Data Analysis Method and System Based on Intelligent Management Platform

Abstract

An embodiment of the present invention provides a data analysis method and system based on an intelligent management platform. By selecting a target user requirement mining model of the first target magnitude in the target platform user requirement mining task, then pushing platform big data to each target user requirement mining model based on the target platform big data collection task of the second target magnitude, and selecting target platform big data push data of the third target magnitude from the platform big data push data. Then, determine the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords, and determine the platform big data push data with a relevance greater than the first target value as the platform big data push data matching the target platform user requirement mining task. In this way, it can provide an effective data basis for user requirement mining, and further improve the accuracy of subsequent user requirement mining.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management platforms, and in particular, to a data analysis method and system based on an intelligent management platform. Background Art

[0002] Currently, in the development process of an intelligent management platform, it is necessary to mine user requirements from the relevant platform big data. How to provide an effective data basis for user requirement mining and then improve the accuracy of subsequent user requirement mining is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0003] In view of this, the purpose of the embodiments of the present invention is to provide a data analysis method and system based on an intelligent management platform, which can provide an effective data basis for user requirement mining and then improve the accuracy of subsequent user requirement mining.

[0004] Based on one aspect of the embodiments of the present invention, a data analysis method based on an intelligent management platform is provided, which is applied to an intelligent management platform. The method includes:

[0005] Select a target user requirement mining model of a first target level in the target platform user requirement mining task. Each of the target user requirement mining models is used to mine platform user requirements for the data analysis based on the intelligent management platform in the target platform user requirement mining task, and the target user requirement mining model is a previously marked key user requirement mining model;

[0006] Push platform big data to each of the target user requirement mining models based on a target platform big data collection task of a second target level, and select target platform big data push data of a third target level from the platform big data push data based on a second mining template;

[0007] Obtain the platform big data push keywords in all the target platform big data push data;

[0008] Determine the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords, and determine the platform big data push data with a relevance greater than a first target value as the platform big data push data matching the target platform user requirement mining task, where the higher the relevance, the higher the matching degree between the target platform user requirement mining task and the platform big data push keywords.

[0009] In some exemplary design ideas, the step of selecting a target user requirement mining model of a first target level in the target platform user requirement mining task includes:

[0010] Divide and conquer the target platform user demand mining task based on the first mining template, and among all the user demand mining models obtained after dividing and conquering the target platform user demand mining task based on the first mining template, obtain the target user demand mining model of the first target magnitude based on a set instruction.

[0011] In some exemplary design ideas, the step of selecting the target platform big data push data of the third target magnitude from the platform big data push data based on the second mining template includes:

[0012] Select the top fourth target magnitude of the platform big data push data in the platform big data push data returned by each of the target platform big data collection tasks for each of the target user demand mining models as the basic recall platform big data push data;

[0013] Determine the relevance between each of the target user demand mining models and the corresponding basic recall platform big data push data;

[0014] Determine the relevance between the basic recall platform big data push data with a relevance higher than the second target value and the corresponding target user demand mining model;

[0015] Based on the relevance, determine the top third target magnitude of the platform big data push data most similar to the target user demand mining model as the target platform big data push data.

[0016] In some exemplary design ideas, the step of determining the relevance between the target platform user demand mining task and the platform big data push keyword includes:

[0017] Divide and conquer the target platform user demand mining task based on the third mining template, and determine the relevance of all the obtained platform big data collection tasks in the platform big data push keyword respectively. For each platform big data push keyword, use the proportion of the platform big data collection tasks with a relevance greater than the third target value in all the platform big data collection tasks obtained after dividing and conquering the target platform user demand mining task based on the third mining template as the relevance of the target platform big data push data.

[0018] In some exemplary design ideas, the step of determining the relevance of all the obtained platform big data collection tasks in the platform big data push keyword respectively includes:

[0019] Classify all the platform big data collection tasks obtained after dividing the target platform user demand mining task based on the third mining template, and set task analysis modules respectively based on the number of task nodes included in all the platform big data collection tasks, and then perform matching between all the platform big data collection tasks and the platform big data push keywords for the task analysis modules;

[0020] In each match, if the proportion of the task nodes displayed in the task analysis module in the platform big data push keywords that match the task nodes in the target platform user demand mining task corresponding to the task analysis module is not less than the fifth target value, determine the second weight ratio of the span between the task nodes that are matched and associated in the target platform user demand mining task to the total number of task nodes, and use the largest weight ratio in the second weight ratio as the association degree of the platform big data collection task corresponding to the task analysis module, where the total number of task nodes is the total number of task nodes in the task analysis module minus one.

[0021] On the other hand, based on an embodiment of the present invention, a data analysis system based on an intelligent management platform is provided, which is applied to the intelligent management platform. The system includes:

[0022] A selection module, configured to select a first target magnitude of target user demand mining models in the target platform user demand mining task, where each target user demand mining model is used to perform platform user demand mining on the data analysis based on the intelligent management platform in the target platform user demand mining task, and the target user demand mining model is a previously labeled key user demand mining model;

[0023] A push module, configured to perform platform big data push on each target user demand mining model based on a second target magnitude of target platform big data collection tasks, and select a third target magnitude of target platform big data push data from the platform big data push data based on a second mining template;

[0024] An acquisition module, configured to acquire the platform big data push keywords in all the target platform big data push data;

[0025] A determination module, configured to determine the relevance between the user demand mining graph of the target platform user demand mining task and the keyword features of the platform big data push keywords, and determine the platform big data push data with a relevance greater than the first target value as the platform big data push data matching the target platform user demand mining task, where the higher the relevance, the higher the matching degree between the target platform user demand mining task and the platform big data push keywords.

[0026] On the other hand of the embodiments of the present invention, a readable storage medium is provided. A determination machine program is stored on the readable storage medium. When the determination machine program is run by a processor, it can execute the steps of the above-mentioned data analysis method based on an intelligent management platform.

[0027] Compared with the prior art, the data analysis method and system based on an intelligent management platform provided by the embodiments of the present invention select a target user requirement mining model of the first target magnitude in the target platform user requirement mining task, then perform platform big data push on each target user requirement mining model based on the target platform big data collection task of the second target magnitude, and select target platform big data push data of the third target magnitude from the platform big data push data based on the second mining template. Then, the platform big data push keywords in all the target platform big data push data are obtained, the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords is determined, and the platform big data push data with a relevance greater than the first target value is determined as the platform big data push data matching the target platform user requirement mining task. In this way, it can provide an effective data basis for user requirement mining, and thus improve the accuracy of subsequent user requirement mining.

[0028] To make the above objects, features, and advantages of the embodiments of the present invention more obvious and understandable, the following will be described in detail in combination with the embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0030] Figure 1 Shows a schematic diagram of the components of the intelligent management platform provided by the embodiments of the present invention;

[0031] Figure 2 Shows a schematic flowchart of the data analysis method based on an intelligent management platform provided by the embodiments of the present invention;

[0032] Figure 3 Shows a functional module block diagram of the data analysis system based on an intelligent management platform provided by the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] To enable students in the technical field to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. According to the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0034] The terms "first", "second", "third", etc. (if any) in the description and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0035] Figure 1 An exemplary component diagram of the intelligent management platform 100 is shown. The intelligent management platform 100 may include one or more processors 104, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The intelligent management platform 100 may also include any storage medium 106 for storing any kind of information such as code, settings, data, etc. Non-limitingly, for example, the storage medium 106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical discs, etc. More generally, any storage medium can store information based on any technology. Further, any storage medium can provide volatile or non-volatile retention of information. Further, any storage medium may represent a fixed or removable component of the intelligent management platform 100. In one case, when the processor 104 executes the associated instructions stored in any storage medium or combination of storage media, the intelligent management platform 100 can perform any operation of the associated instructions. The intelligent management platform 100 also includes one or more drive units 108 for interacting with any storage medium, such as a hard disk drive unit, an optical disc drive unit, etc.

[0036] The intelligent management platform 100 also includes an input / output 110 (I / O) that is used to receive various inputs (via the input unit 112) and to provide various outputs (via the output unit 114). A specific output mechanism may include a presentation device 116 and an associated graphical user interface (GUI) 118. The intelligent management platform 100 may also include one or more network interfaces 120 that are used to exchange data with other devices via one or more communication units 122. One or more communication buses 124 couple the components described above together.

[0037] The communication unit 122 may be implemented in any manner, for example, via a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication unit 122 may include any combination of hardwired links, wireless links, routers, gateway functions, name intelligent management platforms 100, etc. governed by any protocol or combination of protocols.

[0038] Figure 2 A flowchart showing the process of the data analysis method based on the intelligent management platform provided by an embodiment of the present invention is shown. The data analysis method based on the intelligent management platform can be executed by Figure 1 the intelligent management platform 100 shown in the figure, and the detailed steps of the data analysis method based on the intelligent management platform are introduced as follows.

[0039] Step S110, select a target user requirement mining model of the first target magnitude in the target platform user requirement mining task, where each of the target user requirement mining models is used to perform platform user requirement mining on the data analysis based on the intelligent management platform in the target platform user requirement mining task, and the target user requirement mining model is a key user requirement mining model that has been previously annotated;

[0040] Step S120, perform platform big data push on each of the target user requirement mining models based on the target platform big data collection task of the second target magnitude, and select target platform big data push data of the third target magnitude from the platform big data push data based on the second mining template;

[0041] Step S130, obtain the platform big data push keywords in all the target platform big data push data;

[0042] Step S140: Determine the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords, and determine the platform big data push data with a relevance greater than the first target value as the platform big data push data matching the target platform user requirement mining task. Herein, the higher the relevance, the higher the matching degree between the target platform user requirement mining task and the platform big data push keywords.

[0043] Based on the above steps, in this embodiment, by selecting a first target quantity of target user requirement mining models in the target platform user requirement mining task, then performing platform big data push on each target user requirement mining model based on a second target quantity of target platform big data collection tasks, and selecting a third target quantity of target platform big data push data from the platform big data push data based on a second mining template, then obtaining the platform big data push keywords in all the target platform big data push data, determining the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords, and determining the platform big data push data with a relevance greater than the first target value as the platform big data push data matching the target platform user requirement mining task. In this way, it can provide an effective data basis for user requirement mining, and further improve the accuracy of subsequent user requirement mining.

[0044] In some exemplary design ideas, for step S110, this embodiment can perform divide-and-conquer on the target platform user requirement mining task based on a first mining template, and obtain the first target quantity of target user requirement mining models from all the user requirement mining models obtained after performing divide-and-conquer on the target platform user requirement mining task based on the first mining template according to a set instruction.

[0045] In some exemplary design ideas, for step S120, this embodiment can select the first fourth target quantity of platform big data push data in the platform big data push data returned by each target platform big data collection task for each target user requirement mining model as the basic recall platform big data push data, then determine the relevance between each target user requirement mining model and the corresponding basic recall platform big data push data, and determine the relevance between the basic recall platform big data push data with a relevance higher than the second target value and the corresponding target user requirement mining model, so that based on the relevance, the first third target quantity of platform big data push data most similar to the target user requirement mining model can be determined as the target platform big data push data.

[0046] In some exemplary design concepts, for step S140, in this embodiment, the target platform user requirement mining task can be divided and conquered based on the third mining template, and the relevance of all the obtained platform big data collection tasks to the platform big data push keywords can be determined. For each of the platform big data push keywords, the proportion of the platform big data collection tasks with a relevance greater than the third target value to the platform big data push keywords among all the platform big data collection tasks obtained after dividing and conquering the target platform user requirement mining task based on the third mining template is used as the relevance of the target platform big data push data.

[0047] For example, all the platform big data collection tasks obtained after dividing and conquering the target platform user requirement mining task based on the third mining template can be classified, and task analysis modules can be set respectively based on the number of task nodes included in all the platform big data collection tasks, and the matching between all the platform big data collection tasks and the platform big data push keywords can be performed on the task analysis modules accordingly. On this basis, in each match, if the proportion of the task nodes displayed in the task analysis module in the platform big data push keywords that match the task nodes in the target platform user requirement mining task corresponding to the task analysis module is not less than the fifth target value, then the second weight ratio of the span between the task nodes that are matched and associated in the target platform user requirement mining task to the total number of task nodes is determined, and the largest weight ratio in the second weight ratio is used as the relevance of the platform big data collection task corresponding to the task analysis module, where the total number of task nodes is the total number of task nodes in the task analysis module minus one.

[0048] Figure 3 FIG. shows a functional module diagram of a data analysis system 200 based on an intelligent management platform provided by an embodiment of the present invention. The functions implemented by the data analysis system 200 based on the intelligent management platform can correspond to the steps executed by the above method. The data analysis system 200 based on the intelligent management platform can be understood as the above intelligent management platform 100, or the processor of the intelligent management platform 100, or can also be understood as a component that realizes the functions of the present invention under the control of the intelligent management platform 100 and is independent of the above intelligent management platform 100 or the processor, such as Figure 3 As shown, the functions of each functional module of the data analysis system 200 based on the intelligent management platform will be elaborated in detail below.

[0049] The selection module 210 is used to select target user requirement mining models of a first target quantity in the target platform user requirement mining task. Each of the target user requirement mining models is used to perform platform user requirement mining on the data analysis based on the intelligent management platform in the target platform user requirement mining task. The target user requirement mining models are key user requirement mining models that have been pre-annotated.

[0050] The push module 220 is used to perform platform big data push on each of the target user requirement mining models based on the target platform big data collection task of a second target quantity, and select target platform big data push data of a third target quantity from the platform big data push data based on a second mining template.

[0051] The acquisition module 230 is used to acquire the platform big data push keywords in all the target platform big data push data.

[0052] The determination module 240 is used to determine the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords, and determine the platform big data push data with a relevance greater than a first target value as the platform big data push data matching the target platform user requirement mining task. The higher the relevance, the higher the matching degree between the target platform user requirement mining task and the platform big data push keywords.

[0053] In some exemplary design ideas, the method for selecting target user requirement mining models of a first target quantity in the target platform user requirement mining task includes:

[0054] Perform divide-and-conquer on the target platform user requirement mining task based on a first mining template, and obtain the target user requirement mining models of the first target quantity based on a set instruction from all the user requirement mining models obtained after performing divide-and-conquer on the target platform user requirement mining task based on the first mining template.

[0055] In some exemplary design ideas, the method for selecting target platform big data push data of a third target quantity from the platform big data push data based on a second mining template includes:

[0056] Select the top platform big data push data of a fourth target quantity in the platform big data push data returned by each target platform big data collection task for each target user requirement mining model as the basic recall platform big data push data.

[0057] Determine the relevance between each target user requirement mining model and the corresponding basic recall platform big data push data.

[0058] Determine the relevance between the big data push data of the basic recall platform with a relevance higher than the second target value and the corresponding target user demand mining model;

[0059] Based on the relevance, determine the top third target magnitude of platform big data push data that is most similar to the target user demand mining model as the target platform big data push data.

[0060] In some exemplary design ideas, the method for determining the relevance between the target platform user demand mining task and the platform big data push keyword includes:

[0061] Perform divide-and-conquer on the target platform user demand mining task based on the third mining template, and determine the relevance of all obtained platform big data collection tasks in the platform big data push keyword respectively. For each platform big data push keyword, use the proportion of the platform big data collection tasks with a relevance greater than the third target value in all platform big data collection tasks obtained after performing divide-and-conquer on the target platform user demand mining task based on the third mining template as the relevance of the target platform big data push data.

[0062] In some exemplary design ideas, the method for determining the relevance of all obtained platform big data collection tasks in the platform big data push keyword respectively includes:

[0063] Classify all platform big data collection tasks obtained after performing divide-and-conquer on the target platform user demand mining task based on the third mining template, and set task analysis modules respectively based on the number of task nodes included in all platform big data collection tasks, and use this to perform matching between all platform big data collection tasks and the platform big data push keyword for the task analysis modules.

[0064] In each matching, if the matching proportion of the task nodes displayed in the task analysis module in the platform big data push keyword and the task nodes in the target platform user demand mining task corresponding to the task analysis module is not less than the fifth target value, determine the second weight ratio of the span between the task nodes that are matched and associated in the target platform user demand mining task to the total number of task nodes, and use the largest weight ratio in the second weight ratio as the relevance of the platform big data collection task corresponding to the task analysis module, where the total number of task nodes is the total number of task nodes in the task analysis module minus one.

[0065] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0066] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claimed rights.

Claims

1. A data analysis method based on an intelligent management platform, characterized in that Applied to an intelligent management platform, the method includes: Select a target user requirement mining model of the first target magnitude in the target platform user requirement mining task. Each of the target user requirement mining models is used to mine platform user requirements for data analysis based on the intelligent management platform in the target platform user requirement mining task, and the target user requirement mining model is a key user requirement mining model that has been pre-labeled; Push platform big data to each of the target user requirement mining models based on the target platform big data collection task of the second target magnitude, and select target platform big data push data of the third target magnitude from the platform big data push data based on the second mining template; Obtain the platform big data push keywords in all the target platform big data push data; Determine the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords, and determine the platform big data push data with a relevance greater than the first target value as the platform big data push data that matches the target platform user requirement mining task. The higher the relevance, the higher the matching degree between the target platform user requirement mining task and the platform big data push keywords; The step of determining the relevance between the target platform user requirement mining task and the platform big data push keywords includes: Perform divide-and-conquer on the target platform user requirement mining task based on the third mining template, determine the relevance of all the obtained platform big data collection tasks in the platform big data push keywords respectively, and for each of the platform big data push keywords, use the proportion of the platform big data collection tasks with a relevance greater than the third target value in all the platform big data collection tasks obtained after performing divide-and-conquer on the target platform user requirement mining task based on the third mining template as the relevance of the target platform big data push data; The step of determining the relevance of all the obtained platform big data collection tasks in the platform big data push keywords respectively includes: Classify all the platform big data collection tasks obtained after performing divide-and-conquer on the target platform user requirement mining task based on the third mining template, set task analysis modules respectively based on the number of task nodes included in all the platform big data collection tasks, and use this to perform matching between all the platform big data collection tasks and the platform big data push keywords; In each match, if the proportion of the task nodes displayed in the task analysis module among the keywords pushed by the platform big data that match the task nodes in the target platform user demand mining task corresponding to the task analysis module is not less than the fifth target value, then determine the second weight ratio of the span between the task nodes that are matched and associated in the target platform user demand mining task to the total number of task nodes, and use the largest weight ratio in the second weight ratio as the association degree of the platform big data collection task corresponding to the task analysis module, where the total number of task nodes is the total number of task nodes in the task analysis module minus one.

2. The data analysis method based on the intelligent management platform according to claim 1, wherein The step of selecting a target user demand mining model of the first target magnitude in the target platform user demand mining task includes: Performing divide-and-conquer on the target platform user demand mining task based on the first mining template, and obtaining the target user demand mining model of the first target magnitude based on a set instruction from all the user demand mining models obtained after performing divide-and-conquer on the target platform user demand mining task based on the first mining template.

3. The data analysis method based on the intelligent management platform according to claim 1, characterized in that The step of selecting target platform big data push data of the third target magnitude from the platform big data push data based on the second mining template includes: Selecting the top fourth target magnitude of platform big data push data in the platform big data push data returned by each target platform big data collection task for each target user demand mining model as the basic recall platform big data push data; Determining the relevance between each target user demand mining model and the corresponding basic recall platform big data push data; Determining the relevance between the basic recall platform big data push data with a relevance higher than the second target value and the corresponding target user demand mining model; Based on the relevance, determining the top third target magnitude of platform big data push data that is most similar to the target user demand mining model as the target platform big data push data.

4. A data analysis system based on an intelligent management platform, characterized in that, Applied to an intelligent management platform for executing the method according to any one of claims 1-3, the system includes: A selection module for selecting a target user demand mining model of the first target magnitude in the target platform user demand mining task, where each target user demand mining model is used to perform platform user demand mining on the data analysis based on the intelligent management platform in the target platform user demand mining task, and the target user demand mining model is a pre-labeled key user demand mining model; A push module for performing platform big data push on each target user demand mining model based on the target platform big data collection task of the second target magnitude, and selecting target platform big data push data of the third target magnitude from the platform big data push data based on the second mining template; An acquisition module for acquiring the platform big data push keywords in all the target platform big data push data; A determination module, configured to determine the relevance between the user requirement mining graph of the target platform user requirement mining task and the keyword features of the platform big data push keywords, and determine the platform big data push data with a relevance greater than a first target value as the platform big data push data matching the target platform user requirement mining task, where the higher the relevance, the higher the matching degree between the target platform user requirement mining task and the platform big data push keywords.

5. The data analysis system based on the intelligent management platform according to claim 4, characterized in that, The method for selecting a target user requirement mining model of a first target magnitude in the target platform user requirement mining task includes: Performing divide-and-conquer on the target platform user requirement mining task based on a first mining template, and obtaining the target user requirement mining model of the first target magnitude from all the user requirement mining models obtained after performing divide-and-conquer on the target platform user requirement mining task based on the first mining template according to a set instruction.

6. The data analysis system based on the intelligent management platform according to claim 4, wherein The method for selecting target platform big data push data of a third target magnitude from the platform big data push data based on a second mining template includes: Selecting the top fourth target magnitude of the platform big data push data in the platform big data push data returned by each target platform big data collection task for each target user requirement mining model as the basic recall platform big data push data; Determining the relevance between each target user requirement mining model and the corresponding basic recall platform big data push data; Determining the relevance between the basic recall platform big data push data with a relevance higher than a second target value and the corresponding target user requirement mining model; Based on the relevance, determining the top third target magnitude of the platform big data push data most similar to the target user requirement mining model as the target platform big data push data.

7. The data analysis system based on the intelligent management platform according to claim 4, characterized in that, The method for determining the relevance between the target platform user requirement mining task and the platform big data push keywords includes: Performing divide-and-conquer on the target platform user requirement mining task based on a third mining template, and determining the relevance of all the obtained platform big data collection tasks in the platform big data push keywords respectively, and for each platform big data push keyword, taking the proportion of the platform big data collection tasks with a relevance greater than a third target value in the platform big data push keyword among all the platform big data collection tasks obtained after performing divide-and-conquer on the target platform user requirement mining task based on the third mining template as the relevance of the target platform big data push data.

8. The data analysis system based on the intelligent management platform according to claim 7, wherein The method for determining the relevance of all the obtained platform big data collection tasks in the platform big data push keywords respectively includes: Classify all platform big data collection tasks obtained after dividing the target platform user requirement mining task based on the third mining template, and respectively set task analysis modules based on the number of task nodes included in all the platform big data collection tasks, and thereby perform matching between all the platform big data collection tasks and the platform big data push keywords for the task analysis modules; In each match, if the ratio of the task nodes displayed in the task analysis module in the platform big data push keywords that match the task nodes in the target platform user requirement mining task corresponding to the task analysis module is not less than the fifth target value, determine the second weight ratio of the span between the task nodes that are matched and associated in the target platform user requirement mining task to the total number of task nodes, and use the largest weight ratio in the second weight ratios as the association degree of the platform big data collection task corresponding to the task analysis module, where the total number of task nodes is the total number of task nodes in the task analysis module minus one.

Images