WO2023217026A1 - 业务处理方法、设备及可读存储介质 - Google Patents
业务处理方法、设备及可读存储介质 Download PDFInfo
- Publication number
- WO2023217026A1 WO2023217026A1 PCT/CN2023/092471 CN2023092471W WO2023217026A1 WO 2023217026 A1 WO2023217026 A1 WO 2023217026A1 CN 2023092471 W CN2023092471 W CN 2023092471W WO 2023217026 A1 WO2023217026 A1 WO 2023217026A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- network device
- model
- request message
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/02—Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
Definitions
- This application belongs to the field of communication technology, and specifically relates to a business processing method, equipment and readable storage medium.
- 5G drives the Internet of Everything, and all kinds of data have exploded.
- 3GPP 3rd Generation Partnership Project
- 3GPP 3rd Generation Partnership Project
- a large amount of information circulates, and data privacy within the network cannot be protected.
- Embodiments of the present application provide a business processing method, equipment, and a readable storage medium, which can solve the problem that the privacy of data within the network cannot be protected when providing internal network data to third-party applications.
- the first aspect provides a business processing method, including:
- the first network device receives a first request message sent by the second network device, where the first request message is used to request privacy protection for the target service;
- the first network device determines model training related information according to the first request message
- the first network device obtains sample data
- the first network device performs model training based on the sample data and the model training related information to obtain a target model, and the target model is used to protect the privacy of the data required by the target business;
- the first network device sends first information to the second network device, where the first information is used in response to the first request message.
- the second aspect provides a business processing method, including:
- the second network device sends a first request message to the first network device, where the first request message is used to request privacy protection for the target service;
- the second network device receives the first information sent by the first network device, and the first information is used to respond to the first request message.
- a business processing device including:
- the first receiving module is configured to receive a first request message sent by the second network device, where the first request message is used to Request privacy protection for the target business;
- a first determination module configured to determine model training related information according to the first request message
- a training module configured to perform model training based on the sample data and the model training related information to obtain a target model, where the target model is used to protect the privacy of the data required by the target business;
- the first sending module is configured to send first information to the second network device, where the first information is used to respond to the first request message.
- a business processing device including:
- a second sending module configured to send a first request message to the first network device, where the first request message is used to request privacy protection for the target service;
- the second receiving module is configured to receive the first information sent by the first network device, where the first information is used to respond to the first request message.
- a network side device in a fifth aspect, includes a processor and a memory.
- the memory stores programs or instructions that can be run on the processor.
- the program or instructions are executed by the processor.
- a network side device including a processor and a communication interface, wherein the communication interface is used for a first network device to receive a first request message sent by a second network device, and the first request message is used to request privacy protection for the target service; the processor is used for the first network device to determine model training related information according to the first request message; the communication interface is used for the first network device to obtain Sample data; the processor is configured to: the first network device performs model training according to the sample data and the model training related information to obtain a target model, and the target model is used to perform data on the target business requirements. Privacy protection: the communication interface is used for the first network device to send first information to the second network device, and the first information is used to respond to the first request message.
- a network side device in a seventh aspect, includes a processor and a memory.
- the memory stores programs or instructions that can be run on the processor.
- the program or instructions are executed by the processor.
- a network side device including a processor and a communication interface, wherein the communication interface is used for the second network device to send a first request message to the first network device, and the first request message is In order to request privacy protection for the target service, the second network device receives the first information sent by the first network device, and the first information is used to respond to the first request message.
- a readable storage medium is provided. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method are implemented as described in the first aspect. The steps of the method described in the second aspect.
- a chip in a tenth aspect, includes a processor and a communication interface.
- the communication interface is coupled to the processor.
- the processor is used to run programs or instructions to implement the method described in the first aspect. steps, or Implement the steps of the method as described in the second aspect.
- a computer program/program product is provided, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the first aspect The steps of the method, or the steps of implementing the method as described in the second aspect.
- the second network device requests the first network device to perform privacy protection on the target service.
- the first network device performs model training based on the determined model training related information and the obtained sample data, and obtains A target model for privacy processing of data required by target business needs.
- the network provides internal network data to third-party applications, it can perform privacy processing on the data through the target model, so that the privacy of internal network data is protected.
- Figure 1 is a block diagram of a wireless communication system provided by an embodiment of the present application.
- FIG. 2 is one of the flow diagrams of the business processing method provided by the embodiment of the present application.
- Figure 3 is the second schematic flow chart of the business processing method provided by the embodiment of the present application.
- Figure 4a is one of the flow diagrams of an implementation example provided by the embodiment of this application.
- Figure 4b is the second schematic flow diagram of an implementation example provided by the embodiment of the present application.
- Figure 5 is one of the structural schematic diagrams of the business processing device provided by the embodiment of the present application.
- Figure 6 is the second structural schematic diagram of the business processing device provided by the embodiment of the present application.
- Figure 7 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
- Figure 8 is a schematic structural diagram of a network-side device provided by an embodiment of the present application.
- first, second, etc. in the description and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and that "first" and “second” are distinguished objects It is usually one type, and the number of objects is not limited.
- the first object can be one or multiple.
- “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the related objects are in an "or” relationship.
- LTE Long Term Evolution
- LTE-Advanced, LTE-A Long Term Evolution
- CDMA Code Division Multiple Access
- TDMA Time Division Multiple Access
- FDMA Frequency Division Multiple Access
- OFDMA Orthogonal Frequency Division Multiple Access
- SC-FDMA Single-carrier Frequency Division Multiple Access
- NR New Radio
- FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application are applicable.
- the wireless communication system includes a terminal 11 and a network side device 12.
- the terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a palmtop computer, a netbook, or a super mobile personal computer.
- Tablet Personal Computer Tablet Personal Computer
- laptop computer laptop computer
- PDA Personal Digital Assistant
- PDA Personal Digital Assistant
- UMPC ultra-mobile personal computer
- UMPC mobile Internet device
- MID mobile Internet Device
- AR augmented reality
- VR virtual reality
- robots wearable devices
- WUE Vehicle User Equipment
- PUE Pedestrian User Equipment
- smart home home equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.
- game consoles personal computers (personal computer, PC), teller machine or self-service machine and other terminal-side devices.
- Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets) bracelets, smart anklets, etc.), smart wristbands, smart clothing, etc.
- the network side device 12 may include an access network device or a core network device, where the access network device may also be called a radio access network device, a radio access network (Radio Access Network, RAN), a radio access network function or a wireless device.
- Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points, Wireless Fidelity (WiFi) nodes, etc.
- the base station may be called a Node B, an Evolved Node B (eNB), or an access point.
- BTS Base Transceiver Station
- BSS Basic Service Set
- ESS Extended Service Set
- TRP Transmitting Receiving Point
- the base station is not limited to specific technical terms. It should be noted that in this application, in the embodiment, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.
- Core network equipment may include but is not limited to at least one of the following: core network nodes, core network functions, mobility management entities (Mobility Management Entity, MME), access mobility management functions (Access and Mobility Management Function, AMF), session management functions (Session Management Function, SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Service Discovery function (Edge Application Server Discovery Function, EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration ( Centralized network configuration (CNC), network storage function (Network Repository Function, NRF), network opening function (Network Exposure Function (NEF), local NEF (Local NEF, or L-NEF), binding support function (Binding Support Function, BSF), application function (Application Function, AF), etc.
- MME mobility management entities
- AMF Access and Mobility Management Function
- SMF Session Management Function
- UPF User Plane Function
- NEF Network Exposure Function
- NEF is a network element within 3GPP that interacts with third parties authorized by 3GPP through specific interfaces.
- the specific capabilities of the 5G network that can be exposed to the outside include:
- Monitoring capability used to monitor specific events of UE in the 5G system and expose these monitoring event information externally through NEF. Monitoring events mainly include UE location, reachability, roaming status and connection status, etc.;
- Security reporting capabilities Including identity authentication, authorization control, network defense and other services, or third-party applications manage authorized slices to configure and adjust network security capabilities.
- the current 3GPP network can only exchange information with third parties through NEF.
- the information exchanged between 3GPP and third parties is not sufficient, so that a large amount of useful information cannot be effectively circulated, and the value of the data cannot be reflected.
- a large amount of information is circulated, it is not clear how data privacy within the network can be protected.
- an embodiment of the present application provides a service processing method.
- the execution subject of the method is a first network device.
- the first network device refers to a device that has certain analysis, calculation and artificial intelligence (AI) capabilities within 3GPP.
- the network element with the training capability can be an existing 3GPP network element or a newly added network element, which is used to protect the privacy of 3GPP internal data.
- the first network device can be referred to as a network entity for short;
- Methods include:
- Step 201 The first network device receives a first request message sent by the second network device.
- the first request message is used to request privacy protection for a target service.
- the target service may also be called a privacy protection service;
- Step 202 The first network device determines model training related information according to the first request message
- Step 203 The first network device obtains sample data
- Step 204 The first network device performs model training based on the sample data and model training related information to obtain a target model.
- the target model is used to protect the privacy of data required by the target business.
- the target model can also be called a target algorithm, a privacy processing method, Privacy processing algorithms, etc.;
- Step 205 The first network device sends the first information to the second network device, and the first information is used to respond to the first request message.
- the above-mentioned second network device is a third-party network element authorized by 3GPP, and may be an application function (Application Function, AF) entity, for example.
- AF Application Function
- the second network device requests the first network device to perform privacy protection on the target service.
- the first network device performs model training based on the determined model training related information and the obtained sample data, and obtains A target model for privacy processing of data required by target business needs.
- the network provides in-network When collecting external data, the data can be processed privately through the target model to protect the privacy of data within the network.
- using the methods of the embodiments of this application can allow more types of internal network data to interact with third parties while ensuring privacy and security, thereby enabling 3GPP and third parties to interact with a large amount of data and increase the value of the data.
- the first network device receiving the first request message sent by the second network device includes: the first network device receiving the first request message sent by the second network device through the third network device;
- the first network device sending the first information to the second network device includes: the first network device sending the first information to the second network device through the third network device;
- the target business is an authorized business.
- the above-mentioned third network device is a 3GPP information exposure network element, which refers to a network element within 3GPP that has the function of information exchange and authorization with a third party. It can be an existing 3GPP network element or a newly added network element, such as a third-party network element. Network devices can be NEF entities.
- the above target service is an authorized service, which specifically means that when the second network device requests privacy protection for the target service from the first network device, the third network device first determines whether the target service is authorized, that is, the second network device may Unauthorized services will be requested, but can be judged and filtered by the third network device; specifically: the third network device verifies the first request information based on the preconfigured privacy service contract, and determines whether the second network device Authorized to obtain privacy services. If it is determined that the target service is authorized, subsequent operations will be performed.
- Embodiment 1 The first network device determines parameters related to model training based on the business requirements provided by the second network device, collects sample data within 3GPP and performs model training locally to obtain the target model;
- the first request message includes one or more of the following:
- the identification of the second network device which may be AF ID, for example;
- the identification of the target service that is, the privacy protection service ID
- the privacy protection service ID is "beam management optimization”, “user location recommendation”, “UE fitness probability estimation” wait;
- Privacy protection level defined by 3GPP.
- the intensity of protection and exposed content of each level are different.
- the definition principle can be that the higher the level, the fewer the original data features are exposed and the higher the processing complexity.
- the privacy protection level can be related to the basic model and sample features used in model training. For example, the higher the level, the more complex the sample feature extraction method and the greater the number of samples. Correspondingly, the effect of the trained model on privacy protection is The better;
- Model performance information used to indicate the termination conditions of model training, including convergence conditions, iteration performance or model accuracy evaluation, etc.
- the first network device determines model training related information according to the first request message, including:
- the first network device determines model training related information according to the first request message
- the above-mentioned first preset condition refers to the first network device parsing the first request message to determine model training related information. prerequisites.
- the first preset condition includes one or more of the following:
- the target business operates based on privacy data, that is, the data required by the privacy protection business is private data, such as the implementation of privacy data within the terminal or 3GPP;
- Implementation Mode 2 Based on the model training related parameters provided by the second network device, the first network device collects sample data within 3GPP and performs model training locally to obtain a privacy processing method;
- the first request message includes one or more of the following:
- the identification of the second network device which may be AF ID, for example;
- the identification of the target service that is, the privacy protection service ID
- the privacy protection service ID is "beam management optimization”, “user location recommendation”, “UE fitness probability estimation” wait;
- Privacy protection level defined by 3GPP.
- the intensity of protection and exposed content of each level are different.
- the definition principle can be that the higher the level, the fewer the original data features are exposed and the higher the processing complexity; specifically, privacy protection
- the level can be related to the basic model and sample features used in model training. For example, the higher the level, the more complex the sample feature extraction method and the greater the number of samples. Correspondingly, the trained model is better at privacy protection.
- the relevant information of the target model refers to the relevant description of the privacy processing method, which is used to specify the basic training method adopted for privacy processing;
- the relevant information of the target model includes one or more of the following:
- Model training instruction information used to instruct the first network device to perform model training, that is, used to indicate that privacy protection services need to obtain privacy processing methods through model training;
- Model training configuration information used to limit the model training configuration such as the basic model used.
- model training configuration information includes one or more of the following:
- Model type information (or model identification information), such as model ID, etc., is used to indicate the basic model used by the first network device. That is, it is used to instruct network entities what basic model to use for model training, such as using heterogeneous neural networks, decision trees, etc.;
- Model configuration information is used to instruct the first network device to configure parameters for the basic model used when performing model training, that is, to instruct network entities to use a certain model. More specific parameters are needed for model training to define higher-level concepts for the basic model used, such as defining the complexity and learning capabilities of the basic model.
- Model configuration information can include, for example, the number of hidden layers for heterogeneous neural networks. , for the tree depth, number of trees, split points, etc. of the decision tree;
- Model performance information used to indicate the termination conditions of model training, including convergence conditions, iteration performance or model accuracy evaluation, etc.;
- Sample data requirement information including sample type, sample quantity, sample timeliness, sample range, sample collection method, etc.
- the first network device determines model training related information according to the first request message, including:
- the first network device determines model training related information according to the first request message
- the above-mentioned second preset condition refers to a prerequisite for the first network device to parse the first request message to determine model training related information.
- the second preset condition includes one or more of the following:
- the first request message includes model training instruction information
- the target business operates based on privacy data, that is, the data required by the privacy protection business is private data, such as the implementation of privacy data within the terminal or 3GPP;
- the associated data of the same UE in different domains that is, the MM related data generated by the same UE in the CN, the location data generated in the RAN, and the business experience data generated by third-party services, are trained using samples with different characteristics. The modeling effect of increased features can be achieved.
- the model training related information includes one or more of the following:
- Basic model information used to indicate the basic model used by the first network device when performing model training.
- the network entity may parse the first request message and analyze the complex steps to complete the task. degree, required data, etc., and then selects a suitable basic model from the model library that can complete the task; corresponding to the second embodiment above, the network entity selects a model from the model library as the model based on the model type information in the first request message.
- Basic model for training
- Model configuration information is used to instruct the first network device to configure parameters for the basic model used when performing model training, that is, to instruct the network entity to use a certain model for model training. More specific parameters are needed during training to define higher-level concepts for the basic model used, such as defining the complexity and learning capabilities of the basic model.
- the model configuration information can include, for example, the number of hidden layers for heterogeneous neural networks, and the number of hidden layers for heterogeneous neural networks. The tree depth, number of trees, split points, etc. of the decision tree;
- Termination condition information of model training which is used to indicate that model training can be stopped when it reaches a certain level, such as model convergence conditions, model accuracy or the number of iterations of the model, etc.
- the network entity determines based on the model performance information in the first request message.
- the first network device obtains sample data, including:
- the first network device determines the sample data type and sample data source based on the second information
- the first network device obtains sample data according to the sample data type and sample data source
- the second information is the sample data request information in the first request message, or the second information is experience information of model training.
- the second information may also include a privacy protection level.
- the privacy protection level can be related to the basic model and sample features used in model training. For example, the higher the level, the more complex the sample feature extraction method and the greater the number of samples. Correspondingly, the effect of the trained model on privacy protection is The better.
- the first network device can determine the sample data type and sample data source according to the experience information of model training and/or the privacy protection level.
- the sample data source can be a terminal or a network element in the core network.
- Various network functions Network Functions, NFs)), such as Authentication Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF), etc.;
- the first network device can determine the sample data type and sample data source according to the sample data requirement information and/or privacy protection level in the first request message, or the first network device can determine the sample data type and source according to the experience of model training.
- the level of information and/or privacy protection determines the sample data type and sample data source.
- UE location terminal location
- beam angles beam angles
- RAN Location Service
- sample collection process includes the following steps:
- the network entity issues a sample collection request to each sample source.
- the sample collection request may include the sample data type.
- the sample collection request may include the data requirements in the privacy protection service request. At least one of the following: sample type, sample quantity, sample timeliness, sample scope, sample collection method, etc.
- Each sample source collects samples according to the information in the sample collection request, for example, collecting the number of times UE1 goes to the gym between 18:00 and 20:00 every Tuesday and Thursday afternoon.
- Each sample source reports sample data, which may be the result of processing by the sample source.
- the first information includes one or more of the following:
- the timeliness information of the target model is used to indicate the validity time of the target model, that is, the validity time of the trained model corresponding to the privacy protection service. Beyond this time, the 3GPP network Training needs to be performed again when the same privacy service request is received again;
- the identification information of the target model is used to identify the model generated in this privacy protection business training, that is, a specific model, such as a heterogeneous neural network, decision tree, etc.
- the above-mentioned first information may specifically be a model instance ID (model instance ID), which may be used to identify a model training task.
- model instance ID model instance ID
- the method further includes:
- the first network device stores an association relationship between the first information, the identifier of the second network device, and the identifier of the target service.
- the first network device associates the first information, the identifier of the second network device and the identifier of the target service, so that the first network device can later provide privacy protection data for the privacy protection service requested by the second network device.
- the network entity has model instance ID 1, privacy protection service ID 1 and AF ID 1.
- the model is still valid and AF1 requests privacy protection service ID 1
- the network entity directly uses model instance ID 1 to provide privacy protection service for AF 1.
- an embodiment of the present application provides a service processing method.
- the execution subject of the method is a second network device.
- the second network device is a third-party network element authorized by 3GPP, and may be an AF entity, for example.
- Methods include:
- Step 301 The second network device sends a first request message to the first network device, where the first request message is used to request privacy protection for the target service;
- Step 302 The second network device receives the first information sent by the first network device, and the first information is used to respond to the first request message.
- the second network device sends a first request message to the first network device, including:
- the second network device sends the first request message to the first network device through the third network device;
- the second network device receives the first information sent by the first network device, including:
- the second network device receives the first information sent by the first network device through the third network device;
- the target business is an authorized business.
- the above-mentioned third network device is a 3GPP information exposure network element, which refers to a network element within 3GPP that has the function of information exchange and authorization with a third party. It can be an existing 3GPP network element or a newly added network element, such as a third-party network element. Network devices can be NEF entities.
- the above target service is an authorized service, which specifically means that when the second network device requests privacy protection for the target service from the first network device, the third network device first determines whether the target service is authorized, that is, the second network device may Unauthorized services will be requested, but can be judged and filtered by the third network device; specifically: the third network device verifies the first request information based on the preconfigured privacy service contract, and determines whether the second network device Authorized to obtain privacy services. If it is determined that the target service is authorized, subsequent operations will be performed.
- Embodiment 1 The first network device determines parameters related to model training based on the business requirements provided by the second network device, collects sample data within 3GPP and performs model training locally to obtain the target model;
- the first request message includes one or more of the following:
- the identification of the second network device which may be AF ID, for example;
- the identification of the target service that is, the privacy protection service ID
- the privacy protection service ID is "beam management optimization”, “user location recommendation”, “UE fitness probability estimation” wait;
- Privacy protection level defined by 3GPP.
- the intensity of protection and exposed content of each level are different. Definition The principle can be that the higher the level, the fewer original data features are exposed and the higher the processing complexity; specifically, the privacy protection level can be related to the basic model and sample features used in model training. For example, the higher the level, the sample feature extraction method The more complex it is, the greater the number of samples, and correspondingly, the trained model will be better at privacy protection;
- Model performance information used to indicate the termination conditions of model training, including convergence conditions, iteration performance or model accuracy evaluation, etc.
- Implementation Mode 2 Based on the model training related parameters provided by the second network device, the first network device collects sample data within 3GPP and performs model training locally to obtain a privacy processing method;
- the first request message includes one or more of the following:
- the identification of the second network device which may be AF ID, for example;
- the identification of the target service that is, the privacy protection service ID
- the privacy protection service ID is "beam management optimization”, “user location recommendation”, “UE fitness probability estimation” wait;
- the relevant information of the target model refers to the relevant description of the privacy processing method, which is used to specify the basic training method adopted for privacy processing;
- the relevant information of the target model includes one or more of the following:
- Model training instruction information used to instruct the first network device to perform model training, that is, used to indicate that privacy protection services need to obtain privacy processing methods through model training;
- Model training configuration information used to limit the model training configuration such as the basic model used.
- model training configuration information includes one or more of the following:
- Model type information (or model identification information), such as model ID, etc., is used to indicate the basic model used by the first network device, that is, used to indicate what basic model the network entity uses for modeling. Training, such as using heterogeneous neural networks, decision trees, etc.;
- Model configuration information is used to instruct the first network device to configure parameters for the basic model used when performing model training, that is, to instruct network entities to use a certain model. More specific parameters are needed for model training to define higher-level concepts for the basic model used, such as defining the complexity and learning capabilities of the basic model.
- Model configuration information can include, for example, the number of hidden layers for heterogeneous neural networks. , for the tree depth, number of trees, split points, etc. of the decision tree;
- Model performance information used to indicate the termination conditions of model training, including convergence conditions, iteration performance or model accuracy evaluation, etc.;
- Sample data requirement information including sample type, sample quantity, sample timeliness, sample range, sample collection method, etc.
- the first information includes one or more of the following:
- the timeliness information of the target model is used to indicate the validity time of the target model, that is, the validity time of the trained model corresponding to the privacy protection service. Beyond this time, the 3GPP network will again Training needs to be performed again when receiving the same privacy service request;
- the identification information of the target model is used to identify the model generated in this privacy protection business training, that is, specific models such as heterogeneous neural networks, decision trees, etc.
- the above-mentioned first information may specifically be a model instance ID (model instance ID), which may be used to identify a model training task.
- model instance ID model instance ID
- Example 1 The network entity determines the parameters related to model training based on the business requirements provided by AF, collects sample data within 3GPP and performs model training locally to obtain the privacy processing method;
- AF is a third-party network element authorized by 3GPP;
- network entity refers to a network element within 3GPP that has certain analysis, computing and AI training capabilities. It can be an existing network element of 3GPP or a new network element. Used to protect the privacy of 3GPP internal data;
- 3GPP information exposure network elements refer to network elements within 3GPP that have the function of information interaction and authorization with third parties. They can be existing 3GPP network elements or new network elements.
- NEF NEF
- NFs refers to network elements in the core network, which can be AMF, SMF, PCF, etc. The specific network element is analyzed by the network entity using the demand information provided by AF.
- the AF sends a privacy protection service request to the 3GPP network entity.
- the request information includes at least one of the following:
- AF identification such as AF ID
- Privacy protection level defined by 3GPP.
- the intensity of protection and exposed content of each level are different. The principle is that the higher the level, the fewer the original data features are exposed and the higher the processing complexity.
- the privacy protection level can be related to the basic model and sample features used in model training. For example, the higher the level, the more complex the sample feature extraction method and the greater the number of samples. Correspondingly, the effect of the trained model on privacy protection is The better.
- Model performance used to indicate the termination conditions of model training, including convergence conditions, iteration performance or model accuracy evaluation, etc.
- NEF uses the AF identifier to query the privacy protection service list contracted by AF to determine whether the privacy protection service requested by AF is authorized.
- NEF transparently forwards the privacy protection service request message to the network entity.
- the network entity parses the privacy protection service request, including:
- the network entity determines that training is needed to obtain the privacy processing method, and the factors that determine the need for training include at least one of the following:
- the data required by the privacy protection business is private data, such as the implementation of private data within the terminal or 3GPP;
- the data required by privacy protection services have the same sample but different characteristics.
- the associated data of the same UE in different domains that is, the MM related data generated by the same UE in the CN, the location data generated in the RAN, in the third Business experience data generated by third-party services.
- the network entity analyzes the privacy protection business requirements and determines them based on the empirical information of model training and/or the privacy protection level.
- the network entity determines model training related information, including the following:
- the network entity parses the privacy protection request, analyzes the complexity of completing the task, the data required, etc., and selects an appropriate basic model from the model library that can complete the task.
- Model configuration information used to indicate the parameters configured by the first network device for the basic model used when performing model training, that is, used to specify more detailed information during the model training process, thereby defining the basic model used.
- Higher-level concepts such as defining the complexity of the basic model, learning capabilities, and model configuration information can include, for example, the number of hidden layers for heterogeneous neural networks, tree depth, number of trees, split points, etc. for decision trees.
- Network entities are determined based on the determined basic model and model training historical experience information.
- Termination conditions for model training used to indicate that model training can be stopped when it reaches a certain level, such as model convergence conditions or model accuracy.
- the number of iterations of the model, etc. The network entity determines based on the preconfiguration in the privacy protection service agreement or the model performance in the privacy protection service request.
- Sample collection process includes the following steps:
- the network entity issues sample collection requests to each sample source based on the sample data requirements and sample sources determined in step 4.
- Each sample source collects samples according to the information in the sample collection request, for example, collecting the number of times UE1 goes to the gym between 18:00 and 20:00 every Tuesday and Thursday afternoon.
- Each sample source reports sample data, which may be the result of processing by the sample source.
- the network entity uses the collected data to train the model.
- the network entity performs a local training process based on the obtained sample data and the model training related parameters determined in step 4 until the trained model reaches the termination condition of model training.
- the network entity generates a model instance ID for privacy protection business training, which is used to indicate relevant information of this model training, including at least one of the following information:
- Network entity related information which may include network entity ID, name information, etc.
- Model timeliness including model generation time and validity duration, is used to indicate the validity time of the trained model corresponding to the privacy protection service. Beyond this time, the 3GPP network needs to receive the same privacy service request again. Training again.
- Model identification information used to identify the model generated in this privacy protection business training.
- the network entity associates the model instance ID, privacy protection service ID and AF ID for subsequent network use.
- the network entity provides privacy protection data for the privacy protection service requested by the corresponding AF.
- the network entity has model instance ID 1, privacy protection service ID 1 and AF ID 1.
- AF1 requests privacy protection.
- the service ID is 1, the network entity directly uses model instance ID 1 to provide privacy protection services for AF 1.
- the network entity returns a confirmation message to AF through NEF, including the model instance ID.
- Example 2 Based on the model training related parameters provided by AF, the network entity collects sample data within 3GPP and performs model training locally to obtain the privacy processing method;
- AF is a third-party network element authorized by 3GPP;
- network entity refers to a network element within 3GPP that has certain analysis, computing and AI training capabilities. It can be an existing network element of 3GPP or a new network element. Used to protect the privacy of 3GPP internal data;
- 3GPP information exposure network elements refer to network elements within 3GPP that have the function of information interaction and authorization with third parties. They can be existing 3GPP network elements or new network elements.
- NEF NEF
- NFs refers to network elements in the core network, which can be AMF, SMF, PCF, etc. The specific network element is analyzed by the network entity using the demand information provided by AF.
- the AF sends a privacy protection service request to the 3GPP network entity.
- the request information includes at least one of the following:
- AF identification such as AF ID
- Privacy protection level defined by 3GPP.
- the intensity of protection and exposed content of each level are different. The principle is that the higher the level, the fewer the original data features are exposed and the higher the processing complexity.
- the privacy protection level can be related to the basic model and sample features used in model training. For example, the higher the level, the more complex the sample feature extraction method and the greater the number of samples. Correspondingly, the effect of the trained model on privacy protection is The better.
- Model training instructions used to indicate that the privacy protection business needs to obtain privacy protection processing methods through model training
- Model training configuration information used to limit the basic models used, etc., including at least one of the following:
- Model type information (or called model identification information), such as model ID, etc., is used to indicate the basic model used by the first network device, that is, used to indicate what basic model the network entity uses for model training. , including heterogeneous neural networks, decision trees, etc.;
- Model configuration information is used to instruct the first network device to configure parameters for the basic model used when performing model training, that is, used to instruct network entities to use a certain basic model. More specific parameters are required for model training to define higher-level concepts for the basic model used, such as defining the complexity and learning capabilities of the basic model.
- Model configuration information can include, for example, the number of hidden layers for heterogeneous neural networks, For the tree depth, number of trees, split points, etc. of the decision tree;
- NEF uses the AF identifier to query the privacy protection service list contracted by AF to determine whether the privacy protection service requested by AF is authorized.
- NEF transparently forwards the privacy protection service request message to the network entity.
- the network entity determines that it needs to perform a training process to obtain the privacy processing method.
- the factors that determine the need for training to obtain privacy processing methods by the network entity include at least one of the following:
- the privacy protection service request includes model training instructions
- the data requested by the privacy protection service is private data, such as the implementation of private data within the terminal or 3GPP;
- the data requested by the privacy protection service have the same sample but different characteristics.
- the associated data of the same UE in different domains that is, the MM related data generated by the same UE in the CN, the location data generated in the RAN, in the Business experience data generated by third-party services.
- the network entity determines model training related information, including the following:
- Basic model the network entity selects a model from the model library as the basic model for training based on the model information or identification information in the privacy protection request.
- Model configuration information used to indicate the parameters configured by the first network device for the basic model used when performing model training, that is, used to specify more detailed information during the model training process, thereby defining the basic model used.
- Higher-level concepts such as defining the complexity of the basic model, learning capabilities, and model configuration information can include, for example, the number of hidden layers for heterogeneous neural networks, tree depth, number of trees, split points, etc. for decision trees.
- the network entity is determined based on the model configuration information in the privacy protection request.
- Termination conditions for model training used to indicate that model training can be stopped when it reaches a certain level, such as model convergence conditions or model accuracy.
- the number of iterations of the model, etc. Network entities are determined based on model performance in privacy protection requests.
- the basis for determination includes the following:
- the network entity makes recommendations based on the data requirements in the privacy protection service request.
- the network entity is based on the experience information and/or privacy protection level of model training.
- Sample collection process includes the following steps:
- the network entity issues sample collection requests to each sample source, including at least one of the data requirements in the privacy protection business request: sample type, sample quantity, sample aging, sample range, sample collection method, etc.
- Each sample source collects samples according to the information in the sample collection request, for example, collecting the number of times UE1 goes to the gym between 18:00 and 20:00 every Tuesday and Thursday afternoon.
- Each sample source reports sample data, which may be the result of processing by the sample source.
- the network entity uses the collected data to train the model.
- the network entity performs a local training process based on the obtained sample data and the model training related parameters determined in step 4 until the trained model reaches the termination condition of model training.
- the network entity generates a model instance ID for privacy protection business training, which is used to indicate relevant information of this model training, including at least one of the following information:
- Network entity related information which may include network entity ID, name information, etc.
- Model timeliness including model generation time and validity duration, is used to indicate the validity time of the trained model corresponding to the privacy protection service. Beyond this time, the 3GPP network needs to receive the same privacy service request again. Training again.
- Model identification information used to identify the model generated in this privacy protection business training.
- the network entity associates the model instance ID, privacy protection service ID and AF ID, which is used by the network entity to provide privacy protection data for the privacy protection service requested by the corresponding AF.
- the network entity has model instance ID 1, privacy protection Business ID 1 and AF ID 1, when the timeliness of the model is still valid, when AF1 requests the privacy protection service ID 1, the network entity directly uses the model instance ID 1 to provide the privacy protection service for AF 1.
- the network entity returns a confirmation message to AF through NEF, including the model instance ID.
- the execution subject may be a business processing device.
- the business processing device executing the business processing method is taken as an example to illustrate the business processing device provided by the embodiment of the present application.
- an embodiment of the present application provides a service processing device 500.
- the service processing device 500 may be the first network device in the above method side description.
- the business processing device 500 includes:
- the first receiving module 501 is used to receive the first request message sent by the second network device, where the first request message is used to request privacy protection for the target service;
- the first determination module 502 is used to determine model training related information according to the first request message
- the training module 504 is used to perform model training based on sample data and model training related information to obtain a target model.
- the target model is used to protect the privacy of data required by target business needs;
- the first sending module 505 is configured to send first information to the second network device, where the first information is used to respond to the first request message.
- the first receiving module is used for:
- the first sending module is used for:
- the target business is an authorized business.
- the first request message includes one or more of the following:
- the first request message includes one or more of the following:
- the relevant information of the target model includes one or more of the following:
- Model training instruction information used to instruct the business processing device to perform model training
- model training configuration information includes one or more of the following:
- Model type information used to indicate the basic model used by the business processing device
- Model configuration information used to instruct the business processing device to configure parameters for the basic model used when performing model training
- the first determination module is used for:
- the first preset condition includes one or more of the following:
- the target business operates based on private data
- the data meeting the target business requirements have the same samples but different characteristics.
- the first determination module is used for:
- the second preset condition includes one or more of the following:
- the first request message includes model training instruction information
- the target business operates based on private data
- the data required by the target business meet the same sample data but have different characteristics.
- model training related information includes one or more of the following:
- Basic model information used to indicate the basic model used by the business processing device for model training
- Model configuration information used to instruct the business processing device to configure parameters for the basic model used when performing model training
- Termination condition information for model training is
- the second information is the sample data request information in the first request message, or the second information is experience information of model training.
- the first information includes one or more of the following:
- the device also includes:
- the storage module is used to store the association between the first information, the identifier of the second network device, and the identifier of the target service.
- an embodiment of the present application provides a service processing device 600.
- the service processing device 600 may be the second network device in the above method side description.
- the business processing device 600 includes:
- the second sending module 601 is used to send a first request message to the first network device, where the first request message is used to request privacy protection for the target service;
- the second receiving module 602 is configured to receive the first information sent by the first network device, where the first information is used to respond to the first request message.
- the second sending module is used for:
- the second receiving module is used for:
- the target business is an authorized business.
- the first request message includes one or more of the following:
- the first request message includes one or more of the following:
- the relevant information of the target model includes one or more of the following:
- Model training instruction information used to instruct the first network to perform model training
- model training configuration information includes one or more of the following:
- Model type information used to indicate the basic model used by the first network device
- Model configuration information used to indicate the parameters configured by the basic model used by the first network device when performing model training
- the first information includes one or more of the following:
- the business processing device in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in the electronic device, such as an integrated circuit or chip.
- the electronic device may be a server, a network attached storage (Network Attached Storage, NAS), etc., which are not specifically limited in the embodiments of this application.
- Network Attached Storage NAS
- the business processing device provided by the embodiment of the present application can implement each process implemented by the method embodiment of Figures 2 to 4b, and achieve the same technical effect. To avoid duplication, the details will not be described here.
- this embodiment of the present application also provides a communication device 700, which includes a processor 701 and a memory 702.
- the memory 702 stores programs or instructions that can be run on the processor 701, such as , when the communication device 700 is a terminal, when the program or instruction is executed by the processor 701, each step of the above business processing method embodiment is implemented, and the same technical effect can be achieved.
- the communication device 700 is a network-side device, when the program or instruction is executed by the processor 701, each step of the above business processing method embodiment is implemented, and the same technical effect can be achieved. To avoid duplication, the details are not repeated here.
- the embodiment of the present application also provides a network side device.
- the network side device 800 includes: a processor 801 , a network interface 802 and a memory 803 .
- the network interface 802 is, for example, a common public radio interface (CPRI).
- CPRI common public radio interface
- the network side device 800 in the embodiment of the present application also includes: instructions or programs stored in the memory 803 and executable on the processor 801.
- the processor 801 calls the instructions or programs in the memory 803 to execute Figure 5 or Figure 6
- the execution methods of each module are shown and achieve the same technical effect. To avoid repetition, they will not be described in detail here.
- Embodiments of the present application also provide a readable storage medium.
- Programs or instructions are stored on the readable storage medium.
- the program or instructions are executed by a processor, each process of the above business processing method embodiment is implemented and the same can be achieved. The technical effects will not be repeated here to avoid repetition.
- the processor is the processor in the terminal described in the above embodiment.
- the readable storage media includes computer-readable storage media, such as computer read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disks or optical disks, etc.
- An embodiment of the present application further provides a chip.
- the chip includes a processor and a communication interface.
- the communication interface and The processor is coupled, and the processor is used to run programs or instructions to implement each process of the above business processing method embodiment, and can achieve the same technical effect. To avoid duplication, the details will not be described here.
- chips mentioned in the embodiments of this application may also be called system-on-chip, system-on-a-chip, system-on-chip or system-on-chip, etc.
- Embodiments of the present application further provide a computer program/program product.
- the computer program/program product is stored in a storage medium.
- the computer program/program product is executed by at least one processor to implement the above business processing method embodiment.
- Each process can achieve the same technical effect. To avoid repetition, we will not go into details here.
- the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is better. implementation.
- the technical solution of the present application can be embodied in the form of a computer software product that is essentially or contributes to related technologies.
- the computer software product is stored in a storage medium (such as ROM/RAM, disk, CD), including several instructions to cause a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of this application.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Computer Security & Cryptography (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
Description
Claims (37)
- 一种业务处理方法,包括:第一网络设备接收第二网络设备发送的第一请求消息,所述第一请求消息用于请求对目标业务进行隐私保护;所述第一网络设备根据所述第一请求消息,确定模型训练相关信息;所述第一网络设备获取样本数据;所述第一网络设备根据所述样本数据和所述模型训练相关信息进行模型训练,得到目标模型,所述目标模型用于对所述目标业务需求的数据进行隐私保护;所述第一网络设备向所述第二网络设备发送第一信息,所述第一信息用于响应第一请求消息。
- 根据权利要求1所述的方法,其中,所述第一网络设备接收第二网络设备发送的第一请求消息,包括:所述第一网络设备通过第三网络设备接收所述第二网络设备发送的所述第一请求消息;所述第一网络设备向所述第二网络设备发送第一信息,包括:所述第一网络设备通过所述第三网络设备向所述第二网络设备发送所述第一信息;其中,目标业务为被授权的业务。
- 根据权利要求1或2所述的方法,其中,所述第一请求消息中包括以下一项或者多项:所述第二网络设备的标识;所述目标业务的标识;隐私保护等级;模型性能信息。
- 根据权利要求1或2所述的方法,其中,所述第一请求消息中包括以下一项或者多项:所述第二网络设备的标识;所述目标业务的标识;隐私保护等级;所述目标模型的相关信息;其中,所述目标模型的相关信息,包括以下一项或者多项:模型训练指示信息,用于指示所述第一网络设备进行模型训练;模型训练配置信息。
- 根据权利要求4所述的方法,其中,所述模型训练配置信息,包括以下一项或者多项:模型类型信息,用于指示所述第一网络设备使用的基础模型;模型配置信息,用于指示所述第一网络设备进行模型训练时为使用的基础模型配置的参数;模型性能信息;样本数据要求信息。
- 根据权利要求3所述的方法,其中,所述第一网络设备根据所述第一请求消息,确定模型训练相关信息,包括:在满足第一预设条件的情况下,所述第一网络设备根据所述第一请求消息,确定模型训练相关信息;其中,所述第一预设条件包括以下一项或者多项:所述目标业务基于隐私数据运行;所述目标业务需求的数据满足样本相同,特征不同。
- 根据权利要求4所述的方法,其中,所述第一网络设备根据所述第一请求消息,确定模型训练相关信息,包括:在满足第二预设条件的情况下,所述第一网络设备根据所述第一请求消息,确定模型训练相关信息;其中,所述第二预设条件包括以下一项或者多项:所述第一请求消息中包括所述模型训练指示信息;所述目标业务基于隐私数据运行;所述目标业务需求的数据满足样本数据相同,特征不同。
- 根据权利要求1所述的方法,其中,所述模型训练相关信息,包括以下一项或者多项:基础模型信息,用于指示所述第一网络设备进行模型训练时使用的基础模型;模型配置信息,用于指示所述第一网络设备进行模型训练时为使用的基础模型配置的参数;模型训练的终止条件信息。
- 根据权利要求1至3任一项所述的方法,其中,所述第一网络设备获取样本数据,包括:所述第一网络设备根据第二信息,确定样本数据类型和样本数据源;所述第一网络设备根据所述样本数据类型和所述样本数据源,获取样本数据;其中,所述第二信息为所述第一请求消息中的样本数据要求信息,或者,所述第二信息为模型训练的经验信息。
- 根据权利要求1所述的方法,其中,所述第一信息,包括以下一项或者多项:所述第一请求消息的应答ACK信息;所述第一网络设备的相关信息;所述目标模型的时效信息;所述目标模型的标识信息。
- 根据权利要求3或4所述的方法,其中,所述方法还包括:所述第一网络设备存储所述第一信息、所述第二网络设备的标识和所述目标业务的标识之间的关联关系。
- 一种业务处理方法,包括:第二网络设备向第一网络设备发送第一请求消息,所述第一请求消息用于请求对目标业务进行隐私保护;所述第二网络设备接收所述第一网络设备发送的第一信息,所述第一信息用于响应第一请求消息。
- 根据权利要求12所述的方法,其中,所述第二网络设备向第一网络设备发送第一请求消息,包括:所述第二网络设备通过第三网络设备向所述第一网络设备发送所述第一请求消息;所述第二网络设备接收所述第一网络设备发送第一信息,包括:所述第二网络设备通过所述第三网络设备接收所述第一网络设备发送的所述第一信息;其中,目标业务为被授权的业务。
- 根据权利要求12所述的方法,其中,所述第一请求消息中包括以下一项或者多项:所述第二网络设备的标识;所述目标业务的标识;隐私保护等级;模型性能信息。
- 根据权利要求12所述的方法,其中,所述第一请求消息中包括以下一项或者多项:所述第二网络设备的标识;所述目标业务的标识;隐私保护等级;所述目标模型的相关信息;其中,所述目标模型的相关信息,包括以下一项或者多项:模型训练指示信息,用于指示所述第一网络进行模型训练;模型训练配置信息。
- 根据权利要求15所述的方法,其中,所述模型训练配置信息,包括以下一项或者多项:模型类型信息,用于指示所述第一网络设备使用的基础模型;模型配置信息,用于指示所述第一网络设备进行模型训练时为使用的基础模型配置的参数;模型性能信息;样本数据要求信息。
- 根据权利要求12所述的方法,其中,所述第一信息,包括以下一项或者多项:所述第一请求消息的ACK信息;所述第一网络设备的相关信息;所述目标模型的时效信息;所述目标模型的标识信息。
- 一种业务处理装置,包括:第一接收模块,用于接收第二网络设备发送的第一请求消息,所述第一请求消息用于请求对目标业务进行隐私保护;第一确定模块,用于根据所述第一请求消息,确定模型训练相关信息;获取模块,用于获取样本数据;训练模块,用于根据所述样本数据和所述模型训练相关信息进行模型训练,得到目标模型,所述目标模型用于对所述目标业务需求的数据进行隐私保护;第一发送模块,用于向所述第二网络设备发送第一信息,所述第一信息用于响应第一请求消息。
- 根据权利要求18所述的装置,其中,所述第一接收模块,用于:通过第三网络设备接收所述第二网络设备发送的所述第一请求消息;所述第一发送模块,用于:通过所述第三网络设备向所述第二网络设备发送所述第一信息;其中,目标业务为被授权的业务。
- 根据权利要求18或19所述的装置,其中,所述第一请求消息中包括以下一项或者多项:所述第二网络设备的标识;所述目标业务的标识;隐私保护等级;模型性能信息。
- 根据权利要求18或19所述的装置,其中,所述第一请求消息中包括以下一项或者多项:所述第二网络设备的标识;所述目标业务的标识;隐私保护等级;所述目标模型的相关信息;其中,所述目标模型的相关信息,包括以下一项或者多项:模型训练指示信息,用于指示所述业务处理装置进行模型训练;模型训练配置信息。
- 根据权利要求21所述的装置,其中,所述模型训练配置信息,包括以下一项或者多项:模型类型信息,用于指示所述业务处理装置使用的基础模型;模型配置信息,用于指示所述业务处理装置进行模型训练时为使用的基础模型配置的参数;模型性能信息;样本数据要求信息。
- 根据权利要求20所述的装置,其中,所述第一确定模块,用于:在满足第一预设条件的情况下,根据所述第一请求消息,确定模型训练相关信息;其中,所述第一预设条件包括以下一项或者多项:所述目标业务基于隐私数据运行;所述目标业务需求的数据满足样本相同,特征不同。
- 根据权利要求21所述的装置,其中,所述第一确定模块,用于:在满足第二预设条件的情况下,根据所述第一请求消息,确定模型训练相关信息;其中,所述第二预设条件包括以下一项或者多项:所述第一请求消息中包括所述模型训练指示信息;所述目标业务基于隐私数据运行;所述目标业务需求的数据满足样本数据相同,特征不同。
- 根据权利要求18所述的装置,其中,所述模型训练相关信息,包括以下一项或者多项:基础模型信息,用于指示所述业务处理装置进行模型训练时使用的基础模型;模型配置信息,用于指示所述业务处理装置进行模型训练时为使用的基础模型配置的参数;模型训练的终止条件信息。
- 根据权利要求18至20任一项所述的装置,其中,所述获取模块,用于:根据第二信息,确定样本数据类型和样本数据源;根据所述样本数据类型和所述样本数据源,获取样本数据;其中,所述第二信息为所述第一请求消息中的样本数据要求信息,或者,所述第二信息为模型训练的经验信息。
- 根据权利要求18所述的装置,其中,所述第一信息,包括以下一项或者多项:所述第一请求消息的ACK信息;所述业务处理装置的相关信息;所述目标模型的时效信息;所述目标模型的标识信息。
- 根据权利要求20或21所述的装置,其中,所述装置还包括:存储模块,用于存储所述第一信息、所述第二网络设备的标识和所述目标业务的标识之间的关联关系。
- 一种业务处理装置,包括:第二发送模块,用于向第一网络设备发送第一请求消息,所述第一请求消息用于请求对目标业务进行隐私保护;第二接收模块,用于接收所述第一网络设备发送的第一信息,所述第一信息用于响应第一请求消息。
- 根据权利要求29所述的装置,其中,所述第二发送模块,用于:通过第三网络设备向所述第一网络设备发送所述第一请求消息;所述第二接收模块,用于:通过所述第三网络设备接收所述第一网络设备发送的所述第一信息;其中,目标业务为被的业务。
- 根据权利要求29所述的装置,其中,所述第一请求消息中包括以下一项或者多项:所述业务处理装置的标识;所述目标业务的标识;隐私保护等级;模型性能信息。
- 根据权利要求29所述的装置,其中,所述第一请求消息中包括以下一项或者多项:所述业务处理装置的标识;所述目标业务的标识;隐私保护等级;所述目标模型的相关信息;其中,所述目标模型的相关信息,包括以下一项或者多项:模型训练指示信息,用于指示所述第一网络进行模型训练;模型训练配置信息。
- 根据权利要求32所述的装置,其中,所述模型训练配置信息,包括以下一项或者多项:模型类型信息,用于指示所述第一网络设备使用的基础模型;模型配置信息,用于指示所述第一网络设备进行模型训练时为使用的基础模型配置的参数;模型性能信息;样本数据要求信息。
- 根据权利要求29所述的装置,其中,所述第一信息,包括以下一项或者多项:所述第一请求消息的ACK信息;所述第一网络设备的相关信息;所述目标模型的时效信息;所述目标模型的标识信息。
- 一种网络侧设备,包括处理器和存储器,其中,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至11任一项所述的业务处理方法的步骤。
- 一种网络侧设备,包括处理器和存储器,其中,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求12至17任一项所述的业务处理方法的步骤。
- 一种可读存储介质,所述可读存储介质上存储程序或指令,其中,所述程序或指令被处理器执行时实现如权利要求1至11任一项所述的业务处理方法的步骤,或者实现如权利要求12至17任一项所述的业务处理方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210523618.0 | 2022-05-13 | ||
| CN202210523618.0A CN117119442A (zh) | 2022-05-13 | 2022-05-13 | 业务处理方法、设备及可读存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023217026A1 true WO2023217026A1 (zh) | 2023-11-16 |
Family
ID=88729702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2023/092471 Ceased WO2023217026A1 (zh) | 2022-05-13 | 2023-05-06 | 业务处理方法、设备及可读存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN117119442A (zh) |
| WO (1) | WO2023217026A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119450516A (zh) * | 2024-09-06 | 2025-02-14 | 中国电信股份有限公司技术创新中心 | 模型生命周期管理方法、装置、通信设备和存储介质 |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2025145374A1 (zh) * | 2024-01-04 | 2025-07-10 | 富士通株式会社 | 信息收发方法和装置 |
| CN121638497A (zh) * | 2024-08-15 | 2026-03-10 | 荣耀终端股份有限公司 | 通信方法、存储介质、芯片系统及通信系统 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782637A (zh) * | 2020-07-03 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | 一种模型构建方法、装置及设备 |
| US20210014141A1 (en) * | 2019-07-12 | 2021-01-14 | Verizon Patent And Licensing Inc. | System and method of closed loop analytics for network automation |
| CN112818390A (zh) * | 2021-01-26 | 2021-05-18 | 支付宝(杭州)信息技术有限公司 | 一种基于隐私保护的数据信息发布方法、装置及设备 |
| CN113435585A (zh) * | 2021-07-15 | 2021-09-24 | 支付宝(杭州)信息技术有限公司 | 一种业务处理方法、装置及设备 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340242B (zh) * | 2020-05-15 | 2020-08-04 | 支付宝(杭州)信息技术有限公司 | 保护隐私的模型联合训练方法及装置 |
| CN113839797B (zh) * | 2020-06-23 | 2022-11-25 | 华为技术有限公司 | 数据处理方法和装置 |
-
2022
- 2022-05-13 CN CN202210523618.0A patent/CN117119442A/zh active Pending
-
2023
- 2023-05-06 WO PCT/CN2023/092471 patent/WO2023217026A1/zh not_active Ceased
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210014141A1 (en) * | 2019-07-12 | 2021-01-14 | Verizon Patent And Licensing Inc. | System and method of closed loop analytics for network automation |
| CN111782637A (zh) * | 2020-07-03 | 2020-10-16 | 支付宝(杭州)信息技术有限公司 | 一种模型构建方法、装置及设备 |
| CN112818390A (zh) * | 2021-01-26 | 2021-05-18 | 支付宝(杭州)信息技术有限公司 | 一种基于隐私保护的数据信息发布方法、装置及设备 |
| CN113435585A (zh) * | 2021-07-15 | 2021-09-24 | 支付宝(杭州)信息技术有限公司 | 一种业务处理方法、装置及设备 |
Non-Patent Citations (1)
| Title |
|---|
| "3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Study on security aspects of enablers for Network Automation (eNA) for the 5G system (5GS) Phase 2; (Release 17)", 3GPP STANDARD; TECHNICAL REPORT; 3GPP TR 33.866, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, no. V0.8.0, 19 November 2021 (2021-11-19), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, pages 1 - 50, XP052082902 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119450516A (zh) * | 2024-09-06 | 2025-02-14 | 中国电信股份有限公司技术创新中心 | 模型生命周期管理方法、装置、通信设备和存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117119442A (zh) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230007038A1 (en) | Systems and methods for automated quantitative risk and threat calculation and remediation | |
| CN116325686B (zh) | 一种通信方法和装置 | |
| WO2023217026A1 (zh) | 业务处理方法、设备及可读存储介质 | |
| CN116114292B (zh) | 一种通信方法和装置 | |
| CN110650034A (zh) | 一种信息处理方法及装置 | |
| KR20250005393A (ko) | 모델 정보 획득 방법, 송신 방법, 장치, 노드 및 저장 매체 | |
| US12596844B2 (en) | Systems and methods for secure aggregating and reporting of monitored data | |
| WO2023213288A1 (zh) | 模型获取方法及通信设备 | |
| WO2023179709A1 (zh) | 信息处理方法、装置、通信设备及可读存储介质 | |
| US20250071543A1 (en) | Privacy protection information processing method and apparatus, and communication device | |
| US20250061232A1 (en) | Data processing method and apparatus, core network node, electronic device, and storage medium | |
| WO2023185725A1 (zh) | 数据获取方法、装置及网络侧设备 | |
| WO2024032588A1 (zh) | 用户意愿验证方法、装置及网络侧设备 | |
| WO2024078400A1 (zh) | 模型请求方法、装置、通信设备及可读存储介质 | |
| CN116866886A (zh) | 数据获取方法及通信设备 | |
| EP4535209A1 (en) | Service processing method and apparatus, network device and storage medium | |
| WO2025026193A1 (zh) | 业务处理方法、装置、通信设备及可读存储介质 | |
| WO2025026299A1 (zh) | Ai业务建立方法、装置及网络侧设备 | |
| WO2025026194A1 (zh) | 业务处理方法、装置、通信设备及可读存储介质 | |
| CN120321628A (zh) | 通信方法、装置、通信设备及存储介质 | |
| WO2024251012A1 (zh) | 数据收集方法、数据收集装置、通信设备及存储介质 | |
| WO2026082368A1 (en) | Method, apparatus and computer program | |
| WO2026082392A1 (en) | Management and authorisation of distributed ai/ml services in user equipment | |
| WO2025195238A1 (zh) | 任务处理方法、装置及相关设备 | |
| WO2024045970A1 (zh) | 路由选择策略执行结果处理方法、装置及设备 |
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: 23802798 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23802798 Country of ref document: EP Kind code of ref document: A1 |
|
| 32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 07/05/2025) |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23802798 Country of ref document: EP Kind code of ref document: A1 |