Network element selection method and device based on system indexes and service indexes

By obtaining and calculating the service indicators of network elements and selecting the target network elements of 5GC network elements, the problem of not considering the health status of business logic and business-level load in the existing technology is solved, and more accurate network elements are achieved and resources are optimized. Allocation and network performance.

CN119012393APending Publication Date: 2024-11-22CHINA MOBILE GRP GUANGDONG CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410966731.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

When selecting the target network element, the service logic health status and service-level load of the alternative network element are not considered, which may lead to the selection of network elements that cannot provide normal business logic or network elements with excessive service load.

Method used

By obtaining the business indicators of alternative network elements, including the health status of business-level load and business logic, calculating the total deviation score, and selecting the target network elements based on system indicators and business indicators.

Benefits of technology

Avoid choosing network elements that cannot provide normal business logic and network elements that currently have too high service load, ensuring efficient utilization of network resources and overall performance improvement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119012393A_ABST
    Figure CN119012393A_ABST
Patent Text Reader

Abstract

The invention provides a network element selection method and device based on a system index and a service index, and the method comprises the steps: periodically obtaining a network element service index of an alternative network element through an application function unit, the network element service index comprising a service-level load and a health state of a service logic; in response to the condition that the 5GC network element needs to select a target network element, sending an alternative network element data analysis request message to a network data analysis unit, and collecting a network element system index and a network element service index of the alternative network element through the network data analysis unit; calculating the total deviation score of the alternative network element based on the network element system index and the network element service index of the standby network element; and selecting a target network element from the plurality of alternative network elements based on the deviation total score of the alternative network elements. Based on the scheme provided by the invention, the alternative network element which is in a normal network element state but possibly cannot provide normal service logic can be prevented from being selected as the target network element, and the alternative network element with overhigh current service load can also be prevented from being selected as the target network element.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of core networks, and in particular to a method and device for selecting network elements based on system indicators and service indicators. Background Art

[0002] In the prior art, when selecting target network elements, 5GC network elements only consider system indicators such as network element load (NFload, system-level load, with a value of 1-100 to indicate the load ratio), network element status (NF status, the status of the network element instance, such as registered, suspended, undiscoverable, etc.), and network element resource usage (NF resource usage, such as the allocation of CPU, memory, hard disk, etc.) of the candidate network elements, but do not consider business indicators such as the health status of the business logic of the candidate network elements and business-level load. There are two problems:

[0003] On the one hand, a candidate network element with a normal network element status (external interface, heartbeat, and normal process) may no longer be able to provide normal business logic, resulting in the possibility of selecting a target network element that cannot provide normal business logic.

[0004] On the other hand, the network element load belongs to the system-level load situation, which cannot accurately reflect the load situation of various types of services of the candidate network elements. For example, when the voice service load of a candidate network element 1 is 90%, the NAS short message service load is 10%, and the total system load is 80%; the voice service load of the candidate network element 2 is 10%, the NAS short message service load is 90%, and the total system load is 50%, when a new NAS short message service is triggered, according to the existing solution, the candidate network element 2 with a lower system load will be selected. However, the NAS short message service of the candidate network element 2 is close to saturation and is not a suitable target network element. Summary of the invention

[0005] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0006] To this end, the first purpose of the present application is to propose a network element selection method based on system indicators and business indicators to avoid selecting an alternative network element as a target network element whose status is normal but may no longer be able to provide normal business logic, and to avoid selecting an alternative network element whose current business load is too high as a target network element.

[0007] The second objective of the present application is to propose a network element selection device based on system indicators and service indicators.

[0008] The third objective of the present application is to provide an electronic device.

[0009] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a network element selection method based on system indicators and service indicators, including:

[0010] Periodically acquiring network element service indicators of candidate network elements through application function units, wherein the network element service indicators include service-level load and health status of service logic;

[0011] In response to the 5GC network element needing to select a target network element, sending a candidate network element data analysis request message to a network data analysis unit, and collecting network element system indicators and network element service indicators of the candidate network element through the network data analysis unit;

[0012] Calculating the total deviation score of the candidate network element based on the network element system indicator and the network element service indicator of the standby network element;

[0013] A target network element is selected from a plurality of the candidate network elements based on the total deviation scores of the candidate network elements.

[0014] Optionally, the health status of the service logic of the candidate network element is periodically obtained through the application function unit, including:

[0015] Send a simulated service request to the alternative network element through the application function unit, trigger the alternative network element to execute all or part of the service logic, check and store the health status of all or part of the service logic of the alternative network element, wherein the part of the service logic includes at least one key service logic.

[0016] Optionally, the service level load of the candidate network element is periodically obtained through the application function unit, including:

[0017] One, multiple, or all service types currently being processed by the candidate network element and the corresponding load of each service type are obtained through the application function unit.

[0018] Optionally, collecting network element system indicators and network element service indicators of a plurality of the candidate network elements by the network data analysis unit includes:

[0019] Collecting network element system indicators of the plurality of candidate network elements through the network data analysis unit according to the operation management and maintenance unit and the wireless communication unit, wherein the network element system indicators include network element resource usage, network element load and network element status of the candidate network elements;

[0020] The network data analysis unit collects network element service indicators of a plurality of the candidate network elements according to the application function unit.

[0021] Optionally, the calculating the total deviation score of the candidate network element based on the network element system indicator and the network element service indicator of the standby network element includes:

[0022] Calculating a system deviation integral of the candidate network element based on the network element system indicator of the standby network element;

[0023] Calculating a service deviation score of the candidate network element based on the network element service indicator of the standby network element;

[0024] The sum of the system deviation integral and the service deviation integral of the candidate network element is taken as the total deviation score of the candidate network element.

[0025] Optionally, the calculating the system deviation integral of the candidate network element based on the network element system indicator of the standby network element includes:

[0026] Calculate the year-on-year mean and year-on-year coefficient of the system index of the same small sampling period in n1 consecutive large sampling periods. The expression is:

[0027]

[0028] Among them, Ma is the year-on-year mean of the system indicator, Mi represents the year-on-year coefficient of the system indicator in the same small sampling period within the i-th large sampling period, and x i Represents the system index of the same small sampling period within the i-th large sampling period;

[0029] Calculate the month-on-month mean value and month-on-month coefficient of the system index within the n2 small sampling periods. The expression is:

[0030]

[0031] Where Pa is the mean value of the system index compared with the previous period, Pj represents the system index ratio in the jth small sampling period, x k Represents the system index in the jth small sampling period;

[0032] The weighted score calculation formula is used to calculate the system deviation integral of the candidate network element according to the year-on-year mean value of the system indicator, the year-on-year coefficient of the system indicator, the month-on-month mean value of the system indicator, and the month-on-month coefficient of the system indicator. The expression is:

[0033]

[0034] Where Sp is the system deviation integral, θ m is the year-on-year system index intensity coefficient, θ p is the month-on-month system indicator intensity coefficient, β i The system index intensity coefficient of the same small sampling period in the i-th large sampling period, β j is the system index intensity coefficient of the jth small sampling period.

[0035] Optionally, the calculating the service deviation integral of the candidate network element based on the network element service indicator of the standby network element includes:

[0036] Calculate the year-on-year mean and year-on-year coefficient of the business indicators in the same small sampling period within n1 consecutive large sampling periods. The expression is:

[0037]

[0038] Among them, Ma' is the year-on-year mean of the business indicator, Mi' represents the year-on-year coefficient of the business indicator of the same small sampling period in the i-th large sampling period, and x i ' represents the business indicator of the same small sampling period within the i-th large sampling period;

[0039] Calculate the month-on-month mean value and month-on-month coefficient of the business indicators in the n2 small sampling periods. The expression is:

[0040]

[0041] Where Pa' is the mean value of the business indicator on a month-on-month basis, Pj' represents the business indicator's month-on-month coefficient in the jth small sampling period, x j represents the business indicator in the jth small sampling period;

[0042] The weighted score calculation formula is used to calculate the service deviation score of the candidate network element according to the year-on-year mean value of the service indicator, the year-on-year coefficient of the service indicator, the month-on-month mean value of the service indicator, and the month-on-month coefficient of the service indicator. The expression is:

[0043]

[0044] Wherein, Sa is the business deviation integral, θ m ' is the year-on-year business indicator intensity coefficient, θ p ' is the month-on-month business indicator intensity coefficient, β i 'Business indicator intensity coefficient of the same small sampling period in the i-th large sampling period, β j ' is the business indicator intensity coefficient of the jth small sampling period.

[0045] The selecting a target network element from a plurality of the candidate network elements based on the total deviation scores of the candidate network elements comprises:

[0046] The candidate network element with the smallest total deviation score is selected as the target network element.

[0047] To achieve the above-mentioned purpose, the second aspect of the present application proposes a network element selection device based on system indicators and service indicators, including:

[0048] An acquisition module, used to periodically acquire network element service indicators of candidate network elements through application function units, wherein the network element service indicators include service-level load and health status of service logic;

[0049] A collection module, in response to the 5GC network element needing to select a target network element, is used to send a candidate network element data analysis request message to a network data analysis unit, and collect network element system indicators and network element service indicators of the candidate network element through the network data analysis unit;

[0050] A deviation total score calculation module, used to calculate the deviation total score of the candidate network element based on the network element system index and the network element service index of the standby network element;

[0051] The network element selection module is used to select a target network element from a plurality of the candidate network elements based on the total deviation scores of the candidate network elements.

[0052] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0053] The memory stores computer-executable instructions;

[0054] The processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects above.

[0055] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0056] When selecting the target network element, the health of the business logic of the candidate network element is further considered, which can avoid selecting the candidate network element as the target network element whose status is normal (external interface, heartbeat, process is normal) but may no longer be able to provide normal business logic; when selecting the target network element, the service-level load of the candidate network element is further considered, which can avoid selecting the candidate network element with too high current business load as the target network element; using the deviation integral algorithm, the optimal target network element can be accurately calculated, and by comprehensively evaluating the service-level load and business logic health status of the candidate network elements, as well as system-level performance indicators, the network element that is currently most suitable for carrying new services or redirecting existing services can be accurately identified, which helps to optimize resource allocation, ensure that network resources are used efficiently, and improve overall network performance and service quality.

[0057] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0059] Figure 1 It is a flow chart of a network element selection method based on system indicators and service indicators according to an embodiment of the present application;

[0060] Figure 2 is a network architecture diagram according to an embodiment of the present application;

[0061] Figure 3 is a flowchart of steps for calculating the total deviation score of candidate network elements according to an embodiment of the present application;

[0062] Figure 4 is another network architecture diagram shown according to an embodiment of the present application;

[0063] Figure 5 is another network architecture diagram shown according to an embodiment of the present application;

[0064] Figure 6 is another network architecture diagram shown according to an embodiment of the present application;

[0065] Figure 7 is another network architecture diagram shown according to an embodiment of the present application;

[0066] Figure 8 It is a block diagram of a network element selection device based on system indicators and service indicators according to an embodiment of the present application;

[0067] Fig. 9 It is a block diagram of an electronic device. DETAILED DESCRIPTION

[0068] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0069] A method and device for selecting a network element based on system indicators and service indicators according to an embodiment of the present application will be described below with reference to the accompanying drawings.

[0070] Figure 1 is a flow chart of a network element selection method based on system indicators and service indicators according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0071] Step 101: periodically obtain network element service indicators of candidate network elements through application function units. The network element service indicators include service-level load and health status of service logic.

[0072] In some embodiments of the present application, the following is constructed: Figure 2 The network architecture diagram shown is used to implement the solution proposed in this application.

[0073] Specifically, the health status of the service logic and the service-level load of the candidate network elements (NF1-NF4) are periodically obtained through the application function units (AF1-AF4).

[0074] In one embodiment of the present application, a simulated service request is sent to an alternative network element (NF1-NF4) through an application function unit (AF1-AF4), triggering the alternative network element to execute all or part of the service logic, and checking and storing the health status of all or part of the service logic of the alternative network element.

[0075] The partial business logic includes at least one key business logic, which may be one or more key business logics.

[0076] In another embodiment of the present application, one, multiple, or all service types currently being processed by the candidate network element (NF1-NF4) and the corresponding load of each service type are obtained through the application function unit (AF1-AF4).

[0077] Among them, the service types include positioning services, audio and video services, NAS short message services, Internet access services, user authentication and secondary authentication services, QoS monitoring services, PNI-NPN services, Framed Routing services, ULCL diversion services, 5G LAN services and other 5G private network services.

[0078] Step 102, in response to the 5GC network element needing to select a target network element, sends an alternative network element data analysis request message to the network data analysis unit, and collects network element system indicators and network element service indicators of the alternative network elements through the network data analysis unit.

[0079] In an embodiment of the present application, when a 5GC network element Consumer NF needs to select a target network element, it sends an alternative network element data analysis request message to the network data analysis unit NWDAF. The network data analysis unit NWDAF collects network element system indicators of multiple alternative network elements (NF1-NF4) through the network data analysis unit according to the operation management and maintenance unit OAM and the wireless communication unit NRF. The network element system indicators include the network element resource usage, network element load and network element status of the alternative network elements; and the network data analysis unit NWDAF collects network element service indicators of multiple alternative network elements (NF1-NF4) according to the application function unit (AF1-AF4).

[0080] Step 103: Calculate the total deviation score of the candidate network element based on the network element system index and the network element service index of the standby network element.

[0081] In an embodiment of the present application, after collecting the network element system indicators and network element service indicators of the backup network elements (AF1-AF4), the network data analysis unit NWDAF analyzes the collected information and feeds back the information to the consumer NF. The consumer NF calculates the total deviation score of the candidate network elements based on the data analysis results of the candidate network elements fed back by NWDAF.

[0082] Specifically, Figure 3 As shown, step 103 also includes:

[0083] Step 201: Calculate the system deviation integral of the candidate network element based on the network element system indicator of the standby network element.

[0084] In the embodiment of the present application, it is first necessary to calculate the year-on-year mean value and year-on-year coefficient of the system index of the same small sampling period in n1 consecutive large sampling periods, and the expression is:

[0085]

[0086]

[0087] Among them, Ma is the year-on-year mean of the system index, Mi represents the year-on-year coefficient of the system index in the same small sampling period within the i-th large sampling period, corresponding to the current large sampling period, s i Represents the system index of the same small sampling period within the i-th large sampling period.

[0088] Among them, n1>>10.

[0089] In a possible embodiment, the large sampling period is expressed as days / hours, and the small sampling period is expressed as 30 minutes / 5 minutes.

[0090] Then calculate the mean value of the system index and the system index coefficient in the n2 small sampling periods, corresponding to the current small sampling period, and the expression is:

[0091]

[0092] Among them, Pa is the mean value of the system index compared with the previous period, Ph is the system index coefficient compared with the previous period in the jth small sampling period, x j Represents the system index within the jth small sampling period.

[0093] Among them, n2>>20.

[0094] Finally, based on the weighted score calculation formula, the system deviation integral of the candidate network element is calculated according to the year-on-year mean value of the system indicator, the year-on-year coefficient of the system indicator, the month-on-month mean value of the system indicator, and the month-on-month coefficient of the system indicator. The expression is:

[0095]

[0096] Where Sp is the system deviation integral, θ m is the year-on-year system index intensity coefficient, θ p is the month-on-month system indicator intensity coefficient, β i The system index intensity coefficient of the same small sampling period in the i-th large sampling period, β j is the system indicator intensity coefficient of the jth small sampling period.

[0097] It is understandable that θ m ,θ p , β i , β j The values ​​are all within the range of 0-1, and can be determined according to the actual scenario, so this application will not explain them in detail.

[0098] Step 202: Calculate the service deviation score of the candidate network element based on the network element service indicator of the standby network element.

[0099] In the embodiment of the present application, firstly, it is necessary to calculate the year-on-year mean of the business indicator and the year-on-year coefficient of the same small sampling period in n1 consecutive large sampling periods, and the expression is:

[0100]

[0101]

[0102] Among them, Ma' is the year-on-year mean of the business indicator, Mi' represents the year-on-year coefficient of the business indicator in the same small sampling period within the i-th large sampling period, and s i ' represents the business indicator of the same small sampling period within the i-th large sampling period.

[0103] Among them, n1>>10.

[0104] In a possible embodiment, the large sampling period is expressed as days / hours, and the small sampling period is expressed as 30 minutes / 5 minutes.

[0105] Then calculate the month-on-month mean value and month-on-month coefficient of the business indicators in the n2 small sampling periods. The expression is:

[0106]

[0107] Among them, Pa' is the mean value of the business indicator on a month-on-month basis, Pj' represents the business indicator on-month coefficient in the jth small sampling period, x j Represents the business indicators in the jth small sampling period.

[0108] Among them, n2>>10

[0109] Finally, based on the weighted score calculation formula, the business deviation score of the candidate network element is calculated according to the year-on-year mean of the business indicator, the year-on-year coefficient of the business indicator, the month-on-month mean of the business indicator, and the month-on-month coefficient of the business indicator. The expression is:

[0110]

[0111] Where Sa is the business deviation integral, θ m ' is the year-on-year business indicator intensity coefficient, θ p ' is the month-on-month business indicator intensity coefficient, β i 'Business indicator intensity coefficient of the same small sampling period in the i-th large sampling period, β j ' is the business indicator intensity coefficient of the jth small sampling period.

[0112] It is understandable that θ m '、θ p ', β i '、β j 'The values ​​are all within the range of 0-1, and can be determined according to the actual scenario. This application will not explain them in detail here.

[0113] Step 203: The sum of the system deviation score and the service deviation score of the candidate network element is taken as the total deviation score of the candidate network element.

[0114] It can be understood that after obtaining the system deviation integral and the service deviation integral of the candidate network element, the sum of the system deviation integral and the service deviation integral is used as the total deviation score of the candidate network element, and the expression is:

[0115] W=Sp+Sa

[0116] Wherein, W represents the total score of the deviation.

[0117] Step 104: Select a target network element from multiple candidate network elements based on the total deviation scores of the candidate network elements.

[0118] It can be understood that the larger the total deviation score, the greater the fluctuation between the system indicator set and the business indicator set and the historical normal, and the weaker the stability trend and health; the smaller the total deviation score, the smaller the fluctuation between the system indicator set and the business indicator set and the historical normal, and the stronger the stability trend and health.

[0119] That is, in one embodiment of the present application, the candidate network element with the smallest total deviation score is selected as the target network element.

[0120] It should be noted that in some embodiments of actual scenarios, in order to better implement the solution proposed in this application, it is necessary to Figure 2 The network architecture diagram shown in the figure is modified.

[0121] In one embodiment of the present application, Figure 4 As shown, by reusing and extending the existing NFProfile / load field between NRF and 5GC network elements, the NFProfile / load field usually indicates the current workload level or resource usage of the network function, and the service-level load status of the NF is sent to NRF through the existing NFProfile / load field, thereby achieving compatibility with existing specifications and interfaces to a certain extent.

[0122] Reference Figure 1 , in such Figure 4 In the network architecture diagram shown, some implementation methods have been changed, specifically:

[0123] 1) When the candidate network element (NF1-NF4) sends the network function registration and discovery function Nnrf_NFManagementServicex request message to the NRF, it sets its service level load status in the extended NFProfile / load field in the Nnrf_NFManagement Servicex request message;

[0124] 2) Periodically obtain the health status of the service logic of the candidate network elements (NF1-NF4) through the application function units (AF1-AF4);

[0125] 3) When a 5GC network element (Consumer NF) needs to select a target network element, it sends a candidate network element data analysis request message to NWDAF;

[0126] 4) NWDAF collects the resource usage, load, status, and service-level load of the candidate NEs from OAM and NRF; and collects the health status of the service logic of the candidate NEs from AF;

[0127] 5) NWDAF generates data analysis results based on the collected information and feeds them back to the consumer NF;

[0128] 6) The consumer NF calculates the total deviation score of the candidate network elements based on the data analysis results of the candidate network elements fed back by the NWDAF, and selects the target network element from multiple candidate network elements based on the total deviation score of the candidate network elements.

[0129] It is to be understood that steps 2)-6) have been described in detail in the embodiments of the method and will not be elaborated in detail here.

[0130] In another embodiment of the present application, Figure 5 As shown, the health status of the service logic and service-level load of the candidate network elements (NF1-NF4) are obtained through a master control AF, thereby facilitating unified control and calculation.

[0131] In another embodiment of the present application, Figure 6 As shown, OAM / NRF is omitted.

[0132] It can be understood that, under normal circumstances, NWDAF only obtains system indicators of candidate network elements NF from OAM and NRF, and sends them to Consumer NF; Consumer NF selects target NF based on system indicators; only when necessary, NWDAF further obtains business indicators such as the health status of business logic and business-level load of candidate network elements (NF1-NF4) from AF (AF1-AF4), and sends them to Consumer NF; when selecting the target NF, Consumer NF further considers business indicators on the basis of considering system indicators.

[0133] rely on Figure 6 The structure shown obtains business indicators only when necessary, and realizes targeted consideration of business indicators according to the degree of refinement of actual needs.

[0134] In another embodiment of the present application, Figure 7 As shown, NWDAF / OAM / NRF are omitted.

[0135] It can be understood that, under normal circumstances, NWDAF obtains system indicators of candidate network elements NF from OAM and NRF, and sends them to Consumer NF; only when necessary, the master control AF obtains business indicators such as the health status of the business logic and business-level load of the candidate network elements (NF1-NF4) from AF (AF1-AF4), and sends them to Consumer NF; when selecting the target NF, Consumer NF further considers business indicators on the basis of considering system indicators.

[0136] rely on Figure 7 The structure shown obtains service indicators only when necessary; and there is no need to change NWDAF and NRF, and the change to the existing network is minimal.

[0137] It should be noted that Figure 4-7 The proposed network architecture diagram is a diagram of the network architecture in some embodiments. Figure 2 In practical applications, the appropriate network architecture can be selected according to specific needs and scenarios, and this application does not make any specific restrictions here.

[0138] Figure 8 1 is a block diagram of a network element selection device 10 based on system indicators and service indicators according to an embodiment of the present application, including:

[0139] The acquisition module 100 is used to periodically acquire network element service indicators of the candidate network elements through the application function unit, where the network element service indicators include service-level load and health status of service logic;

[0140] The collection module 200, in response to the 5GC network element needing to select a target network element, is used to send a candidate network element data analysis request message to the network data analysis unit, and collect network element system indicators and network element service indicators of the candidate network element through the network data analysis unit;

[0141] The deviation total score calculation module 300 is used to calculate the deviation total score of the candidate network element based on the network element system index and the network element service index of the standby network element;

[0142] The network element selection module 400 is used to select a target network element from a plurality of candidate network elements based on the total deviation scores of the candidate network elements.

[0143] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0144] Fig. 9 A schematic block diagram of an example electronic device 700 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0145] like Fig. 9 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0146] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0147] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as the voice instruction response method. For example, in some embodiments, the voice instruction response method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the voice instruction response method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the voice instruction response method in any other appropriate manner (e.g., by means of firmware).

[0148] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0149] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0150] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0151] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0152] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0153] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0154] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0155] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A network element selection method based on system indicators and service indicators, characterized in that: include: Periodically acquiring network element service indicators of candidate network elements through application function units, wherein the network element service indicators include service-level load and health status of service logic; In response to the 5GC network element needing to select a target network element, sending a candidate network element data analysis request message to a network data analysis unit, and collecting network element system indicators and network element service indicators of the candidate network element through the network data analysis unit; Calculating the total deviation score of the candidate network element based on the network element system indicator and the network element service indicator of the standby network element; A target network element is selected from a plurality of the candidate network elements based on the total deviation scores of the candidate network elements.

2. The method according to claim 1, characterized in that The health status of the service logic of the candidate network element is periodically obtained through the application function unit, including: Send a simulated service request to the alternative network element through the application function unit, trigger the alternative network element to execute all or part of the service logic, check and store the health status of all or part of the service logic of the alternative network element, wherein the part of the service logic includes at least one key service logic.

3. The method according to claim 1, characterized in that The service-level load of the candidate network element is periodically obtained through the application function unit, including: One, multiple, or all service types currently being processed by the candidate network element and the corresponding load of each service type are obtained through the application function unit.

4. The method according to claim 1, characterized in that: Collecting network element system indicators and network element service indicators of a plurality of candidate network elements through the network data analysis unit includes: Collecting network element system indicators of the plurality of candidate network elements through the network data analysis unit according to the operation management and maintenance unit and the wireless communication unit, wherein the network element system indicators include network element resource usage, network element load and network element status of the candidate network elements; The network data analysis unit collects network element service indicators of a plurality of the candidate network elements according to the application function unit.

5. The method according to claim 4, characterized in that The calculating the total deviation score of the candidate network element based on the network element system indicator and the network element service indicator of the standby network element includes: Calculating a system deviation integral of the candidate network element based on the network element system indicator of the standby network element; Calculating a service deviation score of the candidate network element based on the network element service indicator of the standby network element; The sum of the system deviation integral and the service deviation integral of the candidate network element is taken as the total deviation score of the candidate network element.

6. The method according to claim 5, characterized in that The calculating the system deviation integral of the candidate network element based on the network element system indicator of the standby network element includes: Calculate the year-on-year mean and year-on-year coefficient of the system index of the same small sampling period in n1 consecutive large sampling periods. The expression is: Among them, Ma is the year-on-year mean of the system indicator, Mi represents the year-on-year coefficient of the system indicator in the same small sampling period within the i-th large sampling period, and x i Represents the system index of the same small sampling period within the i-th large sampling period; Calculate the month-on-month mean value and month-on-month coefficient of the system index within the n2 small sampling periods. The expression is: Where Pa is the mean value of the system index compared with the previous period, Pj represents the system index ratio in the jth small sampling period, x j Represents the system index in the jth small sampling period; The weighted score calculation formula is used to calculate the system deviation integral of the candidate network element according to the year-on-year mean value of the system indicator, the year-on-year coefficient of the system indicator, the month-on-month mean value of the system indicator, and the month-on-month coefficient of the system indicator. The expression is: Where Sp is the system deviation integral, θ m is the year-on-year system index intensity coefficient, θ p is the month-on-month system indicator intensity coefficient, β i The system index intensity coefficient of the same small sampling period in the i-th large sampling period, β j is the system index intensity coefficient of the jth small sampling period.

7. The method according to claim 5, characterized in that The calculating the service deviation score of the candidate network element based on the network element service indicator of the standby network element includes: Calculate the year-on-year mean and year-on-year coefficient of the business indicators in the same small sampling period within n1 consecutive large sampling periods. The expression is: Among them, Ma' is the year-on-year mean of the business indicator, Mi' represents the year-on-year coefficient of the business indicator of the same small sampling period in the i-th large sampling period, and x i ' represents the business indicator of the same small sampling period within the i-th large sampling period; Calculate the month-on-month mean value and month-on-month coefficient of the business indicators in the n2 small sampling periods. The expression is: Where Pa' is the mean value of the business indicator on a month-on-month basis, Pj' represents the business indicator's month-on-month coefficient in the jth small sampling period, x j represents the business indicator in the jth small sampling period; The weighted score calculation formula is used to calculate the service deviation score of the candidate network element according to the year-on-year mean value of the service indicator, the year-on-year coefficient of the service indicator, the month-on-month mean value of the service indicator, and the month-on-month coefficient of the service indicator. The expression is: Wherein, Sa is the business deviation integral, θ m ' is the year-on-year business indicator intensity coefficient, θ p ' is the month-on-month business indicator intensity coefficient, β i 'Business indicator intensity coefficient of the same small sampling period in the i-th large sampling period, β j ' is the business indicator intensity coefficient of the jth small sampling period.

8. The method according to claim 1, characterized in that The selecting a target network element from a plurality of the candidate network elements based on the total deviation scores of the candidate network elements comprises: The candidate network element with the smallest total deviation score is selected as the target network element.

9. A network element selection device based on system indicators and service indicators, characterized in that: include: An acquisition module, used to periodically acquire network element service indicators of candidate network elements through application function units, wherein the network element service indicators include service-level load and health status of service logic; A collection module, in response to the 5GC network element needing to select a target network element, is used to send a candidate network element data analysis request message to a network data analysis unit, and collect network element system indicators and network element service indicators of the candidate network element through the network data analysis unit; A deviation total score calculation module, used to calculate the deviation total score of the candidate network element based on the network element system index and the network element service index of the standby network element; The network element selection module is used to select a target network element from a plurality of the candidate network elements based on the total deviation scores of the candidate network elements.

10. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 8.