CN111064620A - Power grid multimedia conference room equipment maintenance method and system based on operation and maintenance knowledge base - Google Patents
Power grid multimedia conference room equipment maintenance method and system based on operation and maintenance knowledge base Download PDFInfo
- Publication number
- CN111064620A CN111064620A CN201911330280.1A CN201911330280A CN111064620A CN 111064620 A CN111064620 A CN 111064620A CN 201911330280 A CN201911330280 A CN 201911330280A CN 111064620 A CN111064620 A CN 111064620A
- Authority
- CN
- China
- Prior art keywords
- operation data
- equipment
- conference room
- maintenance
- power grid
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/02—Standardisation; Integration
- H04L41/0246—Exchanging or transporting network management information using the Internet; Embedding network management web servers in network elements; Web-services-based protocols
- H04L41/0253—Exchanging or transporting network management information using the Internet; Embedding network management web servers in network elements; Web-services-based protocols using browsers or web-pages for accessing management information
-
- 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
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L41/0645—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis by additionally acting on or stimulating the network after receiving notifications
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a method and a system for maintaining equipment in a power grid multimedia conference room based on an operation and maintenance knowledge base, wherein the method comprises the following steps: acquiring operation data information of the power grid multimedia conference room equipment based on a sensor arranged on the power grid multimedia conference room equipment, and uploading the acquired operation data information to an operation and maintenance server; when the operation data information is judged to be abnormal, matching the abnormal operation data information with the equipment operation data in the operation and maintenance knowledge base to obtain mutually matched equipment operation data; acquiring retrieval keywords based on the matched equipment operation data, and calling a corresponding fault processing scheme in an operation and maintenance knowledge base according to the labels of the retrieval keywords; and carrying out probability prediction and visualization on the corresponding fault processing scheme, and pushing the visualization processing result to the management user terminal. In the embodiment of the invention, the condition of multiple devices is monitored in real time, and the related processing scheme is pushed in real time according to the fault condition of the devices.
Description
Technical Field
The invention relates to the technical field of intelligent pushing of equipment maintenance schemes, in particular to a method and a system for maintaining equipment in a power grid multimedia conference room based on an operation and maintenance knowledge base.
Background
With the continuous increase of the number of the multimedia meeting rooms of the power grid, meeting place equipment is more and more, on-site operation and maintenance personnel are not enough to support the operation and maintenance of multiple meeting places, new personnel cannot keep up with the technology, and the equipment is more and more difficult to maintain; at present, the state of equipment is urgently needed to be monitored in real time by butting power grid multimedia conference room equipment through an operation and maintenance knowledge base system, a processing scheme is provided for fault equipment, the defects of field maintenance personnel are overcome, the maintenance cost is reduced, and the maintenance quality is guaranteed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a method and a system for maintaining equipment in a power grid multimedia conference room based on an operation and maintenance knowledge base, which can realize real-time monitoring of the conditions of multiple equipment and push related processing schemes according to the equipment fault conditions in real time.
In order to solve the technical problem, an embodiment of the present invention provides an operation and maintenance knowledge base-based power grid multimedia conference room equipment maintenance method, where the method includes:
acquiring operation data information of the power grid multimedia conference room equipment based on a sensor arranged on the power grid multimedia conference room equipment, and uploading the acquired operation data information to an operation and maintenance server based on an HTTP (hyper text transport protocol);
the operation and maintenance server judges whether the operation data information is abnormal or not;
if the abnormal operation data exists, the operation and maintenance server matches the abnormal operation data information with the equipment operation data in the operation and maintenance knowledge base to obtain the equipment operation data matched with each other;
acquiring retrieval keywords based on the matched equipment operation data, and calling a corresponding fault processing scheme in the operation and maintenance knowledge base according to the labels of the retrieval keywords;
and carrying out probability prediction on the corresponding fault processing scheme, carrying out visualization processing according to the prediction result, and pushing the visualization processing result to the management user terminal.
Optionally, the step of updating the data of the operation and maintenance knowledge base includes:
crawling a related fault processing scheme of the power grid multimedia conference room equipment on the Internet based on a crawler algorithm, and carrying out unique coding labeling on the related fault processing scheme according to a crawling time sequence;
extracting retrieval keywords and equipment operation data from the related fault processing scheme based on an NLP algorithm analysis model, and labeling the extracted retrieval keywords and the equipment operation data according to the uniqueness code of the related fault processing scheme;
clustering the marked retrieval keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and dividing the equipment operation data into K clusters;
and respectively establishing full-text indexes of the retrieval keywords and the related fault handling schemes in the K clusters based on an index engine, and updating the full-text indexes to the operation and maintenance knowledge base.
Optionally, before the extracting and processing the retrieval key and the device operation data of the related fault processing scheme based on the NLP algorithm analysis model, the method includes:
and the input end of the NLP algorithm analysis model splits the related fault processing scheme into short texts in segments or sentences.
Optionally, the clustering process is performed on the labeled search keywords and the equipment operation data by using a Canopy-measures clustering algorithm with the equipment operation data as a center, and the equipment operation data is divided into K clusters, including:
carrying out preliminary coarse clustering on the marked retrieval keywords and the equipment operation data by using a Canopy clustering algorithm and taking the equipment operation data as a center to obtain K Canopy centers and preliminary clusters;
and clustering by taking the K Canopy centers and the preliminary cluster as the mass center of a Kmeans clustering algorithm, and dividing the equipment operation data into K clusters.
Optionally, the performing probability prediction on the fault handling scheme corresponding to the fetching includes:
and performing probability prediction on the corresponding fault processing scheme based on the Bayesian probability prediction model.
Optionally, the bayesian probability prediction model formula for performing probability prediction on the corresponding fault handling scheme based on the bayesian probability prediction model is as follows:
in the corresponding failure handling scheme T<A1,A2,A3,…,An>In case of possible selection of ViThe conditional probability selected as a fault handling scheme can be expressed by the following equation:
and the corresponding failure handling scheme T<A1,A2,A3,…,An>Are independent of each other, then:
substituting equation (2) and equation (3) into equation (1) yields:
the conditional probability V of the possibly selected scheme as the fault handling scheme can be calculated through the formula (4)i；
Wherein, T<A1,A2,A3,…,An>Indicates the corresponding fault handling scheme, AnRepresenting an nth corresponding fault handling scheme; viRepresenting the conditional probability selected as a fault handling scheme; 1,2,3, …, m; j is 1,2,3, …, n.
Optionally, the performing visualization processing according to the prediction result includes:
sorting the prediction results in a descending sorting mode to obtain sorted prediction results;
and performing visualization processing on the sequenced prediction results according to a probability map mode.
Optionally, the pushing the visualization processing result to the management user terminal includes:
and pushing the visualization processing result to a management user terminal based on an HTTP transmission protocol.
Optionally, the method further includes:
and pushing the visual processing result to the mobile terminal of the management user in a multimedia message mode based on the mobile number bound by the management user.
In addition, the embodiment of the invention also provides a system for recommending the maintenance scheme of the equipment in the multimedia conference room of the power grid based on the operation and maintenance knowledge base, which comprises the following steps:
a data acquisition module: the system comprises a power grid multimedia conference room device, an operation maintenance server and a data acquisition and processing device, wherein the power grid multimedia conference room device is used for acquiring operation data information of the power grid multimedia conference room device based on a sensor arranged on the power grid multimedia conference room device and uploading the acquired operation data information to the operation maintenance server based on an HTTP (hyper text transport protocol);
a judging module: the operation and maintenance server is used for judging whether the operation data information is abnormal or not;
a matching module: the operation and maintenance server is used for matching abnormal operation data information with equipment operation data in the operation and maintenance knowledge base if the abnormality exists, and obtaining mutually matched equipment operation data;
a scheme calling module: the system comprises an operation and maintenance knowledge base and a fault processing database, wherein the operation and maintenance knowledge base is used for acquiring search keywords based on mutually matched equipment operation data and calling corresponding fault processing schemes in the operation and maintenance knowledge base according to labels of the search keywords;
a prediction and push module: and the system is used for carrying out probability prediction on the called corresponding fault processing scheme, carrying out visual processing according to the prediction result and pushing the visual processing result to the management user terminal.
In the embodiment of the invention, the operation data information of the power grid multimedia conference room equipment is collected in real time, whether the operation data information is abnormal or not is judged, and if the operation data information is abnormal, the operation data information is matched in an operation and maintenance knowledge base to obtain the equipment operation data matched with each other; calling a corresponding fault processing scheme according to the retrieval key words corresponding to the matched equipment operation data; the method has the advantages that the method is visually recommended to a management user terminal after the probability prediction is carried out on the corresponding fault processing scheme, so that the real-time monitoring of the multi-equipment condition is realized, and the related processing scheme is pushed according to the equipment fault condition in real time; after the relevant processing scheme is provided, corresponding maintenance personnel can quickly maintain, the problem of insufficient field maintenance personnel is effectively solved, the maintenance cost is reduced, the maintenance quality is guaranteed, the maintenance efficiency is improved, and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for maintaining equipment in a multimedia conference room of a power grid in an embodiment of the present invention;
fig. 2 is a schematic structural component diagram of a system for recommending a device maintenance scheme in a multimedia conference room of a power grid in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for maintaining equipment in a multimedia conference room of a power grid according to an embodiment of the present invention.
As shown in fig. 1, a method for maintaining equipment in a multimedia conference room of a power grid based on an operation and maintenance knowledge base includes:
s11: acquiring operation data information of the power grid multimedia conference room equipment based on a sensor arranged on the power grid multimedia conference room equipment;
in the specific implementation process of the invention, corresponding sensors are arranged on the power grid multimedia conference room equipment and are used for acquiring the operation data information on the power grid multimedia conference room equipment, and the operation data information on the power grid multimedia conference room equipment is acquired in real time.
S12: uploading the collected operation data information to an operation and maintenance server based on an HTTP (hyper text transport protocol);
in the specific implementation process of the invention, the collected operation data information is uploaded to the operation and maintenance server through an HTTP transmission protocol.
The HTTP Transfer Protocol (HyperText Transfer Protocol) is a HyperText Transfer Protocol; is a network protocol which is most widely applied on the Internet; the HTTP transport protocol is based on a request/response paradigm. After a client establishes connection with a server, a request is sent to the server in the format of Uniform Resource Identifier (URI), protocol version number and MIME information including request modifier, client information and possible contents. After receiving the request, the server gives a corresponding response message in the format of a status line including the protocol version number of the message, a successful or erroneous code, followed by MIME information including server information, entity information and possibly contents.
S13: the operation and maintenance server judges whether the operation data information is abnormal or not;
in the specific implementation process of the invention, the operation and maintenance server receives the operation data information, compares the operation data information with a preset data range to judge whether the operation data information is abnormal or not, if so, enters the next step, and if not, returns to the previous step.
S14: if the abnormal operation data exists, the operation and maintenance server matches the abnormal operation data information with the equipment operation data in the operation and maintenance knowledge base to obtain the equipment operation data matched with each other;
in the specific implementation process of the present invention, the step of updating the data of the operation and maintenance knowledge base includes: crawling a related fault processing scheme of the power grid multimedia conference room equipment on the Internet based on a crawler algorithm, and carrying out unique coding labeling on the related fault processing scheme according to a crawling time sequence; extracting retrieval keywords and equipment operation data from the related fault processing scheme based on an NLP algorithm analysis model, and labeling the extracted retrieval keywords and the equipment operation data according to the uniqueness code of the related fault processing scheme; clustering the marked retrieval keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and dividing the equipment operation data into K clusters; and respectively establishing full-text indexes of the retrieval keywords and the related fault handling schemes in the K clusters based on an index engine, and updating the full-text indexes to the operation and maintenance knowledge base.
Further, before the extracting and processing the retrieval key words and the device operation data of the related fault processing scheme based on the NLP algorithm analysis model, the method includes: and the input end of the NLP algorithm analysis model splits the related fault processing scheme into short texts in segments or sentences.
Further, the clustering processing is performed on the labeled search keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and the equipment operation data is divided into K clusters, including: carrying out preliminary coarse clustering on the marked retrieval keywords and the equipment operation data by using a Canopy clustering algorithm and taking the equipment operation data as a center to obtain K Canopy centers and preliminary clusters; and clustering by taking the K Canopy centers and the preliminary cluster as the mass center of a Kmeans clustering algorithm, and dividing the equipment operation data into K clusters.
Specifically, the operation and maintenance server matches the operation data information judged to be abnormal with the equipment operation data in the operation and maintenance knowledge base, so as to obtain the equipment operation data matched with each other.
The operation and maintenance knowledge base needs to be continuously updated, because the equipment has different problems, different maintenance schemes or the same problem and different maintenance schemes, specifically, the operation and maintenance knowledge base is updated by crawling the fault processing schemes related to the power grid multimedia conference room equipment on the internet by using a crawler algorithm, uniquely coding and marking the fault processing schemes according to the crawling time sequence, and then extracting retrieval keywords and equipment operation data from the obtained related fault processing schemes by using an NLP algorithm analysis model; marking the extracted retrieval key words and the equipment operation data according to the serial number of the fault processing scheme; clustering the extracted retrieval keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and dividing the equipment operation data into K clusters; and then, establishing full-text indexes of the K clusters and the fault processing scheme by using an index engine, and storing the full-text indexes in the operation and maintenance database.
The NLP algorithm analysis model adopts an input, mapping (hiding) and output architecture, wherein the entire fault processing scheme is output from an input end, and extracted retrieval keywords and equipment operation data are output from an output end; specifically, the whole fault processing scheme between input ends in the model is divided into a section of text or a sentence of words, and then a hidden layer is multiplied by a weight matrix to output search keywords and equipment operation data.
Clustering by using a Canopy-Kmeans clustering algorithm, specifically, carrying out primary coarse clustering by using the Canopy clustering algorithm to obtain a plurality of Canopy centers (K in order) and primary clusters, using the K Canopy centers as the centroid of the Kmeans clustering algorithm and the primary clusters as input, and clustering to obtain final clusters; the parallelization improvement idea of the Canopy clustering algorithm and the Kmeans clustering algorithm is to perform local clustering algorithms on search keywords and equipment operation data respectively, and then combine local clustering results after simple calculation to obtain global clustering.
In the embodiment of the invention, if only a Kmeans clustering algorithm is adopted for clustering, the k value needs to be adjusted, and the results obtained by different values are different; the method is sensitive to an initial centroid point, and the influence of outliers on a model is large; not suitable for non-convex shaped clusters, clusters with large size difference; may converge to a local minimum, with slower convergence on large-scale datasets; canopy belongs to a 'rough' clustering algorithm, namely, a simple and quick distance calculation method is used for dividing a data set into a plurality of overlapped subsets Canopy, the algorithm does not need to specify a k value, but has low precision, and can be used together with a Kmeans algorithm: carrying out rough clustering by using a Canopy algorithm to obtain k centroids, and then carrying out clustering by using a Kmeans algorithm; therefore, the technical problem existing in clustering by adopting a Kmeans clustering algorithm can be solved; the method can quickly cluster in the big data set and has good clustering effect.
S15: acquiring retrieval keywords based on the matched equipment operation data, and calling a corresponding fault processing scheme in the operation and maintenance knowledge base according to the labels of the retrieval keywords;
in the specific implementation process of the invention, the related search keywords are obtained through the cluster taking the mutually matched device operation data as the center, and the corresponding fault processing scheme is directly called in the operation and maintenance knowledge base according to the labels of the obtained search keywords.
S16: and carrying out probability prediction on the corresponding fault processing scheme, carrying out visualization processing according to the prediction result, and pushing the visualization processing result to the management user terminal.
In the specific implementation process of the present invention, the probability prediction of the fault handling scheme corresponding to the fetch includes: and performing probability prediction on the corresponding fault processing scheme based on the Bayesian probability prediction model.
Further, the bayesian probability prediction model formula for performing probability prediction on the fault processing scheme based on the bayesian probability prediction model is as follows: in the corresponding failure handling scheme T<A1,A2,A3,…,An>In case of possible selection of ViThe conditional probability selected as a fault handling scheme can be expressed by the following equation:
and the corresponding failure handling scheme T<A1,A2,A3,…,An>Are independent of each other, then:
substituting equation (2) and equation (3) into equation (1) yields:
the conditional probability V of the possibly selected scheme as the fault handling scheme can be calculated through the formula (4)i；
Wherein, T<A1,A2,A3,…,An>Indicates the corresponding fault handling scheme, AnRepresenting an nth corresponding fault handling scheme; viRepresenting the conditional probability selected as a fault handling scheme; 1,2,3, …, m; j is 1,2,3, …, n.
Further, the performing visualization processing according to the prediction result includes: sorting the prediction results in a descending sorting mode to obtain sorted prediction results; and performing visualization processing on the sequenced prediction results according to a probability map mode.
Further, the pushing the visualization processing result to the management user terminal includes: and pushing the visualization processing result to a management user terminal based on an HTTP transmission protocol.
Specifically, the probability prediction of the corresponding fault processing scheme is carried out by adopting a Bayesian probability prediction model, and the specific prediction model formula is as follows:
in the corresponding failure handling scheme T<A1,A2,A3,…,An>In case of possible selection of ViThe conditional probability selected as a fault handling scheme can be expressed by the following equation:
and the corresponding failure handling scheme T<A1,A2,A3,…,An>Are independent of each other, then:
substituting equation (2) and equation (3) into equation (1) yields:
the conditional probability V of the possibly selected scheme as the fault handling scheme can be calculated through the formula (4)i；
Wherein, T<A1,A2,A3,…,An>Indicates the corresponding fault handling scheme, AnRepresenting an nth corresponding fault handling scheme; viRepresenting the conditional probability selected as a fault handling scheme; 1,2,3, …, m; j is 1,2,3, …, n.
The Bayesian probability model is used for prediction, complex learning updating is not needed to be carried out on a large amount of historical data when the Bayesian probability model is used for prediction compared with some existing self-learning models, workload in the early stage is not needed to be increased, a large amount of work such as model construction, data learning and model adjustment in the early stage can be reduced by using the Bayesian probability model under the condition that the prediction accuracy is guaranteed, and the workload can be reduced under the condition that the prediction accuracy is guaranteed.
Specifically, the probabilities of the corresponding fault handling schemes predicted by the bayesian probability model are sorted, and specifically, sorting methods such as descending sorting can be adopted; obtaining a probability ordering result of the corresponding fault handling scheme; then, carrying out visual processing on the sequencing result of the probability of the corresponding fault processing scheme according to a probability map mode; after the visualization processing is completed, the information is transmitted to a designated manager terminal through an HTTP transmission protocol for display.
In the specific implementation process of the invention, the method further comprises the following steps: and pushing the visual processing result to the mobile terminal of the management user in a multimedia message mode based on the mobile number bound by the management user.
Specifically, the mobile number can be bound by the manager, and the sequencing result is directly pushed to the manager mobile terminal in a short message manner for prompting.
In the embodiment of the invention, the operation data information of the power grid multimedia conference room equipment is collected in real time, whether the operation data information is abnormal or not is judged, and if the operation data information is abnormal, the operation data information is matched in an operation and maintenance knowledge base to obtain the equipment operation data matched with each other; calling a corresponding fault processing scheme according to the retrieval key words corresponding to the matched equipment operation data; the method has the advantages that the method is visually recommended to a management user terminal after the probability prediction is carried out on the corresponding fault processing scheme, so that the real-time monitoring of the multi-equipment condition is realized, and the related processing scheme is pushed according to the equipment fault condition in real time; after the relevant processing scheme is provided, corresponding maintenance personnel can quickly maintain, the problem of insufficient field maintenance personnel is effectively solved, the maintenance cost is reduced, the maintenance quality is guaranteed, the maintenance efficiency is improved, and the like.
Examples
Referring to fig. 2, fig. 2 is a schematic structural component diagram of a system for recommending a device maintenance scheme for a multimedia conference room of a power grid according to an embodiment of the present invention.
As shown in fig. 2, a system for recommending a maintenance plan of a multimedia conference room device of a power grid based on an operation and maintenance knowledge base, the system comprising:
the data acquisition module 11: the system comprises a power grid multimedia conference room device, an operation maintenance server and a data acquisition and processing device, wherein the power grid multimedia conference room device is used for acquiring operation data information of the power grid multimedia conference room device based on a sensor arranged on the power grid multimedia conference room device and uploading the acquired operation data information to the operation maintenance server based on an HTTP (hyper text transport protocol);
in the specific implementation process of the invention, corresponding sensors are arranged on the power grid multimedia conference room equipment and are used for acquiring the operation data information on the power grid multimedia conference room equipment, and the operation data information on the power grid multimedia conference room equipment is acquired in real time.
In the specific implementation process of the invention, the collected operation data information is uploaded to the operation and maintenance server through an HTTP transmission protocol.
The HTTP Transfer Protocol (HyperText Transfer Protocol) is a HyperText Transfer Protocol; is a network protocol which is most widely applied on the Internet; the HTTP transport protocol is based on a request/response paradigm. After a client establishes connection with a server, a request is sent to the server in the format of Uniform Resource Identifier (URI), protocol version number and MIME information including request modifier, client information and possible contents. After receiving the request, the server gives a corresponding response message in the format of a status line including the protocol version number of the message, a successful or erroneous code, followed by MIME information including server information, entity information and possibly contents.
The judging module 12: the operation and maintenance server is used for judging whether the operation data information is abnormal or not;
in the specific implementation process of the invention, the operation and maintenance server receives the operation data information, compares the operation data information with a preset data range to judge whether the operation data information is abnormal or not, if so, enters the next step, and if not, returns to the previous step.
The matching module 13: the operation and maintenance server is used for matching abnormal operation data information with equipment operation data in the operation and maintenance knowledge base if the abnormality exists, and obtaining mutually matched equipment operation data;
in the specific implementation process of the present invention, the step of updating the data of the operation and maintenance knowledge base includes: crawling a related fault processing scheme of the power grid multimedia conference room equipment on the Internet based on a crawler algorithm, and carrying out unique coding labeling on the related fault processing scheme according to a crawling time sequence; extracting retrieval keywords and equipment operation data from the related fault processing scheme based on an NLP algorithm analysis model, and labeling the extracted retrieval keywords and the equipment operation data according to the uniqueness code of the related fault processing scheme; clustering the marked retrieval keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and dividing the equipment operation data into K clusters; and respectively establishing full-text indexes of the retrieval keywords and the related fault handling schemes in the K clusters based on an index engine, and updating the full-text indexes to the operation and maintenance knowledge base.
Further, before the extracting and processing the retrieval key words and the device operation data of the related fault processing scheme based on the NLP algorithm analysis model, the method includes: and the input end of the NLP algorithm analysis model splits the related fault processing scheme into short texts in segments or sentences.
Further, the clustering processing is performed on the labeled search keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and the equipment operation data is divided into K clusters, including: carrying out preliminary coarse clustering on the marked retrieval keywords and the equipment operation data by using a Canopy clustering algorithm and taking the equipment operation data as a center to obtain K Canopy centers and preliminary clusters; and clustering by taking the K Canopy centers and the preliminary cluster as the mass center of a Kmeans clustering algorithm, and dividing the equipment operation data into K clusters.
Specifically, the operation and maintenance server matches the operation data information judged to be abnormal with the equipment operation data in the operation and maintenance knowledge base, so as to obtain the equipment operation data matched with each other.
The operation and maintenance knowledge base needs to be continuously updated, because the equipment has different problems, different maintenance schemes or the same problem and different maintenance schemes, specifically, the operation and maintenance knowledge base is updated by crawling the fault processing schemes related to the power grid multimedia conference room equipment on the internet by using a crawler algorithm, uniquely coding and marking the fault processing schemes according to the crawling time sequence, and then extracting retrieval keywords and equipment operation data from the obtained related fault processing schemes by using an NLP algorithm analysis model; marking the extracted retrieval key words and the equipment operation data according to the serial number of the fault processing scheme; clustering the extracted retrieval keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and dividing the equipment operation data into K clusters; and then, establishing full-text indexes of the K clusters and the fault processing scheme by using an index engine, and storing the full-text indexes in the operation and maintenance database.
The NLP algorithm analysis model adopts an input, mapping (hiding) and output architecture, wherein the entire fault processing scheme is output from an input end, and extracted retrieval keywords and equipment operation data are output from an output end; specifically, the whole fault processing scheme between input ends in the model is divided into a section of text or a sentence of words, and then a hidden layer is multiplied by a weight matrix to output search keywords and equipment operation data.
Clustering by using a Canopy-Kmeans clustering algorithm, specifically, carrying out primary coarse clustering by using the Canopy clustering algorithm to obtain a plurality of Canopy centers (K in order) and primary clusters, using the K Canopy centers as the centroid of the Kmeans clustering algorithm and the primary clusters as input, and clustering to obtain final clusters; the parallelization improvement idea of the Canopy clustering algorithm and the Kmeans clustering algorithm is to perform local clustering algorithms on search keywords and equipment operation data respectively, and then combine local clustering results after simple calculation to obtain global clustering.
In the embodiment of the invention, if only a Kmeans clustering algorithm is adopted for clustering, the k value needs to be adjusted, and the results obtained by different values are different; the method is sensitive to an initial centroid point, and the influence of outliers on a model is large; not suitable for non-convex shaped clusters, clusters with large size difference; may converge to a local minimum, with slower convergence on large-scale datasets; canopy belongs to a 'rough' clustering algorithm, namely, a simple and quick distance calculation method is used for dividing a data set into a plurality of overlapped subsets Canopy, the algorithm does not need to specify a k value, but has low precision, and can be used together with a Kmeans algorithm: carrying out rough clustering by using a Canopy algorithm to obtain k centroids, and then carrying out clustering by using a Kmeans algorithm; therefore, the technical problem existing in clustering by adopting a Kmeans clustering algorithm can be solved; the method can quickly cluster in the big data set and has good clustering effect.
The scenario retrieval module 14: the system comprises an operation and maintenance knowledge base and a fault processing database, wherein the operation and maintenance knowledge base is used for acquiring search keywords based on mutually matched equipment operation data and calling corresponding fault processing schemes in the operation and maintenance knowledge base according to labels of the search keywords;
in the specific implementation process of the invention, the related search keywords are obtained through the cluster taking the mutually matched device operation data as the center, and the corresponding fault processing scheme is directly called in the operation and maintenance knowledge base according to the labels of the obtained search keywords.
The prediction and push module 15: and the system is used for carrying out probability prediction on the called corresponding fault processing scheme, carrying out visual processing according to the prediction result and pushing the visual processing result to the management user terminal.
In the specific implementation process of the present invention, the probability prediction of the fault handling scheme corresponding to the fetch includes: and performing probability prediction on the corresponding fault processing scheme based on the Bayesian probability prediction model.
Further, the bayesian probability prediction model formula for performing probability prediction on the fault processing scheme based on the bayesian probability prediction model is as follows: in the corresponding failure handling scheme T<A1,A2,A3,…,An>In case of possible selection of ViThe conditional probability selected as a fault handling scheme can be expressed by the following equation:
and the corresponding failure handling scheme T<A1,A2,A3,…,An>Are independent of each other, then:
substituting equation (2) and equation (3) into equation (1) yields:
the conditional probability V of the possibly selected scheme as the fault handling scheme can be calculated through the formula (4)i；
Wherein, T<A1,A2,A3,…,An>Indicates the corresponding fault handling scheme, AnRepresenting an nth corresponding fault handling scheme; viRepresenting the conditional probability selected as a fault handling scheme; 1,2,3, …, m; j is 1,2,3, …, n.
Further, the performing visualization processing according to the prediction result includes: sorting the prediction results in a descending sorting mode to obtain sorted prediction results; and performing visualization processing on the sequenced prediction results according to a probability map mode.
Further, the pushing the visualization processing result to the management user terminal includes: and pushing the visualization processing result to a management user terminal based on an HTTP transmission protocol.
Specifically, the probability prediction of the corresponding fault processing scheme is carried out by adopting a Bayesian probability prediction model, and the specific prediction model formula is as follows:
in the corresponding failure handling scheme T<A1,A2,A3,…,An>In case of possible selection of ViThe conditional probability selected as a fault handling scheme can be expressed by the following equation:
and the corresponding failure handling scheme T<A1,A2,A3,…,An>Are independent of each other, then:
substituting equation (2) and equation (3) into equation (1) yields:
the conditional probability V of the possibly selected scheme as the fault handling scheme can be calculated through the formula (4)i；
Wherein, T<A1,A2,A3,…,An>Indicates the corresponding fault handling scheme, AnRepresenting an nth corresponding fault handling scheme; viRepresenting the conditional probability selected as a fault handling scheme; 1,2,3, …, m; j is 1,2,3, …, N.
The Bayesian probability model is used for prediction, complex learning updating is not needed to be carried out on a large amount of historical data when the Bayesian probability model is used for prediction compared with some existing self-learning models, workload in the early stage is not needed to be increased, a large amount of work such as model construction, data learning and model adjustment in the early stage can be reduced by using the Bayesian probability model under the condition that the prediction accuracy is guaranteed, and the workload can be reduced under the condition that the prediction accuracy is guaranteed.
Specifically, the probabilities of the corresponding fault handling schemes predicted by the bayesian probability model are sorted, and specifically, sorting methods such as descending sorting can be adopted; obtaining a probability ordering result of the corresponding fault handling scheme; then, carrying out visual processing on the sequencing result of the probability of the corresponding fault processing scheme according to a probability map mode; after the visualization processing is completed, the information is transmitted to a designated manager terminal through an HTTP transmission protocol for display.
In the specific implementation process of the invention, the method further comprises the following steps: and pushing the visual processing result to the mobile terminal of the management user in a multimedia message mode based on the mobile number bound by the management user.
Specifically, the mobile number can be bound by the manager, and the sequencing result is directly pushed to the manager mobile terminal in a short message manner for prompting.
In the embodiment of the invention, the operation data information of the power grid multimedia conference room equipment is collected in real time, whether the operation data information is abnormal or not is judged, and if the operation data information is abnormal, the operation data information is matched in an operation and maintenance knowledge base to obtain the equipment operation data matched with each other; calling a corresponding fault processing scheme according to the retrieval key words corresponding to the matched equipment operation data; the method has the advantages that the method is visually recommended to a management user terminal after the probability prediction is carried out on the corresponding fault processing scheme, so that the real-time monitoring of the multi-equipment condition is realized, and the related processing scheme is pushed according to the equipment fault condition in real time; after the relevant processing scheme is provided, corresponding maintenance personnel can quickly maintain, the problem of insufficient field maintenance personnel is effectively solved, the maintenance cost is reduced, the maintenance quality is guaranteed, the maintenance efficiency is improved, and the like.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, or the like.
In addition, the method and the system for maintaining the equipment in the multimedia conference room of the power grid based on the operation and maintenance knowledge base provided by the embodiment of the invention are described in detail, a specific embodiment is adopted to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A power grid multimedia conference room equipment maintenance method based on an operation and maintenance knowledge base is characterized by comprising the following steps:
acquiring operation data information of the power grid multimedia conference room equipment based on a sensor arranged on the power grid multimedia conference room equipment, and uploading the acquired operation data information to an operation and maintenance server based on an HTTP (hyper text transport protocol);
the operation and maintenance server judges whether the operation data information is abnormal or not;
if the abnormal operation data exists, the operation and maintenance server matches the abnormal operation data information with the equipment operation data in the operation and maintenance knowledge base to obtain the equipment operation data matched with each other;
acquiring retrieval keywords based on the matched equipment operation data, and calling a corresponding fault processing scheme in the operation and maintenance knowledge base according to the labels of the retrieval keywords;
and carrying out probability prediction on the corresponding fault processing scheme, carrying out visualization processing according to the prediction result, and pushing the visualization processing result to the management user terminal.
2. The method for maintaining the equipment in the power grid multimedia conference room as claimed in claim 1, wherein the operation and maintenance knowledge base comprises a data updating step, specifically:
crawling a related fault processing scheme of the power grid multimedia conference room equipment on the Internet based on a crawler algorithm, and carrying out unique coding labeling on the related fault processing scheme according to a crawling time sequence;
extracting retrieval keywords and equipment operation data from the related fault processing scheme based on an NLP algorithm analysis model, and labeling the extracted retrieval keywords and the equipment operation data according to the uniqueness code of the related fault processing scheme;
clustering the marked retrieval keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and dividing the equipment operation data into K clusters;
and respectively establishing full-text indexes of the retrieval keywords and the related fault handling schemes in the K clusters based on an index engine, and updating the full-text indexes to the operation and maintenance knowledge base.
3. The method for maintaining the equipment in the power grid multimedia conference room according to claim 2, wherein before the extracting and processing of the retrieval keywords and the equipment operation data of the related fault processing scheme based on the NLP algorithm analysis model, the method comprises:
and the input end of the NLP algorithm analysis model splits the related fault processing scheme into short texts in segments or sentences.
4. The method for maintaining the equipment in the power grid multimedia conference room as claimed in claim 2, wherein the step of clustering the labeled search keywords and the equipment operation data by using a Canopy-Kmeans clustering algorithm with the equipment operation data as a center, and the step of dividing the equipment operation data into K clusters comprises the steps of:
carrying out preliminary coarse clustering on the marked retrieval keywords and the equipment operation data by using a Canopy clustering algorithm and taking the equipment operation data as a center to obtain K Canopy centers and preliminary clusters;
and clustering by taking the K Canopy centers and the preliminary cluster as the mass center of a Kmeans clustering algorithm, and dividing the equipment operation data into K clusters.
5. The method for maintaining equipment in a power grid multimedia conference room as claimed in claim 2, wherein the probabilistically predicting the corresponding fault handling scheme to be called comprises:
and performing probability prediction on the corresponding fault processing scheme based on the Bayesian probability prediction model.
6. The grid multimedia conference room equipment maintenance method according to claim 5, wherein the Bayesian probability prediction model formula for probability prediction of the corresponding failure handling scheme is based on a Bayesian probability prediction model is as follows:
in the corresponding fault handling scheme T < A1，A2，A3，…，AnIn case V may be selectediThe conditional probability selected as a fault handling scheme can be expressed by the following equation:
and the corresponding failure handling scheme T < A1，A2，A3，…，AnAre independent of each other, then:
substituting equation (2) and equation (3) into equation (1) yields:
the conditional probability V of the possibly selected scheme as the fault handling scheme can be calculated through the formula (4)i；
Wherein T is less than A1，A2，A3，…，AnDenotes the corresponding failure handling scheme, AnRepresenting an nth corresponding fault handling scheme; viRepresenting the conditional probability selected as a fault handling scheme; 1,2,3, …, m; j is 1,2,3, …, n.
7. The method for maintaining equipment in a power grid multimedia conference room as claimed in claim 2, wherein the visualizing process according to the prediction result comprises:
sorting the prediction results in a descending sorting mode to obtain sorted prediction results;
and performing visualization processing on the sequenced prediction results according to a probability map mode.
8. The method for maintaining the equipment in the power grid multimedia conference room as claimed in claim 2, wherein the step of pushing the visualization processing result to the management user terminal comprises:
and pushing the visualization processing result to a management user terminal based on an HTTP transmission protocol.
9. The grid multimedia conference room equipment maintenance method according to claim 8, further comprising:
and pushing the visual processing result to the mobile terminal of the management user in a multimedia message mode based on the mobile number bound by the management user.
10. A power grid multimedia conference room equipment maintenance system based on an operation and maintenance knowledge base is characterized by comprising:
a data acquisition module: the system comprises a power grid multimedia conference room device, an operation maintenance server and a data acquisition and processing device, wherein the power grid multimedia conference room device is used for acquiring operation data information of the power grid multimedia conference room device based on a sensor arranged on the power grid multimedia conference room device and uploading the acquired operation data information to the operation maintenance server based on an HTTP (hyper text transport protocol);
a judging module: the operation and maintenance server is used for judging whether the operation data information is abnormal or not;
a matching module: the operation and maintenance server is used for matching abnormal operation data information with equipment operation data in the operation and maintenance knowledge base if the abnormality exists, and obtaining mutually matched equipment operation data;
a scheme calling module: the system comprises an operation and maintenance knowledge base and a fault processing database, wherein the operation and maintenance knowledge base is used for acquiring search keywords based on mutually matched equipment operation data and calling corresponding fault processing schemes in the operation and maintenance knowledge base according to labels of the search keywords;
a prediction and push module: and the system is used for carrying out probability prediction on the called corresponding fault processing scheme, carrying out visual processing according to the prediction result and pushing the visual processing result to the management user terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911330280.1A CN111064620A (en) | 2019-12-20 | 2019-12-20 | Power grid multimedia conference room equipment maintenance method and system based on operation and maintenance knowledge base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911330280.1A CN111064620A (en) | 2019-12-20 | 2019-12-20 | Power grid multimedia conference room equipment maintenance method and system based on operation and maintenance knowledge base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111064620A true CN111064620A (en) | 2020-04-24 |
Family
ID=70302526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911330280.1A Pending CN111064620A (en) | 2019-12-20 | 2019-12-20 | Power grid multimedia conference room equipment maintenance method and system based on operation and maintenance knowledge base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111064620A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148897A (en) * | 2020-09-14 | 2020-12-29 | 深圳供电局有限公司 | Automatic retrieval and classification method and system for fault information of power system |
| CN112348707A (en) * | 2020-10-24 | 2021-02-09 | 广东冠雄建设集团有限公司 | Holographic intelligent building energy-saving operation and maintenance management system based on BIM model |
| CN113099242A (en) * | 2021-06-09 | 2021-07-09 | 广东电网有限责任公司湛江供电局 | Power transmission line video monitoring data processing method and system |
| CN113132352A (en) * | 2021-03-17 | 2021-07-16 | 中国人民解放军战略支援部队信息工程大学 | Router threat perception method and system based on flow statistical characteristics |
| CN113835401A (en) * | 2021-08-11 | 2021-12-24 | 深圳优制云工业互联网有限公司 | Method, device and system for managing production equipment |
| CN115018095A (en) * | 2022-05-26 | 2022-09-06 | 平安银行股份有限公司 | Equipment fault processing method, device, equipment and storage medium |
| CN116187725A (en) * | 2023-04-27 | 2023-05-30 | 武汉新威奇科技有限公司 | Forging equipment management system for forging automatic line |
| CN117590149A (en) * | 2023-11-14 | 2024-02-23 | 南方电网调峰调频发电有限公司检修试验分公司 | Fault solution generation method, device and equipment based on big data technology |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050060323A1 (en) * | 2003-09-17 | 2005-03-17 | Leung Ying Tat | Diagnosis of equipment failures using an integrated approach of case based reasoning and reliability analysis |
| CN107294788A (en) * | 2017-07-17 | 2017-10-24 | 郑州云海信息技术有限公司 | A kind of method and device of troubleshooting |
| US20190041839A1 (en) * | 2017-08-04 | 2019-02-07 | Hefei University Of Technology | Apparatus for troubleshooting fault component in equipment and method thereof |
| CN109325601A (en) * | 2018-08-21 | 2019-02-12 | 国网江苏省电力有限公司泰州供电分公司 | Logistics equipment malfunction monitoring operation management method |
| CN109474067A (en) * | 2018-08-14 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | A kind of dispatching of power netwoks troubleshooting aid decision-making method |
-
2019
- 2019-12-20 CN CN201911330280.1A patent/CN111064620A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050060323A1 (en) * | 2003-09-17 | 2005-03-17 | Leung Ying Tat | Diagnosis of equipment failures using an integrated approach of case based reasoning and reliability analysis |
| CN107294788A (en) * | 2017-07-17 | 2017-10-24 | 郑州云海信息技术有限公司 | A kind of method and device of troubleshooting |
| US20190041839A1 (en) * | 2017-08-04 | 2019-02-07 | Hefei University Of Technology | Apparatus for troubleshooting fault component in equipment and method thereof |
| CN109474067A (en) * | 2018-08-14 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | A kind of dispatching of power netwoks troubleshooting aid decision-making method |
| CN109325601A (en) * | 2018-08-21 | 2019-02-12 | 国网江苏省电力有限公司泰州供电分公司 | Logistics equipment malfunction monitoring operation management method |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112148897A (en) * | 2020-09-14 | 2020-12-29 | 深圳供电局有限公司 | Automatic retrieval and classification method and system for fault information of power system |
| CN112348707A (en) * | 2020-10-24 | 2021-02-09 | 广东冠雄建设集团有限公司 | Holographic intelligent building energy-saving operation and maintenance management system based on BIM model |
| CN112348707B (en) * | 2020-10-24 | 2024-04-05 | 广东冠雄建设集团有限公司 | BIM model-based holographic intelligent building energy-saving operation and maintenance management system |
| CN113132352A (en) * | 2021-03-17 | 2021-07-16 | 中国人民解放军战略支援部队信息工程大学 | Router threat perception method and system based on flow statistical characteristics |
| CN113132352B (en) * | 2021-03-17 | 2023-02-10 | 中国人民解放军战略支援部队信息工程大学 | Router threat perception method and system based on flow statistical characteristics |
| CN113099242A (en) * | 2021-06-09 | 2021-07-09 | 广东电网有限责任公司湛江供电局 | Power transmission line video monitoring data processing method and system |
| CN113099242B (en) * | 2021-06-09 | 2021-08-24 | 广东电网有限责任公司湛江供电局 | Power transmission line video monitoring data processing method and system |
| CN113835401A (en) * | 2021-08-11 | 2021-12-24 | 深圳优制云工业互联网有限公司 | Method, device and system for managing production equipment |
| CN115018095A (en) * | 2022-05-26 | 2022-09-06 | 平安银行股份有限公司 | Equipment fault processing method, device, equipment and storage medium |
| CN116187725A (en) * | 2023-04-27 | 2023-05-30 | 武汉新威奇科技有限公司 | Forging equipment management system for forging automatic line |
| CN116187725B (en) * | 2023-04-27 | 2023-08-04 | 武汉新威奇科技有限公司 | Forging equipment management system for forging automatic line |
| CN117590149A (en) * | 2023-11-14 | 2024-02-23 | 南方电网调峰调频发电有限公司检修试验分公司 | Fault solution generation method, device and equipment based on big data technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111064620A (en) | Power grid multimedia conference room equipment maintenance method and system based on operation and maintenance knowledge base | |
| US11562304B2 (en) | Preventative diagnosis prediction and solution determination of future event using internet of things and artificial intelligence | |
| KR102504498B1 (en) | Method and apparatus for verifying medical fact | |
| CN104318340A (en) | Information visualization method and intelligent visual analysis system based on text curriculum vitae information | |
| CN109902172A (en) | Merit file classification method, device and storage medium | |
| CN114138968A (en) | Network hotspot mining method, device, equipment and storage medium | |
| CN116502162A (en) | Abnormal computing power federal detection method, system and medium in edge computing power network | |
| CN113220951B (en) | Medical clinic support method and system based on intelligent content | |
| CN115114448A (en) | Intelligent multi-mode fusion electricity utilization inspection method, device, system, equipment and medium | |
| CN117290561B (en) | Service state information feedback method, device, equipment and computer readable medium | |
| CN117455235A (en) | Risk processing method, processing device, electronic equipment and storage medium | |
| CN114925210B (en) | Knowledge graph construction method, device, medium and equipment | |
| CN114443904B (en) | Video query method, device, computer equipment and computer readable storage medium | |
| Liu et al. | Anomaly Recognition, Diagnosis and Prediction of Massive Data Flow Based on Time-GAN and DBSCAN for Power Dispatching Automation System | |
| CN116225848A (en) | Log monitoring method, device, equipment and medium | |
| CN112200602B (en) | Neural network model training method and device for advertisement recommendation | |
| CN116150470A (en) | Content recommendation method, device, apparatus, storage medium and program product | |
| CN115062705A (en) | Data checking method, data checking device, electronic equipment and storage medium | |
| CN114580533A (en) | Method, apparatus, device, medium, and program product for training feature extraction model | |
| CN116956174B (en) | Classification model for cold head state classification detection and life prediction and generation method of prediction model | |
| CN113835387A (en) | Operation and maintenance management method, system and medium | |
| CN113821418A (en) | Fault tracking analysis method and device, storage medium and electronic equipment | |
| KR101878291B1 (en) | Big data management system and management method thereof | |
| CN114548925B (en) | Online activity invitation method, device, equipment and storage medium | |
| WO2024088031A1 (en) | Data acquisition method and apparatus, and related device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200424 |
|
| RJ01 | Rejection of invention patent application after publication |