WO2023093320A1 - 客户自主分析方法、装置以及介质 - Google Patents

客户自主分析方法、装置以及介质 Download PDF

Info

Publication number
WO2023093320A1
WO2023093320A1 PCT/CN2022/124278 CN2022124278W WO2023093320A1 WO 2023093320 A1 WO2023093320 A1 WO 2023093320A1 CN 2022124278 W CN2022124278 W CN 2022124278W WO 2023093320 A1 WO2023093320 A1 WO 2023093320A1
Authority
WO
WIPO (PCT)
Prior art keywords
analysis
customer
data
function
analysis function
Prior art date
Application number
PCT/CN2022/124278
Other languages
English (en)
French (fr)
Inventor
梅承力
李鹏宇
聂衡
夏旭
Original Assignee
中国电信股份有限公司
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 中国电信股份有限公司 filed Critical 中国电信股份有限公司
Publication of WO2023093320A1 publication Critical patent/WO2023093320A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2457—Query processing with adaptation to user needs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Definitions

  • the present disclosure generally relates to client autonomous analysis methods, apparatus, and media.
  • the 5G network can provide various services such as slicing.
  • the standard also introduces the NWDAF (NWDAF-Network Data Analytics Function, network data analysis function) network element architecture to support intelligent analysis, such as slicing SLA (Service Level Agreement, service level agreement) Guarantee, user trajectory, fault analysis, etc., provide users with intelligent analysis.
  • NWDAF NWDAF-Network Data Analytics Function, network data analysis function
  • a method for customer independent analysis of business data including: the first analysis function receives a customer's data analysis request through a network function or an application function, and the data analysis request includes an independent analysis service field, The address of the second analysis function to be used and the customer ID; the value of the autonomous analysis service field in the data analysis request identified by the first analysis function; where said value indicates that the data analysis request is a customer autonomous analysis request, Confirm whether the customer represented by the customer ID is a contracted customer by the first analysis function, and in the case that the customer is a contracted customer, obtain the contract information of the customer by the first analysis function; query by the first analysis function The network element that provides services for the customer corresponding to the subscription information; collect operator data related to the customer from the network element by the first analysis function, and use the collected operator data according to the address Send to the second analysis function; the first analysis function receives the data analysis result from the second analysis function, and makes a decision based on the data analysis result.
  • the second analysis function is an analysis function independently established by the customer, and the second analysis function performs analysis based on the operator data and the customer's service data to obtain the data analysis result.
  • confirming by the first analysis function whether the customer represented by the customer ID is a contracted customer includes: The unified data management function issues an inquiry request to confirm whether the customer represented by the customer ID is a contracted customer.
  • confirming by the first analysis function whether the customer represented by the customer ID is a contracted customer comprises: referring to by the first analysis function The customer's contract information stored in the first analysis function in advance to confirm whether the customer indicated by the customer ID is a contracted customer.
  • the first analysis function queries network elements corresponding to the subscription information that provide services for the customer from the network repository function.
  • the second analysis function is located at the customer's own device, or the second analysis function is located in the network operator's equipment, but is logically separated and independent from other functions of the network operator.
  • the second analysis function comprises an intelligent model that has been trained autonomously by said customer based on operator data and customer's business data.
  • the second analysis function includes a plurality of said smart models
  • said data analysis request further includes the address of the smart model in the second analysis function to be used
  • the collected operating Sending the quotient data to the second analysis function includes: sending the address of the smart model to the second analysis function, so that the smart model represented by the address of the smart model in the second analysis function performs data analysis.
  • the second analysis function is a web data analysis function or an artificial intelligence system.
  • the first analysis function is a web data analysis function.
  • the network element serving the client includes at least one of an access and mobility management function and a session management function.
  • the client autonomous analysis apparatus for providing service data includes: a module configured to execute the method according to the above aspect of the present disclosure.
  • the client-autonomous analysis device for providing business data includes: a memory with instructions stored thereon; and a processor configured to execute the instructions stored in the memory to perform the above-mentioned described method.
  • a computer-readable storage medium comprising computer-executable instructions that, when executed by one or more processors, cause the one or more The processor executes the method according to the above aspects of the present disclosure.
  • FIG. 1 is a schematic diagram illustrating a method for a general public user to request data analysis in the related art.
  • Fig. 2 shows a schematic diagram of analysis function decoupling according to some embodiments of the present disclosure.
  • Fig. 3 shows a schematic flowchart of a method for customer autonomous analysis of service data according to some specific embodiments of the present disclosure.
  • Figure 4 illustrates an example of autonomous analysis service fields according to some embodiments of the present disclosure.
  • Fig. 5 shows a schematic diagram of a process in which a customer signs a contract with an operator and registers to activate a service according to some embodiments of the present disclosure.
  • FIG. 6 illustrates an example of how customer subscription information is used according to some embodiments of the present disclosure.
  • Fig. 7 shows an example of usage of customer subscription information according to another embodiment of the present disclosure.
  • FIG. 8 is a schematic diagram illustrating an example of a first analysis function and a second analysis function according to some embodiments of the present disclosure.
  • FIG. 9 illustrates an example of a customer's analysis function list, model type, and address, according to some embodiments of the present disclosure.
  • FIG. 10 illustrates an exemplary configuration of a computing device in which embodiments according to the present disclosure may be implemented.
  • FIG. 1 is a schematic diagram illustrating a method for a general public user to request data analysis in the related art.
  • the method flow for general public users to request data analysis is as follows:
  • NF network function
  • AF application function
  • NWDAF Network Repository Function, network repository function
  • the present disclosure proposes to enable customers to independently analyze business data.
  • Customer in this disclosure refers to any entity such as business, business, industry, association, school, institution, any organization, group, and government.
  • the terms business or industry referred to in the following description and drawings may be synonymous with any entity as described above.
  • the present disclosure proposes to decouple the analysis function into an auxiliary reasoning analysis function (ie, the first analysis function) and a customer analysis function (ie, the second analysis function).
  • Fig. 2 shows a schematic diagram of analysis function decoupling according to some embodiments of the present disclosure.
  • the auxiliary reasoning NWDAF in Fig. 2 is an example of the first analysis function
  • the training model NWDAF is an example of the second analysis function.
  • the customer can independently establish the second analysis function, and use the second analysis function to independently analyze the customer's own business data and the data provided by the operator, thereby protecting the customer's privacy and relieving the customer of Data analysis security concerns.
  • a method for customer autonomous analysis of business data including: the first analysis function receives the customer's data analysis request through the network function (NF) or application function (AF), and the data analysis request Contains the autonomous analysis service field, the address of the second analysis function to be used, and the client identifier (client ID); the value of the autonomous analysis service field in the data analysis request is identified by the first analysis function; where the value represents the data
  • the analysis request is a customer's own analysis request
  • the first analysis function confirms whether the customer indicated by the customer ID is a contracted customer, and if the customer is a contracted customer, the first analysis function acquires the customer's contract information ; query the network element corresponding to the subscription information by the first analysis function to provide services for the customer; collect operator data related to the customer from the network element by the first analysis function, and collect the collected data according to the address
  • the operator data is sent to the second analysis function; the first analysis function receives the data analysis result from the second analysis function, and makes a decision based on the
  • the data analysis is performed by the first analysis function.
  • the first analysis function may be the network data analysis function (NWDAF) of the operator in the 5G network
  • the second analysis function may be the NWDAF or similar ( artificial intelligence) AI system.
  • the second analysis function may be a function of performing analysis using a fixed model, or a function of using a training model obtained through training capable of intelligent analysis.
  • a customer may have multiple second analysis functions, and different customers may have different second analysis functions. In some embodiments, different customers may also share a certain second analysis function.
  • the address of the second analysis function can be used to locate the second analysis function to be used.
  • a function may be a module such as any one of software, firmware, and hardware, or may be a network element in a network.
  • the second analysis function may perform analysis based on the operator data provided by the operator and the customer's own business data to obtain a data analysis result. Since the second analysis function for analyzing the customer's own business data is a function independently established by the customer, the data privacy of the customer can be more effectively protected.
  • the step of confirming whether the customer represented by the customer ID is a contracted customer by the first analysis function may include: An analysis function sends a query request to the unified data management function (Unified Data Management, UDM) to confirm whether the customer represented by the customer ID is a contracted customer.
  • UDM Unified Data Management
  • the step of confirming whether the customer represented by the customer ID is a contracted customer by the first analysis function may include: An analysis function refers to the customer's contract information previously stored in the first analysis function to confirm whether the customer indicated by the customer ID is a contracted customer. Since the customer's contract information is stored in the first analysis function in advance, the first analysis function does not need to send an inquiry request to other functions, but only by referring to the contract information stored in the first analysis function itself, it can be confirmed whether the customer is already signed. contracted customers.
  • the subscription information may include the customer ID of the customer who has signed up.
  • the first analysis function may query the network element corresponding to the subscription information that provides the service for the customer from the network repository function.
  • the network element may include at least one of AMF (Access and Mobility Management Function), SMF (Session Management Function), and the like.
  • the second analysis function may be located at the customer's own device. That is, the second analysis function can be completely separated from the operator's equipment. In some embodiments, the second analysis function may be located in the network operator's equipment, but logically separate and independent from the network operator's other functions. No matter whether the second analysis function is located in the equipment of the network operator or not, because it is logically separated and independent from other functions of the network operator, it can relieve customers from worrying about the security of their business data.
  • the second analysis function may contain an intelligent model that has been trained autonomously by the customer based on the operator data and the customer's business data. Since the intelligent model is trained based on operator data and customer service data, the intelligent model in the second analysis function can perform autonomous analysis on the data more accurately, efficiently or intelligently.
  • a second analysis function may contain multiple smart models, and the data analysis request may further include the address of the smart model in the second analysis function to be used.
  • the step of sending the collected operator data to the second analysis function according to the address of the second analysis function to be used may include sending the address of the smart model to the second analysis function to be analyzed by the second analysis function.
  • the intelligent model represented by the address of the intelligent model in the function performs data analysis.
  • the data analysis request also includes the address of the intelligent model in the second analysis function to be used, the data analysis can be performed by a specific intelligent model in the second analysis function, and thus can be performed through different Different types of intelligent models in different types of analysis functions to improve the pertinence and professionalism of data analysis.
  • the second analysis function may be a web data analysis function or an artificial intelligence system or any similar function.
  • Fig. 3 shows a schematic flowchart of a method for customer-autonomous analysis of service data according to some embodiments of the present disclosure.
  • the customer autonomous analysis method of some embodiments of the present disclosure will be described below with reference to FIG. 3 .
  • the process example shown in Figure 3 mainly includes the following steps:
  • the NF or AF sends a data analysis request to the reasoning NWDAF (which is an example of the first analysis function), and the request carries the autonomous analysis service field 1, the industry NWDAF used to analyze the data (that is, the enterprise NWDAF or the customer industry NWDAF, which is An example of the second analysis function) address information and customer ID.
  • the reasoning NWDAF which is an example of the first analysis function
  • the industry NWDAF used to analyze the data that is, the enterprise NWDAF or the customer industry NWDAF, which is An example of the second analysis function address information and customer ID.
  • Auxiliary reasoning NWDAF identifies the autonomous analysis service field, that is, identifies the field value 1 of this field.
  • the assisted reasoning NWDAF can query UDM to confirm whether the customer is a contracted customer and obtain the contracted information. If the customer is a contracted customer, go to the next step. If the confirmation fails, that is, the customer is a non-contracted customer, terminate the process and return a service denial notification.
  • the UDM may not be accessed, and the assisted reasoning NWDAF can directly make a judgment by querying local information.
  • NWDAF queries NRF for network element information corresponding to the contract information, such as network elements such as AMF and/or SMF that provide services for enterprises (ie, customers), and starts collecting operator data from these network elements.
  • network elements such as AMF and/or SMF that provide services for enterprises (ie, customers), and starts collecting operator data from these network elements.
  • FIG. 4 illustrates an example of autonomous analysis service fields according to some embodiments of the present disclosure. As shown in FIG. 4 , 0 represents data analysis requested by ordinary users (ie, the aforementioned general public users), and 1 represents autonomous analysis requested by contracted customers.
  • Fig. 5 shows a schematic diagram of a process in which a customer signs a contract with an operator and registers to activate a service according to some embodiments of the present disclosure.
  • customers can register and activate autonomous analysis services through NEF (Network Exposure Function, Network Exposure Function), industry portals, and activation systems.
  • NEF Network Exposure Function
  • the operator may store the customer ID, DNN (data network name), slice ID, etc. associated with the customer in the UDM.
  • FIG. 6 illustrates an example of how customer subscription information is used according to some embodiments of the present disclosure.
  • Fig. 7 shows an example of usage of customer subscription information according to other embodiments of the present disclosure.
  • the auxiliary reasoning NWDAF can identify that the field value of the autonomous analysis service field is 1, and initiate a query request to UDM, compare the customer ID, and confirm the customer As a contracted customer, the independent analysis service will be triggered immediately.
  • the UDM can send the associated customer ID, DNN, and slice ID to the auxiliary reasoning NWDAF.
  • the assisted reasoning NWDAF can directly confirm the customer identity and know the contract information by querying the customer information stored in itself.
  • the decoupling of conventional NWDAF functions is divided into NWDAF for auxiliary reasoning and training model NWDAF, wherein the training model NWDAF is responsible for carrying out model training and data analysis according to customer business data sets.
  • FIG. 8 is a schematic diagram illustrating an example of a first analysis function and a second analysis function according to some embodiments of the present disclosure.
  • the operator's training NWDAF (which is an example of the first analysis function) uses the data collected by the operator, and can perform different model training according to the analysis ID (Analytics ID), and the trained The model and the corresponding Analytics ID are registered with NRF.
  • Customer NWDAF (which is an example of the second analysis function, shown as enterprise self-training NWDAF in Figure 8) can obtain customer business data such as business APP, UE, background data, etc., and combine operator data Trained to meet the specific needs of customers.
  • a second analysis function may contain multiple analysis models or intelligent models.
  • the address of the customer model can be used to determine the analysis model or intelligent model to be used.
  • the type of training model can also be included in the request to more clearly specify the type of data analysis.
  • 9 illustrates an example of a list of a customer's second analysis function (shown as NWDAF as an example) and corresponding model types and model addresses, according to some embodiments of the present disclosure.
  • NWDAF second analysis function
  • a specific second analysis function can be located through the address of the second analysis function, and a specific model in the specific second analysis function can be located through the address of the model.
  • the disclosed method has the main advantages of:
  • the technology disclosed herein provides a method for supporting independent analysis by customers, including corresponding independent analysis service registration and opening, data model training, field definition and independent service process. Make up for the shortcomings of standardization.
  • Customer A signs a contract with the operator and requires to provide independent analysis services.
  • data is obtained from network elements such as AMF used by customers.
  • the data analysis model uses the model M trained by customer A, and the address is M_address.
  • NF or AF sends data analysis request to auxiliary reasoning NWDAF, carrying autonomous analysis service field 1, M_address and customer ID.
  • NWDAF identifies a field value of 1 for the Autonomous Analysis Service field.
  • Auxiliary reasoning NWDAF queries UDM to confirm whether the customer A is a subscriber, and obtains the subscription information.
  • NWDAF queries NRF for network element information corresponding to subscription information, and starts data collection.
  • visit M_address After data collection, visit M_address, use model M for data analysis, and return to auxiliary reasoning NWDAF for decision-making after analysis.
  • a method for supporting customers to carry out intelligent analysis independently including corresponding independent analysis service registration and opening, data model training, field definition and independent service process.
  • UDM adds a self-analysis service field, which identifies two options for providing self-service and operator services.
  • NWDAF assisted reasoning NWDAF
  • the operator's NWDAF can obtain the needs and permissions of the customer's independent analysis through UDM query or pre-stored, obtain relevant data according to the independent demand and route it to the analysis of the customer's self-built independent analysis such as NWDAF or similar AI systems Function.
  • the present disclosure can be used for operators to satisfy important customers, provide the customers with a capability such as independent intelligent analysis, and avoid customers' concerns about data analysis privacy.
  • the present disclosure provides a mechanism for independent intelligent analysis of enterprise customers. Through the cooperation of operators, customers can give full play to the advantages of their back-end business data resources, carry out intelligent data analysis on their own, and avoid concerns about privacy leakage.
  • customers apply for registration and activation of independent intelligent analysis services through the portal or activation system, and sign the trigger conditions.
  • judge whether to trigger the independent intelligent analysis service assist the reasoning NWDAF to obtain the relevant NF data corresponding to the customer event, and then route it to the contracted customer's analysis function such as NWDAF or similar intelligent system for autonomous service.
  • the system integrates the data provided by the operator and the customer's own business data to carry out independent intelligent analysis.
  • Some embodiments of the present disclosure also provide an apparatus for customer-initiated analysis of service data, including: a module configured to execute the method in any one of the above embodiments.
  • the customer independent analysis device for business data includes a receiving module, an identification module, a confirmation module, a query module, a collection module and a decision module.
  • the receiving module is configured to receive a customer's data analysis request through a network function or an application function, and the data analysis request includes an autonomous analysis service field, an address of a second analysis function to be used, and a customer ID.
  • the identification module is configured to identify the value of the autonomous analysis service field in the data analysis request.
  • the confirmation module is configured to confirm whether the customer represented by the customer ID is a contracted customer by the first analysis function if the value indicates that the data analysis request is a customer autonomous analysis request, and if the customer is a contracted customer, by The first analysis function obtains the customer's contract information.
  • the query module is configured to query the network elements corresponding to the subscription information that provide services for customers.
  • the collection module is configured to collect operator data related to customers from the network elements, and send the collected operator data to the second analysis function according to the address.
  • the decision module is configured to receive the data analysis result from the second analysis function by the first analysis function, and make a decision based on the data analysis result.
  • Some other embodiments of the present disclosure also provide a client-autonomous analysis device for business data, including a memory with instructions stored thereon; and a processor configured to execute the instructions stored in the memory to perform any one of the above embodiments Methods.
  • Some other embodiments of the present disclosure also provide a NWDAF, including the device for independently analyzing service data in any one of the above embodiments.
  • FIG. 10 shows an exemplary configuration of a computing device 1200 capable of implementing embodiments according to the present disclosure.
  • Computing device 1200 is an example of a hardware device to which method embodiments of the above-described aspects of the present disclosure can be applied.
  • Computing device 1200 may be any machine configured to perform processing and/or computation.
  • Computing device 1200 may be, but is not limited to, a workstation, server, desktop computer, laptop computer, tablet computer, personal data assistant (PDA), smart phone, vehicle-mounted computer, or combinations thereof.
  • PDA personal data assistant
  • computing device 1200 may include one or more elements that may be connected to or communicate with bus 1202 via one or more interfaces.
  • the bus 1202 may include, but is not limited to, an Industry Standard Architecture (Industry Standard Architecture, ISA) bus, a Micro Channel Architecture (Micro Channel Architecture, MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, etc.
  • Computing device 1200 may include, for example, one or more processors 1204 , one or more input devices 1206 , and one or more output devices 1208 .
  • Processor(s) 1204 may be any kind of processor, and may include, but is not limited to, one or more general purpose processors or special purpose processors (such as dedicated processing chips).
  • the processor 1204 may be configured to implement the above-mentioned customer-independent analysis method of service data.
  • Input device 1206 may be any type of input device capable of entering information into a computing device, and may include, but is not limited to, a mouse, keyboard, touch screen, microphone, and/or remote control.
  • Output devices 1208 may be any type of device capable of presenting information, and may include, but are not limited to, displays, speakers, video/audio output terminals, vibrators, and/or printers.
  • the computing device 1200 may also include or be connected to a non-transitory storage device 1214, which may be any storage device that is non-transitory and capable of data storage, and may include, but is not limited to, a disk drive, optical storage device, solid-state memory, floppy disk, flexible disk, hard disk, magnetic tape or any other magnetic medium, compact disk or any other optical medium, cache memory and/or any other memory chip or module from which data can be read by a computer , instructions and/or code in any other medium.
  • Computing device 1200 may also include random access memory (RAM) 1210 and read only memory (ROM) 1212 .
  • the ROM 1212 may store programs, utilities, or processes to be executed in a non-volatile manner.
  • RAM 1210 may provide volatile data storage and store instructions related to the operation of computing device 1200 .
  • Computing device 1200 may also include network/bus interface 1216 coupled to data link 1218 .
  • Network/bus interface 1216 may be any type of device or system capable of enabling communication with external devices and/or networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication devices, and/or chipsets such as BluetoothTM devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication facilities, etc.).
  • processors may be implemented as an integrated circuit (IC), application specific integrated circuit (ASIC), or large scale integrated circuit (LSI), system LSI, super LSI, or super LSI that performs some or all of the functions described in this disclosure components.
  • IC integrated circuit
  • ASIC application specific integrated circuit
  • LSI large scale integrated circuit
  • the present disclosure includes the use of software, applications, computer programs or algorithms.
  • Software, applications, computer programs or algorithms may be stored on a non-transitory computer readable medium to cause a computer, such as one or more processors, to perform the steps described above and in the figures.
  • a computer such as one or more processors
  • one or more memories store software or algorithms as executable instructions
  • one or more processors can be associated with a set of instructions that execute the software or algorithms to provide various functions according to the embodiments described in this disclosure.
  • Software and computer programs include machine instructions for a programmable processor and may be written in a high-level procedural language, object-oriented programming language, functional programming language , logic programming language or assembly language or machine language.
  • computer-readable medium means any computer program product, means or device for providing machine instructions or data to a programmable data processor, such as a magnetic disk, optical disk, solid state storage device, memory and programmable logic device (PLD) , including a computer-readable medium for receiving machine instructions as computer-readable signals.
  • a computer readable medium may include dynamic random access memory (DRAM), random access memory (RAM), read only memory (ROM), electrically erasable read only memory (EEPROM), compact disk read only memory (CD-ROM) or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or can be used to carry or store required computer-readable program code in the form of instructions or data structures and can be read by general or special purpose computers or general-purpose or any other medium accessed by a dedicated processor.
  • Disk or disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disc and blu-ray Data is copied optically. Combinations of the above should also be included within the scope of computer-readable media.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Debugging And Monitoring (AREA)

Abstract

本公开涉及客户自主分析方法、装置以及介质。一种业务数据的客户自主分析方法，包括：由第一分析功能接收客户的数据分析请求，该请求包含自主分析服务字段、要使用的第二分析功能的地址以及客户ID；由第一分析功能识别请求中的自主分析服务字段的值；在值表示请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户，并且在是已签约客户的情况下，由第一分析功能获取客户的签约信息；由第一分析功能查询与签约信息对应的服务网元；由第一分析功能从网元收集与客户相关的运营商数据，并根据地址将收集到的运营商数据发送给第二分析功能；由第一分析功能从第二分析功能接收分析结果，并基于分析结果进行决策。

Description

客户自主分析方法、装置以及介质
相关申请的交叉引用
本公开以中国申请号为202111429668.4，申请日为2021年11月29日的申请为基础，并主张其优先权，该中国申请的公开内容在此作为整体引入本公开中。
技术领域
本公开总体上涉及客户自主分析方法、装置以及介质。
背景技术
5G网络可以提供切片等各类服务，同时标准也引入了NWDAF(NWDAF-Network Data Analytics Function，网络数据分析功能)网元架构，支持智能化分析，如切片SLA(Service Level Agreement，服务等级协议)保障、用户轨迹、故障分析等，为用户提供了智能化分析。
据目前了解，部分重要的诸如企业、政府之类的客户确实需要NWDAF分析功能，但明确表示不愿意业务数据被运营商分析，希望自己开展模型训练和智能分析，运营商做好配合。
发明内容
在下文中给出了关于本公开的简要概述，以便提供关于本公开的一些方面的基本理解。但是，应当理解，这个概述并不是关于本公开的穷举性概述。它并不是意图用来确定本公开的关键性部分或重要部分，也不是意图用来限定本公开的范围。其目的仅仅是以简化的形式给出关于本公开的某些概念，以此作为稍后给出的更详细描述的前序。
根据本公开实施例的一个方面，提供一种业务数据的客户自主分析方法，包括：由第一分析功能通过网络功能或应用功能接收客户的数据分析请求，该数据分析请求包含自主分析服务字段、要使用的第二分析功能的地址以及客户ID；由第一分析功能识别数据分析请求中的自主分析服务字段的值；在所述值表示所述数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户，并且在所述客户是已签约客户的情况下，由第一分析功能获取所述客户的签约 信息；由第一分析功能查询与所述签约信息对应的为所述客户提供服务的网元；由第一分析功能从所述网元收集与所述客户相关的运营商数据，并根据所述地址将收集到的运营商数据发送给第二分析功能；由第一分析功能从第二分析功能接收数据分析结果，并基于数据分析结果进行决策。
在一些实施例中，第二分析功能是由所述客户自主建立的分析功能，以及第二分析功能基于所述运营商数据和所述客户的业务数据进行分析以获得所述数据分析结果。
在一些实施例中，在所述值表示所述数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户包括：由第一分析功能向统一数据管理功能发出查询请求，以确认由客户ID表示的客户是否为已签约客户。
在一些实施例中，在所述值表示所述数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户包括：由第一分析功能参考事先存储在第一分析功能中的客户的签约信息，以确认由客户ID表示的客户是否为已签约客户。
在一些实施例中，第一分析功能从网络存储库功能查询与所述签约信息对应的为所述客户提供服务的网元。
在一些实施例中，第二分析功能位于所述客户自己的设备处，或者第二分析功能位于网络运营商的设备中，但是在逻辑上与网络运营商的其他功能分离并且独立。
在一些实施例中，第二分析功能包含已经由所述客户自主地基于运营商数据和客户的业务数据训练的智能模型。
在一些实施例中，第二分析功能包含多个所述智能模型，并且所述数据分析请求还包含要使用的第二分析功能中的智能模型的地址，以及根据所述地址将收集到的运营商数据发送给第二分析功能包括：将智能模型的地址发送给第二分析功能，以由第二分析功能中的由智能模型的地址表示的智能模型进行数据分析。
在一些实施例中，第二分析功能是网络数据分析功能或人工智能系统。
在一些实施例中，第一分析功能为网络数据分析功能。
在一些实施例中，为所述客户提供服务的网元包括接入和移动性管理功能和会话管理功能中的至少一个。
根据本公开实施例的另一个方面，提供业务数据的客户自主分析装置，包括：被配置为执行根据本公开的上述方面所述的方法的模块。
根据本公开实施例的另一个方面，提供业务数据的客户自主分析装置，包括：存储器，其上存储有指令；以及处理器，被配置为执行存储在所述存储器上的指令，以执行如上所述的方法。
根据本公开实施例的又一个方面，提供一种计算机可读存储介质，其包括计算机可执行指令，所述计算机可执行指令在由一个或多个处理器执行时，使得所述一个或多个处理器执行根据本公开的上述方面所述的方法。
附图说明
构成说明书的一部分的附图描述了本公开的实施例，并且连同说明书一起用于解释本公开的原理。
参照附图，根据下面的详细描述，可以更清楚地理解本公开，其中：
图1是示出相关技术中的普通公众用户请求进行数据分析的方法的示意图。
图2示出了根据本公开的一些实施例的分析功能解耦的示意图。
图3示出了根据本公开的一些具体实施例的业务数据的客户自主分析方法的流程示意图。
图4示出了根据本公开一些实施例的自主分析服务字段的示例。
图5示出了根据本公开一些实施例的客户与运营商签约并注册开通服务的过程的示意图。
图6示出了根据本公开一些实施例的客户签约信息的使用方式示例。
图7示出了根据本公开另一实施例的客户签约信息的使用方式示例。
图8是示出根据本公开的一些实施例的第一分析功能和第二分析功能的示例的示意图。
图9示出了根据本公开的一些实施例的客户的分析功能列表、模型类型和地址的示例。
图10示出了可以实现根据本公开的实施例的计算设备的示例性配置。
具体实施方式
参考附图进行以下详细描述，并且提供以下详细描述以帮助全面理解本公开的各种示例实施例。以下描述包括各种细节以帮助理解，但是这些细节仅被认为是示例，而不是为了限制本公开，本公开是由随附权利要求及其等同内容限定的。在以下描述 中使用的词语和短语仅用于能够清楚一致地理解本公开。另外，为了清楚和简洁起见，可能省略了对公知的结构、功能和配置的描述。本领域普通技术人员将认识到，在不脱离本公开的精神和范围的情况下，可以对本文描述的示例进行各种改变和修改。
当前3GPP NWDAF架构中，可以为客户提供十几种智能分析。但该架构机制没有区分普通公众用户和诸如企业和政府之类的客户(以下称为客户)，导致客户对数据分析安全性的担忧。
图1是示出相关技术中的普通公众用户请求进行数据分析的方法的示意图。普通公众用户请求进行数据分析的方法流程如下：
1.NF(网络功能)或AF(应用功能)向辅助推理NWDAF发送数据分析请求，携带分析ID(Analytics ID)。
2.辅助推理NWDAF向NRF(Network Repository Function，网络存储库功能)查询Analytics ID对应的模型地址，并收集所使用到的数据。
3.访问分析数据所使用的训练NWDAF地址，并进行数据分析，分析结束后返回辅助推理NWDAF进行决策。如图1所示，该训练NWDAF是由运营商训练的。
从上述流程可知，在相关技术中，用于进行数据分析的训练NWDAF是由运营商训练和管理的，因此这会导致客户对数据分析安全性的担忧。
为了解除客户的担忧，本公开提出使客户能够自主进行业务数据分析。
本公开中的“客户”是指诸如企业、商业、行业、协会、学校、事业单位、任何组织、团体以及政府之类的任何实体。以下描述以及附图中提及的术语企业或行业可以等同于如上所述的任何实体。
在一些实施例中，本公开提出将分析功能解耦，分为辅助推理分析功能(即，第一分析功能)和客户分析功能(即，第二分析功能)。
图2示出了根据本公开的一些实施例的分析功能解耦的示意图。图2中的辅助推理NWDAF是第一分析功能的一个示例，训练模型NWDAF是第二分析功能的一个示例。
通过将分析功能解耦，可以由客户自主建立第二分析功能，并通过第二分析功能对客户自己的业务数据以及由运营商提供的数据进行自主分析，从而能够保护客户的隐私，解除客户对数据分析安全性的担忧。
根据本公开的一些实施例，提出了一种业务数据的客户自主分析方法，包括：由第一分析功能通过网络功能(NF)或应用功能(AF)接收客户的数据分析请求，该 数据分析请求包含自主分析服务字段、要使用的第二分析功能的地址以及客户标识符(客户ID)；由第一分析功能识别数据分析请求中的自主分析服务字段的值；在所述值表示所述数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户，并且在客户是已签约客户的情况下，由第一分析功能获取客户的签约信息；由第一分析功能查询与签约信息对应的为该客户提供服务的网元；由第一分析功能从所述网元收集与所述客户相关的运营商数据，并根据所述地址将收集到的运营商数据发送给第二分析功能；由第一分析功能从第二分析功能接收数据分析结果，并基于数据分析结果进行决策。
在一些实施例中，在所述值表示所述数据分析请求不是客户自主分析请求的情况下，由第一分析功能进行数据分析。
在本公开中，例如，第一分析功能可以是5G网络中的运营商的网络数据分析功能(NWDAF)，第二分析功能可以是由客户自主建立的用于进行自主分析的NWDAF或类似的(人工智能)AI系统。第二分析功能可以是使用固定模型进行分析的功能，也可以是使用能够进行智能分析的通过训练获得的训练模型的功能。
一个客户可以拥有多个第二分析功能，不同的客户可以拥有不同的第二分析功能。在一些实施例中，不同的客户也可以共用某个第二分析功能。第二分析功能的地址可以用于定位到要使用的第二分析功能。
在本公开中，功能可以是例如软件、固件以及硬件中的任一个的模块，也可以是网络中的网元。
在一些实施例中，第二分析功能可以基于由运营商提供的运营商数据和客户自己的业务数据进行分析以获得数据分析结果。由于用于分析客户自己的业务数据的第二分析功能是由客户自主建立的功能，因此能够更加有效地保护客户的数据隐私。
在一些实施例中，在自主分析服务字段的值表示数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户的步骤可以包括：由第一分析功能向统一数据管理功能(Unified Data Management，UDM)发出查询请求，以确认由客户ID表示的客户是否为已签约客户。已签约客户是指与运营商签约并被注册为能够对业务数据进行自主分析的客户。
在一些实施例中，在自主分析服务字段的值表示数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户的步骤可以包括：由第一分析功能参考事先存储在第一分析功能中的客户的签约信息，以确认 由客户ID表示的客户是否为已签约客户。由于事先将客户的签约信息存储在第一分析功能中，因此第一分析功能可以不必向其他功能发出查询请求，仅参考存储在第一分析功能本身中的签约信息，就可以确认客户是否为已签约客户。
在一些实施例中，签约信息可以包括已签约客户的客户ID。
在一些实施例中，第一分析功能可以从网络存储库功能查询与签约信息对应的为所述客户提供服务的网元。网元可以包括AMF(接入和移动性管理功能)和SMF(会话管理功能)中的至少一个等。通过查询为客户提供服务的网元，可以由第一分析功能从这些网元收集与对应的客户相关的运营商数据，从而可以将这些运营商数据提供给第二分析功能以辅助第二分析功能进行数据分析。
在一些实施例中，第二分析功能可以位于客户自己的设备处。即，第二分析功能可以与运营商的设备完全分离。在一些实施例中，第二分析功能可以位于网络运营商的设备中，但是在逻辑上与网络运营商的其他功能分离并且独立。无论第二分析功能是否位于网络运营商的设备中，由于它在逻辑上与网络运营商的其他功能是分离并且独立的，因此能够解除客户对于自己的业务数据的安全性的担忧。
在一些实施例中，第二分析功能可以包含已经由客户自主地基于运营商数据和客户的业务数据训练的智能模型。由于基于运营商数据和客户的业务数据对智能模型进行了训练，因此第二分析功能中的智能模型能够更加准确或高效或智能地对数据进行自主分析。
在一些实施例中，一个第二分析功能可以包含多个智能模型，并且数据分析请求还可以包含要使用的第二分析功能中的智能模型的地址。在此情况下，根据要使用的第二分析功能的地址将收集到的运营商数据发送给第二分析功能的步骤可以包括：将智能模型的地址发送给第二分析功能，以由第二分析功能中的由智能模型的地址表示的智能模型进行数据分析。在此情况下，由于数据分析请求还包含要使用的第二分析功能中的智能模型的地址，因此可以由特定的第二分析功能中的特定的智能模型来进行数据分析，由此可以通过不同类型的分析功能中的不同类型的智能模型来提高数据分析的针对性和专业性。
在一些实施例中，第二分析功能可以是网络数据分析功能或人工智能系统或任何类似的功能。
图3示出了根据本公开的一些实施例的业务数据的客户自主分析方法的流程示意图。以下结合图3对本公开的一些实施例的客户自主分析方法进行描述。
图3所示的流程示例主要包括如下步骤：
①NF或AF向推理NWDAF(其为第一分析功能的一个示例)发送数据分析请求，该请求携带自主分析服务字段1、分析数据所使用的行业NWDAF(即，企业NWDAF或客户行业NWDAF，其为第二分析功能的一个示例)的地址信息以及客户ID。
②辅助推理NWDAF识别自主分析服务字段，即，识别该字段的字段值1。
③在一些实施例中，辅助推理NWDAF可以向UDM查询确认该客户是否为签约客户，并获取签约信息。如果该客户为签约客户，执行下一步，如果确认失败，即，该客户为非签约客户，终止流程，返回拒绝服务通知。
在另一些实施例中，如果签约时采用NWDAF存储模式，即，已经将签约信息存储在辅助推理NWDAF中，那么可以不访问UDM，辅助推理NWDAF可以直接通过查询本地信息来进行判断。
④辅助推理NWDAF向NRF查询与签约信息对应的网元信息，例如为企业(即，客户)提供服务的AMF和/或SMF等网元，并开始从这些网元收集运营商数据。
⑤数据收集结束后，根据企业NWDAF地址访问对应的企业NWDAF，并且企业NWDAF基于收集的运营商数据和企业(即，客户)自己的业务数据进行综合数据分析，分析结束后返回给辅助推理NWDAF以进行决策。
为了实现上述方法，客户需要向运营商注册并开通自主分析服务。为此，需要为客户增加自主分析服务字段。图4示出了根据本公开一些实施例的自主分析服务字段的示例。如图4所示，0代表普通用户(即，前述普通公众用户)请求的数据分析，1代表签约的客户请求的自主分析。
客户需要与运营商签约并注册开通服务。图5示出了根据本公开一些实施例的客户与运营商签约并注册开通服务的过程的示意图。在一些实施例中，客户可以通过NEF(Network Exposure Function，网络开放功能)、行业门户、开通系统等注册开通自主分析服务。在一些实施例中，运营商可以将与客户关联的客户ID、DNN(数据网络名称)、切片ID等存储在UDM中。
图6示出了根据本公开一些实施例的客户签约信息的使用方式示例。图7示出了根据本公开另一些实施例的客户签约信息的使用方式示例。
如图6所示，在一些实施例中，辅助推理NWDAF在接收到数据分析请求后，可以识别自主分析服务字段的字段值为1，并向UDM发起查询请求，比对客户ID，确认该客户为签约客户，随即触发自主分析服务。
如图7所示，在另一些实施例中，在注册流程后，UDM可以把关联的客户ID、DNN、切片ID下发给辅助推理NWDAF。在后续流程中，根据自主分析服务字段和客户ID，辅助推理NWDAF接收到数据分析请求后就可通过查询存储在自身中的客户信息来直接确认客户身份以及知晓签约信息。
如图2所示，在本公开中将常规NWDAF功能的解耦，分为辅助推理的NWDAF以及训练模型NWDAF，其中训练模型NWDAF负责根据客户业务数据集开展模型训练和数据分析。
图8是示出根据本公开的一些实施例的第一分析功能和第二分析功能的示例的示意图。
如图8所示，运营商的训练NWDAF(其为第一分析功能的一个示例)使用运营商收集到的数据，并可以根据分析ID(Analytics ID)进行不同模型的训练，并且将训练好的模型以及对应的Analytics ID注册到NRF。客户NWDAF(其为第二分析功能的一个示例，在图8中被示出为企业自主训练NWDAF)可获取客户的诸如业务APP、UE、后台数据之类的业务数据，并结合运营商数据进行训练，以满足客户的特定需求。
客户在请求数据分析时，可以在请求中携带客户模型的地址，以便于正确路由到客户NWDAF，从而开展自主分析。在一些实施例中，一个第二分析功能中可能包含多个分析模型或智能模型，在此情况下，可以通过客户模型的地址确定所要使用的分析模型或智能模型。
在一些实施例中，客户在请求数据分析时，还可以在请求中携带训练模型类型，以更明确地指定数据分析的类型。图9示出了根据本公开的一些实施例的客户的第二分析功能(作为示例，被示出为NWDAF)列表以及对应的模型类型和模型地址的示例。尽管未示出，但是一个客户可以具有多个第二分析功能，并且每个第二分析功能可以具有多个模型。此外，可以通过第二分析功能的地址来定位到特定的第二分析功能，并且可以通过模型的地址来定位到特定的第二分析功能中的特定模型。
本公开的方法与相关技术相比，主要优势在于：
1.相关技术为5G用户提供了模型训练推理和智能分析，但仅限于运营商侧提供。对于数据和分析训练安全敏感的高价值客户，不愿意在运营商侧分析。本公开可以避免客户的安全顾虑。
2.本公开方法中的数据分析和模型训练掌握企业客户手中，运营商仅提供配合，有效规避了企业对于数据和数据分析安全的担忧，拓展了5G智能分析的应用范围和 场景，满足了客户需求，使得NWDAF的应用更容易落地。
3.相关国际标准和行业标准没有考虑重点企业客户的自主分析需求，没有提供对应的技术方案。
4.本公开的技术提供了一种支持客户自主分析的方法，包括相应的自主分析服务注册开通、数据模型训练、字段定义和自主服务流程。弥补了标准化的缺陷。
以下描述一个特定实施例。A客户与运营商签约，要求提供自主分析服务，进行自主服务时从客户使用的AMF等网元中获取数据，数据分析模型使用A客户所训练的模型M，地址为M_address。
步骤简述：
NF或AF向辅助推理NWDAF发送数据分析请求，携带自主分析服务字段1、M_address以及客户ID。
辅助推理NWDAF识别自主分析服务字段的字段值1。
辅助推理NWDAF向UDM查询确认该客户A是否为签约用户，获取签约信息。
辅助推理NWDAF向NRF查询与签约信息对应的网元信息，并开始进行数据收集。
数据收集结束后，访问M_address，用模型M进行数据分析，分析结束后返回辅助推理NWDAF进行决策。
在本公开中，在一些实施例中，提供了一种支持客户自主开展智能分析的方法，包括相应的自主分析服务注册开通、数据模型训练、字段定义和自主服务流程。在自主分析服务注册开通中，UDM新增自分析服务字段，标识出提供自服务和运营商服务两种选择。运营商NWDAF(辅助推理NWDAF)可以通过UDM查询或事先存储获得客户自主分析的需求和权限，按照自主需求获取相关数据并路由到客户自建的自主分析的诸如NWDAF或类似AI系统之类的分析功能。
本公开可用于运营商满足重要客户，为该客户其提供一种自主智能分析等能力，规避客户对数据分析隐私的担忧。
本公开提供一种企业客户自主智能分析的机制。通过运营商配合，客户可以充分发挥其后台业务数据资源优势，自重开展数据智能分析，规避隐私泄漏的担忧。
实现中，客户通过门户或开通系统等，申请注册开通自主智能分析服务，签约触发条件。客户上线后，判断是否触发自主智能分析服务，辅助推理NWDAF获取客户事件对应的相关NF数据，然后路由至已签约的客户的用于进行自主服务的诸如 NWDAF或类似智能系统之类的分析功能。该系统综合运营商提供的数据和客户自己的业务数据，开展自主智能分析。
本公开一些实施例还提供了一种业务数据的客户自主分析装置，包括：被配置为执行上述任一个实施例的方法的模块。例如，业务数据的客户自主分析装置包括接收模块、识别模块、确认模块、查询模块、收集模块和决策模块。
接收模块被配置为通过网络功能或应用功能接收客户的数据分析请求，该数据分析请求包含自主分析服务字段、要使用的第二分析功能的地址以及客户ID。
识别模块被配置为识别数据分析请求中的自主分析服务字段的值。
确认模块被配置为在值表示数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户，并且在客户是已签约客户的情况下，由第一分析功能获取客户的签约信息。
查询模块被配置为查询与签约信息对应的为客户提供服务的网元。
收集模块被配置为从网元收集与客户相关的运营商数据，并根据地址将收集到的运营商数据发送给第二分析功能。
决策模块被配置为由第一分析功能从第二分析功能接收数据分析结果，并基于数据分析结果进行决策。
本公开另一些实施例还提供了一种业务数据的客户自主分析装置，包括存储器，其上存储有指令；以及处理器，被配置为执行存储在存储器上的指令，以执行如上任意一个实施例的方法。
本公开又一些实施例还提供了一种NWDAF，包括如上任意一个实施例的业务数据的客户自主分析装置。
图10示出了能够实现根据本公开的实施例的计算设备1200的示例性配置。
计算设备1200是能够应用本公开的上述方面的方法实施例的硬件设备的实例。计算设备1200可以是被配置为执行处理和/或计算的任何机器。计算设备1200可以是但不限制于工作站、服务器、台式计算机、膝上型计算机、平板计算机、个人数据助手(PDA)、智能电话、车载计算机或以上组合。
如图10所示，计算设备1200可以包括可以经由一个或多个接口与总线1202连接或通信的一个或多个元件。总线1202可以包括但不限于，工业标准架构(Industry Standard Architecture，ISA)总线、微通道架构(Micro Channel Architecture，MCA)总线、增强ISA(EISA)总线、视频电子标准协会(VESA)局部总线、以及外设组件 互连(PCI)总线等。计算设备1200可以包括例如一个或多个处理器1204、一个或多个输入设备1206以及一个或多个输出设备1208。一个或多个处理器1204可以是任何种类的处理器，并且可以包括但不限于一个或多个通用处理器或专用处理器(诸如专用处理芯片)。处理器1204例如可以被配置为实现上述业务数据的客户自主分析方法。输入设备1206可以是能够向计算设备输入信息的任何类型的输入设备，并且可以包括但不限于鼠标、键盘、触摸屏、麦克风和/或远程控制器。输出设备1208可以是能够呈现信息的任何类型的设备，并且可以包括但不限于显示器、扬声器、视频/音频输出终端、振动器和/或打印机。
计算设备1200还可以包括或被连接至非暂态存储设备1214，该非暂态存储设备1214可以是任何非暂态的并且可以实现数据存储的存储设备，并且可以包括但不限于盘驱动器、光存储设备、固态存储器、软盘、柔性盘、硬盘、磁带或任何其他磁性介质、压缩盘或任何其他光学介质、缓存存储器和/或任何其他存储芯片或模块、和/或计算机可以从其中读取数据、指令和/或代码的其他任何介质。计算设备1200还可以包括随机存取存储器(RAM)1210和只读存储器(ROM)1212。ROM 1212可以以非易失性方式存储待执行的程序、实用程序或进程。RAM 1210可提供易失性数据存储，并存储与计算设备1200的操作相关的指令。计算设备1200还可包括耦接至数据链路1218的网络/总线接口1216。网络/总线接口1216可以是能够启用与外部装置和/或网络通信的任何种类的设备或系统，并且可以包括但不限于调制解调器、网络卡、红外线通信设备、无线通信设备和/或芯片集(诸如蓝牙 TM设备、802.11设备、WiFi设备、WiMax设备、蜂窝通信设施等)。
本公开可以被实现为装置、系统、集成电路和非瞬时性计算机可读介质上的计算机程序的任何组合。可以将一个或多个处理器实现为执行本公开中描述的部分或全部功能的集成电路(IC)、专用集成电路(ASIC)或大规模集成电路(LSI)、系统LSI，超级LSI或超LSI组件。
本公开包括软件、应用程序、计算机程序或算法的使用。可以将软件、应用程序、计算机程序或算法存储在非瞬时性计算机可读介质上，以使诸如一个或多个处理器的计算机执行上述步骤和附图中描述的步骤。例如，一个或多个存储器以可执行指令存储软件或算法，并且一个或多个处理器可以关联执行该软件或算法的一组指令，以根据本公开中描述的实施例提供各种功能。
软件和计算机程序(也可以称为程序、软件应用程序、应用程序、组件或代码) 包括用于可编程处理器的机器指令，并且可以以高级过程性语言、面向对象编程语言、功能性编程语言、逻辑编程语言或汇编语言或机器语言来实现。术语“计算机可读介质”是指用于向可编程数据处理器提供机器指令或数据的任何计算机程序产品、装置或设备，例如磁盘、光盘、固态存储设备、存储器和可编程逻辑设备(PLD)，包括将机器指令作为计算机可读信号来接收的计算机可读介质。
举例来说，计算机可读介质可以包括动态随机存取存储器(DRAM)、随机存取存储器(RAM)、只读存储器(ROM)、电可擦只读存储器(EEPROM)、紧凑盘只读存储器(CD-ROM)或其他光盘存储设备、磁盘存储设备或其他磁性存储设备，或可以用于以指令或数据结构的形式携带或存储所需的计算机可读程序代码以及能够被通用或专用计算机或通用或专用处理器访问的任何其它介质。如本文中所使用的，磁盘或盘包括紧凑盘(CD)、激光盘、光盘、数字多功能盘(DVD)、软盘和蓝光盘，其中磁盘通常以磁性方式复制数据，而盘则通过激光以光学方式复制数据。上述的组合也包括在计算机可读介质的范围内。
提供本公开的主题作为用于执行本公开中描述的特征的装置、系统、方法和程序的示例。但是，除了上述特征之外，还可以预期其他特征或变型。可以预期的是，可以用可能代替任何上述实现的技术的任何新出现的技术来完成本公开的部件和功能的实现。
另外，以上描述提供了示例，而不限制权利要求中阐述的范围、适用性或配置。在不脱离本公开的精神和范围的情况下，可以对所讨论的元件的功能和布置进行改变。各种实施例可以适当地省略、替代或添加各种过程或部件。例如，关于某些实施例描述的特征可以在其他实施例中被结合。
另外，在本公开的描述中，术语“第一”、“第二”、“第三”等仅用于描述目的，而不能理解为指示或暗示相对重要性和顺序。
类似地，虽然在附图中以特定次序描绘了操作，但是这不应该被理解为要求以所示的特定次序或者以顺序次序执行这样的操作，或者要求执行所有图示的操作以实现所希望的结果。在某些情况下，多任务处理和并行处理可以是有利的。

Claims (14)

  1. 一种业务数据的客户自主分析方法，包括：
    由第一分析功能通过网络功能或应用功能接收客户的数据分析请求，该数据分析请求包含自主分析服务字段、要使用的第二分析功能的地址以及客户ID；
    由第一分析功能识别数据分析请求中的自主分析服务字段的值；
    在所述值表示所述数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户，并且在所述客户是已签约客户的情况下，由第一分析功能获取所述客户的签约信息；
    由第一分析功能查询与所述签约信息对应的为所述客户提供服务的网元；
    由第一分析功能从所述网元收集与所述客户相关的运营商数据，并根据所述地址将收集到的运营商数据发送给第二分析功能；以及
    由第一分析功能从第二分析功能接收数据分析结果，并基于数据分析结果进行决策。
  2. 根据权利要求1所述的方法，其中，
    第二分析功能是由所述客户自主建立的分析功能，以及
    第二分析功能基于所述运营商数据和所述客户的业务数据进行分析以获得所述数据分析结果。
  3. 根据权利要求1或2所述的方法，其中，在所述值表示所述数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户包括：
    由第一分析功能向统一数据管理功能发出查询请求，以确认由客户ID表示的客户是否为已签约客户。
  4. 根据权利要求1或2所述的方法，其中，在所述值表示所述数据分析请求是客户自主分析请求的情况下，由第一分析功能确认由客户ID表示的客户是否为已签约客户包括：
    由第一分析功能参考事先存储在第一分析功能中的客户的签约信息，以确认由客户ID表示的客户是否为已签约客户。
  5. 根据权利要求1所述的方法，其中，第一分析功能从网络存储库功能查询与所述签约信息对应的为所述客户提供服务的网元。
  6. 根据权利要求1所述的方法，其中，
    第二分析功能位于所述客户自己的设备处，或者
    第二分析功能位于网络运营商的设备中，但是在逻辑上与网络运营商的其他功能分离并且独立。
  7. 根据权利要求1-6任意一项所述的方法，其中，第二分析功能包含已经由所述客户自主地基于运营商数据和客户的业务数据训练的智能模型。
  8. 根据权利要求7所述的方法，其中，第二分析功能包含多个所述智能模型，并且所述数据分析请求还包含要使用的第二分析功能中的智能模型的地址，以及
    根据所述地址将收集到的运营商数据发送给第二分析功能包括：
    将智能模型的地址发送给第二分析功能，以由第二分析功能中的由智能模型的地址表示的智能模型进行数据分析。
  9. 根据权利要求7所述的方法，其中，第二分析功能是网络数据分析功能或人工智能系统。
  10. 根据权利要求1-9任意一项所述的方法，其中，第一分析功能为网络数据分析功能。
  11. 根据权利要求1-10任意一项所述的方法，其中，为所述客户提供服务的网元包括接入和移动性管理功能和会话管理功能中的至少一个。
  12. 一种业务数据的客户自主分析装置，包括：被配置为执行根据权利要求1至11中的任一项所述的方法的模块。
  13. 一种业务数据的客户自主分析装置，包括：
    存储器，其上存储有指令；以及
    处理器，被配置为执行存储在所述存储器上的指令，以执行根据权利要求1至11中的任一项所述的方法。
  14. 一种计算机可读存储介质，包括计算机可执行指令，所述计算机可执行指令在由一个或多个处理器执行时，使得所述一个或多个处理器执行根据权利要求1至11中的任意一项所述的方法。
PCT/CN2022/124278 2021-11-29 2022-10-10 客户自主分析方法、装置以及介质 WO2023093320A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111429668.4A CN116227943A (zh) 2021-11-29 2021-11-29 客户自主分析方法、装置以及介质
CN202111429668.4 2021-11-29

Publications (1)

Publication Number Publication Date
WO2023093320A1 true WO2023093320A1 (zh) 2023-06-01

Family

ID=86538827

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/124278 WO2023093320A1 (zh) 2021-11-29 2022-10-10 客户自主分析方法、装置以及介质

Country Status (2)

Country Link
CN (1) CN116227943A (zh)
WO (1) WO2023093320A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111083722A (zh) * 2019-04-15 2020-04-28 中兴通讯股份有限公司 模型的推送、模型的请求方法及装置、存储介质
WO2021062740A1 (zh) * 2019-09-30 2021-04-08 华为技术有限公司 一种确定设备信息的方法、装置以及系统
US20210144071A1 (en) * 2019-11-07 2021-05-13 Verizon Patent And Licensing Inc. Systems and methods for network analytics service automation
CN113573331A (zh) * 2020-04-29 2021-10-29 华为技术有限公司 一种通信方法、装置及系统
US20210345158A1 (en) * 2018-09-20 2021-11-04 Telefonaktiebolaget Lm Ericsson (Publ) A Method of Managing Traffic by a User Plane Function, UPF, Corresponding UPF, Session Management Function and Network Data Analytics Function

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210345158A1 (en) * 2018-09-20 2021-11-04 Telefonaktiebolaget Lm Ericsson (Publ) A Method of Managing Traffic by a User Plane Function, UPF, Corresponding UPF, Session Management Function and Network Data Analytics Function
CN111083722A (zh) * 2019-04-15 2020-04-28 中兴通讯股份有限公司 模型的推送、模型的请求方法及装置、存储介质
WO2021062740A1 (zh) * 2019-09-30 2021-04-08 华为技术有限公司 一种确定设备信息的方法、装置以及系统
US20210144071A1 (en) * 2019-11-07 2021-05-13 Verizon Patent And Licensing Inc. Systems and methods for network analytics service automation
CN113573331A (zh) * 2020-04-29 2021-10-29 华为技术有限公司 一种通信方法、装置及系统

Also Published As

Publication number Publication date
CN116227943A (zh) 2023-06-06

Similar Documents

Publication Publication Date Title
US10884825B2 (en) Application programming interface (API) service apparatus and application programming interface (API) service system
US20190266287A1 (en) Bot networks
US20170103053A1 (en) Structured touch screen interface for mobile forms generation for customer relationship management (crm)
US20130275229A1 (en) Apparatus and method for universal personal data portability
CN107133309B (zh) 流程实例的存储、查询方法及装置、存储介质及电子设备
US20180184289A1 (en) Facilitation of user authentication using mobile devices
CN105701122A (zh) 一种日志收集方法、装置及系统
TWI727501B (zh) 無線通訊核心網路與在其中分析用戶設備移動的方法
WO2017041562A1 (zh) 一种识别终端设备用户身份的方法和装置
KR20180052527A (ko) 전화번호의 소유권을 검증하고 소유권 재할당을 트래킹하기 위한 시스템들 및 방법들
CN107103011B (zh) 终端数据搜索的实现方法和装置
CN107181755B (zh) 一种办公平台的身份识别方法、装置及系统
CN112202598B (zh) 一种日志记录方法及装置
CN111694866A (zh) 数据搜索及存储方法、数据搜索系统、装置、设备及介质
TW202032466A (zh) 用戶年齡預測方法、裝置及設備
Zeppenfeld et al. A hybrid neural network, dynamic programming word spotter
US10810099B2 (en) Cognitive in-memory API logging
CN111586177B (zh) 集群会话防丢失方法及系统
CN111783415A (zh) 模板配置方法以及装置
WO2017088347A1 (zh) 基于云平台的应用用户使用信息管理的方法、设备及系统
WO2023093320A1 (zh) 客户自主分析方法、装置以及介质
WO2021012554A1 (zh) 区块链中数据字段的更新方法、装置、介质、电子设备
US20130275409A1 (en) Apparatus and method for universal personal data portability
US20220147645A1 (en) Method, apparatus, and system for discovering private data using configurable rules
CN110011807A (zh) 一种关键信息维护方法及系统

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: 22897405

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE