CN116599862B - Communication method, analysis network element and communication system - Google Patents
Communication method, analysis network element and communication system Download PDFInfo
- Publication number
- CN116599862B CN116599862B CN202310880151.XA CN202310880151A CN116599862B CN 116599862 B CN116599862 B CN 116599862B CN 202310880151 A CN202310880151 A CN 202310880151A CN 116599862 B CN116599862 B CN 116599862B
- Authority
- CN
- China
- Prior art keywords
- analysis
- network element
- analysis result
- result
- request
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 576
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004891 communication Methods 0.000 title claims abstract description 43
- 238000012795 verification Methods 0.000 claims abstract description 128
- 238000012360 testing method Methods 0.000 claims abstract description 73
- 230000004044 response Effects 0.000 claims abstract description 42
- 238000004590 computer program Methods 0.000 claims description 17
- 238000010801 machine learning Methods 0.000 claims description 16
- 238000010200 validation analysis Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 21
- 238000010586 diagram Methods 0.000 description 14
- 238000012545 processing Methods 0.000 description 8
- 238000004088 simulation Methods 0.000 description 4
- 238000012517 data analytics Methods 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0894—Policy-based network configuration management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5003—Managing SLA; Interaction between SLA and QoS
- H04L41/5019—Ensuring fulfilment of SLA
- H04L41/5025—Ensuring fulfilment of SLA by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The disclosure provides a communication method, an analysis network element and a communication system, and relates to the technical field of communication, wherein the method comprises the following steps: the analysis network element receives an analysis request from a service consumer network element; the analysis network element sends a first analysis result of the analysis request to a test verification platform for verification, wherein the test verification platform comprises a twin network element of the network element associated with the analysis result of the analysis request; the analysis network element receives a verification result of the first analysis result from the test verification platform; and the analysis network element sends a first response of the analysis request to the service consumer network element, wherein the first response carries a second analysis result serving as an analysis result of the analysis request, and the second analysis result is obtained according to the verification result. Thus, the accuracy of the analysis result sent by the analysis network element can be improved.
Description
Technical Field
The disclosure relates to the technical field of communication, in particular to a communication method, an analysis network element and a communication system.
Background
In the core network, the analysis network element may send a corresponding analysis result according to an analysis request from the service consumer network element, so that the network element of the user as the analysis result performs a corresponding decision according to the analysis result provided by the analysis network element, thereby improving the autonomy capability and the intelligent level of the core network.
Disclosure of Invention
However, there are cases where the accuracy of the analysis result sent by the analysis network element is low. In this case, the network element of the user as the analysis result may make an erroneous decision according to the analysis result, thereby degrading the user experience.
In view of this, the embodiments of the present disclosure propose a solution capable of improving the accuracy of the analysis result sent by the analysis network element.
According to an aspect of the embodiments of the present disclosure, there is provided a communication method including: the analysis network element receives an analysis request from a service consumer network element; the analysis network element sends a first analysis result of the analysis request to a test verification platform for verification, wherein the test verification platform comprises a twin network element of the network element associated with the analysis result of the analysis request; the analysis network element receives a verification result of the first analysis result from the test verification platform; and the analysis network element sends a first response of the analysis request to the service consumer network element, wherein the first response carries a second analysis result serving as an analysis result of the analysis request, and the second analysis result is obtained according to the verification result.
In some embodiments, the validation result represents an accuracy of the first analysis result; the method further comprises the steps of: and under the condition that the accuracy is lower than a preset accuracy, the analysis network element adjusts the first analysis result to obtain the second analysis result.
In some embodiments, the first response also carries the first analysis result if the accuracy is below the preset accuracy.
In some embodiments, the first analysis result is derived based on a machine learning model; the method further comprises the steps of: and under the condition that the accuracy is lower than a preset accuracy, the analysis network element indicates to continue training the machine learning model.
In some embodiments, the analysis network element takes the first analysis result as the second analysis result in a case that the accuracy is not lower than the preset accuracy.
In some embodiments, under the condition that a preset condition is met, the analysis network element sends the first analysis result to the test verification platform for verification; and if the preset condition is not met, the analysis network element directly sends a second response of the analysis request to the service consumer network element, wherein the second response carries the first analysis result which is the analysis result of the analysis request.
In some embodiments, the preset condition includes a first condition that a duration between a time when an analysis result of the analysis request needs to be used and a current time is greater than a preset duration.
In some embodiments, the preset condition includes a second condition, where the second condition is that an influence of an analysis result of the analysis request on the core network is greater than a preset influence.
In some embodiments, the analysis request carries a first parameter indicative of the influence; the method further comprises the steps of: and the analysis network element determines whether the second condition is met according to the first parameter.
In some embodiments, the first response also carries the verification result.
In some embodiments, the analysis network element is a network data analysis network element.
According to another aspect of the embodiments of the present disclosure, there is provided an analysis network element, comprising: a module configured to perform the communication method according to any one of the above embodiments.
According to yet another aspect of the embodiments of the present disclosure, there is provided an analysis network element, comprising: a memory; and a processor coupled to the memory and configured to perform the communication method of any of the embodiments described above based on instructions stored in the memory.
According to still another aspect of the embodiments of the present disclosure, there is provided a communication system including: the analysis network element of any one of the embodiments above; and the test verification platform comprises a twinning network element of a network element associated with an analysis result of the analysis request and is configured to verify the first analysis result from the analysis network element.
According to a further aspect of the disclosed embodiments, a computer readable storage medium is provided, comprising computer program instructions, wherein the computer program instructions, when executed by a processor, implement the communication method according to any one of the embodiments described above.
According to a further aspect of the disclosed embodiments, there is provided a computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the communication method according to any one of the above embodiments.
In the embodiment of the disclosure, after receiving an analysis request from a service consumer network element, the analysis network element sends a first analysis result of the analysis request to a test verification platform for verification. Then, the analysis network element sends a first response carrying an analysis result to the service consumer network element, wherein the analysis result is a second analysis result obtained according to a verification result fed back by the test verification platform for verifying the first analysis result. Thus, the accuracy of the analysis result sent by the analysis network element can be improved.
The technical scheme of the present disclosure is described in further detail below through the accompanying drawings and examples.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art. In the accompanying drawings:
FIG. 1 is a flow diagram of a communication method according to some embodiments of the present disclosure;
FIG. 2 is a flow diagram of a communication method according to further embodiments of the present disclosure;
fig. 3 is a schematic diagram of an analysis network element according to some embodiments of the present disclosure;
fig. 4 is a schematic structural diagram of an analysis network element according to further embodiments of the present disclosure;
fig. 5 is a schematic diagram of a communication system according to some embodiments of the present disclosure.
Detailed Description
The following description of the technical solutions in the embodiments of the present disclosure will be made clearly and completely with reference to the accompanying drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments in this disclosure without inventive faculty, are intended to fall within the scope of this disclosure.
The relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any specific values should be construed as merely illustrative, and not a limitation. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
Fig. 1 is a flow diagram of a communication method according to some embodiments of the present disclosure.
As shown in FIG. 1, the communication method includes steps 102-108.
In step 102, an analysis network element receives an analysis request from a service consumer network element.
In some embodiments, the analysis network element may be a network data analysis function (Network Data Analytics Function, NWDAF) network element. NWDAF may provide analysis services such as data analysis, predictive analysis, decision analysis, and the like.
As some implementations, the NWDAF network element may include at least one of an analysis logic function (Analytics Logical Function, anLF) and a model training logic function (Model Training logical function, MTLF). In this case, the analysis network element is an NWDAF network element including AnLF. For example, the analysis network element is an NWDAF network element comprising AnLF; for another example, the analysis network element is an NWDAF network element comprising AnLF and MTLF.
Service consumer network elements may include, but are not limited to, access and mobility management function (Access and Mobility Management Function, AMF) network elements, session management function (Session Management Function, SMF) network elements, policy control function (Policy Control Function, PCF) network elements, network opening function (Network Exposure Function, NEF) network elements, user plane function (User Plane Function, UPF) network elements, and the like.
In step 104, the analysis network element sends the first analysis result of the analysis request to the test verification platform for verification.
Here, the test verification platform comprises a twinning network element of the network element associated with the analysis result of the analysis request.
The network element associated with the analysis result of the analysis request may comprise one or more network elements.
For example, the network element associated with the analysis result may include a network element of the user as the analysis result. The user of the analysis result can make corresponding decisions according to the analysis result. In this case, the network elements associated with the analysis result may also comprise network elements affected by the decisions made by the user of the analysis result.
In some embodiments, the user of the analysis result is a service consumer network element that sends the analysis request. In other embodiments, the party using the analysis results is a network element other than the serving consumer network element that sent the analysis request.
The following description will take the PCF network element as the service consumer network element as an example.
The PCF network element may send an analysis request to the analysis network element requesting the analysis network element to predict traffic conditions for a future period. After the analysis network element sends the predicted traffic situation as an analysis result to the PCF network element, the PCF network element may adjust a quality of service (Quality of Service, qoS) profile according to the analysis result.
The PCF network element may then send the adjusted QoS profile to the SMF network element so that the SMF network element configures the UPF network element according to the adjusted QoS profile to achieve flow control.
In this case, the network elements related to the analysis result of the analysis request may include PCF network elements of the user as the analysis result, and SMF network elements and UPF network elements affected by decisions made by the PCF network elements. In other words, in this case, the test verification platform may include at least a twin network element of three network elements, that is, a PCF network element, an SMF network element, and a UPF network element.
As some implementations, the test verification platform may include a digital twin environment of the core network. That is, the digital twinning environment in the test verification platform may include twinning elements for each element in the core network. The digital twin environment simulates real-time data of the core network. The test verification platform can also predict future data of the core network and simulate the future data. Thus, the test verification platform can verify the first analysis result.
In step 106, the analysis network element receives a validation result of the first analysis result from the test validation platform.
In step 108, the analysis network element sends a first response of the analysis request to the service consumer network element.
Here, the first response carries a second analysis result, which is an analysis result of the analysis request, obtained from a verification result fed back by the test verification platform.
In other words, in step 108, the analysis network element sends a first response carrying the analysis result of the analysis request to the service consumer network element according to the verification result. The analysis result is a second analysis result obtained according to the verification result fed back by the test verification platform, so that the accuracy of the second analysis result is higher.
In the above embodiment, after receiving the analysis request from the service consumer network element, the analysis network element sends the first analysis result of the analysis request to the test verification platform for verification. Then, the analysis network element sends a first response carrying an analysis result to the service consumer network element, wherein the analysis result is a second analysis result obtained according to a verification result fed back by the test verification platform for verifying the first analysis result. Thus, the accuracy of the analysis result sent by the analysis network element can be improved.
Further, since the accuracy of the analysis result transmitted by the analysis network element is improved, the possibility that the network element of the user who is the analysis result performs an erroneous decision according to the analysis result is reduced, so that the user experience can be improved.
The communication method shown in fig. 1 is further described below in connection with some embodiments.
In some embodiments, the verification result represents an accuracy of the first analysis result.
For example, the accuracy of the first analysis result may be expressed as one of a plurality of levels. Different levels indicate different accuracies of the first analysis result.
In this case, the analysis network element may obtain the second analysis result carried in the first response as the analysis result according to the following implementation manner.
As some implementations, the analysis network element takes the first analysis result as the second analysis result in a case that the accuracy of the first analysis result represented by the verification result is not lower than a preset accuracy.
The accuracy of the first analysis result represented by the verification result is not lower than the preset accuracy, which indicates that the accuracy of the first analysis result is higher. In this case, the analysis network element directly sends the first analysis result with higher accuracy as the second analysis result to the service consumer network element.
Thus, the processing pressure of the analysis network element can be reduced while the accuracy of the analysis result sent by the analysis network element is improved, so that the possibility of the analysis network element fault can be reduced.
As other implementations, in a case where the accuracy of the first analysis result represented by the verification result is lower than the preset accuracy, the analysis network element may adjust the first analysis result to obtain the second analysis result.
It will be appreciated that in this case the second analysis result is different from the first analysis result.
The verification result indicates that the accuracy of the first analysis result is lower than the preset accuracy, which indicates that the accuracy of the first analysis result is lower. In this case, the analysis result sent by the analysis network element is a second analysis result obtained by adjusting the first analysis result.
Taking the example that the analysis result includes the QoS profile, the second analysis result may be obtained by adjusting the parameters of the QoS profile in the first analysis result.
Therefore, the possibility that the user of the analysis result makes an erroneous decision according to the first analysis result with lower accuracy can be reduced, and the user experience can be improved.
It can be understood that the first analysis result sent to the test verification platform for verification in step 104 may be an analysis result obtained by the analysis network element for the first time in response to the analysis request from the service consumer network element, or may be a second analysis result obtained by the analysis network element by adjusting the first analysis result according to the verification result fed back by the test verification platform.
For example, after the first analysis result is adjusted to obtain the second analysis result, the analysis network element can further send the adjusted second analysis result to the test verification platform as the first analysis result for verification, so that the accuracy of the analysis result sent by the analysis network element can be further improved.
In some embodiments, in a case where the accuracy of the first analysis result represented by the verification result is lower than the preset accuracy, the first response sent by the analysis network element further carries the first analysis result.
That is, in these embodiments, the first response carries both the second analysis result, which is an adjustment to the first analysis result, and the first analysis result.
Because the network element of the user as the analysis result can not directly make a decision according to the analysis result sent by the analysis network element in certain scenes, the analysis result is adaptively adjusted and the decision is made according to the adjusted analysis result.
The analysis network element sends a second analysis result obtained by adjusting according to the first analysis result to the service consumer network element and simultaneously sends a first analysis result with lower accuracy. Therefore, the situation that the network element of the user serving as the analysis result adaptively adjusts the second analysis result to the first analysis result with lower accuracy can be avoided, and the possibility of making an erroneous decision by the network element can be further reduced, so that the user experience is further improved.
In some embodiments, the first response also carries a validation result of the first analysis result. Therefore, the network element of the user as the analysis result can more reasonably decide how to use the analysis result according to the verification result, so that the possibility of making an erroneous decision by the network element according to the analysis result can be further reduced, and the user experience is further improved.
In some embodiments, the first analysis result is obtained based on a machine learning model. In case the accuracy of the first analysis result represented by the verification result is lower than the preset accuracy, the analysis network element may further instruct to continue training the machine learning model.
As some implementations, the analysis network element is an NWDAF network element that includes only AnLF. In this case, the NWDAF network element as the analysis network element may instruct another NWDAF network element including the MTLF to continue training the machine learning model.
As other implementations, the analysis network element is an NWDAF network element that includes AnLF and MTLF. In this case, analysis of the AnLF in the network element may instruct the MTLF to continue training the machine learning model.
The accuracy of the first analysis results is low, which indicates that the performance of the machine learning model may be poor. In this case, the analysis network element indicates to continue training the machine learning model, so that the performance of the machine learning model can be improved.
Therefore, the analysis result can be obtained based on the machine learning model with better performance, so that the accuracy of the analysis result sent by the analysis network element can be further improved.
In some embodiments, the analysis network element may receive a plurality of analysis requests from different service consumer network elements, in which case the analysis network element obtains a first analysis result for each analysis request. As a first implementation manner, the analysis network element may send the first analysis result of each analysis request to the test verification platform for verification. As a second implementation manner, the analysis network element may send only the first analysis result of the partial analysis request to the test verification platform for verification. The second implementation is described below in connection with some embodiments.
In some embodiments, the analysis network element sends the first analysis result to the test verification platform for verification if the preset condition is met, and the analysis network element directly sends the second response of the analysis request to the service consumer network element if the preset condition is not met. The second response carries the first analysis result as an analysis result of the analysis request.
In other words, in case that the preset condition is not satisfied, the analysis network element does not send the first analysis result to the test verification platform for verification, but directly sends the first analysis result as the analysis result of the analysis request to the service consumer network element.
In this way, the analysis network element can send part of the first analysis results to the test verification platform for verification according to the need, and all the first analysis results do not need to be sent to the test verification platform for verification. In this way, the processing pressures of the analysis network element and the test verification platform can be reduced, and thus the possibility of failure of the analysis network element and the test verification platform can be reduced.
As some implementations, the preset conditions include a first condition that a duration between a time when an analysis result of the analysis request needs to be used and a current time is greater than a preset duration.
The current time may be the time at which the analyzing network element obtains the first analysis result in step 104.
The time period between the current time and the time when the analysis result needs to be used is longer than the preset time period (i.e. the first condition is satisfied), which indicates that there is still sufficient time to verify the first analysis result by the test verification platform. In this case, the analysis network element sends the first analysis result to the test verification platform for verification.
Conversely, the duration between the current time and the time at which the analysis result needs to be used is no greater than the preset duration (i.e., the first condition is not satisfied), which indicates that there may not be enough time to verify the first analysis result by the test verification platform. In this case, the analysis network element directly transmits the first analysis result as an analysis result to the service consumer network element.
For example, for some analysis requests with high timeliness requirements, the user needs to use the analysis results as soon as possible. In this case, the analysis network element may carry the analysis result obtained for the first time in response to the analysis request (i.e. the first analysis result) directly as the analysis result in the second response sent to the service consumer network element, without sending to the test verification platform for verification.
For another example, for some analysis requests that do not have high timeliness requirements, the user may need to delay a period of time before using the analysis results. In this case, the analysis network element may send the analysis result obtained for the first time in response to the analysis request (i.e. the first analysis result) to the test verification platform for verification.
If the verification result indicates that the accuracy of the first analysis result is higher, the analysis network element may carry the first analysis result as the analysis result in a first response sent to the service consumer network element. Otherwise, if the verification result indicates that the accuracy of the first analysis result is low, the analysis network element may adjust the first analysis result to obtain the second analysis result.
If the duration between the time when the second analysis result is obtained (i.e. the current time) and the time when the user needs to use the analysis result is still longer than the preset duration, the analysis network element can send the second analysis result to the test verification platform again as the first analysis result for verification. Otherwise, if the duration between the time when the second analysis result is obtained and the time when the user needs to use the analysis result is not greater than the preset duration, the analysis network element may carry the second analysis result as the analysis result in the first response sent to the service consumer network element.
Under the implementation manner, the analysis network element only sends the first analysis result to the test verification platform for verification when the duration between the current time and the time when the analysis result needs to be used is longer than the preset duration, and does not send the first analysis result to the test verification platform for verification when the duration between the current time and the time when the analysis result needs to be used is not longer than the preset duration. In this way, the processing pressures of the analysis network element and the test verification platform can be reduced, and the analysis result can be ensured to be sent to the service consumer network element before the analysis result needs to be used, so that a user can use the analysis result when the analysis result needs to be used.
As other implementations, the preset condition includes a second condition, where the second condition is that an influence of an analysis result of the analysis request on the core network is greater than the preset influence.
In other words, in these implementations, the analysis network element does not need to send the analysis result with smaller influence on the core network to the test verification platform for verification, but only needs to send the analysis result with larger influence on the core network to the test verification platform for verification.
It can be understood that the influence of the analysis result of the analysis request on the core network, i.e. the influence degree of the analysis result on the core network. In some embodiments, the impact of the analysis result on the core network may be determined based on the importance of the analysis result on the core network. For example, in the case where the importance of the analysis result to the core network is higher, the influence of the analysis result to the core network is larger.
For example, in the case that the analysis result is a predicted User Equipment (UE) location, the User of the analysis result may backup UE-related data to a corresponding network element in advance according to the predicted UE location. In this case, even if the analysis result is inaccurate, the advanced backup of the UE data does not have a great influence on the core network. In other words, the impact of such analysis results on the core network is not great. Thus, for such analysis results, the analysis network element may not have to send to the test verification platform for verification.
For another example, in the case where the analysis result is a predicted network load, the user of the analysis result may perform flow control or offload a service with a larger load according to the predicted network load. In this case, such traffic control or offloading services have a large impact on the core network once the analysis results are inaccurate. Thus, for such analysis results, the analysis network element may send to the test verification platform for verification.
Under the implementation mode, the analysis network element only sends the analysis result with larger influence on the core network to the test verification platform for verification, and does not need to send the analysis result with smaller influence on the core network to the test verification platform for verification. Therefore, the accuracy of the analysis result with larger influence on the core network can be ensured while the processing pressure of the analysis network element and the test verification platform is reduced, so that the user experience can be ensured.
In some embodiments, the analysis request carries a first parameter for indicating an impact. In this case, the analysis network element may determine whether the second condition is met based on the first parameter.
As some implementations, the impact of the analysis results of different analysis requests on the core network may be divided into multiple levels. Different levels may correspond to different identifications, in which case the first parameter may be the identification to which a level corresponds.
For example, the plurality of levels includes three levels, which are a first level indicating that the influence of the analysis result on the core network is small, a second level indicating that the influence of the analysis result on the core network is medium, and a third level indicating that the influence of the analysis result on the core network is large.
In this case, the analysis result obtained by the analysis network element performing the data analysis (e.g., counting the historical data) may be a first level, and the analysis result obtained by the analysis network element performing the predictive analysis or the decision analysis may be a second level or a third level. Taking predictive analysis as an example, UE location prediction may be of a second level and network load prediction may be of a third level.
Fig. 2 is a flow chart of a communication method according to further embodiments of the present disclosure.
As shown in FIG. 2, the communication method includes steps 202-226.
In step 202, an analysis network element receives an analysis request from a service consumer network element.
For example, the analysis network element is an NWDAF network element. In this case, the service consumer network element may send an analysis Request to the analysis network element by invoking an analysis information Request (nnwdaf_analysis info_request) service operation among NWDAF service operations. The analysis request may be used to request an analysis network element for data analysis, predictive analysis, decision analysis, etc.
In step 204, the analyzing network element determines whether the second condition is met.
As some implementations, the analysis network element may determine, according to the first parameter in the analysis request, whether an influence of the analysis result on the core network is greater than a preset influence, so as to determine whether the second condition is satisfied.
In step 206, the analyzing network element obtains the analysis result of the analysis request for the first time, and determines whether the first condition is satisfied.
It will be appreciated that step 206 may be performed either after step 204, as shown in fig. 2, before step 204, or simultaneously with step 204. The present disclosure is not limited in this regard.
The analysis network element may obtain the analysis result for the first time based on a machine learning model. Not described in detail herein.
In the case that either of the first condition and the second condition is not satisfied, the analysis network element does not need to send the analysis result obtained for the first time to the test verification platform for verification, but performs step 208.
In step 208, the analysis network element sends a second response of the analysis request directly to the service consumer network element. The second response carries the first analysis result as an analysis result (i.e. the analysis result obtained by the analysis network element for the first time in response to the analysis request).
In case both the first condition and the second condition are fulfilled, the analyzing network element performs step 210.
In step 210, the analysis network element sends the analysis result obtained for the first time (i.e., the first analysis result) to the test verification platform for verification.
The test verification platform may include a twinning network element of one or more network elements associated with the analysis result of the analysis request. As some implementations, the test verification platform may include a digital twin environment of the core network.
In step 212, the test verification platform verifies the first analysis result.
The following description will take an example of decision analysis performed by an analysis network element. The description will be given here taking the PCF network element as the service consumer network element. The PCF network element sends an analysis request to request the analysis network element to predict traffic conditions at a future time period, and make decisions according to the predicted traffic conditions to obtain a QoS profile (i.e., analysis result) suitable for the future time period.
The analysis network element may send the obtained QoS profile to a test verification platform. The test verification platform can predict the flow condition of the period at the future time and simulate the predicted flow condition. The twin network element of the PCF network element in the test verification platform may send the QoS profile to the twin network element of the SMF network element, so that the twin network element of the SMF network element configures the twin network element of the UPF network element according to the QoS profile, thereby performing flow control during simulation according to the QoS profile obtained by the analysis network element and suitable for the future period.
In this case, the test verification platform may determine the accuracy of the QoS profile obtained by analyzing the network element and applicable for the future period according to the network congestion level during the simulation.
For example, during simulation, the network congestion level is high. This indicates that the flow control according to the QoS profile obtained by the analysis network element, which is suitable for the period at a later time, is not effective. In this case, the test verification platform may determine that the accuracy of the QoS profile obtained by the analysis network element for this period of time is low.
As another example, during simulation, the network congestion level is low. This shows that the effect of flow control based on analyzing the QoS profile obtained by the network element for this period of time is better. In this case, the test verification platform may determine that the accuracy of the QoS profile obtained by the analysis network element for this period of time is high.
In step 214, the analysis network element receives a validation result of the first analysis result from the test validation platform.
As some implementations, the validation result of the first analysis result represents an accuracy of the first analysis result.
In case the accuracy of the first analysis result represented by the verification result is lower than the preset accuracy, step 216 is performed. In case the accuracy of the first analysis result represented by the verification result is not lower than the preset accuracy, the analysis network element may take the first analysis result as the second analysis result to execute step 218.
In step 216, the analysis network element adjusts the first analysis result to obtain a second analysis result that is different from the first analysis result.
As some implementations, the analysis network element further instructs to continue training the machine learning model in the event that the accuracy of the first analysis result represented by the validation result is below a preset accuracy.
As some implementations, the analysis network element may also determine again whether the first condition is met when the second analysis result is obtained. If the first condition is satisfied, the analysis network element may take the second analysis result as the first analysis result, so as to execute steps 210 to 214 again. Otherwise, if the first condition is not satisfied, the analysis network element may execute step 218.
In step 218, the analysis network element sends a first response of the analysis request to the service consumer network element. The first response carries a second analysis result as an analysis result. The second analysis result may be a second analysis result obtained by any one of the steps described above.
As some implementations, the first response also carries a validation result of the first analysis result fed back by the test validation platform.
As some implementations, the first response also carries the first analysis result in the event that the second analysis result is different from the first analysis result.
In step 220, the service consumer network element performs a corresponding operation according to the received analysis result.
It will be appreciated that the analysis results may be either the first analysis results carried in the second response received via step 208 or the second analysis results carried in the first response received via step 218.
In some embodiments, the user of the analysis result is a service consumer network element. In this case, the service consumer network element makes decisions directly from the received analysis results.
In other embodiments, the user of the analysis result is a network element other than the service consumer network element. In this case, the service consumer network element may send the analysis result to the party using the analysis result so that the party using the analysis result makes a decision based on the analysis result.
As some implementations, the user of the analysis results makes decisions directly from the analysis results. As other implementations, the user of the analysis result adaptively adjusts the analysis result according to the real-time data, and makes a decision according to the adjusted analysis result.
In step 222, the service consumer network element sends the decision situation to the analysis network element.
As some implementations, the service consumer network element sends the decision-making case to the analysis network element only if the user of the analysis result adapts the analysis result. In other words, in the case that the user of the analysis result directly makes a decision according to the analysis result, the service consumer network element does not need to send the decision situation to the analysis network element. In this way, the communication pressure of interactions between the service consumer network element and the analysis network element can be reduced.
In step 224, the service consumer network element sends the actual situation to the analysis network element.
It will be appreciated that step 222 and step 224 may be performed sequentially or simultaneously. The present disclosure is not limited in this regard.
In step 226, the analysis network element determines the actual accuracy of the analysis result at least according to the actual situation fed back by the service consumer network element.
It will be appreciated that in step 212, the test verification platform verifies that the verification result obtained by verifying the analysis result is a predicted verification result. The actual accuracy of the predicted validation result may be different from the analysis result determined by the analysis network element in step 226.
In some embodiments, the analysis results are derived from predictive analysis based on the analysis network element. In this case, the actual accuracy of the analysis result can be determined by comparing the analysis result predicted by the analysis network element with the actual situation.
For example, the analysis result includes analyzing a predicted location of the UE predicted by the network element at a certain moment. In this case, the service consumer network element sends the actual location (i.e. the actual situation) of the UE at that moment to the analysis network element. The analysis network element may compare the predicted location with the actual location to determine the actual accuracy of the analysis result. If the predicted position and the actual position are close or the same, the actual accuracy of the analysis result is higher.
In other embodiments, the analysis results are obtained by a decision analysis based on the analysis network element. In this case, the analysis network element may determine the actual accuracy of the analysis result according to the decision and actual conditions fed back by the service consumer network element.
For example, the analysis results include analysis of a network element predicted QoS profile applicable for a future period. In this case, the service consumer network element may send the analysis network element the network congestion level (i.e. the actual situation) for this period.
Taking as an example that the user of the analysis result directly uses the QoS profile in the analysis result during this period. If the network congestion degree fed back by the service consumer network element is low, the analysis network element can determine that the actual accuracy of the analysis result is higher. Otherwise, if the network congestion degree fed back by the service consumer network element is high, the analysis network element can determine that the actual accuracy of the analysis result is low.
In some embodiments, in the event that the accuracy of the analysis result is determined to be below a threshold, the analysis network element may further instruct to continue training the machine learning model to further improve the performance of training machine learning.
By executing the communication method shown in fig. 2, the accuracy of the analysis result sent by the analysis network element can be improved, so that the user experience can be improved.
It will be appreciated that the communication method of some embodiments of the present disclosure may include only one or more of steps 202-226 shown in fig. 2.
The embodiment of the disclosure also provides an analysis network element. The analysis network element may be an NWDAF network element, for example.
In some embodiments, the analysis network element comprises a module configured to perform the operations performed by the analysis network element in the communication method of any of the embodiments described above.
In other embodiments, the analysis network element includes a memory and a processor coupled to the memory. The processor is configured to perform the operations performed by the analysis network element in the communication method of any of the embodiments described above based on instructions stored in the memory.
Fig. 3 is a schematic structural diagram of an analysis network element according to some embodiments of the present disclosure.
As shown in fig. 3, the analysis network element comprises a receiving module 301 and a sending module 302.
The receiving module 301 is configured to receive an analysis request from a service consumer network element.
The sending module 302 is configured to send the first analysis result of the analysis request to the test verification platform for verification. Here, the test verification platform comprises a twinning network element of the network element associated with the analysis result of the analysis request.
The receiving module 301 is further configured to receive a validation result of the first analysis result from the test validation platform.
The sending module 302 is further configured to send a first response of the analysis request to the service consumer network element. Here, the first response carries a second analysis result that is an analysis result of the analysis request, the second analysis result being obtained from the verification result.
It will be appreciated that the analysis network element may also include other various modules to perform the operations performed by the analysis network element in the communication method of any of the embodiments described above.
Fig. 4 is a schematic structural diagram of an analysis network element according to further embodiments of the present disclosure.
As shown in fig. 4, the analysis network element 400 includes a memory 401 and a processor 402 coupled to the memory 401, the processor 402 being configured to perform the operations performed by the analysis network element in the communication method of any of the foregoing embodiments based on the instructions stored in the memory 401.
Memory 401 may include, for example, system memory, fixed nonvolatile storage media, and the like. The system memory may store, for example, an operating system, application programs, boot Loader (Boot Loader), and other programs.
The analysis network element 400 may also include an input-output interface 403, a network interface 404, a storage interface 405, etc. These interfaces input/output interface 403, network interface 404, storage interface 405, and memory 401 and processor 402 may be connected by, for example, bus 406. The input/output interface 403 provides a connection interface for input/output devices such as a display, mouse, keyboard, touch screen, etc. Network interface 404 provides a connection interface for various networking devices. The storage interface 405 provides a connection interface for external storage devices such as SD cards, U discs, and the like.
Fig. 5 is a schematic diagram of a communication system according to some embodiments of the present disclosure.
As shown in fig. 5, the communication system comprises an analysis network element 501 and a test verification platform 502.
Analysis network element 501 may be an analysis network element (e.g., analysis network element 300/400) of any of the embodiments described above.
The test verification platform 502 may include a twinning network element of the network elements associated with the analysis results of the analysis request. The test verification platform 502 is configured to verify the first analysis result from the analysis network element 501 to obtain a verification result of the first analysis result.
The disclosed embodiments also provide a computer readable storage medium comprising computer program instructions which, when executed by a processor, implement the communication method of any of the above embodiments.
The disclosed embodiments also provide a computer program product comprising a computer program which, when executed by a processor, implements the communication method of any of the above embodiments.
Thus, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concepts of the present disclosure, some details known in the art are not described. How to implement the solutions disclosed herein will be fully apparent to those skilled in the art from the above description.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, so that the same or similar parts between the embodiments are mutually referred to. For the analysis network element and the communication system embodiments, the description is relatively simple, since it basically corresponds to the communication method embodiments, and the relevant points are referred to in the part of the description of the communication method embodiments.
It will be appreciated by those skilled in the art that embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that functions specified in one or more of the flowcharts and/or one or more of the blocks in the block diagrams may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It will be understood by those skilled in the art that the foregoing embodiments may be modified and equivalents substituted for elements thereof without departing from the scope and spirit of the disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (12)
1. A method of communication, comprising:
the analysis network element receives an analysis request from a service consumer network element;
under the condition that a preset condition is met, the analysis network element sends a first analysis result of the analysis request to a test verification platform for verification, wherein the test verification platform comprises a twin network element of the network element associated with the analysis result of the analysis request;
The analysis network element receives a verification result of the first analysis result from the test verification platform;
the analysis network element sends a first response of the analysis request to the service consumer network element, wherein the first response carries a second analysis result serving as an analysis result of the analysis request, and the second analysis result is obtained according to the verification result; and
if the preset condition is not met, the analysis network element directly sends a second response of the analysis request to the service consumer network element, wherein the second response carries the first analysis result which is the analysis result of the analysis request;
the preset conditions comprise a first condition and a second condition, wherein the first condition is that the duration between the time when the analysis result of the analysis request needs to be used and the current time is longer than the preset duration, and the second condition is that the influence of the analysis result of the analysis request on the core network is greater than the preset influence.
2. The method of claim 1, wherein the validation result represents an accuracy of the first analysis result;
the method further comprises the steps of:
and under the condition that the accuracy is lower than a preset accuracy, the analysis network element adjusts the first analysis result to obtain the second analysis result.
3. The method of claim 2, wherein the first response also carries the first analysis result if the accuracy is below the preset accuracy.
4. The method of claim 2, wherein the first analysis result is derived based on a machine learning model;
the method further comprises the steps of:
and under the condition that the accuracy is lower than a preset accuracy, the analysis network element indicates to continue training the machine learning model.
5. The method according to claim 2, wherein the analysis network element takes the first analysis result as the second analysis result in case the accuracy is not lower than the preset accuracy.
6. The method according to any of claims 1-5, wherein the analysis request carries a first parameter indicating an influence of an analysis result of the analysis request on a core network;
the method further comprises the steps of:
and the analysis network element determines whether the second condition is met according to the first parameter.
7. The method of any of claims 1-5, wherein the first response further carries the validation result.
8. The method according to any of claims 1-5, wherein the analysis network element is a network data analysis network element.
9. An analytic network element, comprising:
a module configured to perform the communication method of any of claims 1-8.
10. An analytic network element, comprising:
a memory; and
a processor coupled to the memory and configured to perform the communication method of any of claims 1-8 based on instructions stored in the memory.
11. A communication system, comprising:
the analysis network element of claim 9 or 10; and
the test verification platform comprises a twinning network element of a network element associated with an analysis result of the analysis request and is configured to verify the first analysis result from the analysis network element.
12. A computer readable storage medium comprising computer program instructions, wherein the computer program instructions, when executed by a processor, implement the communication method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310880151.XA CN116599862B (en) | 2023-07-18 | 2023-07-18 | Communication method, analysis network element and communication system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310880151.XA CN116599862B (en) | 2023-07-18 | 2023-07-18 | Communication method, analysis network element and communication system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116599862A CN116599862A (en) | 2023-08-15 |
| CN116599862B true CN116599862B (en) | 2023-09-29 |
Family
ID=87606657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310880151.XA Active CN116599862B (en) | 2023-07-18 | 2023-07-18 | Communication method, analysis network element and communication system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116599862B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021155090A1 (en) * | 2020-01-29 | 2021-08-05 | Convida Wireless, Llc | Traffic steering enhancements for cellular networks |
| CN114760619A (en) * | 2021-01-08 | 2022-07-15 | 大唐移动通信设备有限公司 | User information analysis result feedback method and device |
| CN116112946A (en) * | 2021-11-10 | 2023-05-12 | 华为技术有限公司 | Communication method and device |
| CN116232909A (en) * | 2021-12-06 | 2023-06-06 | ***通信有限公司研究院 | Policy verification and adjustment method, device and equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4044688A4 (en) * | 2019-11-15 | 2022-09-07 | Huawei Technologies Co., Ltd. | Method, system and apparatus for determining strategy |
-
2023
- 2023-07-18 CN CN202310880151.XA patent/CN116599862B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021155090A1 (en) * | 2020-01-29 | 2021-08-05 | Convida Wireless, Llc | Traffic steering enhancements for cellular networks |
| CN114760619A (en) * | 2021-01-08 | 2022-07-15 | 大唐移动通信设备有限公司 | User information analysis result feedback method and device |
| CN116112946A (en) * | 2021-11-10 | 2023-05-12 | 华为技术有限公司 | Communication method and device |
| CN116232909A (en) * | 2021-12-06 | 2023-06-06 | ***通信有限公司研究院 | Policy verification and adjustment method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116599862A (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112181666B (en) | Equipment assessment and federal learning importance aggregation method based on edge intelligence | |
| CN111371603B (en) | Service instance deployment method and device applied to edge computing | |
| US11102641B2 (en) | SIM card status determination method and SIM card status determination device | |
| US20210042578A1 (en) | Feature engineering orchestration method and apparatus | |
| CN112929187B (en) | Network slice management method, device and system | |
| EP4167149A1 (en) | Method and apparatus for building predictive model, computing device, and storage medium | |
| CN112073991B (en) | Service processing method and device of access network | |
| CN110875838B (en) | Resource deployment method, device and storage medium | |
| CN107943697A (en) | Problem distribution method, device, system, server and computer-readable storage medium | |
| EP4376386A1 (en) | Electronic device and operation method for deploying application | |
| CN111885618A (en) | Network performance optimization method and device | |
| EP4329358A1 (en) | Network slice self-optimization method, base station, and storage medium | |
| WO2021052556A1 (en) | A device for applying artificial intelligence in a communication network | |
| CN116599862B (en) | Communication method, analysis network element and communication system | |
| CN116367223B (en) | XR service optimization method and device based on reinforcement learning, electronic equipment and storage medium | |
| CN117221295A (en) | Low-delay video transmission system based on edge calculation and network slicing | |
| CN115843050A (en) | Network slice configuration method and system, computer storage medium | |
| CN112867064B (en) | Load balancing method, device, storage medium and source base station | |
| CN115460617A (en) | Network load prediction method and device based on federal learning, electronic equipment and medium | |
| CN114423049A (en) | Perception prediction method and device, electronic equipment and storage medium | |
| CN113056024A (en) | Financial big data information storage method and system based on cloud storage | |
| CN110688623A (en) | Training optimization method, device, equipment and storage medium of high-order LR model | |
| CN112822706B (en) | Information processing method and device and computer readable storage medium | |
| WO2024038554A1 (en) | Control system, control device, control method, and non-temporary computer-readable medium | |
| CN112953844B (en) | Network traffic optimization method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |