Data processing method and apparatus

Abstract

Embodiments of the present application disclose a data processing method and device. The data processing method measures performance parameters of data analysis function entities according to service processing parameters of the data analysis function entities, flexibly performs performance analysis on data analysis function entities with different logical functions, evaluates service performance of the data analysis function entities according to performance analysis results, and further processes the data analysis function entities to improve service performance of the data analysis function entities, thereby realizing unified management of the data analysis function entities supporting logical function decomposition.

Description

Technical Field

[0001] This disclosure relates to the field of communications, and more specifically, to a data processing method and apparatus. Background Technology

[0002] Within the framework of 5G network, a network data analytics function (NWDAF) device is defined. The NWDAF device can collect, analyze, and provide feedback on the analysis results of service data in the 5G network based on artificial intelligence (AI) technology and through standardized communication network processes.

[0003] In the 3rd Generation Partnership Project (3GPP) Release 17 (Rel-17) study, NWDAF can be decomposed into Analytics Logical Function (AnLF) and Model Training Logical Function (MTLF), enabling operators to flexibly deploy three types of NWDAF instances: NWDAF devices containing AnLF, NWDAF devices containing MTLF, and NWDAF devices containing both AnLF and MTLF. Different NWDAF instances can provide different functions.

[0004] While NWDAFs that support logical function decomposition are more flexible to deploy, their management methods are correspondingly more complex. Therefore, how to better manage NWDAFs that support logical function decomposition is an urgent problem to be solved. Summary of the Invention

[0005] To address the aforementioned technical problems, embodiments of this application provide a data processing method and apparatus for better management of data analysis functional entities that support logical functional decomposition.

[0006] According to one aspect of the embodiments of this application, a data processing method is provided, applied to the production end of a performance analysis service, comprising: measuring the performance parameters of multiple data analysis functional entities based on business processing parameters of multiple data analysis functional entities; performing performance analysis on the multiple data analysis functional entities based on the measured values ​​of the performance parameters; and processing the multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0007] In some implementations, the business processing parameters include at least one of service request information and service response information; measuring the performance parameters of multiple data analysis functional entities based on the business processing parameters of multiple data analysis functional entities includes: collecting service request information received by the data analysis functional entities within a specified time period, and / or collecting service response information generated by the data analysis functional entities within a specified time period to obtain business processing parameters; generating at least one first performance measurement data for the data analysis functional entities based on the business processing parameters; and sampling and statistically analyzing the first performance measurement data within a specified time period to generate at least one second performance measurement data for the data analysis functional entities.

[0008] In some implementations, the data analysis functional entity includes at least one of the following: a data analysis functional entity with analysis logic function, a data analysis functional entity with model training logic function, and a data analysis functional entity with both analysis logic function and model training logic function.

[0009] In some implementations, the first performance measurement data and the second performance measurement data each include measurement data associated with the logical functions of the data analysis functional entity; generating at least one first performance measurement data for the data analysis functional entity based on business processing parameters; sampling and statistically analyzing the first performance measurement data within a specified time period to generate at least one second performance measurement data for the data analysis functional entity, including: if the data analysis functional entity is a data analysis functional entity with analysis logic functions, then generating first performance measurement data and second performance measurement data corresponding to the data analysis functional entity with analysis logic functions; if the data analysis functional entity is a data analysis functional entity with model training logic functions, then generating first performance measurement data and second performance measurement data corresponding to the data analysis functional entity with model training logic functions; if the data analysis functional entity is a data analysis functional entity that simultaneously possesses analysis logic functions and model training logic functions, then generating first performance measurement data and second performance measurement data corresponding to the data analysis functional entity that simultaneously possesses analysis logic functions and model training logic functions.

[0010] In some implementations, service request information includes at least one of service request and service subscription; service response information includes at least one of service response and service notification; the parameter type of the business processing parameters includes at least one of service request or subscription, service response or notification, service success response or notification, and service error response or notification; generating at least one first performance measurement data for the data analysis function entity based on the business processing parameters includes: determining the cumulative counter corresponding to the business processing parameter according to the parameter type of the business processing parameter; counting the business processing parameter using the cumulative counter within a specified time period to obtain the first performance measurement data; if the business processing parameter... If the parameter type of the data includes service request or subscription, then the value of the cumulative counter corresponding to the service request or subscription parameter is updated to obtain the first performance measurement data; if the parameter type of the business processing parameter includes service response or notification, then the value of the cumulative counter corresponding to the service response or notification parameter is updated to obtain the first performance measurement data; if the parameter type of the business processing parameter includes service success response or notification parameter, then the value of the cumulative counter corresponding to the service success response or notification parameter is updated; if the parameter type of the business processing parameter includes service error response or notification parameter, then the value of the cumulative counter corresponding to the service error response or notification parameter is updated.

[0011] In some implementations, the first performance measurement data includes at least one of the following: the number of service requests or subscriptions, the number of service responses or notifications, the number of successful service responses or notifications, and the number of error service responses or notifications. Within a specified time period, the first performance measurement data is obtained by counting the service processing parameters using a cumulative counter, including: if the data analysis function entity receives a service request or subscription, the value of the first cumulative counter related to the service request or subscription is incremented by 1; if the data analysis function entity generates a service response or notification, the value of the second cumulative counter related to the service response or notification is incremented by 1; if the data analysis function entity generates a successful service response or notification, the value of the third cumulative counter related to the successful service response or notification is incremented by 1; if the data analysis function entity generates an error service response or notification, the value of the fourth cumulative counter related to the error service response or notification is incremented by 1. The first performance measurement data includes at least one of the values ​​of the first cumulative counter, the second cumulative counter, the third cumulative counter, and the fourth cumulative counter.

[0012] In some implementations, within a specified time period, the first performance measurement data is sampled and statistically analyzed to generate at least one second performance measurement data for the data analysis function entity. This includes: if the parameter type of the business processing parameter is a service request or subscription, then within the specified time period, the value of the first cumulative counter corresponding to the service request or subscription is sampled to obtain multiple sampled performance parameters; if the parameter type of the business processing parameter is a service response or notification, then within the specified time period, the value of the second cumulative counter corresponding to the service response or notification is sampled to obtain multiple sampled performance parameters; if the parameter type of the business processing parameter is a service success response or notification, then within the specified time period, the value of the third cumulative counter corresponding to the service success response or notification is sampled to obtain multiple sampled performance parameters; if the parameter type of the business processing parameter is a service error response or notification, then within the specified time period, the value of the fourth cumulative counter corresponding to the service error response or notification is sampled to obtain multiple sampled performance parameters.

[0013] In some implementations, within a specified time period, the first performance measurement data is sampled and statistically analyzed to generate at least one second performance measurement data for the data analysis functional entity. This includes: obtaining a statistical strategy matching the first performance measurement data; if the statistical strategy for the first performance measurement data is an average value statistical strategy, then calculating the average value of multiple sampled performance parameters corresponding to the first performance measurement data, and using the average value as the second performance measurement data corresponding to the first performance measurement data; if the statistical strategy for the first performance measurement data is a maximum value statistical strategy, then calculating the maximum value of multiple sampled performance parameters corresponding to the first performance measurement data, and using the maximum value as the second performance measurement data corresponding to the first performance measurement data; if the statistical strategy for the first performance measurement data is a minimum value statistical strategy, then calculating the minimum value of multiple sampled performance parameters corresponding to the first performance measurement data, and using the minimum value as the second performance measurement data corresponding to the first performance measurement data.

[0014] In some implementations, the second performance measurement data includes at least one of the following: average, maximum, or minimum number of service requests or subscriptions; average, maximum, or minimum number of service responses or notifications; average, maximum, or minimum number of successful service responses or notifications; and average, maximum, or minimum number of error service responses or notifications.

[0015] In some implementations, the first performance measurement data and the second performance measurement data each include measurement data associated with specific information, which includes at least one of the following: single network slice selection assistance information, analysis type information, request type information, subscription type information, service type information, and analysis identification information.

[0016] In some implementations, the method further includes: generating a performance analysis report based on at least one of the first performance measurement data and the second performance measurement data; and sending the performance analysis report to a performance analysis service consumer.

[0017] In some implementations, multiple data analysis functional entities are processed based on the performance analysis results obtained from the performance analysis, including: performing fault prediction on the multiple data analysis functional entities based on the performance analysis results to obtain fault prediction results; determining fault solutions based on the fault prediction results; and executing fault solutions on the data analysis functional entities.

[0018] In some implementations, multiple data analysis functional entities are processed based on the performance analysis results obtained from the performance analysis, including: receiving a data analysis functional entity allocation request, the data analysis functional entity allocation request carrying parameter information of the data analysis service to be processed; selecting a target data analysis functional entity that matches the parameter information of the data analysis service to be processed based on the performance analysis results of the multiple data analysis functional entities; and allocating the data analysis service to be processed to the target data analysis functional entity.

[0019] In some implementations, multiple data analysis functional entities are processed based on the performance analysis results obtained from the performance analysis, including: obtaining the computing resource usage of each of the multiple data analysis functional entities based on the performance analysis results; and allocating computing resources to the multiple data analysis functional entities based on the computing resource usage.

[0020] According to one aspect of the embodiments of this application, a data processing method is provided, applied to a performance analysis service consumer, comprising: receiving measured values ​​of performance parameters sent by a performance analysis service producer; the measured values ​​of the performance parameters are obtained by the performance analysis service producer from measuring the performance parameters of multiple data analysis functional entities based on the business processing parameters of multiple data analysis functional entities; performing performance analysis on the multiple data analysis functional entities based on the measured values ​​of the performance parameters; and processing the multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0021] According to one aspect of the embodiments of this application, a data processing apparatus is provided, applied to a performance analysis service production end, comprising: a performance measurement module configured to measure the performance parameters of multiple data analysis functional entities based on business processing parameters of multiple data analysis functional entities; a first performance analysis module configured to perform performance analysis on the multiple data analysis functional entities based on the measured values ​​of the performance parameters; and a first processing module configured to process the multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0022] According to one aspect of the embodiments of this application, a data processing apparatus is provided, applied to a performance analysis service consumer, comprising: a performance parameter receiving module configured to receive measured values ​​of performance parameters sent by a performance analysis service producer; the measured values ​​of the performance parameters are obtained by the performance analysis service producer from measuring the performance parameters of multiple data analysis functional entities based on the business processing parameters of multiple data analysis functional entities; a second performance analysis module configured to perform performance analysis on the multiple data analysis functional entities based on the measured values ​​of the performance parameters; and a second processing module configured to process the multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0023] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the data processing method described above.

[0024] According to one aspect of the embodiments of this application, an electronic device is provided, including: a processor; and a memory for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the data processing method described above.

[0025] In the technical solution provided in the embodiments of this application, by calculating the performance parameters of the data analysis function entity based on the business processing parameters of the data analysis function entity, the performance of the data analysis function entity with different logical functions can be flexibly analyzed, and the service performance of the data analysis function entity can be evaluated based on the performance analysis results. Then, the data analysis function entity can be processed to improve the service performance of the data analysis function entity and realize unified management of the data analysis function entity that supports logical function decomposition.

[0026] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0028] Figure 1 This is a flowchart illustrating a data processing method in an exemplary embodiment of this application;

[0029] Figure 2This is a schematic diagram illustrating an application scenario of a data processing method as shown in an exemplary embodiment of this application;

[0030] Figure 3 This is a flowchart illustrating a data processing method in another exemplary embodiment of this application;

[0031] Figure 4 This is a schematic diagram illustrating the sampling of performance parameters as an exemplary embodiment of this application;

[0032] Figure 5 This is a flowchart illustrating a data processing method in another exemplary embodiment of this application;

[0033] Figure 6 This is an exemplary embodiment of the present application illustrating the interaction diagram for load balancing of multiple NWDAF devices;

[0034] Figure 7 This is a flowchart illustrating a data processing method in another exemplary embodiment of this application;

[0035] Figure 8 This is an interactive diagram illustrating a data processing method in an exemplary embodiment of this application;

[0036] Figure 9 This is a schematic diagram of a data processing apparatus illustrating an exemplary embodiment of this application;

[0037] Figure 10 This is a schematic diagram of a data processing apparatus illustrating another exemplary embodiment of this application;

[0038] Figure 11 This is a schematic diagram of the structure of a computer system for an electronic device, as illustrated in an exemplary embodiment of this application. Detailed Implementation

[0039] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments identical to those described in this application. Rather, they are merely examples of apparatuses and methods identical to some aspects of this application as detailed in the appended claims.

[0040] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0041] It should be noted that "multiple" as mentioned in this application refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0042] In the eNA (Study of Enablers for Network Automation for 5G) project of 3GPP Release 16 (Rel-16), the concept of NWDAF was proposed. NWDAF is used to perform network data analysis services. It can collect specific data from specific Network Functions (NFs), Operation Administration and Maintenance (OAM) systems, or Application Functions (AFs), perform big data analysis on certain network elements to obtain specific analysis results, and send these results to specific NFs, OAMs, or AFs as needed. NWDAF is a crucial network function for achieving network intelligence. Furthermore, in Rel-17, NWDAF was decomposed into AnLF and MTLF. Therefore, in practical application scenarios, three types of NWDAF instances can be deployed: NWDAF devices containing AnLF, NWDAF devices containing MTLF, and NWDAF devices containing both AnLF and MTLF, improving the flexibility of NWDAF deployment.

[0043] However, while the above solutions can improve the flexibility of NWDAF deployment, they also further increase the difficulty of managing NWDAF, thereby affecting the evaluation and optimization of NWDAF service performance.

[0044] Therefore, this application provides a data processing method, the execution entity of which is the production end of a performance analysis service. For example... Figure 1 As shown, the method includes at least steps S110 to S130, which are described in detail below:

[0045] Step S110: Measure the performance parameters of multiple data analysis functional entities based on their business processing parameters.

[0046] It should be noted that business processing parameters are used to characterize the relevant parameters of the data analysis function entity in processing network data analysis services, while performance parameters are used to characterize the performance of the data analysis function entity.

[0047] It is understood that the data analysis function entity in the embodiments of this application can be an NWDAF device or other data analysis devices, and this application does not impose specific limitations on it. The following embodiments use an NWDAF device as an example to explain this application.

[0048] For example, the performance analysis service provider may send a service processing parameter acquisition request to the NWDAF device, so that the NWDAF device, upon receiving the request, will feed back the service processing parameters to the performance analysis service provider. Alternatively, the NWDAF device may proactively report its own service processing parameters to the performance analysis service provider. For instance, the NWDAF device may report service processing parameters at preset intervals, or it may report service processing parameters every time it performs network data analysis service processing. This application does not impose any specific limitations on this.

[0049] For example, such as Figure 2 As shown, the performance analysis service consumer and the performance analysis service producer are connected. The performance analysis service consumer is used to characterize devices that have performance analysis requirements for NWDAF devices. The performance analysis service producer is connected to n NWDAF devices, where n is an integer greater than or equal to 1. The type of NWDAF device can be one or more of the following: NWDAF device containing AnLF, NWDAF device containing MTLF, and NWDAF device containing both AnLF and MTLF.

[0050] After receiving a performance analysis request from the performance analysis service consumer, the performance analysis service producer sends a service processing parameter acquisition request to each NWDAF device to obtain the service processing parameters returned by each NWDAF device based on the service processing parameter acquisition request, and then measures the performance parameters based on the service processing parameters.

[0051] Step S120: Perform performance analysis on multiple data analysis functional entities based on the measured values ​​of performance parameters.

[0052] Performance analysis is used to analyze the performance of NWDAF devices when performing data analysis on network data analysis services within a preset time period.

[0053] For example, performance analysis can be performed on the measured values ​​of performance parameters of multiple data analysis functional entities based on performance indicators. These performance indicators can be pre-configured in the performance analysis service producer or carried in the performance analysis request sent by the performance analysis service consumer; this application does not impose specific limitations on this. Performance indicators specifically include the measured values ​​(including the range of values) of performance parameters. Based on the relationship between the measured values ​​of performance parameters and the corresponding performance indicators, performance analysis results can be obtained.

[0054] For example, the measured value of the performance parameter is the average analysis time of the NWDAF device in performing network data analysis services within a specified time period. When the measured value of this performance parameter is greater than the average analysis time in the performance index, it indicates that the data analysis time of the NWDAF device is too slow. That is, the performance analysis result of the measured value of this performance parameter is that the data analysis time of the NWDAF device is too slow.

[0055] Optionally, the measured values ​​of performance parameters can be preprocessed according to performance evaluation conditions to obtain preprocessed performance parameters. Performance analysis can then be performed on these preprocessed parameters to obtain performance analysis results. The performance evaluation conditions include one or more of the following: performance data statistical granularity, performance data category, and performance data screening conditions.

[0056] The granularity of performance data statistics indicates the granularity of the performance parameters to be analyzed. Performance data granularity can include one or more of the following: region level, cell level, grid level, network element level, network slice level, subnetwork level, network slice service level, tenant level, and user level. For example, if the performance data granularity is region level, it means that the production end of the performance analysis service needs performance measurement data from each NWDAF device at the region level.

[0057] The performance data category indicates the category of the performance parameter to be analyzed. For example, if the performance data category is Single Network Slice Selection Assistance Information (S-NSSAI), it means that the performance analysis service provider needs the performance measurement data of each NWDAF device associated with S-NSSAI. If the performance data category is Analytics Identity Document (Analytics ID), it means that the performance analysis service provider needs the performance measurement data of each NWDAF device associated with Analytics ID.

[0058] Performance data filtering criteria are used to indicate the filtering conditions that the performance parameters to be analyzed must meet. These criteria can include network problem conditions, time range conditions, etc. For example, if the performance data filtering criteria include a network problem condition, specifically insufficient data processing resources, it means that the performance analysis service provider needs the performance parameters corresponding to when each NWDAF device experiences insufficient data processing resources. As another example, if the performance data filtering criteria include a time range condition, specifically Sundays, it means that the performance analysis service provider needs performance parameters from 0:00 to 24:00 on Sundays.

[0059] Step S130: Process multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0060] It should be noted that the purpose of processing multiple NWDAF devices is to improve the service performance of the NWDAF devices. This can be to perform load balancing of the NWDAF devices, or to perform fault prediction and fault resolution of the NWDAF devices. This application does not impose any specific restrictions on this.

[0061] The load of an NWDAF device measures its current operating status and reflects its workload. A lower workload level indicates a lower load, while a higher workload level indicates a higher load. When the load of an NWDAF device exceeds a preset load limit, it indicates that the load is above the standard value, and therefore load balancing is required.

[0062] Load balancing of NWDAF devices refers to reducing the load on NWDAF devices whose busyness exceeds a preset target, thereby achieving load balancing of NWDAF devices.

[0063] In some implementations, processing multiple data analysis functional entities based on the performance analysis results includes: obtaining the computing resource usage of the multiple data analysis functional entities based on the performance analysis results; and allocating computing resources to the multiple data analysis functional entities based on the computing resource usage.

[0064] For example, a method to reduce the load of an NWDAF device whose load is higher than the preset load index can be to allocate computing resources to the NWDAF device, such as allocating the idle computing resources of an NWDAF device whose load is lower than the preset load index to an NWDAF device whose load is higher than the preset load index, so as to improve the resource utilization of the NWDAF device.

[0065] In some implementations, NWDAF services in NWDAF devices with loads exceeding a preset load threshold may be redistributed to NWDAF devices with loads below a preset load threshold to ensure the processing efficiency of NWDAF services. Alternatively, all NWDAF services may be uniformly allocated to uniformly manage the number of NWDAF services processed by multiple NWDAF devices, thereby avoiding unbalanced loads on NWDAF devices caused by unreasonable NWDAF service allocation.

[0066] The data processing method of this application connects the performance analysis service production end with multiple NWDAF devices, which can flexibly perform performance analysis on NWDAF devices with different logical functions, thereby evaluating the service performance of NWDAF devices, detecting performance problems of NWDAF devices based on the evaluation results, and processing the performance problems of NWDAF devices to improve the service performance of NWDAF devices and realize unified management of NWDA devices that support logical function decomposition.

[0067] In some implementations, please refer to Figure 3 , Figure 3 This is a flowchart illustrating a data processing method according to another exemplary embodiment. In the above exemplary embodiment, the business processing parameters include at least one of service request information and service response information. Figure 1 Step S110 involves measuring the performance parameters of multiple data analysis functional entities based on their business processing parameters, including steps S111 to S113.

[0068] Step S111: Collect service request information received by the data analysis function entity within a specified time period, and / or collect service response information generated by the data analysis function entity within a specified time period to obtain business processing parameters.

[0069] Optionally, the service processing parameters are the service processing status of each NWDAF device. These parameters include the number of service requests received and the number of service responses sent by each NWDAF device. A service request refers to a data analysis request sent from the NWDAF service requester to the NWDAF device, and the NWDAF device sends a service response back to the NWDAF service requester based on the service request.

[0070] The system collects service request information received by the data analysis function entity within a specified time period, and / or collects service response information generated by the data analysis function entity within the specified time period to obtain business processing parameters. The specified time period can be carried in the performance analysis request sent from the performance analysis service consumer to the performance analysis service producer.

[0071] Step S112: Generate at least one first performance measurement data for the data analysis function entity based on the business processing parameters.

[0072] The production side of the performance analysis service obtains the first performance measurement data corresponding to each NWDAF device based on the business processing parameters. For example, the business processing parameters of each NWDAF device are recorded to obtain the first performance measurement data corresponding to each NWDAF device.

[0073] Step S113: Within a specified time period, sample and statistically analyze the first performance measurement data to generate at least one second performance measurement data for the data analysis functional entity.

[0074] The performance analysis service production end can obtain the second performance measurement data of each NWDAF device within a specified time period based on the first performance measurement data corresponding to each NWDAF device. The second performance measurement data is used to characterize the processing status of the NWDAF device when performing data analysis on the network data analysis service within the specified time period.

[0075] Optionally, the performance analysis request sent by the performance analysis service consumer carries a specified time period and sampling interval for the NWDAF device performance analysis. The performance analysis service producer samples the data within the specified time period according to the performance analysis request and at preset time intervals to obtain the sampling results. Then, the sampling results are statistically analyzed to obtain the second performance measurement data for each NWDAF device within the specified time period.

[0076] For example, if the performance analysis service consumer sends a performance analysis request specifying a time period of 9:00 AM to 10:00 AM today for performance analysis of the NWDAF device, with a sampling interval of 5 minutes, then the performance analysis service producer will sample within that specified time period at preset intervals to obtain 12 sampling results. These 12 sampling results are then statistically analyzed to obtain the second performance measurement data of the NWDAF device between 9:00 AM and 10:00 AM.

[0077] Optionally, the formula or algorithm for statistically analyzing the first performance measurement data can be pre-configured. If the performance analysis service producer receives a performance analysis request from the performance analysis service consumer, it can then use the pre-configured statistical formula to calculate the first performance measurement data. For example, if the performance analysis service producer pre-configures an averaging formula for service requests, the average value of service requests received by the NWDAF device within a preset time period can be calculated using the pre-configured formula.

[0078] Optionally, the formula or algorithm for statistically analyzing the first performance measurement data can be included in the performance analysis request sent by the performance analysis service consumer. The performance analysis service producer obtains the statistical formula based on the received performance analysis request and can then use that formula to statistically analyze the first performance measurement data. For example, if the performance analysis request includes a formula for calculating the maximum value of service requests, the formula can be used to calculate the maximum value of service requests received by the NWDAF device within a preset time period.

[0079] In some implementations, the data analysis functional entity includes at least one of the following: a data analysis functional entity with analysis logic function, a data analysis functional entity with model training logic function, and a data analysis functional entity with both analysis logic function and model training logic function.

[0080] In some implementations, the first performance measurement data and the second performance measurement data each include measurement data associated with the logical function of the data analysis functional entity; generating at least one first performance measurement data for the data analysis functional entity based on business processing parameters, and sampling and statistically analyzing the first performance measurement data within a specified time period to generate at least one second performance measurement data for the data analysis functional entity, including:

[0081] If the data analysis function entity is a data analysis function entity with analysis logic function, then generate the first performance measurement data and the second performance measurement data corresponding to the data analysis function entity with analysis logic function.

[0082] If the data analysis function entity is a data analysis function entity with model training logic, then generate the first performance measurement data and the second performance measurement data corresponding to the data analysis function entity with model training logic.

[0083] If the data analysis function entity is a data analysis function entity that has both analysis logic function and model training logic function, then generate the first performance measurement data and the second performance measurement data corresponding to the data analysis function entity that has both analysis logic function and model training logic function.

[0084] It is understandable that NWDAF devices include various types, such as NWDAF devices containing AnLF, NWDAF devices containing MTLF, and NWDAF devices containing both AnLF and MTLF. Each NWDAF device processes various types of business data, such as business data for S-NSSAI and business data for Analytics ID. Therefore, by using data analysis function entity identifiers and business identifiers to instruct the performance analysis service production end to flexibly obtain business processing parameters from multiple NWDAF devices, data processing efficiency can be improved.

[0085] For example, the NWDAF device to be analyzed is identified based on the data analysis function entity identifier, and then the service processing parameters to be analyzed corresponding to the service identifier are obtained from the NWDAF device to be analyzed.

[0086] For example, if the performance analysis request sent from one performance analysis service provider to another carries a data analysis function entity identifier, and the provider determines that the data analysis function entity to be analyzed is one with analysis logic functionality, then it generates first and second performance measurement data corresponding to that entity. If the provider determines that the data analysis function entity to be analyzed is one with model training logic functionality, then it generates first and second performance measurement data corresponding to that entity. If the provider determines that the data analysis function entity to be analyzed is one with both analysis logic and model training logic functionality, then it generates first and second performance measurement data corresponding to that entity.

[0087] In some implementations, service request information includes at least one of service request and service subscription; service response information includes at least one of service response and service notification; the parameter type of the business processing parameters includes at least one of service request or subscription, service response or notification, service success response or notification, and service error response or notification; generating at least one first performance measurement data for the data analysis function entity based on the business processing parameters includes:

[0088] Determine the cumulative counter corresponding to the business processing parameter based on the parameter type of the business processing parameter;

[0089] Within a specified time period, the service processing parameters are counted using a cumulative counter to obtain the first performance measurement data;

[0090] If the parameter type of the business processing parameter includes service request or subscription, then the value of the cumulative counter corresponding to the service request or subscription parameter is updated to obtain the first performance measurement data;

[0091] If the parameter type of the business processing parameter includes service response or notification, then the value of the cumulative counter corresponding to the service response or notification parameter is updated to obtain the first performance measurement data.

[0092] If the parameter type of the business processing parameter includes a service success response or notification parameter, then the value of the cumulative counter corresponding to the service success response or notification parameter is updated.

[0093] If the parameter type of the business processing parameter includes service error response or notification parameters, then the value of the cumulative counter corresponding to the service error response or notification parameter is updated.

[0094] Here, a service request refers to a data analysis and acquisition request sent by the NWDAF service requester to the NWDAF device, and the NWDAF device responding to the service requester with a service response; a service subscription refers to the NWDAF device sending a data acquisition request to the NWDAF service requester, the NWDAF service requester collecting and processing the corresponding business data according to the NWDAF service subscription request, and then uploading the obtained business data to the NWDAF device for data analysis, and the NWDAF device sending a service notification to the NWDAF service requester based on the data analysis results; a service success response refers to a successful service response from the NWDAF service requester; and a service error response refers to a failed service response from the NWDAF service requester.

[0095] Confirm the parameter type of the business processing parameters, and then update the value of the cumulative counter corresponding to each business processing parameter according to the parameter type to obtain the first performance measurement data.

[0096] In some implementations, the first performance measurement data includes at least one of the following: the number of service requests or subscriptions, the number of service responses or notifications, the number of successful service responses or notifications, and the number of error service responses or notifications; within a specified time period, the service processing parameters are counted using a cumulative counter to obtain the first performance measurement data, including:

[0097] If the data analysis function entity receives a service request or subscription, the value of the first cumulative counter related to the service request or subscription is incremented by 1;

[0098] If the data analysis function entity generates a service response or notification, the value of the second cumulative counter associated with the service response or notification is incremented by 1;

[0099] If the data analysis function entity generates a successful service response or notification, the value of the third cumulative counter related to the successful service response or notification is incremented by 1;

[0100] If the data analysis function entity generates a service error response or notification, the value of the fourth cumulative counter related to the service error response or notification is incremented by 1;

[0101] The first performance measurement data includes at least one of the values ​​of the first cumulative counter, the second cumulative counter, the third cumulative counter, and the fourth cumulative counter.

[0102] For example, the performance analysis service producer has a first performance measurement data set, ReqSubNbrNWDAF. This first performance measurement data includes the value of a first cumulative counter corresponding to each NWDAF service discovery request and NWDAF service subscription request received by each NWDAF device. Specifically, whenever an NWDAF device receives a service request or service subscription, it sends a request reception feedback to the performance analysis service producer. This request reception feedback carries the identifier of the NWDAF device and the type identifier of the received content (service request or service subscription). Based on the NWDAF device identifier and the type identifier of the received content in the request reception feedback, the performance analysis service producer increments the value of the corresponding first cumulative counter in the first performance measurement data ReqSubNbrNWDAF by 1.

[0103] For example, the performance analysis service producer has a first performance measurement data set, ResponseNotifyNbrNWDAF. This first performance measurement data includes a second cumulative counter corresponding to the service responses and service notifications sent by each NWDAF device. Typically, whenever an NWDAF device sends a service response or service notification, it sends a response and notification feedback to the performance analysis service producer. This response and notification feedback carries the identifier of the NWDAF device and the type identifier of the sent content (service response or service notification). Based on the NWDAF device identifier and the type identifier of the sent content in the response and notification feedback, the performance analysis service producer increments the value of the corresponding second cumulative counter in the first performance measurement data ResponseNotifyNbrNWDAF by 1.

[0104] For example, the performance analysis service producer has a first performance measurement data set, SucResponseNotifyNbrNWDAF. This first performance measurement data includes a third cumulative counter corresponding to the service success response and service success notification sent by each NWDAF device. It can be that whenever an NWDAF device executes a service success response and service success notification, it sends a success feedback to the performance analysis service producer. This success feedback carries the identifier of the NWDAF device and the type identifier of the success feedback (service success response and service success notification). The performance analysis service producer increments the value of the corresponding third cumulative counter in the first performance measurement data, SucResponseNotifyNbrNWDAF, by 1 based on the NWDAF device identifier and the type identifier of the success feedback.

[0105] For example, the performance analysis service producer has a first performance measurement data set, ErrResponseNotifyNbrNWDAF. This first performance measurement data includes a sub-cumulative counter corresponding to the service error response and service error notification sent by each NWDAF device. It can be that whenever an NWDAF device executes a service error response or service error notification, it sends an error feedback to the performance analysis service producer. This error feedback carries the identifier of the NWDAF device and the type identifier of the error feedback (service error response and service error notification). Based on the NWDAF device identifier and the type identifier of the error feedback in the error feedback, the performance analysis service producer increments the value of the corresponding fourth cumulative counter in the first performance measurement data ErrResponseNotifyNbrNWDAF by 1.

[0106] In some implementations, within a specified time period, the first performance measurement data is sampled and statistically analyzed to generate at least one second performance measurement data for the data analysis functional entity, including:

[0107] If the parameter type of the business processing parameter is service request or subscription, the value of the first cumulative counter corresponding to the service request or subscription is sampled within a specified time period to obtain multiple sampled performance parameters.

[0108] If the parameter type of the business processing parameter is service response or notification, the value of the second cumulative counter corresponding to the service response or notification will be sampled within a specified time period to obtain multiple sampled performance parameters.

[0109] If the parameter type of the business processing parameter is a service success response or notification, then the value of the third cumulative counter corresponding to the service success response or notification is sampled within a specified time period to obtain multiple sampled performance parameters.

[0110] If the parameter type of the business processing parameter is a service error response or notification, then the value of the fourth cumulative counter corresponding to the service error response or notification is sampled within a specified time period to obtain multiple sampled performance parameters.

[0111] Sampling performance parameters refer to the specific content of the cumulative counter at a certain moment. For example, such as... Figure 4 As shown, the preset time interval is 1 minute, and the specified time period is from start time t1 to end time t2. Starting from time t1, every minute, the content of the cumulative counter is collected to obtain a sampling performance parameter, and the collected sampling performance parameter and the collection time are recorded. Until the current time is no longer within the specified time period, n sampling performance parameters are obtained at different times: parameter 1, parameter 2, parameter 3, ..., parameter n-1, parameter n.

[0112] Furthermore, statistical analysis is performed on multiple sampled performance parameters to obtain secondary performance measurement data for multiple NWDAF devices. For example, when the sampled performance parameters are numerical values, the statistical method involves calculating the values, such as averaging or median calculations. It is understandable that different statistical methods can be selected based on the data type of the sampled performance parameters to summarize the performance parameter information within a specified time period and obtain secondary performance measurement data.

[0113] In some implementations, within a specified time period, the first performance measurement data is sampled and statistically analyzed to generate at least one second performance measurement data for the data analysis functional entity, including:

[0114] Obtain statistical strategies that match the first performance measurement data;

[0115] If the statistical strategy for the first performance measurement data is the average value statistical strategy, then the average value of multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and the average value is used as the second performance measurement data corresponding to the first performance measurement data.

[0116] If the statistical strategy for the first performance measurement data is the maximum value statistical strategy, then the maximum value of the multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and the maximum value is used as the second performance measurement data corresponding to the first performance measurement data.

[0117] If the statistical strategy for the first performance measurement data is the minimum value statistical strategy, then the minimum value of multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and the minimum value is used as the second performance measurement data corresponding to the first performance measurement data.

[0118] For example, a statistical strategy matching the first performance measurement data can be obtained based on the parameter type of the first performance measurement data. The parameter type is used to characterize the category information of the first performance measurement data, and the statistical strategy refers to the specific method used to perform statistics on the sampled performance parameters.

[0119] For example, the first performance measurement data can be divided into different parameter types according to the different NWDAF devices. For instance, the parameter type of the first performance measurement data in an NWDAF device containing AnLF is the analysis logic function class; the parameter type of the first performance measurement data in an NWDAF device containing MTLF is the model training logic function class; and the parameter type of the first performance measurement data in an NWDAF device containing both AnLF and MTLF is the analysis and model training logic function class.

[0120] It is understood that the parameter type of the first performance measurement data can be selected according to the actual application situation, and this application does not make specific restrictions here.

[0121] After determining the parameter type of the first performance measurement data, obtain the statistical strategy that matches that parameter type. For example, the performance analysis service production side may store a mapping table between parameter types and statistical strategies. Based on the parameter type of the first performance measurement data, query the mapping table to obtain the matching statistical strategy.

[0122] Optionally, if the statistical strategy for the performance parameters is an average value statistical strategy, then the average value of multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and the average value is used as the second performance measurement data corresponding to the first performance measurement data.

[0123] For example, the calculation of multiple sampled performance parameters for the first performance measurement data with parameter types of service request or service subscription can be achieved using the following formula:

[0124]

[0125] Wherein, ReqSubNbrNWDAFMean is a second performance measurement data with parameter type of service request or service subscription, and ReqSubNbrNWDAF i The sampling performance parameter is the first performance measurement data. This sampling performance parameter is obtained by sampling the first performance measurement data with parameter type of service request or service subscription within a specified time period, where n is the number of sampling performance parameters.

[0126] For example, the calculation of second performance measurement data with parameter types of service response or service notification can be achieved using the following formula:

[0127]

[0128] Among them, ResponseNotifyNbrNWDAFMean is a second performance measurement data with a parameter type of service response or service notification, and ResponseNotifyNbrNWDAF i This is the sampled performance parameter corresponding to the performance parameter. The sampled performance parameter is obtained by sampling the first performance measurement data with the parameter type of service response or service notification within a specified time period. n is the number of sampled performance parameters.

[0129] For example, the calculation of second performance measurement data with parameter types of service success response or service success notification can be achieved using the following formula:

[0130]

[0131] Among them, SucResponseNotifyNbrNWDAFMean is a second performance measurement data with a parameter type of service success response or service success notification, and SucResponseNotifyNbrNWDAF i This is the sampled performance parameter corresponding to the performance parameter. The sampled performance parameter is obtained by sampling the first performance measurement data with the parameter type of service success response or service success notification within a specified time period. n is the number of sampled performance parameters.

[0132] For example, the calculation of second performance measurement data with parameter types of service error response or service error notification can be achieved using the following formula:

[0133]

[0134] Among them, ErrResponseNotifyNbrNWDAFMean is a second performance measurement data with a parameter type of service error response or service error notification, and ErrResponseNotifyNbrNWDAF i This is the sampled performance parameter corresponding to the performance parameter. The sampled performance parameter is obtained by sampling the first performance measurement data with the parameter type of service error response or service error notification within a specified time period, and n is the number of sampled performance parameters.

[0135] Optionally, if the statistical strategy for the first performance measurement data is a maximum value statistical strategy, then the maximum value of the multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and this maximum value is used as the second performance measurement data corresponding to the first performance measurement data. If the statistical strategy for the first performance measurement data is a minimum value statistical strategy, then the minimum value of the multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and this minimum value is used as the second performance measurement data corresponding to the first performance measurement data.

[0136] For example, the calculation of second performance measurement data with parameter types of service request or service subscription can be achieved using the following formula:

[0137] ReqSubNbrNWDAFMax=max(ReqSubNbrNWDAF i ), 1≤i≤n

[0138] Wherein, ReqSubNbrNWDAFMax is the second performance measurement data corresponding to the first performance measurement data whose parameter type is service request or service subscription, and ReqSubNbrNWDAF iThe sampling performance parameter is the first performance measurement data. This sampling performance parameter is obtained by sampling the first performance measurement data with parameter type of service request or service subscription within a specified time period, where n is the number of sampling performance parameters.

[0139] For example, the calculation of second performance measurement data with parameter types of service response or service notification can be achieved using the following formula:

[0140] ResponseNotifyNbrNWDAFMax=max(ResponseNotifyNbrNWDAF i ),1≤i

[0141] ≤n

[0142] Wherein, ResponseNotifyNbrNWDAFMax is the second performance measurement data with a parameter type of service response or service notification, and ResponseNotifyNbrNWDAF i The sampling performance parameter is the first performance measurement data. This sampling performance parameter is obtained by sampling the first performance measurement data with the parameter type of service response or service notification within a specified time period. n is the number of the sampling performance parameters.

[0143] For example, the calculation of second performance measurement data with parameter types of service success response or service success notification can be achieved using the following formula:

[0144] SucResponseNotifyNbrNWDAFMax

[0145] =max(SucResponseNotifyNbrNWDAF i ), 1≤i≤n

[0146] Among them, SucResponseNotifyNbrNWDAFMax is the second performance measurement data with a parameter type of service success response or service success notification, and SucResponseNotifyNbrNWDAF i The sampling performance parameter is the first performance measurement data. This sampling performance parameter is obtained by sampling the first performance measurement data with the parameter type of service success response or service success notification within a specified time period. n is the number of the sampling performance parameters.

[0147] For example, the calculation of second performance measurement data with parameter types of service error response or service error notification can be achieved using the following formula:

[0148] ErrResponseNotifyNbrNWDAFMax

[0149] =max(ErrResponseNotifyNbrNWDAF i ), 1≤i≤n

[0150] Among them, ErrResponseNotifyNbrNWDAFMax is the second performance measurement data with the parameter type of service error response or service error notification, and ErrResponseNotifyNbrNWDAF i The sampling performance parameter is the first performance measurement data. This sampling performance parameter is obtained by sampling the first performance measurement data with the parameter type of service error response or service error notification within a specified time period. n is the number of sampling performance parameters.

[0151] Furthermore, the second performance measurement data corresponding to the first performance measurement data contained in each NWDAF device are summarized to obtain the second performance measurement data of each NWDAF device.

[0152] In some implementations, the second performance measurement data includes at least one of the following: average, maximum, or minimum number of service requests or subscriptions; average, maximum, or minimum number of service responses or notifications; average, maximum, or minimum number of successful service responses or notifications; and average, maximum, or minimum number of error service responses or notifications.

[0153] In some implementations, the first performance measurement data and the second performance measurement data each include measurement data associated with specific information, which includes at least one of the following: single network slice selection assistance information, analysis type information, request type information, subscription type information, service type information, and analysis identification information.

[0154] If the above performance measurement is for S-NSSAI, then the above performance measurement may include performance measurement data for each NWDAF associated with S-NSSAI; if the above performance measurement is for analysis type information, request type information, or subscription type information, then the above performance measurement may include performance measurement data for each NWDAF associated with each analysis type information, request type information, or subscription type information; if the above performance measurement is for Analytics ID, then the above performance measurement may include performance measurement data for each NWDAF associated with Analytics ID.

[0155] In some implementations, the process of performing performance analysis on multiple data analysis functional entities based on the measured values ​​of performance parameters includes: performing numerical anomaly analysis on the second performance measurement data to obtain the numerical analysis results of the parameter items; performing numerical trend analysis on the second performance measurement data based on historical second performance measurement data to obtain the numerical trend analysis results of the parameter items; and determining the performance analysis results based on the numerical analysis results of the parameter items and the numerical trend analysis results of the parameter items.

[0156] The performance analysis results are used to characterize whether there are any anomalies in the various parameters in the second performance measurement data.

[0157] The second performance measurement data includes at least one parameter item. Numerical anomaly analysis is performed on the value corresponding to each parameter item to identify abnormal parameter items in the second performance measurement data, thus obtaining the parameter item numerical analysis result. For example, the performance analysis service production end stores the normal value range for each parameter item of the second performance measurement data. If the value corresponding to a parameter item is detected to be within the normal value range, the parameter item numerical analysis result is considered normal; if the value corresponding to a parameter item is detected to be outside the normal value range, the parameter item numerical analysis result is considered abnormal.

[0158] Furthermore, whenever the performance analysis service generates second performance measurement data, it stores this second performance measurement data and its generation time in a historical second performance measurement data set. Historical second performance measurement data is retrieved by querying this set. Then, based on this historical data, a trend analysis of parameter values ​​is performed to obtain the results. For example, the historical second performance measurement data is sorted according to its generation time, and the trend of each parameter value in the sorted historical second performance measurement data is determined. This trend can be either increasing or decreasing.

[0159] This application embodiment obtains abnormal parameter items in the second performance measurement data by combining the numerical analysis results of parameter items and the numerical change trend analysis results of parameter items, so as to generate performance analysis results based on the abnormal parameter items.

[0160] For example, based on the numerical analysis results of each parameter item in the second performance measurement data, the parameter items that are currently abnormal in the second performance measurement data are obtained; based on the numerical change trend of each parameter item in the second performance measurement data, the value of the parameter item at the next moment is predicted, and numerical anomaly analysis is performed on the value of the parameter item at the next moment to obtain the parameter items that may be abnormal at the next moment in the second performance measurement data.

[0161] In some implementations, processing the plurality of data analysis functional entities based on the performance analysis results obtained from the performance analysis includes: performing fault prediction on the plurality of data analysis functional entities based on the performance analysis results to obtain fault prediction results; determining fault solutions based on the fault prediction results; and executing fault solutions on the data analysis functional entities.

[0162] It should be noted that the performance analysis service stores fault solutions in the production end. Fault prediction is performed based on the performance analysis results to determine whether the corresponding NWDAF device has a fault, so as to obtain the fault prediction result. Then, the fault prediction result that matches the fault solution is sent to the NWDAF device so that the NWDAF device can execute the fault solution to eliminate the fault of each NWDAF device.

[0163] In some implementations, please refer to Figure 5 , Figure 5 This is a flowchart illustrating a data processing method according to another exemplary embodiment. In the above exemplary embodiment, the process of processing multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis in step S130 may include steps S131 to S133:

[0164] Step S131: Receive a data analysis function entity allocation request. The data analysis function entity allocation request carries parameter information of the data analysis service to be processed.

[0165] The data analysis service to be processed can be sent by NWDAF devices to the performance analysis service producer. For example, an NWDAF device whose load exceeds the load threshold sends the data analysis service to be processed to the performance analysis service producer, so that the performance analysis service producer can reallocate the data analysis service to be processed, thereby achieving load balancing for the NWDAF devices. Alternatively, the data analysis service can be sent by an NWDAF service requester with NWDAF service needs to the performance analysis service producer, so that the performance analysis service producer can allocate the NWDAF service according to the performance analysis results of each NWDAF device, thereby achieving load balancing for the NWDAF devices. The NWDAF service requesters include, but are not limited to, NF devices, OAM devices, or AF devices.

[0166] Step S132: Select the target data analysis function entity that matches the parameter information of the data analysis service to be processed based on the performance analysis results of multiple data analysis function entities.

[0167] The performance analysis service production side obtains the target NWDAF device that meets the parameter information carried in the NWDAF service discovery request based on the NWDAF service discovery request.

[0168] The performance analysis service production end stores overview information of each NWDAF device registered on it. This overview information includes the S-NSSAI of the network slice corresponding to the NWDAF device, the Analytics ID of each supported network data analysis service, and the service area information. It also includes the performance analysis results of the corresponding NWDAF device. The performance analysis results are used to characterize the performance parameter information of each network data analysis service supported by the NWDAF device. The performance parameter information of the NWDAF device for different network data analysis services can be used to characterize its performance when performing data analysis on different network data analysis services.

[0169] Specifically, the network slice corresponding to the NWDAF device can be determined based on its S-NSSAI, and the type of network data analysis service supported by the NWDAF device can be determined based on its Analytics ID. It is understood that each NWDAF device can support one or more types of network data analysis services. The service area information of the NWDAF device can be used to determine its service area; for example, this service area information could be a list of tracking areas.

[0170] Step S133: Assign the data analysis service to be processed to the target data analysis function entity.

[0171] An NWDAF service discovery response is generated based on the performance parameter information of the target NWDAF device, and then sent to the NWDAF service requesting end.

[0172] The NWDAF service requester receives the NWDAF service discovery response and determines the NWDAF device to be requested based on the performance parameter information of each target NWDAF device in the NWDAF service discovery response. Then, it sends a service request to the NWDAF device to be requested. The service request contains other parameter information such as the Analytics ID of the requested network data analysis service.

[0173] After receiving a service request, the NWDAF device analyzes the corresponding service data, generates a service response based on the analysis results, and sends the response to the NWDAF service requester. Specifically, the NWDAF device can collect network operation data from the core network control plane network function (NF), obtain terminal and network-related statistical data from the OAM, and acquire application data from the AF to obtain service data, depending on the network data analysis service required. It then analyzes this service data and feeds the analysis results back to the NF device, OAM device, or AF device.

[0174] For example, please see Figure 6 , Figure 6 The interaction diagram for load balancing multiple NWDAF devices includes: Step S610, the performance analysis service producer performs performance analysis based on the service processing parameters of each NWDAF device, obtaining performance analysis results for each of the n NWDAF devices, where n is an integer greater than 1; Step S620, the NWDAF service requesting end sends an NWDAF service discovery request to the performance analysis service producer, which contains parameter information of the network data analysis service requested by the NWDAF service requesting end; Step S630, the performance analysis service producer, based on the network... The data analysis service parameter information and the performance analysis results corresponding to each NWDAF device are used to obtain multiple target NWDAF devices, and an NWDAF service discovery response is sent back to the NWDAF service requesting end based on the multiple target NWDAF devices; in step S640, the NWDAF service requesting end determines the NWDAF device to be requested as NWDAF-1 from the multiple target NWDAF devices and sends a service request to NWDAF-1; in step S650, NWDAF-1 performs data analysis according to the service request and sends a service response to the NWDAF service requesting end based on the data analysis results.

[0175] By storing overview information and performance parameters of each NWDAF device on the production side of the performance analysis service, the production side can allocate appropriate NWDAF devices to received NWDAF service discovery requests, enabling unified management of all NWDAF devices. Simultaneously, when acquiring target NWDAF devices, the production side can select those with lower loads to ensure load balancing across all NWDAF devices.

[0176] In some implementations, the data processing method further includes: generating a performance analysis report based on at least one of the first performance measurement data and the second performance measurement data; and sending the performance analysis report to a performance analysis service consumer.

[0177] In some implementations, please refer to Figure 7 , Figure 7 This is a flowchart illustrating a data processing method according to another exemplary embodiment, applied to a performance analysis service consumer. The method includes at least steps S710 to S730, which are described in detail below:

[0178] Step S710: Receive the measured values ​​of performance parameters sent by the performance analysis service production end; the measured values ​​of performance parameters are obtained by the performance analysis service production end from measuring the performance parameters of multiple data analysis functional entities based on the business processing parameters of multiple data analysis functional entities.

[0179] Step S720: Perform performance analysis on multiple data analysis functional entities based on the measured values ​​of the performance parameters.

[0180] Step S730: Process multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0181] After receiving the performance analysis report sent by the performance analysis service producer, the performance analysis service consumer obtains the measured values ​​of the performance parameters of each data analysis functional entity contained in the performance analysis report, performs performance analysis on multiple data analysis functional entities based on the measured values ​​of the performance parameters, and processes multiple data analysis functional entities based on the performance analysis results obtained.

[0182] The specific implementation method for the performance analysis service consumer to perform performance analysis on multiple data analysis functional entities and process these entities based on the performance analysis results can be found in [link to relevant documentation]. Figure 1 The specific implementation methods of steps S120 and S130 are not described in detail here.

[0183] In some implementations, please refer to Figure 8 , Figure 8 This is an interaction diagram of a data processing method provided as an exemplary embodiment. The data processing method is applied to a data processing system, which includes a performance analysis service producer, a performance analysis service consumer, and n NWDAF devices, where n is an integer greater than 1. The performance analysis service producer, the performance analysis service consumer, and the n NWDAF devices are communicatively connected.

[0184] In this embodiment, the data processing method includes: Step S810, the performance analysis service consumer sends a performance analysis request to the performance analysis service producer, the performance analysis request carrying a data analysis function entity identifier; Step S820, the performance analysis service producer confirms the NWDAF device to be analyzed based on the data analysis function entity identifier in the performance analysis request, and sends a service processing parameter acquisition request to the NWDAF device to be analyzed, so that the NWDAF device can return the service processing parameters; Step S830, the performance analysis service producer measures the performance parameters of the NWDAF device to be analyzed based on the service processing parameters, and sends the measured values ​​of the performance parameters to the performance analysis service consumer; Step S840, the performance analysis service consumer obtains the performance analysis results of the NWDAF device to be analyzed based on the measured values ​​of the performance parameters, so as to process each NWDAF device according to the performance analysis results, such as load balancing, fault prediction and fault resolution, etc.

[0185] The data processing method of this application calculates the performance parameters of the data analysis functional entities based on their business processing parameters. This allows for flexible performance analysis of data analysis functional entities with different logical functions, thereby evaluating their service performance. Based on the evaluation results, performance problems of the data analysis functional entities are detected, and these problems are addressed to improve their service performance and achieve unified management of data analysis functional entities that support logical function decomposition.

[0186] Figure 9 This is a block diagram of a data processing apparatus 900 shown in one embodiment of this application, applied to the production end of a performance analysis service, such as... Figure 9 As shown, the data processing device 900 includes:

[0187] The performance measurement module 910 is configured to measure the performance parameters of multiple data analysis functional entities based on their business processing parameters.

[0188] The first performance analysis module 920 is configured to perform performance analysis on multiple data analysis functional entities based on the measured values ​​of performance parameters.

[0189] The first processing module 930 is configured to process multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0190] In one embodiment of this application, the service processing parameters include at least one of service request information and service response information; the performance measurement module 910 may include:

[0191] The business processing parameter acquisition unit is configured to collect service request information received by the data analysis function entity within a specified time period, and / or collect service response information generated by the data analysis function entity within a specified time period to obtain business processing parameters.

[0192] The first performance measurement data generation unit is configured to generate at least one first performance measurement data for a data analysis function entity based on business processing parameters.

[0193] The second performance measurement data generation unit is configured to sample and statistically analyze the first performance measurement data within a specified time period to generate at least one second performance measurement data for the data analysis function entity.

[0194] In one embodiment of this application, the data analysis function entity includes at least one of the following: a data analysis function entity with analysis logic function, a data analysis function entity with model training logic function, and a data analysis function entity with both analysis logic function and model training logic function.

[0195] In one embodiment of this application, the first performance measurement data and the second performance measurement data respectively include measurement data associated with the logical function of the data analysis function entity; the first performance measurement data generation unit and the second performance measurement data generation unit include:

[0196] The first data measurement unit is configured to generate first performance measurement data and second performance measurement data corresponding to the data analysis function entity that has analysis logic function if the data analysis function entity is a data analysis function entity with analysis logic function.

[0197] The second data measurement unit is configured to generate first performance measurement data and second performance measurement data corresponding to the data analysis function entity that has model training logic if the data analysis function entity is a data analysis function entity with model training logic.

[0198] The third data measurement unit is configured to generate first performance measurement data and second performance measurement data corresponding to the data analysis function entity that simultaneously possesses analysis logic function and model training logic function if the data analysis function entity possesses both analysis logic function and model training logic function.

[0199] In one embodiment of this application, the service request information includes at least one of service request and service subscription; the service response information includes at least one of service response and service notification; and the parameter type of the business processing parameters includes at least one of service request or subscription, service response or notification, service success response or notification, and service error response or notification.

[0200] The first performance measurement data generation unit includes:

[0201] The counter determination unit is configured to determine the cumulative counter corresponding to the business processing parameter based on the parameter type of the business processing parameter.

[0202] The counting unit is configured to use a cumulative counter to count the service processing parameters within a specified time period to obtain the first performance measurement data.

[0203] The first counting subunit is configured to update the value of the cumulative counter corresponding to the service request or subscription parameter if the parameter type of the business processing parameter includes service request or subscription, so as to obtain the first performance measurement data.

[0204] The second counting subunit is configured to update the value of the cumulative counter corresponding to the service response or notification parameter if the parameter type of the service processing parameter includes service response or notification, so as to obtain the first performance measurement data.

[0205] The third counting subunit is configured to update the value of the cumulative counter corresponding to the service success response or notification parameter if the parameter type of the service processing parameter includes a service success response or notification parameter.

[0206] The fourth counting subunit is configured to update the value of the cumulative counter corresponding to the service error response or notification parameter if the parameter type of the service processing parameter includes a service error response or notification parameter.

[0207] In one embodiment of this application, the first performance measurement data includes at least one of the following: the number of service requests or subscriptions, the number of service responses or notifications, the number of successful service responses or notifications, and the number of service error responses or notifications.

[0208] The counting unit includes:

[0209] The first cumulative counter update unit is configured to increment the value of the first cumulative counter related to the service request or subscription by 1 if the data analysis function entity receives a service request or subscription.

[0210] The second cumulative counter update unit is configured to increment the value of the second cumulative counter related to the service response or notification by 1 if the data analysis function entity generates a service response or notification.

[0211] The third cumulative counter update unit is configured to increment the value of the third cumulative counter related to the successful service response or notification if the data analysis function entity generates a successful service response or notification.

[0212] The fourth cumulative counter update unit is configured to increment the value of the fourth cumulative counter related to the service error response or notification by 1 if the data analysis function entity generates a service error response or notification.

[0213] The first performance measurement data includes at least one of the values ​​of the first cumulative counter, the second cumulative counter, the third cumulative counter, and the fourth cumulative counter.

[0214] In one embodiment of this application, the second performance measurement data generation unit includes:

[0215] The first sampling unit is configured to sample the value of the first cumulative counter corresponding to the service request or subscription within a specified time period if the parameter type of the business processing parameter is a service request or subscription, so as to obtain multiple sampling performance parameters.

[0216] The second sampling unit is configured to sample the value of the second cumulative counter corresponding to the service response or notification within a specified time period if the parameter type of the service processing parameter is service response or notification, so as to obtain multiple sampling performance parameters.

[0217] The third sampling unit is configured to sample the value of the third cumulative counter corresponding to the service success response or notification within a specified time period if the parameter type of the service processing parameter is a service success response or notification, so as to obtain multiple sampling performance parameters.

[0218] The fourth sampling unit is configured to sample the value of the fourth cumulative counter corresponding to the service error response or notification within a specified time period if the parameter type of the service processing parameter is a service error response or notification, so as to obtain multiple sampling performance parameters.

[0219] In one embodiment of this application, the second performance measurement data generation unit includes:

[0220] The statistical strategy confirmation unit is configured to acquire a statistical strategy that matches the first performance measurement data.

[0221] The first statistical unit is configured to calculate the average value of multiple sampled performance parameters corresponding to the first performance measurement data if the statistical strategy for the first performance measurement data is the average value statistical strategy, and use the average value as the second performance measurement data corresponding to the first performance measurement data.

[0222] The second statistical unit is configured to calculate the maximum value of multiple sampled performance parameters corresponding to the first performance measurement data if the statistical strategy for the first performance measurement data is the maximum value statistical strategy, and use the maximum value as the second performance measurement data corresponding to the first performance measurement data.

[0223] The third statistical unit is configured to calculate the minimum value of multiple sampled performance parameters corresponding to the first performance measurement data if the statistical strategy for the first performance measurement data is the minimum value statistical strategy, and use the minimum value as the second performance measurement data corresponding to the first performance measurement data.

[0224] In one embodiment of this application, the second performance measurement data includes at least one of the following: average, maximum, or minimum number of service requests or subscriptions; average, maximum, or minimum number of service responses or notifications; average, maximum, or minimum number of successful service responses or notifications; and average, maximum, or minimum number of error service responses or notifications.

[0225] In one embodiment of this application, the first performance measurement data and the second performance measurement data each include measurement data associated with specific information, which includes at least one of the following: single network slice selection assistance information, analysis type information, request type information, subscription type information, service type information, and analysis identification information.

[0226] In one embodiment of this application, the data processing apparatus 900 further includes:

[0227] The performance analysis report generation unit is configured to generate a performance analysis report based on at least one of the first performance measurement data and the second performance measurement data.

[0228] The performance analysis report sending unit is configured to send the performance analysis report to the performance analysis service consumer.

[0229] In one embodiment of this application, the first processing module 930 includes:

[0230] The fault prediction unit is configured to perform fault prediction on multiple data analysis functional entities based on performance analysis results, and obtain fault prediction results.

[0231] The fault solution acquisition unit is configured to determine the fault solution based on the fault prediction results.

[0232] The fault solution sending unit is configured to execute fault solutions for data analysis function entities.

[0233] In one embodiment of this application, the first processing module 930 includes:

[0234] The allocation request receiving unit is configured to receive allocation requests from data analysis function entities, which carry parameter information of the data analysis service to be processed.

[0235] The data analysis function entity matching unit is configured to select a target data analysis function entity that matches the parameter information of the data analysis service to be processed based on the performance analysis results of multiple data analysis function entities.

[0236] The allocation unit is configured to allocate the data analysis service to be processed to the target data analysis function entity.

[0237] In one embodiment of this application, the first processing module 930 includes:

[0238] The computing resource usage acquisition unit is configured to acquire the computing resource usage of the multiple data analysis functional entities based on the performance analysis results.

[0239] The computing resource allocation unit is configured to allocate computing resources to the plurality of data analysis function entities based on the computing resource usage.

[0240] It should be noted that the information transmission device and the data processing method provided in the above embodiments belong to the same concept. The specific ways in which each module and unit performs operations have been described in detail in the method embodiments and will not be repeated here. In practical applications, the information transmission device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation.

[0241] Figure 10 This is a block diagram of a data processing apparatus 1000 shown in one embodiment of this application, applied to a performance analysis service consumer, such as... Figure 10 As shown, the data processing device 1000 includes:

[0242] The performance parameter receiving module 1010 is configured to receive the measured values ​​of performance parameters sent by the performance analysis service production end; the measured values ​​of performance parameters are obtained by the performance analysis service production end from measuring the performance parameters of multiple data analysis functional entities based on the business processing parameters of multiple data analysis functional entities.

[0243] The second performance analysis module 1020 is configured to perform performance analysis on multiple data analysis functional entities based on the measured values ​​of performance parameters.

[0244] The second processing module 1030 is configured to process multiple data analysis functional entities based on the performance analysis results obtained from the performance analysis.

[0245] It should be noted that the information transmission device and the data processing method provided in the above embodiments belong to the same concept. The specific ways in which each module and unit performs operations have been described in detail in the method embodiments and will not be repeated here. In practical applications, the information transmission device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation.

[0246] Figure 11 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown.

[0247] It should be noted that, Figure 11 The computer system 1100 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0248] like Figure 11 As shown, the electronic device 1100 is manifested in the form of a general-purpose computing device. The components of the electronic device 1100 may include, but are not limited to: at least one processing unit 1110, at least one storage unit 1120, a bus 1130 connecting different system components (including storage unit 1120 and processing unit 1110), and a display unit 1140.

[0249] The storage unit stores program code, which can be executed by the processing unit 1110, causing the processing unit 1110 to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0250] Storage unit 1120 may include readable media in the form of volatile storage units, such as random access memory (RAM) 1121 and / or cache memory 1122, and may further include read-only memory (ROM) 1123.

[0251] Storage unit 1120 may also include a program / utility 1124 having a set (at least one) program module 1125, such program module 1125 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0252] Bus 1130 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0253] Electronic device 1100 can also communicate with one or more external devices 1170 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 1100, and / or with any device that enables electronic device 1100 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1150. Furthermore, electronic device 1100 can also communicate with one or more networks (e.g., local area network, wide area network, and / or public network, such as the Internet) via network adapter 1160. As shown, network adapter 1160 communicates with other modules of electronic device 1100 via bus 1130. It should be understood that, although not shown in the figures, other hardware and / or application modules can be used in conjunction with electronic device 1100, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, tape drives, and data backup storage systems.

[0254] In particular, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer applications. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. When the computer program is executed by the processing unit 1110, it performs various functions defined in the system of this application.

[0255] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0256] The units described in the embodiments of this application can be implemented by application programs or by hardware, and the described units can also be located in a processor. The names of these units do not necessarily constitute a limitation on the unit itself.

[0257] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned data processing method. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0258] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the data processing methods provided in the various embodiments described above.

[0259] The above description is merely a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be determined by the scope of protection claimed in the claims.

Claims

1. A data processing method, characterized in that, The method, applied to the production side of performance analysis services, includes: Collect service request information received and / or service response information generated by multiple data analysis functional entities within a specified time period. The data analysis functional entities include at least one of the following: a data analysis functional entity with analysis logic function, a data analysis functional entity with model training logic function, and a data analysis functional entity with both analysis logic function and model training logic function. At least one first performance measurement data is generated for each data analysis functional entity based on the service request information and / or the service response information, and the first performance measurement data is sampled and statistically analyzed within a specified time period to generate at least one second performance measurement data for each data analysis functional entity; wherein the first performance measurement data and the second performance measurement data are respectively associated with the logical functions of the corresponding data analysis functional entities. Anomaly analysis and trend analysis were performed on the second performance measurement data to obtain the performance analysis results. The multiple data analysis functional entities are processed based on the performance analysis results.

2. The method according to claim 1, characterized in that, The service request information includes at least one of service request and service subscription; the service response information includes at least one of service response and service notification; the parameter type of the service request information and / or service response information includes at least one of service request or subscription, service response or notification, service success response or notification, and service error response or notification; generating at least one of the first performance measurement data for the data analysis function entity based on the service request information and / or service response information includes: Determine the cumulative counter corresponding to the service request information and / or service response information based on the parameter type of the service request information and / or service response information; Within a specified time period, the service request information and / or service response information are counted using the cumulative counter to obtain the first performance measurement data; If the parameter type of the service request information and / or service response information includes the service request or subscription, then the value of the cumulative counter corresponding to the service request or subscription parameter is updated to obtain the first performance measurement data; If the parameter type of the service request information and / or service response information includes the service response or notification, then the value of the cumulative counter corresponding to the service response or notification parameter is updated to obtain the first performance measurement data. If the parameter type of the service request information and / or service response information includes the service success response or notification parameter, then the value of the cumulative counter corresponding to the service success response or notification parameter is updated. If the parameter type of the service request information and / or service response information includes the service error response or notification parameter, then the value of the cumulative counter corresponding to the service error response or notification parameter is updated.

3. The method according to claim 2, characterized in that, The first performance measurement data includes at least one of the following: the number of service requests or subscriptions, the number of service responses or notifications, the number of successful service responses or notifications, and the number of error service responses or notifications. The step of using the cumulative counter to count the service request information and / or service response information within a specified time period to obtain the first performance measurement data includes: If the data analysis function entity receives the service request or subscription, the value of the first cumulative counter related to the service request or subscription is incremented by 1; If the data analysis function entity generates the service response or notification, the value of the second cumulative counter related to the service response or notification is incremented by 1; If the data analysis function entity generates a service success response or notification, the value of the third cumulative counter related to the service success response or notification is incremented by 1; If the data analysis function entity generates the service error response or notification, the value of the fourth cumulative counter related to the service error response or notification is incremented by 1; The first performance measurement data includes at least one of the values ​​of the first cumulative counter, the second cumulative counter, the third cumulative counter, and the fourth cumulative counter.

4. The method according to claim 1, characterized in that, The step of sampling and statistically analyzing the first performance measurement data within a specified time period to generate at least one second performance measurement data for the data analysis function entity includes: If the parameter type of the service request information and / or service response information is service request or subscription, then the value of the first cumulative counter corresponding to the service request or subscription is sampled within a specified time period to obtain multiple sampling performance parameters; If the parameter type of the service request information and / or service response information is service response or notification, then the value of the second cumulative counter corresponding to the service response or notification is sampled within a specified time period to obtain multiple sampling performance parameters. If the parameter type of the service request information and / or service response information is a service success response or notification, then the value of the third cumulative counter corresponding to the service success response or notification is sampled within a specified time period to obtain multiple sampling performance parameters. If the parameter type of the service request information and / or service response information is a service error response or notification, then the value of the fourth cumulative counter corresponding to the service error response or notification is sampled within a specified time period to obtain multiple sampled performance parameters.

5. The method according to claim 4, characterized in that, The step of sampling and statistically analyzing the first performance measurement data within a specified time period to generate at least one second performance measurement data for the data analysis function entity includes: Obtain a statistical strategy that matches the first performance measurement data; If the statistical strategy for the first performance measurement data is the average value statistical strategy, then the average value of multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and the average value is used as the second performance measurement data corresponding to the first performance measurement data. If the statistical strategy for the first performance measurement data is the maximum value statistical strategy, then the maximum value of the multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and the maximum value is used as the second performance measurement data corresponding to the first performance measurement data. If the statistical strategy for the first performance measurement data is the minimum value statistical strategy, then the minimum value of multiple sampled performance parameters corresponding to the first performance measurement data is calculated, and the minimum value is used as the second performance measurement data corresponding to the first performance measurement data.

6. The method according to claim 5, characterized in that, The second performance measurement data includes at least one of the following: average, maximum, or minimum number of service requests or subscriptions; average, maximum, or minimum number of service responses or notifications; average, maximum, or minimum number of successful service responses or notifications; and average, maximum, or minimum number of error service responses or notifications.

7. The method according to any one of claims 1 to 6, characterized in that, The first performance measurement data and the second performance measurement data each include measurement data associated with specific information, which includes at least one of the following: single network slice selection assistance information, analysis type information, request type information, subscription type information, service type information, and analysis identification information.

8. The method according to claim 1, characterized in that, The method further includes: A performance analysis report is generated based on at least one of the first performance measurement data and the second performance measurement data; The performance analysis report is sent to the performance analysis service consumer.

9. The method according to claim 1, characterized in that, The process of processing the multiple data analysis functional entities based on the performance analysis results includes: Based on the performance analysis results, fault prediction is performed on the multiple data analysis functional entities to obtain fault prediction results; Determine the fault solution based on the fault prediction results; The fault solution is executed on the data analysis function entity.

10. The method according to claim 1, characterized in that, The process of processing the multiple data analysis functional entities based on the performance analysis results includes: Receive a data analysis function entity allocation request, wherein the data analysis function entity allocation request carries parameter information of the data analysis service to be processed; Based on the performance analysis results of the multiple data analysis functional entities, a target data analysis functional entity that matches the parameter information of the data analysis service to be processed is selected. The data analysis service to be processed is assigned to the target data analysis function entity.

11. The method according to claim 1, characterized in that, The process of processing the multiple data analysis functional entities based on the performance analysis results includes: Based on the performance analysis results, the computing resource usage of the multiple data analysis functional entities is obtained respectively; The computing resources are allocated to the multiple data analysis functional entities based on the computing resource usage.

12. A data processing method, characterized in that, The method, applied to the consumer side of a performance analysis service, includes: The system receives measured values ​​of performance parameters sent by the performance analysis service provider. These measured values ​​are obtained by the performance analysis service provider through the following methods: collecting service request information and / or generated service response information received by multiple data analysis functional entities within a specified time period; generating at least one first performance measurement data for each data analysis functional entity based on the service request information and / or the service response information; and sampling and statistically analyzing the first performance measurement data within the specified time period to generate at least one second performance measurement data. The data analysis functional entities include at least one of the following: data analysis functional entities with analysis logic functions, data analysis functional entities with model training logic functions, and data analysis functional entities that simultaneously possess both analysis logic functions and model training logic functions. The first performance measurement data and the second performance measurement data are respectively associated with the logical functions of the corresponding data analysis functional entities. Anomaly analysis and trend analysis were performed on the second performance measurement data to obtain the performance analysis results. The multiple data analysis functional entities are processed based on the performance analysis results.

13. A data processing apparatus, characterized in that, The device is used in the production side of performance analysis services and includes: A performance measurement module is configured to collect service request information received and / or service response information generated by multiple data analysis functional entities within a specified time period. The data analysis functional entities include at least one of the following: a data analysis functional entity with analysis logic functions, a data analysis functional entity with model training logic functions, and a data analysis functional entity with both analysis logic functions and model training logic functions. The module also generates at least one first performance measurement data for each data analysis functional entity based on the service request information and / or the service response information, and samples and statistically analyzes the first performance measurement data within the specified time period to generate at least one second performance measurement data for each data analysis functional entity. The first performance measurement data and the second performance measurement data are respectively associated with the logical functions of the corresponding data analysis functional entities. The first performance analysis module is configured to perform anomaly analysis and trend analysis on the second performance measurement data to obtain performance analysis results. The first processing module is configured to process the multiple data analysis functional entities based on the performance analysis results.

14. A data processing apparatus, characterized in that, The device is used on the consumer side of performance analysis services and includes: A performance parameter receiving module is configured to receive measured values ​​of performance parameters sent by a performance analysis service producer. The measured values ​​of the performance parameters are obtained by the performance analysis service producer through the following methods: collecting service request information and / or generated service response information received by multiple data analysis functional entities within a specified time period; generating at least one first performance measurement data for each data analysis functional entity based on the service request information and / or the service response information; and sampling and statistically analyzing the first performance measurement data within the specified time period to generate at least one second performance measurement data. The data analysis functional entities include at least one of the following: a data analysis functional entity with analysis logic functions; a data analysis functional entity with model training logic functions; and a data analysis functional entity that simultaneously possesses both analysis logic functions and model training logic functions. The first performance measurement data and the second performance measurement data are respectively associated with the logical functions of the corresponding data analysis functional entities. The second performance analysis module is configured to perform anomaly analysis and trend analysis on the second performance measurement data to obtain performance analysis results. The second processing module is configured to process the multiple data analysis functional entities based on the performance analysis results.

Images