Method and device for realizing network function

Abstract

The invention provides a method and a device for realizing a network function, which are used for realizing the network function under the condition that a distributed network architecture meets credible requirements. The method comprises: a sixth NF network element receiving first information from a first network function NF network element and second information from a second NF network element; acquiring a first model and first data according to the second information; and determining the response of the business demand according to the first model and the first data. The second information indicates a storage condition of data required for realizing a service demand in a third NF network element, the second NF network element is used for recording the storage condition of the data by adopting a distributed account book technology, the third NF network element is used for storing the data by adopting a distributed hash table technology, and the data comprises model data corresponding to a model type and first data corresponding to a data type; the model data is used to determine a first model.

Description

Method and device for implementing network function Technical Field

[0001] The embodiments of the present application relate to the field of communications, and in particular to a method and device for implementing network functions. Background Art

[0002] With the large-scale deployment of distributed edge computing and intelligent user equipment (UE), the development and widespread application of perception and artificial intelligence (AI) technologies, the network architecture of the future sixth-generation mobile communication system (6G) will require distributed network architecture to support computing power, intelligence, and data.

[0003] At the same time, with the implementation of relevant laws and regulations such as the Personal Information Protection Law (PIPL) and the General Data Protection Regulation (GDPR), demands such as user data security and user privacy protection need to be considered at the network architecture level.

[0004] Therefore, when a distributed network architecture satisfies the security of user data and user privacy (for example, meeting trust requirements), how to implement network functions (NFs) under the distributed network architecture is an issue that needs to be discussed urgently.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a method and device for implementing network functions, which are used to implement the network functions of a distributed network architecture while ensuring the security of user data and user privacy.

[0007] In a first aspect, a method for implementing a network function is provided. The method can be executed by a sixth network function (NF) element, or by a component of the sixth NF element, such as a processor, communication interface, chip, or chip system of the sixth NF element. The method can also be implemented by a logic module or software capable of implementing all or part of the sixth NF element's functions. The method includes: receiving first information from a first NF element, the first information indicating a model type and data type corresponding to a service requirement of the first NF element; receiving second information from a second NF element, the second information indicating a storage status of data required to implement the service requirement in a third NF element, the second NF element being configured to record the storage status of the data using a distributed ledger technology, the third NF element being configured to store the data using a distributed hash table technology, the data including model data corresponding to the model type and first data corresponding to the data type, the model data being used to determine a first model; obtaining a first model and first data based on the second information; and determining a response to the service requirement based on the first model and first data.

[0008] Based on this solution, the second NF network element is used to use distributed ledger technology to record the storage status of the data required to implement the business (i.e., on-chain storage), and the third NF network element is used to use distributed hash table technology to store data (i.e., off-chain storage). The security of user data and user privacy is improved through a combination of on-chain and off-chain storage, thereby meeting the trust requirements of the distributed network architecture. While meeting the trust requirements of the distributed network architecture, the sixth NF network element determines the storage status of the data required to implement the business requirements from the second NF network element based on the model type and data type corresponding to the business requirements, and then obtains the first model and first data corresponding to the business requirements based on the data storage status, and determines the response to the business requirements based on the first data and the first model. In this way, network functions can be implemented while the distributed network architecture meets the trust requirements.

[0009] In one possible design, the second NF network element may be a DLT network element, and the third NF network element may be a DHT network element.

[0010] In one possible design, the second information includes first indication information, the first indication information indicating whether the first model is stored in the third NF network element, and when the first indication information indicates that the first model is stored in the third NF network element, the first indication information also indicates whether the first model needs to be updated; wherein, when the first indication information indicates that the first model is not stored in the third NF network element, the model data includes second data, and the second data is used to train to obtain the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the model data includes the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the model data includes the first model and third data, and the third data is used to update the first model to obtain the second model.

[0011] In one possible design, the second information also includes a first pointer; when the first indication information indicates that the first model is not stored in the third NF network element, the first pointer indicates a first storage address, the first storage address is the storage address of the second data in the third NF network element, and the second data is used to train the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the first pointer indicates a second storage address, and the second storage address is the storage address of the first model in the third NF network element; when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the first pointer indicates a third storage address and a second storage address, the third storage address is the storage address of the third data in the third NF network element, and the third data is used to update the first model.

[0012] Based on this possible design, for different scenarios indicated by the first indication information, the first pointer indicates the storage address of the first model, the storage address for obtaining the data of the first model (i.e., the second data), or the storage address for obtaining the data of the second model (the first model and the third data), so that the sixth NF network element can obtain the first model, the data for obtaining the first model, or the data for obtaining the second model from the storage address according to the first pointer.

[0013] In a possible design, the sixth NF network element obtains the first model according to the second information, including: the sixth NF network element obtains the first model according to the first indication information and the first pointer.

[0014] In one possible design, when the first indication information indicates that the first model is not stored in the third NF network element, the sixth NF network element obtains the first model based on the second information, including: the sixth NF network element obtains the second data from the first storage address; sends the second data to the fourth NF network element, where the fourth NF network element is used to train the first model; and receives the first model from the fourth NF network element.

[0015] In one possible design, the method for implementing the network function further includes: the sixth NF network element sends the first model to the third NF network element.

[0016] Based on this possible design, if the third NF does not store the first model, the sixth NF obtains the second data used to train the first model from the third NF, and then trains the first model with the fourth NF to obtain the first model. The first model is stored in the third NF, allowing other NFs to directly use the first model without retraining when they need to use it, thereby reducing resource consumption and improving system efficiency.

[0017] In one possible design, when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the sixth NF network element obtains the first model according to the second information, including: the sixth NF network element obtains the first model from the second storage address.

[0018] Based on this possible design, if the third NF already stores the first model and the first model does not need to be updated, the sixth NF directly obtains the first model from the third NF. This allows other NFs to directly use the first model when they need it, without the need for retraining. This reduces resource consumption and improves system efficiency.

[0019] In one possible design, when the third NF stores the first model and the first model needs to be updated, the sixth NF obtains the first model according to the second information, including:

[0020] The sixth NF obtains the first model from the second storage address and obtains the third data from the third storage address. The method for implementing the network function further includes: the sixth NF sends the third data and the first model to the fourth NF; and receives the second model from the fourth NF, where the second model is an updated version of the first model.

[0021] In one possible design, the method for implementing the network function further includes: the sixth NF network element sends the second model to the third NF network element.

[0022] In one possible design, the sixth NF network element determines a response to the service demand based on the first model and the first data, including determining a response to the service demand based on the second model and the first data.

[0023] In one possible design, when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the first pointer includes a first sub-pointer and a second sub-pointer; the first sub-pointer indicates the third storage address, and the second sub-pointer indicates the second storage address.

[0024] In one possible design, the second information also includes second indication information, and the second indication information indicates whether the first data is stored in the third NF network element.

[0025] In one possible design, the second information also includes a second pointer; when the second indication information indicates that the first data is stored in the third NF network element, the second pointer indicates a fourth storage address, which is the storage address of the first data in the third NF network element; when the second indication information indicates that the first data is not stored in the third NF network element, the second pointer indicates a fifth storage address, which is the storage address of the first data in the fifth NF network element, and the fifth NF network element is used to provide data corresponding to the service needs.

[0026] Based on this possible design, for different scenarios indicated by the second indication information (such as whether the first data is stored in the third NF network element), the second pointer indicates the storage address of the first data in different scenarios, so that the sixth NF network element can obtain the first data according to the storage address.

[0027] In a possible design, the sixth NF network element obtains the first data according to the second information, including: the sixth NF network element obtains the first data according to the second indication information and the second pointer.

[0028] In one possible design, when the second indication information indicates that the third NF network element stores the first data, obtaining the first data according to the second information includes:

[0029] The sixth NF network element obtains the first data from the fourth storage address.

[0030] In one possible design, when the second indication information indicates that the third NF network element does not store the first data, obtaining the first data according to the second information includes: the sixth NF network element sends third information to the fifth NF network element, the third information requests the fifth NF network element to store the first data stored in the fifth storage address in the third NF network element; and receiving the first data from the third NF network element.

[0031] In one possible design, the sixth NF network element receives the first information from the first NF network element, including: the sixth NF network element receives a first message from the first NF network element, where the first message includes the first information and a digital signature of the first NF network element. The digital signature of the first NF network element is used to verify the integrity of the first information.

[0032] Based on this possible design, the digital signature of the first NF network element can be used to ensure the data security of the first information, prevent the first message from being tampered with, and reduce the accuracy of the response to the business demand.

[0033] In one possible design, the second information also includes access policy information, which indicates whether the first NF network element has data access rights.

[0034] In one possible design, the sixth NF network element obtains the first model according to the second information, including: when the access policy information indicates that the first NF network element has data access rights, the sixth NF network element obtains the first model according to the second information.

[0035] In one possible design, the sixth NF network element obtains the first data according to the second information, including: when the access policy information indicates that the first NF network element has data access rights, the sixth NF network element obtains the first data according to the second information.

[0036] In one possible design, the sixth NF network element determines a response to the service demand based on the first model and the first data, including: the sixth NF network element compares a first hash value of the first model with a second hash value of the first model, where the first hash value is a hash value of the first model calculated by the third NF network element, and the second hash value is a hash value of the first model recorded in the second NF network element; and when the first hash value is consistent with the second hash value, determining a response to the service demand based on the first model and the first data.

[0037] Based on this possible design, since the first model is stored off-chain (i.e., the third NF network element) and the second hash value of the first model is recorded on-chain (i.e., the second NF network element), the first model stored off-chain may be tampered with. Before determining the response to the business demand, the sixth NF network element can compare the first hash value with the second hash value to determine whether the first model has been tampered with. When the first hash value is consistent with the second hash value, it indicates that the first model has not been tampered with, that is, after the sixth NF network element determines that the first model has not been tampered with, it determines the response to the business demand based on the first model and the first data, avoiding the use of the tampered first model to determine the response to the business demand, thereby improving the accuracy of the response to the business demand.

[0038] In one possible design, the sixth NF network element determines a response to the service demand based on the first model and the first data, including: the sixth NF network element compares the fifth hash value of the first model with the second hash value of the first model, the fifth hash value is the hash value of the first model determined by the sixth NF network element, and the second hash value is the hash value of the first model recorded in the second NF network element; when the fifth hash value is consistent with the second hash value, determining a response to the service demand based on the first model and the first data.

[0039] Based on this possible design, the first model may have been tampered with during transmission from the third NF to the sixth NF. Therefore, before determining a response to the service request, the sixth NF compares the first hash value with the second hash value to determine whether the first model was tampered with during transmission from the third NF to the sixth NF. If the fifth hash value matches the second hash value, it indicates that the first model has not been tampered with. That is, after determining that the first model has not been tampered with, the sixth NF determines a response to the service request based on the first model and the first data. This avoids using the tampered first model to determine the response to the service request, thereby improving the accuracy of the response to the service request. In one possible design, the sixth NF determines a response to the service request based on the first model and the first data, including: comparing the third hash value of the first data with the fourth hash value of the first data, where the third hash value is the hash value of the first data calculated by the third NF and the fourth hash value is the hash value of the first data recorded by the second NF; if the third hash value matches the fourth hash value, determining a response to the service request based on the first model and the first data.

[0040] Based on this possible design, since the first data is stored off-chain (i.e., the third NF network element) and the fourth hash value of the first data is recorded on-chain (i.e., the second NF network element), the first data stored off-chain may be tampered with. Before determining the response to the business demand, the sixth NF network element compares the third hash value with the fourth hash value to determine whether the first data has been tampered with. When the third hash value is consistent with the fourth hash value, it indicates that the first data has not been tampered with, that is, after the sixth NF network element determines that the first data has not been tampered with, it determines the response to the business demand based on the first model and the first data, avoiding the use of the tampered first data to determine the response to the business demand, thereby improving the accuracy of the response to the business demand.

[0041] In one possible design, the sixth NF network element determines a response to the service demand based on the first model and the first data, including: the sixth NF network element compares a sixth hash value of the first data with a fourth hash value of the first data, where the sixth hash value is the hash value of the first data determined by the sixth NF network element, and the fourth hash value is the hash value of the first data recorded in the second NF network element; when the sixth hash value is consistent with the fourth hash value, determining a response to the service demand based on the first model and the first data.

[0042] Based on this possible design, since the first data may be tampered with during the process of the third NF network element sending the first data to the sixth NF network element, before determining the response to the service demand, the sixth NF network element compares the third hash value with the fourth hash value to determine whether the first data has been tampered with during the transmission process from the third NF network element to the sixth NF network element. If the sixth hash value is consistent with the fourth hash value, it means that the first data has not been tampered with. That is, after the sixth NF network element determines that the first data has not been tampered with, it determines the response to the service demand based on the first model and the first data, avoiding the use of the tampered first data to determine the response to the service demand, thereby improving the accuracy of the response to the service demand.

[0043] In a second aspect, a communication device is provided for implementing various methods. The communication device may be the sixth NF network element in the first aspect, or a device included in the sixth NF network element, such as a chip or chip system. The communication device includes modules, units, or means corresponding to the implementation method. The modules, units, or means may be implemented in hardware, software, or by hardware executing the corresponding software implementation. The hardware or software includes one or more modules or units corresponding to the functions.

[0044] In some possible designs, the communication device may include a processing module and a communication module. The processing module may be configured to implement the processing functionality of any of the above aspects and any possible implementations thereof. The communication module may include a receiving module and a sending module, respectively configured to implement the receiving functionality and the sending functionality of any of the above aspects and any possible implementations thereof.

[0045] In some possible designs, the communication module may be composed of a transceiver circuit, a transceiver, a transceiver or a communication interface.

[0046] In a third aspect, a communication device is provided, comprising: a processor and a memory; the memory is configured to store computer instructions, and when the processor executes the instructions, the communication device performs the method described in any one of the aspects. The communication device may be the sixth NF network element described in the first aspect, or a device included in the sixth NF network element, such as a chip or chip system.

[0047] In a fourth aspect, a communication device is provided, comprising: a processor and a communication interface; the communication interface is configured to communicate with a module external to the communication device; and the processor is configured to execute a computer program or instruction to cause the container cluster management device to perform the method described in any one of the aspects. The communication device may be the sixth NF network element described in the first aspect, or a device included in the sixth NF network element, such as a chip or chip system.

[0048] In a fifth aspect, a communication device is provided, comprising: at least one processor; the processor is configured to execute a computer program or instruction stored in a memory, so that the communication device performs the method described in any one of the aspects. The memory may be coupled to the processor, or may be independent of the processor. The communication device may be the sixth NF network element in the first aspect, or a device included in the sixth NF network element, such as a chip or a chip system.

[0049] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0050] In some possible designs, when the device is a chip system, it can be composed of a chip or include a chip and other discrete devices.

[0051] It can be understood that when the communication device provided in any one of the second to fifth aspects is a chip, the sending action / function of the communication device can be understood as output information, and the receiving action / function of the communication device can be understood as input information.

[0052] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program or instruction, which, when executed on a communication device, enables the communication device to execute the method described in any aspect; or enables the communication device to execute the device described in any aspect.

[0053] In a seventh aspect, a computer program product comprising instructions is provided, which, when executed on a communication device, enables the communication device to execute the method described in any aspect; or enables the communication device to execute the device described in any aspect.

[0054] Among them, the technical effects brought about by any design method in the second to seventh aspects can refer to the technical effects brought about by different design methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] FIG1 is a schematic diagram of a trustworthy-distributed hash table (T-DHT) technology provided by this application;

[0056] FIG2 is a schematic diagram of a distributed network architecture provided by this application;

[0057] FIG3 is a schematic diagram of another distributed network architecture provided by the present application;

[0058] FIG4 is a flow chart of a method for implementing NF provided in this application;

[0059] FIG5 is a schematic diagram of a first message and a second message in a method for implementing an NF provided in this application;

[0060] FIG6 is a flow chart of another NF implementation method provided by the present application;

[0061] FIG7a is a flow chart of another NF implementation method provided by the present application;

[0062] FIG7 b is a flow chart of another NF implementation method provided by the present application;

[0063] FIG7c is a flowchart of another NF implementation method provided by the present application;

[0064] FIG8a is a flow chart of another NF implementation method provided by the present application;

[0065] FIG8b is a flow chart of another NF implementation method provided by the present application;

[0066] FIG9 is a schematic diagram of another distributed network architecture provided by the present application;

[0067] FIG10 is a schematic diagram of another distributed network architecture provided by the present application;

[0068] FIG11 is a schematic diagram of another distributed network architecture provided by the present application;

[0069] FIG12 is a schematic diagram of another distributed network architecture provided by the present application;

[0070] FIG13 is a schematic diagram of another distributed network architecture provided by the present application;

[0071] FIG14 is a schematic diagram of another distributed network architecture provided by the present application;

[0072] FIG15 is a schematic structural diagram of a communication device provided by the present application;

[0073] FIG16 is a schematic structural diagram of another communication device provided in this application. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments.

[0075] In the following, the terms "first," "second," etc. are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the quantity of the technical features indicated. Therefore, a feature specified as "first," "second," etc. may explicitly or implicitly include one or more of the features.

[0076] 1. Distributed network architecture:

[0077] A distributed system is a system where hardware or software components are distributed across different computers, and communication and coordination between these computers is achieved through message passing. The system architecture of a distributed system is a distributed network architecture.

[0078] Distributed systems have the following functions: (1) Resources can be shared between different nodes; (2) Fast running speed; for example, during the task running process, the task can be divided into multiple subtasks and assigned to different nodes to run different subtasks, thereby speeding up the calculation speed; (3) High reliability; for example, during the running process, if one or several nodes fail, it will not cause the distributed system to stop running, and the nodes in the distributed system except the failed nodes can continue to run.

[0079] 2. Network data analysis function (NWDAF):

[0080] NWDAF can be used for big data analysis. For example, it can acquire data, analyze it, and provide the analysis results to other network elements or applications. NWDAF also has functions such as training models and performing inference based on the trained models.

[0081] Specifically, the functions of NWDAF can be decomposed into multiple independent instances. These instances can exist independently and provide certain functions of NWDAF. For example, the model training logical function (MTLF) network element, as an NWDAF instance, can provide model training and provide model functions to other NWDAF instances. For example, the analytics logical function (AnLF) network element, as an NWDAF instance, can obtain models from other NWDAF instances and then perform data analysis based on the obtained models.

[0082] 3. Distributed technology:

[0083] Distributed technologies are primarily used in the field of information technology (IT), including distributed ledger technology (DLT) and distributed hash tables (DHT). DHT enables distributed deployment, fast search, and access to network functions (NFs), meeting the needs of decentralization and autonomy while also offering fault tolerance and scalability.

[0084] With the large-scale deployment of infrastructure with distributed edge computing capabilities and intelligent user equipment (UE), the development and widespread application of perception and artificial intelligence (AI) technologies, the network architecture of the future sixth-generation mobile communication system (6G) will require distributed network architecture to support computing power, intelligence, and data.

[0085] However, with the implementation of data-related laws and regulations such as the Personal Information Protection Law (PIPL) and the General Data Protection Regulation (GDPR), it is necessary to consider user data security and privacy protection demands at the network architecture level, that is, to realize the trust requirements of network functions.

[0086] Based on this, the 3rd Generation Partnership Project (3GPP) communication system introduced the data collection coordinate function (DCCF) network element, the messaging framework adaptor function (MFAF) network element, and the analytics data repository function (ADRF) network element on the basis of NWDAF to meet the trust requirements of NF under the distributed network architecture. Among them, DCCF is used to coordinate the collection and distribution of data, which can avoid multiple subscriptions and responses to the same data. MFAF is used to format data and can adapt between the protocols defined by 3GPP. ADRF is used to store data, retrieve data, and analyze data.

[0087] For example, when a data consumer network element has a data analysis requirement, it can send a data analysis request to the DCCF network element. The DCCF network element forwards the request to the AnLF network element, which performs the data analysis. The AnLF network element needs to use the model and related data to complete the data analysis, so it obtains the model and related data from the DCCF network element.

[0088] If the ADRF network element stores the relevant data, the DCCF network element can instruct the ADRF network element to send the relevant data to the AnLF network element. If the ADRF network element does not store the relevant data, the DCCF network element can instruct the data provider network element to send the relevant data to the MFAF network element. After receiving the relevant data, the MFAF network element sends it to the AnLF network element. At the same time, the MFAF network element also sends the relevant data to the ADRF network element for storage.

[0089] If the model is stored in the ADRF network element, the DCCF network element can instruct the ADRF network element to send the model to the AnLF network element. If the model is not stored in the ADRF network element, the DCCF network element can instruct the ADRF network element to send the historical data to the AnLF network element. After receiving the historical data, the AnLF network element forwards it to the MTLF network element. The MTLF network element trains the model based on the historical data and returns the model to the AnLF network element.

[0090] The AnLF network element completes data analysis based on the relevant data and model, obtains a response corresponding to the request, and returns the response to the data consumer network element through the DCCF network element.

[0091] However, the aforementioned network architecture centrally stores the model and related data within the ADRF network element, potentially creating a single point of failure and potential DDoS attacks. Furthermore, the security of this solution's related data and models relies entirely on user trust in the operator, so the solution's reliability needs to be improved.

[0092] As mentioned above, current solutions for implementing NF trustworthiness still have some shortcomings. Since 6G architecture tends to be distributed, it is necessary to consider meeting trustworthiness requirements within a distributed network architecture. One readily conceivable solution is to directly apply distributed technologies from the IT field to a distributed network architecture. However, applying distributed technologies directly to a distributed network architecture may present some problems:

[0093] (1) DHT lacks a trust mechanism, and the discrete nature of DHT technology leads to detours in the node query process.

[0094] (2) DLT is prone to problems such as block chain expansion and privacy leakage. In addition, due to the immutability of DLT, DLT cannot meet the requirements of relevant laws and regulations such as PIPL and GDPR on the right to data erasure.

[0095] (3) Single-point technology (DLT or DHT) poses security risks.

[0096] In view of this, this application proposes a trustworthy-distributed hash table (T-DHT) technology to enable the distributed network architecture to meet the trust requirements. As shown in Figure 1 (a), T-DHT can be understood as an organic combination of DLT and DHT.

[0097] The ADRF network element is integrated into the DHT in T-DHT. That is, the DHT can store data (for example, the data may include at least one of related data and models, related data and historical data corresponding to the models, models, and historical data corresponding to the models).

[0098] Authentication, authorization and access control (AAA) functions and DCCF network elements are integrated into DLT in T-DHT. That is, DLT can implement functions such as data access and control, and the publication of relevant data and / or models.

[0099] For example, as shown in Figure 1(b), T-DHT technology can employ a combined on-chain and off-chain storage approach. This approach stores some data (such as historical data used for model training and user personal data) off-chain (i.e., in the DHT), while other data (such as public data such as public keys) is stored on-chain (i.e., in the DLT). The off-chain data is packaged, and the hash value of the packaged data is stored on-chain. Because this storage approach stores both historical and personal data off-chain and their hash values ​​on-chain, it conserves on-chain storage space, thereby addressing blockchain bloat. Furthermore, because the data stored on-chain can be shared, models can be deployed or shared across multiple MTLF network elements. Furthermore, because user personal data is stored off-chain, the risk of privacy leaks is reduced. In other words, T-DHT technology employs a combined DHT and DLT storage approach.

[0100] Furthermore, T-DHT technology uses Byzantine attack resistance to address the security risks inherent in single-point technologies. The immutability of DLT enhances DHT, making T-DHT technology trustworthy. Load balancing and a location-aware DHT solution consider the location relationship between logical and physical nodes when selecting storage nodes, addressing DHT's inherent detour issues and improving system computational efficiency.

[0101] Based on the above T-DHT technology, the present application provides a distributed network architecture, wherein the distributed network architecture may include a first NF network element, a second NF network element, a third NF network element, and a sixth NF network element.

[0102] Optionally, the first NF network element is used to provide service requirements. Exemplarily, the first NF network element may be a data consumer network element.

[0103] Optionally, the second NF network element is used to use distributed ledger technology to record the storage status of data required to implement business requirements, where the storage status includes whether the third NF network element stores the model data and the first data required to implement the business requirements, and the storage addresses of the model data and the first data.

[0104] Exemplarily, the second NF network element may be a DLT network element in T-DHT. For ease of description, DLT network elements in T-DHT are collectively referred to as DLH network elements below. Optionally, the third NF network element is configured to store the model data and the first data using distributed hash table technology. Exemplarily, the third NF network element may be a DHT network element in T-DHT. For ease of description, DHT network elements in T-DHT are collectively referred to as DHT network elements below.

[0105] Optionally, the third NF network element may respectively calculate hash values ​​of the model data and the first data stored therein, and send the hash values ​​to the second NF network element, and the second NF network element records the hash values.

[0106] Optionally, the sixth NF network element has the function of determining a response corresponding to the service demand. Exemplarily, the sixth NF network element may be an AnLF network element.

[0107] Optionally, the distributed network architecture based on T-DHT technology provided in this application may also include at least one of a fourth NF network element or a fifth NF network element.

[0108] Optionally, the fourth NF network element has the function of model training and providing the model to other network elements. Exemplarily, the fourth NF network element can be a MTLF network element.

[0109] Optionally, the fifth NF network element is used to provide data corresponding to the service demand. Exemplarily, the fifth NF network element may be a data provider network element.

[0110] For example, taking the first NF network element as a data consumer network element, the second NF network element as a DLT network element, the third NF network element as a DHT network element, the fourth NF network element as an MTLF network element, the fifth NF network element as a data provider network element, and the sixth NF network element as an AnLF network element as an example, the distributed network architecture provided by this application can be shown in Figure 2 or Figure 3.

[0111] As shown in Figure 2 or Figure 3, data consumer network elements, AnLF network elements, and DHT network elements can interact with each other. DLT network elements, AnLF network elements, and DTH network elements can also interact with each other. AnLF network elements can also interact with MTLF network elements. In the distributed network architecture shown in Figure 2, DHT technology is not used in the implementation of AnLF and MTLF network elements. In the distributed network architecture shown in Figure 3, DHT technology is used in the implementation of AnLF and MTLF network elements.

[0112] In addition to the above-mentioned distributed network architecture, the present application also provides a method for implementing a network function, which is used to implement the network function under the above-mentioned distributed network architecture. The following will introduce the method for implementing the network function provided by the present application in conjunction with the accompanying drawings. It can be understood that in the embodiments of the present application, the execution subject can perform some or all of the steps in the embodiments of the present application. These steps or operations are only examples, and the embodiments of the present application can also perform other operations or variations of various operations. In addition, the various steps can be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all operations in the embodiments of the present application need to be performed.

[0113] It should be noted that the names of messages between devices or the names of parameters in messages in the following embodiments of this application are only examples, and other names may be used in specific implementations, and this embodiment of the application does not specifically limit this. As shown in Figure 4, a method for implementing a network function provided in an embodiment of this application includes the following steps:

[0114] S401: A first NF sends first information to a sixth NF. Accordingly, the sixth NF receives the first information from the first NF. The first information indicates a model type and data type corresponding to a service requirement of the first NF. Optionally, the first information may include the model type and data type corresponding to the service requirement.

[0115] For example, business needs include but are not limited to data analysis needs, such as analyzing and predicting the status of an event within a certain time period (such as business load), or analyzing the truth of an event (such as whether an alarm is triggered by a real emergency).

[0116] Optionally, the service requirement may be generated by the application layer of the first NF network element, or may be sent to the first NF network element by other network elements, or may be input by a user, and this application does not make any specific restrictions on this.

[0117] Optionally, after the first NF network element obtains the business demand, it can determine the model type and data type corresponding to the business demand based on the preconfigured correspondence, thereby carrying the model type and data type corresponding to the business demand in the first information.

[0118] Exemplarily, the preconfigured correspondence may include model types and data types corresponding to various business requirements.

[0119] Optionally, after receiving the first information, the sixth NF determines, based on the model type and data type corresponding to the service requirement, model data and first data required to implement the service requirement. The model data is used to determine the first model, so that the sixth NF can implement the service requirement (i.e., a response corresponding to the service requirement) based on the first model and the first data.

[0120] Optionally, the first NF network element sending the first information to the sixth NF network element includes: the first NF network element sending a first message to the sixth NF network element, where the first message includes the first information and a digital signature of the first NF network element. In other words, the first information may be included in the first message. The digital signature of the first NF network element is used to verify the integrity of the first information.

[0121] Based on this optional solution, the digital signature of the first NF network element can be used to ensure the data security of the first information, prevent the first message from being tampered with, and reduce the accuracy of the response to the business demand.

[0122] Optionally, the first message may further include an identification (ID) of the first message.

[0123] Based on this optional solution, the ID of the first message is used to ensure the uniqueness of the first message, avoiding the system from repeatedly executing the service requirements of the first message and wasting resources. As shown in Figure 5, the first message may include a model type, a data type, a digital signature of the first NF network element, and the ID of the first message.

[0124] S402: The second NF sends second information to the sixth NF. In response, the sixth NF receives the second information from the second NF. The second information indicates the storage status of data required to implement the service requirement in the third NF. The storage status includes whether the third NF stores the model data and first data required to implement the service requirement, and the storage addresses of the model data and first data. The model data is used to determine the first model.

[0125] Optionally, the second information may include first indication information. The first indication information indicates whether the first model is stored in the third NF network element, and when the first indication information indicates that the first model is stored in the third NF network element, the first indication information further indicates whether the first model needs to be updated.

[0126] Among them, when the first indication information indicates that the first model is not stored in the third NF network element, the model data includes the second data, and the second data is used to train to obtain the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the model data includes the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the model-related data includes the first model and the third data, and the third data is used to update the first model to obtain the second model.

[0127] Exemplarily, since the second NF records the storage status of data required for the service needs of the third NF, the second NF can determine whether the first model is stored in the third NF by determining whether the first model is recorded. For example, if the hash value of the first model is stored in the second NF (i.e., the first model is recorded in the second NF), it indicates that the first model is stored in the third NF and does not need to be updated; if the hash value of the second data is stored in the second NF (i.e., the second NF records the second data), it indicates that the first model is not stored in the third NF; if the hash value of the first model and the hash value of the third data are stored in the second NF (i.e., the first model and the third data are recorded in the second NF), it indicates that the first model is stored in the third NF and needs to be updated.

[0128] Optionally, different functions of the first indication information may be represented by different bit values.

[0129] For example, 2 bits are used to represent the first indication information. If the value of the 2 bits is 00, the first indication information indicates that the first model is not stored in the third NF network element. If the value of the 2 bits is 01, the first indication information indicates that the first model is stored in the third NF network element and needs to be updated. If the value of the 2 bits is 10, the first indication information indicates that the first model is stored in the third NF network element and does not need to be updated.

[0130] It should be noted that the above is merely an exemplary description of the correspondence between the values ​​of the two bits of the first indication information and the function of the first indication information. Of course, the correspondence between the values ​​of the two bits and the function of the first indication information is not limited to the above example. In practice, other corresponding situations may exist. For example, when the value of the two bits is 11, the first indication information indicates that the first model is not stored in the third NF network element. This application will not elaborate on this further.

[0131] Optionally, the second information may further include a first pointer. Exemplarily, the first pointer may be implemented in the following three possible ways:

[0132] In a first possible implementation, when the first indication information indicates that the first model is not stored in the third NF, the first pointer indicates a first storage address, where the first storage address is a storage address of the second data in the third NF.

[0133] In a second possible implementation, when the first indication information indicates that the first model is stored in the third NF and the first model does not need to be updated, the first pointer indicates a second storage address, where the second storage address is the storage address of the first model in the third NF.

[0134] In a third possible implementation, when the first indication information indicates that the first model stored in the third NF network element needs to be updated, the first pointer indicates a third storage address and a second storage address, and the third storage address is a storage address of the third data in the third NF network element.

[0135] Optionally, the first pointer indicates the third storage address and the second storage address in the following manner: the first pointer includes a first sub-pointer and a second sub-pointer. Exemplarily, the first sub-pointer indicates the third storage address, and the second sub-pointer indicates the second storage address.

[0136] Based on this possible solution, for different scenarios indicated by the first indication information, the first pointer indicates the storage address of the first model, the storage address for obtaining the data of the first model (i.e., the second data), or the storage address for obtaining the data of the second model (the first model and the third data), so that the sixth NF network element can obtain the first model, the data for obtaining the first model, or the data for obtaining the second model from the storage address according to the first pointer.

[0137] Optionally, the second information may further include second indication information, where the second indication information indicates whether the first data is stored in the third NF network element.

[0138] Exemplarily, because the second NF records the storage status of data required for the service needs of the third NF, the second NF can determine whether the first data is stored in the third NF by determining whether the first data is recorded. For example, if the hash value of the first data is stored in the second NF (i.e., the first data is recorded in the second NF), it indicates that the first data is stored in the third NF; if the hash value of the first data is stored in the second NF (i.e., the first data is not recorded in the second NF), it indicates that the first data is not stored in the third NF.

[0139] Optionally, different functions of the second indication information may be represented by different bit values.

[0140] For example, a single bit representing the second indication information is used as an example. When the single bit is a first value, the second indication information indicates that the third NF network element does not store the first data. When the single bit is a second value, the first indication information indicates that the third NF network element stores the first data. Optionally, the first value may be 0, and correspondingly, the second value may be 1. Alternatively, the first value may be 0, and correspondingly, the second value may be 1.

[0141] It should be noted that the above is merely an example of how the function of the second information can be indicated by the first indication information and the second indication information. In practice, the function of the second information can also be indicated by a single indication information, that is, the first indication information and the second indication information can be combined into a single indication information. This application will not elaborate further.

[0142] Optionally, the second information may further include a second pointer. Exemplarily, the second pointer may be implemented in the following two possible ways:

[0143] In a possible implementation, when the second indication information indicates that the first data is stored in the third NF network element, the second pointer indicates a fourth storage address, where the fourth storage address is the storage address of the first data in the third NF network element.

[0144] In another possible implementation, when the second indication information indicates that the first data is not stored in the third NF network element, the second pointer indicates a fifth storage address, where the fifth storage address is the storage address of the first data in the fifth NF network element.

[0145] Based on this possible solution, for different scenarios indicated by the second indication information (such as whether the first data is stored in the third NF network element), the second pointer indicates the storage address of the first data in different scenarios, so that the sixth NF network element can obtain the first data according to the storage address.

[0146] Optionally, the second information may further include access policy information, wherein the access policy information indicates whether the first NF network element has data access rights.

[0147] Exemplarily, the access policy information may be represented by one bit. When the one bit is a first value, the access policy information indicates that the first NF network element has data access rights. When the one bit is a second value, the access policy information indicates that the first NF network element does not have data access rights. Optionally, the first value may be 0, and correspondingly, the second value may be 1. Alternatively, the first value may be 0, and correspondingly, the second value may be 1.

[0148] Optionally, the second NF network element sending the second information to the sixth NF network element includes: the second NF network element sending a second message to the sixth NF network element, where the second message includes the second information and a digital signature of the second NF network element. In other words, the second information may be included in the second message. The digital signature of the second NF network element is used to verify the integrity of the second information.

[0149] Based on this optional solution, the digital signature of the second NF network element is used to ensure the data security of the second information, preventing the second message from being tampered with, which in turn reduces the accuracy of the response to the business demand.

[0150] Optionally, the second message may further include an ID of the second message. That is, as shown in FIG5 , the second message may include the first indication information, the second indication information, the first pointer, the second pointer, the access policy information, the digital signature of the second NF network element, and the ID of the second message.

[0151] Based on this optional solution, the ID of the second message is used to ensure the uniqueness of the second message, thereby preventing the system from repeatedly determining the second message and then repeatedly executing the response to the business demand, which wastes resources.

[0152] Optionally, before step S402, as shown in FIG6 , the method for implementing the network function may further include step S405:

[0153] S405: The sixth NF sends a query message to the second NF. Accordingly, the second NF receives the query message from the second NF. The query message is used to query the first model and the first data. Based on the query message, the second NF sends a second message to the sixth NF.

[0154] Optionally, after receiving the first information, the sixth NF network element sends query information to the second NF network element. In other words, based on the triggering of the first information, the sixth NF network element sends query information to the second NF network element.

[0155] S403: The sixth NF network element obtains the first model and the first data according to the second information.

[0156] Optionally, step S403 may include step S403a and step S403b:

[0157] Step S403a: obtaining a first model according to the second information;

[0158] Step S403b: Obtain first data according to the second information.

[0159] It should be noted that there is no restriction on the order in which step S403a and step S403b are performed. For example, step S403a can be performed before step S403b; or step S403a can be performed after step S403b; or step S403a can be performed simultaneously with step S403b. This embodiment of the present application does not impose any limitation.

[0160] For step S403a:

[0161] Optionally, when the first indication information indicates that the first model is not stored in the third NF network element, or when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the sixth NF network element obtains the first model according to the second information. Optionally, the sixth NF network element obtains the first model according to the second information, including: the sixth NF network element obtains the first model according to the first indication information and the first pointer.

[0162] Optionally, when the first indication information indicates that the third NF stores a first model and the first model needs to be updated, the sixth NF may obtain the first model according to the second information and then obtain a second model according to the first model. The second model is the updated first model.

[0163] Optionally, the sixth NF network element obtains the first model based on the second information, including: when the access policy information indicates that the first NF network element has data access rights, the sixth NF network element obtains the first model or the second model based on the second information. In other words, the sixth NF network element serves the first NF network element (for example, the sixth NF network element determines a response to a service demand of the first NF network element), and therefore the sixth NF network element needs to know whether the first NF network element has data access rights. Only when the first NF network element has data access rights can the sixth NF network element obtain the first model or the second model from the storage address of the third NF network element indicated by the first pointer according to the first indication information.

[0164] For step S403b:

[0165] Optionally, the sixth NF network element obtains the first data according to the second information, including: obtaining the first data according to the second indication information and the second pointer.

[0166] Optionally, the sixth NF acquiring the first data according to the second information includes: when the access policy information indicates that the first NF has data access rights, the sixth NF acquiring the first data according to the second information. That is, when the first NF has data access rights, the sixth NF can acquire the first data from the storage address of the third NF or the fifth NF indicated by the second pointer according to the second indication information.

[0167] That is, before step S403, the sixth NF network element determines the indication of the access policy information. If the access policy information indicates that the first NF network element has the data access right, the sixth NF network element executes step S403.

[0168] S404: The sixth NF network element determines a response to the service demand based on the first model and the first data.

[0169] Optionally, when the first indication information indicates that the first model is not stored in the third NF network element, or the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the sixth NF network element determines a response to the service demand based on the first model and the first data.

[0170] Optionally, when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the sixth NF network element determines the response to the business demand based on the first model and the first data, including: the sixth NF network element obtains the updated first model (i.e., the second model) based on the first model, and determines the response to the business demand based on the second model and the first data.

[0171] Optionally, the sixth NF network element inputs the first data into the first model or the second model, so that the first model or the second model outputs a response to the service demand.

[0172] For example, if the business requirement is a data analysis requirement, the response to the business requirement is the analysis result corresponding to the data analysis requirement. For example, if the data analysis requirement is to predict the status of an event within a certain time period, the response to the business requirement is the status information of the event within that time period; or if the data analysis requirement is to analyze the truth of an alarm event, the response to the business requirement is the analysis result of the truth of the alarm event.

[0173] Optionally, if the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, before step S404, the sixth NF network element may determine whether the first model has been tampered with. If the first model has not been tampered with, step S404 is performed. Exemplarily, determining whether the first model has been tampered with can be implemented based on the following three methods:

[0174] In a first possible implementation, the sixth NF may compare the first hash value of the first model with the second hash value of the first model. If the first hash value and the second hash value are consistent, the sixth NF determines that the first model stored in the third NF has not been tampered with. The first hash value is the hash value corresponding to the first model calculated by the third NF, and the second hash value is the hash value of the first model recorded in the second NF.

[0175] Illustratively, the third NF network element may perform hash value calculation on the first model currently stored in the third NF network element (ie, the latest first model) to determine the first hash value.

[0176] Exemplarily, when the third NF network element stores the first model for the first time, it may calculate the hash value (referred to as the second hash value) of the first model stored for the first time, and send the second hash value to the second NF network element. The second NF network element receives and records the second hash value of the first model.

[0177] Based on this possible implementation, since the first model is stored off-chain (i.e., the third NF network element) and the second hash value of the first model is recorded on-chain (i.e., the second NF network element), the first model stored off-chain may be tampered with. Before determining the response to the business demand, the sixth NF network element can compare the first hash value with the second hash value to determine whether the first model has been tampered with. When the first hash value is consistent with the second hash value, it indicates that the first model has not been tampered with, that is, after the sixth NF network element determines that the first model has not been tampered with, it determines the response to the business demand based on the first model and the first data, avoiding the use of the tampered first model to determine the response to the business demand, thereby improving the accuracy of the response to the business demand.

[0178] In a second possible implementation, the sixth NF may compare the fifth hash value of the first model with the second hash value of the first model. If the fifth hash value matches the second hash value, the sixth NF determines that the first model has not been tampered with during transmission from the third NF to the sixth NF. The fifth hash value is the hash value corresponding to the first model determined by the sixth NF, and the second hash value is the hash value of the first model recorded in the second NF.

[0179] Illustratively, the sixth NF network element may perform hash value calculation on the first model received from the third NF network element to determine a fifth hash value.

[0180] Based on this possible implementation, since the first model may be tampered with during the process of the third NF network element sending the first model to the sixth NF network element, before determining the response to the service demand, the sixth NF network element can compare the first hash value with the second hash value to determine whether the first model has been tampered with during the transmission process from the third NF network element to the sixth NF network element. When the fifth hash value is consistent with the second hash value, it indicates that the first model has not been tampered with. That is, after the sixth NF network element determines that the first model has not been tampered with, it determines the response to the service demand based on the first model and the first data, avoiding the use of the tampered first model to determine the response to the service demand, thereby improving the accuracy of the response to the service demand.

[0181] In a third possible implementation, combining the above two possible implementations, the sixth NF network element may compare the first hash value, the second hash value, and the fifth hash value. If the first hash value, the second hash value, and the fifth hash value are consistent, it is determined that the first model has not been tampered with.

[0182] Optionally, the method for obtaining the first hash value, the second hash value, and the fifth hash value may refer to the method for obtaining the first hash value, the second hash value, and the fifth hash value in the above two possible implementations, and this application will not repeat them here.

[0183] Based on this possible implementation, since the first model is stored off-chain (third NF network element), or there is a risk of tampering during the transmission of the first model from the third NF network element to the sixth NF network element. Therefore, before determining the response to the business demand, the sixth NF network element can compare the first hash value, the second hash value, and the fifth hash value to determine whether the first model has been tampered with. In the case of the first hash value, the second hash value, and the fifth hash value, it indicates that the first model has not been tampered with, that is, after the sixth NF network element determines that the first model has not been tampered with, it determines the response to the business demand based on the first model and the first data, avoiding the use of the tampered first model to determine the response to the business demand, thereby improving the accuracy of the response to the business demand.

[0184] Optionally, when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, or when the first indication information indicates that the third NF network element does not store the first model, the sixth NF network element does not need to compare the hash values.

[0185] Optionally, if the second indication information indicates that the first data is stored in the third NF network element, before step S404, the sixth NF network element may determine whether the first data has been tampered with, and if the first data has not been tampered with, perform step S404. Exemplarily, determining whether the first data has been tampered with can be implemented based on the following three methods:

[0186] In a first possible implementation, the sixth NF may compare the third hash value of the first data with the fourth hash value of the first data. If the third hash value and the fourth hash value are consistent, the sixth NF determines that the first data stored in the third NF has not been tampered with. The third hash value is the hash value corresponding to the first data calculated by the third NF, and the fourth hash value is the hash value of the first data recorded by the second NF.

[0187] Illustratively, the third NF network element may perform hash value calculation on the current first data stored in the third NF network element to determine a third hash value.

[0188] Exemplarily, when the third NF network element stores the first data for the first time, it may calculate and send a hash value (called a fourth hash value) of the first data stored for the first time to the second NF network element, and the second NF network element receives and records the fourth hash value of the first data.

[0189] Based on this possible implementation, since the first data is stored off-chain (i.e., the third NF network element) and the fourth hash value of the first data is recorded on-chain (i.e., the second NF network element), the first data stored off-chain may be tampered with. Before determining the response to the business demand, the sixth NF network element compares the third hash value with the fourth hash value to determine whether the first data has been tampered with. When the third hash value is consistent with the fourth hash value, it indicates that the first data has not been tampered with, that is, after the sixth NF network element determines that the first data has not been tampered with, it determines the response to the business demand based on the first model and the first data, avoiding the use of the tampered first data to determine the response to the business demand, thereby improving the accuracy of the response to the business demand.

[0190] In a second possible implementation, the sixth NF may compare the sixth hash value of the first data with the fourth hash value of the first data. If the sixth hash value matches the fourth hash value, the sixth NF determines that the first data has not been tampered with during transmission from the third NF to the sixth NF. The sixth hash value is the hash value corresponding to the first data determined by the sixth NF, and the fourth hash value is the hash value of the first data recorded in the second NF.

[0191] Illustratively, the sixth NF network element may perform hash value calculation on the first data received from the third NF network element to determine a sixth hash value.

[0192] Based on this optional solution, since the first data may be tampered with during the process of the third NF network element sending the first data to the sixth NF network element, before determining the response to the service demand, the sixth NF network element can compare the third hash value with the fourth hash value to determine whether the first data has been tampered with during the transmission process from the third NF network element to the sixth NF network element. When the sixth hash value is consistent with the fourth hash value, it means that the first data has not been tampered with. That is, after the sixth NF network element determines that the first data has not been tampered with, it determines the response to the service demand based on the first model and the first data, avoiding the use of the tampered first data to determine the response to the service demand, thereby improving the accuracy of the response to the service demand.

[0193] In a third possible implementation, combining the above two possible implementations, the sixth NF network element may compare the third hash value, the fourth hash value, and the sixth hash value, and determine that the first data has not been tampered with when the third hash value, the fourth hash value, and the sixth hash value are consistent.

[0194] Optionally, the method for obtaining the third Hash value, the fourth Hash value, and the sixth Hash value may refer to the method for obtaining the third Hash value, the fourth Hash value, and the sixth Hash value in the above two possible implementations, which will not be described in detail in this application.

[0195] Based on this possible implementation, since the first data is stored off-chain (third NF network element), or there is a risk of tampering during the transmission of the first data from the third NF network element to the sixth NF network element. Therefore, before determining the response to the business demand, the sixth NF network element can compare the third hash value, the fourth hash value, and the sixth hash value to determine whether the first data has been tampered with. In the case of the third hash value, the fourth hash value, and the sixth hash value, it indicates that the first data has not been tampered with, that is, after the sixth NF network element determines that the first data has not been tampered with, it determines the response to the business demand based on the first model and the first data, avoiding the use of the tampered first data to determine the response to the business demand, thereby improving the accuracy of the response to the business demand.

[0196] Optionally, after the sixth NF network element queries the hash value of the first model or the hash value of the first data using at least one of the six possible implementation methods, a query record corresponding to the query may be stored.

[0197] Exemplarily, the query record may be stored on the chain (ie, the second NF network element).

[0198] Optionally, the query record may include the number of times the hash value of the first model or the first data is queried, and further, may include the result of comparing the hash values ​​of the query (such as the hash values ​​are consistent, or the hash values ​​are inconsistent).

[0199] Optionally, after step S404, as shown in FIG6 , the method for implementing the network function may further include step S406:

[0200] S406: The sixth NF sends a response corresponding to the service requirement to the first NF. Correspondingly, the first NF receives the response from the sixth NF.

[0201] Based on the above-mentioned method for implementing network functions, the second NF network element is used to use distributed ledger technology to record the storage status of the data required to implement the business (i.e., on-chain storage), and the third NF network element is used to use distributed hash table technology to store data (i.e., off-chain storage). The security of user data and privacy is improved through a combination of on-chain and off-chain storage methods, thereby meeting the trust requirements of the distributed network architecture. While meeting the trust requirements of the distributed network architecture, the sixth NF network element determines the storage status of the data required to implement the business requirements from the second NF network element based on the model type and data type corresponding to the business requirements, and then obtains the first model and first data corresponding to the business requirements based on the data storage status, and determines the response to the business requirements based on the first data and the first model. In this way, network functions can be implemented while the distributed network architecture meets the trust requirements.

[0202] The following describes the acquisition of the first model involved in the above step S403a. Exemplarily, the acquisition of the first model in step S403a can be based on the following two possible implementations:

[0203] As a first possible implementation, the sixth NF network element obtains the second data for training the first model from the first storage address, and then obtains the first model based on the second data.

[0204] Optionally, when the first indication information indicates that the first model is not stored in the third NF network element, after step S402, as shown in FIG7a , the method for implementing the network function may include steps S407-S410, that is, the above step S403a may include steps S407-S410:

[0205] S407: The sixth NF network element obtains the second data from the first storage address.

[0206] Exemplarily, the sixth NF may send a first request message to the third NF, where the first request message is used to request the second data in the first storage address. After receiving the first request message, the third NF sends the second data to the sixth NF, so that the sixth NF obtains the second data.

[0207] S408: The sixth NF sends the second data to the fourth NF. Correspondingly, the fourth NF receives the second data from the sixth NF.

[0208] S409: The fourth NF network element performs model training according to the second data to obtain a first model.

[0209] S410: The fourth NF sends the first model to the sixth NF. Correspondingly, the sixth NF receives the first model from the fourth NF.

[0210] Optionally, after step S410, as shown in FIG7a , the method for implementing the network function may further include step S411:

[0211] S411: The sixth NF sends the first model to the third NF. Correspondingly, the third NF receives the first model from the sixth NF and stores the first model.

[0212] Based on the above possible implementation, if the third NF does not store the first model, the sixth NF obtains the second data used to train the first model from the third NF, and then trains the first model with the fourth NF, thereby obtaining the first model. The first model is stored in the third NF, allowing other NFs to directly use the first model when they need it, without the need for retraining. This reduces resource consumption and improves system efficiency.

[0213] As a second possible implementation, the sixth NF network element obtains the first model from the second storage address.

[0214] Optionally, when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, after step S402, as shown in FIG7b , the method for implementing the network function may include steps S412-S413, that is, the above step S403a may include steps S412-S413:

[0215] S412: The sixth NF sends a second request to the third NF. Correspondingly, the third NF receives the second request from the sixth NF, wherein the second request requests the first model stored in the second storage address.

[0216] Illustratively, the second request information may carry the second storage address.

[0217] S413: The third NF sends the first model to the sixth NF. Correspondingly, the sixth NF receives the first model from the third NF.

[0218] Based on the above possible implementation, if the third NF already stores the first model and the first model does not need to be updated, the sixth NF directly obtains the first model from the third NF. This allows other NFs to directly use the first model when they need to use it, without the need for retraining, thereby reducing resource consumption and improving system operational efficiency.

[0219] The acquisition of the first model is described above. The acquisition of the second model involved in the above step S403a is introduced below.

[0220] Optionally, the sixth NF obtains the first model from the second storage address, obtains third data from the third storage address, and then obtains the second model based on the third data and the first model, wherein the third data is used to update the first model.

[0221] Optionally, the sixth NF network element obtains the first model from the second storage address, obtains the third data from the third storage address, and uses the fourth NF network element to update the first model, thereby obtaining the second model.

[0222] Exemplarily, the sixth NF network element can obtain the first model from the second storage address by referring to the above steps S412-S413 to obtain the first model. After step S413, as shown in FIG7c, the implementation method of the network function may include steps S414-S418:

[0223] S414: The sixth NF sends a third request to the third NF. Accordingly, the third NF receives the third request from the sixth NF, wherein the third request is for requesting the third data in the third storage address.

[0224] Illustratively, the third request information may carry a third storage address.

[0225] S415: The third NF sends the third data to the sixth NF. Correspondingly, the sixth NF receives the third data from the third NF.

[0226] S416: The sixth NF sends the first model and the third data to the fourth NF. Correspondingly, the third NF receives the first model and the third data from the sixth NF.

[0227] S417: The fourth NF updates the model according to the first model and the third data to obtain a second model.

[0228] S418: The fourth NF sends the second model to the sixth NF. Correspondingly, the sixth NF receives the second model from the fourth NF.

[0229] Optionally, after step S418, the sixth NF network element may send the second model to the third NF network element, and the third NF network element stores the second model.

[0230] Optionally, the third NF network element stores the second model, calculates a hash value of the second model, and stores the hash value of the second model on the chain (second NF network element).

[0231] Optionally, when the sixth NF obtains the second model, after step S403, as shown in FIG7c , step S404a may be executed:

[0232] S404a: The sixth NF network element determines a response to the service demand based on the second model and the first data.

[0233] It should be noted that the above steps S412-S418 are merely exemplary descriptions of the process for obtaining the second model. The order of execution between steps S412 and S414, and the order of execution between steps S413 and S415, can refer to the order of execution between steps S403a and S403b. This application will not elaborate further.

[0234] The above is an explanation of how to obtain the second model. The following describes how to obtain the first data in step S403b. For example, the first data can be obtained based on the following two possible implementations:

[0235] As a first possible implementation, the sixth NF network element obtains the first data from the third NF network element.

[0236] Optionally, the sixth NF network element obtains the first data according to the second indication information and the second pointer, including: when the second indication information indicates that the first data is stored in the third NF network element, the sixth NF network element obtains the first data from the fourth storage address indicated by the second pointer.

[0237] Exemplarily, when the second indication information indicates that the first data is stored in the third NF network element, after step S403a, as shown in FIG8a , the method for implementing the network function may include steps S419-S420, that is, the above-mentioned step S403b may include steps S419-S420:

[0238] S419: The sixth NF sends a fourth request to the third NF. Correspondingly, the third NF receives the fourth request from the sixth NF, wherein the fourth request requests the first data in the fourth storage address.

[0239] Illustratively, the fourth request information may carry a fourth storage address.

[0240] S420: The third NF sends the first data to the sixth NF. Correspondingly, the sixth NF receives the first data from the third NF.

[0241] As a second possible implementation, the sixth NF network element obtains the first data from the fifth NF network element.

[0242] Optionally, obtaining the first data according to the second indication information and the second pointer includes: when the second indication information indicates that the first data is not stored in the third NF network element, the sixth NF network element obtains the first data from the fifth storage address indicated by the second pointer.

[0243] When the second indication information indicates that the first data is not stored in the third NF network element, after step S403a, as shown in FIG8b , the method for implementing the network function may include steps S421-S424, that is, the above step S403b may include steps S421-S424:

[0244] S421: The sixth NF sends third information to the fifth NF. In response, the fifth NF receives the third information from the sixth NF. The third information is used to request the fifth NF to store the first data stored at the fifth storage address in the third NF. S422: The fifth NF sends first data to the third NF. In response, the third NF receives the first data from the fifth NF.

[0245] S423: The third NF network element stores the first data.

[0246] S424: The third NF sends the first data to the sixth NF. Correspondingly, the sixth NF receives the first data from the third NF.

[0247] The above is an explanation of obtaining the first data. The following is an introduction to the application scenarios of the embodiments of the present application.

[0248] Exemplarily, according to the instructions of the first indication information and the second indication information, the embodiment of the present application may include the following six scenarios:

[0249] Scenario 1: The third NF stores the first model and the first data, and the first model does not need to be updated.

[0250] FIG9 shows a distributed network architecture suitable for scenario 1, which includes a first NF, a second NF, a third NF, and a sixth NF. The interactions between the various NFs in the distributed architecture can be as shown in FIG9 .

[0251] Specifically, the first NF network element can send the first information to the sixth NF network element. After receiving the first information, the sixth NF network element determines the first data corresponding to the data type and the model data corresponding to the model type, and then queries the second NF network element for the first data and model data. The sixth NF network element receives the query result (i.e., the second information) from the second NF network element. In this case, the second information indicates that the first model and the first data are stored in the third NF network element and that the first model does not need to be updated. That is, the model data includes the first model, and the second information includes the second storage address and the fourth storage address. Therefore, the sixth NF network element obtains the first model from the second storage address of the third NF network element and obtains the first data from the fourth storage address of the third NF network element. Based on the first model and the first data, the sixth NF network element determines a response corresponding to the service requirement and sends the response corresponding to the service requirement to the first NF network element.

[0252] Optionally, the process of the sixth NF network element obtaining the first model from the third NF network element may refer to steps S412-S413 in Figure 7b above; the process of the sixth NF network element obtaining the first data from the third NF network element may refer to steps S419-S420 in Figure 8a above. This application will not repeat them.

[0253] It should be noted that the above steps S412-S413 and steps S419-S420 are merely exemplary descriptions of the process for obtaining the first model and the first data. The order of execution between steps S412 and S419, and the order of execution between steps S413 and S420, can refer to the order of execution between steps S403a and S403b. This application will not elaborate further.

[0254] Optionally, if step S412 and step S419 can be performed simultaneously, they can be combined into a single step. For example, the sixth NF sends a sixth request message to the third NF, requesting the first model stored in the second storage address and the first data stored in the fourth storage address. In this case, the second request message in step S412 and the fourth request message in step S419 are combined into the sixth request message.

[0255] Scenario 2: The third NF stores the first data but does not store the first model.

[0256] FIG10 shows a distributed network architecture suitable for scenario 2, which includes a first NF, a second NF, a third NF, a fourth NF, and a sixth NF. The interactions between the various NFs in the distributed architecture can be as shown in FIG10 .

[0257] Specifically, the first NF can send first information to the sixth NF. After receiving the first information, the sixth NF determines the first data corresponding to the data type and the model data corresponding to the model type, and then queries the second NF for the first data and model data. The sixth NF receives the query result (i.e., second information) from the second NF. The second information indicates that the third NF stores the first data but not the first model, i.e., the model data includes the second data, and the second information includes the first storage address and the fourth storage address. Therefore, the sixth NF obtains the second data from the first storage address of the third NF and obtains the first data from the fourth storage address of the third NF. After obtaining the second data, the sixth NF sends the second data to the fourth NF. The fourth NF trains a first model based on the second data and sends the trained first model to the sixth NF. Based on the trained first model and the first data, the sixth NF determines a response corresponding to the service requirement and sends the response corresponding to the service requirement to the first NF.

[0258] Optionally, the process of the sixth NF obtaining the second data from the third NF and then obtaining the first model based on the second data can refer to steps S407-S410 in FIG. 7 a ; the process of the sixth NF obtaining the first data from the third NF can refer to steps S419-S420 in FIG. 8 a . This application will not repeat them in detail.

[0259] Optionally, in the case where the sixth NF obtains the second data by sending the first request message to the third NF in step S407, the first request message in step S407 and the fourth request message in step S419 may be combined into a seventh request message. The seventh request message requests the second data in the first storage address and the first data in the fourth storage address.

[0260] Scenario 3: The third NF stores the first model but not the first data, and the first model does not need to be updated.

[0261] FIG11 shows a distributed network architecture suitable for Scenario 3, which includes a first NF, a second NF, a third NF, a fifth NF, and a sixth NF. The interactions between the various NFs in the distributed architecture can be as shown in FIG11 .

[0262] Specifically, the first NF can send a first message to the sixth NF. After receiving the first message, the sixth NF determines the first data corresponding to the data type and the model data corresponding to the model type, and then queries the second NF for the first and model data. The sixth NF receives the query result (i.e., the second message) from the second NF. The second message indicates that the third NF stores the first model but not the first data, and that the first model does not need to be updated. That is, the model data includes the first model, and the second message includes the second storage address and the fifth storage address. Therefore, the sixth NF obtains the first model from the second storage address of the third NF and obtains the first data from the fifth storage address of the fifth NF. In the process of obtaining the first data, the fifth NF first sends the first data to the third NF for storage, which then forwards the first data to the sixth NF. Based on the first model and the first data, the sixth NF determines a response corresponding to the service requirement and sends the response corresponding to the service requirement to the first NF.

[0263] Optionally, the process of the sixth NF network element obtaining the first model from the third NF network element can refer to steps S412-S413 in Figure 7b above; the process of the sixth NF network element obtaining the first data from the fifth NF network element can refer to steps S421-S424 in Figure 8b above. This application will not repeat them.

[0264] It should be noted that the above steps S412-S413 and steps S421-S424 are merely exemplary descriptions of the process for obtaining the first model and the first data. The order of execution between steps S412 and S421, and the order of execution between steps S413 and S424 may refer to the order of execution between steps S403a and S403b. This application will not elaborate further.

[0265] Scenario 4: The first model and the first data are not stored in the third NF.

[0266] FIG12 shows a distributed network architecture suitable for Scenario 4. The distributed network architecture includes a first NF, a second NF, a third NF, a fourth NF, a fifth NF, and a sixth NF. The interactions between the various NFs in the distributed architecture can be as shown in FIG12 .

[0267] Specifically, the first NF network element can send first information to the sixth NF network element. After receiving the first information, the sixth NF network element determines the first data corresponding to the data type and the model data corresponding to the model type, and queries the second NF network element for the first data and model data. The sixth NF network element receives second information from the second NF network element. The second information indicates that the first model and the first data are not stored in the third NF network element, that is, the model data includes the second data, and the second information includes the first storage address and the fifth storage address. Therefore, the sixth NF network element obtains the second data from the first storage address of the third NF network element and sends the second data to the fourth NF network element for model training to obtain the first model. The sixth NF network element obtains the first data from the fifth storage address of the fifth NF network element. Based on the first model and the first data, the sixth NF network element determines a response corresponding to the service requirement and sends the response corresponding to the service requirement to the first NF network element.

[0268] Optionally, the process of the sixth NF network element obtaining the first model from the third NF network element may refer to steps S407-S410 in Figure 7a above; the process of the sixth NF network element obtaining the first data from the fifth NF network element may refer to steps S421-S424 in Figure 8b above. This application will not repeat them.

[0269] It should be noted that the above steps S407-S410 and steps S421-S424 are merely exemplary descriptions of the process for obtaining the first model and the first data. The order of execution between steps S407 and S421, and the order of execution between steps S410 and S424, can refer to the order of execution between steps S403a and S403b. This application will not elaborate further.

[0270] Scenario 5: The third NF stores the first model and the first data, and the first model needs to be updated.

[0271] FIG13 shows a distributed network architecture suitable for Scenario 5. The distributed network architecture includes a first NF, a second NF, a third NF, a fourth NF, and a sixth NF. The interactions between the various NFs in the distributed architecture can be as shown in FIG13 .

[0272] Specifically, in scenario five, the first NF can send a first message to the sixth NF. After receiving the first message, the sixth NF determines the first data corresponding to the data type and the model data corresponding to the model type, and queries the second NF for the first and model data. The sixth NF then receives a second message from the second NF. The second message indicates that the third NF stores the first model and first data and that the first model needs to be updated. Specifically, the model data includes the first model and third data, and the second message includes a second storage address, a third storage address, and a fourth storage address. Therefore, the sixth NF retrieves the first model from the second storage address of the third NF, retrieves the third data from the third storage address of the third NF, and sends the first and third data to the fourth NF for model update, thereby obtaining the second model. The sixth NF then retrieves the first data from the fourth storage address of the third NF. Based on the second model and the first data, the sixth NF determines a response corresponding to the service requirement and sends the response to the first NF.

[0273] Optionally, the process of the sixth NF network element acquiring the second model may refer to steps S412-S418 in Figure 7c above; the process of the sixth NF network element acquiring the first data may refer to steps S419-S420 in Figure 8a above. This application will not repeat them any further.

[0274] It should be noted that the above steps S412-S418 and steps S419-S420 are merely exemplary descriptions of the process for obtaining the second model and the first data. The order of execution of at least one of steps S412 or S414 and step S419 may refer to the order of execution of steps S403a and S403b. This application will not elaborate further.

[0275] Optionally, the second request information in step S412, the third request information in step S414, and the fourth request information in step S419 are combined into an eighth request information as shown in Figure 13. The eighth request information requests the first model in the second storage address, the third data in the third storage address, and the first data in the fourth storage address.

[0276] Scenario 6: The third NF stores the first model but not the first data, and the first model needs to be updated.

[0277] FIG14 shows a distributed network architecture suitable for Scenario 6. The distributed network architecture includes a first NF, a second NF, a third NF, a fourth NF, a fifth NF, and a sixth NF. The interactions between the various NFs in the distributed architecture can be as shown in FIG14 .

[0278] Specifically, in scenario six, the first NF can send a first message to the sixth NF. After receiving the first message, the sixth NF determines the first data corresponding to the data type and the model data corresponding to the model type, and queries the second NF for the first and model data. The sixth NF then receives a second message from the second NF. The second message indicates that the third NF stores the first model but not the first data, and that the first model needs to be updated. Specifically, the model data includes the first model and the third data, and the second message includes the second storage address, the third storage address, and the fifth storage address. Therefore, the sixth NF retrieves the first model from the second storage address of the third NF, retrieves the third data from the third storage address of the third NF, and sends the first and third data to the fourth NF for model update, thereby obtaining the second model. The sixth NF then retrieves the first data from the fifth storage address of the fifth NF. Based on the second model and the first data, the sixth NF determines a response corresponding to the service requirement and sends the response to the first NF.

[0279] Optionally, the process of the sixth NF network element acquiring the second model may refer to steps S412-S418 in Figure 7c above; the process of the sixth NF network element acquiring the first data may refer to steps S421-S424 in Figure 8b above. This application will not repeat them any further.

[0280] It should be noted that the above steps S412-S418 and steps S421-S424 are merely exemplary descriptions of the process for obtaining the second model and the first data. The order of execution of at least one of step S412 or step S414 and step S421, and the order of execution of at least one of step S413 or step S415 and step S424 may refer to the order of execution of step S403a and step S403b. This application will not elaborate further.

[0281] Optionally, the second request information in step S412 and the third request information in step S414 may be combined into a ninth request information as shown in Figure 14. The ninth request information requests the first model in the second storage address and the third data in the third storage address.

[0282] It can be understood that in each of the above embodiments, the implementation method and / or steps of the network function can also be implemented by components of the communication device corresponding to the implementation method of the network function (such as a processor, chip, chip system, circuit, logic module, or software such as a chip or circuit).

[0283] The above mainly introduces the solutions provided by this application. Accordingly, this application also provides a communication device, which is used to implement the various methods described above. The communication device can be the communication device in the above method embodiments, or include the above communication device, or can be a component that can be used in a communication device, such as a chip or chip system.

[0284] It is understandable that, in order to realize the above functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0285] The embodiment of the present application can divide the functional modules of the communication device according to the above method embodiment. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. In actual implementation, there may be other division methods.

[0286] 15 shows a schematic structural diagram of a communication device 150. The communication device 150 includes a processing module 1501 and a communication module 1502. The communication device 150 can be used to implement the functions of each NF network element described above.

[0287] In some embodiments, the communication device 150 may further include a storage module (not shown in FIG. 15 ) for storing program instructions and data.

[0288] In some embodiments, the communication module 1502, which may also be referred to as a transceiver unit, is configured to implement a sending and / or receiving function. The communication module 1502 may be composed of a transceiver circuit, a transceiver, a transceiver, or a communication interface.

[0289] In some embodiments, the communication module 1502 may include a receiving module and a sending module, which are respectively used to execute the receiving and sending steps performed by each NF network element in the above method embodiment, and / or used to support other processes of the technology described herein; the processing module 1501 may be used to execute the processing steps (such as determination, generation, etc.) performed by each NF network element in the above method embodiment, and / or used to support other processes of the technology described herein.

[0290] When the communication device 150 is used to implement the functions of the sixth NF network element:

[0291] In some embodiments, the communication module 1502 is used to receive first information from a first NF network element, where the first information indicates a model type and a data type corresponding to a business requirement of the first NF network element; the communication module 1502 is also used to receive second information from a second NF network element, where the second information indicates a storage status of data required to implement the business requirement in a third NF network element; the processing module 1501 is used to obtain a first model and first data based on the second information; the processing module 1501 is also used to determine a response to the business requirement based on the first model and the first data.

[0292] Among them, the second NF network element is used to record the storage status of data using distributed ledger technology, and the third NF network element is used to store data using distributed hash table technology. The data includes model data corresponding to the model type and first data corresponding to the data type. The model data is used to determine the first model.

[0293] Optionally, the second NF network element may be a DLT network element, and the third NF network element may be a DHT network element.

[0294] Optionally, the second information includes first indication information, the first indication information indicating whether the first model is stored in the third NF network element, and when the first indication information indicates that the first model is stored in the third NF network element, the first indication information also indicates whether the first model needs to be updated; wherein, when the first indication information indicates that the first model is not stored in the third NF network element, the model data includes second data, and the second data is used to train to obtain the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the model data includes the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the model data includes the first model and third data, and the third data is used to update the first model to obtain the second model.

[0295] Optionally, the second information also includes a first pointer; when the first indication information indicates that the first model is not stored in the third NF network element, the first pointer indicates a first storage address, the first storage address is the storage address of the second data in the third NF network element, and the second data is used to train the first model; when the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the first pointer indicates a second storage address, and the second storage address is the storage address of the first model in the third NF network element; when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the first pointer indicates a third storage address and a second storage address, the third storage address is the storage address of the third data in the third NF network element, and the third data is used to update the first model.

[0296] Optionally, the processing module 1501 is further configured to obtain the first model from the second storage address.

[0297] Optionally, the processing module 1501 is further configured to obtain second data from the first storage address. The communication module 1502 is further configured to send the second data to a fourth NF network element and receive the first model from the fourth NF network element. The communication module 1502 is further configured to send the first model to a third NF network element.

[0298] Optionally, the processing module 1501 is also used to obtain third data from a third storage address; the communication module 1502 is also used to send the third data and the first model to the fourth NF network element; the communication module 1502 is also used to receive a second model from the fourth NF network element, where the second model is an updated model of the first model.

[0299] Optionally, the processing module 1501 is further configured to determine a response to the business requirement based on the second model and the first data.

[0300] Optionally, the communication module 1502 is further used to send the second model to the third NF network element.

[0301] Optionally, when the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the first pointer includes a first sub-pointer and a second sub-pointer; the first sub-pointer indicates the third storage address, and the second sub-pointer indicates the second storage address.

[0302] Optionally, the second information also includes second indication information, and the second indication information indicates whether the first data is stored in the third NF network element.

[0303] Optionally, the second information also includes a second pointer; when the second indication information indicates that the first data is stored in the third NF network element, the second pointer indicates a fourth storage address, and the fourth storage address is the storage address of the first data in the third NF network element; when the second indication information indicates that the first data is not stored in the third NF network element, the second pointer indicates a fifth storage address, and the fifth storage address is the storage address of the first data in the fifth NF network element, and the fifth NF network element is used to provide data corresponding to the service requirements.

[0304] Optionally, the processing module 1501 is further configured to obtain the first data according to the second indication information and the second pointer.

[0305] Optionally, the processing module 1501 is further configured to obtain the first data from the fourth storage address.

[0306] Optionally, the communication module 1502 is further used to send third information to the fifth NF network element, where the third information requests the fifth NF network element to store the first data stored in the fifth storage address in the third NF network element; the communication module 1502 is also used to receive the first data from the third NF network element.

[0307] Optionally, the communication module 1502 is further configured to receive a first message from the first NF network element, where the first message includes the first information and a digital signature of the first NF network element.

[0308] Optionally, the second information also includes access policy information, where the access policy information indicates whether the first NF network element has data access rights.

[0309] Optionally, the processing module 1501 is also used to compare the first hash value of the first model with the second hash value of the first model, where the first hash value is the hash value of the first model determined by the sixth NF network element, and the second hash value is the hash value of the first model recorded in the second NF network element; when the first hash value is consistent with the second hash value, the response to the business demand is determined based on the first model and the first data.

[0310] Optionally, the processing module 1501 is also used to compare the third hash value of the first data with the fourth hash value of the first data, where the third hash value is the hash value of the first data determined by the sixth NF network element, and the fourth hash value is the hash value of the first data recorded in the second NF network element; when the third hash value is consistent with the fourth hash value, the response to the business demand is determined based on the first model and the first data.

[0311] Optionally, the processing module 1501 is also used to compare the first hash value of the first model with the second hash value of the first model, where the first hash value is the hash value of the first model calculated by the third NF network element, and the second hash value is the hash value of the first model recorded in the second NF network element; when the first hash value is consistent with the second hash value, the response to the business demand is determined based on the first model and the first data.

[0312] Optionally, the processing module 1501 is also used to compare the fifth hash value of the first model with the second hash value of the first model, where the fifth hash value is the hash value of the first model determined by the sixth NF network element, and the second hash value is the hash value of the first model recorded in the second NF network element; when the fifth hash value is consistent with the second hash value, the response to the business demand is determined based on the first model and the first data.

[0313] Optionally, the processing module 1501 is also used to compare the third hash value of the first data with the fourth hash value of the first data, where the third hash value is the hash value of the first data calculated by the third NF network element, and the fourth hash value is the hash value of the first data recorded in the second NF network element; when the third hash value is consistent with the fourth hash value, the response to the business demand is determined based on the first model and the first data.

[0314] Optionally, the processing module 1501 is also used to compare the sixth hash value of the first data with the fourth hash value of the first data, where the sixth hash value is the hash value of the first data determined by the sixth NF network element, and the fourth hash value is the hash value of the first data recorded in the second NF network element; when the sixth hash value is consistent with the fourth hash value, the response to the business demand is determined based on the first model and the first data.

[0315] Among them, all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.

[0316] In the present application, the communication device 150 may be presented in the form of functional modules divided in an integrated manner. The "module" here may refer to a specific application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, an integrated logic circuit, and / or other devices that can provide the above functions.

[0317] In some embodiments, when the communication device 150 in Figure 15 is a chip or a chip system, the function / implementation process of the communication module 1502 can be implemented through the input and output interface (or communication interface) of the chip or chip system, and the function / implementation process of the processing module 1501 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0318] Since the communication device 150 provided in this embodiment can execute the above method, the technical effects that can be obtained can refer to the above method embodiments and will not be repeated here.

[0319] As a possible product form, the communication device described in the embodiments of the present application can also be implemented using the following: one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0320] As another possible product form, the communication device in this application may adopt the structure shown in Figure 16, or include the components shown in Figure 16. Figure 16 is a schematic diagram of the composition of a communication device 1600 provided in this application, and the communication device 1600 may be a communication device or a chip or system on chip in a communication device.

[0321] As shown in FIG16 , the communication device 1600 includes at least one processor 1601 and at least one communication interface ( FIG16 is merely an example of one communication interface 1604 and one processor 1601). Optionally, the communication device 1600 may further include a communication bus 1602 and a memory 1603.

[0322] Processor 1601 can be a general-purpose central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. Processor 1601 can also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0323] Communication bus 1602 is used to connect the various components in communication device 1600, enabling communication between them. Communication bus 1602 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, for example. This bus can be categorized as an address bus, a data bus, a control bus, and so on. For ease of illustration, FIG16 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0324] Communication interface 1604 is used to communicate with other devices or communication networks. Exemplarily, communication interface 1604 can be a module, circuit, transceiver, or any other device capable of communication. Optionally, communication interface 1604 can also be an input / output interface within processor 1601, used to implement signal input and output to the processor.

[0325] The memory 1603 may be a device with a storage function, used to store instructions and / or data, wherein the instructions may be computer programs.

[0326] Exemplarily, the memory 1603 may be a read-only memory (ROM) or other types of static storage devices that can store static information and / or instructions, or a random access memory (RAM) or other types of dynamic storage devices that can store information and / or instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0327] It should be noted that the memory 1603 can exist independently of the processor 1601 or can be integrated with the processor 1601. The memory 1603 can be located within the communication device 1600 or outside the communication device 1600, without limitation. The processor 1601 can be used to execute instructions stored in the memory 1603 to implement the methods provided in the following embodiments of the present application.

[0328] As an optional implementation, the communication device 1600 may further include an output device 1605 and an input device 1606. The output device 1605 communicates with the processor 1601 and can display information in a variety of ways. For example, the output device 1605 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 1606 communicates with the processor 1601 and can receive user input in a variety of ways. For example, the input device 1606 can be a mouse, a keyboard, a touch screen device, or a sensor device.

[0329] In some embodiments, in terms of hardware implementation, those skilled in the art may conceive that the communication device 150 may take the form of the communication device 1600 shown in FIG. 16 .

[0330] As an example, the functions / implementation process of the processing module 1501 in FIG15 can be implemented by the processor 1601 in the communication device 1600 shown in FIG16 calling the computer-executable instructions stored in the memory 1603. The functions / implementation process of the communication module 1502 in FIG15 can be implemented by the communication interface 1604 in the communication device 1600 shown in FIG16.

[0331] It should be noted that the structure shown in FIG16 does not constitute a specific limitation on the communication device. For example, in other embodiments of the present application, the communication device may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0332] In some embodiments, an embodiment of the present application further provides a communication device, which includes a processor for implementing the method in any of the above method embodiments.

[0333] As a possible implementation, the communication device further includes a memory. The memory is used to store necessary computer programs and data. The computer program may include instructions, and the processor may invoke the instructions in the computer program stored in the memory to instruct the communication device to execute any of the above-described method embodiments. Of course, the memory may not be located in the communication device.

[0334] As another possible implementation, the communication device also includes an interface circuit, which is a code / data read / write interface circuit, and the interface circuit is used to receive computer execution instructions (computer execution instructions are stored in a memory, may be read directly from the memory, or may pass through other devices) and transmit them to the processor.

[0335] As another possible implementation, the communication device further includes a communication interface, where the communication interface is used to communicate with a module outside the communication device.

[0336] It can be understood that the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or include chips and other discrete devices. The embodiments of the present application do not specifically limit this.

[0337] The present application also provides a computer-readable storage medium having a computer program or instruction stored thereon, which implements the functions of any of the above method embodiments when executed by a computer.

[0338] The present application also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

[0339] Those skilled in the art will appreciate that, for the sake of convenience and brevity of description, the specific working processes of the above-described systems, devices, and units may refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0340] It is understood that the systems, devices, and methods described in this application may also be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of devices or units, and may be electrical, mechanical, or other forms.

[0341] The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Components shown as units may or may not be physical units. Some or all of these units may be selected to achieve the objectives of this embodiment as needed.

[0342] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0343] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)). In the embodiment of the present application, the computer may include the aforementioned device.

[0344] Although the present application is described herein in conjunction with various embodiments, in the process of implementing the claimed application, those skilled in the art can understand and implement other changes to the disclosed embodiments by reviewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple situations. A single processor or other unit can implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0345] Although the present application has been described with reference to specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the scope of the present application. Accordingly, this specification and the drawings are merely illustrative of the present application as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, the present application is intended to include such modifications and variations as fall within the scope of the claims of the present application and their equivalents.

Claims

1. A method for implementing a network function, characterized in that: The method comprises: Receiving first information from a first network function NF network element, where the first information indicates a model type and a data type corresponding to a service requirement of the first NF network element; receiving second information from a second NF network element, where the second information indicates a storage status of data required to implement the service requirement in a third NF network element, where the second NF network element is used to record the storage status of the data by using a distributed ledger technology, and the third NF network element is used to store the data by using a distributed hash table technology, where the data includes model data corresponding to the model type and first data corresponding to the data type, and the model data is used to determine the first model; acquiring the first model and the first data according to the second information; A response to the business requirement is determined according to the first model and the first data.

2. The method according to claim 1, characterized in that The second information includes first indication information, The first indication information indicates whether the first model is stored in the third NF network element, and when the first indication information indicates that the first model is stored in the third NF network element, the first indication information also indicates whether the first model needs to be updated; Wherein, when the first indication information indicates that the first model is not stored in the third NF network element, the model data includes second data, and the second data is used to train the first model; When the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the model data includes the first model; The first indication information indicates that the first model is stored in the third NF network element, and when the first model needs to be updated, the model data includes the first model and third data, and the third data is used to update the first model to obtain the second model.

3. The method according to claim 2, characterized in that The second information also includes a first pointer; When the first indication information indicates that the first model is not stored in the third NF network element, the first pointer indicates a first storage address, where the first storage address is a storage address of the second data in the third NF network element; When the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, the first pointer indicates a second storage address, and the second storage address is a storage address of the first model in the third NF network element; When the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the first pointer indicates a third storage address and the second storage address, and the third storage address is the storage address of the third data in the third NF network element.

4. The method according to claim 3, characterized in that When the first indication information indicates that the first model is not stored in the third NF network element, acquiring the first model according to the second information includes: Acquire the second data from the first storage address; Sending the second data to a fourth NF network element, where the fourth NF network element is used for training to obtain the first model; Receive the first model from the fourth NF network element.

5. The method according to claim 4, characterized in that The method further comprises: Send the first model to the third NF network element.

6. The method according to claim 3, characterized in that: When the first indication information indicates that the first model is stored in the third NF network element and the first model does not need to be updated, acquiring the first model according to the second information includes: The first model is obtained from the second storage address.

7. The method according to claim 6, characterized in that Determining a response to the business requirement according to the first model and the first data includes: Compare a first Hash value of the first model with a second Hash value of the first model, where the first Hash value is the Hash value of the first model calculated by the third NF network element, and the second Hash value is the Hash value of the first model recorded in the second NF network element; When the first Hash value is consistent with the second Hash value, a response to the business requirement is determined according to the first model and the first data.

8. The method according to claim 3, characterized in that When the first model is stored in the third NF network element and the first model needs to be updated, acquiring the first model according to the second information includes: Acquire the first model from the second storage address; Acquire the third data from the third storage address; The method further comprises: Sending the third data and the first model to a fourth NF network element; Receive the second model from the fourth NF network element.

9. The method according to claim 8, characterized in that The method further comprises: Send the second model to the third NF network element.

10. The method according to claim 8 or 9, characterized in that: When the first indication information indicates that the first model is stored in the third NF network element and the first model needs to be updated, the first pointer includes a first sub-pointer and a second sub-pointer, the first sub-pointer indicates the third storage address, and the second sub-pointer indicates the second storage address.

11. The method according to any one of claims 8 to 10, characterized in that: Determining a response to the business requirement according to the first model and the first data includes: A response to the business requirement is determined based on the second model and the first data.

12. The method according to any one of claims 1 to 11, characterized in that: The second information includes second indication information, and the second indication information indicates whether the first data is stored in the third NF network element.

13. The method according to claim 12, characterized in that The second information also includes a second pointer; When the second indication information indicates that the third NF network element stores the first data, the second pointer indicates a fourth storage address, and the fourth storage address is a storage address of the first data in the third NF network element; When the second indication information indicates that the third NF network element does not store the first data, the second pointer indicates a fifth storage address, and the fifth storage address is the storage address of the first data in the fifth NF network element.

14. The method according to claim 13, characterized in that When the second indication information indicates that the third NF network element stores the first data, acquiring the first data according to the second information includes: The first data is obtained from the fourth storage address.

15. The method according to claim 14, characterized in that Determining a response to the business requirement according to the first model and the first data includes: Compare a third Hash value of the first data with a fourth Hash value of the first data, where the third Hash value is the Hash value of the first data calculated by the third NF network element, and the fourth Hash value is the Hash value of the first data recorded in the second NF network element; When the third Hash value is consistent with the fourth Hash value, a response to the business requirement is determined according to the first model and the first data.

16. The method according to claim 13, characterized in that When the second indication information indicates that the third NF network element does not store the first data, acquiring the first data according to the second information includes: Sending third information to the fifth NF network element, wherein the third information requests the fifth NF network element to store the first data stored in the fifth storage address in the third NF network element; Receive the first data from the third NF network element.

17. The method according to any one of claims 1 to 16, characterized in that: The receiving first information from the first NF network element includes: A first message is received from the first NF network element, where the first message includes the first information and a digital signature of the first NF network element.

18. The method according to any one of claims 1 to 17, characterized in that: The second information also includes access policy information, and the access policy information indicates whether the first NF network element has data access rights.

19. The method according to claim 18, characterized in that The acquiring the first model and the first data according to the second information includes: When the access policy information indicates that the first NF network element has data access rights, the first model and the first data are acquired according to the second information.

20. A device for implementing a network function, characterized in that: The device for implementing the network function includes a processor; the processor is used to run a computer program or instruction so that the device for implementing the network function executes the method according to any one of claims 1-19.

21. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions or programs. When the computer instructions or programs are executed on a computer, the method according to any one of claims 1 to 19 is executed.

Images