WO2024012203A1 - 用户数据存储容灾方法、装置、电子设备和存储介质 - Google Patents

用户数据存储容灾方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2024012203A1
WO2024012203A1 PCT/CN2023/103332 CN2023103332W WO2024012203A1 WO 2024012203 A1 WO2024012203 A1 WO 2024012203A1 CN 2023103332 W CN2023103332 W CN 2023103332W WO 2024012203 A1 WO2024012203 A1 WO 2024012203A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
user data
data
disaster recovery
cluster
Prior art date
Application number
PCT/CN2023/103332
Other languages
English (en)
French (fr)
Inventor
林昊
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
Publication of WO2024012203A1 publication Critical patent/WO2024012203A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/04Arrangements for maintaining operational condition
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W8/00Network data management
    • H04W8/18Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data

Definitions

  • the present disclosure relates to the field of mobile communication technology, and in particular, to a user data storage disaster recovery method, device, electronic equipment and storage medium.
  • 5G mobile communication technology has been widely used in the industrial Internet.
  • a disaster recovery core network commonly referred to as a small network
  • the campus disaster recovery core network can take over the business, protect the security of the industrial Internet network, and improve the business experience of 2B industry users.
  • Embodiments of the present disclosure provide a user data storage disaster recovery method, device, electronic device, and storage medium.
  • a user data storage disaster recovery method is provided, which is applied to UDM (Unified Data Management) network elements, including: obtaining the characteristic value of user data; and performing operations on the user data according to the characteristic value.
  • Clustering determines the cluster to which the user data belongs.
  • a user data storage disaster recovery device which is applied to UDM network elements.
  • the device includes: a data mining module configured to obtain characteristic values of user data; and a classification module configured to The user data is clustered according to the characteristic values to determine the cluster to which the user data belongs.
  • an electronic device including: a processor and a memory used to store a computer program that can be run on the processor; wherein when the processor is used to run the computer program, the above-mentioned user is executed.
  • Disaster recovery method for household data storage including: a processor and a memory used to store a computer program that can be run on the processor; wherein when the processor is used to run the computer program, the above-mentioned user is executed.
  • a storage medium is also provided.
  • a computer program is stored in the storage medium.
  • the computer program is executed by a processor, the above-mentioned user data storage disaster recovery method is implemented.
  • Figure 1 is a schematic flowchart of a user data storage disaster recovery method according to an embodiment of the present disclosure
  • Figure 2 is a schematic diagram of the new user clustering process according to an embodiment of the present disclosure
  • Figure 3 is a schematic flowchart of a scenario for enabling ToB service intelligent operation and maintenance on a UDM network element in a large network according to an embodiment of the present disclosure
  • Figure 4 is a schematic flow chart of a user's new account opening scenario according to an embodiment of the present disclosure
  • Figure 5 is a schematic flow chart of a scenario where new users access 5G through AMF according to an embodiment of the present disclosure
  • Figure 6 is a schematic structural diagram of a user data storage disaster recovery device according to an embodiment of the present disclosure.
  • Figure 7 is an internal structure diagram of a computer device according to an embodiment of the present disclosure.
  • the embodiment of the present disclosure provides a user data storage disaster recovery method, which is applied to UDM network elements.
  • the method includes: Step 101: Obtain the characteristic value of the user data; and Step 102: Based on the characteristic value of the user
  • the data is clustered to determine the cluster to which the user data belongs.
  • This embodiment can be applied to the storage and disaster recovery process of UDM user data in the core network ToB scenario. Furthermore, it can be applied to the intelligent operation and maintenance of user data synchronization between commercial network UDM equipment and disaster recovery park UDM equipment under the industrial Internet.
  • obtaining the characteristic value of the user data includes using the 5G user location information to query and locate the user's home base station information, the user's contract data information stored in UDM, etc.
  • This embodiment obtains user data feature values from the large network UDM network elements, introduces the feature values into machine learning, and performs cluster analysis on the data in the large network UDM user database, so that user data in the same cluster is gathered, thereby automatically forming Data classification completes the mapping of user data from large networks to small networks to avoid manual operation and maintenance.
  • the campus characteristics in user cluster 1 are: the home base station of characteristic 1 user is A, the account opening operator of characteristic 2 is campus operator 1, and characteristic 3 all start with 4600010000.
  • the campus characteristics in user cluster 2 are: the home base station of characteristic 1 user is B, the account opening operator of characteristic 2 is campus operator 1, and characteristic 3 all start with 4600020000.
  • the characteristic value is introduced into machine learning, and cluster analysis is performed on the data in the UDM user database of the large network. It is learned that the similarity between the new user and user cluster 1 is greater than 80 %, the similarity between the new user and user cluster 2 is 0.5%, so the new user can be assigned to user cluster 2.
  • obtaining the characteristic value of user data includes: when the user is an active user, obtaining the cell location information of the active user from the AMF network element through the providing positioning information (Namf_Location_ProvidePositioningInfo) interface, and using the cell location information as an active user. Characteristic values of the user.
  • the subscription data information includes the user's account opening time, account opening operator, IMSI, MSIDN, user's access and mobility data, and session management. Contract data; and use the contract data information as the user's characteristic value.
  • the process includes steps S301 to S305 as follows.
  • Step S301 UDM activation of the large network enables ToB business intelligent operation and maintenance related functions.
  • Step S302 The data mining related module of Dawang UDM traverses all users stored in UDM. For active users, through the Namf_Location_ProvidePositioningInfo interface defined in the 3GPP protocol specification, the active user's active cell location information is periodically collected from the AMF to which the user belongs, as the user's characteristic value.
  • Step S303 The data mining related module of Dawang UDM traverses all users stored in UDM. Query the user account opening time, account opening operator, IMSI/MSIDN, user access and mobility data (AM data), session management subscription data (SM data), etc. stored in the UDM database as user characteristic values.
  • Step S304 The data mining module of Dawang UDM uses an unsupervised learning algorithm to cluster user data based on the collected user characteristic data.
  • Step S305 Store the clustering results in the UDM database for subsequent use.
  • obtaining the characteristic value of user data includes: when the user is a new account user, query the user's subscription data information in the UDM database.
  • the subscription data information includes the user's account opening time, account opening operator, IMSI, MSIDN, user access and mobility data, and session management subscription data; the proposal uses subscription data information as user characteristic values.
  • the process includes steps S401 to S404 as follows.
  • Step S401 Dawang UDM receives the account opening instruction and completes the account opening operation.
  • Step S402 For new account opening users, the data mining related module of the large network UDM queries the user account opening time, account opening operator, IMSI/MSIDN, user access and mobility data (AM data), and session management contract stored in the UDM database Data (SM data), etc. are used as user characteristic values.
  • the data mining related module of the large network UDM queries the user account opening time, account opening operator, IMSI/MSIDN, user access and mobility data (AM data), and session management contract stored in the UDM database Data (SM data), etc. are used as user characteristic values.
  • Step S403 The data mining module of Dawang UDM uses an unsupervised learning algorithm to calculate similarity based on the collected user characteristic data and the already formed data clusters. Select the cluster with the largest similarity and add this user to it; if the maximum similarity is still less than the threshold, a new data cluster is formed.
  • Step S404 Store the clustering results in the UDM database for subsequent use.
  • obtaining the characteristic value of user data includes: when the user is a new user accessed through the AMF network element, When the user is registered, the cell location information of the active user is obtained from the AMF network element through the Namf_Location_ProvidePositioningInfo interface, and the cell location information is used as the characteristic value of the active user.
  • the process includes steps S501 to S504 as follows.
  • Step S501 After the user terminal accesses the 5G network, the large network UDM receives the Nudm_UECM_Registration message defined in the 3GPP specification sent by the AMF. The UDM completes the registration operation for the user, and at the same time, the UDM marks the user as an active user.
  • Step S502 UDM's data mining related module uses the Namf_Location_ProvidePositioningInfo interface defined in the 3GPP protocol specification to periodically collect the location information of relevant active users' active cells from the AMF to which the user belongs as a characteristic value of the user.
  • Step S503 The data mining module of UDM uses an unsupervised learning algorithm to calculate similarity based on the collected user characteristic data and the already formed data clusters. Select the cluster with the largest similarity and add this user to it; if the maximum similarity is still less than the threshold, a new data cluster is formed.
  • Step S504 Store the clustering results in the UDM database for subsequent use.
  • clustering the user data according to the characteristic values and determining the cluster to which the user data belongs includes: clustering the user data according to the characteristic values using an unsupervised learning algorithm to determine the cluster to which the user data belongs.
  • a machine learning method can be used to independently learn and classify and aggregate the user data in the large network UDM database, thereby clustering the user data and determining the cluster to which the user data belongs.
  • Unsupervised learning algorithms can be used.
  • the unsupervised learning algorithm may include K-means clustering algorithm, sliding window-based clustering algorithm, DBSCAN clustering algorithm, maximum expectation clustering based on Gaussian mixture model, etc.
  • the clustering machine learning algorithm may not be used to perform cluster analysis. Taking advantage of the fact that users in the ToB industry generally do not move, only based on the user's location information query, the user's base station cell data is obtained at a fixed point, and then the user's belonging to the campus is determined. Cluster user data based on the campus to which the user belongs.
  • the method further includes: synchronizing the clustering results of the user data in the current UDM network element to the corresponding disaster recovery core network UDM network element.
  • the method of this embodiment can achieve the effect of automatically maintaining the relationship between ToB industry users and the home campus without manually configuring number segment mapping rules. This in turn reduces labor costs and improves user experience for operator operation and maintenance staff.
  • the user data storage disaster recovery method obtained by the embodiment of the present disclosure obtains the characteristic values of the user data; clusters the user data according to the characteristic values to determine the cluster to which the user data belongs.
  • the solution provided by this disclosure can be used to perform cluster analysis on the data in the UDM user database of the large network, so that user data in the same cluster can be gathered, thereby automatically forming data classification, completing the mapping of large network user data to small networks, and avoiding manual operation and maintenance. .
  • the embodiment of the present disclosure also provides a user data storage disaster recovery device.
  • the user data storage disaster recovery device 600 includes: a data mining module 601 and a classification module 602. data
  • the mining module 601 is configured to obtain feature values of user data
  • the classification module 602 is configured to cluster user data according to the feature values and determine the cluster to which the user data belongs.
  • the data mining module 601 and the classification module 602 can be implemented by the processor in the user data storage disaster recovery device.
  • the embodiment of the present disclosure also provides a computer program product.
  • the computer program product includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.
  • the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the above method.
  • the embodiment of the present disclosure also provides an electronic device (computer device).
  • the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 7 .
  • the computer equipment includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus.
  • the processor A01 of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes internal memory A03 and non-volatile storage medium A06.
  • the non-volatile storage medium A06 stores an operating system B01 and a computer program B02.
  • the internal memory A03 provides an environment for the execution of the operating system B01 and the computer program B02 in the non-volatile storage medium A06.
  • the network interface A02 of the computer device is used to communicate with external terminals through a network connection.
  • the computer program is executed by the processor A01, the method of any one of the above embodiments is implemented.
  • the display screen A04 of the computer device may be a liquid crystal display or an electronic ink display.
  • the input device A05 of the computer device may be a touch layer covered on the display screen, or may be a button, trackball or touch screen provided on the shell of the computer device.
  • a control panel can also be an external keyboard, trackpad, or mouse.
  • FIG. 7 is only a block diagram of a partial structure related to the disclosed solution, and does not constitute a limitation on the computer equipment to which the disclosed solution is applied.
  • the computer device may include: The figures show more or fewer parts, or certain parts combined, or with different arrangements of parts.
  • the device provided by the embodiments of the present disclosure includes a processor, a memory, and a program stored in the memory and executable on the processor.
  • the processor executes the program, the method of any of the above embodiments is implemented.
  • embodiments of the present disclosure may be provided as methods, systems, or computer program products. Accordingly, the present disclosure may employ an entirely hardware embodiment, an entirely software embodiment, or an implementation combining software and hardware aspects. Example form. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the instructions
  • the device implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device.
  • Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • Memory may include non-volatile memory in computer-readable media, random access memory (RAM), and/or non-volatile memory in the form of read-only memory (ROM) or flash memory (flashRAM). Memory is an example of a computer-readable medium.
  • RAM random access memory
  • ROM read-only memory
  • flashRAM flash memory
  • Computer-readable media includes both persistent and non-volatile, removable and non-removable media that can be implemented by any method or technology for storage of information.
  • Information may be computer-readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), and read-only memory.
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • read-only memory read-only memory
  • ROM read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash memory or other memory technology
  • compact disc read-only memory CD-ROM
  • DVD digital versatile disc
  • Magnetic tape cassettes tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium can be used to store information that can be accessed by a computing device.
  • computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • the memory in the embodiment of the present disclosure may be a volatile memory or a non-volatile memory, or may include Includes both volatile and non-volatile memory.
  • the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), an erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only Memory).
  • the magnetic surface memory can be a magnetic disk memory or a magnetic tape memory.
  • the volatile memory may be random access memory (RAM), which is used as an external cache.
  • RAM Random Access Memory
  • SRAM Static Random Access Memory
  • SSRAM Synchronous Static Random Access Memory
  • DRAM Dynamic Random Access Memory
  • SDRAM Synchronous Dynamic Random Access Memory
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced Enhanced Synchronous Dynamic Random Access Memory
  • SLDRAM SyncLink Dynamic Random Access Memory
  • DRRAM Direct Rambus Random Access Memory
  • Embodiments of the present disclosure provide user data storage disaster recovery methods, devices, electronic devices, and storage media.
  • the method includes: obtaining characteristic values of user data; clustering user data according to the characteristic values to determine the cluster to which the user data belongs.
  • the solution provided by this disclosure can be used to perform cluster analysis on the data in the UDM user database of the large network, so that user data in the same cluster can be gathered, thereby automatically forming data classification, completing the mapping of large network user data to small networks, and avoiding manual operation and maintenance. .

Abstract

公开了一种用户数据存储容灾方法、装置、电子设备和存储介质。该方法包括获取用户数据的特征值;以及根据特征值对用户数据进行聚类,确定用户数据归属的簇集。

Description

用户数据存储容灾方法、装置、电子设备和存储介质
相关申请的交叉引用
本公开要求享有2022年07月11日提交的名称为“用户数据存储容灾方法、装置、电子设备和存储介质”的中国专利申请CN202210817918.X的优先权,其全部内容通过引用并入本公开中。
技术领域
本公开涉及移动通信技术领域,尤其涉及一种用户数据存储容灾方法、装置、电子设备和存储介质。
背景技术
随着现代通信技术的发展,5G移动通信技术已经广泛应用于工业互联网。为了实现网络的低延时访问和容灾可靠性等要求,各大运营商都选择在各个工业园区部署一套容灾核心网(一般称作小网)。当商用网络(一般称作大网)出现故障时,园区容灾核心网可以接管业务,保护工业互联网网络安全,提升2B行业用户的业务体验。
目前,各大运营商都发布了自己的企业标准,规定用户签约数据在大小网之间的同步方式。但是相关的企业规范和典型的技术实现中,大网用户数据是按照人工配置号段映射规则,映射到对应的园区小网。每增加一个ToB业务,就需要规划号段配置,而人工号段配置维护管理一直是运营商运维的痛点和难点。随着ToB业务的发展,ToB行业用户的增多,传统的人工运维方式难度会越来越大。
发明内容
本公开实施例提供了一种用户数据存储容灾方法、装置、电子设备和存储介质。
根据本公开的一个方面,提供了一种用户数据存储容灾方法,应用于UDM(Unified Data Management)网元,包括:获取用户数据的特征值;以及根据所述特征值对所述用户数据进行聚类,确定所述用户数据归属的簇集。
根据本公开的一个方面,还提供了一种用户数据存储容灾装置,应用于UDM网元,该装置包括:数据挖掘模块,被配置为获取用户数据的特征值;以及分类模块,被配置为根据所述特征值对所述用户数据进行聚类,确定所述用户数据归属的簇集。
根据本公开的一个方面,还提供了一种电子设备,包括:处理器和用于存储能够在处理器上运行的计算机程序的存储器;其中,处理器用于运行计算机程序时,执行上述的用 户数据存储容灾方法。
根据本公开的一个方面,还提供了一种存储介质,存储介质中存储有计算机程序,计算机程序被处理器执行时,实现上述的用户数据存储容灾方法。
附图说明
图1为本公开实施例用户数据存储容灾方法的流程示意图;
图2为本公开实施例新用户簇集聚类过程示意图;
图3为本公开实施例大网UDM网元开启ToB业务智能运维场景流程示意图;
图4为本公开实施例用户新开户场景流程示意图;
图5为本公开实施例新用户通过AMF接入5G场景流程示意图;
图6为本公开实施例用户数据存储容灾装置的结构示意图;以及
图7为本公开实施例计算机设备的内部结构图。
具体实施方式
下面将结合附图及实施例对本公开作进一步详细的描述。
本公开实施例提供了一种用户数据存储容灾方法,应用于UDM网元,如图1所示,该方法包括:步骤101:获取用户数据的特征值;以及步骤102:根据特征值对用户数据进行聚类,确定用户数据归属的簇集。
本实施例可应用于核心网ToB场景下UDM用户数据的存储容灾过程。进一步地,可应用于工业互联网下,商用网络UDM设备和容灾园区UDM设备用户数据同步的智能运维。
本实施例中,获取用户数据的特征值,包括利用5G用户位置信息查询定位用户归属基站信息、用户在UDM存储的签约数据信息等。
本实施例通过从大网UDM网元中获取用户数据特征值,将特征值引入机器学习中,对大网UDM用户数据库中的数据进行聚类分析,使得同一簇的用户数据聚集,从而自动形成数据分类,完成大网用户数据到小网的映射,避免人工运维。
例如,参见图2,核心网中存在两个用户簇集:用户簇集1和用户簇集2。其中,用户簇集1中的园区特征为:特征1用户归属基站为A、特征2用户开户操作员为园区操作员1、特征3都是4600010000开头。用户簇集2中的园区特征为:特征1用户归属基站为B、特征2用户开户操作员为园区操作员1、特征3都是4600020000开头。当有新的用户时,通过获取用户数据特征值,将特征值引入机器学习中,对大网UDM用户数据库中的数据进行聚类分析,获知新的用户与用户簇集1的相似度大于80%,新的用户与用户簇集2的相似度为0.5%,因此可将新的用户归属于用户簇集2。
在一些实施例中,获取用户数据的特征值,包括:当用户为活动用户时,通过提供定位信息(Namf_Location_ProvidePositioningInfo)接口,从AMF网元中获取活动用户的小区位置信息,将小区位置信息作为活动用户的特征值。
进一步地,当用户为UDM存储的用户时,查询UDM数据库中用户的签约数据信息,签约数据信息包括用户开户时间、开户操作员、IMSI、MSIDN、用户的接入和移动性数据、和会话管理签约数据;以及将签约数据信息作为用户的特征值。
参见图3,在大网UDM开启ToB业务智能运维功能的场景中,过程如下包括步骤S301至步骤S305。
步骤S301:大网UDM开通开启了ToB业务智能运维相关功能。
步骤S302:大网UDM的数据挖掘相关模块遍历UDM存储的所有用户。针对活动用户,通过3GPP协议规范中定义的Namf_Location_ProvidePositioningInfo接口,到用户归属的AMF周期采集相关活动用户活动小区位置信息,作为用户的特征值。
步骤S303:大网UDM的数据挖掘相关模块遍历UDM存储的所有用户。查询UDM数据库中存储的用户开户时间,开户操作员,IMSI/MSIDN,用户的接入和移动性数据(AM data)、会话管理签约数据(SM data)等作为用户的特征值。
步骤S304:大网UDM的数据挖掘模块,根据采集到的用户特征数据,利用非监督学习算法,对用户数据进行聚类。
步骤S305:将聚类结果存储在UDM数据库中,供后续使用。
在一些实施例中,获取用户数据的特征值,包括:当用户为新开户用户时,查询UDM数据库中用户的签约数据信息,签约数据信息包括用户开户时间、开户操作员、IMSI、MSIDN、用户的接入和移动性数据、和会话管理签约数据;意见将签约数据信息作为用户的特征值。
参见图4,在用户新开户场景中,过程如下包括步骤S401至步骤S404。
步骤S401:大网UDM收到开户指令,完成开户操作。
步骤S402:大网UDM的数据挖掘相关模块针对新开户用户,查询UDM数据库中存储的用户开户时间,开户操作员,IMSI/MSIDN,用户的接入和移动性数据(AM data)、会话管理签约数据(SM data)等作为用户的特征值。
步骤S403:大网UDM的数据挖掘模块,根据采集到的用户特征数据,利用非监督学习算法,和已经形成的数据聚类进行相似度计算。选择相似度最大的聚类,并将此用户加入其中;如果最大的相似度依然小于阈值,则形成新的数据聚集。
步骤S404:将聚类结果存储在UDM数据库中,供后续使用。
在一些实施例中,获取用户数据的特征值,包括:当用户为通过AMF网元接入的新用 户时,通过Namf_Location_ProvidePositioningInfo接口,从AMF网元中获取活动用户的小区位置信息,将小区位置信息作为活动用户的特征值。
参见图5,在用户通过AMF接入5G的场景中,过程如下包括步骤S501至步骤S504。
步骤S501:用户终端接入5G网络后,大网UDM收到AMF发来的3GPP规范定义的Nudm_UECM_Registration消息,UDM对此用户完成注册操作,同时UDM并将此用户标记为活动用户。
步骤S502:UDM的数据挖掘相关模块,通过3GPP协议规范中定义的Namf_Location_ProvidePositioningInfo接口,到用户归属的AMF周期采集相关活动用户活动小区位置信息,作为用户的特征值。
步骤S503网UDM的数据挖掘模块,根据采集到的用户特征数据,利用非监督学习算法,和已经形成的数据聚类进行相似度计算。选择相似度最大的聚类,并将此用户加入其中;如果最大的相似度依然小于阈值,则形成新的数据聚集。
步骤S504:将聚类结果存储在UDM数据库中,供后续使用。
在一些实施例中,根据特征值对用户数据进行聚类,确定用户数据归属的簇集,包括:根据特征值利用非监督学习算法对用户数据进行聚类,确定用户数据归属的簇集。
本实施例中,可采用机器学习方法,对大网UDM数据库中的用户数据进行自主学习和分类聚集,从而对用户数据实现聚类,确定用户数据归属的簇集。可采用非监督学习算法。这里,非监督学习算法可包括K均值聚类算法、基于滑动窗口的聚类算法、DBSCAN聚类算法、基于高斯混合模型的最大期望聚类等。
当然,本实施例中,也可以不使用聚类机器学习算法进行聚类分析。利用ToB行业用户一般不移动的特性,仅根据用户的位置信息查询,定点获取用户的所在基站小区数据,进而判断用户归属园区。基于用户归属园区对用户数据进行聚类。
在一些实施例中,确定用户数据归属的簇集之后,该方法还包括:将当前UDM网元中用户数据的聚类结果,同步到对应的容灾核心网UDM网元中。
本实施例方法无需通过人工配置号段映射规则,就可以做到自动维护ToB行业用户和归属园区的关系的效果。进而减少人力成本,提高运营商运维工作人员的用户体验。
本公开实施例提供的用户数据存储容灾方法,获取用户数据的特征值;根据特征值对用户数据进行聚类,确定用户数据归属的簇集。采用本公开提供的方案能对大网UDM用户数据库中的数据进行聚类分析,使得同一簇的用户数据聚集,从而自动形成数据分类,完成大网用户数据到小网的映射,避免人工运维。
为了实现本公开实施例的方法,本公开实施例还提供了一种用户数据存储容灾装置,如图6所示,用户数据存储容灾装置600包括:数据挖掘模块601和分类模块602。数据 挖掘模块601,被配置为获取用户数据的特征值;分类模块602,被配置为根据特征值对用户数据进行聚类,确定用户数据归属的簇集。
实际应用时,数据挖掘模块601和分类模块602可由用户数据存储容灾装置中的处理器实现。
需要说明的是:上述实施例提供的上述装置在执行时,仅以上述各程序模块的划分进行举例说明,实际应用时,可以根据需要而将上述处理分配由不同的程序模块完成,即将终端的内部结构划分成不同的程序模块,以完成以上描述的全部或者部分处理。另外,上述实施例提供的上述装置与上述方法实施例属于同一构思,其实现过程详见方法实施例,这里不再赘述。
为了实现本公开实施例的方法,本公开实施例还提供了一种计算机程序产品,计算机程序产品包括计算机指令,计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取计算机指令,处理器执行计算机指令,使得计算机设备执行上述方法。
基于上述程序模块的硬件实现,且为了实现本公开实施例的方法,本公开实施例还提供了一种电子设备(计算机设备)。在实施例中,该计算机设备可以是终端,其内部结构图可以如图7所示。该计算机设备包括通过系统总线连接的处理器A01、网络接口A02、显示屏A04、输入装置A05和存储器(图中未示出)。其中,该计算机设备的处理器A01用于提供计算和控制能力。该计算机设备的存储器包括内存储器A03和非易失性存储介质A06。该非易失性存储介质A06存储有操作系统B01和计算机程序B02。该内存储器A03为非易失性存储介质A06中的操作系统B01和计算机程序B02的运行提供环境。该计算机设备的网络接口A02用于与外部的终端通过网络连接通信。该计算机程序被处理器A01执行时以实现上述任意一项实施例的方法。该计算机设备的显示屏A04可以是液晶显示屏或者电子墨水显示屏,该计算机设备的输入装置A05可以是显示屏上覆盖的触摸层,也可以是计算机设备外壳上设置的按键、轨迹球或触控板,还可以是外接的键盘、触控板或鼠标等。
本领域技术人员可以理解,图7中示出的结构,仅仅是与本公开方案相关的部分结构的框图,并不构成对本公开方案所应用于其上的计算机设备的限定,计算机设备可以包括比图中所示更多或更少的部件,或者组合某些部件,或者具有不同的部件布置。
本公开实施例提供的设备,设备包括处理器、存储器及存储在存储器上并可在处理器上运行的程序,处理器执行程序时实现上述任意一项实施例的方法。
本领域内的技术人员应明白,本公开的实施例可提供为方法、系统、或计算机程序产品。因此,本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实 施例的形式。而且,本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开是参照根据本公开实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器,使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中,使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品,该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上,使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理,从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中,计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flashRAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括暂存电脑可读媒体(transitorymedia),如调制的数据信号和载波。
可以理解,本公开实施例的存储器可以是易失性存储器或者非易失性存储器,也可包 括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(ROM,Read Only Memory)、可编程只读存储器(PROM,Programmable Read-Only Memory)、可擦除可编程只读存储器(EPROM,Erasable Programmable Read-Only Memory)、电可擦除可编程只读存储器(EEPROM,Electrically Erasable Programmable Read-Only Memory)、磁性随机存取存储器(FRAM,ferromagnetic random access memory)、快闪存储器(Flash Memory)、磁表面存储器、光盘、或只读光盘(CD-ROM,Compact Disc Read-Only Memory);磁表面存储器可以是磁盘存储器或磁带存储器。易失性存储器可以是随机存取存储器(RAM,Random Access Memory),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(SRAM,Static Random Access Memory)、同步静态随机存取存储器(SSRAM,Synchronous Static Random Access Memory)、动态随机存取存储器(DRAM,Dynamic Random Access Memory)、同步动态随机存取存储器(SDRAM,Synchronous Dynamic Random Access Memory)、双倍数据速率同步动态随机存取存储器(DDRSDRAM,Double Data Rate Synchronous Dynamic Random Access Memory)、增强型同步动态随机存取存储器(ESDRAM,Enhanced Synchronous Dynamic Random Access Memory)、同步连接动态随机存取存储器(SLDRAM,SyncLink Dynamic Random Access Memory)、直接内存总线随机存取存储器(DRRAM,Direct Rambus Random Access Memory)。本公开实施例描述的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本公开实施例提供了用户数据存储容灾方法、装置、电子设备和存储介质,该方法包括:获取用户数据的特征值;根据特征值对用户数据进行聚类,确定用户数据归属的簇集。采用本公开提供的方案能对大网UDM用户数据库中的数据进行聚类分析,使得同一簇的用户数据聚集,从而自动形成数据分类,完成大网用户数据到小网的映射,避免人工运维。
还需要说明的是,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
以上仅为本公开的实施例而已,并不用于限制本公开。对于本领域技术人员来说,本公开可以有各种更改和变化。凡在本公开的精神和原理之内所作的任何修改、等同替换、改进等,均应包含在本公开的权利要求范围之内。

Claims (10)

  1. 一种用户数据存储容灾方法,应用于UDM网元,所述用户数据存储容灾方法包括:
    获取用户数据的特征值;以及
    根据所述特征值对所述用户数据进行聚类,确定所述用户数据归属的簇集。
  2. 根据权利要求1所述的方法,其中,所述获取用户数据的特征值,包括:
    在所述用户为活动用户的情况下,通过提供定位信息接口,从AMF网元中获取所述活动用户的小区位置信息,将所述小区位置信息作为所述活动用户的特征值。
  3. 根据权利要求1所述的方法,其中,所述获取用户数据的特征值,包括:
    在所述用户为UDM存储的用户的情况下,查询UDM数据库中所述用户的签约数据信息,所述签约数据信息包括用户开户时间、开户操作员、IMSI、MSIDN、用户的接入和移动性数据、和会话管理签约数据;
    将所述签约数据信息作为所述用户的特征值。
  4. 根据权利要求1所述的方法,其中,所述获取用户数据的特征值,包括:
    在所述用户为新开户用户的情况下,查询UDM数据库中所述用户的签约数据信息,所述签约数据信息包括用户开户时间、开户操作员、IMSI、MSIDN、用户的接入和移动性数据、和会话管理签约数据;
    将所述签约数据信息作为所述用户的特征值。
  5. 根据权利要求1所述的方法,其中,所述获取用户数据的特征值,包括:
    在所述用户为通过AMF网元接入的新用户的情况下,通过提供定位信息接口,从AMF网元中获取所述活动用户的小区位置信息,将所述小区位置信息作为所述活动用户的特征值。
  6. 根据权利要求1所述的方法,其中,所述根据所述特征值对所述用户数据进行聚类,确定所述用户数据归属的簇集,包括:
    根据所述特征值利用非监督学习算法对所述用户数据进行聚类,确定所述用户数据归属的簇集。
  7. 根据权利要求1所述的方法,其中,确定所述用户数据归属的簇集之后,所述用户数据存储容灾方法还包括:
    将当前UDM网元中用户数据的聚类结果,同步到对应的容灾核心网UDM网元中。
  8. 一种用户数据存储容灾装置,应用于UDM网元,所述用户数据存储容灾装置包括:
    数据挖掘模块,被配置为获取用户数据的特征值;以及
    分类模块,被配置为根据所述特征值对所述用户数据进行聚类,确定所述用户数据归属的簇集。
  9. 一种电子设备,包括:处理器和用于存储能够在处理器上运行的计算机程序的存储器;其中,
    所述处理器用于运行所述计算机程序时,执行权利要求1至7任一项所述的用户数据存储容灾方法。
  10. 一种存储介质,所述存储介质中存储有计算机程序,其中,所述计算机程序被处理器执行时,实现权利要求1至7任一项所述的用户数据存储容灾方法。
PCT/CN2023/103332 2022-07-11 2023-06-28 用户数据存储容灾方法、装置、电子设备和存储介质 WO2024012203A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210817918.X 2022-07-11
CN202210817918.XA CN117440359A (zh) 2022-07-11 2022-07-11 用户数据存储容灾方法、装置、电子设备和存储介质

Publications (1)

Publication Number Publication Date
WO2024012203A1 true WO2024012203A1 (zh) 2024-01-18

Family

ID=89535506

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/103332 WO2024012203A1 (zh) 2022-07-11 2023-06-28 用户数据存储容灾方法、装置、电子设备和存储介质

Country Status (2)

Country Link
CN (1) CN117440359A (zh)
WO (1) WO2024012203A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106547894A (zh) * 2016-11-03 2017-03-29 浙江夏农信息技术有限公司 基于移动通信信令大数据挖掘职住位置标签的系统及方法
CN111159243A (zh) * 2019-12-30 2020-05-15 中国移动通信集团江苏有限公司 用户类型识别方法、装置、设备及存储介质
CN113938874A (zh) * 2021-09-28 2022-01-14 中国联合网络通信集团有限公司 数据处理方法、装置、设备及系统
CN114374965A (zh) * 2021-12-30 2022-04-19 广州爱浦路网络技术有限公司 一种用户签约数据处理方法、系统、设备及介质
WO2022121772A1 (zh) * 2020-12-10 2022-06-16 中兴通讯股份有限公司 数据容灾备份方法、统一数据管理udm实体和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106547894A (zh) * 2016-11-03 2017-03-29 浙江夏农信息技术有限公司 基于移动通信信令大数据挖掘职住位置标签的系统及方法
CN111159243A (zh) * 2019-12-30 2020-05-15 中国移动通信集团江苏有限公司 用户类型识别方法、装置、设备及存储介质
WO2022121772A1 (zh) * 2020-12-10 2022-06-16 中兴通讯股份有限公司 数据容灾备份方法、统一数据管理udm实体和存储介质
CN113938874A (zh) * 2021-09-28 2022-01-14 中国联合网络通信集团有限公司 数据处理方法、装置、设备及系统
CN114374965A (zh) * 2021-12-30 2022-04-19 广州爱浦路网络技术有限公司 一种用户签约数据处理方法、系统、设备及介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
NEC: "TS23.502 KI#15 User consent for UE data collection", 3GPP DRAFT; S2-2104616, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG2, no. E (e-meeting); 20210517 - 20210528, 10 May 2021 (2021-05-10), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP052004913 *

Also Published As

Publication number Publication date
CN117440359A (zh) 2024-01-23

Similar Documents

Publication Publication Date Title
US11711420B2 (en) Automated management of resource attributes across network-based services
CN111767143B (zh) 交易数据处理方法、装置、设备及系统
US11349725B2 (en) Method and apparatus for providing cognitive functions and facilitating management in cognitive network management systems
US10735537B2 (en) Information pushing
CN113297396B (zh) 基于联邦学习的模型参数更新方法、装置及设备
TWI694700B (zh) 資料處理方法和裝置、用戶端
CN110765165B (zh) 一种跨系统数据同步处理的方法、装置及系统
CN112905854A (zh) 数据处理方法、装置、计算设备及存储介质
WO2020119437A1 (zh) 语音控制方法、云端服务器及终端设备
WO2021057064A1 (zh) 基于人工智能的数据交互转换方法、装置、设备及介质
WO2021114834A1 (zh) 客服问题的更新方法、系统、终端设备及计算机存储介质
CN111784468B (zh) 一种账户关联方法、装置及电子设备
WO2024012203A1 (zh) 用户数据存储容灾方法、装置、电子设备和存储介质
CN112583941B (zh) 一种支持接入多电力终端的方法、单元节点及电力物联网
KR102481162B1 (ko) 사물 인터넷에서의 구독 데이터 푸시 방법 및 장치, 그 디바이스 및 저장 매체
JP2018525728A (ja) コンピュータ環境からのストリーミングデータセットを分析するための分散型機械学習分析フレームワーク
WO2018188607A1 (zh) 流处理方法及装置
US10638539B2 (en) Facilitating resource frequency management for emergency response
US10146791B2 (en) Open file rebalance
EP3559797A1 (en) Meta-join and meta-group-by indexes for big data
WO2021134252A1 (zh) 设备间通信方法、装置、和存储介质
WO2024001568A1 (zh) Smf网元选择方法、装置、电子设备及存储介质
CN112948593A (zh) 知识图谱的生成方法、装置、设备和介质
CN112527760A (zh) 数据存储方法、装置、服务器及介质
CN111176715A (zh) 一种信息调用方法及服务器

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: 23838697

Country of ref document: EP

Kind code of ref document: A1