CN112911272B - IPTV group fault early warning method and system - Google Patents
IPTV group fault early warning method and system Download PDFInfo
- Publication number
- CN112911272B CN112911272B CN201911226111.3A CN201911226111A CN112911272B CN 112911272 B CN112911272 B CN 112911272B CN 201911226111 A CN201911226111 A CN 201911226111A CN 112911272 B CN112911272 B CN 112911272B
- Authority
- CN
- China
- Prior art keywords
- fault
- iptv
- scene
- group
- data
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Alarm Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an IPTV group fault early warning method and system, and relates to the field of big data and artificial intelligence. The method comprises the following steps: acquiring IPTV fault characteristic data corresponding to each fault scene in a preset time period before a target prediction time range, wherein the target prediction time range comprises a target prediction time or a target prediction time period; inputting IPTV fault characteristic data into a group fault prediction model corresponding to a fault scene, and predicting group fault amount within a target prediction time range; and outputting corresponding alarm information according to the relation between the real group barrier amount and the predicted group barrier amount in the target prediction time range. The method and the system can send out fault warning information in time, and meet the requirements of real-time performance, accuracy, automation and comprehensiveness of IPTV operation and maintenance.
Description
Technical Field
The disclosure relates to the field of big data and artificial intelligence, in particular to an IPTV group fault early warning method and system.
Background
With the development of video and digital television services, the number of users of the IPTV (interactive network television) of the telecom operator is increasing rapidly. The method mainly comprises the steps that the content of complaints of customer service calls made by users and manual equipment inspection are taken as grippers, and operation and maintenance personnel are used for manually checking relevant user configurations and equipment loads from a background system. However, with the increase of the user quantity, the quality of the program source is unstable, old equipment is updated, new terminal manufacturers bid for entering into the market, and other factors, the conventional passive fault processing method has long solution period and poor user experience.
Disclosure of Invention
The technical problem to be solved by the present disclosure is to provide an IPTV group fault early warning method and system, which can send out fault warning information in time.
According to one aspect of the disclosure, an IPTV group fault early warning method is provided, which includes: acquiring IPTV fault characteristic data corresponding to each fault scene in a preset time period before a target prediction time range, wherein the target prediction time range comprises a target prediction time or a target prediction time period; inputting IPTV fault characteristic data into a group fault prediction model corresponding to a fault scene, and predicting group fault amount within a target prediction time range; and outputting corresponding alarm information according to the relation between the real group barrier amount and the predicted group barrier amount in the target prediction time range.
In some embodiments, IPTV fault code data and IPTV platform user service data are obtained; matching and converging IPTV fault code data and IPTV platform user service data, and determining sample fault characteristic data corresponding to each fault scene in a plurality of fault scenes; and training a group fault prediction model according to the sample fault characteristic data.
In some embodiments, outputting corresponding warning information according to a relationship between the real group obstacle amount and the predicted group obstacle amount of the target prediction time range includes: if the real group barrier amount is larger than or equal to the predicted group barrier amount of the first multiple, outputting first alarm information; if the real group barrier amount is smaller than the predicted group barrier amount of the first multiple and larger than or equal to the predicted group barrier amount of the second multiple, outputting second alarm information; if the real group barrier amount is less than the second multiple of the predicted group barrier amount and greater than or equal to the third multiple of the predicted group barrier amount, outputting third alarm information; wherein the first multiple is greater than the second multiple, and the second multiple is greater than the third multiple; the severity of the first warning information is greater than the severity of the second warning information, which is greater than the severity of the third warning information.
In some embodiments, the plurality of fault scenarios include an Electronic Program Guide (EPG) scenario, a Content Delivery Network (CDN) scenario, a set-top box scenario, a product package scenario, a network layer device scenario, an access failure scenario, and a service authentication failure scenario.
In some embodiments, training the group fault prediction model from the sample fault signature data comprises: taking sample fault characteristic data corresponding to the EPG scene as training data of a neural network model, and training the neural network model to obtain a group fault prediction model under the EPG scene; taking sample fault characteristic data corresponding to the CDN scene as training data of a neural network model, and training the neural network model to obtain a group fault prediction model under the CDN scene; taking sample fault characteristic data corresponding to a set top box scene as training data of a neural network model, and training the neural network model to obtain a group fault prediction model under the set top box scene; taking sample fault characteristic data corresponding to the product package scene as training data of a neural network model, and training the neural network model to obtain a group barrier prediction model under the product package scene; taking sample fault characteristic data corresponding to a network layer equipment scene as training data of a neural network model, and training the neural network model to obtain a group fault prediction model under the network layer equipment scene; taking sample fault characteristic data corresponding to the access failure scene as training data of a time series prediction model, and training the time series prediction model to obtain a group barrier prediction model under the access failure scene; and taking the sample fault characteristic data corresponding to the service authentication failure scene as training data of the time series prediction model, and training the time series prediction model to obtain a group barrier prediction model under the service authentication failure scene.
In some embodiments, the IPTV platform user traffic data includes IPTV user home network element data and network topology.
In some embodiments, matching and aggregating the IPTV fault code data with the IPTV platform user service data includes: and performing big data aggregation matching on the IPTV fault code data and IPTV user attributive network element data and network topology according to the service account number of the IPTV fault code data and the production serial number identification field of the set top box, and respectively matching IPTV fault code data corresponding to the EPG equipment, the CDN node, the model of the set top box, the product package, the network layer equipment and the service management platform.
In some embodiments, determining sample fault signature data comprises: respectively extracting feature data of IPTV fault code data corresponding to the EPG equipment, the CDN node, the model of the set top box, the product package and the network layer equipment to obtain sample fault feature data corresponding to an EPG scene, sample fault feature data corresponding to the CDN scene, sample fault feature data corresponding to the set top box scene, sample fault feature data corresponding to the product package scene and sample fault feature data corresponding to the network layer equipment scene; and determining sample fault characteristic data corresponding to an access failure scene and sample fault characteristic data corresponding to a service authentication failure scene according to the fault code meaning of IPTV fault code data corresponding to the service management platform.
In some embodiments, the IPTV fault code data includes fault code data reported by the set top box and fault code data reported by the user through code scanning; analyzing a video source Uniform Resource Locator (URL) requested by a set top box in fault code data reported by the set top box, and determining a television channel corresponding to a fault; and analyzing the EPG page requested by the set-top box in the fault code data reported by the set-top box, and determining the EPG page corresponding to the fault.
According to another aspect of the present disclosure, an IPTV group fault early warning system is further provided, including: the characteristic data acquisition module is configured to acquire IPTV fault characteristic data corresponding to each fault scene in a preset time period before a target prediction time range, wherein the target prediction time range comprises a target prediction time or a target prediction time period; the group fault amount prediction module is configured to input IPTV fault characteristic data into a group fault prediction model corresponding to a fault scene and predict the group fault amount of a target prediction time range; and the early warning and analysis module is configured to output corresponding warning information according to the relation between the real group barrier amount and the predicted group barrier amount of the target prediction time range.
In some embodiments, the data acquisition module is configured to acquire IPTV fault code data and IPTV platform user service data; the big data processing module is configured to match and gather IPTV fault code data and IPTV platform user service data, and determine sample fault characteristic data corresponding to each fault scene in a plurality of fault scenes; and the model training module is configured to train the group fault prediction model according to the sample fault characteristic data.
According to another aspect of the present disclosure, an IPTV group fault early warning system is further provided, including: a memory; and a processor coupled to the memory, the processor configured to execute the IPTV group obstacle warning method as described above based on instructions stored in the memory.
According to another aspect of the present disclosure, a computer-readable storage medium is further provided, on which computer program instructions are stored, and when the instructions are executed by a processor, the IPTV group fault warning method described above is implemented.
Compared with the prior art, the method and the device have the advantages that the group barrier prediction models in different scenes are utilized to predict the group barrier amount of the target prediction time or the target prediction time period, then the fault warning information can be sent out in time according to the relation between the real group barrier amount and the predicted group barrier amount, and the requirements of real-time performance, accuracy, automation and comprehensiveness of IPTV operation and maintenance are met.
Other features of the present disclosure and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic flowchart of some embodiments of an IPTV group fault warning method according to the present disclosure.
Fig. 2 is a schematic flowchart of another embodiment of an IPTV group fault warning method according to the present disclosure.
Fig. 3 is a flowchart illustrating another embodiment of an IPTV group fault warning method according to the disclosure.
Fig. 4 is a schematic structural diagram of some embodiments of an IPTV group obstacle warning system of the present disclosure.
Fig. 5 is a schematic structural diagram of another embodiment of an IPTV group fault early warning system of the present disclosure.
Fig. 6 is a schematic structural diagram of another embodiment of an IPTV group obstacle warning system of the present disclosure.
Fig. 7 is a schematic structural diagram of another embodiment of an IPTV group obstacle warning system of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of parts and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as exemplary only and not as limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be discussed further in subsequent figures.
For the purpose of promoting a better understanding of the objects, aspects and advantages of the present disclosure, reference is made to the following detailed description taken in conjunction with the accompanying drawings.
Fig. 1 is a schematic flowchart of some embodiments of an IPTV group fault warning method according to the present disclosure.
In step 110, IPTV fault characteristic data corresponding to each fault scenario in a predetermined time period before the target prediction time range is obtained. The target prediction time range is, for example, a target prediction time or a target prediction time period.
The IPTV fault feature data may include IPTV fault feature data corresponding to an EPG (Electronic Program Guide) scene, IPTV fault feature data corresponding to a CDN (Content Delivery Network) scene, IPTV fault feature data corresponding to a set-top box scene, IPTV fault feature data corresponding to a product package scene, IPTV fault feature data corresponding to a Network layer device scene, IPTV fault feature data corresponding to an access failure scene, and IPTV fault feature data corresponding to a service authentication failure scene.
In step 120, IPTV fault characteristic data is input to the group fault prediction model corresponding to the fault scene, and the group fault amount in the target prediction time range is predicted. For example, the group barrier amount at a certain time or the group barrier amount in a certain time period in the future is predicted.
The group barrier prediction model comprises a group barrier prediction model under an EPG scene, a CDN scene, a set top box scene, a product package scene, a network layer equipment scene, an access failure scene and a service authentication failure scene.
In step 130, corresponding warning information is output according to the relationship between the real group barrier amount and the predicted group barrier amount in the target prediction time range.
In some embodiments, if the real group barrier amount is larger than or equal to the predicted group barrier amount of the first multiple, outputting first warning information; if the real group barrier amount is smaller than the predicted group barrier amount of the first multiple and larger than or equal to the predicted group barrier amount of the second multiple, outputting second warning information; if the real group barrier amount is less than the second multiple of the predicted group barrier amount and greater than or equal to the third multiple of the predicted group barrier amount, outputting third alarm information; wherein the first multiple is greater than the second multiple, the severity of the first warning information is greater than the severity of the second warning information, and the severity of the second warning information is greater than the severity of the third warning information.
For example, if the predicted group barrier amount at a target prediction time is P, the actual group barrier amount is C, and if C is equal to or greater than Ta × P, the serious alarm information is output, if C is smaller than Ta × P and equal to or greater than Tb × P, the important alarm information is output, and if C is smaller than Tb × P and equal to or greater than Tc, the general alarm information is output, where Ta > Tb > Tc.
In the embodiment, the group barrier prediction models in different scenes are used for predicting the group barrier amount of the target prediction time or the target prediction time period, and then the fault warning information can be sent out in time according to the relation between the real group barrier amount and the predicted group barrier amount, so that the requirements of real-time performance, accuracy, automation and comprehensiveness of IPTV operation and maintenance are met.
Fig. 2 is a flowchart illustrating another embodiment of an IPTV group fault warning method according to the disclosure.
In step 210, IPTV fault code data and IPTV platform user service data are obtained. The IPTV platform user service data comprises IPTV user home network element data and network topology.
In some embodiments, fault code data reported by the set-top box segment and fault code data reported by an IPTV user actively scanning a two-dimensional code of a television are collected. And then, acquiring network element data of the user such as EPG/CDN and network topology, wherein the network topology comprises a network transmission topology of the user from a set top box, an optical splitter and an OLT/BRAS/convergence switch, and the topology forms a network resource tree, wherein the same network equipment can serve a plurality of users. The IPTV subscriber home network element data and the network topology are for example stored in the same network element database.
In step 220, the IPTV fault code data and the IIPTV platform user service data are matched and aggregated, and sample fault feature data corresponding to each fault scenario in a plurality of fault scenarios is determined.
In some embodiments, the IPTV fault code data is stored to a Kafka message queue, e.g., the IPTV fault code data is posted to Kafka by way of an http request. And storing the IPTV user home network element data and the network topology into the HDFS. Reading and extracting a set top box code as an index, and writing network element data and network topology which an IPTV user belongs to into Redis for real-time query; IPTV fault code data in Kafka, user attribution network elements and network equipment resource trees in Redis are read through Spark and matched, generated fault common data are gathered to an EPG scene, a CDN scene, a set top box scene, a product package scene, a network layer equipment scene, an access failure scene and a service authentication failure scene, then characteristic data are extracted, and sample fault characteristic data corresponding to the EPG scene, sample fault characteristic data corresponding to the CDN scene, sample fault characteristic data corresponding to the set top box scene, sample fault characteristic data corresponding to the product package scene, sample fault characteristic data corresponding to the network layer equipment scene, sample fault characteristic data corresponding to the access failure scene and sample fault characteristic data corresponding to the service authentication failure scene are obtained.
In step 230, a group fault prediction model is trained based on the sample fault signature data. In some embodiments, codes are written by using a tensoflow frame to generate an algorithm model, and the group barrier prediction models under each scene are obtained by training the algorithm model, so as to predict the group barrier amount in the target prediction time range, for example, predict the group barrier amount at the target prediction time or predict the group barrier amount in the target prediction time period, according to the trained group barrier prediction models.
In some embodiments, the sample fault feature data may be sorted according to time, the sample fault feature data of a predetermined time period is used as an input parameter of the group barrier prediction model, the group barrier amount of the next time or the next time period of the predetermined time period is used as an output parameter of the group barrier prediction model, and a trained group barrier prediction model is obtained through training iteration.
In step 240, IPTV fault characteristic data corresponding to each fault scenario within a predetermined time period before the target prediction time is obtained. For example, the actual failure amount 12 times before the target prediction time, the actual failure amount yesterday at the same time, and the data attribute set are acquired.
In step 250, IPTV fault characteristic data is input to the group fault prediction model corresponding to the fault scene, and the group fault amount at the target prediction time is predicted.
In step 260, it is determined whether the real group fault amount at the target prediction time is greater than the predicted group fault amount by the first multiple, if so, step 270 is executed, otherwise, step 280 is executed.
In step 270, the critical alert information is sent and the alert contents are stored in a database.
In step 280, it is determined whether the real group barrier amount at the target prediction time is smaller than the first multiple of the predicted group barrier amount and greater than or equal to the second multiple of the predicted group barrier amount, if yes, step 290 is performed, otherwise, step 2100 is performed.
In step 290, important alarm information is sent out and the alarm content is saved in the database.
In step 2100, it is determined whether the real group barrier amount at the target prediction time is smaller than the second multiple of the predicted group barrier amount and greater than or equal to the third multiple of the predicted group barrier amount, if yes, step 2110 is performed, otherwise, step 2120 is performed.
At step 2110, general alarm information is issued and the alarm content is saved in a database.
At step 2120, no alarm is raised.
In the prior art, most of the group fault alarm thresholds are manually set by the maintainer through experience, and cannot be dynamically adjusted, however, the boundary and the grade of the group fault have strong correlation with whether the service is busy, the quality of the network layer and the evolution of the time sequence, and the manual setting cannot accurately delimit and grade the group fault. In the embodiment, when a large-scale fault occurs, fault warning information can be sent out in time by calculating and converging big data and utilizing the group fault prediction model, so that complaints of users can be effectively avoided, and the perception of the users is improved. In addition, due to the fact that the IPTV fault code data are matched with the IPTV platform user service data, the type of the user fault can be accurately obtained, and the specific fault point can be quickly located.
In some embodiments, if the output is the group barrier amount of the target prediction time period, the real group barrier amount of the target prediction time period is compared with the predicted group barrier amount, and the corresponding type of alarm information is output. The group barrier amount of the target prediction time period can constitute a time series curve. In addition, trend analysis can be performed on the real fault quantity and the predicted fault quantity, and meanwhile, support means such as a WebService interface and an Email log are provided for operation and maintenance analysis.
Fig. 3 is a flowchart illustrating an IPTV group fault warning method according to another embodiment of the disclosure.
In step 310, fault code data and IPTV user home network element data and network topology are collected. The fault code data includes a video source URL (Uniform Resource Locator) requested by the set top box and a requested EPG page.
In some embodiments, by analyzing the video source URL requested by the set-top box, the television channel corresponding to the failure can be determined; and analyzing the EPG page requested by the set top box, determining the EPG page and the EPG network element corresponding to the fault, and after positioning to a specific position, informing a broadcast and television live broadcast source to process or logging in the EPG to repair the page.
In step 320, the collected fault code data is cleaned, and data with irregular fault code reporting, missing user account and wrong field type are filtered out.
In step 330, the service account number and the STBID (set-top box production serial number identification) field of the cleaned fault code data are extracted.
In step 340, according to the service account and the STBID field of the IPTV fault code data, big data aggregation matching is performed on the IPTV fault code data and the IPTV user home network element data and network topology, so as to match the IPTV fault code data corresponding to the EPG device, the CDN node, the set top box model, the product package, the network layer device, and the service management platform, respectively.
In some embodiments, according to the service account number and the STBID field, the template of the user can be matched to be information such as baishitong or provincial channel, and the product package of the matched user is an intelligent version user or a high-definition or standard-definition user.
In some embodiments, according to the service account and the STBID field, network layer devices such as a PON (Passive Optical Network) port, an OLT (Optical Line Terminal)/BRAS (Broadband Remote Access Server) device code, and the like of an Access Network corresponding to the IPTV fault code data are matched. In this embodiment, when a fault occurs, the fault can be located to a specific PON port and OLT/BRAS equipment by querying the database.
In some embodiments, according to the service account and the STBID field, a set top box model, a software version, a capability platform where the IPTV fault code data is located, a bound EPG server, a group where the EPG server is located, a CDN node requested by a user, and the like corresponding to the IPTV fault code data are matched. In this embodiment, when a fault occurs, the fault can be located to a specific film source on the CDN node by querying the database.
And converging the matched intermediate results to EPG equipment, CDN nodes, set top box models, product packages, network layer equipment and service management platform scenes in real time, and storing converged convergence results into a database. When the user sees the error report, the system background can accurately acquire the type of the user fault and judge whether the user fault is a problem of network access or a fault of a service authentication module or the IPTV capability platform is in fault.
In the embodiment, the fault position corresponding to the fault code data can be located by querying the database, and compared with the method of locating the fault by querying a local log of the set top box by relying on a manufacturer, the fault locating efficiency is improved. In addition, in the embodiment, batch query and configuration can be realized through mass data analysis, convergence of common faults of users is realized, and the automation degree of the system is improved.
In step 350, missing data completion is performed on the IPTV fault code data corresponding to the matched EPG equipment, CDN node, set top box model, product package, network layer equipment, and service management platform according to the time sequence. For example, the time data missing in the time series is complemented.
In step 360, feature data of IPTV fault code data corresponding to the EPG device, the CDN node, the model of the set top box, the product package, and the network layer device are extracted, respectively, to obtain sample fault feature data corresponding to the EPG scene, sample fault feature data corresponding to the CDN scene, sample fault feature data corresponding to the set top box scene, sample fault feature data corresponding to the product package scene, and sample fault feature data corresponding to the network layer device scene; and determining sample fault characteristic data corresponding to an access failure scene and sample fault characteristic data corresponding to a service authentication failure scene according to the fault code meaning of IPTV fault code data corresponding to the service management platform.
In some embodiments, the sample fault signature data is initialized to N specific sets of discretized attributes.
In step 370, according to the sample fault feature data corresponding to each scenario, a group fault prediction model of the corresponding scenario is trained.
In some embodiments, for EPG scenarios, CDN scenarios, set-top box scenarios, product package scenarios, and network layer device scenarios, a neural network model with two BilTM (bidirectional LSTM) layers plus one Dense (fully connected layer) layer is used. For the access failure scene and the service authentication failure scene, a time series ARIMA model can be adopted because the fault amount is stable and the specific strong time periodicity is strong.
In some embodiments, sample fault characteristic data corresponding to an EPG scene is used as training data of a neural network model, and the neural network model is trained to obtain a group fault prediction model in the EPG scene.
For example, the failure data of the first 12 moments of the target prediction moment, the failure amount of the same moment of yesterday, the CDN node capability, and the CDN node type are used, and a total of 15 input values are used as one piece of training data. The CDN node type is divided into discrete attribute sets of 13 edge nodes +2 cross-domain nodes +1 province center node according to edge nodes, cross-domain nodes and province center nodes in a three-level framework of an IPTV platform and combining city and ground positions of node distribution.
In some embodiments, sample fault feature data corresponding to a CDN scene is used as training data of a neural network model, and the neural network model is trained to obtain a group fault prediction model in the CDN scene.
For example, the failure data of the first 12 times of the target predicted time, the failure amount of the same time yesterday, the EPG device type, the EPG packet, and a total of 15 input values are used as one piece of training data. The EPG equipment types are divided into ten EPG equipment types including a second-long-ZTE 1, a second-long-ZTE 2, a Changle-way KVM-ZTE1, a Changle-way KVM-ZTE2, a Changle-way-ZTE 1, a Changle-way-ZTE 2, a platform newly-expanded device, a Zhongxing-first platform EPG-KVM and a Zhongxing-second platform EPG-KVM according to the fact whether the EPG equipment types are cloud hosts, virtualization technology and the like, and the EPG groups are divided into 13 prefecture EPG groups and 1 default EPG groups according to the existing network IPTV platform.
In some embodiments, sample fault characteristic data corresponding to a set top box scene is used as training data of a neural network model, and the neural network model is trained to obtain a group barrier prediction model under the set top box scene.
For example, the data is divided according to the software versions of the set top box, if 82 software versions are adopted by 7 set top box manufacturers, due to the fact that the number of users of most software versions is small, reported fault records are few, and a part of old standard definition set top boxes do not have the capacity of reporting fault code data, training data are sparse; therefore, the data is smoothed, namely 0 is converted into an extremely small decimal number close to 0, and the situation that the gradient propagation of the neural network is inhibited by all 0 data is avoided. In addition, because the fault amount data of each set top box version does not show obvious periodicity, and the fault amount at the same moment of yesterday has little significance for model construction, the data format after preprocessing is as follows: the fault amount data of the first 12 moments of the target prediction moment and the version of the software of the set top box have 13 input values.
In some embodiments, sample fault feature data corresponding to a product package scene is used as training data of a neural network model, and the neural network model is trained to obtain a group barrier prediction model under the product package scene.
For example, 8 mainstream product packages including an iTV fashion a package, an iTV fashion package, an iTV hotel user, an iTV high-definition fashion a package (common edition), an iTV high-definition fashion a package (smart edition), an iTV high-definition fashion package (common edition), an iTV high-definition fashion package (smart edition), and an iTV high-definition hotel user are extracted. Therefore, the training set format in this scenario is: the failure amount data + the product package name of the first 12 moments of the target prediction moment are 13 input values.
In some embodiments, sample fault characteristic data corresponding to a network layer device scene is used as training data of a neural network model, and the neural network model is trained to obtain a group barrier prediction model under the network layer device scene;
in some embodiments, sample fault feature data corresponding to an access failure scene is used as training data of a time series prediction model, and the time series prediction model is trained to obtain a group fault prediction model in the access failure scene.
For example, firstly, the original time series is subjected to difference method to obtain stable time series, then AR, MA and ARMA models are respectively trained, and the parameter combination takes 3 as the maximum value, and 15 models are obtained in total. And after the training of the models is finished, calculating the AIC of each model to obtain ARIMA (p, d, q) with the minimum AIC, finally predicting a predicted value at the next moment in real time according to the models, and obtaining a predicted value of the fault amount after contrastive classification.
In some embodiments, sample fault feature data corresponding to a service authentication failure scene is used as training data of a time series prediction model, and the time series prediction model is trained to obtain a group barrier prediction model under the service authentication failure scene.
In the embodiment, sample fault feature data corresponding to an EPG scene, sample fault feature data corresponding to a CDN scene, sample fault feature data corresponding to a set-top box scene, sample fault feature data corresponding to a product package scene, sample fault feature data corresponding to a network layer device scene, sample fault feature data corresponding to an access failure scene, and sample fault feature data corresponding to a service authentication failure scene are extracted, and then an LSTM model and an ARIMA model are trained to obtain a group barrier prediction model in each scene, which facilitates subsequent prediction of a group barrier amount at a target time and a group barrier amount at a target time period, so that batch error reporting of a single set-top box model can be monitored and early warned, and batch access failure and service authentication failure of a certain user in a certain city can be detected and early warned. When a certain device or a certain type of set top box version has a large-scale fault, the fault reason can be positioned before a user complains in batches, an alarm is sent out in real time, automatic processing is achieved, and the requirements of real-time performance, accuracy, automation and comprehensiveness of IPTV operation and maintenance are met.
The method of the present disclosure will be described below by taking EPG group barrier prediction as an example.
When some EPG equipment has a fault, the background acquires massive set top box active reporting fault code data and fault code data reported by user code scanning, and writes the fault code data into two topics of itv _ error and itv _ user _ error of a Kafka message queue. And then cleaning the data, and filtering out the data with irregular fault codes, missing fields and wrong types.
And (4) reading fault code data in the itv _ error topic by Spark, and distributing the data to each worker node of the Spark cluster by using a map operator of RDD. For each worker node, initializing a Jedis client, connecting a Redis cluster, inquiring a product package, an access network PON port, an OLT code, a BRAS code, a set top box model, a set top box software version, a capacity platform where the set top box software version is located, a bound EPG server, an EPG packet, a CDN node and the like according to STBID, generating an intermediate result and caching the intermediate result in Spark Streaming.
Taking the fault code | belonging to the platform | EPG code | EPG name | EPG grouping as KEY, respectively counting the sum of the data quantity of the fault codes of each EPG server in the current 5-minute sliding window, wherein the error code of each EPG server is equal to 403, 404, 500, 10071, 13023, 13024 and 70. The reduce ByKeyAndWindow operation is divided into two types of convergence of the total amount of all fault codes and single convergence of each fault code, and the result of the reduce ByKeyAndWindow is stored in the MySQL database.
Reading the fault data of the first 12 moments of the current prediction moment, the fault amount of the same moment of yesterday, the EPG equipment type and the EPG grouping from a MySQL database, taking a total of 15 input values as one input, and predicting the fault amount prediction value P of the EPG server at the next moment through a trained LSTM model.
When the next moment comes, calculating the real fault quantity C under the EPG server in a 5-minute sliding window through spark streaming, reading a predicted value P of the LSTM, and if C is greater than Ta P, sending a serious alarm; if Tb < C < Ta < P, an important alarm is sent out; otherwise, if Tc P < C < Tb P, then sending out general alarm; otherwise, no alarm is given.
And according to the city or resource pool to which the EPG positioned by the alarm belongs, immediately testing the EPG by dialing after the corresponding chartered plane receives the alarm, and verifying whether the service is normal. And if the user fault can be reproduced, immediately drawing the EPG away. Therefore, after the group obstacle early warning and processing of the single EPG are finished, the subsequent new startup user can not be distributed to the EPG for service, and more user obstacles are effectively avoided.
Fig. 4 is a schematic structural diagram of some embodiments of an IPTV group obstacle warning system of the present disclosure. The system comprises a characteristic data acquisition module 410, a group barrier amount prediction module 420 and an early warning and analysis module 430.
The characteristic data obtaining module 410 is configured to obtain IPTV fault characteristic data corresponding to each fault scenario within a predetermined time period before a target prediction time range, where the target prediction time range includes a target prediction time or a target prediction time period.
The IPTV fault feature data may include IPTV fault feature data corresponding to an EPG scene, IPTV fault feature data corresponding to a CDN scene, IPTV fault feature data corresponding to a set top box scene, IPTV fault feature data corresponding to a product package scene, IPTV fault feature data corresponding to a network layer device scene, IPTV fault feature data corresponding to an access failure scene, and IPTV fault feature data corresponding to a service authentication failure scene.
The group fault amount prediction module 420 is configured to input IPTV fault feature data to a group fault prediction model corresponding to a fault scenario, and predict a group fault amount of a target prediction time range. For example, the group barrier amount at a certain time or the group barrier amount in a certain time period in the future is predicted.
The early warning and analysis module 430 is configured to output corresponding warning information according to a relationship between the real group barrier amount and the predicted group barrier amount of the target prediction time range.
In some embodiments, if the real group fault amount is larger than or equal to the predicted group fault amount of the first multiple, outputting first alarm information; if the real group barrier amount is smaller than the predicted group barrier amount of the first multiple and larger than or equal to the predicted group barrier amount of the second multiple, outputting second warning information; if the real group barrier amount is less than the second multiple of the predicted group barrier amount and greater than or equal to the third multiple of the predicted group barrier amount, outputting third alarm information; wherein the first multiple is greater than the second multiple, the severity of the first warning information is greater than the severity of the second warning information, and the severity of the second warning information is greater than the severity of the third warning information.
In the embodiment, the group barrier prediction models in different scenes are used for predicting the group barrier amount of the target prediction time or the target prediction time period, and then the fault warning information can be sent out in time according to the relation between the real group barrier amount and the predicted group barrier amount, so that the requirements of real-time performance, accuracy, automation and comprehensiveness of IPTV operation and maintenance are met.
In some embodiments, the early warning and analysis module 430 may set a short message alarm interface, a WebService interface, and an Email daily interface.
Fig. 5 is a schematic structural diagram of another embodiment of an IPTV group obstacle warning system of the present disclosure. The system also includes a data acquisition module 510, a big data processing module 520, and a model training module 530.
The data acquisition module 510 is configured to acquire IPTV fault code data and IPTV platform user service data. The IPTV platform user service data comprises IPTV user attributive network element data and network topology.
In some embodiments, the collected fault code data can be cleaned, and data with irregular fault code reporting, user account missing and field type errors can be filtered out.
The big data processing module 520 is configured to match and converge the IPTV fault code data and the IPTV platform user service data, and determine sample fault feature data corresponding to each fault scenario in a plurality of fault scenarios.
In some embodiments, according to the service account and the STBID field of the IPTV fault code data, big data aggregation matching is performed on the IPTV fault code data and IPTV user home network element data and network topology, so as to match the IPTV fault code data corresponding to the EPG device, the CDN node, the set top box model, the product package, the network layer device, and the service management platform, respectively. Respectively extracting feature data of IPTV fault code data corresponding to the EPG equipment, the CDN node, the set top box model, the product package and the network layer equipment to obtain sample fault feature data corresponding to an EPG scene, sample fault feature data corresponding to the CDN scene, sample fault feature data corresponding to the set top box scene, sample fault feature data corresponding to the product package scene and sample fault feature data corresponding to the network layer equipment scene; and determining sample fault characteristic data corresponding to an access failure scene and sample fault characteristic data corresponding to a service authentication failure scene according to the fault code meaning of IPTV fault code data corresponding to a service management platform.
In some embodiments, the big data processing module 520 stores the IPTV fault code data to a Kafka message queue, e.g., by reporting the IPTV fault code data to Kafka by way of an http request. And storing the IPTV user home network element data and the network topology into the HDFS. Reading and extracting a set top box code as an index, and writing network element data and network topology which an IPTV user belongs to into Redis for real-time query; and reading IPTV fault code data in Kafka and user attributive network elements and network equipment resource trees in Redis through Spark, and matching.
The model training module 530 is configured to train a group fault prediction model based on the sample fault signature data.
In some embodiments, for an EPG scene, a CDN scene, a set-top box scene, a product package scene, and a network layer device scene, a neural network model with two bilst layers and one sense layer is used. For an access failure scene and a service authentication failure scene, a time series ARIMA model can be adopted because the fault amount is stable and the specific strong time periodicity is strong.
In some embodiments, sample fault characteristic data corresponding to an EPG scene is used as training data of a neural network model, and the neural network model is trained to obtain a group fault prediction model in the EPG scene.
In some embodiments, sample fault feature data corresponding to a CDN scene is used as training data of a neural network model, and the neural network model is trained to obtain a group fault prediction model in the CDN scene.
In some embodiments, the sample fault feature data corresponding to the set top box scene is used as training data of the neural network model, and the neural network model is trained to obtain a group fault prediction model in the set top box scene.
In some embodiments, sample fault feature data corresponding to a product package scene is used as training data of a neural network model, and the neural network model is trained to obtain a group barrier prediction model under the product package scene.
In some embodiments, sample fault feature data corresponding to a network layer device scene is used as training data of a neural network model, and the neural network model is trained to obtain a group barrier prediction model in the network layer device scene.
In some embodiments, sample fault feature data corresponding to an access failure scene is used as training data of a time series prediction model, and the time series prediction model is trained to obtain a group barrier prediction model under the access failure scene.
In some embodiments, sample fault feature data corresponding to a service authentication failure scene is used as training data of a time series prediction model, and the time series prediction model is trained to obtain a group barrier prediction model under the service authentication failure scene.
In the above embodiment, sample fault feature data corresponding to an EPG scene, sample fault feature data corresponding to a CDN scene, sample fault feature data corresponding to a set-top box scene, sample fault feature data corresponding to a product package scene, sample fault feature data corresponding to a network layer device scene, sample fault feature data corresponding to an access failure scene, and sample fault feature data corresponding to a service authentication failure scene are extracted, and then an LSTM model and an ARIMA model are trained to obtain a group fault prediction model in each scene, which facilitates subsequent prediction of a group fault amount at a target time and a group fault amount in a target time period.
Fig. 6 is a schematic structural diagram of another embodiment of an IPTV group fault early warning system of the present disclosure. The system includes a memory 610 and a processor 620, wherein: the memory 610 may be a magnetic disk, flash memory, or any other non-volatile storage medium. The memory is used to store instructions in the embodiments corresponding to fig. 1-3. Processor 620 is coupled to memory 610 and may be implemented as one or more integrated circuits, such as a microprocessor or microcontroller. The processor 620 is configured to execute instructions stored in the memory.
In some embodiments, as also shown in FIG. 7, the system 700 includes a memory 710 and a processor 720. Processor 720 is coupled to memory 710 by BUS 730. The system 700 may be further coupled to an external storage device 750 via a storage interface 740 for facilitating external data transfer, and may be further coupled to a network or another computer system (not shown) via a network interface 760, which will not be described in detail herein.
In the embodiment, the data instruction is stored in the memory, and the processor processes the instruction, so that the fault warning information can be sent out in time, and the requirements of real-time performance, accuracy, automation and comprehensiveness of IPTV operation and maintenance are met.
In other embodiments, a computer-readable storage medium has stored thereon computer program instructions which, when executed by a processor, implement the steps of the method in the embodiments corresponding to fig. 1-3. As will be appreciated by one of skill in the art, embodiments of the present disclosure may be provided as a method, apparatus, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Thus far, the present disclosure has been described in detail. Some details well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. Those skilled in the art can now fully appreciate how to implement the teachings disclosed herein, in view of the foregoing description.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the foregoing examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure. It will be appreciated by those skilled in the art that modifications can be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (10)
1. An IPTV group fault early warning method comprises the following steps:
acquiring IPTV fault code data and IPTV platform user service data;
matching and converging the IPTV fault code data and the IPTV platform user service data, and determining sample fault characteristic data corresponding to each fault scene in a plurality of fault scenes;
training a group fault prediction model according to the sample fault characteristic data;
acquiring IPTV fault characteristic data corresponding to each fault scene in a preset time period before a target prediction time range, wherein the target prediction time range comprises a target prediction time or a target prediction time period;
inputting the IPTV fault characteristic data into a group fault prediction model corresponding to a fault scene to obtain a predicted group fault amount of the target prediction time range;
if the real group barrier amount of the target prediction time range is larger than or equal to the prediction group barrier amount of a first multiple, outputting first warning information, if the real group barrier amount is smaller than the prediction group barrier amount of the first multiple and larger than or equal to the prediction group barrier amount of a second multiple, outputting second warning information, and if the real group barrier amount is smaller than the prediction group barrier amount of the second multiple and larger than or equal to the prediction group barrier amount of a third multiple, outputting third warning information; wherein the first multiple is greater than the second multiple, which is greater than a third multiple; the severity of the first warning information is greater than the severity of the second warning information, and the severity of the second warning information is greater than the severity of the third warning information.
2. The IPTV group obstacle warning method as set forth in claim 1, wherein,
the multiple fault scenes comprise an Electronic Program Guide (EPG) scene, a Content Delivery Network (CDN) scene, a set top box scene, a product package scene, a network layer equipment scene, an access failure scene and a service authentication failure scene.
3. The IPTV group fault pre-warning method of claim 2, wherein training the group fault prediction model according to the sample fault characteristic data comprises:
taking sample fault characteristic data corresponding to the EPG scene as training data of a neural network model, and training the neural network model to obtain a group fault prediction model under the EPG scene;
taking sample fault characteristic data corresponding to the CDN scene as training data of a neural network model, and training the neural network model to obtain a group fault prediction model under the CDN scene;
taking the sample fault characteristic data corresponding to the set top box scene as training data of a neural network model, and training the neural network model to obtain a group fault prediction model under the set top box scene;
taking sample fault characteristic data corresponding to the product package scene as training data of a neural network model, and training the neural network model to obtain a group barrier prediction model in the product package scene;
taking sample fault characteristic data corresponding to the network layer equipment scene as training data of a neural network model, and training the neural network model to obtain a group barrier prediction model under the network layer equipment scene;
taking sample fault characteristic data corresponding to the access failure scene as training data of a time series prediction model, and training the time series prediction model to obtain a group barrier prediction model under the access failure scene;
and taking the sample fault characteristic data corresponding to the service authentication failure scene as training data of a time sequence prediction model, and training the time sequence prediction model to obtain a group fault prediction model under the service authentication failure scene.
4. The IPTV group fault early warning method of claim 2, wherein the IPTV platform user service data comprises IPTV user home network element data and network topology.
5. The IPTV group fault early warning method of claim 4, wherein the matching and aggregating the IPTV fault code data and the IPTV platform user service data comprises:
and performing big data convergence matching on the IPTV fault code data and the IPTV user attributive network element data and network topology according to the service account number of the IPTV fault code data and the identification field of the production serial number of the set top box, and respectively matching IPTV fault code data corresponding to the EPG equipment, the CDN node, the model of the set top box, the product package, the network layer equipment and the service management platform.
6. The IPTV group fault pre-warning method as claimed in claim 5, wherein determining the sample fault signature data comprises:
respectively extracting feature data of IPTV fault code data corresponding to the EPG equipment, the CDN node, the model of the set-top box, the product package and the network layer equipment to obtain sample fault feature data corresponding to the EPG scene, sample fault feature data corresponding to the CDN scene, sample fault feature data corresponding to the set-top box scene, sample fault feature data corresponding to the product package scene and sample fault feature data corresponding to the network layer equipment scene;
and determining sample fault characteristic data corresponding to the access failure scene and sample fault characteristic data corresponding to the service authentication failure scene according to the fault code meaning of the IPTV fault code data corresponding to the service management platform.
7. The IPTV group fault early warning method according to claim 1, wherein the IPTV fault code data comprises fault code data reported by a set top box and fault code data reported by a user through code scanning;
analyzing a video source Uniform Resource Locator (URL) requested by the set top box in fault code data reported by the set top box, and determining a television channel corresponding to a fault;
and analyzing the EPG page requested by the set top box in the fault code data reported by the set top box, and determining the EPG page corresponding to the fault.
8. An IPTV group fault early warning system comprises:
the data acquisition module is configured to acquire IPTV fault code data and IPTV platform user service data;
the big data processing module is configured to match and gather the IPTV fault code data and the IPTV platform user service data, and determine sample fault characteristic data corresponding to each fault scene in a plurality of fault scenes;
a model training module configured to train a group fault prediction model according to the sample fault feature data;
the system comprises a characteristic data acquisition module, a characteristic data acquisition module and a characteristic data acquisition module, wherein the characteristic data acquisition module is configured to acquire IPTV fault characteristic data corresponding to each fault scene in a preset time period before a target prediction time range, and the target prediction time range comprises a target prediction time or a target prediction time period;
the group fault amount prediction module is configured to input the IPTV fault characteristic data into a group fault prediction model corresponding to a fault scene to obtain a predicted group fault amount of the target prediction time range;
the early warning and analysis module is configured to output first warning information if a real group barrier amount of the target prediction time range is larger than or equal to a first multiple of a prediction group barrier amount, output second warning information if the real group barrier amount is smaller than the first multiple of the prediction group barrier amount and is larger than or equal to a second multiple of the prediction group barrier amount, and output third warning information if the real group barrier amount is smaller than the second multiple of the prediction group barrier amount and is larger than or equal to a third multiple of the prediction group barrier amount; wherein the first multiple is greater than the second multiple, which is greater than a third multiple; the severity of the first warning information is greater than the severity of the second warning information, and the severity of the second warning information is greater than the severity of the third warning information.
9. An IPTV group fault early warning system comprises:
a memory; and
a processor coupled to the memory, the processor configured to execute the IPTV group obstacle warning method of any of claims 1-7 based on the instructions stored in the memory.
10. A computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the IPTV group obstacle warning method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911226111.3A CN112911272B (en) | 2019-12-04 | 2019-12-04 | IPTV group fault early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911226111.3A CN112911272B (en) | 2019-12-04 | 2019-12-04 | IPTV group fault early warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112911272A CN112911272A (en) | 2021-06-04 |
| CN112911272B true CN112911272B (en) | 2022-11-11 |
Family
ID=76104517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911226111.3A Active CN112911272B (en) | 2019-12-04 | 2019-12-04 | IPTV group fault early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112911272B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115996265A (en) * | 2023-03-23 | 2023-04-21 | 成都同步新创科技股份有限公司 | Large-area fault early warning method and system applied to maintenance call center |
| CN116248959B (en) * | 2023-05-12 | 2023-07-28 | 深圳市橙视科技发展有限公司 | Network player fault detection method, device, equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5465321A (en) * | 1993-04-07 | 1995-11-07 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Hidden markov models for fault detection in dynamic systems |
| CN101616019A (en) * | 2008-06-26 | 2009-12-30 | 华为技术有限公司 | A kind of method, network node and system that realizes that network failure detects |
| CN104284210A (en) * | 2013-07-05 | 2015-01-14 | 上海帕科软件科技有限公司 | Iptv fault self-diagnosis network system |
| CN108833172B (en) * | 2018-06-21 | 2021-05-25 | 中国联合网络通信集团有限公司 | Network fault alarm processing method and device and network system |
-
2019
- 2019-12-04 CN CN201911226111.3A patent/CN112911272B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112911272A (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11140021B2 (en) | Method and apparatus for determining fault type | |
| US9432272B2 (en) | Automated network condition identification | |
| CN109120461B (en) | A kind of service feature end-to-end monitoring method, system and device | |
| CN112911272B (en) | IPTV group fault early warning method and system | |
| CN111368089A (en) | Service processing method and device based on knowledge graph | |
| CN105577411B (en) | Cloud service monitoring method and device based on service origin | |
| CN109213758B (en) | Data access method, device, equipment and computer readable storage medium | |
| US20150095960A1 (en) | Cable Network Data Analytics System | |
| CN110620699A (en) | Message arrival rate determination method, device, equipment and computer readable storage medium | |
| CN105553700A (en) | Intelligent equipment fault identification detection and solution providing system | |
| CN109740789B (en) | Wiring management method, device, equipment and storage medium | |
| CN109818764B (en) | IPTV network equipment fault detection method and device | |
| TWI662809B (en) | Obstacle location system and maintenance method for image streaming service | |
| CN109040197A (en) | A kind of intelligent gateway management system and method based on web SiteServer LBS | |
| CN116094174A (en) | Knowledge graph-based power grid operation and maintenance monitoring method, system, equipment and medium | |
| CN110647448A (en) | Mobile application operation log data real-time analysis method, server and system | |
| CN116016150A (en) | Early warning method and device for physical network, electronic equipment and storage medium | |
| CN112312209B (en) | Comprehensive alarm generation method, device, server and storage medium | |
| CN114827951A (en) | Vehicle network quality analysis method and system based on vehicle terminal and storage medium | |
| CN109756384B (en) | Data source state determination method and device and computer readable storage medium | |
| CN113327063B (en) | Resource detection method, device, electronic equipment and computer readable storage medium | |
| CN113014907B (en) | Network protocol television fault early warning method, device and storage medium | |
| CN107317692A (en) | Failure report method and device | |
| CN115731487A (en) | Data processing method, device, equipment and readable storage medium | |
| CN116968583A (en) | Method and device for determining fault of charging pile, storage medium and computer equipment |
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 |