WO2020211561A1 - 数据的处理方法、装置、存储介质及电子装置 - Google Patents

数据的处理方法、装置、存储介质及电子装置 Download PDF

Info

Publication number
WO2020211561A1
WO2020211561A1 PCT/CN2020/077980 CN2020077980W WO2020211561A1 WO 2020211561 A1 WO2020211561 A1 WO 2020211561A1 CN 2020077980 W CN2020077980 W CN 2020077980W WO 2020211561 A1 WO2020211561 A1 WO 2020211561A1
Authority
WO
WIPO (PCT)
Prior art keywords
data collection
data
application instance
network node
target network
Prior art date
Application number
PCT/CN2020/077980
Other languages
English (en)
French (fr)
Inventor
孟伟
袁丽雅
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Priority to US17/435,747 priority Critical patent/US12074767B2/en
Priority to EP20791480.5A priority patent/EP3958508A4/en
Publication of WO2020211561A1 publication Critical patent/WO2020211561A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/12—Discovery or management of network topologies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/06—Management of faults, events, alarms or notifications
    • H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0893—Assignment of logical groups to network elements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
    • H04L41/0897—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities by horizontal or vertical scaling of resources, or by migrating entities, e.g. virtual resources or entities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/04—Arrangements for maintaining operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0894—Policy-based network configuration management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/34—Signalling channels for network management communication
    • H04L41/342—Signalling channels for network management communication between virtual entities, e.g. orchestrators, SDN or NFV entities

Definitions

  • This application relates to the field of communications, for example, to a data processing method, device, storage medium, and electronic device.
  • Network automation refers to the process of automatic configuration, management, testing, deployment, and operation of physical and virtual devices in a network.
  • the network under the curse of this technology can automatically execute the tasks and functions established every day.
  • Collaboration, automation, and network orchestration can simplify network operations involving complex configuration and device management to adapt to the business flexibility of the ever-changing environment.
  • the network is becoming more and more complex, and the data generated by the network system also has the characteristics of diversity, multi-dimensionality and unstructured. Due to the possible correlation with business data, the traditional manual analysis and processing methods are inefficient and costly, and the rule-based automated processing methods have narrow application areas, insufficient flexibility and low accuracy. With the rise of big data and artificial intelligence, more and more intelligent analysis algorithms are also applied in the field of operation and maintenance. By analyzing the massive data owned and generated by the operation and maintenance system itself, they play a greater role in problem location, traffic prediction, auxiliary decision-making, intelligent alarms, and automatic fault recovery, thereby further reducing operation and maintenance costs.
  • the embodiments of the present invention provide a data processing method, device, storage medium, and electronic device, so as to at least solve the problem that big data and artificial intelligence technology is introduced into network operation and maintenance management in related technologies, and the network architecture cannot achieve network data acquisition, and The problem of the coordination of the artificial intelligence management plane.
  • a data collection request method which includes: after determining that an application instance is established, an orchestrator generates a data collection request message corresponding to the application instance, and sends it to the next communication node, where ,
  • the next communication node includes one of the following: a network control device, a target network node; the target network node performs data collection according to a data collection request message received from the orchestrator or via the network control device, and
  • the data collection result is sent to the processing device of the application example; the processing device of the application example processes the data collection result through the model in the application example, and outputs the processing result.
  • a data processing device including: a sending module, located in an orchestrator, for generating a data collection request message corresponding to the application instance and sending it to the next communication node,
  • the next communication node includes one of the following: a network control device, a target network node; a collection module, located at the target network node, for data collection requests received from the orchestrator or via the network control device
  • the message performs data collection, and sends the data collection result to the processing device of the application example;
  • the processing module is located in the processing device of the application example and is used to process the data collection result through the model in the application example , And output the processing result.
  • a storage medium in which a computer program is stored, wherein the computer program is configured to execute any one of the above method embodiments when running.
  • an electronic device including a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to execute any of the above Method embodiment.
  • Fig. 1 is a flowchart of a data processing method according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of filtering data options according to an embodiment of the present invention.
  • Fig. 3 is a schematic diagram based on scenario 1 according to an embodiment of the present invention.
  • Fig. 4 is a schematic diagram based on scenario 2 according to an embodiment of the present invention.
  • Fig. 5 is a structural block diagram of a data processing device according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for requesting data collection according to an embodiment of the present invention. As shown in FIG. 1, the process includes the following steps:
  • Step S102 After determining that the application instance is established, the orchestrator generates a data collection request message corresponding to the application instance and sends it to the next communication node, where the next communication node includes one of the following: a network control device, a target Network node.
  • Step S104 The target network node performs data collection according to the data collection request message received from the orchestrator or via the network control device, and sends the data collection result to the processing device of the application instance.
  • Step S106 The processing device of the application example processes the data collection result through the model in the application example, and outputs the processing result.
  • Types of orchestrators include, but are not limited to, Machine Learning Function Orchestrator (MLFO).
  • MLFO Machine Learning Function Orchestrator
  • the orchestrator deploys application instances through the Artificial Intelligence (AI) platform.
  • the application instance management entries are pre-created in the orchestrator, and the state machine in the entries is initialized. After the application instance is successfully created, the successfully created information is sent to the orchestrator, the corresponding application instance management entry in the orchestrator is activated, the state machine in the entry is set to start, and other information in the entry is assigned according to the situation of the instance, and every other segment Time to send a keep-alive message to the processing device of the application instance to determine the status of the use instance; and if the application instance fails to be created, the creation failure message is sent to the orchestrator, and the orchestrator issues an alarm message, starts the automatic repair process or deletes the pre-create Application instance management entries.
  • the management items include information such as the state machine, location, type, model and algorithm combination, life cycle, data preprocessing algorithm, and data collection requirements of each model of the application instance.
  • the network control device refers to a network orchestration or control plane on the network side, for example, a network slice management function (Network Slice Management Function, NSMF).
  • NSMF Network Slice Management Function
  • the type of target network node is also adjusted according to specific implementations.
  • the target network node may be a network element (Network Subnet Slice Management Function) in the 5th Generation (5G) communication system. , NSSMF), and 5G network slicing.
  • NSSMF Network Subnet Slice Management Function
  • the target network node can also be an alarm collection platform.
  • the data collection request message includes: location information of the application instance, network node information, and data collection content.
  • the method further includes: the network control device determines a target network node for data collection according to the network node information in the data collection request message; The network control device sends the data collection request message to the target network node.
  • the number of target network nodes may be one or multiple, there are one or more target network node information in the network node information.
  • this information can be used to instruct the network control device to send data collection request messages to multiple target network nodes at the same time, and it can also be used to instruct the network control device to send data collection request messages to one or more of the multiple target network nodes.
  • the target network node is forwarded to other target network nodes as an intermediate node.
  • the specific quantity depends on the number and type of application instances and the models included in the use cases.
  • the orchestrator will directly send a data collection request message to the target network node.
  • the network node information at this time can also be used to assist the network node receiving the information to determine whether the node is the target network of the orchestrator node. If it is correct, the network node performs corresponding data collection and can also respond to the orchestrator. If the network node information is wrong, the network node will refuse to perform data collection and send an error response message to the orchestrator. So that the orchestrator can find a suitable target network node in time.
  • the method further includes: the network control device receives the processing result output by the processing device of the application instance; and the network control device configures the network according to the processing result.
  • the network control device Since the network control device is used to control the network side, after receiving the processing result output by the processing device, the network control device can optimize the network environment by means of network configuration according to the decision of the application instance.
  • the target network node performs data collection according to a data collection request message received from the orchestrator or via the network control device, including: the target network node determines the need according to the location information of the application instance An application example for data collection; the target network node collects data corresponding to the application example.
  • the collection of the data corresponding to the application instance by the target network node includes: the target network node screens the data collection content according to a data feature set; the target network node screens the filtered data Collect content for data collection.
  • FIG. 2 is an embodiment according to the present invention.
  • the schematic diagram of the selection of data options is shown in Figure 2.
  • the bitmap method can be used to filter the information that needs to be collected in the data feature set.
  • the data feature set is determined in the following manner: the encoder determines the data feature set according to the network requirements of the application instance, and sends it to the next communication node, or, after receiving the After the data collection request message, the target network node analyzes the network requirements of the application instance corresponding to the location information of the application instance, and determines the data feature set.
  • the data feature set includes: network information of the network where the target network node is located; user information of the target network node; device information of the device where the target network node is located; datagram of the target network node Text information.
  • the network node side each has a data feature set, and the network element device will collect data according to the data feature set.
  • the network information includes Internet Protocol (IP) address, protocol number, and port number.
  • the user information includes: user identification (Identifier, ID), charging attributes, and the number of books.
  • the device information can be the current device's fan speed, temperature and humidity and other environmental parameters.
  • the data message information may include: message type, flow, delay and other information.
  • the data collection content includes one of the following: the number and type of users, user session information, user traffic information, data collection period, and network service alarm information.
  • the processing device of the application instance processes the data collection result through the model in the application instance, including: the processing device classifies the data collection result according to the type of the data collection result, and classifies the classified data
  • the data collection result is configured in a corresponding model; the processing device processes the classified data collection result in the model, wherein the processing method includes: predicting data and inferring data .
  • the model refers to a system that is learned from existing data or experience through machine learning, deep learning and other methods to achieve specific analysis, prediction and other functions.
  • Each model has its own functions. For example, certain models can be used to predict when the number of new users and sessions reaches the required number. Another example is some models that can be used to predict the time for slice expansion. In addition, it is also possible to determine the location of the alarm in the device according to the quantity or type of the alarm information. At the same time, the various models are also related. For example, it is used to predict the time when the number of new users and the number of sessions reaches the required number, which needs to be used as the input for predicting the expansion of the slice. Therefore, models can be connected in series. The function of the specific model needs to be determined according to the function of the application instance.
  • the processing device will perform corresponding processing operations. Such as filtering, screening, matching, classification and so on.
  • processing operations Such as filtering, screening, matching, classification and so on.
  • the processed data will continue to be predicted and reasoned in other models in the application instance, until the processing is completed, the final processing result will be output.
  • Prediction refers to the time, location, and corresponding value of resource consumption when the content of data collection reaches the preset result. For example, it is predicted that the number of new users and the peak number of sessions will be completed within 2 hours.
  • Prediction means that within a certain period of time, or in a certain place, the content of the collected data can achieve a predetermined result. For example, within 2 hours, the number of new users and sessions reached a peak. For another example, according to user habits, the traffic used by a user on weekends is predicted to be 10G.
  • Inference is a conclusion based on the content of the collected data or the result of the prediction. For example, if the number of new users and the number of sessions reaches a peak within 2 hours, then it is inferred that the slice expansion needs to be performed after 1.5 hours.
  • the method according to the above embodiment can be implemented by software plus the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation. .
  • the technical solution of the present application can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium (such as ROM/RAM, magnetic disk, and optical disk), and includes several instructions to make a terminal
  • a device which can be a mobile phone, a computer, a server, or a network device, etc.) executes the method described in the embodiment of the present invention.
  • Scenario 1 Use artificial intelligence to realize 5G core network slice usage prediction and intelligent deployment.
  • Fig. 3 is a schematic diagram based on scenario 1 according to an embodiment of the present invention.
  • the orchestrator is presented in the form of MLFO (Machine Learning Function Orchestrator) to realize interaction with application instances and NSMF.
  • MLFO Machine Learning Function Orchestrator
  • the application examples are embedded in NWDAF (Network Data Analysis Function) in the form of microservices.
  • NWDAF Network Data Analysis Function
  • the application examples include data preprocessing modules, model 1 and model 2, and model 1 is for 5G in the next 2 hours.
  • the core network slicing service flow and the number of users are predicted.
  • Model 2 is to calculate the predicted result and analyze whether the capacity needs to be expanded or reduced.
  • the data collector is embedded in the network elements of NSSMF and 5G network slices.
  • application instance 1 (hereinafter referred to as instance 1) is successfully created in NWDAF, and MLFO is notified; MLFO activates the management entry of artificial intelligence instance 1, and sets the state machine of instance 1 to the running state; and sends a guarantee every 60 seconds Live messages to confirm the status of instance 1.
  • the data collection request message includes: the IP address of instance 1 (application instance location information), the designated data collection from NSSMF and 5G network slice 1 (target network element), and the collected content includes the number of existing users, user session information, per second New session information, user traffic information, time stamps, holiday factors, etc. (data collection requirements), data collection cycle is 100ms.
  • MLFO sends the aforementioned data collection request message to NSMF.
  • NSMF analyzes the content of the data collection request message, and sends the IP address and data collection requirements of instance 1 to the designated NSSMF.
  • NSSMF continues to send the IP address and data collection requirements of instance 1 to the designated 5G network slice 1.
  • NSSMF and 5G network slice 1 are collected according to data collection requirements, including the number of users, user session information, new session information per second, user traffic information, time stamps, and holiday factors. And send the above information to Application Example 1.
  • the data preprocessing module classifies the above data and sends it to model 1.
  • Model 1 predicts that the number of new users and sessions will reach a peak in the next 2 hours; and sends the predicted value to Model 2.
  • Model 2 analyzes the need for slice expansion after 1.5 hours based on the results predicted by Model 1.
  • Model 2 sends the relevant expansion decision to the Policy Control FuncTIon (PCF), and the PCF sends the corresponding network management strategy to the NSSMF to execute the expansion plan.
  • PCF Policy Control FuncTIon
  • Scenario 2 Artificial intelligence is applied to the network root cause analysis system, through model reasoning, to achieve precise fault location and traceability.
  • Fig. 4 is a schematic diagram based on scenario 2 according to an embodiment of the present invention.
  • application example 1 is applied to frequent alarm analysis, that is, if a certain number of specific alarms and specific events occur within a certain period of time, it can be considered that there is a certain correlation between these alarms and events.
  • Application example 2 is applied to upper and lower alarm analysis, that is, the impact of a fault in the lower layer business on the same professional network is reflected in a large area of phenomenon alarm caused by a certain root cause alarm, and it is necessary to quickly obtain the root cause alarm that caused the fault.
  • application example 1 (hereinafter referred to as example 1) and application example 2 (hereinafter referred to as example 2) are successfully created in the network root cause analysis system, and the orchestrator is notified; the orchestrator activates the artificial intelligence examples 1 and 2 Manage entries, set the state machines of instance 1 and instance 2 to the running state; and send a keep-alive message every 30 seconds to confirm the status of instance 1 and instance 2.
  • the data collection request message of Example 1 includes: the IP address of Example 1 (application instance location information), the target network element is an alarm collection platform, the collected content includes all equipment alarm information (data collection requirements), and the data collection cycle is triggered to report.
  • the data collection request message of Example 2 includes: the IP address of Example 2 (application instance location information), the target network element is the alarm collection platform, the collected content includes all network service alarm information (data collection requirements), and the data collection cycle is triggered to report .
  • the orchestrator sends the above two data collection request messages to the alarm collection platform.
  • the alarm collection platform receives the alarm information and finds that it is an alarm from the device.
  • the content of the alarm is "The temperature of the A network element B board is too high", so the alarm is sent to application instance 1.
  • the alarm collection platform received 100 of the same above-mentioned alarms within 2 minutes, and the alarm collection platform sent all these alarms to application instance 1.
  • application example 1 receives these alarm information, and the data preprocessing module filters, screens, matches, and classifies the alarm information, and then sends it to model 1.
  • Step 5 Model 1 analyzes and infers by receiving 100 same alarms within 2 minutes, and thinks that it is possible that the temperature of the board may rise due to poor ambient temperature and humidity.
  • Application example 1 combines these alarms and sends the inference result to the root cause alarm summary platform.
  • the sixth step the alarm collection platform received the alarm information and found that it was an alarm from the network.
  • the content of the alarm was "Transport-Multiprotocol Label Switching Section (TMS) link interruption", “B tunnel link interruption” ", “Pseudo-wire C link interruption”, “D service interruption”, “E fiber signal loss (Loss Of Signal, LOS) alarm", so these several alarms are sent to application instance 2.
  • TMS Transport-Multiprotocol Label Switching Section
  • application example 2 receives these alarm information, and the data preprocessing module filters, screens, matches, and classifies the alarm information, and then sends it to model 2.
  • Model 2 analyzes these alarm information and finds that these alarms occur for the same reason, that is, "E fiber is broken, and the port where the fiber is located reports LOS alarm".
  • Application example 2 sends the above reasoning result to the root cause alarm summary platform.
  • Scenario 3 The function of data filtering for a pre-selected data feature set.
  • Table 1 For the intelligent traffic engineering of the bearer network, the following Table 1 is provided for understanding.
  • the numbers in Table 1 represent the feature number identification, namely 0-12, and the text under the feature number identification represents the feature type.
  • the specific table is as follows:
  • the orchestrator collects eight data collection functions numbered 0,1,2,3,8,9,10,11 for the network traffic engineering characteristics of the interactive network. Therefore, the arranger configures the above eight data collection functions in the data feature set.
  • the target network node After receiving the data feature set via the network control device, the target network node performs data collection for 0,1,2,3,8,9,10,11.
  • the target network node collects eight data collection functions numbered 0,1,2,3,8,9,10,11 according to the network traffic engineering characteristics of the network where it is located, and performs data collection.
  • a device for requesting data collection is also provided, and the device is used to implement the above-mentioned embodiments and optional implementation manners, and those that have been explained will not be repeated.
  • the term "module” can implement a combination of software and/or hardware with predetermined functions.
  • the devices described in the following embodiments are preferably implemented by software, hardware or a combination of software and hardware is also possible and conceived.
  • Fig. 5 is a data processing device according to an embodiment of the present invention. As shown in Fig. 5, the device includes:
  • the sending module 52 located in the orchestrator, is used to generate a data collection request message corresponding to the application instance and send it to the next communication node, where the next communication node includes: a network control device, a target network node; and collection
  • the module 54 is located in the target network node, and is used to collect data from the data collection request message received by the orchestrator or via the network control device, and send the data collection result to the processing device of the application instance;
  • the module 56 is located in the processing device of the application example, and is used to process the data collection result through the model in the application example and output the processing result.
  • Each of the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following way, but not limited to this: the above modules are all located in the same processor; or, the above modules are located in different combinations in any combination. In the processor.
  • An embodiment of the present invention also provides a storage medium in which a computer program is stored, wherein the computer program is configured to execute the steps in any one of the foregoing method embodiments when running.
  • the foregoing storage medium may be configured to store a computer program for executing the following steps:
  • the orchestrator After determining that the application instance is established, the orchestrator generates a data collection request message corresponding to the application instance and sends it to the next communication node, where the next communication node includes one of the following: a network control device, a target network Node; S2, the target network node performs data collection according to the data collection request message received from the orchestrator or via the network control device, and sends the data collection result to the processing device of the application instance; S3, so
  • the processing device of the application example processes the data collection result through the model in the application example, and outputs the processing result.
  • the foregoing storage medium may include, but is not limited to: Universal Serial Bus (Universal Serial Bus, U disk), Read-Only Memory (ROM), and Random Access Memory (Random Access Memory, RAM), mobile hard drives, magnetic disks or optical disks and other media that can store computer programs.
  • Universal Serial Bus Universal Serial Bus, U disk
  • ROM Read-Only Memory
  • RAM Random Access Memory
  • mobile hard drives magnetic disks or optical disks and other media that can store computer programs.
  • An embodiment of the present invention also provides an electronic device, including a memory and a processor, the memory is stored with a computer program, and the processor is configured to run the computer program to execute the steps in any of the foregoing method embodiments.
  • the aforementioned electronic device may further include a transmission device and an input-output device, wherein the transmission device is connected to the aforementioned processor, and the input-output device is connected to the aforementioned processor.
  • the foregoing processor may be configured to execute the following steps through a computer program:
  • the orchestrator After determining that the application instance is established, the orchestrator generates a data collection request message corresponding to the application instance and sends it to the next communication node, where the next communication node includes one of the following: a network control device, a target network Node; S2, the target network node performs data collection according to the data collection request message received from the orchestrator or via the network control device, and sends the data collection result to the processing device of the application instance; S3, so
  • the processing device of the application example processes the data collection result through the model in the application example, and outputs the processing result.
  • the above-mentioned modules or steps of this application can be implemented by a general computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by computing
  • the program code executable by the device is implemented, so that they can be stored in a storage device for execution by a computing device, and in some cases, the steps shown or described can be executed in a different order than here, or They are made into individual integrated circuit modules respectively, or multiple modules or steps in them are made into a single integrated circuit module to achieve. In this way, this application is not limited to any specific hardware and software combination.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Debugging And Monitoring (AREA)

Abstract

一种数据的处理方法、装置、存储介质及电子装置，方法包括：在确定应用实例建立后，编排器生成应用实例对应的数据采集请求消息，并发送至下一通信节点，下一通信节点包括网络控制装置、目标网络节点之一；目标网络节点根据从编排器或经由网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至应用实例的处理装置；应用实例的处理装置通过应用实例中的模型对数据采集结果进行处理，并输出处理结果。

Description

数据的处理方法、装置、存储介质及电子装置
本申请要求在2019年04月15日提交中国专利局、申请号为201910300209.2的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信领域，例如，涉及一种数据的处理方法、装置、存储介质及电子装置。
背景技术
随着网络拓扑日益复杂，网络应用日趋繁多，对于很多企业而言，采用缺乏灵活性的网络已成为阻碍其业务发展的一大瓶颈，因为这就降低了部署强大且响应迅速的网络基础架构的可能。另一方面，对于服务提供商而言，因为专注于提高网络灵活性和可靠性，需要控制运营支出和资本支出。这时服务提供商就必须利用自动化去解决那些耗时、重复或容易出错的任务，来提高运营效率、利润以及用户的满意度。
网络自动化是指一个网络中的物理和虚拟设备的自动配置、管理、测试、部署和操作的过程。在该技术加持下的网络，可每天自动执行制定好的任务和功能。而通过协作、自动化和网络编排能够简化涉及复杂配置和设备管理的网络操作，以适应不断变化环境的业务灵活性。
网络日趋复杂，网络系统产生的数据也具备多样性、多维性和非结构化等特点。由于同业务数据可能存在相关性，而传统的手动分析处理方式效率低、成本高，基于规则的自动化处理方式适用面窄、不够灵活且精确度不高。随着大数据和人工智能的兴起，越来越多的智能分析算法也应用于运维领域。它们通过分析运维系统本身所拥有和产生的海量数据，在问题定位、流量预测、辅助决策、智能报警和自动故障恢复等方面发挥较大的作用，从而进一步降低运维成本。
在大数据及人工智能技术引入网络运维管理中，相关技术中的网络并没有如何获取网络数据、与人工智能管理平面的协同等具体实现方案。
发明内容
本发明实施例提供了一种数据的处理方法、装置、存储介质及电子装置，以至少解决相关技术中在大数据及人工智能技术引入网络运维管理中，网络架 构无法实现获取网络数据、与人工智能管理平面的协同的问题。
根据本发明的一个实施例，提供了一种数据采集的请求方法，包括：在确定应用实例建立后，编排器生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括以下之一：网络控制装置，目标网络节点；所述目标网络节点根据从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置；所述应用实例的处理装置通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
根据本发明的另一个实施例，提供了一种数据的处理装置，包括：发送模块，位于编排器中，用于生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括以下之一：网络控制装置，目标网络节点；采集模块，位于所述目标网络节点，用于从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置；处理模块，位于所述应用实例的处理装置，用于通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
根据本发明的又一个实施例，还提供了一种存储介质，所述存储介质中存储有计算机程序，其中，所述计算机程序被设置为运行时执行上述任一项方法实施例。
根据本发明的又一个实施例，还提供了一种电子装置，包括存储器和处理器，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行上述任一项方法实施例。
通过本申请，通过在人工智能管理平面上的应用实例创建后，生成相应的采集请求并发送至网络侧，因此，不仅能够解决，网络架构无法实现获取网络数据、与人工智能管理平面的协同的问题。同时还能够有效地实现网络自动化、智能化和闭环控制。
附图说明
图1是根据本发明实施例的一种数据的处理方法的流程图；
图2是根据本发明实施例的一种数据选项的筛选示意图；
图3是根据本发明实施例的基于场景1的示意图；
图4是根据本发明实施例的基于场景2的示意图；
图5是根据本发明实施例的一种数据的处理装置的结构框图。
具体实施方式
下文中将参考附图并结合实施例来详细说明本申请。
本申请中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
实施例1
在本实施例中提供了一种数据采集的请求方法，图1是根据本发明实施例的一种数据采集的请求方法的流程图，如图1所示，该流程包括如下步骤：
步骤S102，在确定应用实例建立后，编排器生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括以下之一：网络控制装置，目标网络节点。
步骤S104，所述目标网络节点根据从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置。
步骤S106，所述应用实例的处理装置通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
编排器的类型包括但不限于，机器学习功能编排器(Machine Learning Function Orchestrator，MLFO)。
编排器通过人工智能(Artificial Intelligence，AI)平台部署应用实例，编排器内预创建应用实例管理条目，条目中的状态机为初始化。应用实例成功创建后，将成功创建的信息发送到编排器，编排器内相应的应用实例管理条目激活，条目中状态机设置为启动，条目中其他信息按照该实例的情况赋值，并且每隔一段时间向应用实例的处理装置发送保活报文以确定使用实例的状态；而若应用实例创建失败，则发送创建失败的信息到编排器，编排器发出告警信息，启动自动修复流程或删除预创建应用实例管理条目。而管理条目包括应用实例的状态机、位置、类型、模型与算法组合、生命周期、数据预处理算法，以及各模型数据采集需求等信息。
网络控制装置是指，在网络侧当中的网络编排或控制平面，例如，网络切片管理功能网元(Network Slice Management Function，NSMF)。
目标网络节点的类型也根据具体实施方式进行调整。例如，如果编排器为MLFO，网络控制装置为NSMF的情况下，目标网络节点可以是第五代(the 5th Generation，5G)通信系统中的网络子网切片管理功能网元(Network Subnet Slice Management Function，NSSMF)，以及5G网络切片。而例如在系统故障检测 的场景当中，目标网络节点还可以是告警采集平台。
可选地，所述数据采集请求消息包括：所述应用实例的位置信息，网络节点信息，数据采集内容。
可选地，所述下一通信节点为网络控制装置时，所述方法还包括：所述网络控制装置根据所述数据采集请求消息中的网络节点信息确定用于进行数据采集的目标网络节点；所述网络控制装置将所述数据采集请求消息发送至所述目标网络节点。
由于目标网络节点的数量可以是一个，也可以是多个，因此，在网络节点信息当中也存在一个或者多个目标网络节点的信息。在该信息中，可以用于指示网络控制装置同时向多个目标网络节点发送数据采集请求消息，也可以用于指示网络控制装置向多个目标网络节点的其中一个或者多个发送，再由这些目标网络节作为中间节点转发至其他的目标网络节点。具体的数量，编排器根据应用实例的数量、类型以及使用实例中包括的模型相关。
如果没有网络控制装置的话，则编排器会直接向目标网络节点发送数据采集请求消息，此时的网络节点信息还能够用于协助接收到该信息的网络节点判断是否该节点是编排器的目标网络节点。如果正确，则网络节点进行相应的数据采集，还可以对编排器进行响应。而如果网络节点信息错误，则网络节点会拒绝执行数据采集，以及向编排器发送错误响应信息。以便编排器及时找到合适的目标网络节点。
可选地，所述方法还包括：所述网络控制装置接收所述应用实例的处理装置输出的所述处理结果；所述网络控制装置根据所述处理结果对网络进行配置。
由于网络控制装置用于对网络侧进行控制，因此，在接收到处理装置输出的处理结果后，网络控制装置能够根据应用实例的决策通过网络配置的方式去对网络环境进行优化。
可选地，所述目标网络节点根据从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，包括：所述目标网络节点根据所述应用实例的位置信息，确定需要进行数据采集的应用实例；所述目标网络节点采集所述应用实例对应的数据。
可选地，所述目标网络节点采集所述应用实例对应的数据，包括：所述目标网络节点根据数据特征集合对所述数据采集内容进行筛选；所述目标网络节点对筛选后的所述数据采集内容进行数据采集。
通过筛选的方式，目标网络节点筛选出其中适合该应用实例中模型的一部分数据选项，从而避免所有数据选项都进行采集，导致系统负荷过大；例如， 图2是根据本发明实施例的一种数据选项的筛选示意图，如图2所示，可以采用位图方法，对数据特征集合中的需要采集的信息进行筛选。
可选地，所述数据特征集合通过如下方式确定：所述编码器根据所述应用实例的网络需求确定所述数据特征集合，并发送至所述下一通信节点，或，在接收到所述数据采集请求消息后，所述目标网络节点分析所述应用实例的位置信息对应的应用实例的网络需求，并确定所述数据特征集合。
可选地，所述数据特征集合包括：所述目标网络节点所在网络的网络信息；所述目标网络节点的用户信息；所述目标网络节点所在设备的设备信息；所述目标网络节点的数据报文信息。
针对每个应用实例，网络节点侧均互具有数据特征集合，网元设备会根据数据特征集合，进行数据的采集。网络信息包括网际互连协议(Internet Protocol，IP)地址，协议号，端口号。而用户信息包括：用户标识(Identifier，ID)，计费属性，用书数量。设备信息则可以是当前设备的风扇转速，温度湿度等环境参数。数据报文信息则可以包括：报文的类型，流量，时延等信息。
可选地，所述数据采集内容包括以下之一：用户数量和类型，用户会话信息，用户流量信息，数据采集周期，网络业务告警信息。
可选地，所述应用实例的处理装置通过所述应用实例中的模型对所述数据采集结果进行处理，包括：所述处理装置根据所述数据采集结果的类型进行分类，并将分类后的所述数据采集结果配置在对应的模型当中；所述处理装置在所述模型中对分类后的所述数据采集结果进行处理，其中，所述处理方式包括：对数据进行预测，对数据进行推理。
所述模型是指通过机器学习、深度学习等方法，从已有的数据或经验中学习得到的实现特定的分析、预测等功能的系统。
每个模型都有其制定的功能。例如，某些模型可以用于预测在新建用户以及会话的数目达到所需数量的时间。又如某些模型可以用于预测进行切片扩容的时间。此外，还可以是根据告警信息的数量或者类型确定设备中告警的位置。同时各个模型之间也是存在关联的。例如，用于预测在新建用户以及会话的数目达到所需数量的时间需要作为预测进行切片扩容的输入。因此，模型与模型之间可以通过串联连接。具体模型的功能需根据应用实例的功能来决定。
根据每个模型输出的结果，处理装置会进行相应的处理操作。例如过滤，筛选，匹配，分类等等。然而将处理好的数据继续在应用实例中其他的模型中进行预测，推理，直到处理完毕，则将最终的处理结果进行输出。
预测是指数据采集内容达到预设的结果的时间，位置，资源消耗对应的数 值。例如，新建用户以及会话数达到峰值预测在2个小时内完成。
预测是指在某段时间内，或者在某个地方，采集数据内容能够达到预定的结果。例如，在2个小时之内，新建用户以及会话数达到峰值。又例如，根据用户习惯，某个用户在周末所使用的流量预测为10G。
而推理则是根据采集数据内容或者预测的结果所推理出的结论。例如，如果在2个小时之内，新建用户以及会话数达到峰值的话，那么则推理出需要在1.5小时后需要进行切片扩容。
当然，上述预测和推理的描述仅仅是举例，其他类型思路的预测和推理过程均在本实施例的保护范围之内，在此不做赘述。
通过以上的实施方式的描述，可以清楚地了解到根据上述实施例的方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，或者网络设备等)执行本发明实施例所述的方法。
为了更好的理解上述实施例中记载的技术方案，在本实施例中还提供了如下两种场景以便理解：
场景1：运用人工智能实现5G核心网切片使用率预测及智能化部署的方案。
图3是根据本发明实施例的基于场景1的示意图。如图3所示，编排器在此场景中，以MLFO(Machine Learning Function Orchestrator，机器学习功能编排器)的形式呈现，实现与应用实例及NSMF的交互。
应用实例以微服务的形式，嵌入在NWDAF(Network Data Analysis Function，网络数据分析功能网元)内，应用实例包括数据预处理模块，模型1和模型2，模型1是对未来2小时内的5G核心网切片业务流量及用户数进行预测，模型2是对预测的结果进行计算，分析是否需要扩容或缩容。
数据采集器嵌入在NSSMF和5G网络切片的网元中。
第一步，应用实例1(下面称实例1)在NWDAF中创建成功，并通知MLFO；MLFO激活人工智能实例1的管理条目，设置实例1的状态机为运行态；并且，每60秒发送保活报文以确认实例1的状态。
数据采集请求消息包括：实例1的IP地址(应用实例位置信息)、指定从NSSMF及5G网络切片1进行数据采集(目标网元)，采集的内容包括现有用户数、用户会话信息、每秒新建会话信息、用户流量信息、时间戳、节假日因 子等(数据采集需求)、数据采集周期为100ms。
第二步，MLFO发送上述数据采集请求消息到NSMF。
第三步，NSMF分析数据采集请求消息内容，并将实例1的IP地址、数据采集需求发送到所指定的NSSMF。
第四步，NSSMF继续将实例1的IP地址、数据采集需求发送到所指定的5G网络切片1。
第五步，NSSMF和5G网络切片1按照数据采集需求采集，包括用户数、用户会话信息、每秒新建会话信息、用户流量信息、时间戳、节假日因子。并将上述信息发送到应用实例1。
第六步，数据预处理模块对上述数据进行分类，并发送给模型1。
第七步，模型1预测未来2小时，新建用户及会话数将达到峰值；并将预测的值发送到模型2；模型2根据模型1预测的结果，分析在1.5小时后需要进行切片扩容。
第八步，模型2将相关的扩容决策发送给策略控制功能(Policy Control FuncTIon，PCF)，PCF将相应的网络管理策略发送到NSSMF去执行扩容计划。
场景2：人工智能应用于网络根因分析系统，通过模型推理，实现故障的精准定位和溯源。
图4是根据本发明实施例的基于场景2的示意图。如图4所示，应用实例1应用于频发告警分析，即如果一定时间内发生的特定告警和特定事件达到一定的数目，可以认为这些告警和事件之间存在一定的相关性。
应用实例2应用于上下层告警分析，即同专业网上下层业务故障影响体现为某一个根因告警导致了大面积的现象告警，需要快速获取导致故障的根因告警。
第一步，应用实例1(下面称实例1)和应用实例2(下面称实例2)在网络根因分析系统中中创建成功，并通知编排器；编排器激活人工智能实例1和实例2的管理条目，设置实例1和实例2的状态机为运行态；并且，每30秒发送保活报文以确认实例1和实例2的状态。
实例1的数据采集请求消息包括：实例1的IP地址(应用实例位置信息)、目标网元为告警采集平台，采集的内容包括所有设备告警信息(数据采集需求)、数据采集周期为触发上报。
实例2的数据采集请求消息包括：实例2的IP地址(应用实例位置信息)、 目标网元为告警采集平台，采集的内容包括所有网络业务告警信息(数据采集需求)、数据采集周期为触发上报。
第二步，编排器将上述两份数据采集请求消息发送到告警采集平台。
第三步，告警采集平台收到告警信息，发现是来自设备的告警，告警内容为“A网元B单板的温度过高”，于是将该条告警发送到应用实例1。
告警采集平台在2分钟内，收到100条同样的上述告警，告警采集平台将这些告警都发送到应用实例1。
第四步，应用实例1收到这些告警信息，数据预处理模块对这些告警信息进行过滤、筛选、匹配、分类等处理，随后发送到模型1。
第五步；模型1通过2分钟内收到100条同样的告警这样的情况做分析推理，认为有可能因为环境温度湿度不佳导致单板温度上升导致告警。
应用实例1合并这些告警，并将推理结果发送到根因告警汇总平台。
第六步，告警采集平台收到告警信息，发现是来自网络的告警，告警内容为“传送-多协议标记交换段层(T-Multiprotocol Label Switching Section，TMS)链接中断”、“B隧道链接中断”、“伪线C链接中断”、“D业务服务中断”、“E光纤信号丢失(Loss Of Signal，LOS)告警”，于是将这几条告警发送到应用实例2。
第七步，应用实例2收到这些告警信息，数据预处理模块对这些告警信息进行过滤、筛选、匹配、分类等处理，随后发送到模型2。
第八步，模型2通过这几条告警信息分析，得出这几条告警发生于同一原因，即“E光纤断纤，光纤所在端口报LOS告警”。
应用实例2将上述推理结果发送到根因告警汇总平台。
场景3：针对预选的数据特征集合进行数据筛选的功能。
在本实施例中，针对承载网智能化流量工程，提供了如下的表1进行理解。表1中数字代表着特征编号标识，即0-12，特征编号标识下的文字代表着特征类型。具体表格如下：
表1
Figure PCTCN2020077980-appb-000001
Figure PCTCN2020077980-appb-000002
编排器针对交互网络的网络流量工程特征，采集编号为0,1,2,3,8,9,10,11的八项数据采集功能。因此编排器将上述八项数据采集功能配置在数据特征集合中。
经由网络控制装置，目标网络节点接收到了数据特征集合后，针对0,1,2,3,8,9,10,11进行数据采集。
或者，目标网络节点根据自身所处的网络的网络流量工程特征，采集编号为0,1,2,3,8,9,10,11的八项数据采集功能，并进行数据采集。
实施例2
在本实施例中还提供了一种数据采集的请求的装置，该装置用于实现上述实施例及可选实施方式，已经进行过说明的不再赘述。如以下所使用的，术语“模块”可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。
图5是根据本发明实施例的一种数据的处理装置，如图5所示，该装置包括：
发送模块52，位于编排器中，用于生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括：网络控制装置，目标网络节点；采集模块54，位于所述目标网络节点，用于从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置；处理模块56，位于所述应用实例的处理装置，用于通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
上述各个模块是可以通过软件或硬件来实现的，对于后者，可以通过以下方式实现，但不限于此：上述模块均位于同一处理器中；或者，上述各个模块以任意组合的形式分别位于不同的处理器中。
实施例3
本发明的实施例还提供了一种存储介质，该存储介质中存储有计算机程序，其中，该计算机程序被设置为运行时执行上述任一项方法实施例中的步骤。
可选地，在本实施例中，上述存储介质可以被设置为存储用于执行以下步骤的计算机程序：
S1，在确定应用实例建立后，编排器生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括以下之一：网络控制装置，目标网络节点；S2，所述目标网络节点根据从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置；S3，所述应用实例的处理装置通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
可选地，在本实施例中，上述存储介质可以包括但不限于：通用串行总线盘(Universal Serial Bus盘，U盘)、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、移动硬盘、磁碟或者光盘等各种可以存储计算机程序的介质。
本发明的实施例还提供了一种电子装置，包括存储器和处理器，该存储器中存储有计算机程序，该处理器被设置为运行计算机程序以执行上述任一项方法实施例中的步骤。
可选地，上述电子装置还可以包括传输设备以及输入输出设备，其中，该传输设备和上述处理器连接，该输入输出设备和上述处理器连接。
可选地，在本实施例中，上述处理器可以被设置为通过计算机程序执行以下步骤：
S1，在确定应用实例建立后，编排器生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括以下之一：网络控制装置，目标网络节点；S2，所述目标网络节点根据从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置；S3，所述应用实例的处理装置通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
可选地，本实施例中的具体示例可以参考上述实施例及可选实施方式中所描述的示例，本实施例在此不再赘述。
上述的本申请的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，并且在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件结合。

Claims (13)

  1. 一种数据的处理方法，包括：
    在确定应用实例建立后，编排器生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括以下之一：网络控制装置、目标网络节点；
    所述目标网络节点根据从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置；
    所述应用实例的处理装置通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
  2. 根据权利要求1所述的方法，其中，所述数据采集请求消息包括：
    所述应用实例的位置信息、网络节点信息、数据采集内容。
  3. 根据权利要求2所述的方法，其中，在所述下一通信节点为网络控制装置的情况下，所述方法还包括：
    所述网络控制装置根据所述数据采集请求消息中的网络节点信息确定用于进行数据采集的目标网络节点；
    所述网络控制装置将所述数据采集请求消息发送至所述目标网络节点。
  4. 根据权利要求3所述的方法，还包括：
    所述网络控制装置接收所述应用实例的处理装置输出的所述处理结果；
    所述网络控制装置根据所述处理结果对网络进行配置。
  5. 根据权利要求2所述的方法，其中，所述目标网络节点根据从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，包括：
    所述目标网络节点根据所述应用实例的位置信息，确定需要进行数据采集的应用实例；
    所述目标网络节点采集所述应用实例对应的数据。
  6. 根据权利要求5所述的方法，其中，所述目标网络节点采集所述应用实例对应的数据，包括：
    所述目标网络节点根据数据特征集合对所述数据采集内容进行筛选；
    所述目标网络节点对筛选后的所述数据采集内容进行数据采集。
  7. 根据权利要求6所述的方法，其中，所述数据特征集合通过如下方式确定：
    所述编码器根据所述应用实例的网络需求确定所述数据特征集合，并发送至所述下一通信节点；或，
    在接收到所述数据采集请求消息后，所述目标网络节点分析所述应用实例的位置信息对应的应用实例的网络需求，并确定所述数据特征集合。
  8. 根据权利要求7所述的方法，其中，所述数据特征集合包括：
    所述目标网络节点所在网络的网络信息；
    所述目标网络节点的用户信息；
    所述目标网络节点所在设备的设备信息；
    所述目标网络节点的数据报文信息。
  9. 根据权利要求6-8任一项所述的方法，其中，所述数据采集内容包括以下之一：用户数量和类型、用户会话信息、用户流量信息、数据采集周期、网络业务告警信息。
  10. 根据权利要求1所述的方法，其中，所述应用实例的处理装置通过所述应用实例中的模型对所述数据采集结果进行处理，包括：
    所述处理装置根据所述数据采集结果的类型进行分类，并将分类后的数据采集结果配置在对应的模型当中；
    所述处理装置在所述模型中对分类后的数据采集结果进行处理，其中，处理方式包括：对数据进行预测、对数据进行推理。
  11. 一种数据的处理装置，包括：
    发送模块，位于编排器中，设置为在确定应用实例建立后，生成所述应用实例对应的数据采集请求消息，并发送至下一通信节点，其中，所述下一通信节点包括以下之一：网络控制装置、目标网络节点；
    采集模块，位于所述目标网络节点，设置为从所述编排器或经由所述网络控制装置接收的数据采集请求消息进行数据采集，并将数据采集结果发送至所述应用实例的处理装置；
    处理模块，位于所述应用实例的处理装置，设置为通过所述应用实例中的模型对所述数据采集结果进行处理，并输出处理结果。
  12. 一种存储介质，存储有计算机程序，其中，所述计算机程序被设置为运行时执行所述权利要求1-10任一项中所述的数据的处理方法。
  13. 一种电子装置，包括存储器和处理器，其中，所述存储器中存储有计算机程序，所述处理器被设置为运行所述计算机程序以执行所述权利要求1-10 任一项中所述的数据的处理方法。
PCT/CN2020/077980 2019-04-15 2020-03-05 数据的处理方法、装置、存储介质及电子装置 WO2020211561A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US17/435,747 US12074767B2 (en) 2019-04-15 2020-03-05 Data processing method and device for cooperating with an artificial intelligence management plane, electronic device, and storage medium
EP20791480.5A EP3958508A4 (en) 2019-04-15 2020-03-05 DATA PROCESSING METHOD AND DEVICE, STORAGE MEDIA AND ELECTRONIC DEVICE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910300209.2A CN111082960B9 (zh) 2019-04-15 2019-04-15 数据的处理方法及装置
CN201910300209.2 2019-04-15

Publications (1)

Publication Number Publication Date
WO2020211561A1 true WO2020211561A1 (zh) 2020-10-22

Family

ID=70310287

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/077980 WO2020211561A1 (zh) 2019-04-15 2020-03-05 数据的处理方法、装置、存储介质及电子装置

Country Status (4)

Country Link
US (1) US12074767B2 (zh)
EP (1) EP3958508A4 (zh)
CN (1) CN111082960B9 (zh)
WO (1) WO2020211561A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114697219A (zh) * 2022-03-24 2022-07-01 阿里巴巴（中国）有限公司 网络控制方法、直播网络的控制方法、设备及系统
CN116567674A (zh) * 2023-07-07 2023-08-08 中国电信股份有限公司 数据处理方法、装置、网元和可读存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115004755A (zh) * 2020-10-13 2022-09-02 中兴通讯股份有限公司 无线多载波配置和选择
CN115242630B (zh) * 2021-04-23 2023-10-27 中国移动通信集团四川有限公司 一种5g网络切片的编排方法、装置及电子设备
WO2023039905A1 (zh) * 2021-09-18 2023-03-23 Oppo广东移动通信有限公司 Ai数据的传输方法、装置、设备及存储介质
CN114338421B (zh) * 2021-12-29 2024-03-26 中国电信股份有限公司 数据采集优化方法、装置、存储介质及电子设备
CN115361308B (zh) * 2022-08-19 2024-06-25 一汽解放汽车有限公司 一种工控网络数据风险确定方法、装置、设备及存储介质
CN118350058B (zh) * 2024-06-20 2024-08-27 江西省送变电工程有限公司 一种电力物资数据管理方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106533724A (zh) * 2015-09-11 2017-03-22 中国移动通信集团公司 监控和优化网络功能虚拟化nfv网络的方法、装置及系统
WO2018203780A1 (en) * 2017-05-05 2018-11-08 Telefonaktiebolaget Lm Ericsson (Publ) Manager node and method performed therein for handling one or more network functions in a communication network
US20180324207A1 (en) * 2017-05-05 2018-11-08 Servicenow, Inc. Network security threat intelligence sharing

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103684851B (zh) * 2013-11-26 2017-03-08 华为技术有限公司 数据采集方法和装置
CN105284094B (zh) * 2014-05-15 2019-05-28 华为技术有限公司 一种网络功能虚拟化网络系统、数据处理方法及装置
CA2974501C (en) * 2015-01-20 2019-09-10 Huawei Technologies Co., Ltd. Method and apparatus for nfv management and orchestration
WO2017188387A1 (ja) * 2016-04-28 2017-11-02 日本電気株式会社 ネットワーク機能仮想化管理オーケストレーション装置と方法とプログラム
US10924943B2 (en) * 2017-01-05 2021-02-16 Apple Inc. Instantiation and management of physical and virtualized network functions of a radio access network node
CN108809671B (zh) * 2017-04-26 2020-10-09 华为技术有限公司 通信方法、网络设备和系统
US20180317134A1 (en) * 2017-04-28 2018-11-01 Huawei Technologies Co., Ltd. Nssmf nsmf interaction connecting virtual 5g networks and subnets
CN109391504B (zh) * 2017-08-11 2022-04-29 华为技术有限公司 网络切片的部署方法和装置
US20190236485A1 (en) * 2018-01-26 2019-08-01 Cisco Technology, Inc. Orchestration system for distributed machine learning engines
US10892958B2 (en) * 2018-08-03 2021-01-12 Huawei Technologies Co., Ltd. Methods and functions of network performance monitoring and service assurance
EP4380232A3 (en) * 2018-09-17 2024-08-21 Huawei Technologies Co., Ltd. Device and method for providing a quality of service function
CN109120459B (zh) * 2018-09-27 2019-09-20 中国联合网络通信有限公司广东省分公司 一种基于业务编排器的城域网业务处理方法
EP3857818B1 (en) * 2018-09-28 2024-03-06 Nokia Technologies Oy Radio-network self-optimization based on data from radio network and spatiotemporal sensors
US11140048B2 (en) * 2019-01-11 2021-10-05 Huawei Technologies Co., Ltd. Sharable storage method and system for network data analytics
EP3925160A1 (en) * 2019-02-18 2021-12-22 Huawei Technologies Co., Ltd. Entities and methods for automatic configuration and selection of analytics network function instances in 5g networks
US11405931B2 (en) * 2019-12-12 2022-08-02 Oracle International Corporation Methods, systems, and computer readable media for providing for network slice management using feedback mechanism

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106533724A (zh) * 2015-09-11 2017-03-22 中国移动通信集团公司 监控和优化网络功能虚拟化nfv网络的方法、装置及系统
WO2018203780A1 (en) * 2017-05-05 2018-11-08 Telefonaktiebolaget Lm Ericsson (Publ) Manager node and method performed therein for handling one or more network functions in a communication network
US20180324207A1 (en) * 2017-05-05 2018-11-08 Servicenow, Inc. Network security threat intelligence sharing

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3958508A4

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114697219A (zh) * 2022-03-24 2022-07-01 阿里巴巴（中国）有限公司 网络控制方法、直播网络的控制方法、设备及系统
CN114697219B (zh) * 2022-03-24 2024-03-08 阿里巴巴（中国）有限公司 网络控制方法、直播网络的控制方法、设备及系统
CN116567674A (zh) * 2023-07-07 2023-08-08 中国电信股份有限公司 数据处理方法、装置、网元和可读存储介质
CN116567674B (zh) * 2023-07-07 2023-10-03 中国电信股份有限公司 数据处理方法、装置、网元和可读存储介质

Also Published As

Publication number Publication date
US20220052923A1 (en) 2022-02-17
CN111082960B (zh) 2022-12-06
CN111082960B9 (zh) 2023-01-24
EP3958508A1 (en) 2022-02-23
EP3958508A4 (en) 2023-01-18
CN111082960A (zh) 2020-04-28
US12074767B2 (en) 2024-08-27

Similar Documents

Publication Publication Date Title
WO2020211561A1 (zh) 数据的处理方法、装置、存储介质及电子装置
US12038976B2 (en) Model pushing method and device, model requesting method and device, storage medium and electronic device
EP3477894B1 (en) Method and device for controlling virtualized broadband remote access server (vbras), and communication system
CN111818159A (zh) 数据处理节点的管理方法、装置、设备及存储介质
CN112769605B (zh) 一种异构多云的运维管理方法及混合云平台
CN108616912A (zh) 一种网络质量优化方法及装置
CN107204894A (zh) 网络业务质量的监控方法及装置
CN112631725A (zh) 一种基于云边端协同的智慧城市的管理系统及方法
CN117581239A (zh) 用于人工智能定义网络的系统和方法
CN112291075B (zh) 网络故障定位方法、装置、计算机设备及存储介质
CN114091610A (zh) 智能决策方法及装置
CN114706675A (zh) 基于云边协同系统的任务部署方法及装置
Solmaz et al. ALACA: A platform for dynamic alarm collection and alert notification in network management systems
Li et al. Layered fault management scheme for end-to-end transmission in internet of things
CN113448947B (zh) 一种mongo数据库分布式部署运维的方法和装置
CN112671586B (zh) 一种业务配置自动迁移和保障方法及装置
CN110390027A (zh) 一种基于图数据库的信息系统故障模型构建方法及系统
JP2006025434A (ja) 大容量障害相関システム及び方法
CN115037625B (zh) 网络切片处理方法、装置、电子设备及可读存储介质
Jamil et al. Workload Orchestration in Multi-Access Edge Computing Using Belief Rule-Based Approach
CN115705259A (zh) 故障处理方法、相关设备及存储介质
CN114792045A (zh) 一种边缘计算的数字孪生方法和系统
CN114448868A (zh) 一种基于分段路由策略的路径调度方法、装置及设备
Kiran et al. Hecate: Ai-driven wan traffic engineering for science
Santos et al. Using reinforcement learning to allocate and manage SFC in cellular networks

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20791480

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020791480

Country of ref document: EP

Effective date: 20211115