Data processing method and communication apparatus

Abstract

A data processing method and a communication apparatus. An event needing to be simulated can be injected into data generation function network elements of single domains (such as an RAN domain and a CN domain), respectively; the data generation function network element of each single domain simulates and generates simulation data for the corresponding domain on the basis of the injected event, and returns the simulation data to a management service consumer network element; and the management service consumer network element can determine final data (second data) on the basis of the simulation data corresponding to each single domain. Data is generated on the basis of single domain granularity. In addition, the simulation data simulated and generated by data generation function network elements of different single domains all targets data having the same transmission feature, realizing the collaboration of the data generated by different single domains. That is, by performing feature alignment of simulation inputs across the data generation functional network elements of different single domains, independent acquisition of the data by different single domains and the collaboration of the data acquired by the single domains are achieved, thereby providing more accurate data.

Description

Method and communication apparatus for data processing

[0001] The present application claims priority from the Chinese patent application No. 202410770603.3, filed on June 14, 2024, and entitled "Method and communication apparatus for data processing", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and more particularly, to a method and communication apparatus for data processing. BACKGROUND

[0003] In order to obtain an artificial intelligence (AI) or machine learning (ML) model with good effect, a large amount of training data is required. Therefore, network data can be simulated by a data generation function, so as to provide more training data for the AI model or the ML model.

[0004] In the current generation process of AI model or ML model training data, the training data of radio access network (RAN) domain and the training data of core network (CN) domain are not distinguished. The training data collected by the current method is the average value of the training data corresponding to the RAN domain and the CN domain, and the data or indicators corresponding to the RAN domain and the CN domain are not distinguished, that is, the AI model or the ML model training data is not generated according to the domain, which may reduce the precision and accuracy of the AI model or the ML model training data, thereby affecting the precision of the AI model or the ML model. SUMMARY

[0005] The present application provides a method and communication apparatus for data processing. The events to be simulated can be injected into single-domain (for example, including RAN domain and CN domain, etc.) data generation function network elements respectively, so as to generate data according to single-domain granularity. Moreover, the data simulated and generated by different single-domain data generation function network elements are all data for the same transmission characteristics, which ensures that the data simulated and generated by different domain data generation function network elements are matched, and more accurate data can be provided.

[0006] In a first aspect, a method for data processing is provided. The execution subject of the method can be a first network element, a chip, a chip system, or a processor supporting the first network element to implement the method, or a logic node, a logic module, or software capable of implementing all or part of the function of the first network element. The method comprises: receiving, by the first network element, first information from a first domain data generation function network element, the first information comprising: data of the first domain (i.e., simulation data of the first domain) and a first sequence identifier; receiving, by the first network element, second information from a second domain data generation function network element, the second information comprising: data of the second domain (i.e., simulation data of the second domain) and the first sequence identifier, the first domain and the second domain being different; and determining, by the first network element, second data according to the data of the first domain and the data of the second domain and the first sequence identifier, wherein the first sequence identifier is used to indicate an identifier of a data packet or control signaling used by the first domain data generation function network element to generate the data of the first domain, and the data packets or control signaling with the same sequence identifier have the same transmission characteristics.

[0007] The method for data processing provided in the first aspect can inject events that need to be simulated into single-domain data generation function network elements respectively, each single-domain data generation function network element generates data of a corresponding domain according to the injected events and returns the data to a management service consumer network element, and the management service consumer network element can determine the final data according to the data corresponding to each single domain. The data is generated according to the granularity of a single domain. Moreover, the data generated by different single-domain data generation function network elements is all data for the same transmission characteristics, thereby ensuring that the data generated by different domain data generation function network elements matches, and the data generated by different single domains is coordinated. That is, the characteristics of the simulation input of different single-domain data generation function network elements are aligned, the data collected by different single domains is coordinated, and more accurate data is provided.

[0008] For example, the first domain can be a RAN domain, and the second domain can be a CN domain; or the first domain can be a RAN domain, and the second domain can be a TN domain; or the first domain can be a CN domain, and the second domain can be a TN domain, etc. The first network element can be a management service consumer (MnS consumer).

[0009] In a possible implementation of the first aspect, before the first network element receives the first information from the first domain data generation function network element, the method further includes: the first network element sending a first request message to the first domain data generation function network element, the first request message being used to acquire data of the first domain, the first request information including at least one of first event injection indication information, a first event type, a first collection index, or a first collection quantity; wherein the first event injection indication information is used to instruct the first domain data generation function network element to generate according to injected event simulation data, the first event type is used to instruct event content simulated by the first domain data generation function network element, the first collection index is used to instruct a data type collected by the first domain data generation function network element, and the first collection quantity is used to instruct a data quantity collected by the first domain data generation function network element. In this implementation, the first domain data generation function network element can generate data of the first domain according to the first request information, improving the accuracy and efficiency of generating single-domain data.

[0010] For example, the first sequence identifier is an identifier of user plane data packets or control signaling simulated by the first domain data generation function network element. Data packets or control signaling of the same sequence identifier have the same transmission characteristics or input characteristics. The input characteristics represent specific characteristics of the user plane data packets or control signaling.

[0011] In a possible implementation of the first aspect, the first information further includes input characteristics used to instruct transmission characteristics of the data packets or control signaling, and before the first network element receives second information from the second domain data generation function network element, the method further includes: the first network element sending a second request message to the second domain data generation function network element, the second request information being used to acquire data of the second domain, the second request information including at least one of second event injection indication information, a second event type, or a second collection index, and the first sequence identifier and the input characteristics. In this implementation, the first domain data generation function network element and the second domain data generation function network element can simulate data of the same transmission characteristics, and the data simulated by the first domain data generation function network element and the second domain data generation function network element can be matched or corresponding.

[0012] For example, one sequence identifier can correspond to (or uniquely determine) one input characteristic, which includes multiple specific transmission characteristics, or multiple transmission characteristics constitute the input characteristic. Different data packets or different control signaling correspond to different sequence identifiers, and input characteristics corresponding to different data packets or different control signaling can be different or the same, or in other words, input characteristics corresponding to different sequence identifiers can be different or the same. However, data packets or control signaling of the same sequence identifier have the same transmission characteristics. That is, data packets or control signaling of the same sequence identifier correspond to the same transmission characteristics.

[0013] For example, the input features can include: frequency of user plane data packet transmission, packet size, transmission delay, control signaling function, object or signaling size, etc.

[0014] In a possible implementation of the first aspect, the second event type is the same as the first event type, the second collection index is the same as the first collection index, and the second collection quantity is the same as the first collection quantity. In this implementation, the event simulated by the first-domain data generation function network element and the second-domain data generation function network element, the same collection index, and the same collection quantity can be guaranteed, and the accuracy and efficiency of generating single-domain data are improved.

[0015] In a possible implementation of the first aspect, the first request information further includes: an address of the second-domain data generation function network element and verification information of the second-domain data generation function network element; and before receiving the second information from the second-domain data generation function network element, the method further includes: sending, by the first network element, a third request message to the second-domain data generation function network element, the third request message being used to acquire data of the second domain, the third request message including: at least one of second event injection indication information, a second event type, or a second collection index, and first indication information and verification information of the second-domain data generation function network element; and the first indication information is used to indicate that another node triggers the second-domain data generation function network element to generate data of the second domain. In this implementation, the second-domain data generation function network element is triggered by another node to generate data, and the flexibility of the implementation is improved.

[0016] In a possible implementation of the first aspect, the first collection index or the second collection index includes a network performance index and / or an alarm index, and the network performance index and / or the alarm index includes at least one of: a time delay, a packet error rate, a packet loss rate, a protocol data unit (PDU) session quantity, or a throughput.

[0017] In a possible implementation of the first aspect, the first network element determines the second data according to the data of the first domain and the data of the second domain and the first sequence identifier, and the determination includes: the first network element integrates data of the same collection index corresponding to the same data packet or control signaling with the same sequence identifier in the data of the first domain and the data of the second domain, to obtain the second data. In this implementation, the first network element can integrate the data of a single domain to obtain the final data, and the accuracy of the data is improved.

[0018] In a possible implementation of the first aspect, the second data includes: the data of the first domain and / or the data of the second domain. In this implementation, in the case that the indexes collected by different single domains are different, the finally determined data can include the data collected by different single domains, that is, no integration is needed, and the implementation is simple.

[0019] In a second aspect, a method for data processing is provided. The execution subject of the method can be a first domain data generation function network element, a chip, a chip system, or a processor supporting the first domain data generation function network element to implement the method, or a logic node, a logic module, or software, etc. that can implement all or part of the function of the first domain data generation function network element. The method comprises: receiving, by the first domain data generation function network element, first request information from a first network element, the first request information being used to acquire data of a first domain, the first request information comprising at least one of first event injection indication information, a first event type, a first collection index, or a first collection quantity; generating, by the first domain data generation function network element, data of the first domain according to the first request information; and sending, by the first domain data generation function network element, the data of the first domain and a first sequence identifier to the first network element, the first sequence identifier being used to indicate an identifier of a data packet or control signaling used in the generation of the data of the first domain, and the data packet or control signaling with the same sequence identifier having the same transmission characteristics; wherein the first event injection indication information is used to indicate that the data of the first domain is generated by the first domain data generation function network element according to an injected event, the first event type is used to indicate the content of the event simulated by the first domain data generation function network element, the first collection index is used to indicate the type of data collected by the first domain data generation function network element, and the first collection quantity is used to indicate the quantity of data collected by the first domain data generation function network element.

[0020] The method for data processing provided in the second aspect enables the generation of data according to a single domain granularity, because each single domain data generation function network element generates data of a corresponding domain according to an injected event and returns the data to a management service consumer network element.

[0021] In a possible implementation manner of the second aspect, the first request information further comprises an address of a second domain data generation function network element and verification information of the second domain data generation function network element, and the first domain and the second domain are different. The method further comprises: sending, by the first domain data generation function network element, second indication information to the second domain data generation function network element, the second indication information being used to trigger the second domain data generation function network element to generate data, and the second indication information comprising the verification information of the second domain data generation function network element, the first sequence identifier, and input characteristics, the input characteristics being used to indicate the transmission characteristics of the data packet or control signaling. In this implementation manner, different single domain data generation function network elements use the same sequence identifier (transmission characteristics) to simulate the generation of data, thereby enabling the data generated by different single domain data generation function network elements to be coordinated, and making the data generated by a single domain more accurate.

[0022] In a possible implementation manner of the second aspect, the second indication information further comprises at least one of the first event injection indication information, the first event type, the first collection index, or the first collection quantity.

[0023] In a possible implementation of the second aspect, the first domain data generation function network element generates data of the first domain according to the first request information, including: the first domain data generation function network element determines events that need to be simulated according to the first event type; and the first domain data generation function network element determines the value of the collection index corresponding to the data packet or control signaling in the transmission process according to the first collection index and the first collection quantity in the process of simulating the occurrence of the event.

[0024] In a third aspect, a data processing method is provided. The execution subject of the method can be a second domain data generation function network element, a chip, a chip system, or a processor supporting the second domain data generation function network element to implement the method, or a logic node, a logic module, or software that can implement all or part of the function of the second domain data generation function network element. The method includes: the second domain data generation function network element receives third request information from a first network element, the third request information being used to obtain data of a second domain, and the third request information including first indication information and verification information of the second domain data generation function network element; the first indication information is used to indicate that another node triggers the second domain data generation function network element to generate data of the second domain; the second domain data generation function network element receives second indication information from a first domain data generation function network element, the second indication information being used to trigger the second domain data generation function network element to generate data of the second domain, and the second indication information including the verification information of the second domain data generation function network element, a first sequence identifier, and an input feature; the first sequence identifier is used to indicate the identifier of a data packet or control signaling used by the first domain data generation function network element to generate data of the first domain, and the data packet or control signaling with the same sequence identifier has the same transmission feature; the input feature is used to indicate the transmission feature of the data packet or control signaling; and the first domain and the second domain are different; the second domain data generation function network element determines the data of the second domain according to the third request information and the second indication information; and the second domain data generation function network element sends the data of the second domain and the first sequence identifier to the first network element.

[0025] The data processing method provided in the third aspect generates simulation data of a corresponding domain according to injected events and returns the simulation data to a management service consumer network element, which implements data generation in a single-domain granularity. In addition, different single-domain data generation function network elements use the same sequence identifier (transmission feature) to simulate the generation of data, which implements the cooperation of data generated by different single-domain data generation function network elements, and makes the data generated by a single domain more accurate.

[0026] In a possible implementation manner of the third aspect, the third request message further includes at least one of second event injection indication information, a second event type, and a second collection index; the second event injection indication information is used to indicate that the second domain data generation function network element is generated according to injected event simulation data, the second event type is used to indicate event content simulated by the second domain data generation function network element, and the second collection index is used to indicate a data type collected by the first domain data generation function network element. In this implementation manner, the accuracy and efficiency of generating single-domain data can be improved.

[0027] In a possible implementation manner of the third aspect, the second indication information further includes at least one of first event injection indication information, a first event type, a first collection index, or a first collection quantity; the first event injection indication information is used to indicate that the first domain data generation function network element is generated according to injected event simulation data, the first event type is used to indicate event content simulated by the first domain data generation function network element, the first collection index is used to indicate a data type collected by the first domain data generation function network element, and the first collection quantity is used to indicate a data quantity collected by the first domain data generation function network element. In this implementation manner, the accuracy and efficiency of generating single-domain data can be improved, and data generated by different single-domain data generation function network elements is coordinated.

[0028] In a possible implementation manner of the third aspect, the second domain data generation function network element determines the data of the second domain according to the third request information and the second indication information, including: the second domain data generation function network element verifies the check information in the third request information and the second indication information; after the check information in the third request information and the second indication information is verified, the second domain data generation function network element determines an event that needs to be simulated according to the second event type or the first event type; the second domain data generation function network element determines transmission characteristics of a data packet or control signaling according to the first sequence identifier and the input feature in the process of simulating the occurrence of the event; and the second domain data generation function network element determines a value of a collection index corresponding to the data packet or control signaling in the transmission process according to the second collection index or the first collection index.

[0029] In a fourth aspect, a communication apparatus is provided, which includes: a module (for example, including a processing module and an interface module) for performing each step in the above first aspect or any possible implementation manner of the first aspect; a module for performing each step in the above second aspect or any possible implementation manner of the second aspect; or a module for performing each step in the above third aspect or any possible implementation manner of the third aspect.

[0030] In a fifth aspect, a communication apparatus is provided, the apparatus comprising at least one processor and a memory, the at least one processor being configured to perform the method according to the first aspect or any possible implementation of the first aspect, the method according to the second aspect or any possible implementation of the second aspect, or the method according to the third aspect or any possible implementation of the third aspect.

[0031] In a sixth aspect, a communication apparatus is provided, the apparatus comprising at least one processor and an interface circuit, the at least one processor being configured to perform the method according to the first aspect or any possible implementation of the first aspect, the method according to the second aspect or any possible implementation of the second aspect, or the method according to the third aspect or any possible implementation of the third aspect.

[0032] In a seventh aspect, a management service consumer is provided, the management service consumer comprising the communication apparatus according to the fourth aspect, or the management service consumer comprising the communication apparatus according to the fifth aspect, or the management service consumer comprising the communication apparatus according to the sixth aspect.

[0033] In an eighth aspect, a single-domain data generation function network element is provided, the single-domain data generation function network element comprising the communication apparatus according to the fourth aspect, or the single-domain data generation function network element comprising the communication apparatus according to the fifth aspect, or the single-domain data generation function network element comprising the communication apparatus according to the sixth aspect.

[0034] In a ninth aspect, a computer program product is provided, the computer program product comprising a computer program which, when executed by a processor, is configured to perform the method according to the first aspect or any possible implementation of the first aspect, the method according to the second aspect or any possible implementation of the second aspect, or the method according to the third aspect or any possible implementation of the third aspect.

[0035] In a tenth aspect, a computer-readable storage medium is provided, the computer-readable storage medium having stored the computer program which, when executed by a processor, is configured to perform the method according to the first aspect or any possible implementation of the first aspect, the method according to the second aspect or any possible implementation of the second aspect, or the method according to the third aspect or any possible implementation of the third aspect.

[0036] In an eleventh aspect, a chip is provided, the chip comprising: a processor configured to invoke and run a computer program from a memory, so that a communication apparatus in which the chip is installed performs the method in the first aspect or any possible implementation of the first aspect, the method in the second aspect or any possible implementation of the second aspect, or the method in the third aspect or any possible implementation of the third aspect.

[0037] In a twelfth aspect, a communication system is provided, the communication system comprising: the single-domain data generation function network element provided in the eighth aspect and the management service consumer provided in the seventh aspect. BRIEF DESCRIPTION OF DRAWINGS

[0038] FIG. 1 is a schematic diagram of a training data collection process used in training of an AI model or an ML model.

[0039] FIG. 2 is a schematic diagram of a communication system suitable for embodiments of the present application.

[0040] FIG. 3 is a schematic diagram of another communication system suitable for embodiments of the present application.

[0041] FIG. 4 is a schematic flowchart of a method of data processing provided by embodiments of the present application.

[0042] FIG. 5 is a schematic flowchart of another method of data processing provided by embodiments of the present application.

[0043] FIG. 6 is a schematic flowchart of another method of data processing provided by embodiments of the present application.

[0044] FIG. 7 is a schematic block diagram of a communication apparatus provided by embodiments of the present application.

[0045] FIG. 8 is a schematic block diagram of another communication apparatus provided by embodiments of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0047] In the description of embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" herein merely describes an association relationship of associated objects, and means that there can be three relationships, for example, A and / or B, which means that there are three cases of A alone, A and B together, and B alone. In addition, in the description of embodiments of the present application, "multiple" means two or more than two.

[0048] Hereinafter, the terms "first", "second", "third", etc. are used only for the purpose of description, and should not be understood as indicating or implying relative importance or a specific number of the technical features indicated. Therefore, the features defined with "first", "second", etc. can explicitly or implicitly include one or more of the features. In the description of the embodiments, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0049] In the embodiments of the present application, each network element can include a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and a memory (also referred to as main memory). The operating system can be any one or more computer operating systems that implement business processing through processes, such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system. The application layer includes applications such as a browser, an address book, word processing software, and instant messaging software. Moreover, the embodiments of the present application do not particularly limit the specific structure of the execution subject of the method provided by the embodiments of the present application, as long as the execution subject can communicate according to the method provided by the embodiments of the present application by running a program in which the code of the method provided by the embodiments of the present application is recorded. For example, the execution subject of the method provided by the embodiments of the present application can be an access network device or a core network device, or a functional module in the access network device or the core network device that can invoke and execute the program.

[0050] In addition, various aspects or features of the present application can be implemented as methods, apparatus, or articles of manufacture using standard programming and / or engineering techniques. The term "article of manufacture" as used in the application encompasses a computer program accessible from any computer-readable device, carrier, or media. For example, computer-readable media can include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, or magnetic strips), optical disks (e.g., compact disk (CD), digital versatile disk (DVD), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROM), card, stick, or key drive, etc.). In addition, the various storage media described herein can represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" can include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0051] For AI or ML model training scenarios, a large amount of training data is usually required to obtain an AI or ML model with good performance. However, there is limited data in the current network, so network data can be simulated by a data generation function to generate high-value data at low cost and provide more data sources for AI or ML models.

[0052] Currently, AI or ML models can be used in different scenarios or cases, and the requirements for training data used for AI or ML model training are different for different application scenarios or cases. In other words, the training data used for training AI or ML models for different scenarios or cases is also different.

[0053] For example, AI or ML models are used in management data analysis service (MDAS) scenarios. MDAS can be used for network slice analysis, such as service experience, throughput, and traffic prediction analysis and prediction (based on AI or ML models) within a slice. To support this analysis service, the network needs to provide various collected performance data, such as average end-to-end (E2E) slice latency, radio access network (RAN) and user equipment (UE) throughput, etc.

[0054] In the above-mentioned MDAS application scenario:

[0055] The feature data input to the AI or ML model (or also referred to as X data or X variable for AI or ML model training) can include: average e2e uplink / downlink delay for a network slice, round-trip packet delay, UL / DL throughput for network and network slice instance, RAN UE throughput, throughput at N3 interface, etc. The N3 interface is the interface between the RAN and the user plane function (UPF) in the core network (CN).

[0056] The output (prediction) result of the AI model or the ML model (or also referred to as Y data, Y variable, label data, etc. trained by the AI model or the ML model) can include: service experience id, service experience issue type, affected objects, service experienced statistics, service experienced predications, etc.

[0057] For example, the label data can be understood as the result predicted by the AI model or the ML model. For example, the AI model or the ML model needs to predict "male" and "female", and the label data can be "male" and "female". In other words, the label data is what the AI model or the ML model needs to predict, which can be understood as the Y variable in simple linear regression. For example, the label data can be the future price of wheat, the animal species shown in the picture, the meaning of the audio clip, or any thing, etc.

[0058] The feature data can be understood as a series of data or information. If the label data is "male" and "female", the feature data can include: age, height, weight, occupation, etc., which can be used to describe the label data as the characteristics of a person or thing. In other words, the feature data can be the variable input by the AI model or the ML model, which can be understood as the X variable in simple linear regression. A simple AI model or ML model may use a single feature, while a more complex AI model or ML model may use millions of features.

[0059] The AI model or the ML model defines the relationship between the feature data and the label data.

[0060] As can be seen from the above MDAS application scenarios, the output result of the AI model or the ML model includes problem positioning (delimitation), such as service experience issue type, whether it is a problem of RAN domain or a problem of CN domain.

[0061] Therefore, it is very important to train the corresponding AI model or ML model according to the use scenario. For example, in the MDAS scenario, the training data used for training the AI model or the ML model needs to include the training data corresponding to the RAN domain and the CN domain respectively.

[0062] Figure 1 shows a schematic diagram of a training data collection process for training an AI model or a ML model. As shown in Figure 1:

[0063] In step 1, a management service consumer (MnS consumer) unit sends an E2E data request to a provisioning or performance collection management service producing (PM MnS producer) unit, which can carry a management object instance (MOI) indicating the requirements or conditions of the E2E data to be collected. In other words, in step 1, the MnS consumer can collect E2E data by creating an MOI through a request. The management service consumer can be understood as a requester of the management service, and the provisioning or performance collection management service producing unit can be understood as a provider of the management service.

[0064] In step 2, the provisioning or performance collection management service producing unit collects E2E data according to the attributes or requirements indicated by the MOI.

[0065] For example, the MOI carries the data name to be collected, the time window, etc.

[0066] In step 3, the provisioning or performance collection management service producing unit sends the collected E2E data to the management service consumer network element.

[0067] Currently, the E2E data collected by the provisioning or performance collection management service producing unit is all average indicators or average data of end-to-end, i.e., average indicators or average data between a UE and a UPF in the core network. For example, it includes the average delay of multiple data packets between the UE and the UPF, etc., and does not distinguish the data or indicators corresponding to the RAN domain and the CN domain. In other words, the currently collected E2E data is the average value of the data or indicators corresponding to the RAN domain and the CN domain, and the E2E data indicates the data transmission parameters on the entire link between the UE and the UPF, which includes the RAN domain and the CN domain.

[0068] It can be seen that the training data used for training the AI model or the ML model is currently average data of end-to-end, but for some AI models or ML models corresponding to a use case, the training data of the AI model or the ML model needs to distinguish the training data corresponding to different domains, i.e., cross-domain AI model or ML model training data. For example, in the above-mentioned MDAS scenario, problem positioning (delimitation) is needed, i.e., the RAN domain data and the CN domain data need to be distinguished. However, the training data collected by the current method is the average value of the training data corresponding to the RAN domain and the CN domain, and the current method does not support generating AI model or ML model training data by domain. Moreover, the training data collected by the current method is all real data in the live network (RAN domain and CN domain).

[0069] In view of this, the application provides a data processing method and a communication device. Events that need to be simulated can be injected into single-domain (for example, including a RAN domain and a CN domain, etc.) data generation function network elements respectively. Each single-domain data generation function network element generates data of a corresponding domain (i.e., simulation data of the corresponding domain) according to the injected events and returns the data to a management service consumer network element. The management service consumer network element can determine final data (second data) according to the simulation data of each single domain. The data is generated according to the granularity of a single domain. Moreover, the simulation data generated by different single-domain data generation function network elements are all for data with the same transmission characteristics, for example, data packets or control signaling with the same transmission characteristics, so as to ensure that the simulation data simulated by different domain data generation function network elements match, and the simulation data generated by different single domains are coordinated. That is, the characteristics of the simulation input of different single-domain data generation function network elements are aligned, the data collected by different single domains is coordinated, and more accurate data is provided.

[0070] For example, the injected events can include corner cases. The corner cases or extreme cases can be understood as cases or data that are difficult to collect in a live network.

[0071] The data generated by the RAN domain can be understood as data generated at a network device (for example, a base station), for example, including data on a link between a terminal device and the network device. The data of the CN domain can be understood as data generated at a core network. For example, including data on a link between a network device and a UPF in the core network.

[0072] It should be understood that in the embodiments of the application, the "events" can be understood as various cases that can be sent in a communication network, for example, base station failure, change of base station power, throughput in a communication process, etc. The "events" can include corner cases.

[0073] To facilitate understanding of the embodiments of the application, first, a communication system suitable for the embodiments of the application is briefly introduced in combination with FIG. 2 and FIG. 3.

[0074] For example, FIG. 2 shows a schematic diagram of a communication system applicable to the embodiments of the present application. As shown in FIG. 2, the communication system includes a third-party management service consumer (MnS consumer), a management service consumer (MnS consumer), an element management system in a RAN domain (EMS-RAN), an element management system in a CN domain (EMS-CN), an element in the RAN domain, an element in the CN domain, and the like.

[0075] The EMS-RAN can include a RAN domain data generation function element, and the EMS-CN can include a CN domain data generation function element. The EMS-RAN and the EMS-CN can be located in an operations, administration and maintenance (OAM) system, and the MnS consumer can also be located in the OAM system. The third-party management service consumer or the management service consumer can be understood as a requestor of simulation data, the RAN domain data generation function element is used to generate simulation data of the RAN domain, and the CN domain data generation function element is used to generate simulation data of the CN domain. The management service consumer (MnS consumer) can forward a simulation data request of the third-party management service consumer.

[0076] Optionally, the management service consumer can be located in a network management system (NMS), and the NMS can also be understood as a cross domain management system. The NMS can also be located in the OAM system. Alternatively, the management service consumer can also be located on any element in the communication system, or in other words, the function of the MnS consumer can be integrated on any element in the communication system.

[0077] Optionally, the element management system (EMS) can also be understood as a single domain management system.

[0078] For another example, FIG. 3 shows another example of a communication system applicable to the embodiments of the present application. As shown in FIG. 3, the communication system includes a third-party management service consumer (MnS consumer), a management service consumer (MnS consumer), a RAN-domain data generation function network element, a CN-domain data generation function network element, a network element in the RAN domain (e.g., including a base station, a UE), a network element in the CN domain (e.g., including a UPF, an AMF, an SMF), and the like.

[0079] It should be understood that in the examples shown in FIG. 2 and FIG. 3, the CN-domain data generation function network element and the RAN-domain data generation function network element can both integrate the NDT function. Alternatively, the CN-domain data generation function network element and the RAN-domain data generation function network element can both implement the NDT function, and the CN-domain data generation function network element and the RAN-domain data generation function network element can respectively implement their data generation functions by using the NDT.

[0080] For example, in the embodiments of the present application, the management service consumer (MnS consumer) can be located in an NMS or a vertical industry system, and is configured to invoke a management service.

[0081] Optionally, in some possible implementations, the system shown in FIG. 2 and FIG. 3 can also not include the third-party management service consumer, in which case the simulation data request can be triggered by the management service consumer.

[0082] It should be understood that the communication system shown in FIG. 2 and FIG. 3 is only exemplary, and should not impose any limitation on the communication system applicable to the embodiments of the present application. For example, the communication system shown in FIG. 2 and FIG. 3 can further include more or fewer network elements, or the communication system can be networked in other manners, and the embodiments of the present application do not limit this.

[0083] In the following examples, the RAN-domain data generation function network element and the CN-domain data generation function network element respectively generate simulation data are taken as examples for illustration.

[0084] It should be understood that the RAN-domain data generation function network element and the CN-domain data generation function network element respectively generating simulation data can be used for AI model or ML model training. Of course, in other implementations of the present application, the simulation data respectively generated by the RAN-domain data generation function network element and the CN-domain data generation function network element can also be used in other scenarios, for example, can be used in network data analysis, self-organized network (SON) decision-making, and the like. The embodiments of the present application do not limit this.

[0085] It should also be understood that, in the following examples, the RAN domain and the CN domain are taken as examples of the single domain, and in other implementations of the present application, the single domain can also include other domains, such as a transport network (TN) domain. Optionally, the transport network can also be referred to as a bearer network, which is located between the access network and the switch, and is a network for transmitting various voice and data services, and is usually optical fiber as the transmission medium. The RAN domain or the CN domain below can be replaced by the TN domain, or the TN domain can also be added on the basis of the RAN domain and the CN domain: The TN domain generates corresponding domain data according to the injected event simulation and returns to the management service consumer network element. The embodiments of the present application are not limited here.

[0086] Optionally, in the embodiments of the present application, any one of the RAN domain, the CN domain or the TN domain can be referred to as a first domain, and the other of the RAN domain, the CN domain or the TN domain can be referred to as a second domain. The first domain and the second domain are different, for example, the first domain can be the RAN domain, and the second domain can be the CN domain; or the first domain can be the RAN domain, and the second domain can be the TN domain; or the first domain can be the CN domain, and the second domain can be the TN domain, and so on. The embodiments of the present application are not limited here.

[0087] FIG. 4 is a schematic flowchart of a method of data processing according to an embodiment of the present application. The method 400 can be applied in the scenarios or communication architectures shown in FIG. 2 or FIG. 3, and of course can also be applied in other communication scenarios or communication architectures that have the above-mentioned problems. The embodiments of the present application are not limited here.

[0088] As shown in FIG. 4, the method 400 shown in FIG. 4 can include S401 to S407. The following will be described in detail in combination with FIG. 4.

[0089] S401, the management service consumer (MnS consumer) sends request information to the RAN domain data generation function network element, the request information being used to obtain simulation data corresponding to the RAN domain, and the request information including at least one of event injection indication information, event type, collection index, or collection quantity.

[0090] Optionally, the request information in S401 can also be referred to as first request information. The event injection indication information, the event type, the collection index, and the collection quantity included in the request information can be referred to as first event injection indication information, first event type, first collection index, and first collection quantity, respectively.

[0091] The event injection indication information (first event injection indication information) is used to indicate that the RAN domain data generation function network element needs to generate simulation data according to the injected event.

[0092] The event type (first event type) indicates which events the RAN domain data generation function network element needs to simulate or emulate.

[0093] For example, the event type can include base station failure, alarm, or corner case.

[0094] For example, the corner case can include communication network failure caused by extreme weather (such as flood, snow disaster), and communication network quality degradation caused by high temperature of base station hardware device.

[0095] The collection index (first collection index) can be understood as which type of simulation data the RAN domain data generation function network element needs to collect. For example, the collection index (first collection index) can include network performance index, alarm index, and the like.

[0096] For example, the collection index can include delay, packet error rate, packet loss rate, PDU session quantity, throughput, and the like. The embodiment of the application does not limit the specific content of the collection index.

[0097] The collection quantity (first collection quantity) can be understood as the number of data sets or the number of simulation data that the RAN domain data generation function network element needs to collect.

[0098] Correspondingly, the RAN domain data generation function network element receives the request information.

[0099] Optionally, the management service consumer (MnS consumer) can also be referred to as a first network element.

[0100] S402, the RAN domain data generation function network element simulates the occurrence of an event and collects the simulation data corresponding to the RAN domain according to the request information.

[0101] Optionally, the simulation data corresponding to the RAN domain can also be referred to as data of the first domain or data corresponding to the RAN domain.

[0102] For example, the RAN domain data generation function network element can determine the event that needs to be simulated according to the event injection indication and the event type, simulate the occurrence of the event, and thus complete the event injection.

[0103] After the RAN domain data generation function network element is injected with the event (that is, in the process of simulating the occurrence of the event by the RAN domain data generation function network element), the RAN domain data generation function network element can randomly simulate the input characteristics (also referred to as transmission characteristics) of the data packet or control signaling, such as the frequency of data packet transmission and the packet size, collect the required index according to the simulated input characteristics, until the requirement of the collection quantity is met, and thus obtain the simulation data corresponding to the RAN domain.

[0104] The input feature can be understood as a transmission feature of the (simulated) data or control signaling used by the RAN domain data generation function network element in the process of simulating the event. For example, the input feature can include the frequency of sending user plane data packets in the RAN domain, the packet size, the transmission delay, and / or the signaling feature of the control plane in the RAN domain. The signaling feature of the control plane in the RAN domain can include, for example, the function, object, signaling size, and the like of the control signaling. Each of the frequency of sending data packets, the packet size, the transmission delay, the function, object, signaling size, and the like of the control signaling can be understood as a transmission feature. In other words, the input feature can represent the specific transmission feature of the data packet (user plane data) or control signaling (control plane data) simulated by the RAN domain data generation function network element. One input feature can include one or more specific transmission features.

[0105] Optionally, the input feature can be determined by the RAN domain data generation function network element itself in the process of simulating the event.

[0106] It can be understood that the RAN domain data generation function network element can use NDT to simulate the occurrence of the event.

[0107] Optionally, the RAN domain data generation function network element can also determine a sequence identifier (which can also be referred to as a first sequence identifier), wherein the sequence identifier is an identifier of the user plane data packet or control signaling simulated by the RAN domain data generation function network element. In other words, the sequence identifier is used to indicate which user plane data packet or which (kind of) control signaling is simulated by the RAN domain data generation function network element. For example, the sequence identifier can be an identifier of the data packet or an identifier of the control signaling (such as RRC, etc.). The input feature represents the specific feature of these user plane data packets or control signaling. The data packets or control signaling of the same sequence identifier have the same transmission feature or input feature.

[0108] In the embodiments of the present application, the RAN domain data generation function network element can determine one or more sequence identifiers, that is, the first sequence identifier can include at least one sequence identifier, and each sequence identifier is used to indicate (identify) one data packet or one (kind of) control signaling. That is, the RAN domain data generation function network element can simulate (emulate) multiple different data flows or multiple (kinds of) control signaling. Different data packets or different control signaling correspond to different sequence identifiers, and the input features corresponding to different data packets or different control signaling can be different or the same, or in other words, the input features corresponding to different sequence identifiers can be different or the same. However, the data packets or control signaling of the same sequence identifier have the same transmission feature. That is, the transmission features corresponding to the data packets or control signaling of the same sequence identifier are the same.

[0109] In other words, one sequence identifier can correspond to (or uniquely determine) one input feature, which includes a plurality of specific transmission features, or a plurality of transmission features constitute the input feature.

[0110] For example, the sequence identifier can be used to distinguish different data packets, which correspond to different sequence identifiers, in the case that the RAN domain data generation function network element simulates a plurality of data packets. The features of the data packets are represented by input features, and each data packet can correspond to a plurality of input features. Of course, if the RAN domain data generation function network element only simulates one data packet, the RAN domain data generation function network element can also not determine the sequence identifier.

[0111] The following examples are used for illustration.

[0112] For example, it is assumed that the RAN domain data generation function network element simulates data packet A and data packet B, which are transmitted from the terminal device to the network device. Data packet A corresponds to input feature A, and data packet B corresponds to input feature B. After simulating the injected event, the RAN domain data generation function network element collects the delay of the RAN domain for data packet A and the packet error rate of the RAN domain for data packet B. The sequence identifier of data packet A can be A, and the sequence identifier of data packet B can be B. The sequence identifier A corresponds to the input feature A, and the sequence identifier B corresponds to the input feature B. The input feature B and the input feature A can be the same or different. The data set (the number of simulation data) collected by the RAN domain data generation function network element can be two, which are the packet error rate and the delay, i.e., the number of collection is two. In other words, the number of sequence identifiers can be the same as the number of collection.

[0113] Of course, data packet A can collect more collection indicators (for example, three), and data packet B can collect more collection indicators (for example, four). In this case, the number of collection can be understood as the sum of the number of indicators collected by data packet A and the number of indicators collected by data packet B (for example, seven), or the number of collection can still be two.

[0114] That is, in the embodiment of the present application, the number of collection can be the same as the number of sequence identifiers, or can be the same as the number of collection indicators.

[0115] Optionally, the collection indicators corresponding to different sequence identifiers (different control signaling or data packets) can be different or the same. One sequence identifier can correspond to one or more collection indicators. In other words, there can be a corresponding relationship between the sequence identifier and the collection indicator.

[0116] It can be understood that the input feature and the sequence identifier can be used to determine which data (user plane data and / or control plane data) and transmission features of the data the RAN domain data generation function network element simulates.

[0117] It should also be understood that the RAN domain data generation function network element generates simulation data corresponding to the RAN.

[0118] S403, the RAN domain data generation function network element returns the simulation data corresponding to the RAN domain to the management service consumer, and the sequence identifier and the input feature.

[0119] Optionally, S403 can also be expressed as: the RAN domain data generation function network element returns first information to the management service consumer, and the first information includes: data of the RAN domain, a first sequence identifier, and an input feature.

[0120] It can be understood that the simulation data of the RAN domain can include: the value of the collected index (index value).

[0121] Optionally, the simulation data of the RAN domain can also include event information simulated by the RAN domain, i.e., event type.

[0122] S404, the management service consumer sends request information to the CN domain data generation function network element, the request information is used to obtain simulation data corresponding to the CN domain, and the request information includes: at least one of event injection indication information, event type, and collected index, and sequence identifier and input feature.

[0123] It should be understood that the sequence identifier and the input feature returned by the RAN domain data generation function network element to the management service consumer in S403 and the sequence identifier and the input feature sent by the management service consumer to the CN domain data generation function network element in S404 are the same, and can include one or more sequence identifiers.

[0124] Optionally, the request information in S404 can also be called second request information. The request information includes: event injection indication information, event type, and collected index, which can be called second event injection indication information, second event type, second collected index, and second collected number, respectively.

[0125] The second event injection indication information is used to instruct the CN domain data generation function network element to generate according to the injected event simulation data.

[0126] The second event type instructs the CN domain data generation function network element to simulate or simulate which events, or in other words, the event type can indicate the specific event content.

[0127] The second collection index can be understood as which type of simulation data needs to be collected by the CN domain data generation function network element. For example, the second collection index can also include network performance indexes, alarm indexes, and the like.

[0128] For example, the second collection index can include at least one of the following indexes: time delay, packet error rate, packet loss rate, PDU session quantity, or throughput, and the like.

[0129] The second collection quantity can be understood as the quantity of data sets (simulation data) that need to be collected by the CN domain data generation function network element.

[0130] It can be understood that the first event type indicated by the management service consumer to the CN domain data generation function network element in S401 and the second event type (i.e., specific event) indicated to the RAN domain data generation function network element in S404 can be the same or different; the first collection index and the second collection index can be the same or different; and the first collection quantity and the second collection quantity can be the same or different.

[0131] The sequence identifier and the input feature can be used by the CN domain data generation function network element to determine which data (user plane data and / or control plane data) and transmission features of the data need to be simulated, so that the CN domain data generation function network element and the RAN domain data generation function network element simulate the same transmission feature data, which can ensure that the data simulated by the CN domain and RAN domain data generation function network elements match or correspond, and the data generated by the RAN domain data generation function network element and the CN domain data generation function network element are coordinated.

[0132] Optionally, the request information in S404 can also include the collection quantity.

[0133] S405, the CN domain data generation function network element simulates the occurrence of the event and collects the simulation data corresponding to the CN domain according to the request information.

[0134] Optionally, the simulation data corresponding to the CN domain can also be referred to as the data of the second domain or the data corresponding to the CNN domain.

[0135] For example, the CN domain data generation function network element can determine the event to be simulated according to the second event injection indication and the second event type, simulate occurrence of the event, and thus complete event injection. After the event is injected into the CN domain data generation function network element (i.e., in the process of simulating occurrence of the event), the CN domain data generation function network element can determine, according to the sequence identifier and the input feature, which data packets and transmission features of the data packets need to be simulated, or which control signaling and transmission features of the control signaling need to be simulated. Then, the required indicators (second collection indicators) are collected according to the data features (i.e., the input features) to be simulated until the collection quantity requirement is met, so as to obtain corresponding simulation data.

[0136] Optionally, if the request information in S404 does not include the collection quantity, the CN domain data generation function network element can determine the collection quantity according to the number of the sequence identifiers. For example, the collection quantity can be the same as the number of the sequence identifiers.

[0137] It can be understood that the CN domain data generation function network element can also use NDT to simulate occurrence of the event.

[0138] It should also be understood that the CN domain data generation function network element generates simulation data corresponding to the CN domain.

[0139] Through the sequence identifier and the input feature described above, it can be ensured that the CN domain data generation function network element and the RAN domain data generation function network element simulate data packets or control signaling with the same transmission features, so as to ensure that the data simulated (simulated) by the CN domain data generation function network element and the RAN domain data generation function network element match or correspond, realize cooperation of the data generated by the RAN domain data generation function network element and the CN domain data generation function network element, and improve accuracy of the simulation data generated by a single domain.

[0140] For example, in combination with the above example, the CN domain data generation function network element also simulates data packet A and data packet B, which are transmitted from a network device to a UPF in a core network. The sequence identifier of data packet A is A, and the sequence identifier of data packet B is B. Data packet A corresponds to input feature A, and data packet B corresponds to input feature B. The CN domain data generation function network element collects the indicator of data packet A as the delay of the CN domain, and collects the indicator of data packet B as the packet error rate of the CN domain. The CN domain data generation function network element can determine the input feature A of data packet A according to the sequence identifier A, simulate the input feature A of data packet A, and collect the delay of data packet A in the CN domain, determine the input feature B of data packet B according to the sequence identifier B, simulate the input feature B of data packet B, and collect the packet error rate of data packet B in the CN domain.

[0141] S406, the CN domain data generation function network element returns the CN domain corresponding simulation and sequence identification to the management service consumer (MnS consumer).

[0142] Optionally, S406 can also be described as: the RAN domain data generation function network element returns the second information to the management service consumer, and the first information includes: the RAN domain data and the first sequence identification.

[0143] Optionally, in S406, the CN domain data generation function network element can also return the input feature to the management service consumer (MnS consumer).

[0144] It can be understood that the simulation data of the CN domain can include: the value of the collected index (index value).

[0145] Optionally, the simulation data of the CN domain can also include the event information simulated by the CN domain, i.e., the event type.

[0146] It can be understood that the sequence identification returned by the CN domain data generation function network element and the RAN domain data generation function network element to the management service consumer is the same.

[0147] S407, the management service consumer integrates the simulation data corresponding to the CN domain and the RAN domain respectively according to the sequence identification, to obtain the integrated simulation data.

[0148] Optionally, S407 can also be described as: S407, the management service consumer determines the second data according to the simulation data corresponding to the CN domain and the RAN domain respectively.

[0149] In some possible implementation manners, the management service consumer (MnS consumer) can determine which user plane data packet or which control signaling is simulated (simulated) by the RAN domain data generation function network element and the CN domain data generation function network element respectively according to the sequence identification, and then integrate the end-to-end data according to the sequence identification, to obtain the integrated simulation data. Optionally, the simulation data obtained after integration can also be referred to as the second data.

[0150] For example, the management service consumer can find the simulation data with the same sequence identification from the simulation data returned in S403 and S406 respectively, and integrate them. The specific integration method is related to the type of simulation data (i.e., the collected index), for example, if the type of simulation data is the time delay, the time delay of the RAN domain and the time delay of the CN domain of the data packet with the same sequence identification are added to obtain the end (RAN) to end (CN) data packet time delay (i.e., the second data).

[0151] It should be understood that if the collection indexes corresponding to the RAN domain and the CN domain are completely different, for example, the CN domain collects latency and the RAN domain collects throughput, the management service consumer can also not integrate the data collected by the RAN domain and the CN domain. In this case, the data (second data) finally obtained (determined) by the management service consumer can include the simulation data of the CN domain (data of the second domain) and / or the simulation data of the RAN domain (data of the first domain).

[0152] If the collection indexes corresponding to the RAN domain and the CN domain are partially the same, for example, the CN domain collects latency, and the RAN domain collects throughput and latency, the management service consumer can integrate the latency data collected by each single domain, and the throughput index does not need to be integrated. In this case, the second data includes the latency data after the integration of the latency data collected by each single domain and the throughput data.

[0153] The method for data processing provided in the embodiments of the present application can inject events that need to be simulated into the RAN domain data generation function network element and the CN domain data generation function network element respectively, each single domain data generation function network element generates simulation data of the corresponding domain according to the injected events and returns the simulation data to the management service consumer network element, thereby realizing the generation of simulation data according to the single domain granularity. In addition, the input features and the sequence identifiers are used to make the simulation data generated by the CN domain and the RAN domain be data for the same transmission feature, thereby realizing the cooperation of the simulation data generated by the RAN domain data generation function network element and the CN domain data generation function network element, and thus more accurate simulation data can be provided.

[0154] The method for data processing provided in the present application is described below in combination with specific examples. In the examples below, the generation of AI models or ML models by the RAN domain data generation function network element and the CN domain data generation function network element is taken as an example for description, that is, the generation of simulation data by the RAN domain data generation function network element and the CN domain data generation function network element for the AI model or ML model training scenario is taken as an example for description.

[0155] For example, in order to make the AI model or the ML model more accurate and the MDAS analysis output result more reliable, the data requester (which can be an MnS consumer) can inject events into the RAN domain data generation function network element and the CN domain data generation function network element through network digital twin (NDT) technology. The RAN domain data generation function network element and the CN domain data generation function network element respectively simulate data generation according to the injected events, and then send the generated AI model or ML model training data to the data requester. Moreover, the AI model or ML model training data generated by multiple single-domain data generation function network elements is for data packets with the same transmission characteristics, which can ensure the coordination of data collected in multiple single domains.

[0156] The MnS consumer can inject corner cases affecting slice service experience into the single-domain data generation function network element through NDT. The single-domain data generation function network element collects relevant performance indicators of the network as X data for AI model or ML model training, and takes the injection point (i.e. the affected object), the influence type, and the service level as Y data for AI model or ML model training. After the single-domain data generation function network element collects the X data (feature data) and the Y data (label data), it reports to the data requester (which can be an MnS consumer) to supplement the training data of the AI model or ML model.

[0157] For example, in the scenario where the AI model or the ML model is applied to the MDAS, in order to supplement the training data of the AI model or the ML model, the data requester (which can be an MnS consumer) can request the single-domain data generation function network element to construct training data. For example, the data requester requests the RAN domain data generation function network element to obtain training data in a certain area, which includes, for example: integrated UL / DL delay in RAN, RAN UE throughput, base station identifier, slice identifier to which the base station belongs, injection event, slice identifier affected by the injection event, service experience level, etc. Among them, the integrated UL / DL delay in RAN, the RAN UE throughput, the base station identifier, and the slice identifier to which the base station belongs can be X data for AI model or ML model training, and the injection event, the slice identifier affected by the injection event, and the service experience level can be Y data for AI model or ML model training. The data requester can also specify the number of training data sets to be generated, the type of event, etc.

[0158] After the RAN domain data generation function network element receives the request, it randomly injects events in the specified area range of the base station, such as base station A failure; base station B power is halved and the like. The RAN domain data generation function network element model simulates the occurrence of these situations and collects corresponding X data and Y data and returns to the data requester.

[0159] The data requester integrates the training data generated by the RAN domain data generation function network element and the training data generated by the CN domain data generation function network element (such as calculating the end-to-end delay, calculating the end-to-end service level, etc.) to obtain a complete training set, and starts AI model or ML model training. Among them, the training data generated by the RAN domain data generation function network element and the training data generated by the CN domain data generation function network element are for the same feature data packet, for example, the same data packet sending frequency and packet size.

[0160] FIG. 5 is a schematic flowchart of another embodiment of the data processing method of the present application. As shown in FIG. 5, the method 500 shown in FIG. 5 can include S501 to S507. The following will be described in detail in combination with FIG. 5.

[0161] S501, the management service consumer (MnS consumer) sends request information to the RAN domain data generation function network element, the request information is used to obtain the AI model or ML model training data corresponding to the RAN domain, and the request information includes at least one of event injection indication information, event type, collection index, or collection quantity.

[0162] Optionally, the request information in S501 can also be referred to as first request information. The event injection indication information, the event type, the collection index, and the collection quantity included in the request information can be referred to as first event injection indication information, first event type, first collection index, and first collection quantity, respectively.

[0163] For the event injection indication information (first event injection indication information), the event type (first event type), the collection index (first collection index), and the collection quantity (first collection quantity), reference can be made to the corresponding description of S401 in method 400. For brevity, it will not be repeated here.

[0164] It can be understood that the event injection indication information and the event type can be used to generate or simulate the label data (Y data) of the AI model or ML model training data set.

[0165] It should be understood that the collection index can indicate the feature data of the AI model or ML model training data set that needs to be collected. Therefore, the collection index can indicate which type of feature data needs to be collected by the RAN domain data generation function network element.

[0166] The collection quantity (the first collection quantity) can be understood as the quantity of data sets (or the quantity of training data) that need to be collected by the RAN domain data generation function network element. Each data set can include multiple pieces of data, that is, multiple samples. One sample can be understood as one piece of data in the data set, and the sample is the basic unit in the data set. Generally, one sample is composed of a group of feature data and a label data.

[0167] Correspondingly, the RAN domain data generation function network element receives the request information.

[0168] S502, the RAN domain data generation function network element simulates the occurrence of the event and collects the RAN domain corresponding training data according to the request information.

[0169] Optionally, the RAN domain corresponding training data can also be referred to as the first domain data.

[0170] For example, the RAN domain data generation function network element can determine the event that needs to be simulated according to the event injection indication and the event type, simulate the occurrence of the event, generate the label data (Y data) of the AI model or ML model training data set, and thus complete the event injection. In other words, the specific event content indicated by the event type can be understood as the label data of the generated AI model or ML model training data set.

[0171] After the RAN domain data generation function network element is injected with the event (that is, in the process of simulating the occurrence of the event), the RAN domain data generation function network element can randomly simulate the input feature (also referred to as the transmission feature) of the data packet or the control signaling, such as the frequency of data packet transmission and the packet size, collect the required indicators according to the simulated input feature, until the requirement of the collection quantity is met, and thus obtain the feature data (X data) of the AI model or ML model training data set.

[0172] Optionally, the RAN domain data generation function network element can also determine the sequence identifier (also referred to as the first sequence identifier), wherein the sequence identifier is the identifier of the user plane data packet or the control signaling simulated by the RAN domain data generation function network element. The data packets or control signaling of the same sequence identifier have the same transmission feature or input feature.

[0173] It should also be understood that the RAN domain data generation function network element simulates the AI model or ML model training data corresponding to the RAN.

[0174] S503, the RAN domain data generation function network element returns the AI model or ML model training data corresponding to the RAN, the sequence identifier and the input feature to the management service consumer.

[0175] Optionally, S503 can also be described as: the RAN domain data generation function network element returns first information to the management service consumer, and the first information includes: training data of the RAN domain, a first sequence identifier, and input features.

[0176] It can be understood that the training data of the RAN domain can include the value of the collected index (index value) and event information. The value of the collected index can be understood as the value of the feature data (X data) of the AI model or ML model training data set corresponding to the RAN domain. The event information can be understood as the label data of the AI model or ML model training data set corresponding to the RAN domain, that is, the event type simulated by the RAN domain. In other words, the training data of the RAN domain includes the feature data and the label data of the AI model or ML model training data set corresponding to the RAN domain.

[0177] For specific descriptions of the first sequence identifier and the input features, reference can be made to the descriptions in the method 400, which will not be repeated here for brevity.

[0178] S504, the management service consumer sends request information to the CN domain data generation function network element, the request information is used to acquire the AI model or ML model training data corresponding to the CN domain, and the request information includes: at least one of event injection indication information, event type, or collected index, sequence identifier, and input features.

[0179] It should be understood that the sequence identifier and the input features returned by the RAN domain data generation function network element to the management service consumer in S503 and the sequence identifier and the input features sent by the management service consumer to the CN domain data generation function network element in S504 are the same, and can include one or more sequence identifiers.

[0180] Optionally, the request information in S504 can also be referred to as second request information. The event injection indication information, the event type, and the collected index included in the request information can be referred to as second event injection indication information, second event type, second collected index, and second collected number, respectively.

[0181] It can be understood that the first event type indicated by the management service consumer to the CN domain data generation function network element in S501 and the second event type (i.e., specific event) indicated to the RAN domain data generation function network element in S504 can be the same or different; the first collected index and the second collected index can be the same or different; and the first collected number and the second collected number can be the same or different.

[0182] Optionally, the request information in S504 can also include a collected number.

[0183] S505, the CN domain data generation function network element simulates the occurrence of an event and collects the training data corresponding to the CN domain according to the request information.

[0184] Optionally, the training data corresponding to the CN domain can also be referred to as the data of the second domain.

[0185] For example, the CN domain data generation function network element can determine the event to be simulated according to the second event injection indication and the second event type, simulate the occurrence of the event, generate the label data (Y data) of the AI model or ML model training data set, and thus complete the event injection.

[0186] After the event injection CN domain data generation function network element (i.e., in the process of simulating the occurrence of the event by the CN domain data generation function network element), the CN domain data generation function network element can determine which data packets and transmission characteristics of the data packets, or which control signaling and transmission characteristics of the control signaling, need to be simulated according to the sequence identifier and the input feature. Then, the required indicators (second collection indicators) are collected according to the data features (i.e., input features) that need to be simulated until the collection quantity requirement is met, so as to obtain the feature data (X data) of the AI model or ML model training data set.

[0187] S506, the CN domain data generation function network element returns the AI model or ML model training data corresponding to the CN domain and the sequence identifier to the management service consumer (MnS consumer).

[0188] Optionally, S506 can also be expressed as: the RAN domain data generation function network element returns the second information to the management service consumer, and the first information includes: the training data of the RAN domain and the first sequence identifier.

[0189] Optionally, in S506, the CN domain data generation function network element can also return the input feature to the management service consumer (MnS consumer).

[0190] It can be understood that the training data of the CN domain can include: the value of the collection indicator (indicator value) and the event information. The value of the collection indicator can be understood as: the value of the feature data (X data) of the AI model or ML model training data set corresponding to the CN domain. The event information can be understood as: the label data (Y data) of the AI model or ML model training data set corresponding to the CN domain, i.e., the event type simulated by the CN domain. In other words, the training data of the CN domain includes: the feature data and the label data of the AI model or ML model training data set corresponding to the CN domain.

[0191] It can be understood that the sequence identifiers returned by the CN domain data generation function network element and the RAN domain data generation function network element to the management service consumer are the same.

[0192] S507, the management service consumer integrates the training data of the AI model or the ML model corresponding to the CN domain and the RAN domain respectively according to the sequence identifier, and obtains the integrated training data set.

[0193] Optionally, the integrated training data can also be referred to as second data.

[0194] For the description of S507, reference can be made to the description of S407 described above. For brevity, the description is not repeated here.

[0195] The method for data processing provided by the embodiment of the application can inject the events that need to be simulated into the RAN domain data generation function network element and the CN domain data generation function network element respectively, each single-domain data generation function network element generates model training data of the corresponding domain according to the injected events and returns the model training data to the management service consumer network element, thereby realizing the generation of AI model or ML model training data according to single-domain granularity. In addition, the input features and the sequence identifier are used to make the data simulated by the RAN domain and the CN domain be data for the same transmission characteristics, thereby realizing the cooperation of the data generated by the RAN domain data generation function network element and the CN domain data generation function network element, and providing more accurate training data for the AI model or the ML model.

[0196] FIG. 6 is a schematic flowchart of a method for data processing according to another embodiment of the application. As shown in FIG. 6, the method 600 shown in FIG. 6 can include S601 to S608. The steps in the method 600 will be described in detail below in combination with FIG. 6.

[0197] S601, the management service consumer (MnS consumer) sends request information to the RAN domain data generation function network element, the request information being used to acquire AI model or ML model training data corresponding to the RAN domain, the request information including at least one of event injection indication information, event type, collection index, or collection quantity, and an address of a CN domain data generation function network element and verification information of the CN domain data generation function network element.

[0198] For the event injection indication information (first event injection indication information), the event type (first event type), the collection index (first collection index), and the collection quantity (first collection quantity), reference can be made to the corresponding description of S401 in the method 400. For brevity, the description is not repeated here.

[0199] The address of the CN domain data generation function network element can be understood as a communication address of the CN domain data generation function network element, such as an IP address, etc. The RAN domain data generation function network element can communicate with the CN domain data generation function network element according to the address.

[0200] The check information of the CN domain data generation function network element can be understood as: the proofreading information of the CN domain data generation function network element itself, used for checking the identity of the CN domain data generation function network element and the like. For example, the check information of the CN domain data generation function network element can be a token or a mark of the CN domain data generation function network element.

[0201] S602, the management service consumer sends request information to the CN domain data generation function network element, the request information being used for obtaining AI model or ML model training data corresponding to the CN domain, the request information comprising at least one of event injection indication information, an event type, or a collection index, and check information of the CN domain data generation function network element.

[0202] Optionally, the request information in S602 can also be referred to as third request information. The event injection indication information, the event type, the collection index, and the collection quantity included in the request information can be referred to as second event injection indication information, a second event type, a second collection index, respectively. The indication information included in the request information can be referred to as first indication information.

[0203] The first indication information is used to indicate that other nodes will trigger the CN domain data generation function network element to generate AI model or ML model training data. In other words, the first indication information can indicate to the CN domain data generation function network element that other nodes will trigger the CN domain data generation function network element to start collecting training data corresponding to the CN domain in the future.

[0204] It can be understood that the second event type indicated by the management service consumer to the CN domain and the first event type indicated to the RAN domain can be the same or different; the first collection index and the second collection index can be the same or different; the first collection quantity and the second collection quantity can be the same or different.

[0205] Optionally, the request information in S602 can also include a collection quantity (second collection quantity).

[0206] S603, the RAN domain data generation function network element simulates event occurrence and collects training data corresponding to the RAN domain according to the request information.

[0207] For the description of S603, reference can be made to the description of S402 in method 400, and details are not repeated here for brevity.

[0208] S604, the RAN domain data generation function network element returns AI model or ML model training data corresponding to the RAN domain and a sequence identifier to the management service consumer.

[0209] It can be understood that the training data of the RAN domain can include the value of the collected index (index value) and event information. The value of the collected index can be understood as the feature data (X data) of the AI model or ML model training data set corresponding to the RAN domain. The event information can be understood as the label data (Y data) of the AI model or ML model training data set corresponding to the RAN domain, that is, the event type simulated by the RAN domain. In other words, the training data of the RAN domain includes the feature data and label data of the AI model or ML model training data set corresponding to the RAN domain.

[0210] The sequence identifier is used to indicate (identify) the identifier of the user plane data packet or control signaling simulated by the RAN domain data generation function network element. In other words, the sequence identifier is used to indicate which user plane data packet or control signaling is simulated by the RAN domain data generation function network element.

[0211] In the embodiment of the application, the RAN domain data generation function network element can determine one or more sequence identifiers. The description of the sequence identifier can refer to the description of S402 in method 400, which will not be repeated here.

[0212] S605, the RAN domain data generation function network element sends the indication information to the CN domain data generation function network element, the indication information is used to trigger (or indicate) the CN domain data generation function network element to generate the AI model or ML model training data, and the indication information includes the verification information, the input feature and the sequence identifier of the CN domain data generation function network element.

[0213] Optionally, the indication information in S605 can also be called second indication information.

[0214] For example, the RAN domain data generation function network element can send the indication information to the CN domain data generation function network element according to the address of the CN domain data generation function network element.

[0215] The input feature can be understood as the transmission feature of the (simulated) data used by the RAN domain data generation function network element in the process of simulating the event, in other words, the input feature can represent the specific transmission feature of the data packet or control signaling simulated by the RAN domain data generation function network element. The input feature can be determined by the RAN domain data generation function network element itself in the process of simulating the event.

[0216] Of course, if the request information sent by the management service consumer to the CN domain data generation function network element in S602 does not include at least one of the event second injection indication information, the second event type, the second collection index, or the first collection quantity, the RAN domain data generation function network element can also send at least one of the first event injection indication information, the first event type, the first collection index, or the first collection quantity to the CN domain data generation function network element in S605.

[0217] In S606, the CN domain data generation function network element checks the verification information, and after verification, simulates the occurrence of an event and collects the training data corresponding to the CN domain.

[0218] For example, the CN domain data generation function network element can check the token or the mark carried by the indication information, and in the case of consistency with the token or the mark sent by the management service consumer in S602, the verification is passed.

[0219] Then, the CN domain data generation function network element determines the event to be simulated according to the event injection indication and the event type in S602, simulates the occurrence of the event, generates the label data of the AI model or ML model training data set, and thus completes the event injection.

[0220] After the event injection CN domain data generation function network element, the CN domain data generation function network element can determine which data packets and transmission characteristics of these data packets, or which control signaling and transmission characteristics of these control signaling need to be simulated according to the input features and sequence identifiers in S605, and then collect the required indicators according to the required data transmission characteristics for simulation until the collection quantity requirement is met, thereby obtaining the feature data (X data) of the AI model or ML model training data set.

[0221] Optionally, if the request information in S602 does not include the collection quantity, the CN domain data generation function network element can determine the collection quantity according to the number of sequence identifiers. For example, the collection quantity can be the same as the number of sequence identifiers.

[0222] It can be understood that the CN domain data generation function network element can also use NDT to simulate the occurrence of an event.

[0223] It should also be understood that the CN domain data generation function network element simulates the AI model or ML model training data corresponding to the CN domain.

[0224] In S607, the CN domain data generation function network element returns the AI model or ML model training data corresponding to the CN domain and the sequence identifier to the management service consumer.

[0225] It can be understood that the sequence identifiers returned by the CN domain data generation function network element and the RAN domain data generation function network element to the management service consumer are the same.

[0226] S608, the management service consumer integrates the training data of the AI model or the ML model corresponding to the CN domain and the RAN domain according to the sequence identifier, and obtains an integrated training data set.

[0227] It can be understood that in the method 600, the CN domain data generation function network element is triggered by the RAN domain to generate the AI model or the ML model training data. In other implementations of the present application, the RAN domain data generation function network element can also be triggered by the CN domain to generate the AI model or the ML model training data, and in this case:

[0228] S601 can be replaced by: the management service consumer sends request information to the CN domain data generation function network element, the request information being used to obtain the AI model or the ML model training data corresponding to the CN domain, the request information including at least one of event injection indication information, event type, collection index, and collection quantity, and address of the RAN domain data generation function network element and verification information of the RAN domain data generation function network element.

[0229] S602 can be replaced by: the management service consumer sends request information to the RAN domain data generation function network element, the request information being used to obtain the AI model or the ML model training data corresponding to the RAN domain, the request information including at least one of event injection indication information, event type, or collection index, and indication information and verification information of the RAN domain data generation function network element.

[0230] The indication information is used to indicate that other nodes will trigger the RAN domain data generation function network element to generate the AI model or the ML model training data.

[0231] S603 can be replaced by: the CN domain data generation function network element simulates event occurrence and collects the training data corresponding to the CN domain according to the request information.

[0232] S604 can be replaced by: the CN domain data generation function network element returns the AI model or the ML model training data corresponding to the CN domain and the sequence identifier to the management service consumer.

[0233] S605 can be replaced by: the CN domain data generation function network element sends indication information to the RAN domain data generation function network element, the indication information being used to trigger the RAN domain data generation function network element to generate the AI model or the ML model training data, the indication information including verification information of the RAN domain data generation function network element, input features, and the sequence identifier.

[0234] S606 can be replaced by: the RAN domain data generation function network element collates the check information, and after the check passes, a simulation event occurs and training data corresponding to the RAN domain is collected.

[0235] S607 can be replaced by: the RAN domain data generation function network element returns the AI model or ML model training data corresponding to the RAN domain and the sequence identifier to the management service consumer.

[0236] The method for data processing provided in the embodiments of the present application can inject the events that need to be simulated into the RAN domain data generation function network element and the CN domain data generation function network element respectively, and the AI model or ML model training data can be generated by the RAN domain triggering the CN domain; or the AI model or ML model training data is generated by the RAN domain triggering the CN domain, and each single-domain data generation function network element generates the training data of the corresponding domain according to the injected events and returns it to the management service consumer network element, thereby realizing the generation of the AI model or ML model training data in the single-domain granularity. In addition, the input features and the sequence identifier are used to make the data simulated by the CN domain and the RAN domain be the data for the same transmission characteristics, thereby realizing the cooperation of the data generated by the RAN domain data generation function network element and the CN domain data generation function network element, so as to provide more accurate training data for the AI model or ML model.

[0237] It should be understood that the above is only to help those skilled in the art better understand the embodiments of the present application, and is not intended to limit the scope of the embodiments of the present application. Those skilled in the art can obviously make various equivalent modifications or changes according to the above examples given, for example, some steps in the above method embodiments can not be necessary, or some steps can be newly added, etc. Or a combination of any two or more embodiments. Such modifications, changes or combinations also fall within the scope of the embodiments of the present application.

[0238] It should also be understood that the ways, cases, categories and divisions of embodiments in the embodiments of the present application are only for the convenience of description and should not be considered as special limitations. The features in various ways, categories, cases and embodiments can be combined without contradiction.

[0239] It should also be understood that the various numerical designations involved in the embodiments of the present application are only for the convenience of differentiation and do not limit the scope of the embodiments of the present application. The size of the serial number of the above processes does not mean the order of execution, and the execution order of the processes should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0240] It should also be understood that the above description of the embodiments of the present application focuses on the differences between the various embodiments, and the same or similar parts not mentioned can be referred to each other. For the sake of brevity, they will not be repeated here.

[0241] The method of the embodiment of the present application is described in detail above in combination with FIG. 1 to FIG. 6. The communication device of the embodiment of the present application is described in detail below in combination with FIG. 7 and FIG. 8.

[0242] The embodiment can divide the functional modules of each network element (management service consumer, RAN domain data generation function network element, CN domain data generation function network element, etc.) according to the method described above. For example, each function can be divided into a functional module, or two or more functions can be integrated in one processing module. The integrated module can be implemented in the form of hardware. It should be noted that the division of the modules in the embodiment is illustrative, and is only a logical functional division. Actual implementation can have another division manner.

[0243] It should be noted that the related content of each step involved in the method embodiment described above can be cited in the functional description of the corresponding functional module, which will not be described here.

[0244] The management service consumer, single-domain data generation function network element (for example, RAN domain data generation function network element, CN domain data generation function network element, etc.) provided by the embodiment of the present application is used to execute any one of the data processing methods provided by the method embodiment described above, so as to achieve the same effect as the implementation method described above. In the case of using an integrated unit, the management service consumer, RAN domain data generation function network element, and CN domain data generation function network element can include a processing module, and optionally a storage module and a communication module. The processing module can be used to control and manage the actions of the management service consumer, RAN domain data generation function network element, or CN domain data generation function network element. For example, it can be used to support the management service consumer, RAN domain data generation function network element, or CN domain data generation function network element to execute the steps executed by the processing unit. The storage module can be used to support the storage of program code and data, etc. The communication module can be used to support the communication between the management service consumer, RAN domain data generation function network element, or CN domain data generation function network element and other network elements.

[0245] The processing module can be a processor or a controller. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the present application. The processor can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc. The storage module can be a memory. The communication module can be a radio frequency circuit, a Bluetooth chip, and other devices that interact with other electronic devices.

[0246] For example, FIG. 7 shows a schematic block diagram of a communication apparatus 700 according to the embodiments of the present application, which can correspond to the management service consumer, the RAN domain data generation function network element or the CN domain data generation function network element described in the above method 400, method 500 or method 600, or a chip or component applied to the management service consumer, the RAN domain data generation function network element or the CN domain data generation function network element, and each module or unit in the communication apparatus 700 is respectively configured to perform each action or process performed by the management service consumer, the RAN domain data generation function network element or the CN domain data generation function network element in any possible implementation manner of the above method 400, method 500 or method 600.

[0247] As shown in FIG. 7, the communication apparatus 700 can include a processing unit 710 and a transceiver unit 720. The transceiver unit 720 is configured to perform specific signal transceiving under the control of the processing unit 710. The processing unit can also be referred to as a processing module, and the transceiver unit can also be referred to as a communication unit or a communication module.

[0248] In some embodiments,

[0249] The communication apparatus 700 can correspond to the management service consumer described in the above method 400, method 500 or method 600, or a chip or component applied to the management service consumer, and each module or unit in the communication apparatus 700 is respectively configured to perform each action or process performed by the management service consumer in any possible implementation manner of the method 400, method 500 or method 600.

[0250] For example, the transceiver unit 720 is configured to receive first information from the first domain data generation function network element, the first information including data of the first domain and a first sequence identifier.

[0251] The transceiver unit 720 is further configured to receive second information from the second domain data generation function network element, the second information including data of the second domain and the first sequence identifier, the first domain and the second domain being different;

[0252] The processing unit 710 is configured to determine second data according to the data of the first domain and the data of the second domain, and the first sequence identifier, wherein the first sequence identifier is used to indicate that data packets or control signaling with the same sequence identifier have the same transmission characteristics.

[0253] The communication apparatus provided in the application can inject events that need to be simulated into different single-domain data generation function network elements respectively, each single-domain data generation function network element generates data of a corresponding domain according to the injected events and returns the data to the communication apparatus, thereby realizing data generation according to single-domain granularity. Moreover, the data generated by different single-domain data generation function network elements is integrated by using the same sequence identifier, thereby realizing cooperation of the data generated by the single-domain data generation function network elements, and making the integrated data more accurate.

[0254] For example, the first domain can be a RAN domain, and the second domain can be a CN domain.

[0255] In some possible implementation manners, before receiving the first information from the first-domain data generation function network element, the transceiver 720 is further configured to: send a first request message to the first-domain data generation function network element, the first request message being used to acquire data of the first domain, and the first request information including at least one of first event injection indication information, a first event type, a first collection index, or a first collection quantity; wherein the first event injection indication information is used to instruct the first-domain data generation function network element to generate data according to the injected events, the first event type is used to instruct content of the events simulated by the first-domain data generation function network element, the first collection index is used to instruct a data type collected by the first-domain data generation function network element, and the first collection quantity is used to instruct a data quantity collected by the first-domain data generation function network element.

[0256] In some possible implementation manners, the first information further includes an input feature, the input feature being used to instruct a transmission feature of the data packet or the control signaling, and before receiving the second information from the second-domain data generation function network element, the transceiver 720 is further configured to: send a second request message to the second-domain data generation function network element, the second request information being used to acquire data of the second domain, and the second request information including at least one of second event injection indication information, a second event type, or a second collection index, and the first sequence identifier and the input feature.

[0257] In some possible implementation manners, the second event type is the same as the first event type, the second collection index is the same as the first collection index, and the first collection quantity is the same as the second collection quantity.

[0258] In some possible implementation, the first request information further includes: an address of the second domain data generation function network element and verification information of the second domain data generation function network element; and before receiving the second information from the second domain data generation function network element, the transceiver 720 is further configured to: send a third request message to the second domain data generation function network element, the third request message being used to acquire data of the second domain, the third request message including: at least one of second event injection indication information, a second event type, or a second collection index, and the first indication information and the verification information of the second domain data generation function network element; and the first indication information is used to indicate that the other nodes trigger the second domain data generation function network element to generate the data of the second domain.

[0259] In some possible implementation, the first collection index or the second collection index includes at least one of a time delay, a packet error rate, a packet loss rate, a protocol data unit (PDU) session quantity, or a throughput.

[0260] In some possible implementation, the processing unit 710 is further configured to: in the data of the first domain and the data of the second domain, integrate data of the same collection index corresponding to the same data packet or control signaling with the same sequence identifier to obtain second data.

[0261] In some possible implementation, the second data includes: the data of the first domain and / or the data of the second domain.

[0262] It should be understood that the specific process in which the units in the communication apparatus 700 perform the corresponding steps described above can refer to the foregoing description related to the management service consumer in the embodiments of the method 400 or the method 500, and will not be repeated here for brevity.

[0263] In some other embodiments:

[0264] The communication apparatus 700 can correspond to the RAN domain data generation function network element or the CN domain data generation function network element described in the method 400, the method 500, or the method 600, or be a chip or component applied to the RAN domain data generation function network element or the CN domain data generation function network element, and each module or unit in the communication apparatus 700 is respectively configured to perform each action or processing process performed by the RAN domain data generation function network element or the CN domain data generation function network element in any one of the possible implementation manners of the method 400, the method 500, or the method 600.

[0265] For example, the transceiver 720 is configured to: receive first request information from a first network element, the first request message being used to acquire data of a first domain, the first request information including: at least one of first event injection indication information, a first event type, a first collection index, or a first collection quantity;

[0266] The processing unit 710 is configured to generate data of the first domain according to the first request information.

[0267] The transceiver unit 720 is further configured to send the data of the first domain and a first sequence identifier to the first network element, the first sequence identifier being used to indicate an identifier of a data packet or control signaling used in the generation of the data of the first domain, and data packets or control signaling of the same sequence identifier have the same transmission characteristics; wherein the first event injection indication information is used to indicate that the first domain data generation function network element generates according to the injected event simulation data, the first event type is used to indicate the event content simulated by the first domain data generation function network element, the first collection index is used to indicate the data type collected by the first domain data generation function network element, and the first collection quantity is used to indicate the number of data sets collected by the first domain data generation function network element.

[0268] The communication apparatus provided by the embodiments of the present application can generate training data of the corresponding domain according to the injected event simulation by each single-domain data generation function network element and return the training data to the management service consumer network element, thereby realizing the generation of data according to the single-domain granularity. In addition, the same sequence identifier (transmission characteristics) is used by different single-domain data generation function network elements to simulate the generation of data, thereby realizing the cooperation of the data generated by different single-domain data generation function network elements, and making the data generated by the single domain more accurate.

[0269] For example, the first domain can be the RAN domain, and the second domain can be the CN domain.

[0270] It should be understood that the specific processes of the units in the communication apparatus 700 for performing the corresponding steps described above can refer to the descriptions of the RAN domain data generation function network element or the CN domain data generation function network element in the related embodiments of the method 400, the method 500, or the method 600. For brevity, the details are not described here.

[0271] Optionally, the transceiver unit 720 can include a receiving unit (module) and a sending unit (module) for performing the steps of receiving information and sending information by the RAN domain data generation function network element or the CN domain data generation function network element in the method 400, the method 500, or the method 600.

[0272] Further, the communication apparatus 700 can further include a storage unit. The transceiver unit 720 can be a transceiver, an input / output interface, or an interface circuit. The storage unit is used to store the instructions executed by the transceiver unit 720 and the processing unit 710. The transceiver unit 720, the processing unit 710, and the storage unit are coupled to each other. The storage unit stores instructions, the processing unit 710 is configured to execute the instructions stored in the storage unit, and the transceiver unit 720 is configured to perform specific signal transceiving under the control of the processing unit 710.

[0273] Optionally, the storage unit can store one or more of information processed by the processing unit, parameters used by the processing unit, or information generated by the processing.

[0274] It should be understood that the transceiving unit 720 can be a transceiver, an input / output interface, or an interface circuit. The storage unit can be a memory. The processing unit 710 can be implemented by a processing circuit. As shown in FIG. 8, the communication apparatus 800 can include a processing circuit 810 and a transceiving circuit 820.

[0275] The processing circuit 810 can be one or more processors, or all or part of one or more processors used for control or processing functions.

[0276] The transceiving circuit 820 can be a transceiver, an input / output interface, or an interface circuit.

[0277] The communication apparatus 700 shown in FIG. 7 or the communication apparatus 800 shown in FIG. 8 can implement the steps in the foregoing method 400, method 500, or method 600 managed by the service consumer, the RAN domain data generation function network element, or the CN domain data generation function network element. Similar descriptions can be referred to the descriptions in the foregoing corresponding methods. To avoid repetition, no further description is given here.

[0278] It should also be understood that the communication apparatus 700 shown in FIG. 7 or the communication apparatus 800 shown in FIG. 8 can be the service consumer, the RAN domain data generation function network element, or the CN domain data generation function network element, or the service consumer, the RAN domain data generation function network element, or the CN domain data generation function network element can include the communication apparatus 700 shown in FIG. 7 or the communication apparatus 800 shown in FIG. 8.

[0279] It should also be understood that the division of the units in the above apparatus is only a logical functional division, and all or part of them can be integrated onto one physical entity, or can be physically separated. The units in the apparatus can all be implemented in the form of software invoked by a processing element; or all be implemented in the form of hardware; or some units are implemented in the form of software invoked by a processing element, and some units are implemented in the form of hardware. For example, each unit can be a separately established processing element, or can be integrated into a chip of the apparatus, and in addition, can be stored in the form of a program in the memory, and the function of the unit is invoked and executed by a processing element of the apparatus. The processing element can also be referred to as a processor, which can be an integrated circuit with signal processing capability. In the implementation process, each step of the above method or each unit can be implemented by an integrated logic circuit of hardware in the processing element, or in the form of software invoked by the processing element.

[0280] In one example, the units in any of the above apparatuses can be one or more integrated circuits, configured to implement one or more of the above methods, e.g., one or more application specific integrated circuits (ASICs), or, one or more DSPs, or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these forms of integrated circuits. In another example, when the units in the apparatuses can be implemented in the form of a processing element scheduler, the processing element can be a general purpose processor, e.g., a central processing unit (CPU) or other processor that can invoke a program. In yet another example, the units can be integrated together, implemented in the form of a system-on-a-chip (SOC).

[0281] It should be understood that, in the embodiments of the present application, the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0282] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an EPROM, an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0283] The embodiments of the present application also provide a communication system, which includes a first network element (managing a service consumer) and a plurality of single-domain data generation function network elements. For example, the data generation function network elements include a CN domain data generation function network element and a RAN domain data generation function network element.

[0284] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded or executed on a computer, the computer instructions or computer programs wholly or partially produce the processes or functions according to the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another by wired (such as infrared, wireless, microwave, etc.) or wireless means.

[0285] The embodiment of the present application further provides a computer readable medium for storing computer program codes, the computer program codes comprising instructions for executing any of the data processing methods provided by the above-mentioned embodiments of the present application. The readable medium can be the memory of the above-mentioned examples, and the embodiment of the present application does not limit this.

[0286] The present application further provides a computer program product comprising instructions which, when executed, cause a management service consumer to perform operations corresponding to the management service consumer in the above-mentioned methods, or cause a single-domain data generation function network element to perform operations corresponding to the single-domain data generation function network element in the above-mentioned methods.

[0287] The embodiment of the present application further provides a chip comprising a processing unit, for example, a processor, and a communication unit, for example, an input / output interface, a pin, a circuit, etc. The processing unit can execute computer instructions to cause the chip in the communication device, for example, a management service consumer, a RAN domain data generation function network element or a CN domain data generation function network element, to perform any of the data processing methods provided by the above-mentioned embodiments of the present application.

[0288] Optionally, any of the communication devices provided by the above-mentioned embodiments of the present application can comprise the chip.

[0289] Optionally, the computer instructions are stored in a storage unit.

[0290] Optionally, the storage unit is a storage unit in the chip, such as a register, a cache, etc. The storage unit can also be a storage unit in the communication device outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, a RAM, etc. The processor mentioned in any of the above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the programs of the above-mentioned methods. The processing unit and the storage unit can be decoupled and arranged on different physical devices, and connected through wired or wireless means to realize the respective functions of the processing unit and the storage unit to support the chip to realize various functions in the above-mentioned embodiments. Alternatively, the processing unit and the storage unit can be coupled on the same device.

[0291] The processor mentioned in any of the above can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned information processing method. The processing unit and the storage unit can be decoupled and arranged on different physical devices, connected by wired or wireless means to realize the respective functions of the processing unit and the storage unit to support the chip to realize various functions in the above embodiments. Alternatively, the processing unit and the storage unit can also be coupled on the same device.

[0292] The terms "system" and "network" are often used interchangeably herein. The term "and / or" herein is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after it.

[0293] Various objects such as messages / information / devices / systems / devices / actions / operations / processes, etc. that can appear in the present application are named. It can be understood that these specific names do not constitute a limitation on the related objects, and the assigned names can be changed according to the scene, context or usage habits, etc. The technical meaning of the technical terms in the present application should be mainly determined from the function and technical effect embodied / executed in the technical scheme.

[0294] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0295] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the unit is only a logical function division, and actual implementation can have another division manner, for example, a plurality of 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 between the displayed or discussed objects can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0296] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0297] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit.

[0298] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of data processing, characterized by, The method comprises: The first network element receives first information from a first domain data generation function network element, the first information comprising: data of the first domain and a first sequence identifier; The first network element receives second information from a second domain data generation function network element, the second information comprising: data of the second domain and the first sequence identifier, the first domain and the second domain being different; The first network element determines second data according to the data of the first domain and the data of the second domain, and the first sequence identifier; The first sequence identifier is used to indicate an identifier of a data packet or control signaling used by the first domain data generation function network element to generate the data of the first domain, and data packets or control signaling of the same sequence identifier have the same transmission characteristics.

2. The method of claim 1, wherein, Before the first network element receives the first information from the first domain data generation function network element, the method further comprises: The first network element sends a first request message to the first domain data generation function network element, the first request message being used to acquire the data of the first domain, the first request information comprising: at least one of first event injection indication information, a first event type, a first collection index, or a first collection quantity; The first event injection indication information is used to indicate that the first domain data generation function network element generates according to injected event simulation data, the first event type is used to indicate event content simulated by the first domain data generation function network element, the first collection index is used to indicate a data type collected by the first domain data generation function network element, and the first collection quantity is used to indicate a data quantity collected by the first domain data generation function network element.

3. The method of claim 2, wherein, The first information further comprises: input characteristics used to indicate transmission characteristics of data packets or control signaling, and before the first network element receives the second information from the second domain data generation function network element, the method further comprises: The first network element sends a second request message to the second domain data generation function network element, the second request information being used to acquire the data of the second domain, the second request information comprising: at least one of second event injection indication information, a second event type, or a second collection index, and the first sequence identifier and the input characteristics.

4. The method of claim 3, wherein, The second event type is the same as the first event type, the second collection index is the same as the first collection index, and the first collection quantity is the same as the second collection quantity.

5. The method of claim 2, wherein, The first request information further comprises: an address of the second domain data generation function network element and verification information of the second domain data generation function network element; Before receiving the second information from the second domain data generation function network element, the method further comprises: The first network element sends a third request message to the second domain data generation function network element, the third request message being used to acquire the data of the second domain, the third request message comprising: at least one of second event injection indication information, a second event type, or a second collection index, and the first indication information and verification information of the second domain data generation function network element; The first indication information is used for indicating that other nodes trigger the second domain data generation function network element to generate data of the second domain.

6. The method according to any one of claims 2 to 5, characterized in that, The first collection index or the second collection index comprises a network performance index and / or an alarm index, and the network performance index and / or the alarm index comprises at least one of a time delay, a packet error rate, a packet loss rate, a protocol data unit (PDU) session quantity or a throughput.

7. The method according to any one of claims 1 to 6, characterized in that, The first network element determines second data according to the data of the first domain and the data of the second domain and the first sequence identifier. The first network element integrates data of the same collection index corresponding to the same data packet or control signaling with the same sequence identifier in the data of the first domain and the data of the second domain to obtain the second data.

8. The method according to any one of claims 1 to 6, characterized in that, The second data comprises the data of the first domain and / or the data of the second domain.

9. A method of data processing, characterized by, The method comprises: The first domain data generation function network element receives first request information from the first network element, the first request information is used for acquiring data of the first domain, and the first request information comprises at least one of first event injection indication information, a first event type, a first collection index or a first collection quantity. The first domain data generation function network element generates the data of the first domain according to the first request information. The first domain data generation function network element sends the data of the first domain and a first sequence identifier to the first network element, the first sequence identifier is used for indicating an identifier of a data packet or control signaling used for generating the data of the first domain, and data packets or control signaling with the same sequence identifier have the same transmission characteristics. The first event injection indication information is used for indicating that the first domain data generation function network element is generated according to injected event simulation data, the first event type is used for indicating event content simulated by the first domain data generation function network element, the first collection index is used for indicating a data type collected by the first domain data generation function network element, and the first collection quantity is used for indicating a data quantity collected by the first domain data generation function network element.

10. The method of claim 9, wherein, The first request information further comprises an address of a second domain data generation function network element and verification information of the second domain data generation function network element, the first domain and the second domain are different, and the method further comprises: The first domain data generation function network element sends second indication information to the second domain data generation function network element, the second indication information is used for triggering the second domain data generation function network element to generate data, and the second indication information comprises the verification information of the second domain data generation function network element, the first sequence identifier and input characteristics, the input characteristics are used for indicating transmission characteristics of a data packet or control signaling.

11. The method according to claim 9 or 10, characterized in that, The second indication information further comprises at least one of the first event injection indication information, the first event type, the first collection index or the first collection quantity.

12. The method according to any one of claims 9 to 11, characterized in that, The first domain data generation function network element generates the data of the first domain according to the first request information. The first domain data generation function network element determines the event that needs to be simulated according to the first event type; In the process of simulating the occurrence of the event, the first domain data generation function network element determines the value of the collection index corresponding to the data packet or control signaling in the transmission process according to the first collection index and the first collection quantity.

13. A communications device, characterized by Comprise: Units for performing the steps of the method according to any one of claims 1 to 8, units for performing the steps of the method according to any one of claims 9 to 12.

14. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program comprises program instructions, the program instructions make the processor execute the following when executed by the processor: the method according to any one of claims 1 to 8, the method according to any one of claims 9 to 12.

15. A chip, characterized by Comprise: processor, for calling and running computer program from memory, so that the communication device installed with the chip executes: the method according to any one of claims 1 to 8, the method according to any one of claims 9 to 12.

Images