CN113795032A - Method and device for judging room division invisible fault, storage medium and equipment - Google Patents
Method and device for judging room division invisible fault, storage medium and equipment Download PDFInfo
- Publication number
- CN113795032A CN113795032A CN202111132007.5A CN202111132007A CN113795032A CN 113795032 A CN113795032 A CN 113795032A CN 202111132007 A CN202111132007 A CN 202111132007A CN 113795032 A CN113795032 A CN 113795032A
- Authority
- CN
- China
- Prior art keywords
- data
- user behavior
- behavior data
- decision tree
- tree model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 97
- 238000003066 decision tree Methods 0.000 claims abstract description 107
- 230000006399 behavior Effects 0.000 claims description 143
- 238000012545 processing Methods 0.000 claims description 31
- 238000012360 testing method Methods 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 29
- 230000008569 process Effects 0.000 claims description 22
- 238000010606 normalization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000000638 solvent extraction Methods 0.000 claims 1
- 238000010276 construction Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 238000010295 mobile communication Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- H04L67/50—Network services
- H04L67/535—Tracking the activity of the user
-
- 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)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application provides a method, a device, a storage medium and equipment for judging a room division invisible fault, wherein the method comprises the following steps: acquiring user behavior data of an indoor distribution system; and inputting the user behavior data of the indoor distribution system into the decision tree model, and acquiring the judgment result of the indoor distribution invisible fault output by the decision tree model. According to the method for judging the indoor distribution invisible fault, the acquired user behavior data of the indoor distribution system are processed regularly and input into the model for judgment, so that the fault does not need to be detected on site through a manual method when the indoor distribution system has the invisible fault, and the fault can be analyzed and judged efficiently.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a method, a device, a storage medium and equipment for judging a room division invisible fault.
Background
A conventional indoor subsystem is a Radio frequency signal transmission system that connects a Radio Remote Unit (RRU) with a baseband processing Unit (BBU) and uses an antenna feed system as a carrier. The antenna feed system comprises passive devices such as a power divider, a coupler and a ceiling antenna, wherein the passive devices are dummy network elements and monitoring means are in a missing state. Hidden faults of the indoor distribution system can occur in the application process, such as damage or performance degradation of passive devices, affect the network quality and are difficult to discover. Therefore, timely discovery and repair is required after stealth failure of the indoor distribution system.
The existing method for judging the invisible fault of the room subsystem mainly comprises the steps of manually judging on site, and judging whether the invisible fault of the room subsystem occurs or not by comparing data in the aspects of Radio Resource Control (RRC) connection construction success times, Radio Access Bearer (RAB) construction success times, call drop rate and the like with the engineer through site survey of the running state of the room subsystem.
However, in the manual on-site determination method, because the number of users involved in the room distribution system with the hidden fault is large, the data volume required to be compared and analyzed is huge, and the method is easily interfered by factors such as holidays and the like, so that the workload of workers is heavy, the maintenance efficiency is low, and the room distribution hidden fault is difficult to be efficiently analyzed and determined.
Disclosure of Invention
The application provides a method, a device, a storage medium and equipment for judging a room division invisible fault, which are used for solving the technical problem that the room division invisible fault is difficult to be efficiently analyzed and judged in the prior art.
In a first aspect, the present application provides a method for determining a room stealth fault, where the method includes:
acquiring user behavior data of an indoor distribution system;
inputting user behavior data of the indoor distribution system into a decision tree model, and obtaining a judgment result of the indoor distribution invisible fault output by the decision tree model, wherein the decision tree model comprises a plurality of internal nodes, and each internal node is used for judging the relevance of different types of user behavior data and the indoor distribution invisible fault.
In an optional implementation manner, before the inputting user behavior data of the room division system into a decision tree model and obtaining a determination result of the room division stealth fault output by the decision tree model, the method further includes:
and training the decision tree model according to the historical user behavior data of the indoor distribution system.
In an alternative embodiment, the training the decision tree model includes:
removing useless data in the historical user behavior data;
generating data to be trained of the decision tree model according to the historical user behavior data after the useless data are removed;
and training the decision tree model by using the data to be trained.
In an optional embodiment, before the eliminating useless data in the historical user behavior data, the method further comprises:
determining a correlation of the historical user behavior data to the compartmental stealth failure;
according to the relevance between the historical user behavior data and the compartment invisible faults, sequencing the historical user behavior data in a sequence from high to low;
and determining the historical user behavior data which is sorted at the last preset number as useless data according to the sorting result of the historical user behavior data.
In an optional embodiment, the generating training set data of the decision tree model according to the historical user behavior data after the useless data are eliminated includes:
filling null values in the historical user behavior data after the useless data are removed;
determining label data in the historical user behavior data, and keeping the characteristic data in the historical user behavior data as data to be trained;
and dividing the data to be trained into training set data and test set data according to a preset quota dividing ratio.
In an optional embodiment, before the dividing the data to be trained into training set data and test set data, the method further includes:
and performing randomization treatment and normalization treatment on the data to be trained.
In an alternative embodiment, the randomization process is used to shuffle the order of the data to be trained.
In an optional embodiment, the normalization process is configured to scale the data to be trained to be within a target interval.
In an alternative embodiment, the user behavior data of the room distribution system comprises at least one of: the number of successful construction times of the radio resource control connection, the number of trial construction times of the radio resource control connection, the number of successful construction times of the radio access bearer, the number of trial construction times of the radio access bearer, the call drop rate, the number of successful switching times, the number of solution switching times, the cell flow, the cell traffic, the working day information, the weekend information and the holiday information.
In a second aspect, the present application provides a device for determining a room stealth fault, the device including:
the acquisition module is used for acquiring user behavior data of the indoor distribution system; and the processing module is used for inputting the user behavior data of the indoor distribution system into a decision tree model and acquiring the judgment result of the indoor distribution invisible fault output by the decision tree model, wherein the decision tree model comprises a plurality of internal nodes, and each internal node is used for judging the relevance of different types of user behavior data and the indoor distribution invisible fault.
In an optional embodiment, the processing module is further configured to train the decision tree model according to historical user behavior data of the indoor distribution system.
In an optional implementation manner, the processing module is specifically configured to remove useless data in the historical user behavior data; generating data to be trained of the decision tree model according to the historical user behavior data after the useless data are removed; and training the decision tree model by using the data to be trained.
In an optional embodiment, the processing module is further configured to determine a correlation between the historical user behavior data and the compartment stealth fault; according to the relevance between the historical user behavior data and the compartment invisible faults, sequencing the historical user behavior data in a sequence from high to low; and determining the historical user behavior data which is sorted at the last preset number as useless data according to the sorting result of the historical user behavior data.
In an optional implementation manner, the processing module is specifically configured to perform data filling on null values in the historical user behavior data from which the useless data is removed; determining label data in the historical user behavior data, and keeping the characteristic data in the historical user behavior data as data to be trained; and dividing the data to be trained into training set data and test set data according to a preset quota dividing ratio.
In an optional implementation manner, the processing module is further configured to perform randomization and normalization on the data to be trained.
In a third aspect, the present application also provides a computer program product comprising a computer program that, when executed by a processor, performs the method of any of the first aspects.
In a fourth aspect, the present invention also provides a computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform a method according to any of the first aspect.
In a fifth aspect, the present application further provides an electronic device, including: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method according to any of the first aspects.
According to the method, the device, the storage medium and the equipment for judging the indoor distribution invisible faults, the user behavior data of the indoor distribution system are firstly obtained, then the user behavior data of the indoor distribution system are input into the decision tree model, and then the judgment results of the indoor distribution invisible faults output by the decision tree model are obtained. By the mode, the acquired user behavior data of the indoor distribution system can be processed regularly and input into the model for judgment, so that the fault is not required to be detected on site by a manual method when the indoor distribution system has an invisible fault, and the fault can be analyzed and judged efficiently.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the following briefly introduces the drawings needed to be used in the description of the embodiments or the prior art, and obviously, the drawings in the following description are some embodiments of the present invention, and those skilled in the art can obtain other drawings according to the drawings without inventive labor.
Fig. 1 is a schematic view of an application scenario of a method for determining a room stealth fault according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for determining a room stealth fault according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a method for constructing a decision tree model according to an embodiment of the present disclosure;
fig. 4 is a schematic flowchart of a method for generating data to be trained according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a device for determining a room stealth fault according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all 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 application.
In recent years, with the development and maturity of mobile communication network technology, the number of mobile users has increased rapidly, and the requirements for traffic density and network coverage have also increased. The Distributed Antenna System (DAS), also called as an indoor partition, is a System that uniformly distributes signals of mobile communication base stations to every indoor corner by using a related art means, thereby effectively improving a signal coverage environment in a building.
The traditional division is a Radio frequency signal transmission system which adopts a baseband processing Unit (BBU) to connect a Radio Remote Unit (RRU) and then uses an antenna feed system as a carrier. The antenna feed system comprises passive devices such as a feed line, a power divider, a coupler and a ceiling antenna, wherein the passive devices are dummy network elements and monitoring means are in a missing state. Hidden faults, such as damage or performance degradation of passive devices, may occur in the application process of the indoor distribution system, and the hidden faults affect the quality of the mobile communication network and are difficult to be discovered, and usually, the troubleshooting process can be performed only after the complaints of users are passively received. Therefore, after the hidden fault of the indoor partition occurs, the relevant fault needs to be timely discovered and repaired, and the indoor communication is ensured to be smooth.
The existing method for judging the room division invisible fault mainly depends on manual field judgment, engineers survey the running state of the room division system on the field, and judge whether the room division system has the invisible fault by comparing whether the data in the aspects of Radio Resource Control (RRC) connection construction success times, Radio Access Bearer (RAB) construction success times, call drop rate and the like have obvious mutation.
However, in the process of manual on-site judgment, because the number of users involved in the indoor distribution system with the invisible fault is large, the total amount of data to be compared and analyzed is huge, and the indoor distribution system is easily interfered by factors such as holidays and the like, the workload of workers is heavy, the maintenance efficiency is low, and the invisible fault of the indoor distribution system is difficult to be analyzed and judged efficiently.
In order to solve the above technical problem, embodiments of the present application provide a method, an apparatus, a storage medium, and a device for determining a room stealth fault. In the embodiment of the application, the user behavior data can be input into the decision tree model for analysis to obtain the judgment result of the indoor distribution invisible fault, and the fault is not required to be detected on site by a manual method, so that whether the indoor distribution system has the invisible fault in the application process can be judged efficiently.
The method for judging the room distribution invisible fault provided by the embodiment of the application can be applied to traditional room distribution systems, such as a Passive Distributed Antenna System (Passive Distributed Antenna System), an Active Distributed Antenna System (Active Distributed Antenna System) and the like, and can also be applied to other room distribution systems, such as a novel digital room distribution System which adopts a feeder line for extension connection under a remote radio unit (picoRRU, pRRU) and the like.
An application scenario of the method for determining a room stealth fault according to the present application will be described below.
Fig. 1 is a schematic view of an application scenario of a method for determining a room stealth fault according to an embodiment of the present application. As shown in fig. 1, the system includes a server 101 and a terminal device 102, where the server 101 has a function of generating user behavior data and determining a failure. When the user is in the mobile communication network, the server 101 generates user behavior data of the indoor distribution system, and obtains, processes and analyzes the user behavior data through an instruction to determine whether the indoor distribution system generates an invisible fault. If an invisible fault occurs, the server 101 may send alarm information to the terminal device 102 to be alarmed.
The server may be, but is not limited to, a single network server, a server group consisting of a plurality of network servers, or a cloud based on cloud computing, which is composed of a large number of computers or network servers.
The terminal device may be a mobile phone (mobile phone), a tablet computer (pad), a computer with a wireless transceiving function, a Virtual Reality (VR) terminal device, an Augmented Reality (AR) terminal device, a wireless terminal in a self driving (self driving), a wireless terminal in a remote surgery (remote medical supply), a wireless terminal in a smart grid (smart grid), a wireless terminal in a smart home (smart home), and the like. In the embodiment of the present application, the apparatus for implementing the function of the terminal may be the terminal, or may be an apparatus capable of supporting the terminal to implement the function, such as a chip system, and the apparatus may be installed in the terminal. In the embodiment of the present application, the chip system may be composed of a chip, and may also include a chip and other discrete devices.
It should be understood that the application scenario of the present technical solution may be the determination scenario of the compartment stealth fault in fig. 1, but is not limited thereto, and may also be applied to other scenarios requiring the determination of the compartment stealth fault.
It can be understood that the method for determining a hidden fault in a room can be implemented by the device for determining a hidden fault in a room provided in the embodiments of the present application, and the device for determining a hidden fault in a room can be part or all of a certain device, for example, a server.
The following takes a processor integrated or installed with relevant execution codes as an example, and details the technical solution of the embodiments of the present application with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a schematic flow chart of a method for determining an indoor distribution stealth fault according to an embodiment of the present application, which relates to a process for determining whether an indoor distribution system has an stealth fault. As shown in fig. 2, the method includes:
s201, user behavior data of the indoor distribution system is obtained.
In the embodiment of the application, the server can acquire the user behavior data of the indoor distribution system through the instruction, so that whether the indoor distribution system has the invisible fault or not is judged.
When a user uses a mobile communication network under a certain indoor subsystem, a server can generate data related to the operation of the indoor subsystem, and the data are called user behavior data. It should be understood that the user behavior data may comprise various types, and may illustratively include the number of RRC connection construction attempts, the number of RRC connection construction successes, the number of RAB construction attempts, the number of RAB construction successes, the number of handover out requests, the number of handover out successes, cell traffic volume, call drop rate, weekday information, weekend information, holiday information, and the like.
For example, the user behavior data of the room subsystem may be stored in a user behavior data list, and table 1 is a user behavior data list provided in an embodiment of the present application.
TABLE 1
It should be understood that the embodiment of the present application is not limited to the type of user behavior data that needs to be obtained, and may be of any number of types. In some embodiments, the type of the user behavior data to be obtained may be a type of the user behavior data included in the decision tree model. Illustratively, if the decision tree model includes five types of user behavior data, i.e., the number of times of RRC connection construction attempts, the number of times of success of handover, cell traffic, and whether to save or holiday, only the five types of user behavior data need to be acquired.
The embodiment of the application does not limit the acquisition source of the user behavior data. In some embodiments, the source of the user behavior data may be any server, and in other embodiments, the source of the user behavior data may be any device that can generate or store the user behavior data.
It should be noted that, the obtaining time of the user behavior data is not limited in the embodiment of the present application, and may be specifically set according to an actual situation. In some embodiments, the user behavior data may be obtained periodically, for example, every 5 days for analysis.
S202, inputting the user behavior data of the indoor distribution system into the decision tree model, and obtaining the judgment result of the indoor distribution invisible fault output by the decision tree model.
In this step, after obtaining the user behavior data of the indoor distribution system, the server may input the user behavior data of the indoor distribution system into the decision tree model according to the instruction, and obtain a result of determining the indoor distribution hidden fault output by the decision tree model.
Wherein, the decision tree (decision tree) is a tree structure, each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a category. In the embodiment of the application, the decision tree model comprises a plurality of internal nodes, and each internal node is used for judging the relevance of different types of user behavior data and compartment stealth faults. It should be noted that, in the embodiment of the present application, a tree structure of the decision tree model is not limited, and in some embodiments, the tree structure of the decision tree model may be a binary tree, and in other embodiments, the tree structure may also be a non-binary tree.
In some embodiments, the data may also be processed before entering the user behavior data of the room subsystem into the decision tree model. The embodiment of the application does not limit how to process the user behavior data of the indoor distribution system, and can be specifically set according to actual conditions. In some embodiments, the server may perform data filling on null values in the user behavior data according to the instruction, and then perform normalization processing on the filled data.
It should be understood that there may be some cases where a data value is missing, i.e., displayed as a null value, in the user behavior data acquired by the server. The type of the null value is not limited in the embodiments of the present application, and in some embodiments, the null value may belong to three types, namely holiday information, weekend information and weekday information. Illustratively, when the occurrence of a null value belongs to whether a holiday or not, the missing data value may be "yes" or "no".
Further, how to fill the null value in the user behavior data is not limited in the embodiment of the application, and the null value may be specifically set according to an actual situation. In some embodiments, padding may be based on the type to which the null value belongs and the missing data value. Illustratively, when the missing data value is "no" when the occurrence of a null value belongs to holidays or not, the null value may be filled with "no".
The normalization processing is used for eliminating dimension influence among different data types and solving the comparability problem among the data types. The embodiment of the application does not limit how to normalize the data, and can be specifically set according to actual conditions. In some embodiments, the data may be scaled to within the target interval. For example, the data may be scaled down by 25%, 50%, and 75%, respectively, and then the final scaling rate may be determined according to the interval in which the scaled-down data falls. The size of the target interval for scaling the data is not limited in the embodiments of the present application.
It should be understood that, in the embodiment of the present application, no limitation is imposed on the output form of the chamber invisible failure determination result, and the output form may be specifically set according to an actual situation. In some embodiments, the decision tree model may output the determination result by "1" or "0", and for example, the decision tree model output "1" may represent "invisible failure of the room distribution system", and the output "0" may represent "invisible failure of the room distribution system".
In other embodiments, the method further includes, if the judgment result output by the decision tree model indicates that the room distribution system has the hidden fault, determining the terminal device to be alarmed according to the relevant information of the room distribution system with the fault, and then sending alarm information to the terminal device to be alarmed by the server.
According to the method for judging the indoor distribution invisible fault, the user behavior data of the indoor distribution system are firstly obtained, then the user behavior data of the indoor distribution system are processed, finally the processed user behavior data are input into the decision tree model, and the judgment result of the indoor distribution invisible fault output by the decision tree model is obtained. By the mode, the user behavior data of the indoor subsystem can be regularly acquired and processed and input into the decision tree model for judgment, and the fault is not required to be detected on site by a manual method, so that whether the indoor subsystem has the invisible fault or not can be efficiently analyzed and judged.
On the basis of the above embodiments, how to construct the decision tree model is explained below. Fig. 3 is a schematic flowchart of a method for constructing a decision tree model according to an embodiment of the present application, and as shown in fig. 3, the method includes:
s301, historical user behavior data of the indoor distribution system are obtained.
In this step, the server may obtain historical user behavior data of the room distribution system through the instruction.
The historical user behavior data is the user behavior data in the existing normal time period and the existing invisible fault time period in the indoor distribution system. The historical user behavior data includes data of 'whether hidden faults exist' in the indoor distribution system.
It should be understood that, in the embodiment of the present application, there is no limitation on the type and the number of the historical user behavior data that needs to be obtained, and the historical user behavior data may be specifically set according to an actual situation. In some embodiments, the types of the historical user behavior data that need to be obtained should include all types of the user behavior data as much as possible, so as to improve the accuracy of the constructed decision tree model.
S302, determining and processing label data in the historical user behavior data, and keeping other data as characteristic data.
In this step, after obtaining the historical user behavior data, the server may determine and process the tag data in the historical user behavior data through the instruction, and retain other data as the feature data.
Wherein the label data is a kind of data related to the output result of the decision tree model. Illustratively, if the output result of the decision tree model is "whether there is an invisible fault", the tag data is determined as "whether there is an invisible fault".
Further, in the embodiment of the present application, according to the output result of the decision tree model, "whether there is an invisible fault" is determined as the tag data, and the data included in the tag data is "yes" or "no". Further, the embodiment of the present application does not limit how to process the tag data. In some embodiments, a "yes" or a "no" may be converted to a "1" or a "0", respectively, to facilitate the training and learning process of the model.
S303, determining the relevance between the feature data in the historical user behavior data and the label data, and generating the data to be trained of the decision tree model according to the relevance.
In this step, after determining and processing the tag data, the server may determine the relevance between the feature data in the historical user behavior data and the tag data through an instruction, and generate the data to be trained of the decision tree model according to the relevance.
It should be understood that the embodiment of the present application is not limited to how to determine the association between the feature data and the tag data. In some embodiments, the server may determine the association between the characteristic data and the tag data in the historical user behavior data through a relevance analysis method.
In some embodiments, the server may determine the feature data with low relevance to the room invisible fault as the useless data, and after the useless data is removed, the data to be trained of the decision tree model is generated.
S304, processing the data to be trained of the decision tree model.
In this step, after generating the data to be trained of the decision tree model according to the relevance, the server may process the data through an instruction.
The embodiment of the application does not limit how to process the data to be trained of the decision tree model, and can be specifically set according to actual conditions. In some embodiments, the server may perform data padding on null values in the data to be trained according to the instruction, and then perform randomization and normalization on the padded data.
The null value filling and normalization processing method can be understood by referring to S202 shown in fig. 2, and will not be described herein again. The randomization is used to disorder the order of the data, and how to randomize the data after null padding is not limited in the embodiment of the present application, and may be specifically set according to an actual situation. In some embodiments, the data may be randomized when the same data values for any type of user behavior are too concentrated. Illustratively, when "yes" or "no" is too concentrated in a certain area of the list, the data may be randomly shuffled.
It should be understood that, in the embodiment of the present application, the order of the randomizing and normalizing the data after null value filling is not limited, and may be specifically set according to an actual situation.
In the method, the data after the null value filling is subjected to randomization processing and normalization processing, so that the data distribution can be more randomized and homogenized, and the accuracy of analysis and judgment of the room division invisible faults and the accuracy of the constructed decision tree model can be improved.
S305, dividing the data to be trained into training set data and test set data according to a preset quota dividing ratio.
In this step, after processing the data to be trained of the decision tree model, the server may divide the data to be trained into training set data and test set data according to a preset division ratio through an instruction.
The preset amount is the proportion set by dividing the data to be trained into training set data and test set data. The embodiment of the present application is not limited to how to set the preset amount, and in some embodiments, the preset amount may be set to 8-2, 7-3, 6-4, and 5-5.
In the embodiment of the application, the training set data is used for generating the decision tree model, and the test set data is used for testing the accuracy and the error of the decision tree model and verifying the effectiveness of the model. It should be understood that the embodiments of the present application are not limited to how to divide the data to be trained into the training set data and the test set data. Illustratively, when the pre-set value is set to 8-2, 80% of the data to be trained can be directly and randomly divided into training set data, and the rest can be used as test set data.
S306, constructing a decision tree model, and training the decision tree model by using the training set data.
In this step, after dividing the data to be trained into training set data and test set data, the server may construct a decision tree model through an instruction, and train the decision tree model using the training set data.
The embodiment of the application does not limit the machine learning library selected by the construction of the decision tree model. In some embodiments, the server may choose to build the decision tree model based on a machine learning library in Python language (Scikit-Learn, Sklearn).
The embodiment of the application does not limit the parameters selected for constructing the decision tree model. In some embodiments, the server may choose criteria (criterion), giri impurity (Gini), split (split), and maximum depth of the tree (max _ depth) as parameters for building the decision tree model. Wherein, criterion is used for measuring the quality of classification, gini is used for measuring the probability of the error of a randomly selected sample, splitter is used for selecting the splitting strategy at each node, the strategy can be divided into 'best' selection best segmentation and 'random' selection best random segmentation, and max _ depth represents the maximum depth of the tree.
And S307, testing the decision tree model by using the test set data, and generating the decision tree model according to the accuracy of the test result.
In this step, after the decision tree model is trained using the training set data, the server may test the decision tree model using the test set data through an instruction, and generate the decision tree model according to the accuracy of the test result.
Wherein, the accuracy of the test result is the ratio of the test value to the true value. It should be understood that the embodiments of the present application do not limit the accuracy of the test results that can be generated into the decision tree model. In some embodiments, a decision tree model is considered to be generated when the accuracy of the test results is greater than 90%. Illustratively, when the accuracy of the test result is 92.08%, the result obtained by the model is considered to be accurate, and a decision tree model can be generated.
Illustratively, table 2 provides a table of test results for embodiments of the present application, wherein "1" represents the existence of stealth failure in the chamber, and "0" represents the absence of stealth failure in the chamber, and the accuracy of the test results in table 2 is 90.91%.
TABLE 2
| Serial number | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 |
| Test results | 1 | 1 | 1 | 1 | 0 | 1 | 1 | 1 | 0 | 0 | 0 |
| Real result | 0 | 1 | 1 | 1 | 0 | 1 | 1 | 1 | 0 | 0 | 0 |
It should be noted that, the output method of the decision tree model is not limited in the embodiment of the present application. In some embodiments, the server may output the generated decision tree model through a decision tree visualization tool. Illustratively, the decision tree model may be output through a decision tree output function (tree.
The technical terms, technical effects, technical features, and alternative embodiments of S301 to S307 can be understood with reference to S201 to S203 shown in fig. 2, and repeated descriptions thereof will not be repeated here.
On the basis of the above embodiment, how to generate the data to be trained of the decision tree model according to the historical user behavior data is explained below. Fig. 4 is a schematic flow chart of a method for generating data to be trained according to an embodiment of the present application, and as shown in fig. 4, the method includes:
s401, obtaining historical user behavior data of the indoor distribution system.
S402, determining and processing label data in the historical user behavior data, and keeping other data as feature data.
And S403, determining the relevance between the characteristic data and the tag data in the historical user behavior data.
In this step, after determining and processing the tag data, the server may determine the association between the feature data in the historical user behavior data and the tag data through an instruction.
It should be understood that the embodiment of the present application is not limited to how to determine the association between the feature data and the tag data. In some embodiments, the server may first calculate a correlation coefficient between each type of feature data and the tag data through a correlation analysis method, and then determine the association between each type of feature data and the tag data according to the correlation coefficient.
S404, sorting the feature data from high to low according to the relevance of the feature data and the label data.
In this step, after determining the relevance between the feature data and the tag data, the server may order the types of the feature data in the order of the relevance from high to low through an instruction.
The embodiment of the application does not limit the sorting of the types of the feature data according to the relevance. In some embodiments, the order of the correlation coefficients may be from high to low. Illustratively, table 3 is an association sorting table provided in the embodiments of the present application.
TABLE 3
And S405, determining the feature data sorted in the last preset number as useless data according to the sorting result.
In this step, after sorting the feature data, the server may determine, as the useless data, the feature data sorted in the last preset number according to the sorting result of the feature data.
The useless data is characteristic data having a low correlation with the tag data "presence or absence of stealth failure". The preset amount or the determination method of the useless data is not limited in the embodiment of the application, and can be specifically set according to actual conditions. In some embodiments, the determination may be made from the absolute value of the correlation coefficient. For example, the feature data having the absolute value of the correlation coefficient smaller than 0.3 may be determined as the unnecessary data.
And S406, eliminating useless data in the characteristic data, and generating data to be trained of the decision tree model according to the characteristic data after the useless data are eliminated.
In this step, after determining the useless data, the server may remove the useless data in the feature data by an instruction, and generate the data to be trained of the decision tree model according to the feature data from which the useless data is removed.
It should be understood that the embodiments of the present application do not limit the method for eliminating the useless data. In some embodiments, the server may delete the useless data directly, and use the feature data from which the useless data are removed as the data to be trained.
The technical terms, technical effects, technical features, and alternative embodiments of S401 to S406 can be understood with reference to S201 to S203 shown in fig. 2, and repeated descriptions thereof will not be repeated here.
According to the method for judging the indoor distribution invisible fault, the user behavior data of the indoor distribution system are firstly obtained, then the user behavior data of the indoor distribution system are processed, finally the processed user behavior data are input into the decision tree model, and the judgment result of the indoor distribution invisible fault output by the decision tree model is obtained. By the mode, the user behavior data of the indoor subsystem can be regularly acquired and processed and input into the decision tree model for judgment, and the fault is not required to be detected on site by a manual method, so that whether the indoor subsystem has the invisible fault or not can be efficiently analyzed and judged.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer readable storage medium, and when executed, performs steps comprising the method embodiments; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Fig. 5 is a schematic structural diagram of a device for determining a room stealth fault according to an embodiment of the present application. The device for determining the hidden room fault may be implemented by software, hardware, or a combination of the two, and may be, for example, the server in the foregoing embodiment, to execute the method for determining the hidden room fault in the foregoing embodiment. As shown in fig. 5, the device 500 for determining a chamber stealth fault includes:
an obtaining module 501, configured to obtain user behavior data of an indoor distribution system;
the processing module 502 is configured to input user behavior data of the indoor distribution system into a decision tree model, and obtain a determination result of the indoor distribution stealth fault output by the decision tree model, where the decision tree model includes a plurality of internal nodes, and each internal node is configured to determine relevance between different types of user behavior data and the indoor distribution stealth fault.
In an alternative embodiment, the processing module 502 is further configured to train the decision tree model according to historical user behavior data of the indoor distribution system.
In an optional implementation, the processing module 502 is specifically configured to remove useless data in the historical user behavior data; generating data to be trained of the decision tree model according to the historical user behavior data after the useless data are removed; and training the decision tree model by using the data to be trained.
In an alternative embodiment, the processing module 502 is further configured to determine a correlation between the historical user behavior data and the compartment stealth fault; according to the relevance between the historical user behavior data and the compartment invisible faults, sequencing the historical user behavior data from high to low; and determining the historical user behavior data which is sorted at the last preset number as useless data according to the sorting result of the historical user behavior data.
In an optional implementation manner, the processing module 502 is specifically configured to perform data filling on null values in the historical user behavior data after the useless data is removed; determining label data in historical user behavior data, and keeping characteristic data in the historical user behavior data as data to be trained; and dividing the data to be trained into training set data and test set data according to a preset quota dividing ratio.
In an optional implementation manner, the processing module 502 is further configured to perform randomization and normalization on the data to be trained.
It should be noted that the device for determining a hidden fault in a chamber partition provided in the embodiment shown in fig. 5 can be used to execute the method provided in any of the above embodiments, and the specific implementation manner and the technical effect are similar, and are not described again here.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 6, the electronic device may include: at least one processor 601 and memory 602. Fig. 6 shows an electronic device as an example of a processor.
A memory 602 for storing programs. In particular, the program may include program code including computer operating instructions.
The memory 602 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The processor 601 is used for executing computer execution instructions stored in the memory 602 to implement the method for judging the room stealth fault;
the processor 601 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement the embodiments of the present Application.
Alternatively, in a specific implementation, if the communication interface, the memory 602 and the processor 601 are implemented independently, the communication interface, the memory 602 and the processor 601 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. Buses may be classified as address buses, data buses, control buses, etc., but do not represent only one bus or type of bus.
Alternatively, in a specific implementation, if the communication interface, the memory 602 and the processor 601 are integrated into a chip, the communication interface, the memory 602 and the processor 601 may complete communication through an internal interface.
The embodiment of the application also provides a chip which comprises a processor and an interface. Wherein the interface is used for inputting and outputting data or instructions processed by the processor. The processor is configured to perform the methods provided in the above method embodiments. The chip can be applied to a device for judging the invisible faults of the chamber.
The embodiment of the present application further provides a program, which is used for executing the method for determining the room stealth fault provided by the above method embodiment when the program is executed by a processor.
The present application further provides a program product, such as a computer-readable storage medium, having instructions stored therein, which when run on a computer, cause the computer to execute the method for determining a compartment stealth fault provided in the foregoing method embodiment.
The present application also provides a computer-readable storage medium, which may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk. Specifically, the computer-readable storage medium stores therein program information for the method of determining the above-described compartment stealth failure.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the embodiments of the invention are brought about in whole or in part when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (20)
1. A method for judging a room stealth fault is characterized by comprising the following steps:
acquiring user behavior data of an indoor distribution system;
inputting user behavior data of the indoor distribution system into a decision tree model, and obtaining a judgment result of the indoor distribution invisible fault output by the decision tree model, wherein the decision tree model comprises a plurality of internal nodes, and each internal node is used for judging the relevance of different types of user behavior data and the indoor distribution invisible fault.
2. The method of claim 1, wherein before inputting user behavior data of the indoor subsystem into a decision tree model and obtaining the judgment result of the indoor subsystem invisible fault output by the decision tree model, the method further comprises:
and training the decision tree model according to the historical user behavior data of the indoor distribution system.
3. The method of claim 2, wherein the training the decision tree model comprises:
removing useless data in the historical user behavior data;
generating data to be trained of the decision tree model according to the historical user behavior data after the useless data are removed;
and training the decision tree model by using the data to be trained.
4. The method of claim 3, wherein prior to said culling unwanted data from said historical user behavior data, said method further comprises:
determining a correlation of the historical user behavior data to the compartmental stealth failure;
according to the relevance between the historical user behavior data and the compartment invisible faults, sequencing the historical user behavior data in a sequence from high to low;
and determining the historical user behavior data which is sorted at the last preset number as useless data according to the sorting result of the historical user behavior data.
5. The method according to claim 3, wherein the generating data to be trained of the decision tree model according to the historical user behavior data after the useless data are eliminated comprises:
filling null values in the historical user behavior data after the useless data are removed;
determining label data in the historical user behavior data, and keeping the characteristic data in the historical user behavior data as data to be trained;
and dividing the data to be trained into training set data and test set data according to a preset quota dividing ratio.
6. The method of claim 5, wherein prior to said partitioning the data to be trained into training set data and test set data, the method further comprises:
and performing randomization treatment and normalization treatment on the data to be trained.
7. The method of claim 6, wherein the randomization process is configured to shuffle an order of the data to be trained.
8. The method of claim 6, wherein the normalization process is used to scale the data to be trained to within a target interval.
9. The method of any one of claims 1-8, wherein the user behavior data of the room subsystem comprises at least one of: the number of times of attempt of establishing radio resource control connection, the number of times of success of establishing radio resource control connection, the number of times of attempt of establishing radio access bearer, the number of times of success of establishing radio access bearer, the number of times of request for handover, the number of times of success of handover, cell traffic, call drop rate, information of working day, information of weekend and holiday.
10. A device for judging an invisible fault of a room, comprising:
the acquisition module is used for acquiring user behavior data of the indoor distribution system;
and the processing module is used for inputting the user behavior data of the indoor distribution system into a decision tree model and acquiring the judgment result of the indoor distribution invisible fault output by the decision tree model, wherein the decision tree model comprises a plurality of internal nodes, and each internal node is used for judging the relevance of different types of user behavior data and the indoor distribution invisible fault.
11. The apparatus of claim 10, wherein the processing module is further configured to train the decision tree model according to historical user behavior data of the room subsystem before inputting the user behavior data of the room subsystem into the decision tree model and obtaining the result of determining the hidden fault of the room subsystem output by the decision tree model.
12. The apparatus according to claim 11, wherein the processing module is specifically configured to cull useless data in the historical user behavior data; generating data to be trained of the decision tree model according to the historical user behavior data after the useless data are removed; and training the decision tree model by using the data to be trained.
13. The apparatus of claim 12, wherein the processing module is further configured to determine a correlation of the historical user behavior data to the compartment stealth fault; according to the relevance between the historical user behavior data and the compartment invisible faults, sequencing the historical user behavior data in a sequence from high to low; and determining the historical user behavior data which is sorted at the last preset number as useless data according to the sorting result of the historical user behavior data.
14. The apparatus according to claim 12, wherein the processing module is specifically configured to perform data padding on null values in the historical user behavior data after the garbage data is removed; determining label data in the historical user behavior data, and keeping the characteristic data in the historical user behavior data as data to be trained; and dividing the data to be trained into training set data and test set data according to a preset quota dividing ratio.
15. The apparatus of claim 14, wherein the processing module is further configured to perform a randomization process and a normalization process on the data to be trained.
16. The apparatus of claim 15, wherein the randomization process is configured to shuffle an order of the data to be trained.
17. The apparatus of claim 15, wherein the normalization process is configured to scale the data to be trained to a target interval.
18. Apparatus according to any of claims 10 to 17, wherein the user behaviour data of the room subsystem comprises at least one of: the number of times of attempt of establishing radio resource control connection, the number of times of success of establishing radio resource control connection, the number of times of attempt of establishing radio access bearer, the number of times of success of establishing radio access bearer, the number of times of request for handover, the number of times of success of handover, cell traffic, call drop rate, information of working day, information of weekend and holiday.
19. A computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method of any of claims 1-9.
20. An electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111132007.5A CN113795032B (en) | 2021-09-26 | 2021-09-26 | Method and device for judging invisible faults of indoor division, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111132007.5A CN113795032B (en) | 2021-09-26 | 2021-09-26 | Method and device for judging invisible faults of indoor division, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113795032A true CN113795032A (en) | 2021-12-14 |
| CN113795032B CN113795032B (en) | 2023-12-08 |
Family
ID=79184423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111132007.5A Active CN113795032B (en) | 2021-09-26 | 2021-09-26 | Method and device for judging invisible faults of indoor division, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113795032B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114339852A (en) * | 2021-12-31 | 2022-04-12 | 中国联合网络通信集团有限公司 | Cell fault analysis method and device, electronic equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012171168A1 (en) * | 2011-06-13 | 2012-12-20 | 华为技术有限公司 | Method, device and system for monitoring indoor overlay network |
| CN103714348A (en) * | 2014-01-09 | 2014-04-09 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on decision-making tree |
| CN105024765A (en) * | 2014-04-17 | 2015-11-04 | 中国移动通信集团广东有限公司 | Method and device for quickly positioning fault of indoor antenna distribution system |
| CN106713016A (en) * | 2016-12-07 | 2017-05-24 | 中国联合网络通信集团有限公司 | Fault reasoning method and apparatus of indoor distribution system |
| CN107437124A (en) * | 2017-07-20 | 2017-12-05 | 大连大学 | A kind of operator based on big data analysis complains and trouble correlation analytic method |
| CN109150564A (en) * | 2017-06-19 | 2019-01-04 | 中国移动通信集团广东有限公司 | A kind of prediction technique and device for cell fault warning |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| US20200015189A1 (en) * | 2018-07-06 | 2020-01-09 | Cisco Technology, Inc. | Location accuracy assessment and remediation for indoor positioning system deployments |
| CN111338836A (en) * | 2020-02-24 | 2020-06-26 | 北京奇艺世纪科技有限公司 | Method, device, computer equipment and storage medium for processing fault data |
| CN112825576A (en) * | 2019-11-20 | 2021-05-21 | 中国电信股份有限公司 | Method and device for determining cell capacity expansion and storage medium |
| WO2021151503A1 (en) * | 2020-01-31 | 2021-08-05 | Telefonaktiebolaget Lm Ericsson (Publ) | Analytics node and method thereof |
-
2021
- 2021-09-26 CN CN202111132007.5A patent/CN113795032B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012171168A1 (en) * | 2011-06-13 | 2012-12-20 | 华为技术有限公司 | Method, device and system for monitoring indoor overlay network |
| CN103714348A (en) * | 2014-01-09 | 2014-04-09 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on decision-making tree |
| CN105024765A (en) * | 2014-04-17 | 2015-11-04 | 中国移动通信集团广东有限公司 | Method and device for quickly positioning fault of indoor antenna distribution system |
| CN106713016A (en) * | 2016-12-07 | 2017-05-24 | 中国联合网络通信集团有限公司 | Fault reasoning method and apparatus of indoor distribution system |
| CN109150564A (en) * | 2017-06-19 | 2019-01-04 | 中国移动通信集团广东有限公司 | A kind of prediction technique and device for cell fault warning |
| CN107437124A (en) * | 2017-07-20 | 2017-12-05 | 大连大学 | A kind of operator based on big data analysis complains and trouble correlation analytic method |
| US20200015189A1 (en) * | 2018-07-06 | 2020-01-09 | Cisco Technology, Inc. | Location accuracy assessment and remediation for indoor positioning system deployments |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| CN112825576A (en) * | 2019-11-20 | 2021-05-21 | 中国电信股份有限公司 | Method and device for determining cell capacity expansion and storage medium |
| WO2021151503A1 (en) * | 2020-01-31 | 2021-08-05 | Telefonaktiebolaget Lm Ericsson (Publ) | Analytics node and method thereof |
| CN111338836A (en) * | 2020-02-24 | 2020-06-26 | 北京奇艺世纪科技有限公司 | Method, device, computer equipment and storage medium for processing fault data |
Non-Patent Citations (3)
| Title |
|---|
| 唐晓芳;周武;吴超;: "一种室内分布隐性故障分析算法", 信息通信, no. 03 * |
| 杨文; 杜犇; 陈洁: "基于AI的室分故障问题定位方法研究与实践", 《电信工程技术与标准化》, pages 2 * |
| 王琳;: "构建"3D"室分隐性故障监控体系", 科技视界, no. 27 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114339852A (en) * | 2021-12-31 | 2022-04-12 | 中国联合网络通信集团有限公司 | Cell fault analysis method and device, electronic equipment and storage medium |
| CN114339852B (en) * | 2021-12-31 | 2023-08-01 | 中国联合网络通信集团有限公司 | Cell fault analysis method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113795032B (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106776253A (en) | A kind of interface interim card monitoring method and device | |
| CN107980241B (en) | Gateway multi-connection method and device | |
| CN110430068B (en) | Characteristic engineering arrangement method and device | |
| CN109768886B (en) | Network planning evaluation method and device | |
| CN103686818B (en) | Simulation test method and equipment | |
| US20220078630A1 (en) | Station placement designing method, station placement designing apparatus and program | |
| CN111181800A (en) | Test data processing method and device, electronic equipment and storage medium | |
| CN113536081A (en) | Data center data management method and system based on artificial intelligence | |
| CN108446712B (en) | ODN network intelligent planning method, device and system | |
| CN107229660A (en) | A kind of method and apparatus of data deduplication | |
| CN107886113B (en) | Electromagnetic spectrum noise extraction and filtering method based on chi-square test | |
| CN113795032B (en) | Method and device for judging invisible faults of indoor division, storage medium and equipment | |
| CN113660687B (en) | Network difference cell processing method, device, equipment and storage medium | |
| CN109740789B (en) | Wiring management method, device, equipment and storage medium | |
| CN104053159B (en) | The frequency collocation method and device of a kind of Multi-Carrier basestation | |
| CN117729576A (en) | Alarm monitoring method, device, equipment and storage medium | |
| CN110798857A (en) | Simulation method for influence of 5G slice network on service | |
| CN105704173A (en) | Cluster system data distribution method and server | |
| CN110909288B (en) | Service data processing method, device, platform, service end, system and medium | |
| CN110191462B (en) | Method, device, medium and equipment for determining mobile terminal | |
| CN114386468A (en) | Network abnormal flow detection method and device, electronic equipment and storage medium | |
| CN109121140B (en) | Parameter configuration method and equipment for wireless network cell | |
| CN116541252B (en) | Computer room fault log data processing method and device | |
| CN106332123B (en) | Method and device for testing expansion of number of users | |
| CN104703219B (en) | A kind of method and apparatus for inhibiting mould three to interfere |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |