Node importance degree determination method and device based on data relevance and medium

Abstract

The invention provides a node importance degree determination method and device based on data relevance and a medium, and the method comprises the steps: obtaining an influence value of each node feature according to the influence value of each node feature when each data node executes a plurality of types of historical tasks in a first historical time period and a second historical time period; determining a total influence value vector and a node influence value vector corresponding to each data node, thereby determining a first importance degree and a second importance degree corresponding to each node feature of each data node; and according to the matching degree of each node influence value vector and the total influence value vector, processing the first importance degree and the second importance degree corresponding to each node feature to obtain the target importance degree corresponding to each node feature of each data node, and by considering the specificity of different node features of different data nodes, the target importance degree corresponding to each node feature of each data node is obtained. Therefore, the accuracy of the task execution efficiency of the subsequently obtained data nodes is improved through the determined target importance degree.

Description

Technical Field

[0001] This invention relates to the field of data processing, and in particular to a method, device, and medium for determining the importance of nodes based on data correlation. Background Technology

[0002] Different data nodes will have different efficiency when processing the same data, depending on their own node characteristics (such as processor performance, number of processing threads, etc.). Therefore, it is necessary to statistically analyze the data processing efficiency of several data nodes in the same processing system in order to allocate the data nodes reasonably.

[0003] Current methods for analyzing the processing efficiency of data nodes are based on node characteristics, and the importance (such as weight) assigned to each node characteristic is the same. They do not consider the impact of different node characteristics on the processing of different types of tasks. Therefore, the accuracy of the data processing efficiency of data nodes determined by this importance is low. Summary of the Invention

[0004] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0005] According to one aspect of this application, a method for determining the importance of nodes based on data correlation is provided, comprising:

[0006] Step S100: Every preset fixed time interval, determine the total influence value vector based on the influence value of each node feature of each data node on each type of historical task when each data node performs several types of historical tasks in the first historical time interval; the end time of the first historical time interval is the current time, and the length of the first historical time interval is greater than the preset fixed time interval.

[0007] Step S200: Based on the influence value of each node feature of each data node on each type of historical task when each data node performs several types of historical tasks in the second historical time period, determine the node influence value vector corresponding to each data node; the end time of the second historical time period is the current time, and the length of the second historical time period is a preset fixed duration.

[0008] Step S300: Based on the influence value corresponding to each node feature in the total influence value vector and the influence value corresponding to each node feature in each node influence value vector, determine the first importance and second importance of each node feature of each data node.

[0009] Step S400: Based on the matching degree between the influence value vector of each node and the total influence value vector, process the first importance and second importance of each node feature to obtain the target importance of each node feature of each data node.

[0010] In one exemplary embodiment of this application, step S100 includes:

[0011] Step S110: Obtain the influence value of each node's features on the historical tasks of each type when each data node performs several types of historical tasks within the first historical time period, so as to obtain a list set of first task influence values ​​Y1, Y2, ..., Y for several data nodes. i ,...,Y j Where i = 1, 2, ..., j; j is the number of data nodes; Y i This is a list of the first task impact values ​​corresponding to the i-th data node within the first historical time period;

[0012] Y i =(Y i1 ,Y i2 ,...,Y im ,...,Y in ); m = 1, 2, ..., n; n is the number of node features corresponding to the data node; Y im This is a list of task impact values ​​corresponding to the feature of the m-th node of the i-th data node within the first historical time period.

[0013] Y im =(Y im1 ,Y im2 ,...,Y ime ,...,Y imf ); e = 1, 2, ..., f; f is the number of historical task groups; Y ime When the i-th data node performs the e-th type of historical task in the first historical time period, the influence value of the m-th node feature on the e-th type of historical task is given.

[0014] Step S120: Based on the first task influence value list set corresponding to each data node, determine the first feature influence value list X1, X2, ..., X for each data node. i ,...,X j ; where X i This is a list of feature influence values ​​corresponding to the i-th data node;

[0015] X i =(X i1 ,X i2 ,...,X im ,...,X in); X im X is the feature influence value corresponding to the feature of the m-th node of the i-th data node; im =(∑ e＝1 f Y ime ) / f;

[0016] Step S130: Based on the list of first feature influence values ​​corresponding to each data node, determine the total influence value vector C = (C1, C2, ..., C...). m ,...,C n ); where C m =(∑ i＝1 j X im ) / j.

[0017] In one exemplary embodiment of this application, step S200 includes:

[0018] Step S210: Obtain the influence value of each node feature of each data node on the type of historical task when each data node performs several types of historical tasks within the second historical time period, so as to obtain a list set D1, D2, ..., D corresponding to several data nodes of the second task influence value. i ,...,D j ; where D i This is a list of the second task impact values ​​corresponding to the i-th data node within the second historical time period;

[0019] D i =(D i1 D i2 ,...,D im ,...,D in );D im This is a list of task impact values ​​corresponding to the m-th node feature of the i-th data node within the second historical time period.

[0020] D im =(D im1 D im2 ,...,D ime ,...,D imf );D ime When the i-th data node performs the e-th type of historical task in the second historical time period, the influence value of the m-th node feature on the e-th type of historical task is given.

[0021] Step S220: Based on the second task influence value list set corresponding to each data node, determine the node influence value vector E1, E2, ..., E1 for each data node. i ,...,E j Among them, E iE is the node influence value vector corresponding to the i-th data node; i =(E i1 E i2 ,...,E im ,...,E in ); E im =(∑ e＝1 f D ime ) / f.

[0022] In one exemplary embodiment of this application, step S300 includes:

[0023] Step S310: According to the preset indicator importance determination method, process the total influence value vector C to obtain the first importance list F = (F1, F2, ..., F...). m ,...,F n ); where F m The first importance level corresponding to the m-th node feature of each data node;

[0024] Step S320: Based on the preset indicator importance determination method, determine the node influence value vector E corresponding to the i-th data node. i Process the data to obtain the second importance list G corresponding to the i-th data node. i =(G i1 G i2 ,...,G im ,...,G in ); where G im This represents the second importance level corresponding to the feature of the m-th node of the i-th data node.

[0025] In one exemplary embodiment of this application, step S400 includes:

[0026] Step S410: Based on the matching degree between the influence value vector of each node and the total influence value vector, determine the first adjustment coefficient of the first importance and the second adjustment coefficient of the second importance corresponding to each node feature of each data node;

[0027] Step S420: Determine the target importance of each node feature of each data node based on the first importance, first adjustment coefficient, second importance, and second adjustment coefficient corresponding to each node feature of each data node.

[0028] In one exemplary embodiment of this application, step S410 includes:

[0029] Step S411: Perform matching degree processing on the influence value vector of each node and the total influence value vector to obtain the matching degree list L = (L1, L2, ..., L...).i ,...,L j ); where L i Let E be the node influence value vector corresponding to the i-th data node. i The degree of matching with the total influence value vector C;

[0030] Step S412, if L i If the match is less than or equal to a preset matching threshold, then the first adjustment coefficient p corresponding to each node feature of the i-th data node is determined. i Second adjustment coefficient q i Both are 0.5.

[0031] In one exemplary embodiment of this application, step S411 further includes:

[0032] Step S413, if L i If the matching degree is greater than the preset threshold, then determine the second adjustment coefficient q corresponding to each node feature of the i-th data node. i 0.5-(0.5×(L) i -MIN(L)) / (MAX(L)-MIN(L))); where MIN() is the preset minimum value determination function; MAX() is the preset maximum value determination function;

[0033] Step S414: Determine the first adjustment coefficient p corresponding to each node feature of the i-th data node. i 1-q i .

[0034] In one exemplary embodiment of this application, step S420 includes:

[0035] Step S421: Determine the target importance Z corresponding to the feature of the m-th node of the i-th data node. im =p i ×F m +q i ×G im .

[0036] According to another aspect of this application, a non-transitory computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored in the storage medium, and the at least one instruction or at least one program is loaded and executed by a processor to implement the aforementioned method for determining the importance of nodes based on data association.

[0037] According to another aspect of this application, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0038] The present invention has at least the following beneficial effects:

[0039] The node importance determination method based on data correlation of the present invention, at preset predetermined time intervals, determines a total influence value vector based on the influence value of each node feature on a certain type of historical task performed by each data node in a first historical time period, and determines a node influence value vector corresponding to each data node based on the influence value of each node feature of each data node on a certain type of historical task performed by each data node in a second historical time period, and then determines the first importance and second importance corresponding to each node feature of each data node based on the influence value corresponding to each node feature in the total influence value vector and the influence value corresponding to each node feature in each node influence value vector. Based on the matching degree between the influence value vector of each node and the total influence value vector, the first and second importance levels corresponding to each node feature are processed to obtain the target importance level corresponding to each node feature of each data node. By analyzing the influence values ​​of several node features of different data nodes when executing historical tasks in the first and second historical time periods, the correlation between the influence of different node features on different types of historical tasks is analyzed to determine the specific importance level of each node feature of each data node. The specificity of different node features of different data nodes for processing the same type of task is considered to ensure that the accuracy of the task execution efficiency of the subsequently obtained data nodes is improved by using the determined target importance level. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 A flowchart of a method for determining the importance of nodes based on data correlation provided in an embodiment of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] This application proposes a method for determining the importance of nodes based on data correlation, such as... Figure 1 As shown, it includes the following steps:

[0044] Step S100: Every preset fixed time interval, determine the total influence value vector based on the influence value of each node feature of each data node on each type of historical task when each data node performs several types of historical tasks in the first historical time period.

[0045] A data node is an entity node that processes data during task execution; it can be a computer device or other data processing machine.

[0046] The node features corresponding to a data node are the characteristic information that affects the data processing when the data node is processing data, such as the number of processors, processor performance parameters, number of processing threads, and available computing power capacity of the data node. The number and type of node features of several data nodes are the same, that is, the type of node features of each data node is consistent (for example, the node features of the first data node are the number of processors, processor performance parameters, number of processing threads, and available computing power capacity in sequence, the node features of the second data node are also the number of processors, processor performance parameters, number of processing threads, and available computing power capacity, and so on), so as to ensure data consistency when analyzing several node features of the data node in the future.

[0047] The end time of the first historical time period is the current time, and the length of the first historical time period is greater than the preset fixed duration.

[0048] Historical tasks are divided into several categories based on task type or classification rules preset by staff. After each data node completes a category of historical tasks, staff will score the impact status of each node feature in the execution of that category of historical tasks based on the execution efficiency or execution status of each node feature. The impact value is determined by the staff according to the preset rules. The larger the impact value, the greater the impact of the corresponding node feature on the execution efficiency of that category of historical tasks (the impact includes both positive and negative impacts, and the specific impact selection is determined by the staff).

[0049] Furthermore, step S100 includes steps S110-S130:

[0050] Step S110: Obtain the influence value of each node's features on the historical tasks of each type when each data node performs several types of historical tasks within the first historical time period, so as to obtain a list set of first task influence values ​​Y1, Y2, ..., Y for several data nodes. i ,...,Y j Where i = 1, 2, ..., j; j is the number of data nodes; Y i This is a list of the first task impact values ​​corresponding to the i-th data node within the first historical time period;

[0051] Y i =(Y i1 ,Y i2 ,...,Y im ,...,Y in ); m = 1, 2, ..., n; n is the number of node features corresponding to the data node; Y im This is a list of task impact values ​​corresponding to the feature of the m-th node of the i-th data node within the first historical time period.

[0052] Y im =(Y im1 ,Y im2 ,...,Y ime ,...,Y imf ); e = 1, 2, ..., f; f is the number of historical task groups; Y ime When the i-th data node performs the e-th type of historical task in the first historical time period, the influence value of the m-th node feature on the e-th type of historical task is given.

[0053] Step S120: Based on the first task influence value list set corresponding to each data node, determine the first feature influence value list X1, X2, ..., X for each data node. i ,...,X j ; where X i This is a list of feature influence values ​​corresponding to the i-th data node;

[0054] X i =(X i1 ,X i2 ,...,X im ,...,X in ); X im X is the feature influence value corresponding to the feature of the m-th node of the i-th data node; im =(∑ e＝1 f Y ime ) / f;

[0055] Step S130: Based on the list of first feature influence values ​​corresponding to each data node, determine the total influence value vector C = (C1, C2, ..., C...). m ,...,C n ); where C m =(∑ i＝1 j X im ) / j.

[0056] Step S200: Based on the influence value of each node feature of each data node on each type of historical task when each data node performs several types of historical tasks in the second historical time period, determine the node influence value vector corresponding to each data node.

[0057] The end time of the second historical time period is the current time, and the length of the second historical time period is a preset fixed duration.

[0058] Furthermore, step S200 includes steps S210-S220:

[0059] Step S210: Obtain the influence value of each node feature of each data node on the type of historical task when each data node performs several types of historical tasks within the second historical time period, so as to obtain a list set D1, D2, ..., D corresponding to several data nodes of the second task influence value. i ,...,D j ; where D i This is a list of the second task impact values ​​corresponding to the i-th data node within the second historical time period;

[0060] D i =(D i1 D i2 ,...,D im ,...,D in );D im This is a list of task impact values ​​corresponding to the m-th node feature of the i-th data node within the second historical time period.

[0061] D im =(D im1 D im2 ,...,D ime ,...,D imf );D ime When the i-th data node performs the e-th type of historical task in the second historical time period, the influence value of the m-th node feature on the e-th type of historical task is given.

[0062] Step S220: Based on the second task influence value list set corresponding to each data node, determine the node influence value vector E1, E2, ..., E1 for each data node. i ,...,E j Among them, E i E is the node influence value vector corresponding to the i-th data node; i =(E i1 E i2 ,...,E im ,...,E in ); E im =(∑ e＝1f D ime ) / f.

[0063] Step S300: Based on the influence value corresponding to each node feature in the total influence value vector and the influence value corresponding to each node feature in each node influence value vector, determine the first importance and second importance of each node feature of each data node.

[0064] The first and second importance levels represent the degree of influence of the corresponding node features in the first historical time period and the degree of influence in the second historical time period, respectively.

[0065] Furthermore, step S300 includes steps S310-S320:

[0066] Step S310: According to the preset indicator importance determination method, process the total influence value vector C to obtain the first importance list F = (F1, F2, ..., F...). m ,...,F n ); where F m The first importance level corresponding to the m-th node feature of each data node;

[0067] Step S320: Based on the preset indicator importance determination method, determine the node influence value vector E corresponding to the i-th data node. i Process the data to obtain the second importance list G corresponding to the i-th data node. i =(G i1 G i2 ,...,G im ,...,G in ); where G im This represents the second importance level corresponding to the feature of the m-th node of the i-th data node.

[0068] The preset method for determining the importance of indicators can be determined by staff according to preset rules (such as staff defining a mapping table, which includes the mapping relationship between several influence values ​​and importance), or it can be an existing method for determining the importance of indicators (such as the statistical average method or the coefficient of variation method).

[0069] Step S400: Based on the matching degree between the influence value vector of each node and the total influence value vector, process the first importance and second importance of each node feature to obtain the target importance of each node feature of each data node.

[0070] After determining the first and second importance of node features, in order to further improve the accuracy of the target importance weight and reflect the specificity of data nodes, it is necessary to further process the first and second importance of each node feature based on the matching degree between the influence value vector of each node and the total influence value vector, so as to reasonably allocate the proportion of the first and second importance in the target importance.

[0071] Furthermore, step S400 includes steps S410-S420:

[0072] Step S410: Based on the matching degree between the influence value vector of each node and the total influence value vector, determine the first adjustment coefficient of the first importance and the second adjustment coefficient of the second importance corresponding to each node feature of each data node;

[0073] Step S420: Determine the target importance of each node feature of each data node based on the first importance, first adjustment coefficient, second importance, and second adjustment coefficient corresponding to each node feature of each data node.

[0074] Step S410 includes steps S411-S414:

[0075] Step S411: Perform matching degree processing on the influence value vector of each node and the total influence value vector to obtain the matching degree list L = (L1, L2, ..., L...). i ,...,L j ); where L i Let E be the node influence value vector corresponding to the i-th data node. i The degree of matching with the total influence value vector C;

[0076] Step S412, if L i If the match is less than or equal to a preset matching threshold, then the first adjustment coefficient p corresponding to each node feature of the i-th data node is determined. i Second adjustment coefficient q i Both are 0.5;

[0077] Step S413, if L i If the matching degree is greater than the preset threshold, then determine the second adjustment coefficient q corresponding to each node feature of the i-th data node. i 0.5-(0.5×(L) i -MIN(L)) / (MAX(L)-MIN(L)));

[0078] Wherein, MIN() is the preset function for determining the minimum value; MAX() is the preset function for determining the maximum value;

[0079] Step S414: Determine the first adjustment coefficient p corresponding to each node feature of the i-th data node. i 1-q i .

[0080] Step S420 includes step S421:

[0081] Step S421: Determine the target importance Z corresponding to the feature of the m-th node of the i-th data node. im =p i ×F m +q i ×G im .

[0082] Furthermore, this application can also be applied to the analysis of agricultural science and technology innovation capabilities. Specifically, when applied to the field of agricultural science and technology innovation, the data nodes of this application can be countries (such as the member states of the Shanghai Cooperation Organisation), and the node features can be agricultural science and technology innovation level parameters for each country (such as basic innovation capabilities, economic level, agricultural land area, agricultural water resources, agricultural capital investment, etc.). The historical tasks are the production tasks of crops planted within a historical time period (such as the production task of soybean planting). Since the demand for the same crop planted in each country is different at different points in time, and different planting standards also affect the maturity of different crops, when it is necessary to plant the same crop in each country... When crops are in use (i.e., when several data nodes receive the same task to be processed), the planting demand for the same crop varies in different countries at the same time point. Therefore, it is necessary to analyze the crops planted and the planting demand in each country during historical periods to determine the planting efficiency or maturity of the same crop in several countries at the corresponding time points. In determining the planting efficiency, it is necessary to reflect the specificity of each data node and analyze the degree of influence of specific node characteristics on task execution to make the obtained planting efficiency more accurate. The planting efficiency can be calculated by multiplying the target importance of each node feature of each data node by the efficiency value of that node feature when executing the corresponding historical task.

[0083] The node importance determination method based on data correlation of the present invention, at preset predetermined time intervals, determines a total influence value vector based on the influence value of each node feature on a certain type of historical task performed by each data node in a first historical time period, and determines a node influence value vector corresponding to each data node based on the influence value of each node feature of each data node on a certain type of historical task performed by each data node in a second historical time period, and then determines the first importance and second importance corresponding to each node feature of each data node based on the influence value corresponding to each node feature in the total influence value vector and the influence value corresponding to each node feature in each node influence value vector. Based on the matching degree between the influence value vector of each node and the total influence value vector, the first and second importance levels corresponding to each node feature are processed to obtain the target importance level corresponding to each node feature of each data node. By analyzing the influence values ​​of several node features of different data nodes when executing historical tasks in the first and second historical time periods, the correlation between the influence of different node features on different types of historical tasks is analyzed to determine the specific importance level of each node feature of each data node. The specificity of different node features of different data nodes for processing the same type of task is considered to ensure that the accuracy of the task execution efficiency of the subsequently obtained data nodes is improved by using the determined target importance level.

[0084] Embodiments of the present invention also provide a computer program product including program code, which, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above in various exemplary embodiments of the present invention.

[0085] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0086] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0087] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0088] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: entirely hardware implementations, entirely software implementations (including firmware, microcode, etc.), or implementations combining hardware and software aspects, collectively referred to herein as “circuits,” “modules,” or “systems.”

[0089] An electronic device according to this embodiment of the invention. The electronic device is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the invention.

[0090] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0091] The storage device stores program code that can be executed by the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of the present invention.

[0092] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0093] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0094] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0095] Electronic devices can also communicate with one or more external devices (such as keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable users to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (such as routers, modems, etc.). This communication can be performed through input / output (I / O) interfaces. Furthermore, electronic devices can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via network adapters.

[0096] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the invention may also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the invention described in the "Exemplary Methods" section of this specification.

[0097] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0098] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0099] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0100] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0101] Furthermore, the above-described figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above-described figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0102] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0103] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for determining the importance of nodes based on data correlation, characterized in that, include: Step S100: Every preset fixed time interval, based on the influence value of each node feature of each data node on each type of historical task when each data node performs several types of historical tasks within the first historical time interval, determine the total influence value vector; the end time of the first historical time interval is the current time, and the length of the first historical time interval is greater than the preset fixed time interval; the total influence value vector includes the influence value of each node feature on each type of historical task within the first historical time interval. Step S200: Based on the influence value of each node feature of each data node on each type of historical task when each data node performs several types of historical tasks within the second historical time period, determine the node influence value vector corresponding to each data node; the end time of the second historical time period is the current time, and the length of the second historical time period is a preset predetermined duration; the node influence value vector includes the influence value of each node feature of the corresponding data node on each type of historical task within the second historical time period. Step S300: Based on the influence value corresponding to each node feature in the total influence value vector and the influence value corresponding to each node feature in each node influence value vector, determine the first importance and second importance of each node feature of each data node. Step S400: Based on the matching degree between each node influence value vector and the total influence value vector, process the first importance degree and the second importance degree corresponding to each node feature to obtain the target importance degree corresponding to each node feature of each data node.

2. The method according to claim 1, characterized in that, Step S100 includes: Step S110: Obtain the influence value of each node feature on the historical task of each type when each data node performs several types of historical tasks within the first historical time period, so as to obtain a list set Y1, Y2, ..., Y corresponding to several data nodes of the first task influence value. i ,...,Y j Where i = 1, 2, ..., j; j is the number of data nodes; Y i For the i-th data node, there is a list of first task impact values ​​corresponding to the first historical time period; Y i =(Y i1 ,Y i2 ,...,Y im ,...,Y in ); m = 1, 2, ..., n; n is the number of node features corresponding to the data node; Y im This is a list of task impact values ​​corresponding to the m-th node feature of the i-th data node within the first historical time period. Y im =(Y im1 ,Y im2 ,...,Y ime ,...,Y imf ); e = 1, 2, ..., f; f is the number of class groups for the historical task; Y ime When the i-th data node performs the e-type historical task in the first historical time period, the influence value of the m-th node feature on the e-type historical task; Step S120: Based on the first task influence value list set corresponding to each data node, determine the first feature influence value list X1, X2, ..., X... for each data node. i ,...,X j ; where X i This is a list of feature influence values ​​corresponding to the i-th data node; X i =(X i1 ,X i2 ,...,X im ,...,X in ); X im X is the feature influence value corresponding to the m-th node feature of the i-th data node; im =(∑ e＝1 f Y ime ) / f; Step S130: Based on the list of first feature influence values ​​corresponding to each data node, determine the total influence value vector C = (C1, C2, ..., C...). m ,...,C n ); where C m =(∑ i＝1 j X im ) / j.

3. The method according to claim 2, characterized in that, Step S200 includes: Step S210: Obtain the influence value of each node feature of each data node on the type of historical task when each data node performs several types of historical tasks within the second historical time period, so as to obtain a list set D1, D2, ..., D corresponding to several data nodes of the second task influence value. i ,...,D j ; where D i This is a list of the second task impact values ​​corresponding to the i-th data node within the second historical time period; D i =(D i1 D i2 ,...,D im ,...,D in );D im This is a list of task impact values ​​corresponding to the m-th node feature of the i-th data node within the second historical time period; D im =(D im1 D im2 ,...,D ime ,...,D imf );D ime When the i-th data node performs the e-type historical task in the second historical time period, the influence value of the m-th node feature on the e-type historical task; Step S220: Based on the second task influence value list set corresponding to each data node, determine the node influence value vector E1, E2, ..., E1 for each data node. i ,...,E j Among them, E i E is the node influence value vector corresponding to the i-th data node; i =(E i1 E i2 ,...,E im ,...,E in ); E im =(∑ e＝1 f D ime ) / f.

4. The method according to claim 3, characterized in that, Step S300 includes: Step S310: According to the preset indicator importance determination method, process the total influence value vector C to obtain the first importance list F = (F1, F2, ..., F...). m ,...,F n ); where F m The first importance level corresponding to the m-th node feature of each data node; Step S320: According to the preset indicator importance determination method, determine the node influence value vector E corresponding to the i-th data node. i Processing is performed to obtain the second importance list G corresponding to the i-th data node. i =(G i1 G i2 ,...,G im ,...,G in ); where G im The second importance level corresponds to the m-th node feature of the i-th data node.

5. The method according to claim 4, characterized in that, Step S400 includes: Step S410: Based on the matching degree between each node influence value vector and the total influence value vector, determine the first adjustment coefficient of the first importance and the second adjustment coefficient of the second importance corresponding to each node feature of each data node; Step S420: Determine the target importance of each node feature of each data node based on the first importance, the first adjustment coefficient, the second importance, and the second adjustment coefficient corresponding to each node feature of each data node.

6. The method according to claim 5, characterized in that, Step S410 includes: Step S411: Perform matching degree processing on each node influence value vector and the total influence value vector to obtain a matching degree list L = (L1, L2, ..., L...). i ,...,L j ); where L i The node influence value vector E corresponding to the i-th data node. i The degree of matching with the total influence value vector C; Step S412, if L i If the match is less than or equal to a preset matching threshold, then the first adjustment coefficient p corresponding to each node feature of the i-th data node is determined. i Second adjustment coefficient q i Both are 0.

5.

7. The method according to claim 6, characterized in that, Step S411 further includes: Step S413, if L i If the matching degree is greater than a preset threshold, then the second adjustment coefficient q corresponding to each node feature of the i-th data node is determined. i 0.5-(0.5×(L) i -MIN(L)) / (MAX(L)-MIN(L))); where MIN() is the preset minimum value determination function; MAX() is the preset maximum value determination function; Step S414: Determine the first adjustment coefficient p corresponding to each node feature of the i-th data node. i 1-q i .

8. The method according to claim 7, characterized in that, Step S420 includes: Step S421: Determine the target importance Z corresponding to the m-th node feature of the i-th data node. im =p i ×F m +q i ×G im .

9. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the method as described in any one of claims 1-8.

10. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 9.

Images