzzy target data pool of large and medium-sized enterprises of the same type, the data processing module will further determine the adjustment mode according to the comparison result of the comprehensive evaluation value with the preset comprehensive evaluation value, which helps to reduce data redundancy and outdated information, thereby improving the accuracy and efficiency of the management system.

[0131] Specifically, the data optimization module determines the optimization method of the data volume of the fuzzy target data pool according to the comparison object under the condition that the data processing module performs the comparison;

[0132] If the data volume of the fuzzy target data pool is compared with the data volume of its own historical fuzzy target data pool, it is determined that data related to the fuzzy target data pool is supplemented from the target data pool to the fuzzy target data pool;

[0133] If the data volume of the fuzzy target data pool is compared with the data volume of the external fuzzy target data pool, it is determined that the data volume that is relevant to the fuzzy target data pool is supplemented from the external target data pool to the fuzzy target data pool.

[0134] In the embodiment of the present invention, the data that is relevant to the fuzzy target data pool is data that is consistent with the fuzzy target data pool in terms of classification.

[0135] Specifically, after receiving the comparison result from the data processing module, the data optimization module of the present invention determines the corresponding optimization method according to the specific object of comparison, thereby improving the accuracy and efficiency of the management system.

[0136] On the other hand, the present invention also provides a BI business opportunity mining method based on big data, comprising:

[0137] Step S1, obtaining massive enterprise information data from an external enterprise information database and an internal enterprise information database by data crawling;

[0138] Step S2, determining the eligibility of a single data according to the comparison result of the frequency of occurrence of the single data in the massive enterprise information data with the preset frequency;

[0139] Step S3, under the condition that the single data is determined to be qualified, the single data is stored in the data lake, and a number of data in the data lake are clustered, and the qualified clustering data is stored in the target data pool according to the clustering eligibility, and the unqualified clustering data is stored in the fuzzy target data pool;

[0140] Step S4, determining the eligibility of the data volume of the fuzzy target data pool, the strategy for comparing the data volume of the fuzzy data pool with the data volume of the same type and different scale enterprises, and the adjustment method for updating the data volume according to the comparison result of the coincidence evaluation value of the data volume of the fuzzy target data pool and the preset coincidence value;

[0141] Step S5, determining an optimization method for the data volume of the fuzzy target data pool according to the comparison result, so as to supplement the data volume from the target data pool or the external target data pool to the fuzzy target data pool.

[0142] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0143] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A BI business opportunity mining management system based on big data, characterized in that: include: Data mining module, used to obtain massive enterprise information data from the enterprise information database; A data cleaning module, which is connected to the data mining module and is used to determine the eligibility of a single data volume based on the frequency of occurrence of the single data volume in the massive enterprise information data; A data storage module connected to the data cleaning module is used to determine that the clustering is unqualified when the characteristic evaluation value of the data volume is greater than the preset characteristic evaluation value under the condition that the single data is qualified, and store the data volume into the fuzzy target data pool; A data analysis module, which is connected to the data storage module, is used to determine the eligibility of the data volume of the fuzzy target data pool according to the comparison result of the coincidence evaluation value and the preset coincidence evaluation value under the condition of unqualified clustering, and to determine the strategy of comparing the data volume of the fuzzy target data pool with the data volume of the fuzzy target data pool of the same type of small and micro-sized enterprises or the data volume of the fuzzy target data pool of the same type of large and medium-sized enterprises according to the evaluation value of the uniformity of the distribution of the data volume of the fuzzy target data pool; A data processing module, which is connected to the data analysis module, and is used to determine the adjustment of the data volume of the fuzzy target data pool according to the difference between the preset coincidence evaluation value and the coincidence evaluation value under the condition that the data volume of the fuzzy target data pool is unqualified, and to determine the adjustment of the data volume of the fuzzy target database according to the management evaluation value or the comprehensive evaluation value based on the strategy of comparing the data volume of the fuzzy target data pool with the data volume of the fuzzy target data pool of the same type of small and micro-sized enterprises or the data volume of the fuzzy target data pool of the same type of large and medium-sized enterprises; The data processing module determines, under the condition that the data volume of the fuzzy target data pool is unqualified, a strategy for comparing the data volume of the fuzzy target data pool with the data volume of the same type of small and micro-sized enterprises according to the comparison result that the distribution uniformity evaluation value of the data volume of the fuzzy target data pool is less than or equal to the preset distribution uniformity evaluation value, and determines to update the data volume of the fuzzy target data pool with the management adjustment coefficient based on the comparison result that the management evaluation value is less than or equal to the preset management evaluation value; The data processing module determines, under the condition that the data volume of the fuzzy target data pool is unqualified, a strategy for comparing the data volume of the fuzzy target data pool with that of large and medium-sized enterprises of the same type according to the comparison result that the distribution uniformity evaluation value of the data volume of the fuzzy target data pool is greater than the preset distribution uniformity evaluation value, and determines to delete the data volume of the fuzzy target data pool by the deletion adjustment coefficient based on the comprehensive evaluation value being less than or equal to the preset comprehensive evaluation value; A data optimization module, which is connected to the data processing module, and is used to determine the optimization of the data volume of the fuzzy target database according to the comparison object based on the data processing module performing a data volume comparison of its own historical fuzzy target data pool or a data volume comparison of an external fuzzy target data pool; The data optimization module, under the condition that the data processing module determines the corresponding comparison strategy, if the comparison strategy is to compare the data volume of the fuzzy target data pool with the data volume of its own historical fuzzy target data pool, determines to supplement the data volume from the target data pool to the fuzzy target data pool; if the comparison strategy is to compare the data volume of the fuzzy target data pool with the data volume of the external fuzzy target data pool, determines to supplement the data volume from the external target data pool to the fuzzy target data pool.

2. The BI business opportunity mining management system based on big data according to claim 1 is characterized in that: The data analysis module determines that a single data volume is qualified based on the frequency of occurrence of the single data volume being less than or equal to a preset frequency, and determines that clustering is unqualified based on a comparison result based on a characteristic evaluation value of the data volume being greater than a preset characteristic evaluation value, under the condition that the data mining module obtains massive enterprise information data. The data analysis module determines that the data volume in the fuzzy target data pool is unqualified based on the fact that the overlap evaluation value between the data volume in the fuzzy target data pool and the data volume in its own historical fuzzy target data pool is less than or equal to a preset overlap evaluation value.

3. The BI business opportunity mining management system based on big data according to claim 2 is characterized in that: The data processing module, under the condition that it is determined that the data volume of the fuzzy target data pool is unqualified, determines to update the data volume of the fuzzy target data pool to a corresponding value using a first preset update adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is less than or equal to a first preset ratio.

4. The BI business opportunity mining management system based on big data according to claim 2 is characterized in that: The data processing module determines, under the condition that the data volume of the fuzzy target data pool is unqualified, that the data volume of the fuzzy target data pool is updated to a corresponding value using a second preset update adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is greater than a first preset ratio.

5. The BI business opportunity mining management system based on big data according to claim 2 is characterized in that: The data processing module, under the condition that it is determined that the data volume of the fuzzy target data pool is unqualified, determines to reduce the data volume of the fuzzy target data pool to a corresponding value using a first preset deletion adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is less than or equal to a second preset ratio.

6. The BI business opportunity mining management system based on big data according to claim 2 is characterized in that: The data processing module determines, under the condition that the data volume of the fuzzy target data pool is unqualified, that the data volume of the fuzzy target data pool is reduced to a corresponding value using a second preset deletion adjustment coefficient based on a comparison result in which the ratio of a preset coincidence evaluation value to a difference between the coincidence evaluation values ​​is greater than a second preset ratio.

7. A BI business opportunity mining method based on big data, using the BI business opportunity mining management system based on big data according to any one of claims 1 to 6, characterized in that: include: Step S1, obtaining massive enterprise information data from an external enterprise information database and an internal enterprise information database by data crawling; Step S2, determining the eligibility of a single data according to the comparison result of the frequency of occurrence of the single data in the massive enterprise information data with the preset frequency; Step S3, under the condition that the single data is determined to be qualified, the single data is stored in the data lake, and a number of data in the data lake are clustered, and the qualified clustering data is stored in the target data pool according to the clustering eligibility, and the unqualified clustering data is stored in the fuzzy target data pool; Step S4, determining the eligibility of the data volume of the fuzzy target data pool, the strategy for comparing the data volume of the fuzzy data pool with the data volume of the same type and different scale enterprises, and the adjustment method for updating the data volume according to the comparison result of the coincidence evaluation value of the data volume of the fuzzy target data pool and the preset coincidence value; Step S5, determining an optimization method for the data volume of the fuzzy target data pool according to the comparison result, so as to supplement the data volume from the target data pool or the external target data pool to the fuzzy target data pool.

Images