CN111667015A - Internet of things equipment state detection method and device and detection equipment - Google Patents
Internet of things equipment state detection method and device and detection equipment Download PDFInfo
- Publication number
- CN111667015A CN111667015A CN202010531411.9A CN202010531411A CN111667015A CN 111667015 A CN111667015 A CN 111667015A CN 202010531411 A CN202010531411 A CN 202010531411A CN 111667015 A CN111667015 A CN 111667015A
- Authority
- CN
- China
- Prior art keywords
- parameter
- internet
- state
- label
- things device
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- 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
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a method and a device for detecting the state of equipment of the Internet of things and detection equipment. According to the method, a first operation state track of first Internet of things equipment and a second operation state track of second Internet of things equipment are determined, a state association list between the first Internet of things equipment and the second Internet of things equipment is generated based on the first operation state track and the second operation state track, then state parameters under an independent node parameter set and under an associated node parameter set of the first Internet of things equipment are migrated when abnormal records exist in equipment operation records of the second Internet of things equipment, and then the state of the first Internet of things equipment is detected according to parameter index information corresponding to the calculated independent node parameter set. Therefore, the accuracy of state detection of the first Internet of things equipment can be improved, and the missing judgment and the misjudgment are avoided.
Description
Technical Field
The disclosure relates to the technical field of equipment detection, in particular to a method and a device for detecting the state of equipment in the Internet of things and detection equipment.
Background
With the development of science and technology, the application of the internet of things equipment is more and more extensive. Taking smart home as an example, an intelligent home system formed by an internet of things device cluster can provide comfortable and convenient home life for a user. However, in the smart home system, the types of the internet of things devices are often complicated, and if the operating state of one of the internet of things devices fails, the safe and stable operation of the whole internet of things device may be affected. Therefore, the running state of the internet of things equipment needs to be detected in real time to determine whether the internet of things equipment is in a fault state. However, in the prior art, the accuracy of the state detection of the internet of things equipment is poor, and the missed judgment and the misjudgment often occur.
Disclosure of Invention
In order to solve the technical problems in the related art, the disclosure provides a method and a device for detecting the state of equipment of the internet of things and detection equipment.
An Internet of things equipment state detection method, comprising:
aiming at a first Internet of things device and a second Internet of things device of which the communication frequency is greater than a set frequency, generating a first operation state track corresponding to the first Internet of things device and a second operation state track corresponding to the second Internet of things device; the first running state track and the second running state track respectively comprise a plurality of state nodes with different track identification degrees;
determining a device attribute label of the first internet of things device at any state node of the first running state track, and determining a state node with the minimum track identification degree in the second running state track as a first node; mapping the device attribute label to the first node based on the difference value of the longitude and latitude coordinates of the first internet of things device and the second internet of things device to obtain a target attribute label in the first node, and generating a state association list between the first internet of things device and the second internet of things device according to a label matching coefficient between the device attribute label and the target attribute label;
when detecting that an abnormal record exists in the equipment operation record of the second internet-of-things equipment, acquiring an abnormal information list of the abnormal record and each group of state parameters of the first internet-of-things equipment in a time period corresponding to the abnormal record; under the condition that the first Internet of things device is determined to contain an independent node parameter set according to the abnormal information list and the state association list, determining association degrees between each state parameter of the first Internet of things device under an associated node parameter set and each state parameter of the first Internet of things device under the independent node parameter set according to the state parameter of the first Internet of things device under the independent node parameter set and the parameter weight of the first Internet of things device, and migrating the state parameter of the first Internet of things device under the associated node parameter set and the state parameter associated with the state parameter under the independent node parameter set to the independent node parameter set;
determining the parameter centrality of each group of state parameters under the independent node parameter set, calculating the parameter index information corresponding to the independent node parameter set according to the parameter centrality, and judging that the first Internet of things device has a state abnormal risk when the parameter index information does not meet set conditions.
Optionally, the method further comprises:
determining the association degree of the first internet of things device among the state parameters of the first internet of things device under the associated node parameter set according to the state parameters of the first internet of things device under the independent node parameter set and the parameter weight thereof under the condition that the associated node parameter set corresponding to the first internet of things device contains a plurality of state parameters;
screening the state parameters under the associated node parameter set according to the association degree between the state parameters of the associated node parameter set corresponding to the first internet of things device to obtain multiple groups of target state parameters;
and distributing a migration grade for each group of target state parameters obtained by screening according to the state parameters of the first Internet of things equipment under the independent node parameter set and the parameter weight thereof, and selecting a set number of target state parameters from regions according to the sequence of the migration grades from large to small to migrate to the independent node parameter set.
Optionally, determining the parameter centrality of each group of state parameters under the independent node parameter set includes:
acquiring parameter labels of each group of state parameters, listing the label attributes of each parameter label, and establishing a label similarity distribution graph of each group of state parameters; the label similarity distribution graph is a regional graph set, the graph set of each region corresponds to one region identifier, each region identifier has at least one label attribute, and each region of the label similarity distribution graph has an incidence relation from small to large;
determining parameter characteristic information of each group of state parameters, extracting a mapping path of the parameter characteristic information corresponding to each group of state parameters from the label similarity distribution graph of each group of state parameters based on the parameter characteristic information, and finding out the characteristic identification degree of the parameter characteristic information in the label similarity distribution graph according to the mapping path;
establishing a credibility query list between the parameter labels and the label similarity distribution graph of each group of state parameters according to the characteristic identification degree, and generating a characteristic clustering model of each group of state parameters according to the credibility query list; generating a feature clustering model according to the credibility query list, wherein the feature clustering model comprises the following steps: converting each parameter label into a corresponding character code; respectively generating at least one first coding sequence of each string of character codes; obtaining a first coding sequence of the parameter label which is not repeated with each other to form a second coding sequence; mapping each first coding sequence in the second coding sequence to the label similarity distribution graph of each group of state parameters to form a feature clustering model;
traversing and matching the label attribute contained in each parameter label of each group of state parameters with each target label attribute in the feature clustering model; if all the label attributes of a first coding sequence are matched with the corresponding target label attributes in the feature clustering model, determining the parameter label corresponding to the first coding sequence as a credible label;
and extracting the associated parameters of each group of state parameters based on the credible label to obtain an associated parameter set, clustering the associated parameters in the associated parameter set by adopting a multi-dimensional characteristic clustering method to obtain a plurality of target clusters, and calculating the parameter centrality of each group of state parameters according to the number of the target clusters.
Optionally, calculating parameter index information corresponding to the independent node parameter set according to the parameter centrality includes:
sorting the parameter centralities according to the sequence of the parameter centralities from large to small to obtain a centrality sorting sequence, and determining the centrality of a target parameter from the centrality sorting sequence based on the parameter structure information corresponding to the independent node parameter sets; determining a first sequence weight in the centrality of the target parameter;
judging whether the difference value between a first sequence weight in the centrality of the target parameter and a second sequence weight of the centrality of a parameter which is previous to the centrality of the target parameter is smaller than a set threshold value or not;
if so, determining the determined first sequence weight of the centrality of the target parameter as a first current sequence weight of the centrality of the target parameter; otherwise, performing weighted summation on the determined first sequence weight of the centrality of the target parameter and the second current sequence weight of the centrality of the previous parameter, and determining the weight obtained by the weighted summation as the first current sequence weight of the centrality of the target parameter; and extracting the dimension value of each state parameter in the independent node parameter set based on the first current sequence weight and calculating parameter index information corresponding to the independent node parameter set according to the extracted dimension value.
An internet of things equipment state detection device, the device comprising:
the track generation module is used for generating a first running state track corresponding to the first internet of things device and a second running state track corresponding to the second internet of things device aiming at the first internet of things device and the second internet of things device of which the communication frequency is greater than the set frequency; the first running state track and the second running state track respectively comprise a plurality of state nodes with different track identification degrees;
the list determining module is used for determining the device attribute label of the first internet of things device at any state node of the first running state track, and determining the state node with the minimum track identification degree in the second running state track as the first node; mapping the device attribute label to the first node based on the difference value of the longitude and latitude coordinates of the first internet of things device and the second internet of things device to obtain a target attribute label in the first node, and generating a state association list between the first internet of things device and the second internet of things device according to a label matching coefficient between the device attribute label and the target attribute label;
the parameter migration module is used for acquiring an abnormal information list of the abnormal record and each group of state parameters of the first internet of things device in a time period corresponding to the abnormal record when the abnormal record exists in the device operation record of the second internet of things device; under the condition that the first Internet of things device is determined to contain an independent node parameter set according to the abnormal information list and the state association list, determining association degrees between each state parameter of the first Internet of things device under an associated node parameter set and each state parameter of the first Internet of things device under the independent node parameter set according to the state parameter of the first Internet of things device under the independent node parameter set and the parameter weight of the first Internet of things device, and migrating the state parameter of the first Internet of things device under the associated node parameter set and the state parameter associated with the state parameter under the independent node parameter set to the independent node parameter set;
the state detection module is used for determining the parameter centrality of each group of state parameters under the independent node parameter set, calculating the parameter index information corresponding to the independent node parameter set according to the parameter centrality, and judging that the first Internet of things device has a state abnormal risk when the parameter index information does not meet set conditions.
Optionally, the parameter migration module is further configured to:
determining the association degree of the first internet of things device among the state parameters of the first internet of things device under the associated node parameter set according to the state parameters of the first internet of things device under the independent node parameter set and the parameter weight thereof under the condition that the associated node parameter set corresponding to the first internet of things device contains a plurality of state parameters;
screening the state parameters under the associated node parameter set according to the association degree between the state parameters of the associated node parameter set corresponding to the first internet of things device to obtain multiple groups of target state parameters;
and distributing a migration grade for each group of target state parameters obtained by screening according to the state parameters of the first Internet of things equipment under the independent node parameter set and the parameter weight thereof, and selecting a set number of target state parameters from regions according to the sequence of the migration grades from large to small to migrate to the independent node parameter set.
Optionally, the state detection module is specifically configured to:
acquiring parameter labels of each group of state parameters, listing the label attributes of each parameter label, and establishing a label similarity distribution graph of each group of state parameters; the label similarity distribution graph is a regional graph set, the graph set of each region corresponds to one region identifier, each region identifier has at least one label attribute, and each region of the label similarity distribution graph has an incidence relation from small to large;
determining parameter characteristic information of each group of state parameters, extracting a mapping path of the parameter characteristic information corresponding to each group of state parameters from the label similarity distribution graph of each group of state parameters based on the parameter characteristic information, and finding out the characteristic identification degree of the parameter characteristic information in the label similarity distribution graph according to the mapping path;
establishing a credibility query list between the parameter labels and the label similarity distribution graph of each group of state parameters according to the characteristic identification degree, and generating a characteristic clustering model of each group of state parameters according to the credibility query list; generating a feature clustering model according to the credibility query list, wherein the feature clustering model comprises the following steps: converting each parameter label into a corresponding character code; respectively generating at least one first coding sequence of each string of character codes; obtaining a first coding sequence of the parameter label which is not repeated with each other to form a second coding sequence; mapping each first coding sequence in the second coding sequence to the label similarity distribution graph of each group of state parameters to form a feature clustering model;
traversing and matching the label attribute contained in each parameter label of each group of state parameters with each target label attribute in the feature clustering model; if all the label attributes of a first coding sequence are matched with the corresponding target label attributes in the feature clustering model, determining the parameter label corresponding to the first coding sequence as a credible label;
and extracting the associated parameters of each group of state parameters based on the credible label to obtain an associated parameter set, clustering the associated parameters in the associated parameter set by adopting a multi-dimensional characteristic clustering method to obtain a plurality of target clusters, and calculating the parameter centrality of each group of state parameters according to the number of the target clusters.
Optionally, the state detection module is specifically configured to:
sorting the parameter centralities according to the sequence of the parameter centralities from large to small to obtain a centrality sorting sequence, and determining the centrality of a target parameter from the centrality sorting sequence based on the parameter structure information corresponding to the independent node parameter sets; determining a first sequence weight in the centrality of the target parameter;
judging whether the difference value between a first sequence weight in the centrality of the target parameter and a second sequence weight of the centrality of a parameter which is previous to the centrality of the target parameter is smaller than a set threshold value or not;
if so, determining the determined first sequence weight of the centrality of the target parameter as a first current sequence weight of the centrality of the target parameter; otherwise, performing weighted summation on the determined first sequence weight of the centrality of the target parameter and the second current sequence weight of the centrality of the previous parameter, and determining the weight obtained by the weighted summation as the first current sequence weight of the centrality of the target parameter; and extracting the dimension value of each state parameter in the independent node parameter set based on the first current sequence weight and calculating parameter index information corresponding to the independent node parameter set according to the extracted dimension value.
A detection apparatus comprising a processor and a memory in communication with each other, the processor implementing the above method by retrieving a computer program from the memory and executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when executed, implements the method described above.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects.
The method comprises the steps of firstly determining a first running state track of first Internet of things equipment and a second running state track of second Internet of things equipment, secondly generating a state association list between the first Internet of things equipment and the second Internet of things equipment based on the first running state track and the second running state track, then transferring state parameters under an independent node parameter set and an associated node parameter set of the first Internet of things equipment when detecting that an abnormal record exists in an equipment running record of the second Internet of things equipment, and further detecting the state of the first Internet of things equipment according to calculated parameter index information corresponding to the independent node parameter set. Therefore, the accuracy of state detection of the first Internet of things equipment can be improved, and the missing judgment and the misjudgment are avoided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic view of a communication architecture of an internet of things device state detection system provided in this embodiment.
Fig. 2 is a schematic flow chart of the method for detecting the state of the internet of things device provided in this embodiment.
Fig. 3 is a functional block diagram of the device for detecting the state of the internet of things device provided in this embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
Fig. 1 is a schematic diagram of a communication architecture of an internet of things device status detection system 100 according to the present disclosure, where the internet of things device status detection system 100 includes a detection device 200 and a plurality of internet of things devices 300. Wherein the detection device 200 and the internet of things device 300 communicate with each other. In this embodiment, the detection device 200 may be a cloud control center, and the internet of things device 300 may be a smart home.
Referring to fig. 2, a flow chart of a method for detecting a device status of the internet of things is provided, and the method may be applied to the detection device 200 in fig. 1, and specifically may include the following steps.
Step S21, aiming at a first Internet of things device and a second Internet of things device of which the communication frequency is greater than a set frequency, generating a first operation state track corresponding to the first Internet of things device and a second operation state track corresponding to the second Internet of things device; the first running state track and the second running state track respectively comprise a plurality of state nodes with different track identification degrees.
Step S22, determining a device attribute label of the first internet of things device at any state node of the first operation state trajectory, and determining a state node with a minimum trajectory identification degree in the second operation state trajectory as a first node; and mapping the device attribute label to the first node based on the difference value of the longitude and latitude coordinates of the first internet of things device and the second internet of things device to obtain a target attribute label in the first node, and generating a state association list between the first internet of things device and the second internet of things device according to a label matching coefficient between the device attribute label and the target attribute label.
Step S23, when detecting that an abnormal record exists in the device operation record of the second Internet of things device, acquiring an abnormal information list of the abnormal record and each group of state parameters of the first Internet of things device in a time period corresponding to the abnormal record; and under the condition that the first Internet of things equipment contains an independent node parameter set according to the abnormal information list and the state association list, determining association degrees between each state parameter of the first Internet of things equipment under an associated node parameter set and each state parameter of the first Internet of things equipment under the independent node parameter set according to the state parameter of the first Internet of things equipment under the associated node parameter set and the parameter weight of the first Internet of things equipment, and migrating the state parameter of the first Internet of things equipment under the associated node parameter set, which is associated with the state parameter under the independent node parameter set, to the independent node parameter set.
Step S24, determining a parameter centrality of each group of state parameters under the independent node parameter set, calculating parameter index information corresponding to the independent node parameter set according to the parameter centrality, and determining that the first internet of things device has a state anomaly risk when the parameter index information does not meet a set condition.
It can be understood that through the descriptions in the above steps S21 to S24, first, a first operation state trajectory of the first internet of things device and a second operation state trajectory of the second internet of things device are determined, then, a state association list between the first internet of things device and the second internet of things device is generated based on the first operation state trajectory and the second operation state trajectory, then, when it is detected that an abnormal record exists in the device operation record of the second internet of things device, state parameters under the independent node parameter set and under the associated node parameter set of the first internet of things device are migrated, and then, the state of the first internet of things device is detected according to the calculated parameter index information corresponding to the independent node parameter set. Therefore, the accuracy of state detection of the first Internet of things equipment can be improved, and the missing judgment and the misjudgment are avoided.
In a possible embodiment, in order to ensure the accuracy of the migration of the state parameters, on the basis of step S23, the method may further include what is described in the following sub-steps:
determining the association degree of the first internet of things device among the state parameters of the first internet of things device under the associated node parameter set according to the state parameters of the first internet of things device under the independent node parameter set and the parameter weight thereof under the condition that the associated node parameter set corresponding to the first internet of things device contains a plurality of state parameters;
screening the state parameters under the associated node parameter set according to the association degree between the state parameters of the associated node parameter set corresponding to the first internet of things device to obtain multiple groups of target state parameters;
and distributing a migration grade for each group of target state parameters obtained by screening according to the state parameters of the first Internet of things equipment under the independent node parameter set and the parameter weight thereof, and selecting a set number of target state parameters from regions according to the sequence of the migration grades from large to small to migrate to the independent node parameter set.
In specific implementation, the accuracy of the migration of the state parameters can be ensured through the content described in the sub-steps.
In practical application, the inventor finds that the parameter characteristics of the state parameters are often easy to ignore when determining the parameter centrality, so that the determined parameter centrality is low in reliability, and the accuracy of state detection of the internet of things equipment is difficult to ensure. In order to improve the above problem, in step S24, the parameter centrality of each set of status parameters under the independent node parameter set is determined, which may specifically include the contents described in steps S241 to S245 below.
Step S241, acquiring the parameter labels of each group of state parameters, listing the label attributes of each parameter label, and establishing a label similarity distribution graph of each group of state parameters; the label similarity distribution graph is a regional graph set, the graph set of each region corresponds to one region identifier, each region identifier has at least one label attribute, and each region of the label similarity distribution graph has a correlation relationship from small to large.
Step S242, determining parameter feature information of each group of state parameters, extracting a mapping path of the parameter feature information corresponding to each group of state parameters from the tag similarity distribution graph of each group of state parameters based on the parameter feature information, and finding out the feature identification degree of the parameter feature information in the tag similarity distribution graph according to the mapping path.
Step S243, establishing a credibility query list between the parameter label and the label similarity distribution graph of each group of state parameters according to the characteristic identification degree, and generating a characteristic clustering model of each group of state parameters according to the credibility query list; generating a feature clustering model according to the credibility query list, wherein the feature clustering model comprises the following steps: converting each parameter label into a corresponding character code; respectively generating at least one first coding sequence of each string of character codes; obtaining a first coding sequence of the parameter label which is not repeated with each other to form a second coding sequence; and mapping each first coding sequence in the second coding sequence to the label similarity distribution graph of each group of state parameters to form a feature clustering model.
Step S244, traversing and matching the label attribute contained in each parameter label of each group of state parameters with each target label attribute in the feature clustering model; and if all the label attributes of one first coding sequence are matched with the corresponding target label attributes in the feature clustering model, determining the parameter label corresponding to the first coding sequence as a credible label.
Step S245, extracting the associated parameters of each group of state parameters based on the credible labels to obtain an associated parameter set, clustering the associated parameters in the associated parameter set by adopting a multi-dimensional characteristic clustering method to obtain a plurality of target clusters, and calculating the parameter centrality of each group of state parameters according to the number of the target clusters.
In specific implementation, by executing the steps S241 to S245, the parameter feature analysis of the state parameter can be performed, so that the clustering number of the associated parameter set corresponding to the state parameter is determined based on a multidimensional feature clustering method, and thus the reliability of the determined parameter centrality can be ensured, and the accuracy of the state detection of the internet of things device can be ensured.
In one possible embodiment, in order to ensure the integrity of the parameter index information, in step S24, the parameter index information corresponding to the independent node parameter set is calculated according to the parameter centrality, which may specifically include the contents described in the following steps a to d.
Step a, sorting the parameter centrality according to the sequence of the parameter centrality from big to small to obtain a centrality sorting sequence, and determining the centrality of a target parameter from the centrality sorting sequence based on the parameter structure information corresponding to the independent node parameter set; determining a first sequence weight in the centrality of the target parameter.
And b, judging whether the difference value between the first sequence weight in the centrality of the target parameter and the second sequence weight of the centrality of the parameter before the centrality of the target parameter is smaller than a set threshold value.
Step c, if yes, determining the first sequence weight of the determined centrality of the target parameter as a first current sequence weight of the centrality of the target parameter; otherwise, performing weighted summation on the determined first sequence weight of the centrality of the target parameter and the second current sequence weight of the centrality of the previous parameter, and determining the weight obtained by the weighted summation as the first current sequence weight of the centrality of the target parameter; and extracting the dimension value of each state parameter in the independent node parameter set based on the first current sequence weight and calculating parameter index information corresponding to the independent node parameter set according to the extracted dimension value.
It can be understood that based on the above steps a-c, the parameter index information can be completely determined.
On the basis, whether the parameter index information meets the set condition can be determined by the following steps: determining a conversion factor of the parameter index information according to the number of the state parameters in the independent node parameter set, converting the parameter index information through the conversion factor to obtain a risk coefficient corresponding to the parameter index information, and judging that the parameter index information does not meet the set condition when the risk coefficient is greater than a set coefficient.
On the basis, please refer to fig. 3 in combination, a device 400 for detecting the status of an internet of things device is provided, which includes the following functional modules:
a track generating module 410, configured to generate, for a first internet of things device and a second internet of things device whose communication frequencies are greater than a set frequency, a first operating state track corresponding to the first internet of things device and a second operating state track corresponding to the second internet of things device; the first running state track and the second running state track respectively comprise a plurality of state nodes with different track identification degrees;
a list determining module 420, configured to determine a device attribute tag of the first internet of things device at any state node of the first operation state track, and determine a state node with a minimum track identification degree in the second operation state track as a first node; mapping the device attribute label to the first node based on the difference value of the longitude and latitude coordinates of the first internet of things device and the second internet of things device to obtain a target attribute label in the first node, and generating a state association list between the first internet of things device and the second internet of things device according to a label matching coefficient between the device attribute label and the target attribute label;
the parameter migration module 430 is configured to, when it is detected that an abnormal record exists in the device operation record of the second internet-of-things device, obtain an abnormal information list of the abnormal record and each set of state parameters of the first internet-of-things device in a time period corresponding to the abnormal record; under the condition that the first Internet of things device is determined to contain an independent node parameter set according to the abnormal information list and the state association list, determining association degrees between each state parameter of the first Internet of things device under an associated node parameter set and each state parameter of the first Internet of things device under the independent node parameter set according to the state parameter of the first Internet of things device under the independent node parameter set and the parameter weight of the first Internet of things device, and migrating the state parameter of the first Internet of things device under the associated node parameter set and the state parameter associated with the state parameter under the independent node parameter set to the independent node parameter set;
the state detection module 440 is configured to determine a parameter centrality of each group of state parameters under the independent node parameter set, calculate parameter index information corresponding to the independent node parameter set according to the parameter centrality, and determine that the first internet of things device has a state anomaly risk when the parameter index information does not meet a set condition.
Optionally, the parameter migration module 430 is further configured to:
determining the association degree of the first internet of things device among the state parameters of the first internet of things device under the associated node parameter set according to the state parameters of the first internet of things device under the independent node parameter set and the parameter weight thereof under the condition that the associated node parameter set corresponding to the first internet of things device contains a plurality of state parameters;
screening the state parameters under the associated node parameter set according to the association degree between the state parameters of the associated node parameter set corresponding to the first internet of things device to obtain multiple groups of target state parameters;
and distributing a migration grade for each group of target state parameters obtained by screening according to the state parameters of the first Internet of things equipment under the independent node parameter set and the parameter weight thereof, and selecting a set number of target state parameters from regions according to the sequence of the migration grades from large to small to migrate to the independent node parameter set.
Optionally, the state detection module 440 is specifically configured to:
acquiring parameter labels of each group of state parameters, listing the label attributes of each parameter label, and establishing a label similarity distribution graph of each group of state parameters; the label similarity distribution graph is a regional graph set, the graph set of each region corresponds to one region identifier, each region identifier has at least one label attribute, and each region of the label similarity distribution graph has an incidence relation from small to large;
determining parameter characteristic information of each group of state parameters, extracting a mapping path of the parameter characteristic information corresponding to each group of state parameters from the label similarity distribution graph of each group of state parameters based on the parameter characteristic information, and finding out the characteristic identification degree of the parameter characteristic information in the label similarity distribution graph according to the mapping path;
establishing a credibility query list between the parameter labels and the label similarity distribution graph of each group of state parameters according to the characteristic identification degree, and generating a characteristic clustering model of each group of state parameters according to the credibility query list; generating a feature clustering model according to the credibility query list, wherein the feature clustering model comprises the following steps: converting each parameter label into a corresponding character code; respectively generating at least one first coding sequence of each string of character codes; obtaining a first coding sequence of the parameter label which is not repeated with each other to form a second coding sequence; mapping each first coding sequence in the second coding sequence to the label similarity distribution graph of each group of state parameters to form a feature clustering model;
traversing and matching the label attribute contained in each parameter label of each group of state parameters with each target label attribute in the feature clustering model; if all the label attributes of a first coding sequence are matched with the corresponding target label attributes in the feature clustering model, determining the parameter label corresponding to the first coding sequence as a credible label;
and extracting the associated parameters of each group of state parameters based on the credible label to obtain an associated parameter set, clustering the associated parameters in the associated parameter set by adopting a multi-dimensional characteristic clustering method to obtain a plurality of target clusters, and calculating the parameter centrality of each group of state parameters according to the number of the target clusters.
Optionally, the state detection module 440 is specifically configured to:
sorting the parameter centralities according to the sequence of the parameter centralities from large to small to obtain a centrality sorting sequence, and determining the centrality of a target parameter from the centrality sorting sequence based on the parameter structure information corresponding to the independent node parameter sets; determining a first sequence weight in the centrality of the target parameter;
judging whether the difference value between a first sequence weight in the centrality of the target parameter and a second sequence weight of the centrality of a parameter which is previous to the centrality of the target parameter is smaller than a set threshold value or not;
if so, determining the determined first sequence weight of the centrality of the target parameter as a first current sequence weight of the centrality of the target parameter; otherwise, performing weighted summation on the determined first sequence weight of the centrality of the target parameter and the second current sequence weight of the centrality of the previous parameter, and determining the weight obtained by the weighted summation as the first current sequence weight of the centrality of the target parameter; and extracting the dimension value of each state parameter in the independent node parameter set based on the first current sequence weight and calculating parameter index information corresponding to the independent node parameter set according to the extracted dimension value.
For the description of the above functional modules, refer to the description of the method shown in fig. 2, and no further description is made here.
On the basis of the above, there is also provided a detection device comprising a processor and a memory communicating with each other, the processor implementing the above method by retrieving a computer program from the memory and executing the computer program.
Further, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when executed, implements the above-described method.
In summary, when the technical solution provided in the present application is applied, first an operation state trajectory of a first internet of things device and a second operation state trajectory of a second internet of things device are determined, then a state association list between the first internet of things device and the second internet of things device is generated based on the first operation state trajectory and the second operation state trajectory, and then state parameters under an independent node parameter set and under an associated node parameter set of the first internet of things device are migrated when an abnormal record is detected in an operation record of the second internet of things device, so as to detect a state of the first internet of things device according to parameter index information corresponding to the calculated independent node parameter set. Therefore, the accuracy of state detection of the first Internet of things equipment can be improved, and the missing judgment and the misjudgment are avoided.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. A method for detecting the state of equipment of the Internet of things is characterized by comprising the following steps:
aiming at a first Internet of things device and a second Internet of things device of which the communication frequency is greater than a set frequency, generating a first operation state track corresponding to the first Internet of things device and a second operation state track corresponding to the second Internet of things device; the first running state track and the second running state track respectively comprise a plurality of state nodes with different track identification degrees;
determining a device attribute label of the first internet of things device at any state node of the first running state track, and determining a state node with the minimum track identification degree in the second running state track as a first node; mapping the device attribute label to the first node based on the difference value of the longitude and latitude coordinates of the first internet of things device and the second internet of things device to obtain a target attribute label in the first node, and generating a state association list between the first internet of things device and the second internet of things device according to a label matching coefficient between the device attribute label and the target attribute label;
when detecting that an abnormal record exists in the equipment operation record of the second internet-of-things equipment, acquiring an abnormal information list of the abnormal record and each group of state parameters of the first internet-of-things equipment in a time period corresponding to the abnormal record; under the condition that the first Internet of things device is determined to contain an independent node parameter set according to the abnormal information list and the state association list, determining association degrees between each state parameter of the first Internet of things device under an associated node parameter set and each state parameter of the first Internet of things device under the independent node parameter set according to the state parameter of the first Internet of things device under the independent node parameter set and the parameter weight of the first Internet of things device, and migrating the state parameter of the first Internet of things device under the associated node parameter set and the state parameter associated with the state parameter under the independent node parameter set to the independent node parameter set;
determining the parameter centrality of each group of state parameters under the independent node parameter set, calculating the parameter index information corresponding to the independent node parameter set according to the parameter centrality, and judging that the first Internet of things device has a state abnormal risk when the parameter index information does not meet set conditions.
2. The method of claim 1, further comprising:
determining the association degree of the first internet of things device among the state parameters of the first internet of things device under the associated node parameter set according to the state parameters of the first internet of things device under the independent node parameter set and the parameter weight thereof under the condition that the associated node parameter set corresponding to the first internet of things device contains a plurality of state parameters;
screening the state parameters under the associated node parameter set according to the association degree between the state parameters of the associated node parameter set corresponding to the first internet of things device to obtain multiple groups of target state parameters;
and distributing a migration grade for each group of target state parameters obtained by screening according to the state parameters of the first Internet of things equipment under the independent node parameter set and the parameter weight thereof, and selecting a set number of target state parameters from regions according to the sequence of the migration grades from large to small to migrate to the independent node parameter set.
3. The method of claim 1 or 2, wherein determining the parameter centrality of each set of state parameters under the independent node parameter set comprises:
acquiring parameter labels of each group of state parameters, listing the label attributes of each parameter label, and establishing a label similarity distribution graph of each group of state parameters; the label similarity distribution graph is a regional graph set, the graph set of each region corresponds to one region identifier, each region identifier has at least one label attribute, and each region of the label similarity distribution graph has an incidence relation from small to large;
determining parameter characteristic information of each group of state parameters, extracting a mapping path of the parameter characteristic information corresponding to each group of state parameters from the label similarity distribution graph of each group of state parameters based on the parameter characteristic information, and finding out the characteristic identification degree of the parameter characteristic information in the label similarity distribution graph according to the mapping path;
establishing a credibility query list between the parameter labels and the label similarity distribution graph of each group of state parameters according to the characteristic identification degree, and generating a characteristic clustering model of each group of state parameters according to the credibility query list; generating a feature clustering model according to the credibility query list, wherein the feature clustering model comprises the following steps: converting each parameter label into a corresponding character code; respectively generating at least one first coding sequence of each string of character codes; obtaining a first coding sequence of the parameter label which is not repeated with each other to form a second coding sequence; mapping each first coding sequence in the second coding sequence to the label similarity distribution graph of each group of state parameters to form a feature clustering model;
traversing and matching the label attribute contained in each parameter label of each group of state parameters with each target label attribute in the feature clustering model; if all the label attributes of a first coding sequence are matched with the corresponding target label attributes in the feature clustering model, determining the parameter label corresponding to the first coding sequence as a credible label;
and extracting the associated parameters of each group of state parameters based on the credible label to obtain an associated parameter set, clustering the associated parameters in the associated parameter set by adopting a multi-dimensional characteristic clustering method to obtain a plurality of target clusters, and calculating the parameter centrality of each group of state parameters according to the number of the target clusters.
4. The method according to claim 1, wherein calculating parameter index information corresponding to the independent node parameter set according to the parameter centrality comprises:
sorting the parameter centralities according to the sequence of the parameter centralities from large to small to obtain a centrality sorting sequence, and determining the centrality of a target parameter from the centrality sorting sequence based on the parameter structure information corresponding to the independent node parameter sets; determining a first sequence weight in the centrality of the target parameter;
judging whether the difference value between a first sequence weight in the centrality of the target parameter and a second sequence weight of the centrality of a parameter which is previous to the centrality of the target parameter is smaller than a set threshold value or not;
if so, determining the determined first sequence weight of the centrality of the target parameter as a first current sequence weight of the centrality of the target parameter; otherwise, performing weighted summation on the determined first sequence weight of the centrality of the target parameter and the second current sequence weight of the centrality of the previous parameter, and determining the weight obtained by the weighted summation as the first current sequence weight of the centrality of the target parameter; and extracting the dimension value of each state parameter in the independent node parameter set based on the first current sequence weight and calculating parameter index information corresponding to the independent node parameter set according to the extracted dimension value.
5. The utility model provides a thing networking device state detection device which characterized in that, the device includes:
the track generation module is used for generating a first running state track corresponding to the first internet of things device and a second running state track corresponding to the second internet of things device aiming at the first internet of things device and the second internet of things device of which the communication frequency is greater than the set frequency; the first running state track and the second running state track respectively comprise a plurality of state nodes with different track identification degrees;
the list determining module is used for determining the device attribute label of the first internet of things device at any state node of the first running state track, and determining the state node with the minimum track identification degree in the second running state track as the first node; mapping the device attribute label to the first node based on the difference value of the longitude and latitude coordinates of the first internet of things device and the second internet of things device to obtain a target attribute label in the first node, and generating a state association list between the first internet of things device and the second internet of things device according to a label matching coefficient between the device attribute label and the target attribute label;
the parameter migration module is used for acquiring an abnormal information list of the abnormal record and each group of state parameters of the first internet of things device in a time period corresponding to the abnormal record when the abnormal record exists in the device operation record of the second internet of things device; under the condition that the first Internet of things device is determined to contain an independent node parameter set according to the abnormal information list and the state association list, determining association degrees between each state parameter of the first Internet of things device under an associated node parameter set and each state parameter of the first Internet of things device under the independent node parameter set according to the state parameter of the first Internet of things device under the independent node parameter set and the parameter weight of the first Internet of things device, and migrating the state parameter of the first Internet of things device under the associated node parameter set and the state parameter associated with the state parameter under the independent node parameter set to the independent node parameter set;
the state detection module is used for determining the parameter centrality of each group of state parameters under the independent node parameter set, calculating the parameter index information corresponding to the independent node parameter set according to the parameter centrality, and judging that the first Internet of things device has a state abnormal risk when the parameter index information does not meet set conditions.
6. The apparatus of claim 5, wherein the parameter migration module is further configured to:
determining the association degree of the first internet of things device among the state parameters of the first internet of things device under the associated node parameter set according to the state parameters of the first internet of things device under the independent node parameter set and the parameter weight thereof under the condition that the associated node parameter set corresponding to the first internet of things device contains a plurality of state parameters;
screening the state parameters under the associated node parameter set according to the association degree between the state parameters of the associated node parameter set corresponding to the first internet of things device to obtain multiple groups of target state parameters;
and distributing a migration grade for each group of target state parameters obtained by screening according to the state parameters of the first Internet of things equipment under the independent node parameter set and the parameter weight thereof, and selecting a set number of target state parameters from regions according to the sequence of the migration grades from large to small to migrate to the independent node parameter set.
7. The apparatus according to claim 5 or 6, wherein the status detection module is specifically configured to:
acquiring parameter labels of each group of state parameters, listing the label attributes of each parameter label, and establishing a label similarity distribution graph of each group of state parameters; the label similarity distribution graph is a regional graph set, the graph set of each region corresponds to one region identifier, each region identifier has at least one label attribute, and each region of the label similarity distribution graph has an incidence relation from small to large;
determining parameter characteristic information of each group of state parameters, extracting a mapping path of the parameter characteristic information corresponding to each group of state parameters from the label similarity distribution graph of each group of state parameters based on the parameter characteristic information, and finding out the characteristic identification degree of the parameter characteristic information in the label similarity distribution graph according to the mapping path;
establishing a credibility query list between the parameter labels and the label similarity distribution graph of each group of state parameters according to the characteristic identification degree, and generating a characteristic clustering model of each group of state parameters according to the credibility query list; generating a feature clustering model according to the credibility query list, wherein the feature clustering model comprises the following steps: converting each parameter label into a corresponding character code; respectively generating at least one first coding sequence of each string of character codes; obtaining a first coding sequence of the parameter label which is not repeated with each other to form a second coding sequence; mapping each first coding sequence in the second coding sequence to the label similarity distribution graph of each group of state parameters to form a feature clustering model;
traversing and matching the label attribute contained in each parameter label of each group of state parameters with each target label attribute in the feature clustering model; if all the label attributes of a first coding sequence are matched with the corresponding target label attributes in the feature clustering model, determining the parameter label corresponding to the first coding sequence as a credible label;
and extracting the associated parameters of each group of state parameters based on the credible label to obtain an associated parameter set, clustering the associated parameters in the associated parameter set by adopting a multi-dimensional characteristic clustering method to obtain a plurality of target clusters, and calculating the parameter centrality of each group of state parameters according to the number of the target clusters.
8. The apparatus of claim 5, wherein the status detection module is specifically configured to:
sorting the parameter centralities according to the sequence of the parameter centralities from large to small to obtain a centrality sorting sequence, and determining the centrality of a target parameter from the centrality sorting sequence based on the parameter structure information corresponding to the independent node parameter sets; determining a first sequence weight in the centrality of the target parameter;
judging whether the difference value between a first sequence weight in the centrality of the target parameter and a second sequence weight of the centrality of a parameter which is previous to the centrality of the target parameter is smaller than a set threshold value or not;
if so, determining the determined first sequence weight of the centrality of the target parameter as a first current sequence weight of the centrality of the target parameter; otherwise, performing weighted summation on the determined first sequence weight of the centrality of the target parameter and the second current sequence weight of the centrality of the previous parameter, and determining the weight obtained by the weighted summation as the first current sequence weight of the centrality of the target parameter; and extracting the dimension value of each state parameter in the independent node parameter set based on the first current sequence weight and calculating parameter index information corresponding to the independent node parameter set according to the extracted dimension value.
9. A detection device, characterized in that the detection device comprises a processor and a memory communicating with each other, the processor implementing the method of any of the preceding claims 1-4 by retrieving a computer program from the memory and executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when executed, implements the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531411.9A CN111667015B (en) | 2020-06-11 | 2020-06-11 | Method and device for detecting state of equipment of Internet of things and detection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010531411.9A CN111667015B (en) | 2020-06-11 | 2020-06-11 | Method and device for detecting state of equipment of Internet of things and detection equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111667015A true CN111667015A (en) | 2020-09-15 |
| CN111667015B CN111667015B (en) | 2023-06-27 |
Family
ID=72386725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010531411.9A Active CN111667015B (en) | 2020-06-11 | 2020-06-11 | Method and device for detecting state of equipment of Internet of things and detection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111667015B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112766383A (en) * | 2021-01-22 | 2021-05-07 | 浙江工商大学 | Label enhancement method based on feature clustering and label similarity |
| CN113162830A (en) * | 2021-06-15 | 2021-07-23 | 杭州海康威视数字技术股份有限公司 | Internet of things intelligent terminal equipment discovery method and device and electronic equipment |
| WO2022082870A1 (en) * | 2020-10-23 | 2022-04-28 | 苏州聚慧邦信息科技有限公司 | Information security detection method and apparatus based on office device, and computer device |
| CN117978669A (en) * | 2024-04-01 | 2024-05-03 | 北京大学 | Heterogeneous Internet of things interaction method and device and nonvolatile storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030061213A1 (en) * | 2001-07-31 | 2003-03-27 | International Business Machines Corporation | Method for building space-splitting decision tree |
| US20100159832A1 (en) * | 2008-11-28 | 2010-06-24 | Canon Kabushiki Kaisha | Methods for managing communications of a wireless communications network, corresponding storage means and devices |
| CN107393340A (en) * | 2017-07-25 | 2017-11-24 | 维沃移动通信有限公司 | A kind of communication means and communication terminal |
| WO2018122585A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for urban road traffic incident detecting based on floating-car data |
| CN109212520A (en) * | 2018-09-29 | 2019-01-15 | 河北德冠隆电子科技有限公司 | The road conditions perception accident detection alarm system and method for comprehensive detection radar |
| US20190141485A1 (en) * | 2016-06-24 | 2019-05-09 | JIO, Inc. | Communicating location change information |
| CN111060220A (en) * | 2019-12-30 | 2020-04-24 | 中祖建设安装工程有限公司 | Intelligent construction site personnel positioning method, safety positioning equipment, storage medium and system |
| CN111181957A (en) * | 2019-12-27 | 2020-05-19 | 陈玉鋆 | Internet of things equipment security verification method and system and central control equipment |
| CN111260504A (en) * | 2020-02-11 | 2020-06-09 | 吴龙圣 | Intelligent power grid monitoring method and system and intelligent power grid controller |
-
2020
- 2020-06-11 CN CN202010531411.9A patent/CN111667015B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030061213A1 (en) * | 2001-07-31 | 2003-03-27 | International Business Machines Corporation | Method for building space-splitting decision tree |
| US20100159832A1 (en) * | 2008-11-28 | 2010-06-24 | Canon Kabushiki Kaisha | Methods for managing communications of a wireless communications network, corresponding storage means and devices |
| US20190141485A1 (en) * | 2016-06-24 | 2019-05-09 | JIO, Inc. | Communicating location change information |
| WO2018122585A1 (en) * | 2016-12-30 | 2018-07-05 | 同济大学 | Method for urban road traffic incident detecting based on floating-car data |
| CN107393340A (en) * | 2017-07-25 | 2017-11-24 | 维沃移动通信有限公司 | A kind of communication means and communication terminal |
| CN109212520A (en) * | 2018-09-29 | 2019-01-15 | 河北德冠隆电子科技有限公司 | The road conditions perception accident detection alarm system and method for comprehensive detection radar |
| CN111181957A (en) * | 2019-12-27 | 2020-05-19 | 陈玉鋆 | Internet of things equipment security verification method and system and central control equipment |
| CN111060220A (en) * | 2019-12-30 | 2020-04-24 | 中祖建设安装工程有限公司 | Intelligent construction site personnel positioning method, safety positioning equipment, storage medium and system |
| CN111260504A (en) * | 2020-02-11 | 2020-06-09 | 吴龙圣 | Intelligent power grid monitoring method and system and intelligent power grid controller |
Non-Patent Citations (2)
| Title |
|---|
| 周卫庆等: "基于灰色关联分析的电站设备状态评价方法", 《华东电力》 * |
| 王艳军等: "基于物联网传感器的城市交通状态预测", 《武汉理工大学学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022082870A1 (en) * | 2020-10-23 | 2022-04-28 | 苏州聚慧邦信息科技有限公司 | Information security detection method and apparatus based on office device, and computer device |
| CN112766383A (en) * | 2021-01-22 | 2021-05-07 | 浙江工商大学 | Label enhancement method based on feature clustering and label similarity |
| CN113162830A (en) * | 2021-06-15 | 2021-07-23 | 杭州海康威视数字技术股份有限公司 | Internet of things intelligent terminal equipment discovery method and device and electronic equipment |
| CN117978669A (en) * | 2024-04-01 | 2024-05-03 | 北京大学 | Heterogeneous Internet of things interaction method and device and nonvolatile storage medium |
| CN117978669B (en) * | 2024-04-01 | 2024-06-04 | 北京大学 | Heterogeneous Internet of things interaction method and device and nonvolatile storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111667015B (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111667015B (en) | Method and device for detecting state of equipment of Internet of things and detection equipment | |
| WO2021189729A1 (en) | Information analysis method, apparatus and device for complex relationship network, and storage medium | |
| CN111949410B (en) | Data integration method based on big data and edge calculation and cloud big data center | |
| CN105069703B (en) | A kind of electrical network mass data management method | |
| CN106936806A (en) | A kind of recognition methods of account abnormal login and device | |
| US20140156606A1 (en) | Method and System for Integrating Data Into a Database | |
| CN110210723B (en) | Electricity stealing identification method based on analytic hierarchy process and isolated forest | |
| CN111797435B (en) | Data analysis method based on Internet of things interaction and cloud computing communication and cloud server | |
| CN114004155A (en) | Transient stability assessment method and device considering topological structure characteristics of power system | |
| CN114785548B (en) | Intelligent flow monitoring platform | |
| CN112287338A (en) | Intrusion detection method and device based on ADASYN algorithm and improved convolutional neural network | |
| Shanmugam et al. | Student Psychology based optimized routing algorithm for big data clustering in IoT with MapReduce framework | |
| CN112925964A (en) | Big data acquisition method based on cloud computing service and big data acquisition service system | |
| CN117556369A (en) | Power theft detection method and system for dynamically generated residual error graph convolution neural network | |
| CN103209094A (en) | System and method for fault positioning on basis of events | |
| CN103455491A (en) | Method and device for classifying search terms | |
| CN112579755A (en) | Information response method and information interaction platform based on artificial intelligence and cloud computing | |
| CN104376000A (en) | Webpage attribute determination method and webpage attribute determination device | |
| Museba et al. | ADES: A New Ensemble Diversity‐Based Approach for Handling Concept Drift | |
| CN111740494B (en) | Data management method based on edge computing and cloud computing and edge computing platform | |
| AU2021106594A4 (en) | Online anomaly detection method and system for streaming data | |
| CN114238045A (en) | System and method for judging and automatically repairing integrity of multi-source measurement data of power grid | |
| CN112579756A (en) | Service response method based on cloud computing and block chain and artificial intelligence interaction platform | |
| Cao et al. | Research on deep mining of MOOC multimodal resources based on improved Eclat algorithm | |
| CN110401639A (en) | Abnormality determination method, device, server and its storage medium of network access |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230601 Address after: 518000 World Trade Plaza 101-1, Funan Community, Futian Street, Futian District, Shenzhen, Guangdong Province Applicant after: SHENZHEN XINGHAI IOT TECHNOLOGY Co.,Ltd. Address before: 710000 Collective, No. 18 Chang'an Middle Road, Yanta District, Xi'an City, Shaanxi Province Applicant before: Wang Yue |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |