CN116823510A - Node influence measuring method, device, equipment and storage medium - Google Patents
Node influence measuring method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116823510A CN116823510A CN202310630256.XA CN202310630256A CN116823510A CN 116823510 A CN116823510 A CN 116823510A CN 202310630256 A CN202310630256 A CN 202310630256A CN 116823510 A CN116823510 A CN 116823510A
- Authority
- CN
- China
- Prior art keywords
- node
- network
- determining
- influence
- network node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000005259 measurement Methods 0.000 claims abstract description 123
- 238000005303 weighing Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 description 15
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 238000000691 measurement method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method, a device, equipment and a storage medium for measuring influence of nodes. The method comprises the following steps: acquiring node attribute information of each network node in a network to be measured; determining the target node weight of each network node according to the node attribute information and the node association relation between each network node; determining a target node metric value of each network node according to the node association relationship and the target node weight; and carrying out node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result. The technical scheme of the embodiment of the invention improves the accuracy of the node influence force.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for measuring influence of a node.
Background
With the rapid development of information technology, social circles are gradually expanded, and social network media become an important channel for information propagation. The users can pay additional attention to the information of interest, and the users influence each other in a direct or indirect way in the social network information transmission process. Influence concepts have been applied to the propagation of various social network information, and therefore, it is critical to measure the influence of user network nodes in a social network.
At present, the existing technical scheme generally adopts a node measurement mode such as a centrality evaluation algorithm, an intermediate centrality evaluation algorithm or a PageRank (webpage sorting) algorithm and the like to measure the influence of user network nodes. However, the existing method for measuring the influence of the node does not consider the node characteristics, so that the influence is lower in accuracy of the measured result.
Disclosure of Invention
The invention provides a point influence measuring method, a point influence measuring device, point influence measuring equipment and a storage medium, so as to improve the accuracy of node influence measurement.
According to an aspect of the present invention, there is provided a node influence measurement method, the method comprising:
acquiring node attribute information of each network node in a network to be measured;
determining the target node weight of each network node according to the node attribute information and the node association relation between each network node;
determining a target node metric value of each network node according to the node association relationship and the target node weight;
and carrying out node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result.
Optionally, the determining the target node weight of each network node according to the node attribute information and the node association relationship between each network node includes:
Determining a first node weight of each network node according to the node attribute information and the node association relation between each network node;
determining a second node weight of each network node according to the node association relation among the network nodes;
and determining the target node weight of each network node according to the first node weight and the second node weight.
According to the technical scheme, the weight influence of the node attribute characteristics of the network node and the weight influence of the access degree characteristics of the network node are comprehensively considered in the process of determining the weight of the target node, so that the accuracy of determining the weight of the target node is improved, and the accuracy of determining the measurement value of the target node is improved.
Optionally, the determining the first node weight of each network node according to the node attribute information and the node association relationship between each network node includes:
determining a first node influence index of each network node according to the node attribute information;
according to the node association relation of each network node, determining a first association network node corresponding to each network node respectively;
Determining a second node influence index of the first associated network node corresponding to each network node according to the node attribute information of the first associated network node;
and determining the first node weight of each network node according to the first node influence index and the second node influence index of the corresponding network node.
According to the technical scheme, in the process of determining the first node weight, the influence of other network nodes on the self network node is comprehensively considered, and the node attribute characteristics of the self network node are considered, so that the accuracy of determining the first node weight is improved, and the accuracy of determining the target node weight of the network node is improved.
Optionally, the determining the second node weight of each network node according to the node association relationship between the network nodes includes:
determining a first node degree value of each network node according to the node association relation; the method comprises the steps of,
determining a second node output value of a second associated network node corresponding to each network node respectively;
and determining the second node weight of each network node according to the first node degree value and the second node degree value of the corresponding network node.
According to the technical scheme, the accuracy of determining the second node weight is improved by comprehensively considering the outbound characteristics of the own network node and the outbound characteristics of the associated network node with the directed relation with the own network node in the process of determining the second node weight, so that the accuracy of determining the target node weight of the network node is improved.
Optionally, the determining, according to the node association relationship and the target node weight, a target node metric value of each network node includes:
determining second associated network nodes corresponding to the network nodes respectively according to the node association relation;
and determining a target node metric value of each network node based on a preset iteration parameter according to the target node weight and the node initial parameter value of the second associated network node.
According to the technical scheme, the second associated network nodes corresponding to the network nodes are determined according to the node association relation, the target node metric value of each network node is determined based on the preset iteration parameter according to the target node weight and the node initial parameter value of the second associated network node, and the accuracy of determining the target node metric value is improved, so that the accuracy of determining the subsequent influence on the node metric result is improved. In addition, in the determining process of the target node metric value, the node with high network node weight and the node with low network node weight can be separated more quickly due to different target node weights of the network nodes, so that the convergence speed is increased, and the determining efficiency of the target node metric value is higher.
Optionally, after performing node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result, the method further includes:
acquiring at least one influence weighing model;
determining reference node measurement values of each network node in the network to be measured under each influence and measurement model respectively;
according to the reference node measurement value of the corresponding influence and measurement model, carrying out node influence and measurement on each network node to obtain a reference influence and measurement result under each influence and measurement model;
determining a result correlation coefficient between a node influence weighing result and each reference influence weighing result respectively;
and determining whether to update the iteration parameters according to each result correlation coefficient.
According to the technical scheme, the reference influence intensity measurement results of the network nodes under the influence intensity measurement models are determined, whether iteration parameters are updated or not is determined according to the result correlation coefficients between the node influence intensity measurement results and the reference influence intensity measurement results, and whether the iteration parameters are updated or not is accurately determined, so that the target node measurement values can be optimized continuously, and the accuracy of determining the node influence intensity measurement results is improved.
Optionally, the determining whether to update the iteration parameter according to each of the result correlation coefficients includes:
determining target correlation coefficients meeting preset correlation judgment conditions in the result correlation coefficients;
determining the coefficient quantity of the target correlation coefficient;
and determining whether to update the iteration parameters according to the coefficient quantity and a preset coefficient quantity threshold value.
According to the technical scheme, the target correlation coefficient meeting the preset correlation judgment condition in the correlation coefficients of the results is determined, and whether the iteration parameters are updated or not is determined according to the coefficient number of the target correlation coefficient and the preset coefficient number threshold, so that the accurate judgment on whether the iteration parameters are updated or not is improved, the accuracy of determining the target node measurement value is improved, and the accuracy of determining the node influence force measurement result is improved.
According to another aspect of the present invention, there is provided a node influence weighing apparatus, the apparatus comprising:
the attribute information acquisition module is used for acquiring node attribute information of each network node in the network to be measured;
the target weight determining module is used for determining the target node weight of each network node according to the node attribute information and the node association relation between each network node;
The target node measurement value determining module is used for determining target node measurement values of the network nodes according to the node association relation and the target node weight;
and the measurement result determining module is used for measuring the influence of the nodes on each network node according to the target node measurement value to obtain a node influence measurement result.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the node impact measurement method according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement a node influence measure method according to any of the embodiments of the present invention when executed.
The technical scheme of the embodiment of the invention obtains the node attribute information of each network node in the network to be measured; determining the target node weight of each network node according to the node attribute information and the node association relation between each network node; determining a target node metric value of each network node according to the node association relationship and the target node weight; and carrying out node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result. According to the technical scheme, node attribute information and node association relations are comprehensively considered in the process of determining the weight of the target nodes, so that the weight of the target nodes of each determined network node is not completely the same, and the difference of the network nodes is fully represented; the target node metric value of each network node is determined through the node association relation and the target node weight, and the accuracy of determining the target node metric value is improved, so that the accuracy of determining the influence on the node metric result is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for measuring influence of a node according to a first embodiment of the invention;
FIG. 2 is a flow chart of a method for measuring influence of a node according to a second embodiment of the invention;
FIG. 3 is a flow chart of a method for measuring influence of nodes according to a third embodiment of the invention;
fig. 4 is a schematic structural diagram of a node influence measuring device according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device implementing a node influence measuring method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for measuring node influence in a social network according to an embodiment of the present invention, where the method may be performed by a node influence measuring device, and the node influence measuring device may be implemented in hardware and/or software, and the node influence measuring device may be configured in an electronic device. As shown in fig. 1, the method includes:
s110, acquiring node attribute information of each network node in the network to be measured.
The network to be measured can be a network to be subjected to node influence measurement, for example, the network to be measured can be a social network. The network node may be a node constituting a network to be measured, for example, if the network to be measured is a social network, the corresponding network node may be a user node.
Wherein the node attribute information is used to describe node characteristics of the network node. For example, if the network to be measured is a social network and the network node is a user node, the corresponding node attribute information may include at least one of a user attention number, a user rating number, a user endorsement number, and the like.
It should be noted that, because of the node difference of the network nodes in the network to be measured, the obtained node attribute information of the network nodes is different. The method is characterized in that the obtained node attribute information of different network nodes has the same information characteristics and different values corresponding to the information characteristics. For example, the information feature of the node attribute information may be the number of user attention, the number of user rating, the number of user endorsements, and the like. If the obtained information features of the node attribute information of the network node a are the user attention number and the user attention number, the obtained information features of the node attribute information of the other network nodes except the network node a are the user attention number and the user attention number. Accordingly, the number of user interests and the number of user interests corresponding to different network nodes are different, and the values of the user interests and the number of user interests may be the same or different, and the values of the user interests and the number of user interests are specifically related to the user characteristics corresponding to the network nodes.
S120, determining the target node weight of each network node according to the node attribute information and the node association relation between each network node.
The node association relationship between the network nodes may be a directional node pointing relationship between the network nodes.
In the conventional method of determining the node influence vector result, the same node weight is generally set for each network node. However, in a real scenario, different network nodes have different node characteristics, and setting the same node weights all cannot exhibit node differences between the different network nodes. Therefore, according to actual requirements, different target node weights are given to different network nodes by combining node characteristics in a real scene.
The method comprises the steps of obtaining historical node attribute information and historical node association relation of each network node in a historical period, performing model training on a preset first network model by adopting the historical node attribute information and the historical node association relation, and obtaining a weight determination network model after training is completed. The weight determination network model is used for determining node weights of the network nodes. And inputting the acquired node attribute information and the node association relation between the network nodes into a weight determination network model to obtain the target node weights respectively corresponding to the network nodes.
S130, determining a target node metric value of each network node according to the node association relation and the target node weight.
The method comprises the steps of obtaining a history node association relation and a history target node weight determined in a history period, and performing model training on a preset second network model by adopting the history node association relation and the history target node weight to obtain an influence quantity network model after training is completed. The impact metric network model is used to determine node metric values for the network nodes. And inputting the determined node association relation and the target node weight of each network node into the influence degree network model to obtain the target node metric value of each network node.
And S140, carrying out node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result.
For example, the metric values of the target nodes corresponding to the network nodes can be ranked, and the higher the ranking is, namely the larger the impact of the network nodes with the larger the metric values of the target nodes is; the later the ranking, i.e., the smaller the target node metric value, the less impact the network node has. The metrics of each network node may be ranked as node impact strength metric results.
The technical scheme of the embodiment of the invention obtains the node attribute information of each network node in the network to be measured; determining the target node weight of each network node according to the node attribute information and the node association relation between each network node; determining a target node metric value of each network node according to the node association relationship and the target node weight; and carrying out node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result. According to the technical scheme, node attribute information and node association relations are comprehensively considered in the process of determining the weight of the target nodes, so that the weight of the target nodes of each determined network node is not completely the same, and the difference of the network nodes is fully represented; the target node metric value of each network node is determined through the node association relation and the target node weight, and the accuracy of determining the target node metric value is improved, so that the accuracy of determining the influence on the node metric result is improved.
Example two
Fig. 2 is a flowchart of a method for measuring influence of a node according to a second embodiment of the present invention, where the method is optimized and improved based on the above technical solutions.
Further, the step of determining the target node weight of each network node according to the node attribute information and the node association relation between the network nodes is thinned into the step of determining the first node weight of each network node according to the node attribute information and the node association relation between the network nodes; determining second node weights of the network nodes according to the node association relations among the network nodes; and determining the target node weight of each network node according to the first node weight and the second node weight. To perfect the determination of the target node weight of each network node.
Further, the step of determining the target node metric value of each network node according to the node association relationship and the target node weight is refined into the step of determining the second association network node corresponding to each network node according to the node association relationship; and determining the target node metric value of each network node based on the preset iteration parameters according to the target node weight and the node initial parameter value of the second associated network node. To perfect the determination of the target node metric value for each network node. In the embodiments of the present invention, the descriptions of other embodiments may be referred to in the portions not described in detail.
As shown in fig. 2, the method comprises the following specific steps:
s210, acquiring node attribute information of each network node in the network to be measured.
S220, determining first node weights of all network nodes according to node attribute information and node association relations among all network nodes.
Wherein the first node weight may be used to characterize node popularity of the network node, i.e. node popularity of the network node.
In an alternative embodiment, determining the first node weight of each network node according to the node attribute information and the node association relationship between each network node includes: determining a first node influence index of each network node according to the node attribute information; according to the node association relation of each network node, determining a first association network node corresponding to each network node respectively; determining second node influence indexes of the first associated network nodes corresponding to the network nodes respectively according to the node attribute information of the first associated network nodes; and determining the first node weight of each network node according to the first node influence index and the second node influence index of the corresponding network node.
Wherein the first node impact index is used to characterize the popularity or popularity of the network node. The determination of the first node influence index is related to the number of information features contained in the node attribute information and the feature value corresponding to the information feature. In addition, the first node influence index is also related to a characteristic attribute of the information characteristic. For example, if the node attribute information includes a user attention number and a user attention number, a feature attribute of the user attention number may be an attention degree feature of the network node; the characteristic attribute of the number of users' attention may be an attention degree characteristic of the network node.
For example, if the information features included in the node attribute information include information feature a, information feature B, and information feature C. The characteristic attributes of the information characteristic A and the information characteristic B are attention degree characteristics of the node; the feature attribute of the information feature C is the degree of interest feature of the node. Information characteristic A, letterThe feature values corresponding to the information feature B and the information feature C are features respectively a 、feature b And feature c . The first node influence index c is determined as follows:
in a specific embodiment, if the node attribute information includes information features that are the user attention number and the user attention number, respectively; the characteristic value corresponding to the user attention number of the network node i is concept, and the characteristic value corresponding to the user attention number is funs, so that the first node influence index c of the network node i i The following are provided:
it will be appreciated that, based on the node association relationship of each network node, an associated network node having a directional relationship with its own network node may be determined. The first associated network node may be an associated network node directed to its own network node. The determining manner of the second node influence index of the first association network node is the same as the determining manner of the first influence index, and the determining is performed based on the node attribute information, which is not described in detail in this embodiment.
Illustratively, the manner in which the first node weight M of each network node is determined according to the first node influence index and the second node influence index of the corresponding network node may be as follows:
wherein c i A first node influence index, which may represent a network node i; c j A second node influence index, which may represent a first associated network node j; n may represent the number of nodes of the first associated network node j.
The optional embodiment determines the first node weight of each network node according to the first node influence index and the second node influence index of the corresponding network node by determining the first node influence index of each network node according to the node attribute information, determining the first associated network node corresponding to each network node respectively according to the node association relation of each network node, determining the second node influence index of the first associated network node, and determining the first node weight of each network node according to the first node influence index and the second node influence index of the corresponding network node. According to the technical scheme, in the process of determining the first node weight, the influence of other network nodes on the network node is comprehensively considered, the node attribute characteristics of the network node are considered, and the accuracy of determining the first node weight is improved, so that the accuracy of determining the target node weight of the network node is improved.
S230, determining second node weights of the network nodes according to the node association relations among the network nodes.
The second node weight may reflect the actual node operation condition of the network node, and may specifically reflect the influence of the subjective factor of the network node by the node association relationship and the node access condition.
In an alternative embodiment, determining the second node weight of each network node according to the node association relationship between each network node includes: determining a first node degree value of each network node according to the node association relation; determining second node output values of second associated network nodes corresponding to the network nodes respectively; and determining the second node weight of each network node according to the first node output value and the second node output value of the corresponding network node.
It may be appreciated that, according to the node association relationship, the associated network node to which the own network node points may be determined, and the first node degree value may be the number of nodes of the associated network node to which the network node points. The second associated network node may be an associated network node to which the own network node points; the second node degree value may be the number of nodes of the associated network node to which the second associated network node itself points.
For example, the manner of determining the second node weight N of each network node according to the first node output value and the second node output value of the corresponding network node may be as follows:
wherein, a first node out-degree value representing a network node i; />A second node degree value, which may represent a second associated network node p; m may represent the number of nodes of the second associated network node p.
According to the alternative embodiment, the first node output value of each network node is determined according to the node association relation, and the second node output value of the second associated network node corresponding to each network node is determined; and determining the second node weight of each network node according to the first node output value and the second node output value of the corresponding network node. According to the technical scheme, in the process of determining the second node weight, the outbound characteristics of the network node and the outbound characteristics of the associated network node in a pointing relation with the network node are comprehensively considered, so that the accuracy of determining the second node weight is improved, and the accuracy of determining the target node weight of the network node is improved.
S240, determining the target node weight of each network node according to the first node weight and the second node weight.
For example, the sum of the weights of the first node weight and the second node weight of the respective network node may be determined as the target node weight of the respective network node.
Alternatively, the target node weight of the corresponding network node may also be determined by the weight average of the first node weight and the second node weight of the corresponding network node. Specifically, the determination manner of the weight of the target node may be as follows:
wherein M may represent a first node weight; n may represent a second node weight; omega i The target node weight of network node i may be represented.
Optionally, the target node weight of the corresponding network node may be determined according to a weight average value of the first node weight and the second node weight of the corresponding network node based on a preset weight proportion. Specifically, the determination manner of the weight of the target node may be as follows:
ω i ＝α 1 *M+α 2 *N；
wherein alpha is 1 And alpha 2 The weight ratio of the first node weight and the second node weight can be respectively represented, and the weight ratio can be specifically preset by related technicians according to actual requirements; m may represent a first node weight; n may represent a second node weight; omega i The target node weight of network node i may be represented.
S250, determining second associated network nodes corresponding to the network nodes respectively according to the node association relation.
For example, according to the node association relationship of each network node, the associated network node having a pointing relationship with the own network node can be determined; the second associated network node may be the associated network node to which the own network node points.
S260, determining a target node metric value of each network node based on a preset iteration parameter according to the target node weight and the node initial parameter value of the second associated network node.
The node initial parameter value may be preset by a related technician, for example, the node initial parameter value may be set to 1. The iteration parameter may be the iteration number of the node metric in the process of determining the target node metric, and may be preset by a related technician according to the actual requirement. The larger the iteration frequency set value is, the higher the accuracy of determining the target node metric value is, and the lower the iteration efficiency is; the smaller the iteration number set value is, the lower the accuracy of determining the target node metric value is, and the higher the iteration efficiency is. The method can comprehensively consider the accuracy of the measurement value and the iteration efficiency, and set the iteration parameters by combining the self requirements.
For example, according to the target node weight and the node initial parameter value of the second associated network node, the determining manner of the target node metric value of each network node based on the preset iteration parameter may be as follows:
wherein a is ij Can represent the pointing relationship of network node i and network node j, if network node i points to network node j, then a ij The value of (2) may be 1; if network node i does not point to network node j, then a ij The value of (2) may be 0.WL (WL) i A target node metric value representing a network node i; t can represent an iteration parameter, and the value of t is not less than 1; omega i The target node weight of network node i may be represented; n may represent the number of network nodes of the network to be scheduled. When t is 1, WL j (0) A node initial parameter value representing a second associated network node j.
And S270, performing node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result.
According to the technical scheme of the embodiment, the first node weight of each network node is determined according to the node attribute information and the node association relation among the network nodes, the second node weight of each network node is determined according to the node association relation among the network nodes, and the target node weight of each network node is determined according to the first node weight and the second node weight. According to the technical scheme, the weight influence of the node attribute characteristics of the network node and the weight influence of the access degree characteristics of the network node are comprehensively considered in the process of determining the weight of the target node, so that the accuracy of determining the weight of the target node is improved, and the accuracy of determining the measurement value of the target node is improved. According to the node association relation, the second association network nodes corresponding to the network nodes are determined, the target node metric value of each network node is determined based on the preset iteration parameters according to the target node weight and the node initial parameter value of the second association network node, and the accuracy of determining the target node metric value is improved, so that the accuracy of determining the subsequent influence on the node metric result is improved. In addition, in the determining process of the target node metric value, the node with high network node weight and the node with low network node weight can be separated more quickly due to different target node weights of the network nodes, so that the convergence speed is increased, and the determining efficiency of the target node metric value is higher.
It will be appreciated that the setting of the iteration parameters is critical, as it directly affects the accuracy and efficiency of the determination of the target node metric. In order to further improve the accuracy of determining the node influence and measurement result, the node measurement value of the network node to be measured can be further measured according to at least one preset influence and measurement model for evaluating the node measurement value, so that iteration parameters are continuously updated according to the measurement result, and the influence and measurement result of the network node is more accurate.
In an alternative embodiment, according to the target node metric value, performing node influence metric on each network node, and after obtaining the node influence metric result, further including: acquiring at least one influence weighing model; determining reference node measurement values of all network nodes in the network to be measured under all influence and measurement models respectively; according to the reference node measurement value of the corresponding influence and measurement model, carrying out node influence and measurement on each network node to obtain a reference influence and measurement result under each influence and measurement model; determining a result correlation coefficient between the node influence weighing result and each reference influence weighing result respectively; and determining whether to update the iteration parameters according to the correlation coefficients of the results.
The influence and measurement model can comprise at least one of a centrality measurement model, an intermediate centrality measurement model, a near centrality measurement model, a feature vector centrality measurement model, a PageRank measurement model, a LeaderRank (opinion leader mining algorithm) and the like.
Illustratively, the influence weighing model includes a PageRank weighing model. The manner in which the PageRank metric model determines the reference node metric value of the network node may be as follows:
wherein PR (a) may represent a reference node metric value of the network node a; t (T) i (i=1, 2,3, …, n) may represent other network nodes T pointing to network node a i Is a reference node metric value for (a); PR (T) i ) A reference node metric value that may represent other network nodes i; the initial PR value of each network node may be preset by a related technician. d can represent the probability of a user voting to a network node randomly, the value interval is 0 to 1, and the value interval can be preset by relevant technicians, for example, can be set to be 0.85; c (T) i ) May represent other network nodes T i Node output value of (2); n may represent the number of nodes of the network node.
Illustratively, the influence weighing model includes a LeaderRank weighing model. The core idea of the leader rank algorithm is to add a background node which is connected with all other network nodes in a bidirectional way in the network, so as to obtain a strong-connection network to be scheduled of n+1 network nodes. The manner in which the loaderrank metric model determines the reference node metric value of the network node may be as follows:
Wherein a is ij Can represent the pointing relationship between the network node i and the network node j if the network node i points toNetwork node j, then a ij The value of (2) may be 1; if network node i does not point to network node j, then a ij The value of (2) may be 0;a node metric value representing a network node i; i, j=1, 2,3, … …, N, n+1; LR (LR) j A reference node metric value representing a network node j; t represents the iteration number, which can be specifically preset by a related technician; n represents the number of nodes of the network node, and n+1 represents N network nodes and one background node.
Optionally, the reference node metric value may be a node metric value determined based on a centrality metric model, a node metric value determined based on an intermediate centrality metric model, a node metric value determined based on a near centrality metric model, and a node metric value determined based on a near feature vector centrality metric model.
It should be noted that, according to the reference node metric values of the corresponding impact metric model, the node impact metric is performed on each network node to obtain the reference impact metric result under each impact metric model, which may be the same as the manner in which the node impact is performed on each network node according to the target node metric value to obtain the node impact metric result, specifically, the metric value sorting is performed on the reference node metric values corresponding to each network node respectively, so as to obtain the reference impact metric result under each impact metric model, which is not described in detail in this embodiment.
Illustratively, determining a result correlation coefficient between the node influence metric result and each reference influence metric result respectively; and determining whether to update the iteration parameters according to the correlation coefficients of the results. Taking the reference influence force result of any influence force model as an example for illustration. And respectively selecting the node metric values ranked by a preset number from the node influence metric results and the reference influence metric results. For example, the node metric values of the top-ranked 20 network nodes may be selected, and the correlation between the two sets of top-ranked 20 network nodes may be calculated to obtain the correlation coefficient. The correlation coefficient is used for representing correlation between the node influence weighted result and the reference influence weighted result. And respectively determining the correlation coefficients with other influence weighing models in the mode.
After determining each correlation coefficient, it may be determined whether to update the iteration parameters based on each resulting correlation coefficient. Specifically, according to the correlation coefficient of each result, determining a coefficient mean value, and if the coefficient mean value is not greater than a preset mean value threshold, updating the iteration parameter; if the coefficient mean value is larger than the preset mean value threshold value, the iteration parameters are not required to be updated.
According to the scheme of the alternative embodiment, the reference node measurement values of all network nodes in the network to be measured under all influence and measurement models are determined; according to the reference node measurement value of the corresponding influence and measurement model, carrying out node influence and measurement on each network node to obtain a reference influence and measurement result under each influence and measurement model; determining a result correlation coefficient between the node influence weighing result and each reference influence weighing result respectively; and determining whether to update the iteration parameters according to the correlation coefficients of the results. According to the technical scheme, the reference influence intensity measurement results of the network nodes under the influence intensity measurement models are determined, whether iteration parameters are updated or not is determined according to the result correlation coefficients between the node influence intensity measurement results and the reference influence intensity measurement results, and whether the iteration parameters are updated or not is accurately determined, so that the target node measurement values can be optimized continuously, and the accuracy of determining the node influence intensity measurement results is improved.
It should be noted that, in order to further improve the accuracy of determining whether to update the iteration parameters, the condition judgment may also be performed on each result correlation coefficient.
In an alternative embodiment, determining whether to update the iteration parameters based on each resulting correlation coefficient includes: determining target correlation coefficients meeting preset correlation judgment conditions in the correlation coefficients of all results; determining the coefficient quantity of the target correlation coefficient; and determining whether to update the iteration parameters according to the coefficient quantity and a preset coefficient quantity threshold value.
The preset relevant judgment conditions can be preset by relevant technicians. For example, the preset correlation determination condition may be whether the result correlation coefficient is not smaller than a preset coefficient threshold, and if so, the corresponding result correlation coefficient is determined as the target correlation coefficient.
Illustratively, a target correlation coefficient satisfying the correlation determination condition is determined, and the number of coefficients of the target correlation coefficient is determined. If the coefficient number is larger than a preset coefficient number threshold, updating of iteration parameters is not needed; and if the coefficient number is not greater than the preset coefficient number threshold, updating the iteration coefficient.
According to the method, the device and the system, the target correlation coefficient meeting the preset correlation judgment conditions in the correlation coefficients of all results is determined, and whether iteration parameters are updated or not is determined according to the coefficient quantity of the target correlation coefficient and the preset coefficient quantity threshold, so that accurate judgment on whether the iteration parameters are updated or not is improved, the accuracy of determining the measurement value of the target node is improved, and the accuracy of determining the influence on the measurement result of the node is improved.
Example III
Fig. 3 is a flowchart of a method for measuring influence of a node according to a third embodiment of the present invention. The present embodiment provides a preferred example based on the above-described embodiments.
As shown in fig. 3, the method comprises the following specific steps:
s310, acquiring node attribute information of each network node in the network to be measured.
S320, determining a first node influence index of each network node according to the node attribute information.
S330, according to the node association relation of each network node, determining the first association network node corresponding to each network node.
S340, determining second node influence indexes of the first associated network nodes corresponding to the network nodes respectively according to the node attribute information of the first associated network nodes.
S350, determining the first node weight of each network node according to the first node influence index and the second node influence index of the corresponding network node.
S360, determining a first node degree value of each network node according to the node association relation.
S370, determining second node output values of second associated network nodes corresponding to the network nodes respectively.
S380, determining the second node weight of each network node according to the first node output value and the second node output value of the corresponding network node.
S390, determining the target node weight of each network node according to the first node weight and the second node weight.
S3100, determining second associated network nodes corresponding to the network nodes respectively according to the node association relation.
S3110, determining a target node metric value of each network node based on a preset iteration parameter according to the target node weight and the node initial parameter value of the second associated network node.
And S3120, carrying out node influence measurement on each network node according to the target node measurement value, and obtaining a node influence measurement result.
Optionally, after obtaining the node influence weighing result, at least one influence weighing model may be obtained; determining reference node measurement values of all network nodes in the network to be measured under all influence and measurement models respectively; according to the reference node measurement value of the corresponding influence and measurement model, carrying out node influence and measurement on each network node to obtain a reference influence and measurement result under each influence and measurement model; determining a result correlation coefficient between the node influence weighing result and each reference influence weighing result respectively; determining target correlation coefficients meeting preset correlation judgment conditions in the correlation coefficients of all results; determining the coefficient quantity of the target correlation coefficient; and determining whether to update the iteration parameters according to the coefficient quantity and a preset coefficient quantity threshold value.
Example IV
Fig. 4 is a schematic structural diagram of a node influence measuring apparatus according to a fourth embodiment of the present invention. The device for measuring the influence of the node provided by the embodiment of the invention can be suitable for measuring the influence of the node of the user node of the social network, and the device for measuring the influence of the node can be realized in a form of hardware and/or software, as shown in fig. 4, and specifically comprises: an attribute information acquisition module 401, a target weight determination module 402, a target metric value determination module 403, and a metric result determination module 404. Wherein,
an attribute information obtaining module 401, configured to obtain node attribute information of each network node in the network to be measured;
a target weight determining module 402, configured to determine a target node weight of each network node according to the node attribute information and a node association relationship between each network node;
a destination node metric value determining module 403, configured to determine a destination node metric value of each network node according to the node association relationship and the destination node weight;
and the measurement result determining module 404 is configured to perform node influence measurement on each network node according to the target node measurement value, so as to obtain a node influence measurement result.
The technical scheme of the embodiment of the invention obtains the node attribute information of each network node in the network to be measured; determining the target node weight of each network node according to the node attribute information and the node association relation between each network node; determining a target node metric value of each network node according to the node association relationship and the target node weight; and carrying out node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result. According to the technical scheme, node attribute information and node association relations are comprehensively considered in the process of determining the weight of the target nodes, so that the weight of the target nodes of each determined network node is not completely the same, and the difference of the network nodes is fully represented; the target node metric value of each network node is determined through the node association relation and the target node weight, and the accuracy of determining the target node metric value is improved, so that the accuracy of determining the influence on the node metric result is improved.
Optionally, the target weight determining module 402 includes:
a first node weight determining unit, configured to determine a first node weight of each network node according to the node attribute information and a node association relationship between each network node;
A second node weight determining unit, configured to determine a second node weight of each network node according to a node association relationship between each network node;
and the target node weight determining unit is used for determining the target node weight of each network node according to the first node weight and the second node weight.
Optionally, the first node weight determining unit includes:
a first influence index determining subunit, configured to determine a first node influence index of each network node according to the node attribute information;
a first association node determining subunit, configured to determine, according to a node association relationship of each network node, a first association network node corresponding to each network node respectively;
a second influence index determining subunit, configured to determine, according to node attribute information of the first associated network node, a second node influence index of the first associated network node corresponding to each network node respectively;
and the first node weight determining subunit is used for determining the first node weight of each network node according to the first node influence index and the second node influence index of the corresponding network node.
Optionally, the second node weight determining unit includes:
a first node output value determining subunit, configured to determine a first node output value of each network node according to the node association relationship; the method comprises the steps of,
a second node output value determining subunit, configured to determine a second node output value of a second associated network node corresponding to each of the network nodes respectively;
and the second node weight determining subunit is used for determining the second node weight of each network node according to the first node output value and the second node output value of the corresponding network node.
Optionally, the target metric value determining module 403 includes:
a second association node determining unit, configured to determine second association network nodes corresponding to the network nodes respectively according to the node association relationship;
and the target node metric value determining unit is used for determining the target node metric value of each network node based on a preset iteration parameter according to the target node weight and the node initial parameter value of the second associated network node.
Optionally, the method further comprises:
the measurement model acquisition module is used for acquiring at least one influence measurement model after measuring the influence of the nodes on each network node according to the target node measurement value to obtain a node influence measurement result;
The reference metric value determining module is used for determining reference node metric values of all network nodes in the network to be measured under all the influence metric models respectively;
the reference measurement result determining module is used for measuring the node influence of each network node according to the reference node measurement value of the corresponding influence measurement model to obtain the reference influence measurement result under each influence measurement model;
the correlation coefficient determining module is used for determining result correlation coefficients between the node influence weighted results and the reference influence weighted results respectively;
and the updating judgment module is used for determining whether to update the iteration parameters according to the result correlation coefficients.
Optionally, the update judgment module includes:
the target coefficient determining unit is used for determining target correlation coefficients meeting preset correlation judgment conditions in the result correlation coefficients;
a coefficient number determining unit configured to determine a coefficient number of the target correlation coefficient;
and the updating judgment unit is used for determining whether to update the iteration parameters according to the coefficient quantity and a preset coefficient quantity threshold value.
The node influence measuring device provided by the embodiment of the invention can execute the node influence measuring method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
Example five
Fig. 5 shows a schematic diagram of an electronic device 50 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 50 includes at least one processor 51, and a memory, such as a Read Only Memory (ROM) 52, a Random Access Memory (RAM) 53, etc., communicatively connected to the at least one processor 51, in which the memory stores a computer program executable by the at least one processor, and the processor 51 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 52 or the computer program loaded from the storage unit 58 into the Random Access Memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the electronic device 50 can also be stored. The processor 51, the ROM 52 and the RAM 53 are connected to each other via a bus 54. An input/output (I/O) interface 55 is also connected to bus 54.
Various components in the electronic device 50 are connected to the I/O interface 55, including: an input unit 56 such as a keyboard, a mouse, etc.; an output unit 57 such as various types of displays, speakers, and the like; a storage unit 58 such as a magnetic disk, an optical disk, or the like; and a communication unit 59 such as a network card, modem, wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.
The processor 51 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 51 performs the various methods and processes described above, such as the node impact metric method.
In some embodiments, the node impact metric method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 50 via the ROM 52 and/or the communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the node impact measurement method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured to perform the node impact metric method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of node influence measurement, comprising:
acquiring node attribute information of each network node in a network to be measured;
determining the target node weight of each network node according to the node attribute information and the node association relation between each network node;
determining a target node metric value of each network node according to the node association relationship and the target node weight;
And carrying out node influence measurement on each network node according to the target node measurement value to obtain a node influence measurement result.
2. The method according to claim 1, wherein determining the target node weight of each network node according to the node association relationship between the node attribute information and each network node comprises:
determining a first node weight of each network node according to the node attribute information and the node association relation between each network node;
determining a second node weight of each network node according to the node association relation among the network nodes;
and determining the target node weight of each network node according to the first node weight and the second node weight.
3. The method according to claim 2, wherein determining the first node weight of each network node according to the node attribute information and the node association relationship between each network node comprises:
determining a first node influence index of each network node according to the node attribute information;
according to the node association relation of each network node, determining a first association network node corresponding to each network node respectively;
Determining a second node influence index of the first associated network node corresponding to each network node according to the node attribute information of the first associated network node;
and determining the first node weight of each network node according to the first node influence index and the second node influence index of the corresponding network node.
4. The method of claim 2, wherein determining the second node weight of each of the network nodes according to the node association relationship between each of the network nodes comprises:
determining a first node degree value of each network node according to the node association relation; the method comprises the steps of,
determining a second node output value of a second associated network node corresponding to each network node respectively;
and determining the second node weight of each network node according to the first node degree value and the second node degree value of the corresponding network node.
5. The method according to any one of claims 1-4, wherein determining a target node metric value for each of the network nodes based on the node association and the target node weight comprises:
determining second associated network nodes corresponding to the network nodes respectively according to the node association relation;
And determining a target node metric value of each network node based on a preset iteration parameter according to the target node weight and the node initial parameter value of the second associated network node.
6. The method of claim 5, wherein after performing a node impact metric on each of the network nodes based on the target node metric values to obtain a node impact metric result, the method further comprises:
acquiring at least one influence weighing model;
determining reference node measurement values of each network node in the network to be measured under each influence and measurement model respectively;
according to the reference node measurement value of the corresponding influence and measurement model, carrying out node influence and measurement on each network node to obtain a reference influence and measurement result under each influence and measurement model;
determining a result correlation coefficient between a node influence weighing result and each reference influence weighing result respectively;
and determining whether to update the iteration parameters according to each result correlation coefficient.
7. The method of claim 6, wherein said determining whether to update the iteration parameters based on each of the resulting correlation coefficients comprises:
Determining target correlation coefficients meeting preset correlation judgment conditions in the result correlation coefficients;
determining the coefficient quantity of the target correlation coefficient;
and determining whether to update the iteration parameters according to the coefficient quantity and a preset coefficient quantity threshold value.
8. A node influence weighing apparatus, comprising:
the attribute information acquisition module is used for acquiring node attribute information of each network node in the network to be measured;
the target weight determining module is used for determining the target node weight of each network node according to the node attribute information and the node association relation between each network node;
the target node measurement value determining module is used for determining target node measurement values of the network nodes according to the node association relation and the target node weight;
and the measurement result determining module is used for measuring the influence of the nodes on each network node according to the target node measurement value to obtain a node influence measurement result.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the node impact metric method of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to implement the node influence metric method of any of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310630256.XA CN116823510A (en) | 2023-05-30 | 2023-05-30 | Node influence measuring method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310630256.XA CN116823510A (en) | 2023-05-30 | 2023-05-30 | Node influence measuring method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116823510A true CN116823510A (en) | 2023-09-29 |
Family
ID=88125013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310630256.XA Pending CN116823510A (en) | 2023-05-30 | 2023-05-30 | Node influence measuring method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116823510A (en) |
-
2023
- 2023-05-30 CN CN202310630256.XA patent/CN116823510A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112907128B (en) | Data analysis method, device, equipment and medium based on AB test result | |
| CN112580733B (en) | Classification model training method, device, equipment and storage medium | |
| CN114065864B (en) | Federal learning method, federal learning device, electronic apparatus, and storage medium | |
| CN113657538B (en) | Model training and data classification method, device, equipment, storage medium and product | |
| CN113361956B (en) | Resource quality evaluation method, device, equipment and storage medium for resource producer | |
| CN117993478A (en) | Model training method and device based on bidirectional knowledge distillation and federal learning | |
| CN116962272B (en) | Abnormality detection method, device, equipment and storage medium for network index | |
| CN116228301A (en) | Method, device, equipment and medium for determining target user | |
| CN116226628A (en) | Feature optimization method, device, equipment and medium | |
| CN116823510A (en) | Node influence measuring method, device, equipment and storage medium | |
| CN114756753A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN113434378B (en) | Webpage stability detection method and device, electronic equipment and readable storage medium | |
| CN113360798B (en) | Method, device, equipment and medium for identifying flooding data | |
| CN114398558B (en) | Information recommendation method, device, electronic equipment and storage medium | |
| CN115578583B (en) | Image processing method, device, electronic equipment and storage medium | |
| CN114547417B (en) | Media resource ordering method and electronic equipment | |
| CN118312663A (en) | Method and device for determining article information, electronic equipment and storage medium | |
| CN117271882A (en) | Multi-target fusion processing method and device, electronic equipment and storage medium | |
| CN117575655A (en) | Product information transmission method, device, equipment and storage medium | |
| CN117331924A (en) | Data model matching degree checking method, device, equipment and storage medium | |
| CN117540698A (en) | SRAM selection method, device, equipment and medium with variable weight | |
| CN118413450A (en) | Method, device, equipment and storage medium for evaluating entity trust in power network space | |
| CN117573983A (en) | Recommendation method and device of financing scheme, electronic equipment and storage medium | |
| CN117195104A (en) | Resource classification method, device, electronic equipment and storage medium | |
| CN117493690A (en) | Data pushing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |