Evaluation Method and Device for Equipment System Contribution Degree

Abstract

The present application proposes a method and device for evaluating the contribution degree of an equipment system, which relates to the field of evaluating the contribution rate of a weapon equipment system. In the present application, each equipment is taken as a node, and the information exchange channels between the equipments are taken as links to obtain the structure model corresponding to the equipment system; based on the input-output relationship under the operating state of the equipment system, the input-output relationship between the nodes, and the timing relationship of the node events of the nodes, an event flow response model is constructed; based on the structure model and the event flow response model, the system input data, node event data, and system output data under multiple operations of the equipment system are obtained, and the equipment system is associated and mined to obtain the contribution degree data of each node. The present application comprehensively considers the support degree of node events for the output of the equipment system and the degree of meeting the task-oriented requirements, and more accurately and comprehensively evaluates the contribution rate of the activity events of each node to the system.

Description

Technical Field

[0001] This application relates to the technical fields of weapon and equipment simulation and the evaluation technology of the contribution rate of weapon and equipment systems, and particularly relates to an evaluation method and device for the contribution degree of an equipment system. Background Art

[0002] The contribution rate of weapon and equipment systems is a concept proposed by our military in recent years, which has important guiding significance for equipment construction and is an important support for the construction, development, and application of equipment systems. Due to the complexity of the composition and relationships of weapon and equipment systems, it is difficult to evaluate the contribution rates of the various components in weapon and equipment systems, and it is difficult to achieve comprehensive and accurate evaluation using a single method. Summary of the Invention

[0003] This application aims to solve at least one of the technical problems in the related art to some extent.

[0004] To this end, one object of this application is to propose an evaluation method for the contribution degree of an equipment system. By taking each piece of equipment as a node and the information exchange channels between the equipment as links, a structural model corresponding to the equipment system is obtained; based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the nodes, an event flow response model is constructed; based on the structural model and the event flow response model, the system input data, node event data, and system output data under multiple operations of the equipment system are obtained, where the node event data includes the actual input data and actual output data of each node event; based on the system input data, node event data, and system output data, association mining is performed on the equipment system to obtain the contribution degree data of each node.

[0005] This application comprehensively considers the support degree of node events for the output of the equipment system and the degree of meeting the task-oriented requirements, and more accurately and comprehensively evaluates the contribution rates of the activity events of each node to the system.

[0006] The second object of this application is to propose an evaluation device for the contribution degree of an equipment system.

[0007] The third object of this application is to propose an electronic device.

[0008] The fourth object of this application is to propose a non-transitory computer-readable storage medium.

[0009] The fifth object of this application is to propose a computer program product.

[0010] To achieve the above object, an embodiment of the first aspect of the present application provides an evaluation method for the contribution degree of an equipment system, including: taking each equipment as a node, taking the information exchange channels between the equipments as links, and obtaining the structure model corresponding to the equipment system; constructing an event flow response model based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the node; based on the structure model and the event flow response model, obtaining the system input data, node event data, and system output data under multiple runs of the equipment system, where the node event data includes the actual input data and actual output data of each node event; and performing association mining on the equipment system based on the system input data, node event data, and system output data to obtain the contribution degree data of each node.

[0011] The present application comprehensively considers the support degree of node events for the output of the equipment system and the degree of meeting the task-oriented requirements, and more accurately and comprehensively evaluates the contribution rate of the activity events of each node to the system.

[0012] To achieve the above object, an embodiment of the second aspect of the present application provides an evaluation device for the contribution degree of an equipment system, including: a first acquisition module for taking each equipment as a node, taking the information exchange channels between the equipments as links, and obtaining the structure model corresponding to the equipment system; a construction module for constructing an event flow response model based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the node; a second acquisition module for obtaining the system input data, node event data, and system output data under multiple runs of the equipment system based on the structure model and the event flow response model, where the node event data includes the actual input data and actual output data of each node event; and a mining module for performing association mining on the equipment system based on the system input data, node event data, and system output data to obtain the contribution degree data of each node.

[0013] To achieve the above object, an embodiment of the third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the evaluation method for the contribution degree of the equipment system as in the embodiment of the first aspect of the present application.

[0014] To achieve the above object, an embodiment of the fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to implement the evaluation method for the contribution degree of the equipment system as in the embodiment of the first aspect of the present application.

[0015] To achieve the above object, an embodiment of the fifth aspect of the present application provides a computer program product, including a computer program which, when executed by a processor, implements the method for evaluating the contribution degree of an equipment system according to the embodiment of the first aspect of the present application. Description of the Drawings

[0016] Figure 1 FIG. is an exemplary diagram of a method for evaluating the contribution degree of an equipment system according to an embodiment of the present application.

[0017] Figure 2 FIG. is an exemplary diagram of obtaining a structural model corresponding to an equipment system according to an embodiment of the present application.

[0018] Figure 3 FIG. is an exemplary diagram of obtaining a first frequent item set according to a candidate 1-item set according to an embodiment of the present application.

[0019] Figure 4 FIG. is an exemplary diagram of obtaining a second frequent item set according to a candidate 2-item set according to an embodiment of the present application.

[0020] Figure 5 FIG. is an exemplary diagram of obtaining an average ability weight vector of each node according to an embodiment of the present application.

[0021] Figure 6 FIG. is an overall flowchart of a method for evaluating the contribution degree of an equipment system according to an embodiment of the present application.

[0022] Figure 7 FIG. is an exemplary diagram of an apparatus for evaluating the contribution degree of an equipment system according to an embodiment of the present application.

[0023] Figure 8 FIG. is a schematic diagram of an electronic device according to an embodiment of the present application. Detailed Embodiments

[0024] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0025] Figure 1 FIG. is an exemplary implementation manner of a method for evaluating the contribution degree of an equipment system proposed by the present application. As Figure 1 shown, the method for evaluating the contribution degree of the equipment system includes the following steps:

[0026] S101: Regarding each equipment as a node and the information exchange channels between the equipments as links, obtain the structural model corresponding to the equipment system.

[0027] The test of the contribution rate of the equipment system is an important part of the combat test in the system test. The contribution rate of the equipment system refers to the size of the contribution of a single piece of equipment to the overall indicators of the system (such as the combat effectiveness or operational efficiency of the system) in the composition of the weapon equipment system or combat system, in accordance with the overall goals and operating rules of the system, that is, the size of the promotion effect of the addition of this equipment on the increase of the combat effectiveness (performance / capability) of the system.

[0028] In this application, for the convenience of understanding, each piece of equipment with independent and complete functions is regarded as a node, and the information exchange channel between any piece of equipment and other equipment is regarded as a link. Then the equipment system is a complex network composed of multiple nodes and multiple links; the node event refers to the business activity of the node, which is the complete process of the node responding to the input data and outputting the processing result.

[0029] Furthermore, the system generally refers to the whole formed by a certain range or similar things combined according to a certain order and internal connection, which is a complex system composed of different systems. The method proposed in this application can also be applied to other systems under corresponding conditions, such as the natural ecological system, the financial system of human society, etc.

[0030] Regarding each piece of equipment as a node and the information exchange channel between the equipment as a link, the structural model corresponding to the equipment system is obtained. Optionally, the attributes of each node in the equipment system and the link relationship between each node and other nodes can be analyzed to generate the structural model corresponding to the equipment system.

[0031] S102, based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the nodes, construct an event flow response model.

[0032] Each equipment system contains multiple nodes. When the equipment system runs, the first-level node responds to the input data of the equipment system and outputs the response result to the next-level node; the next-level node receives the output data of the previous-level node and generates a response, and outputs the result to the next-next-level node. After passing through multiple levels of nodes, the output data of the equipment system is formed at the last node. This complete process can be regarded as an event sequence.

[0033] Based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of node events of the node, an event flow response model is constructed. Exemplarily, Table 1 is an exemplary schematic diagram for modeling the composition attributes of the equipment system. As shown in Table 1, the event flow response model of the equipment system includes system input features, the attributes of each node event, and system output characteristics. Among them, the system input features include the system operation start time, operation input data, and the starting node; the attributes of each node event include the node event start time, the node event subject, the node event end time, the node event end time, the node body output, and the object of action; the system output characteristics include the operation end time and the system output data.

[0034] Table 1 Event Flow Response Model of Equipment System

[0035]

[0036] S103. Based on the structure model and the event flow response model, obtain the system input data, node event data, and system output data under multiple runs of the equipment system. Among them, the node event data includes the actual input data and actual output data of each node event.

[0037] Perform multiple runs on the equipment system to obtain the system input data, node event data, and system output data under multiple runs of the equipment system. Among them, the node event data includes the actual input data and actual output data of each node event.

[0038] Exemplarily, Table 2 is a schematic diagram of node events and system input-output data. As shown in Table 2, assume that there are a total of M pieces of system input data and N nodes in the equipment system. Among them, the M pieces of system input data may be the same or different. Exemplarily, this system can be used to simulate the analysis of Minimum Shift Keying (MSK) signals. Then, input data 1 can be an MSK signal, node 1 event 1 is that node 1 performs signal processing operations, node 2 event 1 is that node 2 performs signal analysis operations, node 3 event 1 is that node 3 performs intelligence extraction operations, etc. System output 1 can be represented by a vector to indicate the result of the system operation.

[0039] Table 2 Set of Node Events and System Input-Output Data Items

[0040]

[0041] S104. Based on the system input data, node event data, and system output data, perform association mining on the equipment system to obtain the contribution degree data of each node.

[0042] Based on the system input data, node event data, and system output data obtained above, perform association mining on the equipment system to obtain the contribution degree data of each node.

[0043] Optionally, an association analysis algorithm can be used to mine the frequent itemsets between node events and system output data and calculate the support degree of the frequent itemsets. According to the support degree, calculate the conditional probability of the system output event occurring under the condition that the node event occurs, and combine the conditional probability of the system output event occurring under the condition that the node event occurs with the ability weight of the corresponding node to obtain the contribution degree data of each node.

[0044] This application proposes a method for evaluating the contribution degree of an equipment system. By taking each equipment as a node and the information exchange channels between the equipments as links, a corresponding structure model of the equipment system is obtained; based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the node, an event flow response model is constructed; based on the structure model and the event flow response model, the system input data, node event data, and system output data under multiple operations of the equipment system are obtained, where the node event data includes the actual input data and actual output data of each node event; based on the system input data, the node event data, and the system output data, perform association mining on the equipment system to obtain the contribution degree data of each node. This application comprehensively considers the support degree of node events for the output of the equipment system and the degree of meeting the requirements of the task, and more accurately and comprehensively evaluates the contribution rate of the activity events of each node to the system.

[0045] Figure 2 is an exemplary implementation manner of a method for evaluating the contribution degree of an equipment system proposed in this application, as Figure 2 shown. Based on the above embodiments, obtaining the corresponding structure model of the equipment system includes the following steps:

[0046] S201, generate a composition attribute modeling corresponding to the equipment system based on the system attributes of the equipment system and the node attributes of each node.

[0047] Analyze the system attributes of the equipment system, the composition node attributes, and the relationship characteristics between each node to generate a composition attribute modeling corresponding to the equipment system.

[0048] Exemplarily, Table 3 is an exemplary schematic diagram of the composition attribute modeling of the equipment system. As shown in Table 3, the system attributes of the equipment system describe the basic information of the equipment system, including the system name, system structure type, and number of system composition nodes; the node attributes describe the basic information of each node in the system, including the node name, node number, node function, link relationship between the node and other nodes, node input, node response, and node output.

[0049] Table 3 Composition Attribute Modeling of Equipment System

[0050]

[0051] S202. Generate the corresponding relationship attribute modeling of the equipment system based on the links between each node.

[0052] Construct the relationship feature attributes between nodes in the equipment system according to the links between each node in the equipment system, and generate the corresponding relationship attribute modeling of the equipment system.

[0053] Exemplarily, Table 4 is an exemplary schematic diagram of the relationship attribute modeling of the equipment system. As shown in Table 4, the relationship feature attributes between nodes include the node numbers at both ends of the link, the link number, the link type (unidirectional transmission link / bidirectional transmission link), and the link transmission direction.

[0054] Table 4 Relationship Attribute Modeling of Equipment System

[0055]

[0056] S203. Generate the corresponding structure model of the equipment system based on the composition attribute modeling and the relationship attribute modeling.

[0057] Fuse the obtained composition attribute modeling and relationship attribute modeling above to generate the corresponding structure model of the equipment system.

[0058] Figure 3 This is an exemplary implementation manner of an evaluation method for the contribution degree of an equipment system proposed in this application. As Figure 3 shown, based on the above embodiments, perform association mining on the equipment system based on system input data, node event data, and system output data, including the following steps:

[0059] S301. Based on the node event data, obtain all candidate 1-itemsets corresponding to the node events.

[0060] Optionally, select the Apriori algorithm to perform association mining on the equipment system. Among them, the Apriori algorithm is an algorithm for mining association rules through frequent item sets. This algorithm can not only discover frequent item sets but also mine the association rules between items, and can use support and confidence to quantify frequent item sets and association rules respectively. Its core idea is to mine frequent item sets through two stages: candidate set generation and downward closure test of episodes.

[0061] Exemplarily, use In m to represent system input m, E nm to represent node n event m, and use O mDenote the system output as m, then the data in Table 2 can be expressed as:

[0062]

[0063] Among them, the node event matrix The system output matrix

[0064] Based on the node event matrix, obtain the candidate 1-itemsets corresponding to all node events. Among them, the candidate 1-itemsets can be expressed as {E 11}, {E 12}... {E NM}, etc. It should be noted that in the total data under multiple runs of the equipment system, if the same event occurs at the same node multiple times, according to the rules for constructing candidate 1-itemsets, there is no need to construct the candidate 1-itemset multiple times, and only one construction is required.

[0065] Exemplarily, configure the node event labels of node 1. For example, node event 1 of node 1 represents that node 1 performs signal processing, which is represented by {E 11}, and node event 2 of node 1 represents that node 1 performs image processing, which is represented by {E 12}, etc. If in the 8th set of system data, the node event of node 1 is image processing, denoted as E 12 ; if in the 99th set of system data, the node event of node 1 is still image processing, it is still denoted as E 12 . When obtaining the candidate 1-itemsets corresponding to all node events, only one {E 12} is constructed.

[0066] S302. Obtain the first occurrence count of each candidate 1-itemset.

[0067] Obtain the occurrence count of each candidate 1-itemset in the above node event matrix as the first occurrence count, and denote the first occurrence count as k E , for example, if the occurrence count of {E 12} is 66, then the first occurrence count of the candidate 1-itemset {E 12} is 66.

[0068] S303. Based on the first occurrence count of each candidate 1-itemset, the total number of system input data, and the total number of nodes, obtain the first support degree of each candidate 1-itemset.

[0069] Obtain the first product N×M of the total number of system input data M and the total number of nodes N, and divide the first occurrence count of each candidate 1-itemset by the first product to obtain the first support degree of each candidate 1-itemset. Denote the first support degree as rs E, then the formula for obtaining the first support of each candidate 1-itemset is:

[0070]

[0071] It should be noted that the first support of the candidate 1-itemset can be used as the occurrence probability P(E) of the node event E corresponding to the candidate 1-itemset in the entire node event data.

[0072] S304, obtain the event types corresponding to all candidate 1-itemsets, and generate a support set corresponding to all node events based on the event types and the first support of each candidate 1-itemset.

[0073] Analyze all candidate 1-itemsets, obtain the event types corresponding to all candidate 1-itemsets, and generate a support set corresponding to all node events based on the event types and the first support of each candidate 1-itemset. Exemplarily, if there are a total of L types of event types, which are [signal processing, signal analysis,..., intelligence transmission] in sequence, then the support set RS corresponding to the node events can be generated E =[rs E1 , rs E2 , …, rs EL , where rs E1 is the first support of signal processing, rs E2 is the first support of signal analysis, etc.

[0074] S305, in response to the first support of any candidate 1-itemset in the support set being greater than or equal to the first preset support threshold, use the candidate 1-itemset as the first frequent itemset.

[0075] Set a first preset support threshold, compare the first support of each candidate 1-itemset with the first preset support threshold. If the first support of a certain candidate 1-itemset is greater than or equal to the first preset support threshold, then use the candidate 1-itemset as the first frequent itemset.

[0076] Figure 4 is an exemplary implementation manner of an evaluation method for the contribution degree of an equipment system proposed in this application. As Figure 4 shown, based on the above embodiments, based on the system input data, node event data, and system output data, association mining is performed on the equipment system, and the following steps are further included:

[0077] S401, based on the node event data and the system output data, obtain candidate 2-itemsets composed of 1 node event data and 1 system output data.

[0078] According to the above node event matrix and system output matrix Obtain candidate 2-itemsets consisting of 1 node event data and 1 system output data. 1 node event - 1 system output can be represented as the following matrix:

[0079]

[0080] A single candidate 2-itemset can be respectively represented as {E 11 ,O1}, {E 21 ,O1}... {E NM ,O M}.

[0081] S402. Obtain the second occurrence count of each candidate 2-itemset.

[0082] Obtain the occurrence count of each candidate 2-itemset in the above 1 node event - 1 system output matrix as the second occurrence count, and denote the second occurrence count as k Eo For example, if the occurrence count of {E 11 ,O1} is 22, then the second occurrence count of the candidate 2-itemset {E 11 ,O1} is 22.

[0083] S403. Based on the second occurrence count of each candidate 2-itemset, the total number of system input data, and the total number of nodes, obtain the second support of each candidate 2-itemset.

[0084] Obtain the first product N×M of the total number of system input data M and the total number of nodes N, and divide the second occurrence count of each candidate 2-itemset by the first product to obtain the second support of each candidate 2-itemset. Denote the second support as rs EO Then the formula for obtaining the second support of each candidate 2-itemset is:[[]]

[0085]

[0086] It should be noted that the second support of a candidate 2-itemset can be used as the probability P(EO) that the corresponding node event E and system output O of the candidate 2-itemset occur simultaneously.

[0087] S404. In response to the second support of any candidate 2-itemset being greater than or equal to the second preset support threshold, regard the candidate 2-itemset as a second frequent itemset.

[0088] Set a second preset support threshold, compare the second support of each candidate 2-itemset with the second preset support threshold. If the second support of a certain candidate 2-itemset is greater than or equal to the second preset support threshold, then regard the candidate 2-itemset as a second frequent itemset.

[0089] Further, define the support degree RS of a node event for the equipment system as the probability P(O|E) of the system output O after the occurrence of the node event E, and denote the probability P(O|E) of the system output O after the occurrence of the node event E as the third support degree of the node event for the equipment system. Obtain the first support degree P(E) of each first frequent item set, and obtain the second support degree P(EO) of each second frequent item set. Since P(E) represents the occurrence probability of the node event E in the entire node event data, and P(EO) represents the probability of the simultaneous occurrence of the node event E and the system output O, then according to the first support degree P(E) and the second support degree P(EO), the formula for obtaining the third support degree of each node corresponding to the node event for the equipment system is:

[0090]

[0091] Sort the third support degrees from largest to smallest, obtain the largest third support degree corresponding to each node, arrange the N third support degrees in the order of the nodes, and obtain the third support degree vector RS = [rs1, rs2,..., rs N .

[0092] Figure 5 is an exemplary implementation manner of an evaluation method for the contribution degree of an equipment system proposed in this application. As Figure 5 shown, based on the above embodiments, based on the system input data, node event data, and system output data, perform association mining on the equipment system, and further include the following steps:

[0093] S501, calculate the expected output data of each node according to the performance parameters of the node.

[0094] Obtain the performance parameters of each node. The performance parameters of the equipment are a vector composed of multiple dimensional parameters. Assume that the dimension of the equipment performance parameters is F (F is a constant), and the equipment performance parameter vector is C = (c1, c2,..., c F ).

[0095] Let the system run for the mth time, and the input data of node n is in m , and calculate the expected output data of each node as outa m .

[0096] S502, obtain the actual output data of each node under any operating state of the equipment system.

[0097] Let the system run for the mth time, and the input data of node n is in m , and obtain the actual output data outb of each node under any operating state of the equipment system m .

[0098] S503. Divide the actual output data of each node by the corresponding expected output data to determine the ability weight of each node in any operating state of the equipment system.

[0099] The range of the ability weight of each node to process events is 0 to 1, which refers to the inherent ability manifestation degree of the node during the operation of the system. A weight of 1 indicates that the node contributes the highest ability level to the system, a weight less than 1 indicates that the ability level contributed by the node to the system is lower than its inherent ability expected value, and the lower the weight, the lower the ability contribution level of the node.

[0100] Divide the actual output data outb of each node m by the corresponding expected output data outa m to determine the ability weight cn of node n in any operating state of the equipment system. The calculation formula for determining the ability weight cn of node n in any operating state of the equipment system is:

[0101]

[0102] S504. Determine multiple ability weights of each node in multiple operating states of the equipment system.

[0103] Assume that the equipment system operates M times, then determine M ability weights of node n obtained respectively in M operating states of the equipment system.

[0104] S505. Perform weighted averaging on multiple ability weights to obtain the average ability weight of each node.

[0105] Assume that the equipment system operates M times, then according to the M system operation conditions, perform weighted averaging on the M ability weights of node n to obtain the average ability weight of each node. The calculation formula for obtaining the average ability weight cn of node n is:

[0106]

[0107] S506. Arrange the average ability weights of all nodes in the order of the nodes to obtain the average ability weight vector.

[0108] Arrange the average ability weights of all nodes in the order of the nodes to obtain the average ability weight vector CN = (c1, c2,..., cn).

[0109] Further, the occurrence probability of the system output under the node event condition can be regarded as the influence degree of the node event on the system output, and the ability weight of the node describes the ability contribution degree of the node to the system. Generally speaking, the higher the inherent ability of the node, the higher the expected contribution degree to the system. However, when the actual ability contribution degree of the node is lower than the expected value, its contribution degree evaluation will decrease accordingly. Based on the analysis of the influence degree of the node event on the system, this application introduces the node ability weight to realize the comprehensive evaluation of the system contribution rate. Multiply the value corresponding to each node in the third support vector RS = [rs1, rs2,..., rs N by the value corresponding to each node in the average ability weight vector CN = (c1, c2,..., cn). Exemplarily, the contribution rate CR(n) of node n in the system to the system is:

[0110] CR(n) = rs N × cn

[0111] Figure 6 is an exemplary implementation manner of an evaluation method for the contribution degree of an equipment system proposed in this application. As Figure 6 shown, this evaluation method for the contribution degree of the equipment system includes the following steps:

[0112] S601, generate a composition attribute model corresponding to the equipment system.

[0113] S602, generate a relationship attribute model corresponding to the equipment system.

[0114] S603, based on the composition attribute model and the relationship attribute model, generate a structure model corresponding to the equipment system.

[0115] Regarding the implementation manners of steps S601 to S603, the implementation manners in the various embodiments of this application can be adopted, and details will not be elaborated here.

[0116] S604, based on the input-output relationship under the operation state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the nodes, construct an event flow response model.

[0117] S605, based on the structure model and the event flow response model, obtain system input data, node event data, and system output data.

[0118] S606, obtain the candidate 1-itemsets corresponding to all node events.

[0119] S607, obtain the first occurrence times of each candidate 1-itemset.

[0120] S608, obtain the first support degree of each candidate 1-itemset.

[0121] S609. Mine the first frequent item set from the candidate 1-item sets.

[0122] S610. Obtain the first support degree of each first frequent item set.

[0123] Regarding the implementation manners of steps S606 to S610, the implementation manners in the various embodiments of this application can be adopted, and details are not described herein again.

[0124] S611. Obtain the candidate 2-item sets composed of 1 node event data and 1 system output data.

[0125] S612. Obtain the second occurrence times of each candidate 2-item set.

[0126] S613. Obtain the second support degree of each candidate 2-item set.

[0127] S614. Mine the second frequent item set from the candidate 2-item sets.

[0128] S615. Obtain the second support degree of each second frequent item set.

[0129] S616. Obtain the third support degree of each node corresponding node event pair to the equipment system.

[0130] S617. Obtain the third support degree vector of the node event pair to the equipment system.

[0131] Regarding the implementation manners of steps S611 to S617, the implementation manners in the various embodiments of this application can be adopted, and details are not described herein again.

[0132] S618. Obtain the expected output data of each node.

[0133] S619. Obtain the actual output data of each node.

[0134] S620. Determine the single ability weight of each node.

[0135] S621. Obtain the average ability weight of each node.

[0136] S622. Obtain the average ability weight vector corresponding to all nodes.

[0137] Regarding the implementation manners of steps S618 to S622, the implementation manners in the various embodiments of this application can be adopted, and details are not described herein again.

[0138] S623. Multiply the value of each node in the third support degree vector by the corresponding value in the average ability weight vector to determine the contribution degree data of each node.

[0139] The present application proposes a method for evaluating the contribution degree of an equipment system. By taking each equipment as a node and the information exchange channels between the equipments as links, a structure model corresponding to the equipment system is obtained; based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the node, an event flow response model is constructed; based on the structure model and the event flow response model, the system input data, node event data, and system output data under multiple operations of the equipment system are obtained, where the node event data includes the actual input data and actual output data of each node event; based on the system input data, the node event data, and the system output data, an association mining is performed on the equipment system to obtain the contribution degree data of each node. The present application comprehensively considers the support degree of node events for the output of the equipment system and the degree of meeting the task-oriented requirements, and more accurately and comprehensively evaluates the contribution rate of the activity events of each node to the system.

[0140] Figure 7 is a schematic diagram of an evaluation device for the contribution degree of an equipment system proposed in the present application, as Figure 7 shown. The evaluation device 700 for the contribution degree of the equipment system includes a first acquisition module 71, a construction module 72, a second acquisition module 73, and a mining module 74, where:

[0141] The first acquisition module 71 is configured to take each equipment as a node and the information exchange channels between the equipments as links, and obtain a structure model corresponding to the equipment system.

[0142] The construction module 72 is configured to construct an event flow response model based on the input-output relationship under the operating state of the equipment system, the input-output relationship between each node, and the timing relationship of the node events of the node.

[0143] The second acquisition module 73 is configured to obtain the system input data, node event data, and system output data under multiple operations of the equipment system based on the structure model and the event flow response model, where the node event data includes the actual input data and actual output data of each node event.

[0144] The mining module 74 is configured to perform an association mining on the equipment system based on the system input data, node event data, and system output data, and obtain the contribution degree data of each node.

[0145] Furthermore, the first acquisition module 71 is further configured to: generate a composition attribute modeling corresponding to the equipment system based on the system attributes of the equipment system and the node attributes of each node; generate a relationship attribute modeling corresponding to the equipment system based on the links between each node; and generate a structure model corresponding to the equipment system based on the composition attribute modeling and the relationship attribute modeling.

[0146] Further, the mining module 74 is further configured to: based on the node event data, obtain candidate 1-itemsets corresponding to all node events; obtain the first occurrence count of each candidate 1-itemset; based on the first occurrence count of each candidate 1-itemset, the total number of system input data, and the total number of nodes, obtain the first support degree of each candidate 1-itemset; obtain the event types corresponding to all candidate 1-itemsets, and based on the event types and the first support degree of each candidate 1-itemset, generate a support degree set corresponding to all node events.

[0147] Further, the mining module 74 is further configured to: in response to the first support degree of any candidate 1-itemset in the support degree set being greater than or equal to the first preset support degree threshold, use the candidate 1-itemset as the first frequent itemset.

[0148] Further, the mining module 74 is further configured to: obtain the first product of the total number of system input data and the total number of nodes; divide the first occurrence count of each candidate 1-itemset by the first product to obtain the first support degree of each candidate 1-itemset.

[0149] Further, the mining module 74 is further configured to: based on the node event data and the system output data, obtain candidate 2-itemsets composed of 1 node event data and 1 system output data; obtain the second occurrence count of each candidate 2-itemset; based on the second occurrence count of each candidate 2-itemset, the total number of system input data, and the total number of nodes, obtain the second support degree of each candidate 2-itemset; in response to the second support degree of any candidate 2-itemset being greater than or equal to the second preset support degree threshold, use the candidate 2-itemset as the second frequent itemset.

[0150] Further, the mining module 74 is further configured to: obtain the first product of the total number of system input data and the total number of nodes; divide the second occurrence count of each candidate 2-itemset by the first product to obtain the second support degree of each candidate 2-itemset.

[0151] Further, the mining module 74 is further configured to: obtain the first support degree of each first frequent itemset; obtain the second support degree of each second frequent itemset; based on the first support degree and the second support degree, obtain the third support degree of the node event pair of each node for the equipment system; arrange the multiple third support degrees in the order of the nodes to obtain the third support degree vector.

[0152] Further, the mining module 74 is further configured to: calculate the expected output data of each node according to the performance parameters of the nodes; obtain the actual output data of each node in any equipment system operating state; divide the actual output data of each node by the corresponding expected output data to determine the ability weight of each node in any equipment system operating state.

[0153] Furthermore, the mining module 74 is further configured to: determine multiple ability weights of each node under multiple operation states of the equipment system; perform weighted averaging on the multiple ability weights to obtain the average ability weight of each node.

[0154] Furthermore, the mining module 74 is further configured to: arrange the average ability weights of all nodes in the order of the nodes to obtain an average ability weight vector.

[0155] Furthermore, the mining module 74 is further configured to: multiply the value of each node in the third support degree vector by the corresponding value in the average ability weight vector to determine the contribution degree data of each node.

[0156] To implement the above embodiments, an electronic device 800 is further proposed in an embodiment of the present application. As Figure 8 shown, the electronic device 800 includes: a processor 801 and a memory 802 communicatively connected to the processor. The memory 802 stores instructions executable by at least one processor. The instructions are executed by at least one processor 801 to implement the evaluation method for the contribution degree of the equipment system as shown in the above embodiments.

[0157] To implement the above embodiments, a non-transitory computer-readable storage medium storing computer instructions is further proposed in an embodiment of the present application, wherein the computer instructions are used to cause a computer to implement the evaluation method for the contribution degree of the equipment system as shown in the above embodiments.

[0158] To implement the above embodiments, a computer program product is further proposed in an embodiment of the present application, including a computer program which, when executed by a processor, implements the evaluation method for the contribution degree of the equipment system as shown in the above embodiments.

[0159] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present application.

[0160] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of this application, "a plurality of" means two or more unless specifically defined otherwise.

[0161] In the description of this specification, the description with reference to terms such as "an embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0162] Although the embodiments of this application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting this application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. An evaluation method for the contribution degree of an equipment system, characterized in that, Including: Regarding each piece of equipment as a node and the information exchange channels between the pieces of equipment as links, obtaining the structure model corresponding to the equipment system; Based on the input-output relationship under the operating state of the equipment system, the input-output relationships between the nodes, and the timing relationships of the node events of the nodes, constructing an event flow response model; Based on the structure model and the event flow response model, obtaining the system input data, node event data, and system output data during multiple operations of the equipment system, where the node event data includes the actual input data and actual output data of each node event; Based on the node event data, obtaining the candidate 1-itemsets corresponding to all the node events, and obtaining the first occurrence count of each candidate 1-itemset; Based on the first occurrence count of each candidate 1-itemset, the total number of the system input data, and the total number of the nodes, obtaining the first support degree of each candidate 1-itemset; Obtaining the event types corresponding to all the candidate 1-itemsets, and generating a support degree set corresponding to all the node events based on the event types and the first support degree of each candidate 1-itemset; In response to the first support degree of any candidate 1-itemset in the support degree set being greater than or equal to a first preset support degree threshold, regarding the candidate 1-itemset as a first frequent itemset; Based on the node event data and the system output data, obtaining candidate 2-itemsets composed of 1 piece of node event data and 1 piece of system output data, and obtaining the second occurrence count of each candidate 2-itemset; Based on the second occurrence count of each candidate 2-itemset, the total number of the system input data, and the total number of the nodes, obtaining the second support degree of each candidate 2-itemset; In response to the second support degree of any candidate 2-itemset being greater than or equal to a second preset support degree threshold, regarding the candidate 2-itemset as a second frequent itemset; Obtaining the third support degree of each node corresponding to the node event for the equipment system according to the first support degree of each first frequent itemset and the second support degree of each second frequent itemset; Obtaining the maximum third support degree corresponding to each node and arranging them in the order of the nodes to obtain a third support degree vector; Obtaining the average ability weight of each node, and arranging the average ability weights of all the nodes in the order of the nodes to obtain an average ability weight vector; Multiplying the value of each node in the third support degree vector by the corresponding value in the average ability weight vector to obtain the contribution degree data of each node.

2. The method according to claim 1, characterized in that, The obtaining of the structure model corresponding to the equipment system includes: Based on the system attributes of the equipment system and the node attributes of each node, generating a composition attribute modeling corresponding to the equipment system; Based on the links between the nodes, generating a relationship attribute modeling corresponding to the equipment system; Based on the composition attribute modeling and the relationship attribute modeling, generating the structure model corresponding to the equipment system.

3. The method according to claim 1, wherein Obtaining the first support degree of each candidate 1-itemset based on the first occurrence times of each candidate 1-itemset, the total number of the system input data, and the total number of the nodes includes: Obtaining a first product of the total number of the system input data and the total number of the nodes; Dividing the first occurrence times of each candidate 1-itemset by the first product to obtain the first support degree of each candidate 1-itemset.

4. The method according to claim 1, characterized in that, Obtaining the second support degree of each candidate 2-itemset based on the second occurrence times of each candidate 2-itemset, the total number of the system input data, and the total number of the nodes includes: Obtaining a first product of the total number of the system input data and the total number of the nodes; Dividing the second occurrence times of each candidate 2-itemset by the first product to obtain the second support degree of each candidate 2-itemset.

5. The method according to any one of claims 1-4, characterized in that, The obtaining of the average ability weight of each node includes: Calculating the expected output data of each node according to the performance parameters of the node; Obtaining the actual output data of each node in any operation state of the equipment system; Dividing the actual output data of each node by the corresponding expected output data to determine the ability weight of each node in any operation state of the equipment system; Determining multiple ability weights of each node in multiple operation states of the equipment system; Performing a weighted average on the multiple ability weights to obtain the average ability weight of each node.

6. An evaluation device for the contribution degree of an equipment system, characterized in that Including: A first obtaining module, configured to use each piece of equipment as a node and use the information exchange channels between the pieces of equipment as links to obtain the structure model corresponding to the equipment system; A constructing module, configured to construct an event flow response model based on the input-output relationship in the operation state of the equipment system, the input-output relationship between the nodes, and the timing relationship of the node events of the nodes; A second obtaining module, configured to obtain the system input data, the node event data, and the system output data in multiple operations of the equipment system based on the structure model and the event flow response model, where the node event data includes the actual input data and the actual output data of each node event; A mining module, configured to obtain all candidate 1-itemsets corresponding to the node event data based on the node event data, and obtain the first occurrence count of each candidate 1-itemset; obtain the first support degree of each candidate 1-itemset based on the first occurrence count of each candidate 1-itemset, the total number of the system input data, and the total number of the nodes; obtain the event types corresponding to all the candidate 1-itemsets, and generate a support degree set corresponding to all the node events based on the event types and the first support degree of each candidate 1-itemset; in response to the first support degree of any candidate 1-itemset in the support degree set being greater than or equal to a first preset support degree threshold, use the candidate 1-itemset as the first frequent itemset; obtain candidate 2-itemsets composed of one piece of the node event data and one piece of the system output data based on the node event data and the system output data, and obtain the second occurrence count of each candidate 2-itemset; obtain the second support degree of each candidate 2-itemset based on the second occurrence count of each candidate 2-itemset, the total number of the system input data, and the total number of the nodes; in response to the second support degree of any candidate 2-itemset being greater than or equal to a second preset support degree threshold, use the candidate 2-itemset as the second frequent itemset; obtain the third support degree of each node corresponding to the node event for the equipment system according to the first support degree of each first frequent itemset and the second support degree of each second frequent itemset; obtain the maximum third support degree corresponding to each node and arrange them in the order of the nodes to obtain a third support degree vector; obtain the average ability weight of each node, and arrange the average ability weights of all the nodes in the order of the nodes to obtain an average ability weight vector; multiply the value of each node in the third support degree vector by the corresponding value in the average ability weight vector to obtain the contribution degree data of each node.

7. The device according to claim 6, characterized in that, The first obtaining module is further configured to: generate a composition attribute model corresponding to the equipment system based on the system attributes of the equipment system and the node attributes of each node; generate a relationship attribute model corresponding to the equipment system based on the links between each pair of nodes; generate a structure model corresponding to the equipment system based on the composition attribute model and the relationship attribute model.

8. The device according to claim 6, characterized in that The mining module is further configured to: obtain a first product of the total number of the system input data and the total number of the nodes; divide the first occurrence count of each candidate 1-itemset by the first product to obtain the first support degree of each candidate 1-itemset.

9. The device according to claim 6, characterized in that The mining module is further configured to: obtain a first product of the total number of the system input data and the total number of the nodes; divide the second occurrence count of each candidate 2-itemset by the first product to obtain the second support degree of each candidate 2-itemset.

10. The device according to any one of claims 6-9, characterized in that The mining module is further configured to: Calculating the expected output data of each of the nodes based on the performance parameters of the nodes; Obtaining the actual output data of each of the nodes in any one of the operating states of the equipment system; Dividing the actual output data of each of the nodes by the corresponding expected output data to determine the ability weight of each of the nodes in any one of the operating states of the equipment system; Determining multiple ability weights of each of the nodes in multiple operating states of the equipment system; Performing a weighted average on the multiple ability weights to obtain the average ability weight of each of the nodes.

11. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

13. A computer program product, comprising a computer program, wherein the computer program implements the method according to any one of claims 1-5 when executed by a processor.

Images