WO2021232849A1 - 一种通信方法、装置及系统 - Google Patents

一种通信方法、装置及系统 Download PDF

Info

Publication number
WO2021232849A1
WO2021232849A1 PCT/CN2021/074345 CN2021074345W WO2021232849A1 WO 2021232849 A1 WO2021232849 A1 WO 2021232849A1 CN 2021074345 W CN2021074345 W CN 2021074345W WO 2021232849 A1 WO2021232849 A1 WO 2021232849A1
Authority
WO
WIPO (PCT)
Prior art keywords
network element
target object
data
analysis result
analysis
Prior art date
Application number
PCT/CN2021/074345
Other languages
English (en)
French (fr)
Inventor
崇卫微
辛阳
Original Assignee
华为技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21807898.8A priority Critical patent/EP4145889A4/en
Priority to BR112022023665A priority patent/BR112022023665A2/pt
Publication of WO2021232849A1 publication Critical patent/WO2021232849A1/zh
Priority to US17/990,934 priority patent/US11991049B2/en

Links

Images

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
    • H04L41/14—Network analysis or design
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/04—Arrangements for maintaining operational condition
    • 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
    • H04L41/142—Network analysis or design using statistical or mathematical methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
    • H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
    • 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
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H04L43/0888—Throughput
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/20—Arrangements for monitoring or testing data switching networks the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV

Definitions

  • This application relates to the field of communication technology, and in particular to a communication method, device and system.
  • some network elements may have network data analysis functions, such as the network data analysis function (NWDAF) network elements in the 3rd generation partnership project (3GPP) network.
  • NWDAF network data analysis function
  • 3GPP 3rd generation partnership project
  • the embodiments of the present application provide a communication method, device, and system to improve the accuracy of the analysis result generated by the data analysis network element.
  • an embodiment of the present application provides a communication method.
  • a second data analysis network element receives a state analysis result of a target object from the first data analysis network element.
  • the target object includes network equipment, network domain, and network One or more of the entire domain and terminal equipment; the second data analysis network element obtains the first input data corresponding to the target analysis type according to the status analysis result of the target object, wherein, when the status of the target object When the analysis result indicates that the state of the target object is abnormal, the first input data does not include the data corresponding to the target object; the second data analysis network element generates the data corresponding to the target analysis type according to the first input data The first analysis result.
  • the state analysis result of the target object received by the second data analysis network element can characterize whether the target object is in an abnormal state, and if the target object is in an abnormal state, the data corresponding to the target object may be incorrect.
  • the first input data corresponding to the target analysis type acquired by the second data analysis network element may not include the data corresponding to the target object, which enables the second data analysis network element to generate data based on the first input data
  • the first analysis result corresponding to the target analysis type may not be affected by the data corresponding to the wrong target object, so that the correctness of the first analysis result can be improved.
  • the first data analysis network element can separately detect whether the state of each object is abnormal.
  • the second data analysis network element sends the first analysis result and/or first indication information to the first network element, and the first indication information is used to indicate the first
  • the network element disables the second analysis result or lowers the confidence level corresponding to the second analysis result to the first confidence level, and the second analysis result is generated by the second data analysis network element according to the second input data.
  • the analysis result of the target analysis type sent to the first network element, and the second input data includes data corresponding to the target object.
  • the second data analysis network element may send the generated first analysis result to the first network element, so that the first network element can use the first analysis result with higher accuracy (as opposed to the first analysis result based on the target object).
  • the second analysis result generated by the corresponding data executes corresponding processing operations, for example, the previous operations performed based on the second analysis result can be modified.
  • the second data analysis network element may also send the first network element to the first network element. Indication information to indicate that the confidence level of the second analysis result previously received by the first network element is lowered, that is, the credibility of the second analysis result is reduced. In this way, the first network element can be lowered according to the confidence level. Perform corresponding processing on the second analysis result. For example, when the confidence of the second analysis result is reduced from 90% to 30%, the second analysis result can be disabled.
  • the second analysis result is generated based on the data corresponding to a larger number of objects, and the number of target objects in an abnormal state is small, the confidence level of the second analysis result is lowered, for example, from 90% To 89%, etc., at this time, the first network element continues to use the second analysis result to perform corresponding processing.
  • the sending of the first analysis result by the second data analysis network element to the first network element includes: when the second data analysis network element determines that the first analysis result and the first network element When the two analysis results are different, the second data analysis network element sends the first analysis result to the first network element.
  • the first analysis result is different from the second analysis result, it means that the data corresponding to the target object may have a greater impact on the generated analysis result.
  • the analysis result specifically represents the level of service quality of the terminal device
  • the second analysis result previously received by the first network element may indicate that the service quality of the terminal device is high, while the first analysis result indicates that the service quality of the terminal device is low.
  • the first network element may be based on The received first analysis result improves the network resources allocated to the terminal device, so as to improve the service quality of the terminal device.
  • the second data analysis network element may also determine that the input data that originally generated the analysis result includes data corresponding to the target object, and when the target object is in an abnormal state, it may be determined to generate The first analysis result is sent to the first network element.
  • the method further includes: the second data analysis network element acquiring first time information and/or first area information corresponding to the status analysis result of the target object; the first input data Excluding the data corresponding to the target object includes: the first input data does not include the data corresponding to the first time information and/or the first area information of the target object.
  • the first data analysis network element when it obtains the input data required to generate the state analysis result of the target object, it may obtain the input data corresponding to the first time information and/or the first area information, and based on the input data The input data generates a state analysis result of the target object corresponding to the first time information and/or the first area information.
  • the first time information may include any one or more of start time, end time, and duration, and the first area information may be expressed as a network area and/or a geographic area.
  • the method further includes: the second data analysis network element sending second time information and/or second area information corresponding to the first indication information to the first network element .
  • the first indication information sent by the second data analysis network element may correspond to a specific time period or a specific area, so that the confidence of the first analysis result in the time period or within the area can be reduced. , And the confidence in other time periods or other regions does not need to be lowered.
  • the second time information may be determined by the second data analysis network element according to the first time information.
  • the time period indicated by the second time information may be a subset of the time period indicated by the first time information, etc.
  • the time period indicated by the second time information may be a time period during which the second data analysis network element makes a prediction.
  • the second area information may be determined by the second data analysis network element according to the first area information.
  • the area indicated by the second area information may be a subset of the area indicated by the first area information.
  • the method further includes: the second data analysis network element sending third time information and/or third area to which the first analysis result is applicable to the first network element information.
  • the third time information sent by the second data analysis network element to the first network element may be used to indicate the time period in which the first network element is suitable for performing corresponding processing using the first analysis result, that is, the The time period to which the first analysis result is applicable;
  • the third area information sent by the second data analysis network element to the first network element can be used to indicate the area in which the first network element is suitable for performing corresponding processing using the first analysis result, that is The area used by the first analysis result.
  • the third time information may be determined by the second data analysis network element according to the first time information.
  • the time period indicated by the third time information may be a subset of the time period indicated by the first time information, etc.
  • the third area information may be determined by the second data analysis network element according to the first area information.
  • the area indicated by the third area information may be a subset of the area indicated by the first area information.
  • the method further includes: the second data analysis network element sends a first abnormal cause to the first network element, and the first abnormal cause is used to instruct to send the first The analysis result and/or the reason for the first indication information.
  • the first network element may determine the reason for the second data analysis network element to send the first analysis result and/or the first indication information to the first network element based on the first abnormal cause, for example, The first network element can determine based on the first abnormal reason that the confidence level corresponding to the second analysis result is lowered because the second input data that previously generated the second analysis result includes data of the target object in an abnormal state, etc., or it can determine that the first 2.
  • the second analysis result previously sent by the data analysis network element is inaccurate, etc.
  • the second data analysis network element obtaining the first input data corresponding to the target analysis type according to the status analysis result of the target object includes: the second data analysis network element obtains the first input data from the The data corresponding to the target object is deleted from the third input data corresponding to the target analysis type to obtain the first input data; or, the second data analysis network element cancels the subscription to the second network element Data corresponding to the target object, and receiving the first input data from the third network element.
  • the way for the second data analysis network element to acquire the first input data that does not include the data corresponding to the target object may be to exclude the target object in an abnormal state from the third data corresponding to all the acquired objects.
  • the remaining data after the elimination can be used as the input data for generating the first analysis result; or, the second data analysis network element can also unsubscribe the target object from the corresponding network element in the network In this way, the corresponding network element in the network can no longer provide the data corresponding to the target object to the second data analysis network element, so that the second data analysis network element obtains the first analysis result from the network
  • the required input data does not include the data corresponding to the target object.
  • the second data analysis network element acquiring the first input data corresponding to the target analysis type according to the status analysis result of the target object includes: the second data analysis network element refuses to receive data from Data corresponding to the target object of the first network element.
  • the first network element can still send data corresponding to the target object to the second data analysis network element.
  • the second data analysis network element can refuse to receive the data, thereby The input data obtained by the second data analysis network element as the first analysis result may not include the data corresponding to the target object.
  • the state analysis result of the target object includes a state prediction analysis result of the target object.
  • the state analysis result of the target object may also be obtained by predicting the state of the target object. For example, based on the temperature data generated by the target object over a period of time in history, through corresponding analysis, it can be predicted that since the device temperature of the target object is always increasing without slowing down, the target object will be in the future for a period of time. During the time period, malfunctions may occur due to excessive temperature rise.
  • the status analysis result of the target object may also be a result obtained by including statistics on the status of the target object. For example, based on the temperature data generated by the target object in a historical period of time, it can be determined that its temperature during that period of time exceeds the upper temperature limit under normal conditions, and then it can be determined that the target object is in an abnormal state due to excessive temperature.
  • the state analysis result of the target object includes an analysis result of the historical state of the target object, and/or an analysis result of the future state of the target object.
  • the state analysis result of the target object may be the result obtained by analyzing whether the target object is abnormal in the historical state, or may be the result obtained by predicting whether the target object is abnormal in the future state.
  • the method further includes: the second data analysis network element receives a second confidence level corresponding to the state analysis result of the target object from the first data analysis network element;
  • the second data analysis network element acquiring the first input data corresponding to the target analysis type according to the status analysis result of the target object includes: when the second data analysis network element determines that the second confidence level is greater than a first threshold, And when it is determined that the state of the target object is abnormal according to the state analysis result of the target object, the second data analysis network element obtains the first input data corresponding to the target analysis type according to the state analysis result of the target object.
  • the result of analyzing the state of the target object may also have a corresponding degree of confidence (that is, the aforementioned second degree of confidence).
  • the second data analysis network element may determine whether to adjust the input data that generates the first analysis result according to the second confidence level corresponding to the status analysis result of the target object. For example, when the state analysis result of the target object indicates that the target object is in an abnormal state, but the confidence level of the state analysis result of the target object is 30%, it indicates that the probability of the target object being in an abnormal state is only 30%, and the target object is in an abnormal state. The probability that the object is in a normal state is 70%, that is, the target object is more likely to be in a normal state.
  • the second data analysis network element can also generate the first analysis without adjusting the input data that generates the first analysis result.
  • the input data of the result may contain data corresponding to the target object.
  • the method further includes: the second data analysis network element sends a third confidence level corresponding to the first analysis result to the first network element, and the third confidence level Is determined by the second data analysis network element based on the first input data and the second confidence.
  • the first analysis result fed back by the second data analysis network element to the first network element may also have a corresponding degree of confidence. In this way, when the first analysis result has a greater degree of confidence, it indicates that the first analysis result If the credibility of the result is high, the first network element performs corresponding processing operations based on the first analysis result; and when the confidence of the first analysis result is low, it indicates that the credibility of the first analysis result is low. Then the first network element can deactivate the first analysis result.
  • the second data analysis network element receiving the state analysis result of the target object from the first data analysis network element includes: the second data analysis network element obtains the state analysis result from the fourth network element
  • the status analysis result of the target object, the status analysis result of the target object is sent by the first data analysis network element to the fourth network element.
  • the first data analysis network element after the first data analysis network element generates the status analysis result of the target object, it can be sent to the fourth network element (such as UDM, UDR network element, etc.) for storage, and when the second data analysis
  • the network element needs to obtain the status analysis result of the target object it can directly obtain it from the fourth network element, so that the fourth network element can provide a unified interface for each data analysis network element in the network to obtain what it needs.
  • the status analysis result of the object after the first data analysis network element generates the status analysis result of the target object, it can be sent to the fourth network element (such as UDM, UDR network element, etc.) for storage, and when the second data analysis When the network element needs to obtain
  • the method further includes: the second data analysis network element sending second indication information to the first data analysis network element, where the second indication information is used to indicate the first data analysis network element A data analysis network element feeds back the status analysis result of the target object when the status of the target object is abnormal.
  • the first data analysis network element may, based on the second indication information, feed back the status analysis result of the target object to the second data analysis network element when it is determined that the target object is in an abnormal state, and when it is determined that the target object is in an abnormal state, In the normal state, the feedback of the state analysis result is not performed.
  • the second data analysis network element can determine that the target object is in an abnormal state after receiving the state analysis result of the target object, but determines when the state analysis result of the target object is not received
  • the target object is in a normal state, which can reduce the number of data communications and the amount of data between the first data analysis network element and the second data analysis network element, and save network resources.
  • the method further includes: the second data analysis network element sends a query request to the fifth network element, and the query request is used to query all sources that generate the status analysis result of the target object.
  • the first data analysis network element; the second data analysis network element receives the identification information of the first data analysis network element sent by the fifth network element in response to the query request; the second data analysis The network element sends a first request message to the first data analysis network element according to the identification information of the first data analysis network element, where the first request message is used to request the first data analysis network element for the The status analysis result of the target object.
  • the second data analysis network element can also query which data analysis network it is. Meta provides services that generate the status analysis results of the target object.
  • the query request may include one or more of slice identification, service area identification, anomaly type identification, anomaly subtype identification and other information.
  • the state analysis result of the target object includes state indication information, and the state indication information is used to indicate that the target object is in any one of the following states: normal state, abnormal state, and unknown state .
  • the state indication information indicates an unknown state, it indicates that it is unknown whether the state of the target state is abnormal.
  • the status analysis result of the target object includes any one or more of the following information: abnormality type, abnormality subtype, second abnormality reason, abnormality degree, and abnormality trend.
  • the status analysis result of the target object can not only indicate whether the status of the target object is abnormal, but also can include other more information.
  • the first network element can use the abnormality The trend determines the time period to which the first analysis result is applicable, etc.
  • the network sub-domains include one or more of an access network domain, a core network domain, and a transmission network domain.
  • the target object includes a target object of a target network slice.
  • the target object may specifically be an object within a certain network slice.
  • the second data analysis network element requests the first data analysis network element for the state analysis result corresponding to the target object, it may request the first data analysis
  • the network element sends relevant information of the target network slice, such as an identifier, so that the first data analysis network element determines the target network slice based on the relevant information of the target network slice, so that the object in the target network slice can be regarded as the target object, and further Feed back the state analysis result corresponding to the target object to the second data analysis network element.
  • the network slice includes a slice instance and a slice sub-instance.
  • an embodiment of the present application also provides a communication method, the method includes: a first data analysis network element obtains a status analysis result of a target object, and the target object includes a network device, a network domain, and a network entire domain. One or more of the terminal devices; the first data analysis network element sends the status analysis result of the target object to the second data analysis network element.
  • the first data analysis network element can obtain the status analysis result of the target object, and send it to the second data analysis network element, so that the second data analysis network element can determine according to the status analysis result of the target object Whether to adjust the input data that generates the analysis result corresponding to the target analysis type, so that the analysis result generated by the second data analysis network element based on the input data that does not include the data corresponding to the target object can be free from the data corresponding to the wrong target object In turn, the accuracy of the first analysis result can be improved.
  • the method further includes: the first data analysis network element sends to the second data analysis network element first time information corresponding to the status analysis result of the target object and/or The first area information.
  • the first time information may include any one or more of start time, end time, and duration, and the first area information may be expressed as a network area and/or a geographic area.
  • the state analysis result of the target object includes an analysis result of the historical state of the target object, or an analysis result of the future state of the target object.
  • the state analysis result of the target object may be the result obtained by analyzing whether the target object is abnormal in the historical state, or may be the result obtained by predicting whether the target object is abnormal in the future state.
  • the method further includes: the first data analysis network element sending a second confidence level corresponding to the state analysis result of the target object to the second data analysis network element.
  • the result of analyzing the state of the target object may also have a corresponding degree of confidence (that is, the aforementioned second degree of confidence).
  • the second data analysis network element may determine whether to generate the first analysis result according to the second confidence level corresponding to the state analysis result of the target object The input data is adjusted.
  • the method further includes: the first data analysis network element receives second indication information from the second data analysis network element;
  • the data analysis network element sending the status analysis result of the target object includes: the first data analysis network element sends to the data analysis network element when it is determined that the status of the target object is abnormal based on the second indication information The status analysis result of the target object.
  • the first data analysis network element sends the status analysis result of the target object to the second data analysis network element only when it is determined that the target object is in an abnormal state based on the second indication information, and when it is determined that the target object is in a normal state In the state, the state analysis result of the target object is not fed back to the second data analysis network element. In this way, the number of data communications and the amount of data between the first data analysis network element and the second data analysis network element can be reduced, thereby saving Internet resources.
  • obtaining the state analysis result of the target object by the first data analysis network element includes: the first data analysis network element receives a first request message from the second data analysis network element, and The first request message is used to request the state analysis result of the target object from the first data analysis network element; the first data analysis network element generates the state analysis of the target object in response to the first request message result.
  • the state analysis result of the target object includes state indication information, and the state indication information is used to indicate that the target object is in any one of the following states: normal state, abnormal state, and unknown state .
  • the status analysis result of the target object includes any one or more of the following information: abnormality type, abnormality subtype, second abnormality reason, abnormality degree, and abnormality trend.
  • the status analysis result of the target object can not only indicate whether the status of the target object is abnormal, but also can include other more information.
  • the first network element can use the abnormality The trend determines the time period to which the first analysis result is applicable, etc.
  • the target object includes a target object of a target network slice.
  • the target object may specifically be an object within a certain network slice.
  • the second data analysis network element requests the first data analysis network element for the state analysis result corresponding to the target object, it may request the first data analysis
  • the network element sends relevant information of the target network slice, such as an identifier, so that the first data analysis network element determines the target network slice based on the relevant information of the target network slice, so that the object in the target network slice can be regarded as the target object, and further Feed back the state analysis result corresponding to the target object to the second data analysis network element.
  • the network slice includes a slice instance and a slice sub-instance.
  • the network sub-domains include one or more of an access network domain, a core network domain, and a transmission network domain.
  • an embodiment of the present application also provides a communication device, including: a receiving unit, configured to receive a state analysis result of a target object from a first data analysis network element, where the target object includes a network device and a network domain. , One or more of the entire network domain and terminal equipment;
  • the processing unit is configured to obtain first input data corresponding to the target analysis type according to the status analysis result of the target object, wherein, when the status analysis result of the target object indicates that the target object is in an abnormal state, the first input The data does not include the data corresponding to the target object; the first analysis result corresponding to the target analysis type is generated according to the first input data.
  • the device further includes: a sending unit, configured to send the first analysis result and/or first indication information to the first network element, where the first indication information is used to indicate all
  • the first network element disables the second analysis result or reduces the confidence level corresponding to the second analysis result to the first confidence level, and the second analysis result is determined by the second data analysis network element according to the second input
  • the analysis result of the target analysis type generated by data and sent to the first network element, and the second input data includes data corresponding to the target object.
  • the sending unit is specifically configured to: when the second data analysis network element determines that the first analysis result is different from the second analysis result, the second data analysis network element The first network element sends the first analysis result.
  • the receiving unit is further configured to receive first time information and/or first area information corresponding to the status analysis result of the target object;
  • the first input data does not include data corresponding to the target object, including: the first input data does not include data corresponding to the first time information and/or the first area information of the target object.
  • the sending unit is further configured to send second time information and/or second area information corresponding to the first indication information to the first network element.
  • the sending unit is further configured to send third time information and/or third area information to which the first analysis result is applicable to the first network element.
  • the sending unit is further configured to send a first abnormal cause to the first network element, where the first abnormal cause is used to instruct to send the first analysis result and/or the State the reason for the first indication message.
  • the processing unit is specifically configured to delete the data corresponding to the target object from the acquired third input data corresponding to the target analysis type to obtain the first input data; Or, cancel the subscription of the data corresponding to the target object from the second network element, and receive the first input data from the third network element.
  • the state analysis result of the target object includes a state prediction analysis result of the target object.
  • the receiving unit is further configured to receive a second confidence level corresponding to the state analysis result of the target object from the first data analysis network element;
  • the processing unit is specifically configured to: when the second data analysis network element determines that the second confidence level is greater than a first threshold, and it is determined that the target object is in an abnormal state according to the result of the state analysis of the target object, the The second data analysis network element obtains the first input data corresponding to the target analysis type according to the status analysis result of the target object.
  • the sending unit is further configured to send a third confidence level corresponding to the first analysis result to the first network element, where the third confidence level is determined by the second The data analysis network element is determined based on the first input data and the second confidence.
  • the receiving unit is specifically configured to obtain a state analysis result of the target object from a fourth network element, and the state analysis result of the target object is determined by the first data analysis network. Sent to the fourth network element.
  • the state analysis result of the target object includes state indication information, and the state indication information is used to indicate that the target object is in any one of the following states: normal state, abnormal state, and unknown state .
  • the status analysis result of the target object includes any one or more of the following information: abnormality type, abnormality subtype, second abnormality reason, abnormality degree, and abnormality trend.
  • the communication device described in the third aspect corresponds to the communication method described in the first aspect. Therefore, the various possible implementations and beneficial effects of the third aspect may refer to the corresponding implementations and beneficial effects in the first aspect. Description, I won’t repeat it here.
  • an embodiment of the present application also provides a communication device.
  • the device includes a processing unit configured to obtain a status analysis result of a target object.
  • the target object includes a network device, a network domain, a network entire domain, One or more of terminal devices; a sending unit, used to send the status analysis result of the target object.
  • the sending unit is further configured to send first time information and/or first area information corresponding to the status analysis result of the target object to the second data analysis network element.
  • the state analysis result of the target object includes an analysis result of the historical state of the target object, or an analysis result of the future state of the target object.
  • the sending unit is further configured to send a second confidence level corresponding to the state analysis result of the target object to the second data analysis network element.
  • the device further includes: a receiving unit, configured to receive second indication information from the second data analysis network element; and the sending unit, specifically configured to be based on the second indication Information, when it is determined that the status of the target object is abnormal, the status analysis result of the target object is sent to the data analysis network element.
  • the processing unit is specifically configured to generate the state analysis result of the target object in response to the first request message from the second data analysis network element received by the receiving unit, and The first request message is used to request the state analysis result of the target object from the first data analysis network element.
  • the state analysis result of the target object includes state indication information, and the state indication information is used to indicate that the target object is in any one of the following states: normal state, abnormal state, and unknown state .
  • the status analysis result of the target object includes any one or more of the following information: abnormality type, abnormality subtype, second abnormality reason, abnormality degree, and abnormality trend.
  • the target object includes a target object of a target network slice.
  • the network slice includes a slice instance and a slice sub-instance.
  • the network sub-domains include one or more of an access network domain, a core network domain, and a transmission network domain.
  • the communication device described in the fourth aspect corresponds to the communication method described in the second aspect. Therefore, various possible implementations and beneficial effects of the fourth aspect may refer to the corresponding implementations and beneficial effects in the second aspect. Description, I won’t repeat it here.
  • an embodiment of the present application also provides a communication device, including: a processor and a memory; the memory is used to store instructions or computer programs; the processor is used to execute the instructions or computer programs, The method described in any one of the implementation manners of the first aspect to the method described in any one of the implementation manners of the second aspect is executed.
  • the communication device described in the fifth aspect corresponds to the communication method described in the first aspect to the second aspect. Therefore, various possible implementations of the fifth aspect and its beneficial effects can be referred to in the first aspect to the second aspect Corresponding implementation manners and related descriptions of beneficial effects will not be repeated here.
  • the embodiments of the present application also provide a computer-readable storage medium, including instructions or computer programs, which when run on a computer, cause the computer to execute the method described in any one of the above-mentioned implementations of the first aspect To the method described in any one of the embodiments of the second aspect.
  • the computer-readable storage medium described in the sixth aspect corresponds to the communication method described in the first or second aspect. Therefore, various possible implementations of the sixth aspect and its beneficial effects can be referred to from the first to the second aspects. Corresponding implementations and related descriptions of beneficial effects in the two aspects are not repeated here.
  • an embodiment of the present application also provides a communication system, which may include the second data analysis network element described in any implementation manner in the first aspect and the second data analysis network element described in any implementation manner in the second aspect.
  • the first data analysis network element may include the second data analysis network element described in any implementation manner in the first aspect and the second data analysis network element described in any implementation manner in the second aspect.
  • the communication system described in the seventh aspect corresponds to the communication method described in the first or second aspect. Therefore, various possible implementations of the seventh aspect and its beneficial effects can be referred to in the first or second aspect Corresponding implementation manners and related descriptions of beneficial effects will not be repeated here.
  • an embodiment of the present application provides a chip that includes a processor and a communication interface, and the communication interface is coupled to the processor.
  • the processor is used to run computer programs or instructions to implement various aspects of the first to second aspects. A communication method described in Possible Implementations.
  • the communication interface is used to communicate with other modules outside the chip.
  • FIG. 1 is a schematic diagram of the architecture of an exemplary communication system in an embodiment of the application
  • FIG. 2 is a schematic flowchart of a communication method in an embodiment of this application.
  • FIG. 3 is a schematic diagram of signaling interaction of a communication method combined with specific scenarios in an embodiment of the application;
  • FIG. 4 is a schematic diagram of signaling interaction of yet another communication method combined with specific scenarios in an embodiment of the application;
  • FIG. 5 is a schematic structural diagram of a communication device in an embodiment of this application.
  • FIG. 6 is a schematic structural diagram of another communication device in an embodiment of this application.
  • FIG. 7 is a schematic diagram of the hardware structure of a communication device in an embodiment of the application.
  • FIG. 8 is a schematic diagram of the hardware structure of a chip in an embodiment of the application.
  • the embodiments of the present application can be applied to the exemplary communication system shown in FIG. 1.
  • the communication system may be a communication system that supports fourth-generation (4G) access technology, such as long-term evolution (LTE) access technology; or, the communication system may also support fifth-generation (fifth generation) access technology.
  • 4G fourth-generation
  • LTE long-term evolution
  • fifth generation fifth-generation
  • generation, 5G) access technology communication system such as new radio (NR) access technology
  • NR new radio
  • the communication system can also be a communication system supporting multiple wireless technologies, such as a communication system supporting LTE technology and NR technology .
  • the communication system can also be applied to future-oriented communication technologies.
  • the terminal accesses the core network through an access network (AN) network element or a radio access network (radio access network, RAN).
  • the terminal includes but is not limited to: user equipment (UE), user unit, user station, mobile station, mobile station, remote station, remote terminal equipment, mobile terminal equipment, user terminal equipment, terminal equipment, wireless communication equipment ,
  • UE user equipment
  • user unit user station
  • mobile station mobile station
  • remote station remote terminal equipment
  • mobile terminal equipment user terminal equipment
  • user terminal equipment user terminal equipment
  • wireless communication equipment User agent
  • user device cellular phone, cordless phone, session initiation protocol (SIP) phone, wireless local loop (WLL) station, personal digital assistant (PDA), with Handheld devices with wireless communication functions, computing devices, processing devices connected to wireless modems, in-vehicle devices, wearable devices, terminal devices in the Internet of Things, household appliances, virtual reality devices, terminal devices in the future 5G network, or the future Terminal equipment in the evolved public land mobile network (PLMN).
  • PLMN evolved public land mobile network
  • AN may be a network element that communicates with the terminal.
  • AN (or RAN) can provide communication coverage for a specific geographic area, and can communicate with user equipment located in the coverage area (cell).
  • AN (or RAN) can communicate with any number of UEs.
  • AN (or RAN) can support communication protocols of different standards, or can support different communication modes.
  • AN is an evolved base station (evolved node B, eNodeB), or a wireless fidelity access point (WiFi AP), or a global interoperability base station for microwave access (worldwide).
  • interoperability for microwave access base station, WiMAX BS), or the wireless controller in the cloud radio access network (CRAN), or the access network element can be the access network in the future 5G network Or the access network element in the future evolution of PLMN, etc.
  • the core network may include: user plane function (UPF) network elements, network slice selection function (network slice selection function, NSSF), network capability exposure function (NEF), network storage function (network repository function) , NRF), policy control function (PCF) network element, unified data management (UDM) network element, network data analysis function (NWDAF) network element, authentication service function (authentication server function, AUSF) network element, access management function (AMF) network element, session management function (SMF) network element, and service control point (SCP).
  • UPF user plane function
  • NSSF network slice selection function
  • NEF network capability exposure function
  • NRF network storage function
  • PCF policy control function
  • UDM unified data management
  • NWDAF network data analysis function
  • AMF authentication service function
  • SMF session management function
  • SCP service control point
  • the AMF network element can be used to provide the UE with functions such as mobility management, or access authorization and authentication.
  • Application function (AF) network elements can be divided into operator AF network elements and third-party AF network elements, and the difference lies in whether they are deployed by the operator.
  • Third-party AF network elements include various application-related servers deployed by non-operators, such as railway system-related AF, medical system-related AF, OTT (over the top) business-related AF, and government community-related AF (such as community service apps, etc.).
  • NEF network elements can be used to open data and services of the communication operator's network to external AF, or reversely open AF data or services to the operator.
  • NWDAF network elements can have one or more of the following functions: data collection, training, analysis, and reasoning functions.
  • NWDAF network elements are used to collect relevant data from network network elements, third-party service servers, terminal equipment or network management systems, and perform analysis and training based on the relevant data, so as to provide network elements, third-party service servers, terminal equipment or The network management system provides corresponding data analysis results, which can assist the network in selecting service quality parameters for services, or assist the network in performing traffic routing, or assist the network in selecting background traffic transmission strategies.
  • the NWDAF network element can be set separately as an independent network element in the network, or the NWDAF network element can be combined with other network elements.
  • the NWDAF network element function can be set on the SMF network element and the AMF network element.
  • the network may include one or more NWDAF network elements, and different NWDAF network elements may have different data type analysis functions, and of course, they may also have the same data type analysis function.
  • NFs network functions
  • network functions refer to other nodes or physical devices in the network that can have one or more of the following functions: provide corresponding functional support for UE access to the network, session, authentication, policy control, etc., Corresponding network data will also be generated.
  • AMF Access Management Function
  • SMF Session Management Function
  • UDM User Data Management Function
  • the terminal can communicate with the network element and different network elements through the corresponding service interface or point-to-point interface.
  • the UE can communicate with the AMF network element through the N1 interface
  • the AN can communicate with the UPF network element through the N3 interface, etc.
  • Point-to-point interfaces such as N2, N4, N6, and N9 are similar
  • AMF network elements can communicate with other network elements in the network through the business interface Namf interface
  • AF network elements can communicate with other network elements in the network through the business interface Naf interface
  • Other network elements communicate, etc., and the rest will not be repeated here.
  • the functions of the constituent network elements are only exemplary, and not all the functions are necessary when the constituent network elements are applied to the embodiments of the present application. It should be noted that the communication system shown in FIG. 1 is only an example of a communication system provided by the embodiment of the present application, and the embodiment of the present application can be applied to any applicable communication system, and is not limited to the one shown in FIG. 1 above. Communication Systems.
  • the communication system shown in Fig. 1 may include at least two NWDAF network elements, such as NWDAF1 and NWDAF2 network elements in Fig. 1. Of course, the communication system may also include more than three (including three) NWDAF network elements. Wait.
  • NWDAF1 network element can be sent to NWDAF2, and NWDAF2 can adjust its own input data according to the analysis results sent by NWDAF1, and generate corresponding analysis results based on the adjusted input data to improve the analysis generated by NWDAF2 The accuracy of the results.
  • the NWDAF1 network element can also send the generated analysis results to the third NWDAF network element and the fourth NWDAF network element at the same time for other
  • the NWDAF network element adjusts its input data accordingly based on the received analysis result.
  • FIG. 2 shows a schematic flowchart of a communication method in an embodiment of the present application.
  • the method may be applied to the communication system shown in FIG. 1, or may be applied to other applicable communication systems.
  • the first data analysis network element in this embodiment may be the NWDAF1 network element in the communication system shown in FIG. 1, and the second data analysis network element may be the communication system.
  • the data analysis network element can also be other network elements with data analysis capabilities in the network, such as the management data analysis function (MDAF) network element;
  • the first network element can be a communication system
  • NWDAF management data analysis function
  • other network elements such as AF network elements, AMF network elements, UDM network elements, RAN network elements, UE, etc.
  • the first network element and the data analysis network element can be co-located or independent in the network deploy.
  • the method may specifically include:
  • the first data analysis network element obtains the status analysis result of the target object, where the target object may include one or more of terminal equipment, network equipment, network sub-domain, and network entire domain, and the number of target objects It can be one or multiple.
  • the first data analysis network element sends the status analysis result of the target object to the second data analysis network element.
  • the first data analysis network element may detect the state of the target object in the communication system and generate a corresponding state analysis result.
  • the state analysis result of the target object may indicate whether the state of the target object is abnormal.
  • the target object may specifically be any one of the terminal device, the network device, the network sub-domain, and the entire network domain in the communication system, or it may be a variety of them.
  • the first data analysis network element can separately detect whether the state of each object is abnormal.
  • the network domain may include one or more of an access network domain, a core network domain, and a transmission network domain.
  • another network element in the communication system may request the first data analysis network element to detect the state of the target object.
  • the second data analysis network element in the communication system may send a first request message to the first data analysis network element to request the first data analysis network element to feed back the status analysis result of the target object, where the first request message may carry There is an identification of the target object.
  • the network element that requests the first data analysis network element to detect the target object can be other network elements such as AMF network elements, UDM network elements, etc., in addition to the second data analysis network element. It is not limited.
  • the first request message received by the first data analysis network element may include the first time information and/or the first area information, and the first data analysis network element is acquiring the status analysis result of the generated target object
  • the input data corresponding to the first time information and/or the first area information can be obtained, and the state of the target object corresponding to the first time information and/or the first area information can be generated based on the input data Analyze the results. For example, if the first time information indicates the time period from 8:00 to 12:00 on April 28, 2020, the first data analysis network element may only obtain relevant data of the target object in this time period from other network elements , And based on the data in this period of time to generate the state analysis results of the corresponding target object.
  • the first time information can include any one or more of the start time, the end time, and the duration.
  • the first area information (the following The second area information, the third area information, etc. can be expressed as a network area (such as a network area served by a certain or some network elements, such as a cell, a tracking area TA, etc.) and/or a geographic area (such as an administrative area) Or use the physical area represented by the coordinate value, etc.).
  • the first request message received by the first data analysis network element may also include the identification information of the network slice, the service type, the data network name (DNN), the abnormal type, and the abnormal subtype. Any one or more.
  • the characterization requests the first data analysis network element for the target object corresponding to the service type for status analysis
  • the characterization The first data analysis network element requests the status analysis of the target object in the network slice corresponding to the identifier of the network slice.
  • the network slice may include slice instances, slice sub-instances, etc.; when the first request message includes DNN information , The characterization requests the first data analysis network element to analyze the status of the target object in the specific DNN in the network; when the first request message includes the abnormality type and/or abnormal subtype, the characterization requests the first data analysis network element to feedback The target object is in the abnormal state indicated by the abnormal type and/or abnormal subtype.
  • the abnormal type can be, for example, network attack, network load overload, network equipment failure, insufficient network resources, weak network signal coverage, abnormal terminal device behavior, etc.; at the same time, the abnormal type can be subdivided into multiple abnormal subtypes, for example, network
  • the abnormal type of attack can be subdivided into DDoS (distributed denial of service) attacks, network tampering, and identity impersonation.
  • the abnormal behavior of terminal equipment can be subdivided into The terminal accesses the cell ping-pong, the terminal is suspected of launching a DDoS attack, the terminal device is abnormally awakened, the battery is consumed abnormally, the flow is abnormal, and the air interface link is disconnected abnormally.
  • the first data analysis network element can respond to the received first request message, and based on the identification of the target object parsed from the first request message, from the corresponding network element in the network (such as RAN, AMF, SMF, UPF, OAM) , NRF, UDM network element, etc.) to obtain the relevant data of the target object.
  • the first data analysis network element may send a data report request including the identifier of the target object to the corresponding network element in the network to request the network element to send
  • the first data analysis network element reports the relevant information of the target object, so that the first data analysis network element can analyze and process the received data, generate state analysis results for the target object, and send the generated state analysis results Analyze the network element for the second data.
  • the data obtained from the corresponding network element in the network may be as shown in Table 1:
  • NSSAI refers to network slice selection support information (network slice selection assistance information)
  • S-NSSAI refers to single network slice selection support information (single NSSAI)
  • NSI refers to network slice instance (network slice instance)
  • IMS IP Multimedia subsystem (IP multimedia subsystem)
  • TA refers to tracking area
  • IMSI refers to international mobile subscriber identity (international mobile subscriber identity)
  • GPSI refers to generic public subscription identifier.
  • the input data collected by the first data analysis network element described in Table 1 is only an optional example. In other possible implementation manners, it may also include other types of data, such as the registration success rate of the terminal device, etc.; Or it may include part of the type data in Table 1 above, which is not limited in this embodiment.
  • the first data analysis network element may obtain different input data.
  • the data type obtained by the first data analysis network element may include: slice identification, sampling time, area information, network equipment identification, network equipment load , Network equipment temperature, network equipment resource utilization rate, etc.
  • the data type obtained by the first data analysis network element may include: slice identification, DNN, sampling time, area information, network average traffic, network Peak throughput rate, network device identification, network device load, network device resource occupancy rate, terminal device identification, terminal device reconnection rate, terminal device registration failure rate (or the number of terminals that fail to register), terminal device session success rate (or terminal Device session failure rate) and so on.
  • the first data analysis network element After the first data analysis network element obtains the input data, it can use the pre-trained model to analyze and reason to obtain the state analysis result of the target object.
  • the module may be obtained by the first data analysis network element through training according to the corresponding sample data, or it may be sent to the first data analysis network element after the training is completed by a dedicated model training platform.
  • the trained model can characterize the relationship between the input data and whether there is abnormal state, and further, it can also characterize the relationship between the input data and the abnormal type, abnormal subtype, second abnormal cause, abnormal degree, and abnormal trend. Relationship, etc.
  • the status analysis result of the target object generated by the first data analysis network element may not only include information indicating whether the status of the target object is abnormal, but also include the abnormality type, abnormality subtype, second abnormality cause, abnormality degree, abnormality trend, etc. Any one or more of the information (at this time, the target object is in an abnormal state).
  • the abnormal trend refers to the abnormal development of the target object when the state is abnormal. For example, it can be defined as “rising” (representing an increase in abnormal conditions), “declining” (representing a reduction in abnormal conditions), and “stable” (representing abnormal conditions) Stable) and “unknown” describe the development trend of the abnormal situation of the target object.
  • the status analysis result of the target object may also include only information indicating whether the status of the target object is abnormal.
  • the degree of abnormality may specifically be a quantitative value, for example, it may be expressed as a degree value such as “high”, “medium”, or “low”, or may be expressed as a specific numerical value.
  • the included status indication information may be used to indicate whether the target object is in a normal state or an abnormal state.
  • the status indication information may also be used to indicate that the status of the target object is an unknown state, that is, the first data analysis network element may not be able to determine whether the target object is in a normal state or abnormal based on the input data that has been obtained. State. At this time, it can be considered that the state of the target object is unknown.
  • the state of the target object fed back by the first data analysis network element to the second data analysis network element may be any one of a normal state, an abnormal state, and an unknown state.
  • the status analysis result of the target object may be the analysis result of the historical status of the target object (statistics).
  • the input data obtained by the first data analysis network element may include the load of the network device in the past period of time and the CPU occupancy rate. If the first data analysis network element determines that the load of the network device is lower than the first preset value, and the CPU occupancy rate is higher than the second preset value, it can be inferred that the network device was in an abnormal state during the past period of time , Such as possible network attacks that lead to high CPU usage.
  • the analysis result of the current state of the target object although the real-time requirement is high, belongs to the state of the target object that has occurred, and can be classified as the analysis result of the historical state of the target object.
  • the state analysis result of the target object may also be the prediction of the future state of the target object.
  • the input data obtained by the first data analysis network element may include the temperature data of the terminal device in the past period of time (that is, the observation time), although The temperature data of the terminal device during the observation time is in a normal state, such as always less than 60°C, etc., but if the temperature data of the terminal device is continuously increasing during the observation time period, the first data analysis network element is based on the terminal The current temperature increase trend of the device can predict that the temperature of the terminal device will exceed 60°C in a certain period of time in the future, so the first data analysis network element can predict that the temperature data of the terminal device in the future period of time will be abnormal, that is, It is predicted that the terminal equipment will be in an abnormal state for a period of time in the future.
  • the state analysis result of the target object may have a corresponding confidence level (for ease of description, hereinafter referred to as the second confidence level), the second confidence level may be used to characterize the credibility of the state analysis result indicating the normal/abnormal state For example, when the second confidence level is 70%, the credibility that the target object is in a normal (or abnormal) state is 70%, and correspondingly, the credibility that the target object is in an abnormal (or normal) state is 30%.
  • the state analysis result of the target object generated by the first data analysis network element may be the first time information and/or The state analysis result corresponding to the data in the first area information (observation area information)
  • the state analysis result will be illustrated by taking the state of the target object specifically as a network attack as an example.
  • the content included in the state analysis result of the target object may specifically be:
  • the first data analysis network element may only feed back the state analysis result of the target object to the second data analysis network element when the target object is in an abnormal state, so as to notify the second data analysis network element that the state of the target object is abnormal.
  • the second data analysis network element (or other network element) may send second indication information to the first data analysis network element, and the second indication information may be used to indicate that the first data analysis network element is in the target object.
  • the status is abnormal, the status analysis result of the target object is fed back.
  • the second indication information may be carried in the aforementioned first request message and sent to the first data analysis network element together with the first request message.
  • the first data analysis network element determines that the target object is in an abnormal state, it sends the state analysis result of the target object to the second data analysis network element; and when the first data analysis network element determines that the target object is in a normal state, it may not The status analysis result of the target object is fed back to the second data analysis network element.
  • the second data analysis network element does not receive the status analysis result of the target object, it can default that the target object is in a normal state, which can reduce the first The number of data communications and the amount of data between the data analysis network element and the second data analysis network element save network resources.
  • the communication network may also include other data analysis network elements.
  • the first data analysis network element is determining that the target object is in an abnormal state. Later, while the status analysis result of the target object is fed back to the second data analysis network element, the status analysis result of the target object can also be fed back to other data analysis network elements.
  • the first data analysis network element can directly feed back the status analysis result of the target object to the second data analysis network element, or it can send the status analysis result of the target object to the fourth network element.
  • the element stores the status analysis result of the target object; when the second data analysis network element needs to obtain the status analysis result of the target object, the required status analysis result can be obtained from the fourth network element.
  • the fourth network element can store the status analysis results of different target objects generated by each data analysis network element in the network, and the fourth network element uniformly provides other data analysis network elements with the required status analysis results.
  • the fourth network element may be, for example, a UDM network element, a user data repository (UDR) network element, or a network repository function (NRF) network element.
  • the second data analysis network element can also query which data analysis network element provides the service of generating the result of the state analysis of the target object, where different data
  • the functions of the analysis network elements can be different. For example, some data analysis network elements can analyze and determine whether the target object is in a network attack state, while another part of data analysis network elements can analyze and determine whether the target object is in a network overload state.
  • the second data analysis network element may send a query request to the fifth network element, and the query request is used to request the fifth network element to query the first data analysis network element that generates the status analysis result of the target object.
  • the query request can carry one or more of slice identification, service area identification, abnormal type identification, abnormal subtype identification, and other information; the fifth network element can respond to the query request by pre-saving the corresponding data analysis network element Find out the identification information of the first data analysis network element that matches the query request in the profile of Send the identification information of the first data analysis network element to the second data analysis network element.
  • the second data analysis network element may send a first request message to the first data analysis network element according to the identification information of the first data analysis network element to request the first data analysis network element to feed back the status analysis result of the target object.
  • the identification information of the first data analysis network element may be, for example, the IP address of the first data analysis network element, or the fully qualified domain name (FQDN) of the first data analysis network element, etc.
  • the five network elements can be, for example, NRF network elements or UDM network elements, etc.
  • first data analysis network element and the second data analysis network element in this embodiment may be different network elements deployed separately.
  • first data analysis network element and the second data analysis network element The data analysis network elements may also be set as the same network element. In this case, the data interaction between the first data analysis network element and the second data analysis network element can be omitted as appropriate.
  • the second data analysis network element obtains the first input data corresponding to the target analysis type according to the received status analysis result of the target object, wherein, when the status analysis result of the target object indicates that the target object is abnormal, the first input data may not Include data corresponding to the target object.
  • the second data analysis network element may generate a first analysis result corresponding to the target analysis type according to the first input data.
  • the data corresponding to the target object may have errors. This makes the second data analysis network element correct the first analysis result obtained when the second data analysis network element performs corresponding analysis based on the data of the target object containing the error. Performance may be affected.
  • the second data analysis network element receives the status analysis result of the target object from the first data analysis network element, if it is determined that the target object is in an abnormal state, for example, according to the status analysis
  • the status indication information in the result determines that the status of the target object is abnormal, etc.
  • the first analysis result when the corresponding analysis result (hereinafter referred to as the first analysis result) is generated, it can be determined whether the input data that generates the first analysis result includes the target object's correlation If the data is included, the input data needs to be adjusted so that the input data does not include the relevant data of the target object, and the accuracy of the first analysis result obtained based on the first input data that does not contain erroneous data Corresponding improvement can also be obtained; if it is not included, there is no need to adjust the input data.
  • the data corresponding to the target object may be data related to the target object that is required to generate a corresponding analysis result for the target object.
  • the data corresponding to the target object may be data related to the service quality analysis result of the terminal device, such as the service MOS generated by the terminal device in the AF network element, and the terminal device in the AMF network element
  • the location information generated in the UPF network element, the service flow data generated by the terminal device in the UPF network element, etc.; for another example, when the target object is the network device NF network element, the data corresponding to the target object may be NF-related data. Such as NF load data, etc.
  • the first analysis result may be the analysis result corresponding to the target analysis type generated by the second data analysis network element for the first network element (that is, other network elements in the network).
  • the first network element is an AMF network element
  • the second data analysis network element An analysis result may be the movement trajectory analysis result of the terminal device in a certain area generated by the second data analysis network element at the request of the AMF network element, and the movement trajectory analysis result may represent the movement trajectory information of the terminal object in the area; or,
  • the first analysis result may be the service quality analysis result generated by the second data analysis network element at the request of the PCF network element, and the service quality analysis result may characterize the service quality of the terminal device that executes the service.
  • the input data obtained by the second data analysis network element is also the data required for analyzing the analysis result of the target analysis type (such as the above-mentioned movement track analysis type or service quality analysis type of the terminal device).
  • the first network element may be an AMF network element or a PCF network element, or other network elements in the network, such as an AF network element, UDM network element, RAN network element, and so on. After the second data analysis network element generates the first analysis result, the first analysis result may be sent to the first network element.
  • the second data analysis network element when the second data analysis network element adjusts and generates the input data corresponding to the first analysis result, it may be implemented by data elimination. Specifically: when the second data analysis network element needs to generate the first analysis result, the second data analysis network element may obtain the third input data required to generate the first analysis result from the corresponding network element in the network. The input data includes the data corresponding to the target object. At this time, if the second data analysis network element receives the status analysis result of the target object, and the status analysis result indicates that the status of the target object is abnormal, the second data analysis network element may The data corresponding to the target object in the third input data is deleted to obtain the first input data (that is, the remaining third input data), and the corresponding first analysis result is generated based on the first input data. Alternatively, when the second network element in the network feeds back the data corresponding to the target object to the second data analysis network element, the second data analysis network element may refuse to receive the data corresponding to the target object sent by the second network element.
  • the input data can be adjusted by canceling the data subscription.
  • the second data analysis network element may send a subscription message to the corresponding network element in the network in advance to subscribe to the input data required to generate the first analysis result from the corresponding network element in the network, where the input data can be It includes data corresponding to the target object subscribed from the second network element, and other data included in the input data may be subscribed from a third network element, and the third network element may include one or more network elements.
  • the second data analysis network element may send an unsubscribe message to the second network element, and the unsubscribe message may be used to indicate
  • the second network element stops feeding back the data corresponding to the target object to the second data analysis network element, and the third network element can continue to send the second data based on the instructions of the previous subscription message without receiving the unsubscribe message.
  • the analysis network element feeds back other input data, so that the first input data obtained by the second data analysis network element may not include data corresponding to the target object.
  • the second data analysis network element after the second data analysis network element sends an unsubscribe message to the second network element, it can unsubscribe the data corresponding to all objects on the second network element used to generate the analysis result, and all objects include data for Target objects in abnormal state and objects in normal state. At this time, in the process of generating the first analysis result, the first input data of the second data analysis network element may not include any object data on the second network element.
  • the second network element can still feed back the data corresponding to the object in the normal state to the second data analysis network element, and use it as a part of the first input data.
  • the second data analysis network element can also send subscription messages periodically or on demand, when the second data analysis network element determines the status of the target object according to the received status analysis result of the target object When abnormal, the second data analysis network element may not send the data subscription message for the target object to the second network element, but may send the data subscription message to the third network element, so as to obtain the first data that does not include the data corresponding to the target object.
  • One input data One input data.
  • the second data analysis network element may also first determine the target object corresponding to the abnormal state.
  • the relevant analysis result or the analysis type corresponding to the analysis result (such as analytics ID).
  • the second data analysis network element can determine which analysis type (such as analytics ID) corresponds to the data corresponding to the target object in the abnormal state. Analyze the results. If the data corresponding to the target object does not participate in the generation of the analysis result corresponding to the target analysis type, the second data analysis network element may not need to adjust the analysis result corresponding to the generated target analysis type.
  • the second data analysis network element when the second data analysis network element generates the analysis results of the two analysis types, service MOS or network performance, the accuracy of the analysis results corresponding to these two analysis types may not be affected due to the failure of the NF network element. , And a certain (or some) terminal equipment UE failure may affect the accuracy of the analysis results corresponding to these two analysis types. Therefore, when the target object in the abnormal state is the terminal equipment UE, the second data The analysis network element can determine that the input data that generates the analysis results of the two types of analysis is adjusted so that it does not contain the data corresponding to the terminal device UE; and when the target object in the state is the NF network element, the second data The analysis network element may not need to adjust the input data for generating the analysis results of these two types of analysis.
  • the status analysis result of the target object received by the second data analysis network element corresponds to the first time information and/or the first area information
  • the status analysis result indicates that the target object is in an abnormal state
  • it indicates The target object generates abnormal data during the time period indicated by the first time information and/or in the area indicated by the first area information, so that when the second data analysis network element generates the first analysis result, its first input data can be It does not include data generated by the target object in the time period indicated by the first time information and/or data generated by the target object in the area indicated by the first area information.
  • the second data analysis network element also receives the state analysis result of the target object sent by the first data analysis network element. If the state analysis result corresponds to the second confidence level, the second data analysis network element may also determine whether to adjust the input data based on the second confidence level. Specifically, while the second data analysis network element determines that the status of the target object is abnormal according to the status analysis result of the target object, the second confidence level corresponding to the status analysis result is also greater than the first threshold.
  • the second data analysis network element It can be determined that the input data required to generate the first analysis result is adjusted so that the adjusted input data does not include the data corresponding to the target object; and when the second confidence level corresponding to the state analysis result is not greater than the first threshold, Even if the status analysis result of the target object indicates that the status of the target object is abnormal, the second data analysis network element may not adjust the input data.
  • the first analysis result may be sent to the first network element, so that the first network element performs corresponding processing according to the first analysis result.
  • the first network element can determine whether there is a terminal device in the area according to the analysis result of the movement trajectory of the terminal device in the area.
  • There are terminal devices with overlapping trajectories of the equipment for example, when the first analysis result is specifically the service quality analysis result for the service type, the first network element can determine whether it is the service quality according to the service quality of the service type.
  • the business type adjusts the corresponding QoS strategy, etc.
  • the first network element and the processing procedure executed by the first network element according to the first analysis result are not limited, and they can be applied to any applicable scenario.
  • the second data analysis network element may also send the status analysis result of the target object and the target analysis type (such as analytics ID) to the first network element, so that the first network element can make a decision based on the information related to the abnormal state of the target object Whether to disable the second analysis result corresponding to the target analysis type or reduce the confidence of the second analysis result corresponding to the target analysis type.
  • the second data analysis network element when the second data analysis network element generates analysis results of two analysis types: service MOS or network performance, and the target object is the terminal device UE, the second data analysis network element can compare the status analysis results of the UE and the service MOS Or, the two analysis types (identifications) of network performance are sent to the first network element together, so that the first network element can perform corresponding judgment and processing operations.
  • the first analysis result may be generated by the first network element requesting the second data analysis network element.
  • the first network element may send a second request message to the second data analysis network element, and the second request message may carry a target analysis type, for example, an analytic ID, etc.
  • the target analysis type is used to indicate the second Which type of analysis result is generated by the data analysis network element; the second data analysis network element may generate the first analysis result corresponding to the target analysis type based on the second request message sent by the first network element, and then compare the first analysis result The result is sent to the first network element.
  • the first analysis result may correspond to a specific time period and/or a specific area.
  • the second data analysis network element may also send third time information and/or third area information to which the first analysis result is applicable to the first network element.
  • the third time information can be used to indicate the time period in which the first network element is suitable to use the first analysis result to perform the corresponding processing operation
  • the third area information can be used to indicate the area in which the first network element is suitable to use the first network element. Analyze the results and perform corresponding processing operations.
  • the third time information may be determined by the second data analysis network element according to the first time information.
  • the time period indicated by the third time information may be a subset of the time period indicated by the first time information, etc.
  • the third area information may be determined by the second data analysis network element according to the first area information.
  • the area indicated by the third area information may be a subset of the area indicated by the first area information.
  • the second data analysis network element may send the analysis result to the first network element every time the analysis result is generated. In another embodiment, after the second data analysis network element generates the first analysis result, it can compare whether the first analysis result is the same as the second analysis result previously sent to the first network element. If it is determined to be the same, Then the second data analysis network element does not need to send the first analysis result to the first network element. Accordingly, the first network element continues to execute the corresponding processing procedure based on the second analysis result; if it is determined that they are not the same, the first data analysis network The element may send the first analysis result to the first network element. In another embodiment, the second data analysis network element may also send the first network element to the first network element when it is determined that the first input data of the analysis result for the same target analysis type does not include the data corresponding to the target object. 1. Analyze the results.
  • the second data analysis network element may also feed back a third degree of confidence, and the third degree of confidence may be used to indicate the first analysis.
  • the credibility of the results For example, when the first analysis result is specifically the service quality analysis result of the service type, the third confidence level may be used to characterize the credibility that the terminal device has a higher service quality.
  • the first network element may execute the corresponding processing procedure based on the first analysis result, and when the value of the third degree of confidence is small, For example, when it is not greater than the second threshold, the reliability of the first analysis result is not high.
  • the first network element may not rely on the first analysis result when executing the corresponding processing process. For example, it may be based on the second analysis result.
  • the second analysis result fed back by the data analysis network element before executes the corresponding processing process and so on.
  • the magnitude of the third degree of confidence is affected by the second degree of confidence and the first input data. Therefore, the third degree of confidence may be determined based on the second degree of confidence and the first input data corresponding to the first analysis result.
  • the second data analysis network element may send first indication information to the first network element, where the first indication information is used to instruct the second data analysis network element to stop using the second analysis Result or lower the confidence level corresponding to the second analysis result to the first confidence level, the second analysis result is the analysis of the target analysis type generated by the second data analysis network element based on the second input data and sent to the first network element
  • the second input data may include data corresponding to the target object.
  • the second analysis result that the second data analysis network element previously fed back to the first network element is generated based on the second input data including the data corresponding to the target object
  • the data corresponding to the target object may be due to the abnormal state of the target object
  • An error occurs, which reduces the accuracy of the second analysis result generated based on the data, and correspondingly, the credibility of the second analysis result also decreases.
  • the second data analysis network element may send the deactivation indication information for the second analysis result to the first network element to indicate that the first network element is in an abnormal state.
  • the network element deactivates the second analysis result, or cancels the related operation performed according to the second analysis result, or refuses to continue to perform the corresponding operation according to the second analysis result.
  • the second data analysis network element determines that the target object is in an abnormal state
  • the confidence of the second analysis result can be reduced.
  • the confidence level corresponding to the second analysis result is lowered to the first confidence level, so that the first network element can determine to execute the corresponding processing process based on the first confidence level of the second analysis result.
  • the second data analysis network element may also send the first analysis result and/or the reason for the first indication information to the first network element.
  • the second data analysis network element may send the first abnormal cause to the first network element, and the first abnormal cause may be used to instruct the second data analysis network element to send the first analysis result and/or the first analysis result to the first network element.
  • a reason for indicating information For example, the first reason for abnormality can indicate that the confidence level corresponding to the second analysis result is lowered because the second input data that previously generated the second analysis result includes the data of the target object in an abnormal state, or the first An abnormal cause may indicate that the second analysis result previously sent by the second data analysis network element is inaccurate.
  • the first reason for the abnormality may also indicate the type of abnormality in the second analysis result, for example, the target object is subjected to a DOS attack.
  • the second input data that generates the second analysis result may include not only data corresponding to the target object, but also data corresponding to other objects.
  • the second data analysis network element may be based on 50 objects (such as a certain The data corresponding to 50 objects in a network slice, etc.) generates the second analysis result, and there may be only one or two target objects in an abnormal state.
  • the second data analysis network element When the second data analysis network element generates a second analysis result based on the data corresponding to the first number of objects, and there is a second number of target objects in the first number of objects, the status is abnormal.
  • the second data analysis may not send the above-mentioned deactivation indication information or the first indication information to the first network element (or even if the first indication information is sent, the degree of confidence reduction may be smaller than the second value);
  • the second data may send the deactivation instruction information or the first instruction information to the first network element based on the foregoing implementation manner.
  • the second data analysis network element when it determines that the target object is in an abnormal state based on the first analysis result generated by the first data analysis network element, it may also only send the above-mentioned deactivation instruction information or the first network element to the first network element.
  • An indication information to notify the first network element to stop using the second analysis result fed back by the second data analysis network element before or to lower the confidence of the second analysis result, without obtaining the first input data and generating the first analysis result.
  • the second data analysis network element may not send the deactivation instruction information or the first instruction information to the first network element, but may send information about the target object in the abnormal state to the first network element.
  • the relevant information about the target object being in an abnormal state can be, for example, any one of the target object’s identification information, status indication information, abnormality type, abnormality subtype, abnormality cause, abnormality degree, abnormality trend, etc.
  • the first network element can determine whether to deactivate the second analysis result or reduce the confidence of the second analysis result based on the information sent by the second data analysis network element.
  • the first network element may determine according to the abnormal trend information from 8:00 to 10:00 according to the second analysis As a result, perform corresponding processing operations, and stop using the second analysis result (such as discarding the second analysis result, etc.) from 10:00 to 24:00 (or any time after 10:00) or refuse to continue using the second analysis result Analyze the results and perform corresponding processing operations.
  • the second analysis result such as discarding the second analysis result, etc.
  • the first indication information sent by the second data analysis network element to the first network element may correspond to a specific time period or a specific area, indicating that the first analysis result is reduced during the time period or The confidence level within this area does not need to be lowered in other time periods or other areas.
  • the second data analysis network element may also send second time information and/or second area information corresponding to the first indication information to the first network element, and the second time information It is used to indicate the time corresponding to the reduced first confidence level, that is, the confidence level of the first analysis result in the time period indicated by the second time information is the first confidence level, and the first confidence level in other time periods
  • the confidence of an analysis result may be higher than the first confidence
  • the second area information is used to indicate the area corresponding to the first confidence, that is, the confidence of the first analysis result in the area indicated by the second area information
  • the degree is the first confidence degree, and the confidence degree of the first analysis result in other regions may be higher than the first confidence degree.
  • the first network element after the first network element receives the second time information and/or the second area information, it can determine whether an incorrect processing operation has been performed in the past based on the second analysis result and its corresponding confidence level, or it can determine In which time period and/or in which area the second analysis result is disabled, so as to improve the correctness of the processing operation performed by the first network element.
  • the second time information may be determined by the second data analysis network element according to the first time information.
  • the time period indicated by the second time information may be a subset of the time period indicated by the first time information, etc.
  • the time period indicated by the second time information may be a time period during which the second data analysis network element performs prediction, and the first analysis result is available within the time period indicated by the second time information.
  • the second area information may be determined by the second data analysis network element according to the first area information.
  • the area indicated by the second area information may be a subset of the area indicated by the first area information.
  • the second data analysis network element sends the second time information to the first network element while feeding back the first indication information, which may also be used to indicate the time when the first analysis result is available.
  • the second analysis result can predict the time when the first analysis result is available in the future.
  • the start time in the next three hours can be set As the available time of the first analysis result, so that the first network element executes the operation corresponding to the first analysis result according to the available time indicated by the second time information.
  • the state analysis result of the target object from the first data analysis network element received by the second data analysis network element can characterize whether the target object is in an abnormal state.
  • the target object corresponds to There may be errors in the data of the target object. Therefore, when the status analysis result of the target object indicates that the target object status is abnormal, the first input data corresponding to the target analysis type acquired by the second data analysis network element may not include the target object Corresponding data, which enables the first analysis result corresponding to the target analysis type generated by the second data analysis network element based on the first input data to not be affected by the data corresponding to the wrong target object, thereby improving the first analysis result The correctness.
  • the second data analysis network element adjusts the input data according to the status analysis result determined by the first data analysis network element, and the first network element executes the corresponding data according to the first analysis result fed back by the second data analysis network element. Processing operations.
  • the first network element may also directly obtain the status analysis result of the target object generated by the first data analysis network element, and determine whether the target object is abnormal based on the status analysis result of the target object; When it is determined that the target object is abnormal, the first network element can perform the same operations as the above-mentioned first network element and/or the second data analysis network element. For example, the first network element can down-regulate data related to the target object. The confidence level of the analysis result, or disable the acquired analysis result based on the data corresponding to the target object, or cancel or modify the relevant operation based on the previous analysis result.
  • the NWDAF in the network may include at least NWDAF1 and NWDAF2.
  • NWDAF3 and NWDAF4 NWDAF3 and NWDAF4.
  • the scenario embodiment shown in FIG. 3 is only used as an exemplary description, and is not used to limit the technical solution of the embodiment of the present application to be limited to the example shown in FIG. 3 during specific implementation.
  • the steps and/or information content shown in FIG. 3 may be added, deleted or replaced as appropriate.
  • the following notification message may contain the identification information of the terminal device, the status analysis result, the confidence level, and the Any one or more of exception type, time information, and area information.
  • the method may specifically include:
  • NWDAF1 may monitor one or more UEs to determine whether the UE is in an abnormal state.
  • NWDAF1 can obtain UE-related data from the UE and other network elements in the network (such as AMF, SMF, UDM, UDR, etc.), and generate a state analysis result for the UE based on the data, which can indicate Whether the status of the UE is abnormal.
  • NWDAF1 may be configured to actively perform state monitoring on the UE, so as to determine whether the UE is in an abnormal state through the generated state analysis result.
  • the NWDAF2 or other network elements in the network may request the NWDAF1 to monitor whether the state of the UE is abnormal.
  • NWDAF1 sends a notification message to UDM/UDR.
  • the notification message may include UE identification information, status analysis result, abnormality type, confidence level, time information, and area information.
  • NWDAF1 determines that the UE is in an abnormal state based on the state analysis result, it can determine the abnormality type when the UE is abnormal, and determine the confidence that the UE is in the abnormal state, the time information and area information of the UE in the abnormal state, and so on. Then, NWDAF1 can generate a notification message based on the information, and send the notification message to UDM/UDR for storage.
  • the status analysis result can be expressed as normal or abnormal to reflect whether the UE is in an abnormal state, or can be expressed as a numerical value, such as using "0" to indicate that the UE is in an abnormal state, and "1" to indicate that the UE is in a normal state, etc.; abnormal type It can include DOS attacks, too frequent service access, abnormal data traffic, ping-pong UE, abnormal UE location, abnormal sleep/wakeup, wrong destination address, etc.; time information can characterize the observation when NWDAF1 observes that the UE is in an abnormal state Time, that is, whether the UE is in a normal state or an abnormal state during the observation period; area information can indicate the area corresponding to NWDAF1 to determine that the UE is in a normal state or an abnormal state.
  • NWDAF1 determines that the UE is in a normal state when it is located in area 1, and is located in area 2.
  • Confidence degree can represent the credibility of NWDAF1 to determine that the UE is in a normal state or an abnormal state. It can be expressed in the form of levels, such as “high”, “medium”, “low”, etc., among which, “high” ”Means that NWDAF1 has a higher degree of confidence in determining that the UE is in an abnormal state, while “low” means that NWDAF1 has a lower degree of confidence in determining that the UE is in an abnormal state, or it can be expressed as a numerical value, such as "3", "2",” 1" and so on, where “3” indicates that NWDAF1 has a higher degree of credibility to determine that the UE is in an abnormal state, and “1” indicates that NWDAF1 has a lower degree of credibility in determining that the UE is in an abnormal state.
  • the notification message sent by NWDAF1 to UDM/UDR may only include the UE's identity, status analysis result, confidence level, time information, and area information.
  • NWDAF1 may only send notification messages to UDM/UDR when it is determined that the UE is in an abnormal state, and not send notification messages when it is determined that the UE is in a normal state, thereby reducing the amount of data sent by NWDAF1 and also Reduce the amount of data stored in UDM/UDR, which can reduce the consumption of network resources.
  • the UDM/UDR saves the notification message, specifically, it may save the identification information of the UE, the status analysis result, the abnormality type, the confidence level, the time information, and the area information included in the notification message. During specific implementation, the UDM/UDR may save the notification message in the context data or subscription data of the UE.
  • NWDAF1 may send a notification message specific to the network device to the NRF network element, and save the notification message in the NRF network element,
  • NWDAF2 may request the NRF network element for the status analysis result of the network device.
  • NWDAF2 sends a request message to the UDM/UDR, where the request message is used to request the status analysis result of the UE.
  • NWDAF2 When the input data required by NWDAF2 to generate the analysis result corresponding to the target analysis type includes the data corresponding to the UE, or NWDAF2 determines that it needs to collect the sample data of the UE from the data provider (such as AF, NF, UE, etc.) as training data, NWDAF2 A request message can be sent to the UDM/UDR to request the UDM/UDR to feed back the status analysis result of the UE, so that the NWDAF2 can determine whether the UE is in an abnormal state.
  • the data provider such as AF, NF, UE, etc.
  • NWDAF2 needs to do relevant analysis and training work for a specific user or group (for example, analyze the movement track information of one or more UEs), then NWDAF2 can obtain samples of the specific user or group The data is used as training data, or other analysis results of the specific user or group are obtained as input data. Before that, NWDAF2 can request to obtain the status analysis results of the UE of the specific user or group to determine whether the UE is In an abnormal state, the request message includes the UE identification information corresponding to the specific user or the UE group identification information corresponding to the group.
  • NWDAF2 needs to analyze network granularity (such as analyzing network load), or regional granularity (such as analyzing the number of users in an area), or business granularity (such as analyzing service experience), then NWDAF2 It is possible to obtain sample data of a large number of users in the network or in the area as training data, or other analysis results of a large number of users in the network or in the area need to be obtained as input data. Before that, NWDAF2 can request to obtain the corresponding The UE's status analysis result is used to determine whether the UE is in an abnormal state.
  • the request message contains network identification information (such as PLMN ID or S-NSSAI, etc.) or area identification (such as TA list or cell list, etc.) information.
  • UDM/UDR may not feed back the status analysis result of the UE to NWDAF2. Accordingly, NWDAF2 may not receive the status analysis result fed back by UDM/UDR.
  • the UE is in a normal state by default.
  • the UDM/UDR feeds back the status analysis result of the UE to NWDAF2 to notify NWDAF2 that the UE is in an abnormal state, thereby reducing the data transmitted between NWDAF2 and UDM/UDR In this way, the consumption of network resources can be reduced.
  • UDM/UDR feeds back a response message to NWDAF2.
  • the response message includes UE identification information, status analysis result, abnormality type, confidence level, time information, and area information.
  • the response message fed back by the UDM/UDR to the NWDAF2 may also include only the status analysis result. For example, when the confidence level is greater than a preset threshold, it indicates that the UE is in a normal state or an abnormal state is more likely, so that only the state analysis result can be fed back to NWDAF2.
  • the data corresponding to the UE may have errors, which makes the correctness of the analysis results obtained when NWDAF2 performs corresponding analysis based on the data of the UE containing errors. Therefore, this implementation For example, when NWDAF2 determines that the UE is in an abnormal state and the confidence is greater than the preset threshold, it can generate corresponding analysis results based on input data that does not include the data corresponding to the UE, so as to avoid the analysis results generated by the data corresponding to the UE for NWDAF2 The accuracy affects the accuracy of the analysis results.
  • NWDAF2 may obtain the third input data required to generate the analysis result from the corresponding network element in the network.
  • the three input data includes the data corresponding to the UE.
  • NWDAF2 can delete the data corresponding to the UE in the third input data to obtain the first input data (that is, the remaining third input data), and based on the first input data Generate the corresponding analysis results.
  • the NWDAF2 may refuse to receive the data corresponding to the UE sent by the network element.
  • NWDAF2 may send a subscription message to the corresponding network element in the network in advance to subscribe to the input data required to generate the analysis result from the corresponding network element in the network, where the input data It may include data corresponding to the target object subscribed from the second network element, and other data included in the input data may be subscribed from a third network element, and the third network element may include one or more network elements.
  • NWDAF2 may send an unsubscribe message to the second network element.
  • the unsubscribe message may be used to instruct the second data to stop feeding back the data corresponding to the UE to NWDAF2, and In the case that the third network element does not receive the unsubscribe message, it can continue to feed back other input data to NWDAF2 based on the instructions of the previous subscription message, which in turn can make the first input data obtained by NWDAF2 not include the UE corresponding data.
  • NWDAF2 may also send a new subscription request message or subscription modification message, in which one or some users are implicitly set as a subscription blacklist.
  • NWDAF2 determines that the UE is in a normal state and the confidence level is greater than the preset threshold, NWDAF2 can generate corresponding analysis results based on the input data containing the data corresponding to the UE.
  • the analysis result can be sent to the network element that subscribes to the analysis result, and the UE can be placed in an abnormal state at the same time.
  • the abnormal type, time information, and area information of the time are fed back to the network element, so that the network element can perform corresponding processing operations based on the received information, such as correcting the performed error operations.
  • NWDAF2 when NWDAF2 determines that the UE is in an abnormal state, it may also send deactivation indication information or first indication information to the network element subscribing to the analysis result.
  • the deactivation instruction information may instruct the network element to deactivate the analysis result that was previously fed back by NWDAF2, or cancel the relevant operation performed based on the previously fed back analysis result, or refuse to continue to perform the corresponding operation based on the previous feedback analysis result, etc.;
  • An indication information that can instruct the network element to reduce the confidence level of the analysis result previously fed back by NWDAF2, so that the network element determines to execute the corresponding processing procedure based on the analysis result of the reduced confidence level, for example, when the network element determines according to the first indication information
  • the confidence of the analysis result fed back by NWDAF2 is lowered to 30%, the previous operation based on the analysis result can be cancelled, or the opposite operation can be performed.
  • the status analysis result monitored and generated by NWDAF1 is sent to the UDM/UDR for storage, and when NWDAF2 needs the UE status analysis result, it can be obtained from the UDM/UDR.
  • NWDAF1 after NWDAF1 generates the status analysis result corresponding to the UE, it can directly notify the status analysis result to NWDAF2, instead of storing it in the UDM/UDR.
  • FIG. 4 shows a schematic diagram of signaling interaction in another scenario embodiment in an embodiment of the present application. The method may specifically include:
  • NWDAF2 sends a subscription message or request message for the status analysis result of the UE to NWDAF1, and the subscription message or request message is used to request the status analysis result of the UE.
  • NWDAF2 may subscribe to or request the status analysis result of the UE from NWDAF1, so as to determine whether the UE is in an abnormal state according to the status analysis result fed back by NWDAF1.
  • the subscription message/request message may include UE identification information corresponding to a specific user or UE group identification information corresponding to a group; or, the subscription message/request message may include network identification information or area identification information to Request the status analysis results of one or more UEs located in the network corresponding to the network identification information, or request the status analysis results of one or more UEs located in the area corresponding to the area identification information.
  • NWDAF1 generates a status analysis result of the UE.
  • step S402 in this embodiment is similar to that of step S301.
  • step S301 please refer to the related description of step S301, which is not repeated here.
  • NWDAF1 sends a notification or response message to NWDAF2.
  • the notification or response message may include UE identification information, status analysis result, abnormality type, confidence level, time information, and area information.
  • NWDAF1 after NWDAF1 generates the status analysis result corresponding to the UE, it can directly notify other NWDAFs (including NWDAF2) in the network of the status analysis result, so that the notification message can be stored without UDM/UDR.
  • NWDAF2 after NWDAF1 generates the status analysis result corresponding to the UE, it can directly notify other NWDAFs (including NWDAF2) in the network of the status analysis result, so that the notification message can be stored without UDM/UDR.
  • other NWDAFs that have received the status analysis result may initiate a subscription or request for the analysis result of the UE to NWDAF1 in advance.
  • FIG. 5 shows a schematic structural diagram of a communication device in an embodiment of the present application.
  • the device 500 can be applied to a second data analysis network element, and can perform the execution performed by the second data analysis network element in the foregoing method embodiment. Method steps.
  • the apparatus 500 may include: a receiving unit 501 and a processing unit 502.
  • the device 500 may further include a sending unit 503 and a storage unit 504.
  • the receiving unit 501 is configured to receive a state analysis result of a target object from a first data analysis network element, where the target object includes one or more of a network device, a network domain, a network domain, and a terminal device;
  • the processing unit 502 is configured to obtain first input data corresponding to the target analysis type according to the status analysis result of the target object, wherein, when the status analysis result of the target object indicates that the target object is in an abnormal state, the first input data The input data does not include the data corresponding to the target object; the first analysis result corresponding to the target analysis type is generated according to the first input data.
  • the storage unit 504 in the device 500 can be used to store corresponding data, for example, can store the state analysis result, the first input data, and the first analysis result corresponding to the above-mentioned target object.
  • the storage unit 504 may also store the data received by the receiving unit 501 in the following various possible implementations, and the data obtained by the processing unit 502 when performing corresponding processing, and the sending unit 503 may send the storage unit Part or all of the data in 504.
  • the sending unit 503 is configured to send the first analysis result and/or first indication information to the first network element, where the first indication information is used to indicate the first network element Disable the second analysis result or lower the confidence level corresponding to the second analysis result to the first confidence level.
  • the second analysis result is generated by the second data analysis network element according to the second input data and sent to the For the analysis result of the target analysis type sent by the first network element, the second input data includes data corresponding to the target object.
  • the sending unit 503 is specifically configured to: when the second data analysis network element determines that the first analysis result is different from the second analysis result, the second data analysis network element Sending the first analysis result to the first network element.
  • the receiving unit 501 is further configured to receive first time information and/or first area information corresponding to the status analysis result of the target object;
  • the first input data does not include data corresponding to the target object, and includes:
  • the first input data does not include data corresponding to the first time information and/or the first area information of the target object.
  • the sending unit 503 is further configured to send second time information and/or second area information corresponding to the first indication information to the first network element.
  • the sending unit 503 is further configured to send third time information and/or third area information to which the first analysis result is applicable to the first network element.
  • the sending unit 503 is further configured to send a first abnormality cause to the first network element, where the first abnormality cause is used to instruct to send the first analysis result and/or The reason for the first indication information.
  • the processing unit 502 is specifically configured to delete the data corresponding to the target object from the acquired third input data corresponding to the target analysis type to obtain the first input data ;
  • the state analysis result of the target object includes a state prediction analysis result of the target object.
  • the receiving unit 501 is further configured to receive a second confidence level corresponding to the state analysis result of the target object from the first data analysis network element;
  • the processing unit 502 is specifically configured to: when the second data analysis network element determines that the second confidence level is greater than the first threshold, and determines that the target object is in an abnormal state according to the result of the state analysis of the target object, The second data analysis network element obtains the first input data corresponding to the target analysis type according to the status analysis result of the target object.
  • the sending unit 503 is further configured to send a third confidence level corresponding to the first analysis result to the first network element, where the third confidence level is determined by the first network element.
  • the second data analysis network element is determined based on the first input data and the second confidence.
  • the receiving unit 501 is specifically configured to obtain the status analysis result of the target object from a fourth network element, and the status analysis result of the target object is analyzed by the first data.
  • the network element sends to the fourth network element.
  • the state analysis result of the target object includes state indication information, and the state indication information is used to indicate that the target object is in any one of the following states: normal state, abnormal state, and unknown state .
  • the status analysis result of the target object includes any one or more of the following information: abnormality type, abnormality subtype, second abnormality reason, abnormality degree, and abnormality trend.
  • FIG. 6 shows a schematic structural diagram of a communication device in an embodiment of the present application.
  • the device 600 can be applied to a first data analysis network element, and can perform the execution performed by the first data analysis network element in the foregoing method embodiment. Method steps.
  • the apparatus 600 may include: a processing unit 601 and a sending unit 602.
  • the device 600 may further include a receiving unit 603 and a storage unit 604.
  • the processing unit 601 is configured to obtain a status analysis result of a target object, where the target object includes one or more of a network device, a network sub-domain, a network entire domain, and a terminal device;
  • the sending unit 602 is configured to send the status analysis result of the target object.
  • the storage unit 604 in the device 600 can be used to store corresponding data, for example, can store the state analysis results corresponding to the aforementioned target objects.
  • the storage unit 604 can also store the data received by the receiving unit 603 in the following various possible implementations, and the data obtained by the processing unit 601 when performing corresponding processing, and the sending unit 602 can send the storage unit Part or all of the data in 604.
  • the sending unit 602 is further configured to send the first time information and/or first area information corresponding to the status analysis result of the target object to the second data analysis network element.
  • the state analysis result of the target object includes an analysis result of the historical state of the target object, or an analysis result of the future state of the target object.
  • the sending unit 602 is further configured to send a second confidence level corresponding to the state analysis result of the target object to the second data analysis network element.
  • the receiving unit 603 is configured to receive second indication information from the second data analysis network element
  • the sending unit 602 is specifically configured to send the status analysis result of the target object to the data analysis network element when it is determined that the status of the target object is abnormal based on the second indication information.
  • the processing unit 601 is specifically configured to generate the state analysis result of the target object in response to the first request message from the second data analysis network element received by the receiving unit,
  • the first request message is used to request the state analysis result of the target object from the first data analysis network element.
  • the state analysis result of the target object includes state indication information, and the state indication information is used to indicate that the target object is in any one of the following states: normal state, abnormal state, and unknown state .
  • the status analysis result of the target object includes any one or more of the following information: abnormality type, abnormality subtype, second abnormality reason, abnormality degree, and abnormality trend.
  • the target object includes a target object of a target network slice.
  • the network slice includes a slice instance and a slice sub-instance.
  • the network sub-domains include one or more of an access network domain, a core network domain, and a transmission network domain.
  • the processing unit, the receiving unit, the sending unit, and the storage unit may be physically separated units, or they may be integrated into one or more physical units. limited.
  • the receiving unit and the sending unit are used to implement content interaction between the device and other units or network elements.
  • the sending unit may be a sending circuit or a transmitter.
  • the receiving unit may be a receiving circuit or a receiver.
  • the sending unit and the receiving unit may also be the communication unit of the communication device.
  • the sending unit and the receiving unit may also be a communication interface or a transceiver circuit of the processing unit.
  • the sending unit and the receiving unit may be a transceiver chip.
  • the communication device may also include multiple transmitting units and multiple receiving units.
  • the sending unit and the receiving unit may also be subunits of one or more transceiver units.
  • the processing unit is used to implement data processing by the communication device.
  • the processing unit can be a processing circuit or a processor.
  • the communication device may also include multiple processing units or the processing unit may include multiple sub-data processing units.
  • the processor may be a single-CPU (single-CPU) processor or a multi-core (multi-CPU) processor.
  • the storage unit may be a unit independent of the processing unit, or may be a storage unit in the processing unit, which is not limited herein.
  • the communication device may also include a plurality of storage units or the storage unit may include a plurality of sub-storage units.
  • the embodiment of the present application also provides a communication device.
  • the communication transfer device can be applied to the first data analysis network element or the second data analysis network element mentioned in the foregoing method embodiment.
  • the communication device may include a processor and a memory, and the processor is coupled with the memory;
  • the memory is used to store computer programs or instructions
  • the processor is configured to execute the computer program or instruction to cause the communication method executed by the first data analysis network element in the foregoing method embodiment to be executed, or to cause the communication method executed by the second data analysis network element in the foregoing method embodiment to be executed
  • the communication method is executed.
  • the processor executing the computer program or instruction may also cause the communication method executed by the core network element in the foregoing method embodiment to be executed.
  • FIG. 7 is a schematic diagram of the hardware structure of a communication device, which may be the first network element or the data analysis network element in the embodiment of the present application.
  • the communication device includes at least one processor 71 (as shown in FIG. 7 may also include a processor 75, etc.), at least one memory 72, and at least one communication interface 73.
  • the processor 71, the memory 72, and the communication interface 73 are connected, for example, connected through a communication line 74.
  • the processor 71 may include a CPU, as shown in FIG.
  • the processor 71 may also include multiple CPUs. As shown in FIG. 7, the processor 71 may include CPU0 and CPU1. Of course, the processor 71 may also include more than three (including three) CPUs.
  • the communication device further includes other processors, as shown in FIG. 7 may also include a processor 75, and other processors may also include one or more CPUs.
  • the connection may include various interfaces, transmission lines or buses, etc., which is not limited in this embodiment.
  • the communication interface 73 is used to connect the communication device to other communication devices through a communication link.
  • the communication interface 73 may be an S1 interface, or an X2, Xn interface, and so on.
  • the processor 71 shown in FIG. 7 can specifically complete the actions of the data analysis network element or the first network element in the above method, the memory 72 can complete the actions stored in the above method, and the communication interface 73 can complete the communication in the above method.
  • the interaction between the device and other network elements is illustrated below by taking the communication device shown in FIG. 7 applied to a data analysis network element as an example:
  • the processor 71 may obtain the first input data corresponding to the target analysis type according to the state analysis result of the target object, and generate the first analysis result corresponding to the target analysis type according to the first input data.
  • the memory 72 may store the status analysis result, the first input data, the first analysis result, and the like of the target object. Among them, the status analysis result of the target object, the first input data, and the specific content in the first analysis result can be specifically referred to related descriptions in other embodiments.
  • the processor in the embodiment of the present application may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), and a microcontroller
  • CPU central processing unit
  • DSP digital signal processor
  • MCU microcontroller unit
  • each computing device may include one or more cores for executing software instructions for calculation or processing.
  • the processor can be a single semiconductor chip, or it can be integrated with other circuits to form a semiconductor chip. For example, it can form an SoC (on-chip) with other circuits (such as codec circuits, hardware acceleration circuits, or various bus and interface circuits).
  • the processor may further include necessary hardware accelerators, such as field programmable gate array (FPGA) and PLD (programmable logic device) , Or a logic circuit that implements dedicated logic operations.
  • FPGA field programmable gate array
  • PLD programmable logic device
  • the memory in the embodiments of the present application may include at least one of the following types: read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory , RAM) or other types of dynamic storage devices that can store information and instructions, and may also be electrically erasable programmable read-only memory (EEPROM).
  • ROM read-only memory
  • RAM random access memory
  • EEPROM electrically erasable programmable read-only memory
  • the memory can also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital universal discs, Blu-ray discs, etc.) , Disk storage media or other magnetic storage devices, or any other media that can be used to carry or store desired program codes in the form of instructions or data structures and that can be accessed by a computer, but are not limited thereto.
  • CD-ROM compact disc read-only memory
  • optical disc storage including compact discs, laser discs, optical discs, digital universal discs, Blu-ray discs, etc.
  • Disk storage media or other magnetic storage devices or any other media that can be used to carry or store desired program codes in the form of instructions or data structures and that can be accessed by a computer, but are not limited thereto.
  • the memory 72 may exist independently and is connected to the processor 71 (and the processor 75).
  • the memory 72 may be integrated with the processor 71 (and the processor 75), for example, integrated in one chip.
  • the memory 72 can store program codes for executing the technical solutions of the embodiments of the present application, and is controlled by the processor 71 to execute, and various types of computer program codes that are executed can also be regarded as drivers of the processor 71.
  • the processor 71 is configured to execute computer program codes stored in the memory 72, so as to implement the technical solutions in the embodiments of the present application.
  • the instructions stored in the memory for execution by the processor may be implemented in the form of a computer program product.
  • the computer program product may be written in the memory in advance, or it may be downloaded and installed in the memory in the form of software.
  • the computer program product includes one or more computer instructions.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • Computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • computer instructions may be transmitted from a website, computer, server, or data center through a cable (such as Coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) to transmit to another website site, computer, server or data center.
  • a cable such as Coaxial cable, optical fiber, digital subscriber line (DSL)
  • wireless such as infrared, wireless, microwave, etc.
  • the computer-readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk, SSD).
  • FIG. 8 is a schematic diagram of the hardware structure of a chip 80 provided by an embodiment of the present application.
  • the chip 80 includes one or more (including two) processors 810 and a communication interface 830.
  • the processor 810 may be coupled to the communication interface 830.
  • the connection may include various interfaces, transmission lines, or buses, etc., which is not limited in this embodiment.
  • the communication interface 830 is used to connect the chip 80 with other communication devices through a communication link.
  • the chip 80 further includes a memory 840, and the memory 840 may be connected to the processor 810 and the communication interface 830, for example, through a communication line 820.
  • the memory 840 may include a read-only memory and a random access memory, and provides operation instructions and data to the processor 810.
  • a part of the memory 840 may also include a non-volatile random access memory (NVRAM).
  • NVRAM non-volatile random access memory
  • the memory 840 stores the following elements, execution modules or data structures, or their subsets, or their extended sets.
  • the corresponding operation is executed by calling the operation instruction stored in the memory 840 (the operation instruction may be stored in the operating system).
  • the processor 810 shown in FIG. 8 can specifically complete the actions of the data analysis network element or the first network element in the above method
  • the memory 840 can complete the actions stored in the above method
  • the communication interface 830 can complete the above method
  • the following is an example of using the chip shown in FIG. 8 to be applied to a data analysis network element:
  • the processor 810 may obtain the first input data corresponding to the target analysis type according to the state analysis result of the target object, and generate the first analysis result corresponding to the target analysis type according to the first input data.
  • the memory 820 may store the state analysis result, the first input data, the first analysis result, and the like of the target object. Among them, the status analysis result of the target object, the first input data, and the specific content in the first analysis result can be specifically referred to related descriptions in other embodiments.
  • the embodiment of the present application also provides a computer-readable storage medium.
  • the methods described in the foregoing embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. If implemented in software, the functions can be stored on a computer-readable medium or transmitted on a computer-readable medium as one or more instructions or codes.
  • Computer-readable media may include computer storage media and communication media, and may also include any media that can transfer a computer program from one place to another.
  • the storage medium may be any target medium that can be accessed by a computer.
  • the computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that is targeted to carry or use instructions or data structures.
  • the required program code is stored in the form of and can be accessed by the computer.
  • any connection is properly termed a computer-readable medium. For example, if you use coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wireless technology (such as infrared, radio and microwave) to transmit software from a website, server or other remote source, then coaxial cable, fiber optic cable , Twisted pair, DSL or wireless technologies such as infrared, radio and microwave are included in the definition of the medium.
  • DSL digital subscriber line
  • wireless technology such as infrared, radio and microwave
  • Magnetic disks and optical disks as used herein include compact disks (CDs), laser disks, optical disks, digital versatile disks (DVDs), floppy disks and blu-ray disks, in which disks usually reproduce data magnetically, and optical disks use lasers to optically reproduce data. Combinations of the above should also be included in the scope of computer-readable media.
  • the embodiment of the present application also provides a computer program product.
  • the methods described in the foregoing embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. If it is implemented in software, it can be fully or partially implemented in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the above computer program instructions are loaded and executed on the computer, the procedures or functions described in the above method embodiments are generated in whole or in part.
  • the above-mentioned computer may be a general-purpose computer, a special-purpose computer, a computer network, a base station, a terminal, or other programmable devices.
  • At least one refers to one or more.
  • Multiple means two or more.
  • And/or describes the association relationship of the associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the associated objects before and after are in an “or” relationship.
  • the following at least one item (a)” or similar expressions refers to any combination of these items, including any combination of a single item (a) or a plurality of items (a).
  • a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple .
  • words such as “first” and “second” are used to distinguish the same or similar items with substantially the same function and effect. Those skilled in the art can understand that words such as “first” and “second” do not limit the quantity and order of execution, and words such as “first” and “second” do not limit the difference.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Mathematical Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Algebra (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Maintenance And Management Of Digital Transmission (AREA)

Abstract

本申请公开了一种通信方法、装置及系统，包括：第二数据分析网元接收来自第一数据分析网元的目标对象的状态分析结果，目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；第二数据分析网元根据目标对象的状态分析结果获取目标分析类型对应的第一输入数据，当目标对象的状态分析结果指示目标对象状态异常时，第一输入数据不包括目标对象对应的数据；第二数据分析网元根据第一输入数据生成目标分析类型对应的第一分析结果。当目标对象的状态分析结果表征目标对象处于异常状态时，第一输入数据中不包括该目标对象对应的数据，这使得第一分析结果可以不受错误的目标对象对应的数据的影响，从而可以提高第一分析结果的正确性。

Description

一种通信方法、装置及系统
本申请要求于2020年5月22日递交中国专利局、申请号为202010441748.0，发明名称为“一种通信方法、装置及系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，特别是涉及一种通信方法、装置及系统。
背景技术
在无线通信网络中，部分网元可以具有网络数据分析功能，例如第三代合作伙伴计划(3rd generation partnership project，3GPP)网络中的网络数据分析功能(network data analytics function，NWDAF)网元，其可以获取网络中的数据并利用机器学习等方法执行相应训练分析工作，生成分析结果，该分析结果可以用于辅助网络的策略制定和执行。
但是，若该部分网元基于错误的样本数据生成分析结果，所得到的分析结果的准确性可能较低。
发明内容
本申请实施例提供了一种通信方法、装置及系统，以提高数据分析网元所生成的分析结果的准确性。
第一方面，本申请实施例提供了一种通信方法，第二数据分析网元接收来自第一数据分析网元的目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，其中，当所述目标对象的状态分析结果指示所述目标对象状态异常时，所述第一输入数据不包括所述目标对象对应的数据；所述第二数据分析网元根据所述第一输入数据生成所述目标分析类型对应的第一分析结果。在该实施方式中，由于第二数据分析网元接收到的目标对象的状态分析结果，可以表征目标对象是否处于异常状态，而若目标对象处于异常状态，则该目标对象对应的数据可能出现错误，此时，第二数据分析网元所获取的目标分析类型对应的第一输入数据中可以不包括该目标对象所对应的数据，这使得第二数据分析网元基于该第一输入数据所生成的目标分析类型对应的第一分析结果可以不受错误的目标对象对应的数据的影响，从而可以提高第一分析结果的正确性。
其中，当目标对象包括多种对象时，第一数据分析网元可以分别检测每种对象的状态是否存在异常。
在一种可能的实施方式中，所述第二数据分析网元向第一网元发送所述第一分析结果和/或第一指示信息，所述第一指示信息用于指示所述第一网元停用第二分析结果或将所述第二分析结果对应的置信度下调至第一置信度，所述第二分析结果是由所述第二数据分析网元根据第二输入数据生成并向所述第一网元发送的所述目标分析类型的分析结果，所述第二输入数据包括所述目标对象对应的数据。在该实施方式中，第二数据分析网元可以将生成的第一分析结果发送给第一网元，以便于第一网元根据正确性更高的第一分析结果(相对于基于包含目标对象对应的数据所生成的第二分析结果)执行相应的处理操作，比如， 可以修改之前基于第二分析结果所执行的操作等。并且，由于第一网元之前所接收到的第二分析结果是基于包含处于异常状态的目标对象对应的数据所生成的，因此，第二数据分析网元也可以向第一网元发送第一指示信息，以指示第一网元其之前所接收到的第二分析结果的置信度下调，也即为该第二分析结果的可信程度降低，这样，第一网元可以根据置信度下调后的第二分析结果执行相应的处理，比如，当第二分析结果的置信度由90％下调至30％时，可以停用该第二分析结果。特别的，若基于较多数量的对象所对应的数据生成第二分析结果，而处于异常状态的目标对象的数量较少，则第二分析结果的置信度下调幅度较低，比如由90％下调至89％等，此时，第一网元继续使用该第二分析结果执行相应处理。
在一种可能的实施方式中，所述第二数据分析网元向第一网元发送所述第一分析结果，包括：当所述第二数据分析网元确定所述第一分析结果与第二分析结果不同时，所述第二数据分析网元向所述第一网元发送所述第一分析结果。在该实施方式中，若第一分析结果与第二分析结果不同，说明目标对象对应的数据对于生成的分析结果的影响可能较大，比如，当分析结果具体为表征终端设备的业务质量高低的分析结果时，第一网元之前所接收到的第二分析结果可能表征终端设备的业务质量较高，而第一分析结果表征终端设备的业务质量较低，此时，第一网元可以基于接收到的第一分析结果提高为终端设备分配的网络资源，以提高终端设备的业务质量。
而在其它可能的实施方式中，也可以是第二数据分析网元在确定原先生成分析结果的输入数据中包括目标对象对应的数据，并且，该目标对象处于异常状态时，可以确定将生成的第一分析结果发送给第一网元。
在一种可能的实施方式中，方法还包括：所述第二数据分析网元获取所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息；所述第一输入数据不包括所述目标对象对应的数据，包括：所述第一输入数据不包括所述目标对象在所述第一时间信息和/或所述第一区域信息对应的数据。在该实施方式中，第一数据分析网元在获取生成目标对象的状态分析结果所需的输入数据时，可以获取与该第一时间信息和/或第一区域信息对应的输入数据，并基于该输入数据生成第一时间信息和/或第一区域信息对应的目标对象的状态分析结果。其中，第一时间信息可以包括开始时间、结束时间以及持续时长中的任意一种或多种信息，第一区域信息可以表现为网络区域和/或地理区域。
在一种可能的实施方式中，所述方法还包括：所述第二数据分析网元向所述第一网元发送所述第一指示信息对应的第二时间信息和/或第二区域信息。在该实施方式中，第二数据分析网元所发送的第一指示信息可以对应于特定的时间段或者特定的区域，从而可以降低第一分析结果在该时间段或者该区域范围内的置信度，而在其它时间段或者其它区域内的置信度无需降低。这样，第一网元在接收到该第二时间信息和/或第二区域信息后，可以确定过去是否根据第二分析结果以及其对应的置信度执行了错误的处理操作，或者，可以确定在哪个时间段和/或哪个区域停用该第二分析结果，以便提高第一网元所执行的处理操作的正确性。其中，第二时间信息，可以是由第二数据分析网元根据第一时间信息确定的，例如，第二时间信息所指示的时间段可以是第一时间信息所指示的时间段的子集等；或者，该第二时间信息所指示的时间段可以是第二数据分析网元进行预测的时间段。第二区域信息，可以是由第二数据分析网元根据第一区域信息确定的，例如，第二区域信息所指示的 区域可以是第一区域信息所指示的区域的子集等。
在一种可能的实施方式中，所述方法还包括：所述第二数据分析网元向所述第一网元发送所述第一分析结果所适用的第三时间信息和/或第三区域信息。在该实施方式中，第二数据分析网元向第一网元发送的第三时间信息，可以用于指示第一网元适合在哪个时间段内利用第一分析结果执行相应的处理，即该第一分析结果所适用的时间段；第二数据分析网元向第一网元发送的第三区域信息，可以用于指示第一网元适合在哪个区域利用第一分析结果执行相应处理，即第一分析结果所使用的区域。其中，第三时间信息，可以是由第二数据分析网元根据第一时间信息确定的，例如，第三时间信息所指示的时间段可以是第一时间信息所指示的时间段的子集等；第三区域信息，可以是由第二数据分析网元根据第一区域信息确定的，例如，第三区域信息所指示的区域可以是第一区域信息所指示的区域的子集等。
在一种可能的实施方式中，所述方法还包括：所述第二数据分析网元向所述第一网元发送第一异常原因，所述第一异常原因用于指示发送所述第一分析结果和/或所述第一指示信息的原因。在该实施方式中，第一网元可以基于该第一异常原因，确定因为何种缘故使得第二数据分析网元向第一网元发送第一分析结果和/或第一指示信息，例如，第一网元基于该第一异常原因可以确定下调第二分析结果对应的置信度是因为之前生成第二分析结果的第二输入数据中包括处于异常状态的目标对象的数据等，或者可以确定第二数据分析网元之前发送的第二分析结果不准确等。
在一种可能的实施方式中，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，包括：所述第二数据分析网元从已获取的所述目标分析类型对应的第三输入数据中删除所述目标对象对应的数据，得到所述第一输入数据；或者，所述第二数据分析网元取消从第二网元处订阅所述目标对象对应的数据，并接收来自第三网元的所述第一输入数据。在该实施方式中，第二数据分析网元获取不包括目标对象对应的数据的第一输入数据的方式，可以是将已获取的所有对象对应的第三数据中剔除处于异常状态的目标对象所对应的数据，这样，剔除后所剩余的数据即可作为用于生成第一分析结果的输入数据；或者，第二数据分析网元也可以是向网络中的相应网元取消订阅该目标对象对应的数据，这样，网络中的相应网元可以不再向第二数据分析网元提供该目标对象对应的数据，从而使得第二数据分析网元从网络中所获取的用于生成第一分析结果所需的输入数据中不包括该目标对象对应的数据。
在一种可能的实施方式中，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，包括：所述第二数据分析网元拒绝接收来自所述第一网元的所述目标对象对应的数据。在该实施方式中，第一网元仍然可以向第二数据分析网元发送目标对象对应的数据，但是，第二数据分析网元在确定目标对象处于异常状态后，可以拒绝接收该数据，从而第二数据分析网元所获取的作为生成第一分析结果的输入数据中可以不包括该目标对象对应的数据。
在一种可能的实施方式中，所述目标对象的状态分析结果包括对所述目标对象的状态预测分析结果。在该实施方式中，目标对象的状态分析结果也可以是通过对目标对象的状态进行预测而得到的。比如，可以根据目标对象在历史一段时间内所产生的温度数据，通 过相应的分析可以预测出，由于该目标对象的设备温度始终处于持续增长并且没有减缓的状态，因此，该目标对象在未来一段时间段内可能会因为温度上升过高会发生故障等。
当然，在其它可能的实施方式中，该目标对象的状态分析结果也可以是包括对目标对象的状态进行统计而得到的结果。比如，可以根据目标对象在历史一段时间段所产生的温度数据，确定其在该时间段内的温度超过正常情况下的温度上限，则可以确定该目标对象因为温度过高而处于异常状态
在一种可能的实施方式中，所述目标对象的状态分析结果包括所述目标对象历史状态的分析结果，和/或，所述目标对象未来状态的分析结果。在该实施方式中，目标对象的状态分析结果可以是对目标对象在历史状态是否异常进行分析所得到的结果，也可以是对目标对象在未来状态是否异常进行预测而得到的结果。
在一种可能的实施方式中，所述方法还包括：所述第二数据分析网元接收来自所述第一数据分析网元的所述目标对象的状态分析结果对应的第二置信度；所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，包括：当所述第二数据分析网元确定所述第二置信度大于第一阈值，且根据所述目标对象的状态分析结果确定所述目标对象状态异常时，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据。在该实施方式中，关于目标对象的状态分析结果，也可以是具有相应的置信度(即前述第二置信度)。则，第二数据分析网元可以根据该目标对象的状态分析结果对应的第二置信度确定是否对生成第一分析结果的输入数据进行调整。比如，当目标对象的状态分析结果表征目标对象处于异常状态，但是，该目标对象的状态分析结果的置信度为30％时，表明该目标对象处于异常状态的可能性仅有30％，而目标对象处于正常状态的可能性为70％，即目标对象处于正常状态的可能性较大，此时，第二数据分析网元也可以无需调整生成第一分析结果的输入数据，即生成第一分析结果的输入数据中可能包含该目标对象对应的数据。
在一种可能的实施方式中，所述方法还包括：所述第二数据分析网元向所述第一网元发送所述第一分析结果对应的第三置信度，所述第三置信度是由所述第二数据分析网元基于所述第一输入数据和所述第二置信度确定的。在该实施方式中，第二数据分析网元向第一网元反馈的第一分析结果还可以具有相应的置信度，这样，当第一分析结果的置信度较大时，表明该第一分析结果的可信度较高，则第一网元基于该第一分析结果进行相应的处理操作；而当第一分析结果的置信度较小时，表明该第一分析结果的可信度较低，则第一网元可以停用该第一分析结果。
在一种可能的实施方式中，第二数据分析网元接收来自第一数据分析网元的目标对象的状态分析结果，包括：所述第二数据分析网元从第四网元中获取所述目标对象的状态分析结果，所述目标对象的状态分析结果是由所述第一数据分析网元发送给所述第四网元。在该实施方式中，第一数据分析网元在生成目标对象的状态分析结果后，可以将其发送至第四网元(如UDM、UDR网元等)中进行存储，而当第二数据分析网元需要获取该目标对象的状态分析结果时，可以直接从该第四网元中进行获取，从而第四网元可以为网络中的各个数据分析网元提供统一的接口来获取其所需的对象的状态分析结果。
在一种可能的实施方式中，所述方法还包括：所述第二数据分析网元向所述第一数据 分析网元发送第二指示信息，所述第二指示信息用于指示所述第一数据分析网元在所述目标对象状态异常时反馈所述目标对象的状态分析结果。在该实施方式中，第一数据分析网元可以基于该第二指示信息，在确定目标对象处于异常状态时才向第二数据分析网元反馈目标对象的状态分析结果，而在确定目标对象处于正常状态时不进行状态分析结果的反馈，相应的，第二数据分析网元在接收到目标对象的状态分析结果可以确定目标对象处于异常状态，而在没有接收到目标对象的状态分析结果时确定目标对象处于正常状态，这样可以减少第一数据分析网元与第二数据分析网元之间的数据通信次数以及数据量，节省网络资源。
在一种可能的实施方式中，所述方法还包括：所述第二数据分析网元向第五网元发送查询请求，所述查询请求用于查询生成所述目标对象的状态分析结果的所述第一数据分析网元；所述第二数据分析网元接收所述第五网元响应于所述查询请求而发送的所述第一数据分析网元的标识信息；所述第二数据分析网元根据所述第一数据分析网元的标识信息，向所述第一数据分析网元发送第一请求消息，所述第一请求消息用于向所述第一数据分析网元请求所述目标对象的状态分析结果。在该实施方式中，由于网络中的不同数据分析网元可以具有不同的功能，或者负责不同网络区域的数据分析处理工作，因此，在第二数据分析网元还可以查询具体是哪个数据分析网元提供生成目标对象的状态分析结果的服务。作为一种示例，该查询请求中可以包括切片标识、服务区域标识、异常类型标识、异常子类型标识等信息中的一种或多种。
在一种可能的实施方式中，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知状态。其中，当状态指示信息指示未知状态时，表明对于目标状态所处的状态是否异常未知。
在一种可能的实施方式中，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常程度、异常趋势。在该实施方式中，目标对象的状态分析结果除了可以指示目标对象的状态是否发生异常以外，还可以包括其他更多的信息，比如，当其包括异常趋势时，第一网元可以根据该异常趋势确定第一分析结果所适用的时间段等。
在一种可能的实施方式中，所述网络分域包括接入网域、核心网域、传输网域中的一种或多种。
在一种可能的实施方式中，所述目标对象包括目标网络切片的目标对象。在该实施方式中，目标对象具体可以是某个网络切片内的对象，则第二数据分析网元在向第一数据分析网元请求目标对象对应的状态分析结果时，可以向第一数据分析网元发送目标网络切片的相关信息，如标识等，以便第一数据分析网元基于该目标网络切片的相关信息确定目标网络切片，从而可以将该目标网络切片内的对象作为目标对象，并进一步向第二数据分析网元反馈该目标对象对应的状态分析结果。
在一种可能的实施方式中，所述网络切片包括切片实例、切片子实例。
第二方面，本申请实施例还提供了一种通信方法，所述方法包括：第一数据分析网元获取目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端 设备中的一种或多种；所述第一数据分析网元向第二数据分析网元发送所述目标对象的状态分析结果。在该实施方式中，第一数据分析网元可以获得目标对象的状态分析结果，并将其发送给第二数据分析网元，以便于第二数据分析网元根据该目标对象的状态分析结果确定是否对生成目标分析类型对应的分析结果的输入数据进行调整，以使得第二数据分析网元基于不包括目标对象对应的数据的输入数据所生成的分析结果可以不受错误的目标对象对应的数据的影响，进而可以提高第一分析结果的正确性。
在一种可能的实施方式中，所述方法还包括：所述第一数据分析网元向所述第二数据分析网元发送所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息。其中，第一时间信息可以包括开始时间、结束时间以及持续时长中的任意一种或多种信息，第一区域信息可以表现为网络区域和/或地理区域。
在一种可能的实施方式中，所述目标对象的状态分析结果包括对所述目标对象历史状态的分析结果，或者，所述目标对象未来状态的分析结果。在该实施方式中，目标对象的状态分析结果可以是对目标对象在历史状态是否异常进行分析所得到的结果，也可以是对目标对象在未来状态是否异常进行预测而得到的结果。
在一种可能的实施方式中，所述方法还包括：所述第一数据分析网元向所述第二数据分析网元发送所述目标对象的状态分析结果对应的第二置信度。在该实施方式中，关于目标对象的状态分析结果，也可以是具有相应的置信度(即前述第二置信度)。第一数据分析网元将第二置信度发送给第二数据分析网元后，第二数据分析网元可以根据该目标对象的状态分析结果对应的第二置信度确定是否对生成第一分析结果的输入数据进行调整。
在一种可能的实施方式中，所述方法还包括：所述第一数据分析网元接收来自所述第二数据分析网元的第二指示信息；所述第一数据分析网元向第二数据分析网元发送所述目标对象的状态分析结果，包括：所述第一数据分析网元基于所述第二指示信息，在确定所述目标对象状态异常时，向所述数据分析网元发送所述目标对象的状态分析结果。在该实施方式中，第一数据分析网元基于该第二指示信息，仅在确定目标对象处于异常状态时向第二数据分析网元发送目标对象的状态分析结果，而在确定目标对象处于正常状态时，不向第二数据分析网元反馈目标对象的状态分析结果，这样，第一数据分析网元与第二数据分析网元之间的数据通信次数以及数据量可以得到减少，从而可以节省网络资源。
在一种可能的实施方式中，第一数据分析网元获取目标对象的状态分析结果，包括：所述第一数据分析网元接收来自所述第二数据分析网元的第一请求消息，所述第一请求消息用于向所述第一数据分析网元请求所述目标对象的状态分析结果；所述第一数据分析网元响应所述第一请求消息，生成所述目标对象的状态分析结果。
在一种可能的实施方式中，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知状态。
在一种可能的实施方式中，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常程度、异常趋势。在该实施方式中，目标对象的状态分析结果除了可以指示目标对象的状态是否发生异常以外，还可以包括其他更多的信息，比如，当其包括异常趋势时，第一网元可以根据该异常趋势确定第一分析 结果所适用的时间段等。
在一种可能的实施方式中，所述目标对象包括目标网络切片的目标对象。在该实施方式中，目标对象具体可以是某个网络切片内的对象，则第二数据分析网元在向第一数据分析网元请求目标对象对应的状态分析结果时，可以向第一数据分析网元发送目标网络切片的相关信息，如标识等，以便第一数据分析网元基于该目标网络切片的相关信息确定目标网络切片，从而可以将该目标网络切片内的对象作为目标对象，并进一步向第二数据分析网元反馈该目标对象对应的状态分析结果。
在一种可能的实施方式中，所述网络切片包括切片实例、切片子实例。
在一种可能的实施方式中，所述网络分域包括接入网域、核心网域、传输网域中的一种或多种。
第三方面，本申请实施例还提供了一种通信装置，包括：接收单元，用于接收来自第一数据分析网元的目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；
处理单元，用于根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，其中，当所述目标对象的状态分析结果指示所述目标对象状态异常时，所述第一输入数据不包括所述目标对象对应的数据；根据所述第一输入数据生成所述目标分析类型对应的第一分析结果。
在一种可能的实施方式中，所述装置还包括：发送单元，用于向第一网元发送所述第一分析结果和/或第一指示信息，所述第一指示信息用于指示所述第一网元停用第二分析结果或将所述第二分析结果对应的置信度下调至第一置信度，所述第二分析结果是由所述第二数据分析网元根据第二输入数据生成并向所述第一网元发送的所述目标分析类型的分析结果，所述第二输入数据包括所述目标对象对应的数据。
在一种可能的实施方式中，所述发送单元，具体用于当所述第二数据分析网元确定所述第一分析结果与第二分析结果不同时，所述第二数据分析网元向所述第一网元发送所述第一分析结果。
在一种可能的实施方式中，所述接收单元，还用于接收所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息；
所述第一输入数据不包括所述目标对象对应的数据，包括：所述第一输入数据不包括所述目标对象在所述第一时间信息和/或所述第一区域信息对应的数据。
在一种可能的实施方式中，其特征在于，所述发送单元，还用于向所述第一网元发送所述第一指示信息对应的第二时间信息和/或第二区域信息。
在一种可能的实施方式中，其特征在于，所述发送单元，还用于向所述第一网元发送所述第一分析结果所适用的第三时间信息和/或第三区域信息。
在一种可能的实施方式中，所述发送单元，还用于向所述第一网元发送第一异常原因，所述第一异常原因用于指示发送所述第一分析结果和/或所述第一指示信息的原因。
在一种可能的实施方式中，所述处理单元，具体用于从已获取的所述目标分析类型对应的第三输入数据中删除所述目标对象对应的数据，得到所述第一输入数据；或者，取消从第二网元处订阅所述目标对象对应的数据，并接收来自第三网元的所述第一输入数据。
在一种可能的实施方式中，所述目标对象的状态分析结果包括对所述目标对象的状态预测分析结果。
在一种可能的实施方式中，所述接收单元，还用于接收来自所述第一数据分析网元的所述目标对象的状态分析结果对应的第二置信度；
所述处理单元，具体用于当所述第二数据分析网元确定所述第二置信度大于第一阈值，且根据所述目标对象的状态分析结果确定所述目标对象状态异常时，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据。
在一种可能的实施方式中，所述发送单元，还用于向所述第一网元发送所述第一分析结果对应的第三置信度，所述第三置信度是由所述第二数据分析网元基于所述第一输入数据和所述第二置信度确定的。
在一种可能的实施方式中，所述接收单元，具体用于从第四网元中获取所述目标对象的状态分析结果，所述目标对象的状态分析结果是由所述第一数据分析网元发送给所述第四网元。
在一种可能的实施方式中，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知状态。
在一种可能的实施方式中，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常程度、异常趋势。
第三方面所描述的通信装置，对应于第一方面所描述的通信方法，因此，第三方面的各种可能的实施方式以及其有益效果可以参照第一方面中对应实施方式以及有益效果的相关描述，在此不做赘述。
第四方面，本申请实施例还提供了一种通信装置，所述装置包括：处理单元，用于获取目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；发送单元，用于发送所述目标对象的状态分析结果。
在一种可能的实施方式中，所述发送单元，还用于向所述第二数据分析网元发送所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息。
在一种可能的实施方式中，所述目标对象的状态分析结果包括对所述目标对象历史状态的分析结果，或者，所述目标对象未来状态的分析结果。
在一种可能的实施方式中，所述发送单元，还用于向所述第二数据分析网元发送所述目标对象的状态分析结果对应的第二置信度。
在一种可能的实施方式中，所述装置还包括：接收单元，用于接收来自所述第二数据分析网元的第二指示信息；所述发送单元，具体用于基于所述第二指示信息，在确定所述目标对象状态异常时，向所述数据分析网元发送所述目标对象的状态分析结果。
在一种可能的实施方式中，所述处理单元，具体用于响应利用接收单元接收到的来自所述第二数据分析网元的第一请求消息，生成所述目标对象的状态分析结果，所述第一请求消息用于向所述第一数据分析网元请求所述目标对象的状态分析结果。
在一种可能的实施方式中，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知 状态。
在一种可能的实施方式中，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常程度、异常趋势。
在一种可能的实施方式中，所述目标对象包括目标网络切片的目标对象。
在一种可能的实施方式中，所述网络切片包括切片实例、切片子实例。
在一种可能的实施方式中，所述网络分域包括接入网域、核心网域、传输网域中的一种或多种。
第四方面所描述的通信装置，对应于第二方面所描述的通信方法，因此，第四方面的各种可能的实施方式以及其有益效果可以参照第二方面中对应实施方式以及有益效果的相关描述，在此不做赘述。
第五方面，本申请实施例还提供了一种通信装置，包括：处理器和存储器；所述存储器，用于存储指令或计算机程序；所述处理器，用于执行所述指令或计算机程序，使得上述第一方面中任一种实施方式所述的方法至第二方面中任一种实施方式所述的方法被执行。
第五方面所描述的通信装置，对应于第一方面至第二方面所描述的通信方法，因此，第五方面的各种可能的实施方式以及其有益效果可以参照第一方面至第二方面中对应实施方式以及有益效果的相关描述，在此不做赘述。
第六方面，本申请实施例还提供了一种计算机可读存储介质，包括指令或计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面中任一种实施方式所述的方法至第二方面中任一种实施方式所述的方法。
第六方面所描述的计算机可读存储介质，对应于第一方面或第二方面所描述的通信方法，因此，第六方面的各种可能的实施方式以及其有益效果可以参照第一方面至第二方面中对应实施方式以及有益效果的相关描述，在此不做赘述。
第七方面，本申请实施例还提供了一种通信系统，该系统可以包括上述第一方面中任一实施方式所述的第二数据分析网元以及上述第二方面中任一实施方式所述的第一数据分析网元。
第七方面所描述的通信系统，对应于第一方面或第二方面所描述的通信方法，因此，第七方面的各种可能的实施方式以及其有益效果可以参照第一方面或第二方面中对应实施方式以及有益效果的相关描述，在此不做赘述。
第八方面，本申请实施例提供一种芯片，该芯片包括处理器和通信接口，通信接口和处理器耦合，处理器用于运行计算机程序或指令，以实现第一方面至第二方面中各种可能的实现方式中所描述的一种通信方法。通信接口用于与芯片之外的其它模块进行通信。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请中记载的一些实施例，对于本领域普通技术人员来讲，还可以根据这些附图获得其他的附图。
图1为本申请实施例中一种示例性通信系统的架构示意图；
图2为本申请实施例中一种通信方法的流程示意图；
图3为本申请实施例中结合具体场景的一种通信方法的信令交互示意图；
图4为本申请实施例中结合具体场景的又一种通信方法的信令交互示意图；
图5为本申请实施例中一种通信装置的结构示意图；
图6为本申请实施例中又一种通信装置的结构示意图；
图7为本申请实施例中一种通信装置的硬件结构示意图；
图8为本申请实施例中一种芯片的硬件结构示意图。
具体实施方式
本申请实施例可以应用于如图1所示的示例性通信系统。该通信系统可以是支持第四代(fourth generation，4G)接入技术的通信系统，例如长期演进(long term evolution，LTE)接入技术；或者，该通信系统也可以是支持第五代(fifth generation，5G)接入技术通信系统，例如新无线(new radio，NR)接入技术；或者，该通信系统还可以是支持多种无线技术的通信系统，例如支持LTE技术和NR技术的通信系统。另外，该通信系统也可以适用于面向未来的通信技术。
在该通信系统中，终端通过接入网(access network,AN)网元或者无线接入网(radio access network，RAN)接入核心网。其中，终端包括但不限于：用户设备(user equipment,UE)，用户单元、用户站、移动站、移动台、远方站、远程终端设备、移动终端设备、用户终端设备、终端设备、无线通信设备、用户代理、用户装置、蜂窝电话、无绳电话、会话启动协议(session initiation protocol，SIP)电话、无线本地环路(wireless local loop，WLL)站、个人数字处理(personal digital assistant，PDA)、具有无线通信功能的手持设备、计算设备、连接到无线调制解调器的处理设备、车载设备、可穿戴设备、物联网中的终端设备设备、家用电器、虚拟现实设备、未来5G网络中的终端设备设备或者未来演进的公共陆地移动网络(public land mobile network，PLMN)中的终端设备等。在本申请的实施例中，以终端为UE进行举例说明。
AN(或者RAN)可以是与终端进行通信的网元。AN(或RAN)可以为特定的地理区域提供通信覆盖，并且可以与位于该覆盖区域(小区)内的用户设备进行通信。AN(或RAN)可以与任意数目UE通信。AN(或RAN)与UE之间可以有多个空口连接，例如，AN(或RAN)与UE之间存在两个空口连接，分别用于传输数据流A和数据流B。AN(或RAN)可以支持不同制式的通信协议，或者可以支持不同的通信模式。例如，AN(或RAN)以是演进型基站(evolved node B，eNodeB)，或者是无线保真接入点(wireless fidelity access point，WiFi AP)、或者是全球微波接入互操作性基站(worldwide interoperability for microwave access base station，WiMAX BS)，或者是云无线接入网络(cloud radio access network，CRAN)中的无线控制器，或者该接入网网元可以为未来5G网络中的接入网网元或者未来演进PLMN中的接入网网元等。
核心网可以包括：用户面功能(user plane function，UPF)网元、网络切片选择功能(network slice selection function，NSSF)、网络能力开放功能(network exposure function，NEF)、网络存储功能(network repository function，NRF)、策略控制功能(policy control function，PCF)网元、统一数据管理功能(unified data management，UDM)网 元、网络数据分析功能(network data analytics function，NWDAF)网元、鉴权服务功能(authentication server function，AUSF)网元、接入管理功能(access management function，AMF)网元、会话管理功能(session management function，SMF)网元以及服务控制点(service control point，SCP)。通过AN(或RAN)和用户面功能网元，可以实现UE和数据网络(data network，DN)之间用户面数据的传输。
其中，AMF网元，可以用于为UE提供移动性管理、或者接入授权以及鉴权等功能。
应用功能(application function，AF)网元，可分为运营商AF网元和第三方AF网元，区别在于是否由运营商部署。第三方AF网元包括非运营商部署的各种应用相关服务器，如铁路系统相关AF，医疗系统相关AF、OTT(over the top)业务相关AF，政府社区相关AF(如社区服务app等)。
NEF网元，可以用于将通信运营商网络的数据和服务向外部AF开放，或者反向将AF数据或服务向运营商开放。
NWDAF网元，可以具备以下一种或多种功能：数据收集、训练、分析、推理功能。例如NWDAF网元用于收集来自网络网元、第三方业务服务器、终端设备或网管系统中的相关数据，并基于相关数据做分析训练，从而向网络网元、第三方业务服务器、提供终端设备或网管系统提供相应的数据分析结果，该分析结果可协助网络选择业务的服务质量参数，或协助网络执行流量路由，或协助网络选择背景流量传输策略等。其中，NWDAF网元可以在网络中作为独立网元进行单独设置，也可以是将NWDAF网元与其他网元合设，如NWDAF网元功能设置于SMF网元、AMF网元上。网络中可以包含一个或者多个NWDAF网元，不同NWDAF网元之间可以具有不同的数据类型分析功能，当然，也可以具有相同数据类型分析的功能。
其他NF(网络功能)，即指网络中的其它节点或物理设备，可以具备以下一种或多种功能：为UE接入网络、进行会话、鉴权认证、策略控制等提供相应的功能支持，也会产生相应的网络数据。例如上述AMF、SMF、UDM等都是NF的一种实例。
终端与网元以及不同网元之间可以通过相应的业务接口或者点到点的接口进行通信，如UE可以通过N1接口与AMF网元进行通信，AN可以通过N3接口与UPF网元进行通信等(诸如N2、N4、N6以及N9等点到点的接口类似)；又如，AMF网元可以通过业务接口Namf接口与网络中的其他网元进行通信，AF网元可以通过业务接口Naf接口与其它网元进行通信等，其余在此不再赘述。
其中，在图1所示的通信系统中，各组成网元的功能仅为示例性的，各个组成网元在应用于本申请的实施例中时，并非全部功能都是必需的。需要说明的是，图1所示的通信系统仅是本申请实施例提供的一个通信系统示例，本申请实施例可以应用于任何可适用的通信系统中，而不局限于上述图1所示的通信系统。
在图1所示的通信系统中，可以包括至少两个NWDAF网元，如图1中的NWDAF1网元以及NWDAF2网元，当然，在通信系统也可以包括三个以上(包括三个)的NWDAF等。NWDAF1网元所生成的分析结果可以发送给NWDAF2，NWDAF2可以根据NWDAF1发送的分析结果对自身的输入数据做出调整，并基于调整后的输入数据生成相应的分析结果，以提高NWDAF2所生成的分析结果的准确性。当通信系统中包括第三个NWDAF网元、第四个NWDAF网元等时， NWDAF1网元也可以将生成的分析结果同时发送给第三个NWDAF网元、第四个NWDAF网元，以便其它NWDAF网元基于所接收到的分析结果对自身的输入数据进行相应调整。
为使本申请的上述目的、特征和优点能够更加明显易懂，下面将结合附图对本申请实施例中的各种非限定性实施方式进行示例性说明。显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本申请保护的范围。
参阅图2，图2示出了本申请实施例中一种通信方法的流程示意图，该方法可以应用于图1所示的通信系统中，也可以是应用于其它可适用的通信系统中。当应用于图1所示的通信系统中时，本实施例中的第一数据分析网元可以是图1所示的通信系统中的NWDAF1网元、第二数据分析网元可以是该通信系统中的NWDAF2网元，当然，数据分析网元也可以是网络中其他具有数据分析能力的网元，如管理数据分析功能(management data analysis function，MDAF)网元；第一网元可以是通信系统中除NWDAF网元之外的其它网元，如AF网元、AMF网元、UDM网元、RAN网元、UE等，第一网元可以与数据分析网元可以在网络中合设或独立部署。该方法具体可以包括：
S201：第一数据分析网元获取目标对象的状态分析结果，其中，该目标对象可以包括终端设备、网络设备、网络分域以及网络整域中的一种或多种，并且，目标对象的数量可以是一个，也可以是多个。
S202：第一数据分析网元向第二数据分析网元发送该目标对象的状态分析结果。
本实施例中，第一数据分析网元可以对通信系统中的目标对象的状态进行检测，并生成相应的状态分析结果，该目标对象的状态分析结果可以表征目标对象的状态是否存在异常。其中，目标对象，具体可以是通信系统中终端设备、网络设备、网络分域以及网络整域中的任意一种，也可以是其中的多种。特别的，当目标对象包括多种对象时，第一数据分析网元可以分别检测每种对象的状态是否存在异常。其中，网络分域可以包括接入网域、核心网域以及传输网域中的一种或多种。
作为一种示例，第一数据分析网元可以是被配置为主动对网络中的目标对象进行状态检测，以确定该目标对象是否处于异常状态。
而在另一种示例中，也可以是通信系统中的其它网元请求第一数据分析网元对目标对象的状态进行检测。例如，通信系统中第二数据分析网元可以向第一数据分析网元发送第一请求消息，以请求第一数据分析网元反馈目标对象的状态分析结果，其中，该第一请求消息可以携带有目标对象的标识。当然，请求第一数据分析网元对目标对象进行检测的网元除了可以是第二数据分析网元之外，还可以是AMF网元、UDM网元等其它网元，本实施例中对此并不进行限定。
可选的，第一数据分析网元所接收到的第一请求消息中，可以包括第一时间信息和/或第一区域信息，则第一数据分析网元在获取生成目标对象的状态分析结果所需的输入数据时，可以获取与该第一时间信息和/或第一区域信息对应的输入数据，并基于该输入数据生成第一时间信息和/或第一区域信息对应的目标对象的状态分析结果。例如，若第一时间信息指示2020年4月28日8:00至12:00的时间段，则第一数据分析网元可以从其它网元 处仅获取该时间段内的目标对象的相关数据，并基于该段时间内的数据生成相应目标对象的状态分析结果。
其中，第一时间信息(后文的第二时间信息、第三时间信息等类似)可以包括开始时间、结束时间以及持续时长中的任意一种或多种信息，第一区域信息(后文的第二区域信息、第三区域信息等类似)可以表现为网络区域(如某个或者某些网元所服务的网络区域，如小区cell、跟踪区TA等)和/或地理区域(如行政区域或者利用坐标值表征的物理区域等)。
另外，第一数据分析网元所接收到的第一请求消息中，也可以是包括网络切片的标识信息、业务类型、数据网络名称(data network name，DNN)、异常类型、异常子类型中的任意一种或多种。其中，当第一请求消息中包括业务类型时，表征向第一数据分析网元请求与该业务类型对应的目标对象进行状态分析，当第一请求消息中包括网络切片的标识信息时，表征向第一数据分析网元请求对处于该网络切片的标识所对应的网络切片内的目标对象进行状态分析，该网络切片可以包括切片实例、切片子实例等；当第一请求消息中包括DNN信息时，表征向第一数据分析网元请求对网络中的特定DNN中的目标对象进行状态分析；当第一请求消息中包括异常类型和/或异常子类型时，表征请求第一数据分析网元反馈该目标对象处于该异常类型和/或异常子类型所指示的异常状态。其中，异常类型例如可以是网络攻击、网络负荷超载、网络设备故障、网络资源不足、网络信号弱覆盖、终端设备行为异常等；同时，异常类型可以细分为多种异常子类型，例如，网络攻击这种异常类型可以细分为DDoS(distributed denial of service,分布式拒绝服务)攻击、网络篡改以及身份冒充等异常子类型，又比如，对于终端设备行为异常这种异常类型，可以细分为终端接入小区乒乓、终端疑似发起DDoS攻击、终端设备被异常唤醒、电池异常耗电、异常流量、异常空口链路断开等。
第一数据分析网元可以响应接收到的第一请求消息，并基于从第一请求消息中解析出的目标对象的标识，从网络中的相应网元(如RAN、AMF、SMF、UPF、OAM、NRF、UDM网元等)处获取该目标对象的相关数据，比如可以是第一数据分析网元向网络中的相应网元发送包括目标对象的标识的数据上报请求，以请求该网元向第一数据分析网元上报目标对象的相关信息，从而第一数据分析网元可以根据所接收到的数据进行分析处理，生成针对于目标对象的状态分析结果，并将所生成的状态分析结果发送给第二数据分析网元。举例来说，第一数据分析网元在接收到第一请求消息后，从网络中相应网元处获取的数据可以如表1所示：
表1
Figure PCTCN2021074345-appb-000001
Figure PCTCN2021074345-appb-000002
其中，NSSAI是指网络切片选择支撑信息(network slice selection assistance information)，S-NSSAI是指单网络切片选择支撑信息(single NSSAI)，NSI是指网络切片实例(network slice instance)；IMS是指IP多媒体子系统(IP multimedia subsystem)；TA是指跟踪区(tracking area)；IMSI是指国际移动用户识别码(international mobile subscriber identity)，GPSI是指一般公共订阅标识(generic public subscription identifier)。
当然，表1中描述的第一数据分析网元所采集的输入数据仅作为一种可选示例，在其他可能的实施方式中，也可以包括其它类型的数据，如终端设备注册成功率等；或者是包括上述表1中的部分类型数据，本实施例对此并不进行限定。
同时，当向第一数据分析网元请求不同异常类型的状态分析时，第一数据分析网元可以获取不同的输入数据。比如，当向第一数据分析网元请求分析的异常类型为网络设备故障时，第一数据分析网元获取的数据类型可以包含：切片标识、采样时间、区域信息、网络设备标识、网络设备负载、网络设备温度、网络设备资源使用率等。又比如，当向第一数据分析网元请求分析的异常类型为网络攻击时，第一数据分析网元获取的数据类型可以包括：切片标识、DNN、采样时间、区域信息、网络平均流量、网络峰值吞吐率、网络设备标识、网络设备负载、网络设备资源占用率、终端设备标识、终端设备重新连接率、终端 设备注册失败率(或注册失败的终端数目)、终端设备会话成功率(或终端设备会话失败率)等。
第一数据分析网元在获取到输入数据后，可以利用预先完成训练的模型分析推理得到目标对象的状态分析结果。其中，该模块可以是由第一数据分析网元根据相应的样本数据进行训练得到，也可以是由专用的模型训练平台完成训练后发送给该第一数据分析网元。所训练得到的模型可以表征输入数据与是否存在状态异常之间的关联关系，进一步的，还可以表征输入数据与异常类型、异常子类型、第二异常原因、异常程度、异常趋势之间的关联关系等。则，第一数据分析网元生成的目标对象的状态分析结果不仅可以包括指示目标对象的状态是否异常的信息，还可以包括异常类型、异常子类型、第二异常原因、异常程度以及异常趋势等信息中的任意一种或多种(此时，目标对象处于异常状态)。其中，异常趋势，是指目标对象发生状态异常时的异常发展情况，如可以是定义“上升”(表征异常情况加剧)、“下降”(表征异常状情况缓解)、“平稳”(表征异常情况稳定)以及“未知”等描述目标对象的异常情况的发展趋势。当然，目标对象的状态分析结果也可以是只包括指示目标对象状态是否异常的信息。在一些示例中，异常程度具体可以是定量值，例如，可以表现为“高”、“中”、“低”这种程度值，或者可以表现为具体的数值等。
可选的，目标对象的状态分析结果中，可以是利用其包括的状态指示信息，来指示目标对象处于正常状态还是异常状态。在一种可能的实施方式中，该状态指示信息还可以用于指示目标对象的状态为未知状态，即第一数据分析网元基于已获取的输入数据可能无法确定该目标对象处于正常状态还是异常状态，此时，可以认为目标对象的状态未知。在该实施方式中，第一数据分析网元向第二数据分析网元反馈的目标对象的状态，可以是正常状态、异常状态以及未知状态中的任意一种。
目标对象的状态分析结果，可以是目标对象历史状态的分析结果(statistics)。例如，当目标对象具体为某个或者某些网络设备时，第一数据分析网元所获取的输入数据中可以包括网络设备在过去一段时间内所具有的负载以及CPU占用率两种数据，这样，若第一数据分析网元确定该网络设备的负载低于第一预设值，而CPU占用率高于第二预设值，则可以推测该网络设备在过去的该段时间内处于异常状态，如可能受到网络攻击导致CPU占用率过高等。注意，对于目标对象当前状态的分析结果，虽然实时性要求较高，但属于目标对象已经发生状态，可归类为目标对象历史状态的分析结果。
又或者，目标对象的状态分析结果，也可以是目标对象未来状态的分析结果(prediction)。比如，当目标对象具体为某个或者某些终端设备时，第一数据分析网元所获取的输入数据中可以包括该终端设备在过去一段时间(也即为观测时间)的温度数据，虽然在该终端设备在观测时间内的温度数据属于正常状态，如一直小于60℃等，但是若该终端设备的温度数据在该观测时间段内处于持续递增状态，则第一数据分析网元基于该终端设备的当前温度递增趋势，可以预测该终端设备在未来某段时间内的温度超过60℃，从而第一数据分析网元可以预测该终端设备在未来一段时间内的温度数据发生异常，也即为预测该终端设备在未来一段时间内处于异常状态。
进一步的，目标对象的状态分析结果可以具有相应的置信度(为便于描述，以下称之为第二置信度)，第二置信度可以用于表征状态分析结果指示处于正常/异常状态的可信程 度，如第二置信度为70％时，表征目标对象处于正常(或异常)状态的可信程度为70％，相应的，目标对象处于异常(或正常)状态的可信程度为30％。
可选的，当第一请求消息中携带有第一时间信息和/或第一区域信息时，第一数据分析网元生成的目标对象的状态分析结果，即可以是第一时间信息和/或第一区域信息(观测区域信息)内数据所对应的状态分析结果
为便于理解第一数据分析网元所反馈的目标对象的状态分析结果，下面以目标对象的状态具体为网络攻击为例对该状态分析结果进行举例说明。
如表2所示，当第一数据分析网元针对于目标对象是否处于网络攻击状态进行分析时，目标对象的状态分析结果所包括的内容具体可以是：
表2
Figure PCTCN2021074345-appb-000003
进一步的，第一数据分析网元可以仅是在目标对象处于异常状态时，向第二数据分析网元反馈目标对象的状态分析结果，以通知第二数据分析网元目标对象的状态异常。作为 一种示例，第二数据分析网元(或者其它网元)可以向第一数据分析网元发送第二指示信息，该第二指示信息可以用于指示第一数据分析网元在目标对象的状态异常时反馈该目标对象的状态分析结果，示例性的，该第二指示信息可以被携带于前述第一请求消息，随第一请求消息一起发送给第一数据分析网元。这样，第一数据分析网元在确定目标对象处于异常状态时，向第二数据分析网元发送目标对象的状态分析结果；而当第一数据分析网元确定目标对象处于正常状态时，可以不向第二数据分析网元反馈目标对象的状态分析结果，相应的，第二数据分析网元在未接收到目标对象的状态分析结果时，可以默认目标对象处于正常状态，以此可以减少第一数据分析网元与第二数据分析网元之间的数据通信次数以及数据量，节省网络资源。
需要说明，通信网络中除了可以包括第一数据分析网元以及第二数据分析网元以外，还可以包括其它的数据分析网元，此时，第一数据分析网元在确定目标对象处于异常状态后，在将目标对象的状态分析结果反馈给第二数据分析网元的同时，还可以向其他数据分析网元反馈该目标对象的状态分析结果。
作为一种示例，第一数据分析网元可以直接将目标对象的状态分析结果反馈给第二数据分析网元，也可以是将目标对象的状态分析结果发送至第四网元，由第四网元存储该目标对象的状态分析结果；当第二数据分析网元需要获取目标对象的状态分析结果时，可以从第四网元处获取所需的状态分析结果。这样，第四网元可以存储网络中的各个数据分析网元所生成的不同目标对象的状态分析结果，并由该第四网元统一为其它数据分析网元提供其所需的状态分析结果。示例性的，该第四网元例如可以是UDM网元、用户数据库(user data repository，UDR)网元或者网络存储功能(network repository function，NRF)网元等。
进一步的，第二数据分析网元在向第一数据分析网元发送第一请求消息之前，还可以查询具体是哪个数据分析网元提供生成目标对象的状态分析的结果的服务，其中，不同数据分析网元所具有的功能可以不同，比如，部分数据分析网元可以分析确定目标对象是否处于网络攻击状态，而另一部分数据分析网元可以分析确定目标对象是否处于网络负荷超载状态等。
具体的，第二数据分析网元可以向第五网元发送查询请求，该查询请求用于请求第五网元查询生成目标对象的状态分析结果的第一数据分析网元，示例性的，该查询请求中可以携带有切片标识、服务区域标识、异常类型标识、异常子类型标识等信息中的一种或多种；第五网元可以响应该查询请求，从预先保存各个数据分析网元对应的属性信息(profile)中查找出与该查询请求相匹配的第一数据分析网元的标识信息，例如，查询出具有为目标对象分析是否处于网络攻击状态的第一数据分析网元等，并将该第一数据分析网元的标识信息发送给第二数据分析网元。这样，第二数据分析网元可以根据第一数据分析网元的标识信息，向该第一数据分析网元发送第一请求消息，以请求第一数据分析网元反馈目标对象的状态分析结果。示例性的，该第一数据分析网元的标识信息，例如可以是第一数据分析网元的IP地址，或者是第一数据分析网元的全量域名(fully qualified domain name，FQDN)等；第五网元例如可以是NRF网元或者UDM网元等
需要说明的是，本实施例中的第一数据分析网元与第二数据分析网元可以是分开部署 的不同网元，在其他可能的实施方式中，该第一数据分析网元与第二数据分析网元也可以是合设为同一个网元，此时，上述第一数据分析网元与第二数据分析网元之间的数据交互可以酌情进行省略。
S203：第二数据分析网元根据接收到的目标对象的状态分析结果获取目标分析类型对应的第一输入数据，其中，当目标对象的状态分析结果指示目标对象异常时，第一输入数据可以不包括目标对象对应的数据。
S204：第二数据分析网元可以根据该第一输入数据生成目标分析类型对应的第一分析结果。
由于目标对象的状态异常时，该目标对象对应的数据可能出现错误，这使得第二数据分析网元在基于包含错误的目标对象的数据进行相应的分析时，所得到的第一分析结果的正确性可能会受到影响，因此，本实施例中，第二数据分析网元在接收到来自第一数据分析网元的目标对象的状态分析结果后，若确定目标对象处于异常状态，如根据状态分析结果中的状态指示信息确定目标对象的状态异常等，则在生成相应的分析结果(以下称之为第一分析结果)时，可以确定生成第一分析结果的输入数据中是否包括目标对象的相关数据，若包括，则需要对输入数据进行调整，以使得该输入数据中不包括该目标对象的相关数据，而基于不包含错误数据的第一输入数据所得到的第一分析结果，其准确性也可以得到相应的提高；而若不包括，则可以无需调整输入数据。
其中，目标对象对应的数据可以是针对于目标对象生成相应分析结果所需的与目标对象相关的数据。例如，当目标对象为终端设备时，目标对象对应的数据可以是与生成终端设备的业务质量分析结果相关的数据，如终端设备在AF网元中所产生的service MOS、终端设备在AMF网元中所产生的位置信息、终端设备在UPF网元中所产生的业务流数据等；又例如，当目标对象为网络设备NF网元时，该目标对象对应的数据，可以是NF相关的数据，如NF load数据等。
第一分析结果，可以是第二数据分析网元为第一网元(即网络中其它网元)生成的目标分析类型对应的分析结果，如当第一网元为AMF网元时，该第一分析结果可以是第二数据分析网元应AMF网元的请求所生成的某区域内终端设备的移动轨迹分析结果，该移动轨迹分析结果可以表征该区域内终端对象的移动轨迹信息；或者，第一分析结果可以是第二数据分析网元应PCF网元的请求所生成的业务质量分析结果，该业务质量分析结果可以表征执行该业务的终端设备的业务质量高低等。相应的，第二数据分析网元所获取的输入数据，也即为用于分析该目标分析类型(如上述终端设备的移动轨迹分析类型或业务质量分析类型)的分析结果所需要的数据。本实施例中，第一网元可以是AMF网元或PCF网元，也可以是网络中的其它网元，如AF网元、UDM网元、RAN网元等。第二数据分析网元在生成第一分析结果后，可以将该第一分析结果发送给第一网元。
作为一种示例，第二数据分析网元在调整生成第一分析结果所对应的输入数据时，可以是通过数据剔除的方式实现。具体的：当第二数据分析网元需要生成第一分析结果时，第二数据分析网元可以从网络中的相应网元处获取生成第一分析结果所需的第三输入数据，该第三输入数据中包括该目标对象对应的数据，此时，若第二数据分析网元接收到目标对象的状态分析结果，并且该状态分析结果表征目标对象的状态异常时，第二数据分析 网元可以删除第三输入数据中有关目标对象对应的数据，得到第一输入数据(即为剩余的第三输入数据)，并基于该第一输入数据生成相应的第一分析结果。或者，当网络中的第二网元向第二数据分析网元反馈目标对象对应的数据时，第二数据分析网元可以拒绝接收第二网元所发送的目标对象对应的数据。
而在另一种示例中，可以是通过取消数据订阅的方式实现输入数据的调整。具体的，第二数据分析网元预先可以向网络中的相应网元发送订阅消息，以从网络中的相应网元处订阅生成第一分析结果所需的输入数据，其中，该输入数据中可以包括从第二网元处订阅的目标对象对应的数据，输入数据中包括的其它数据可以是从第三网元处订阅得到，该第三网元可以包括一个或者多个网元。当第二数据分析网元根据接收到的目标对象的状态分析结果确定目标对象的状态异常时，第二数据分析网元可以向第二网元发送取消订阅消息，该取消订阅消息可以用于指示第二网元停止向第二数据分析网元反馈该目标对象对应的数据，而第三网元在没有收到取消订阅消息的情况下，可以基于之前的订阅消息的指示，继续向第二数据分析网元反馈其它的输入数据，依次可以使得第二数据分析网元所获得第一输入数据中可以不包括目标对象对应的数据。
需要说明的是，第二数据分析网元向第二网元发送取消订阅消息后，可以取消订阅用于生成分析结果的第二网元上的所有对象对应的数据，该所有对象中包括用于处于异常状态的目标对象以及处于正常状态的对象。此时，在生成第一分析结果的过程中，第二数据分析网元的第一输入数据中可以不包括第二网元上的任何对象的数据。或者，第二数据分析网元向第二网元发送取消订阅消息后，所取消订阅的仅是处于异常状态的目标对象对应的数据，而对于第二网元上其它处于正常状态的对象对应的数据，第二网元依然可以将该处于正常状态的对象所对应的数据反馈给第二数据分析网元，并将其作为第一输入数据中的一部分。
在其它取消数据订阅的方式中，第二数据分析网元也可以是周期性或者根据需求发送订阅消息，则当第二数据分析网元根据接收到的目标对象的状态分析结果确定目标对象的状态异常时，第二数据分析网元可以不向第二网元发送针对于目标对象的数据订阅消息，而可以向第三网元发送数据订阅消息，以此获得不包括目标对象对应的数据的第一输入数据。
可选的，由于第二数据分析网元生成的所有分析结果对应的输入数据中可能并非均包含该目标对象对应的数据，因此，第二数据分析网元还可以先确定与异常状态的目标对象相关的分析结果或该分析结果对应的分析类型(如analytics ID)，换句话说，第二数据分析网元可以确定异常状态的目标对象对应的数据影响了哪些分析类型(如analytics ID)对应的分析结果。而若目标对象对应的数据并不参与目标分析类型对应的分析结果的生成时，第二数据分析网元可以无需对生成目标分析类型对应的分析结果进行调整。举例来说，当第二数据分析网元生成service MOS或者network performance这两种分析类型的分析结果时，由于NF网元故障与否可能并不影响这两种分析类型对应的分析结果的准确性，而某个(或某些)终端设备UE发生故障后可能会影响这两种分析类型对应的分析结果的准确性，因此，当处于异常状态的目标对象为该终端设备UE时，第二数据分析网元可以确定出对生成这两种分析类型的分析结果的输入数据进行调整，使其不包含该终端设备UE对应的 数据；而当处于状态的目标对象为NF网元时，第二数据分析网元可以无需对生成这两种分析类型的分析结果的输入数据进行调整。
示例性的，当第二数据分析网元所接收到的目标对象的状态分析结果对应于第一时间信息和/或第一区域信息时，若该状态分析结果中指示目标对象处于异常状态，表明目标对象在第一时间信息所指示的时间段和/或在第一区域信息所指示的区域内产生异常数据，从而第二数据分析网元在生成第一分析结果时，其第一输入数据可以不包括目标对象在该第一时间信息所指示的时间段内产生的数据和/或目标对象在该第一区域信息所指示的区域内产生的数据。
可选的，在第二数据分析网元生成第一分析结果的过程中，第二数据分析网元在接收到第一数据分析网元发送的目标对象的状态分析结果的同时，还接收到该状态分析结果对应的第二置信度，则第二数据分析网元还可以基于该第二置信度的大小，确定是否对输入数据进行调整。具体的，在第二数据分析网元根据目标对象的状态分析结果确定目标对象的状态异常的同时，状态分析结果对应的第二置信度也大于第一阈值，此时，第二数据分析网元可以确定对生成第一分析结果所需的输入数据进行调整，以使得调整后的输入数据中不包括目标对象对应的数据；而当状态分析结果对应的第二置信度不大于第一阈值时，即使目标对象的状态分析结果表征目标对象的状态异常，第二数据分析网元也可以不对输入数据进行调整。
第二数据分析网元在生成第一分析结果后，可以将该第一分析结果发送给第一网元，以便第一网元根据该第一分析结果执行相应的处理。比如，当第一分析结果具体为针对于某区域内终端设备移动轨迹的分析结果时，第一网元可以根据该区域内终端设备移动轨迹的分析结果确定该区域内是否存在与某设定终端设备的移动轨迹存在重叠的终端设备等；又比如，当第一分析结果具体为针对于业务类型的业务质量分析结果时，第一网元可以根据该业务类型的业务质量高低，确定是否为该业务类型调整对应的QoS策略等。本实施例中，对于第一网元以及第一网元根据第一分析结果所执行的处理过程，并不进行限定，其可以应用于任何可适用的场景中。
进一步的，第二数据分析网元还可以将目标对象的状态分析结果以及目标分析类型(如analytics ID)发送给第一网元，以便于第一网元根据目标对象处于异常状态的相关信息决定是否停用该目标分析类型对应的第二分析结果或者降低该目标分析类型对应的第二分析结果的置信度。比如，当第二数据分析网元生成service MOS或者network performance这两种分析类型的分析结果，并且，目标对象为终端设备UE时，第二数据分析网元可以将UE的状态分析结果以及service MOS或者network performance这两种分析类型(标识)一同发送给第一网元，以便第一网元执行相应的判断和处理操作。
在一种示例中，第一分析结果可以是第一网元请求第二数据分析网元生成的。具体的，第一网元可以向第二数据分析网元发送第二请求消息，该第二请求消息中可以携带有目标分析类型，例如可以是analytic ID等，该目标分析类型用于指示第二数据分析网元生成哪种类型的分析结果；第二数据分析网元可以基于第一网元发送的第二请求消息，生成该目标分析类型所对应的第一分析结果，并将该第一分析结果发送给第一网元。
在一种可能的实施方式中，第一分析结果，可以对应于特定的时间段和/或特定的区域。 示例性的，第二数据分析网元在向第一网元发送第一分析结果的同时，还可以向第一网元发送第一分析结果所适用的第三时间信息和/或第三区域信息，该第三时间信息可以用于指示第一网元适合在哪个时间段内利用第一分析结果执行相应处理操作，第三区域信息可以用于指示第一网元适合在哪个区域内利用第一分析结果执行相应处理操作。其中，第三时间信息，可以是由第二数据分析网元根据第一时间信息确定的，例如，第三时间信息所指示的时间段可以是第一时间信息所指示的时间段的子集等；第三区域信息，可以是由第二数据分析网元根据第一区域信息确定的，例如，第三区域信息所指示的区域可以是第一区域信息所指示的区域的子集等。
第二数据分析网元可以在每次生成分析结果后，都将该分析结果发送给第一网元。而在另一种实施方式中，第二数据分析网元在生成第一分析结果后，可以比较该第一分析结果与之前发送给第一网元的第二分析结果是否相同，若确定相同，则第二数据分析网元可以不用将第一分析结果发送给第一网元，相应的，第一网元继续基于第二分析结果执行相应的处理过程；若确定不相同，第一数据分析网元可以向第一网元发送该第一分析结果。在又一种实施方式中，第二数据分析网元也可以是在确定针对于相同目标分析类型的分析结果的第一输入数据不包括目标对象对应的数据时，可以向第一网元发送第一分析结果。
在一种可能的实施方式中，第二数据分析网元在向第一网元反馈第一分析结果的同时，还可以反馈第三置信度，该第三置信度可以用于指示该第一分析结果的可信程度。比如，当第一分析结果具体为业务类型的业务质量分析结果时，该第三置信度可以用于表征终端设备具有较高业务质量的可信程度。当第三置信度的值较大时，比如大于预设的第二阈值时，第一网元可以基于该第一分析结果执行相应的处理过程，而当该第三置信度的值较小时，比如，不大于第二阈值时，表征该第一分析结果的可信度不高，此时，第一网元执行相应的处理过程时可以不依据该第一分析结果，比如，可以基于第二数据分析网元之前所反馈第二分析结果执行相应的处理过程等。其中，第三置信度的大小，受第二置信度以及第一输入数据的影响，因此，可以是基于第二置信度以及生成第一分析结果所对应的第一输入数据确定第三置信度。
可选的，第二数据分析网元在确定目标对象的状态异常后，可以向第一网元发送第一指示信息，该第一指示信息用于指示第二数据分析网元停止使用第二分析结果或将第二分析结果对应的置信度下调至第一置信度，该第二分析结果为第二数据分析网元之前根据第二输入数据生成并发送给第一网元的目标分析类型的分析结果，该第二输入数据中可以包括有目标对象对应的数据。
由于第二数据分析网元之前反馈给第一网元的第二分析结果，是基于包括有目标对象对应的数据的第二输入数据生成的，而目标对象对应的数据可能因为目标对象的状态异常而产生错误，这使得基于该数据所生成的第二分析结果的准确性下降，相应的，该第二分析结果的可信程度也会降低。基于此，在一种可能的实施方式中，第二数据分析网元在确定目标对象处于异常状态时，可以向第一网元发送针对于第二分析结果的停用指示信息，以指示第一网元停用该第二分析结果，或者取消根据第二分析结果所执行的相关操作，或者拒绝继续根据第二分析结果进行相应操作。
而在另一种可能的实施方式中，第二数据分析网元在确定目标对象处于异常状态时， 通过向第一网元发送第一指示信息，可以降低第二分析结果的置信度，具体可以是将该第二分析结果对应的置信度下调至第一置信度，以便于第一网元可以基于第二分析结果的第一置信度，确定执行相应的处理过程。以第二分析结果为网络性能(network performance)分析结果为例，第一网元在接收到第二分析结果时确定其置信度为90％并且其表征网络的负载较高，因此，第一网元需要对网络进行增加资源的处理；而当第一网元接收到第一指示信息，并且该第一指示信息指示将第二分析结果的置信度下调至30％时，表征网络的负载高的概率较低，即，网络仍然大概率处于轻载的状态中，此时，第一网元可以暂不进行增加网络资源的处理。
进一步的，第二数据分析网元还可以向第一网元发送第一分析结果和/或第一指示信息的原因。具体的，第二数据分析网元可以向第一网元发送第一异常原因，该第一异常原因可以用于指示第二数据分析网元向第一网元发送第一分析结果和/或第一指示信息的原因，如该第一异常原因可以指示下调第二分析结果对应的置信度是因为之前生成第二分析结果的第二输入数据中包括处于异常状态的目标对象的数据等，或者第一异常原因可以指示第二数据分析网元之前发送的第二分析结果不准确等。进一步的，该第一异常原因还可以指示出第二分析结果异常的类型，如目标对象遭受DOS攻击等。
可选的，由于生成第二分析结果的第二输入数据中可能不仅包括目标对象对应的数据，还可能包括其他对象对应的数据，比如，第二数据分析网元可能根据50个对象(如某一网络切片中的50个对象等)对应的数据生成第二分析结果，而其中可能只有1个或者2个目标对象处于异常。当第二数据分析网元基于第一数量的对象所对应的数据生成第二分析结果，而第一数量的对象中存在第二数量的目标对象发生状态异常，此时，若第一数量远远大于第二数量，比如，第一数量与第二数量的差值或者比值大于第一值，则第二分析结果的准确性受到第一数量的目标对象的影响可能较小，则第二数据分析网元可以不向第一网元发送上述停用指示信息或者第一指示信息(或者即使发送第一指示信息，置信度下调的幅度也可以小于第二值)；而当第一数量与第二数量相距较小时，第二数据可以基于前述实施方式向第一网元发送停用指示信息或者第一指示信息。
可选的，第二数据分析网元在基于第一数据分析网元所生成的第一分析结果确定目标对象处于异常状态时，也可以是仅向第一网元发送上述停用指示信息或者第一指示信息，以通知第一网元停止使用之前第二数据分析网元所反馈的第二分析结果或者下调第二分析结果的置信度，而可以无需获取第一输入数据以及生成该第一分析结果。
或者，第二数据分析网元在确定目标对象处于异常状态后，可以不向第一网元发送停用指示信息或者第一指示信息，而可以是将该目标对象处于异常状态的相关信息发送给第一网元，该目标对象处于异常状态的相关信息例如可以是目标对象的标识信息、状态指示信息、异常类型、异常子类型、异常原因、异常程度、异常趋势等信息中的任意一种或多种，从而第一网元可以基于第二数据分析网元发送的信息确定是否停用第二分析结果或者降低第二分析结果的置信度。比如，当目标对象处于异常状态的相关信息中包括异常趋势并且该异常趋势表征为“上升”时，第一网元可以根据该异常趋势信息确定在8:00至10:00依然根据第二分析结果执行相应的处理操作，而在10:00至24:00(或者10:00以后的任意时间)停止使用该第二分析结果(如丢弃该第二分析结果等)或者拒绝继续采用该第二 分析结果执行相应的处理操作。
在一种可能的实施方式中，第二数据分析网元向第一网元发送的第一指示信息，可以对应于特定的时间段或者特定的区域，表征降低第一分析结果在该时间段或者该区域范围内的置信度，而在其它时间段或者其它区域内的置信度无需降低。具体实现时，第二数据分析网元在反馈第一指示信息的同时，还可以向第一网元发送第一指示信息对应的第二时间信息和/或第二区域信息，该第二时间信息用于指示下调后的第一置信度所对应的时间，即，在该第二时间信息所指示的时间段内第一分析结果的置信度为该第一置信度，而在其它时间段内第一分析结果的置信度可以高于该第一置信度，该第二区域信息用于指示该第一置信度对应的区域，即在该第二区域信息所指示的区域内第一分析结果的置信度为该第一置信度，而在其它区域内第一分析结果的置信度可以高于该第一置信度。这样，第一网元在接收到该第二时间信息和/或第二区域信息后，可以确定过去是否根据第二分析结果以及其对应的置信度执行了错误的处理操作，或者，可以确定在哪个时间段和/或哪个区域停用该第二分析结果，以便提高第一网元所执行的处理操作的正确性。
其中，第二时间信息，可以是由第二数据分析网元根据第一时间信息确定的，例如，第二时间信息所指示的时间段可以是第一时间信息所指示的时间段的子集等；或者，该第二时间信息所指示的时间段可以是第二数据分析网元进行预测的时间段，而第一分析结果在该第二时间信息所指示的时间段内可用。第二区域信息，可以是由第二数据分析网元根据第一区域信息确定的，例如，第二区域信息所指示的区域可以是第一区域信息所指示的区域的子集等。
或者，第二数据分析网元在反馈第一指示信息的同时，向第一网元发送第二时间信息，也可以用于指示第一分析结果可用的时间。例如，第二分析结果可以预测该第一分析结果未来可用的时间，如当第二数据分析网元确定的第一分析结果在未来三小时后可用，则可以将未来三小时后的起始时间作为该第一分析结果可用的时间，以便第一网元根据该第二时间信息所指示的可用时间执行该第一分析结果对应的操作。
本实施例中，第二数据分析网元接收到的来自第一数据分析网元的目标对象的状态分析结果，可以表征目标对象是否处于异常状态，由于目标对象处于异常状态时，该目标对象对应的数据可能出现错误，因此，当所述目标对象的状态分析结果指示所述目标对象状态异常时，第二数据分析网元所获取的目标分析类型对应的第一输入数据中可以不包括目标对象对应的数据，这使得第二数据分析网元基于该第一输入数据所生成的目标分析类型对应的第一分析结果可以不受错误的目标对象对应的数据的影响，从而可以提高第一分析结果的正确性。
上述实施例中，第二数据分析网元根据第一数据分析网元所确定出的状态分析结果调整输入数据，而第一网元根据第二数据分析网元所反馈的第一分析结果执行相应的处理操作。而在其他可能的实施例中，第一网元也可以是直接获取第一数据分析网元所生成的目标对象的状态分析结果，并基于该目标对象的状态分析结果确定目标对象是否存在异常；当确定目标对象存在异常时，第一网元可以执行如同上述第一网元和/或第二数据分析网元所执行的操作，比如，第一网元可以下调与该目标对象对应的数据相关的分析结果的置信度，或者，停用已获取的基于该目标对象对应的数据所生成的分析结果，或者，撤销或者 修改基于之前基于该分析结果所执行的相关操作等。
为了便于理解，下面结合目标对象具体为终端设备UE这一具体场景对本申请实施例的技术方案进行示例性说明。在该场景中，网络中NWDAF至少可以包括NWDAF1以及NWDAF2，当然，在其它场景中，还可以包括NWDAF3、NWDAF4等更多个NWDAF。需要说明的是，图3所示的场景实施例仅作为一种示例性说明，并不用于限定本申请实施例的技术方案在具体实施时局限于图3所示示例。例如，在其它实施例中，可以对图3所示的步骤和/或信息内容酌情增加、删减或替换，比如下述通知消息中可以包含终端设备的标识信息、状态分析结果、置信度、异常类型、时间信息、区域信息中的任意一种或多种，部分实施方式的具体实现细节可以参照前述方案实施例中相关之处描述。该方法具体可以是包括：
S301：NWDAF1生成UE的状态分析结果。
本实施例中，NWDAF1可以对一个或者多个UE进行监测，以确定该UE是否处于异常状态。具体实现时，NWDAF1可以从UE以及网络中的其它网元处(如AMF、SMF、UDM以及UDR等)获取UE的相关数据，并基于该数据为UE生成状态分析结果，该状态分析结果可以指示UE的状态是否异常。
其中，NWDAF1可以是被配置为主动对该UE进行状态监测，以便通过生成的状态分析结果确定该UE是否处于异常状态。当然，在其它可能的场景中，也可以是NWDAF2或者网络中的其它网元请求该NWDAF1监测UE的状态是否处于异常。
S302：NWDAF1向UDM/UDR发送通知消息，该通知消息中可以包括UE的标识信息、状态分析结果、异常类型、置信度、时间信息以及区域信息。
NWDAF1基于状态分析结果确定UE处于异常状态时，可以确定出该UE发生异常时的异常类型，并确定UE处于异常状态的置信度、UE处于异常状态的时间信息以及区域信息等。然后，NWDAF1可以基于这些信息生成通知消息，并将该通知消息发送给UDM/UDR中进行保存。其中，状态分析结果可以表现为正常或者异常，以体现UE是否处于异常状态，或者可以表现为数值，如利用“0”表征UE处于异常状态，用“1”表征UE处于正常状态等；异常类型可以包括DOS攻击、过于频繁的业务接入、异常数据流量、乒乓UE、异常UE位置、异常睡眠/苏醒、错误的目的地址等类型；时间信息，可以表征NWDAF1观测到UE处于异常状态时的观测时间，即在该观测时间段内UE处于正常状态还是异常状态；区域信息，可以表征NWDAF1确定UE处于正常状态或者异常状态对应的区域，如NWDAF1确定UE位于区域1时处于正常状态，位于区域2时处于异常状态等；置信度，可以表征NWDAF1确定UE处于正常状态或者异常状态的可信程度，其可以表现为等级形式，如“高”、“中”、“低”等，其中，“高”表征NWDAF1确定UE处于异常状态的可信程度较高，而“低”表征NWDAF1确定UE处于异常状态的可信程度较低，或者，可以表现为数值，如“3”、“2”、“1”等，其中，“3”表征NWDAF1确定UE处于异常状态的可信程度较高，而“1”表征NWDAF1确定UE处于异常状态的可信程度较低。
当NWDAF1基于状态分析结果确定UE处于正常状态时，NWDAF1向UDM/UDR发送的通知消息中可以仅包括UE的标识、状态分析结果、置信度、时间信息以及区域信息等。
在进一步可能的实施方式中，NWDAF1可以仅在确定UE处于异常状态时，向UDM/UDR 发送通知消息，而在确定UE处于正常状态时不发送通知消息，从而可以减少NWDAF1发送的数据量，也减少了UDM/UDR存储的数据量，从而可以降低网络资源的消耗。
S303：UDM/UDR保存通知消息。
其中，UDM/UDR保存通知消息，具体可以是保存该通知消息中所包括的UE的标识信息、状态分析结果、异常类型、置信度、时间信息以及区域信息。具体实现时，UDM/UDR可以将该通知消息保存在UE的上下文数据中或者签约数据中。
在其他可能的实施例中，当目标对象具体为网络设备时，如NF网元，NWDAF1可以向NRF网元发送针对于该网络设备的通知消息，并将该通知消息保存于NRF网元中，相应的，当NWDAF2需要获取该网络设备的状态分析结果时，NWDAF2可以向NRF网元请求该网络设备的状态分析结果。
S304：NWDAF2向UDM/UDR发送请求消息，该请求消息用于请求UE的状态分析结果。
当NWDAF2生成目标分析类型对应的分析结果所需的输入数据中包括UE对应的数据，或者NWDAF2确定需从数据提供方(如AF、NF、UE等)收集UE的样本数据作为训练数据时，NWDAF2可以向UDM/UDR发送请求消息，以请求UDM/UDR反馈UE的状态分析结果，以便NWDAF2确定UE是否处于异常状态。比如，在一种可能的场景中，NWDAF2需要针对某特定用户或群组做相关分析训练工作(例如分析一个或者多个UE的移动轨迹信息)，则NWDAF2可以获取该特定用户或群组的样本数据作为训练数据，或者，获取该特定的用户或群组的其他分析结果作为输入数据，而在此之前，NWDAF2可以先请求获取该特定用户或群组的UE的状态分析结果，以确定UE是否处于异常状态，请求消息中包含该特定用户对应的UE标识信息或群组对应的UE群组标识信息。又比如，在一种可能的场景中，NWDAF2需要分析网络粒度(如分析网络负荷)、或区域粒度(如分析区域内用户数量)、或业务粒度(如分析业务体验)的分析工作，则NWDAF2可以获取网络内或区域内大量的用户的样本数据作为训练数据，或者需要获取网络内或区域内大量的用户的其他分析结果作为输入数据，在此之前，NWDAF2可以先请求获取大量的用户对应的UE的状态分析结果，以确定UE是否处于异常状态，请求消息中包含网络标识信息(如PLMN ID或S-NSSAI等)或区域标识(如TA list或cell list等)信息。
进一步的，当UE的状态分析结果表征UE处于正常状态时，UDM/UDR可以不向NWDAF2反馈UE的状态分析结果，相应的，NWDAF2可以在没有接收到UDM/UDR反馈的状态分析结果的情况下，默认UE处于正常状态。而当UE的状态分析结果表征UE处于异常状态时，UDM/UDR才向NWDAF2反馈UE的状态分析结果，以通知NWDAF2该UE处于异常状态，以此可以减少NWDAF2与UDM/UDR之间传输的数据量，从而可以降低网络资源的消耗。
S305：UDM/UDR向NWDAF2反馈响应消息，该响应消息包括UE的标识信息、状态分析结果、异常类型、置信度、时间信息以及区域信息。
在一种可能的实施方式中，UDM/UDR向NWDAF2反馈的响应消息中，也可以是仅包括状态分析结果。比如，当置信度大于预设阈值时，表明UE处于正常状态或者异常状态的可能性较高，从而可以仅将状态分析结果反馈给NWDAF2。
S306：NWDAF2在根据响应消息中的状态分析结果确定UE处于异常状态并且置信度大于预设阈值时，根据不包含该UE对应的数据的输入数据生成目标分析类型对应的分析结 果。
由于UE的状态异常时，该UE对应的数据可能出现错误，这使得NWDAF2在基于包含错误的UE的数据进行相应的分析时，所得到的分析结果的正确性可能会受到影响，因此，本实施例中，NWDAF2在确定UE处于异常状态并且置信度大于预设阈值时，可以基于不包括UE对应的数据的输入数据生成相应的分析结果，以避免该UE对应的数据对于NWDAF2所生成的分析结果的准确性影响，提高分析结果的准确性。
在一种示例性的实施方式中，当NWDAF2确定UE处于异常状态并且置信度大于预设阈值时，NWDAF2可以从网络中的相应网元处获取生成分析结果所需的第三输入数据，该第三输入数据中包括该UE对应的数据，然后，NWDAF2可以删除第三输入数据中有关UE对应的数据，得到第一输入数据(即为剩余的第三输入数据)，并基于该第一输入数据生成相应的分析结果。或者，当网络中的相应网元向NWDAF2反馈UE对应的数据时，NWDAF2可以拒绝接收该网元发送的UE对应的数据。
而在另一种示例性的实施方式中，NWDAF2预先可以向网络中的相应网元发送订阅消息，以从网络中的相应网元处订阅生成分析结果所需的输入数据，其中，该输入数据中可以包括从第二网元处订阅的目标对象对应的数据，输入数据中包括的其它数据可以是从第三网元处订阅得到，该第三网元可以包括一个或者多个网元。当NWDAF2确定UE处于异常状态并且置信度大于预设阈值时，NWDAF2可以向第二网元发送取消订阅消息，该取消订阅消息可以用于指示第二数据停止向NWDAF2反馈该UE对应的数据，而第三网元在没有收到取消订阅消息的情况下，可以基于之前的订阅消息的指示，继续向NWDAF2反馈其它的输入数据，依次可以使得NWDAF2所获得第一输入数据中可以不包括UE对应的数据。或者，NWDAF2也可以发送新的订阅请求消息或者订阅修改消息，其中隐式地将某个或某些用户设置为订阅黑名单。
而当NWDAF2确定UE处于正常状态，并且置信度大于预设阈值时，NWDAF2可以基于包含该UE对应的数据的输入数据生成相应的分析结果，
进一步的，NWDAF2在基于不包括处于异常状态下的UE对应的数据的输入数据生成分析结果后，可以将该分析结果发送给向其订阅该分析结果的网元，并同时可以将UE处于异常状态时的异常类型、时间信息以及区域信息一并反馈给该网元，以便于该网元基于所接收到的信息执行相应的处理操作，如对已执行的错误操作进行更正等。
进一步的，NWDAF2在确定UE处于异常状态时，还可以向订阅该分析结果的网元发送停用指示信息或者第一指示信息。其中，停用指示信息可以指示该网元停用该之前NWDAF2反馈的分析结果，或者取消根据之前反馈的分析结果所执行的相关操作，或者拒绝继续根据之前反馈的分析结果进行相应操作等；第一指示信息，可以指示该网元降低NWDAF2之前反馈的分析结果的置信度，以便该网元基于置信度下调的分析结果确定执行相应的处理过程，比如，当该网元根据第一指示信息确定NWDAF2之前反馈的分析结果的置信度下调至30％时，可以撤销之前基于该分析结果所执行的操作，或者执行与之前相反的操作等。
上述场景实施例中，NWDAF1监测并生成的状态分析结果是发送至UDM/UDR中进行存储，并且，当NWDAF2需要UE的状态分析结果时，可以从该UDM/UDR中获取。而在其它可能的 实施例中，NWDAF1在生成UE对应的状态分析结果后，可以直接将该状态分析结果通知给NWDAF2，而可以不用将其存储于UDM/UDR中。具体的，参阅图4，图4示出了本申请实施例中又一场景实施例的信令交互示意图，该方法具体可以包括：
S401：NWDAF2向NWDAF1发送针对于UE的状态分析结果的订阅消息或请求消息，该订阅消息或请求消息用于请求UE的状态分析结果。
本实施例中，NWDAF2可以向NWDAF1订阅或者请求UE的状态分析结果，以便于根据NWDAF1反馈的状态分析结果确定UE是否处于异常状态。
作为一种示例，订阅消息/请求消息中可以包含特定用户对应的UE标识信息或群组对应的UE群组标识信息；或者，该订阅消息/请求消息可以包括网络标识信息或区域标识信息，以请求位于该网络标识信息所对应的网络内的一个或者多个UE的状态分析结果，或者请求位于该区域标识信息所对应的区域内的一个或者多个UE的状态分析结果。
S402：NWDAF1生成UE的状态分析结果。
本实施例中的步骤S402与步骤S301的具体实现方式类似，具体可参见前述步骤S301的相关之处描述，在此不做赘述。
S403：NWDAF1向NWDAF2发送通知或响应消息，该通知或响应消息中可以包括UE的标识信息、状态分析结果、异常类型、置信度、时间信息以及区域信息。
本实施例中，NWDAF1在生成UE对应的状态分析结果后，可以直接将该状态分析结果通知给网络中的其它NWDAF(包括NWDAF2)，从而可以不用UDM/UDR对该通知消息进行存储。其中，接收到状态分析结果的其它NWDAF预先可以向NWDAF1发起针对于UE的分析结果的订阅或请求。
S404：NWDAF2根据接收到的状态分析结果确定UE处于异常状态并且置信度大于预设阈值时，根据不包含该UE对应的数据的输入数据生成目标分析类型对应的分析结果。
此外，本申请实施例还提供了一种通信装置。参阅图5，图5示出了本申请实施例中一种通信装置的结构示意图，该装置500可以应用于第二数据分析网元，可以执行上述方法实施例中第二数据分析网元所执行的方法步骤。具体的，该装置500可以包括：接收单元501，处理单元502。该装置500还可以包括发送单元503以及存储单元504。
其中，接收单元501，用于接收来自第一数据分析网元的目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；
处理单元502，用于根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，其中，当所述目标对象的状态分析结果指示所述目标对象状态异常时，所述第一输入数据不包括所述目标对象对应的数据；根据所述第一输入数据生成所述目标分析类型对应的第一分析结果。
装置500中的存储单元504，可以用于存储相应的数据，比如可以存储上述目标对象对应的状态分析结果、第一输入数据以及第一分析结果等。可选的，存储单元504还可以存储下述各种可能的实施方式中接收单元501所接收到的数据，以及处理单元502在执行相应处理时所得到的数据，而发送单元503可以发送存储单元504中的部分或者全部数据。
在一种可能的实施方式中，发送单元503，用于向第一网元发送所述第一分析结果和/ 或第一指示信息，所述第一指示信息用于指示所述第一网元停用第二分析结果或将所述第二分析结果对应的置信度下调至第一置信度，所述第二分析结果是由所述第二数据分析网元根据第二输入数据生成并向所述第一网元发送的所述目标分析类型的分析结果，所述第二输入数据包括所述目标对象对应的数据。
在一种可能的实施方式中，所述发送单元503，具体用于当所述第二数据分析网元确定所述第一分析结果与第二分析结果不同时，所述第二数据分析网元向所述第一网元发送所述第一分析结果。
在一种可能的实施方式中，所述接收单元501，还用于接收所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息；
所述第一输入数据不包括所述目标对象对应的数据，包括：
所述第一输入数据不包括所述目标对象在所述第一时间信息和/或所述第一区域信息对应的数据。
在一种可能的实施方式中，所述发送单元503，还用于向所述第一网元发送所述第一指示信息对应的第二时间信息和/或第二区域信息。
在一种可能的实施方式中，所述发送单元503，还用于向所述第一网元发送所述第一分析结果所适用的第三时间信息和/或第三区域信息。
在一种可能的实施方式中，所述发送单元503，还用于向所述第一网元发送第一异常原因，所述第一异常原因用于指示发送所述第一分析结果和/或所述第一指示信息的原因。
在一种可能的实施方式中，所述处理单元502，具体用于从已获取的所述目标分析类型对应的第三输入数据中删除所述目标对象对应的数据，得到所述第一输入数据；
或者，取消从第二网元处订阅所述目标对象对应的数据，并接收来自第三网元的所述第一输入数据。
在一种可能的实施方式中，所述目标对象的状态分析结果包括对所述目标对象的状态预测分析结果。
在一种可能的实施方式中，所述接收单元501，还用于接收来自所述第一数据分析网元的所述目标对象的状态分析结果对应的第二置信度；
所述处理单元502，具体用于当所述第二数据分析网元确定所述第二置信度大于第一阈值，且根据所述目标对象的状态分析结果确定所述目标对象状态异常时，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据。
在一种可能的实施方式中，所述发送单元503，还用于向所述第一网元发送所述第一分析结果对应的第三置信度，所述第三置信度是由所述第二数据分析网元基于所述第一输入数据和所述第二置信度确定的。
在一种可能的实施方式中，所述接收单元501，具体用于从第四网元中获取所述目标对象的状态分析结果，所述目标对象的状态分析结果是由所述第一数据分析网元发送给所述第四网元。
在一种可能的实施方式中，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知状态。
在一种可能的实施方式中，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常程度、异常趋势。
上述装置各模块之间的信息交互、执行过程等内容，由于与本申请实施例中方法实施例基于同一构思，其带来的技术效果与本申请实施例中方法实施例相同，为描述的方便和简洁，上述描述的装置、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
此外，本申请实施例还提供了一种通信装置。参阅图6，图6示出了本申请实施例中一种通信装置的结构示意图，该装置600可以应用于第一数据分析网元，可以执行上述方法实施例中第一数据分析网元所执行的方法步骤。具体的，该装置600可以包括：处理单元601、发送单元602。该装置600还可以包括接收单元603、存储单元604。
处理单元601，用于获取目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；
发送单元602，用于发送所述目标对象的状态分析结果。
装置600中的存储单元604，可以用于存储相应的数据，比如可以存储上述目标对象对应的状态分析结果等。
可选的，存储单元604还可以存储下述各种可能的实施方式中接收单元603所接收到的数据，以及处理单元601在执行相应处理时所得到的数据，而发送单元602可以发送存储单元604中的部分或者全部数据。
在一种可能的实施方式中，所述发送单元602，还用于向所述第二数据分析网元发送所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息。
在一种可能的实施方式中，所述目标对象的状态分析结果包括对所述目标对象历史状态的分析结果，或者，所述目标对象未来状态的分析结果。
在一种可能的实施方式中，所述发送单元602，还用于向所述第二数据分析网元发送所述目标对象的状态分析结果对应的第二置信度。
在一种可能的实施方式中，所述接收单元603，用于接收来自所述第二数据分析网元的第二指示信息；
所述发送单元602，具体用于基于所述第二指示信息，在确定所述目标对象状态异常时，向所述数据分析网元发送所述目标对象的状态分析结果。
在一种可能的实施方式中，所述处理单元601，具体用于响应利用接收单元接收到的来自所述第二数据分析网元的第一请求消息，生成所述目标对象的状态分析结果，所述第一请求消息用于向所述第一数据分析网元请求所述目标对象的状态分析结果。
在一种可能的实施方式中，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知状态。
在一种可能的实施方式中，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常程度、异常趋势。
在一种可能的实施方式中，所述目标对象包括目标网络切片的目标对象。
在一种可能的实施方式中，所述网络切片包括切片实例、切片子实例。
在一种可能的实施方式中，所述网络分域包括接入网域、核心网域、传输网域中的一种或多种。
上述装置各模块之间的信息交互、执行过程等内容，由于与本申请实施例中方法实施例基于同一构思，其带来的技术效果与本申请实施例中方法实施例相同，为描述的方便和简洁，上述描述的装置、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在图5和图6所示的装置中，处理单元、接收单元、发送单元以及存储单元可以是在物理上相互分离的单元，也可以是集成到一个或者多个物理单元中，在此不做限定。
接收单元和发送单元用于实现该装置与其他单元或者网元的内容交互。发送单元可以是发送电路或者发送器。接收单元可以是接收电路或者接收器。发送单元和接收单元还可以是该通信装置的通信单元。发送单元和接收单元还可以是处理单元的通信接口或者收发电路。可选的，发送单元和接收单元可以是一个收发芯片。该通信装置也可以包括多个发送单元和多个接收单元。发送单元和接收单元还可以是一个或者多个收发单元的子单元。
处理单元用于实现通信装置对数据的处理。处理单元可以是处理电路，也可以是处理器。通信装置也可以包括多个处理单元或者处理单元包括多个子数据处理单元。具体的，处理器可以是一个单核(single-CPU)处理器，也可以是一个多核(multi-CPU)处理器。
存储单元可以是独立于处理单元的单元，也可以是处理单元中的存储单元，在此不做限定。通信装置也可以包括多个存储单元或者存储单元包括多个子存储单元。
此外，本申请实施例还提供了一种通信装置。其中，该通信转装置可以应用于上述方法实施例中所提及的第一数据分析网元或者第二数据分析网元。该通信装置可以包括处理器以及存储器，所述处理器与存储器耦合；
所述存储器用于存储计算机程序或指令；
所述处理器用于执行所述计算机程序或指令，使得上述方法实施例中第一数据分析网元所执行的通信方法被执行，或者是使得上述方法实施例中第二数据分析网元所执行的通信方法被执行。
在一些可能的实施方式中，所述处理器执行所述计算机程序或指令，也可以使得上述方法实施例中核心网网元所执行的通信方法被执行。
图7是一种通信装置的硬件结构示意图，可以是本申请实施例中的第一网元或数据分析网元。该通信装置包括至少一个处理器71(如图7中还可以包括处理器75等)、至少一个存储器72、至少一个通信接口73。处理器71、存储器72、和通信接口73相连，例如通过通信线路74相连，在本申请实施例中，处理器71可以包括一个CPU，如图7中处理器71可以仅包括CPU0，或者，处理器71也可以包括多个CPU，如图7中处理器71可以包括CPU0以及CPU1等，当然，处理器71还可以三个以上(包括三个)的CPU。可选的，通信装置还包括其它处理器，如图7中还可以包括处理器75，则其它处理器中也可以包括一个或者多个CPU。所述连接可包括各类接口、传输线或总线等，本实施例对此不做限定。通信接口73用于使得通信装置通过通信链路，与其它通信设备相连，例如通信接口73可以是S1接口，或者是X2、Xn接口等。
其中，图7中所示的处理器71具体可以完成上述方法中数据分析网元或者第一网元处 理的动作，存储器72可以完成上述方法中存储的动作，通信接口73可以完成上述方法中通信装置与和其他网元之间进行交互的动作，下面以图7所示的通信装置应用于数据分析网元为例进行示例性的说明：
处理器71可以根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，并根据第一输入数据生成目标分析类型对应的第一分析结果。存储器72可以存储目标对象的状态分析结果、第一输入数据以及第一分析结果等。其中，目标对象的状态分析结果、第一输入数据以及第一分析结果中的具体内容具体可以参照其它实施例中相关之处的介绍。
本申请实施例中的处理器，例如处理器71，可以包括但不限于以下至少一种：中央处理单元(central processing unit，CPU)、微处理器、数字信号处理器(DSP)、微控制器(microcontroller unit，MCU)、或人工智能处理器等各类运行软件的计算设备，每种计算设备可包括一个或多个用于执行软件指令以进行运算或处理的核。该处理器可以是个单独的半导体芯片，也可以跟其他电路一起集成为一个半导体芯片，例如，可以跟其他电路(如编解码电路、硬件加速电路或各种总线和接口电路)构成一个SoC(片上系统)，或者也可以作为一个ASIC的内置处理器集成在所述ASIC当中，该集成了处理器的ASIC可以单独封装或者也可以跟其他电路封装在一起。该处理器除了包括用于执行软件指令以进行运算或处理的核外，还可进一步包括必要的硬件加速器，如现场可编程门阵列(field programmable gate array，FPGA)、PLD(可编程逻辑器件)、或者实现专用逻辑运算的逻辑电路。
本申请实施例中的存储器，可以包括如下至少一种类型：只读存储器(read-only memory，ROM)或可存储静态信息和指令的其他类型的静态存储设备，随机存取存储器(random access memory，RAM)或者可存储信息和指令的其他类型的动态存储设备，也可以是电可擦可编程只读存储器(Electrically erasable programmabler-only memory，EEPROM)。在某些场景下，存储器还可以是只读光盘(compact disc read-only memory，CD-ROM)或其他光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质，但不限于此。
存储器72可以是独立存在，与处理器71(以及处理器75)相连。可选的，存储器72可以和处理器71(以及处理器75)集成在一起，例如集成在一个芯片之内。其中，存储器72能够存储执行本申请实施例的技术方案的程序代码，并由处理器71来控制执行，被执行的各类计算机程序代码也可被视为是处理器71的驱动程序。例如，处理器71用于执行存储器72中存储的计算机程序代码，从而实现本申请实施例中的技术方案。
在上述实施例中，存储器存储的供处理器执行的指令可以以计算机程序产品的形式实现。计算机程序产品可以是事先写入在存储器中，也可以是以软件形式下载并安装在存储器中。
计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时，全部或部分地产生按照本申请实施例的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质 中，或者从一个计算机可读存储介质向另一计算机可读存储介质传输，例如，计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。计算机可读存储介质可以是计算机能够存储的任何可用介质或者是包括一个或多个可用介质集成的服务器、数据中心等数据存储设备。可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘solid state disk，SSD)等。
图8是本申请实施例提供的芯片80的硬件结构示意图。芯片80包括一个或两个以上(包括两个)处理器810和通信接口830。处理器810可以与通信接口830耦合相连，本申请实施例中，所述连接可包括各类接口、传输线或总线等，本实施例对此不做限定。通信接口830用于使得芯片80通过通信链路，与其它通信设备相连。
可选的，该芯片80还包括存储器840，该存储器840可以与处理器810和通信接口830相连，例如通过通信线路820相连。存储器840可以包括只读存储器和随机存取存储器，并向处理器810提供操作指令和数据。存储器840的一部分还可以包括非易失性随机存取存储器(non-volatile random access memory，NVRAM)。
在一些实施方式中，存储器840存储了如下的元素，执行模块或者数据结构，或者他们的子集，或者他们的扩展集。
在本申请实施例中，通过调用存储器840存储的操作指令(该操作指令可存储在操作系统中)，执行相应的操作。
其中，图8中所示的处理器810具体可以完成上述方法中数据分析网元或者第一网元处理的动作，存储器840可以完成上述方法中存储的动作，通信接口830可以完成上述方法中与和其他网元(或其他网元中的模块)之间进行交互的动作，下面以图8所示的芯片应用于数据分析网元为例进行示例性的说明：
处理器810可以根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，并根据第一输入数据生成目标分析类型对应的第一分析结果。存储器820可以存储目标对象的状态分析结果、第一输入数据以及第一分析结果等。其中，目标对象的状态分析结果、第一输入数据以及第一分析结果中的具体内容具体可以参照其它实施例中相关之处的介绍。
本申请实施例还提供了一种计算机可读存储介质。上述实施例中描述的方法可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。如果在软件中实现，则功能可以作为一个或多个指令或代码存储在计算机可读介质上或者在计算机可读介质上传输。计算机可读介质可以包括计算机存储介质和通信介质，还可以包括任何可以将计算机程序从一个地方传送到另一个地方的介质。存储介质可以是可由计算机访问的任何目标介质。
作为一种可选的设计，计算机可读介质可以包括RAM，ROM，EEPROM，CD-ROM或其它光盘存储器，磁盘存储器或其它磁存储设备，或目标于承载的任何其它介质或以指令或数据结构的形式存储所需的程序代码，并且可由计算机访问。而且，任何连接被适当地称为计算机可读介质。例如，如果使用同轴电缆，光纤电缆，双绞线，数字用户线(DSL)或无线技术(如红外，无线电和微波)从网站，服务器或其它远程源传输软件，则同轴电缆，光 纤电缆，双绞线，DSL或诸如红外，无线电和微波之类的无线技术包括在介质的定义中。如本文所使用的磁盘和光盘包括光盘(CD)，激光盘，光盘，数字通用光盘(DVD)，软盘和蓝光盘，其中磁盘通常以磁性方式再现数据，而光盘利用激光光学地再现数据。上述的组合也应包括在计算机可读介质的范围内。
本申请实施例还提供了一种计算机程序产品。上述实施例中描述的方法可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。如果在软件中实现，可以全部或者部分得通过计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行上述计算机程序指令时，全部或部分地产生按照上述方法实施例中描述的流程或功能。上述计算机可以是通用计算机、专用计算机、计算机网络、基站、终端或者其它可编程装置。
需要说明的是，本申请中“的(英文：of)”，相应的“(英文corresponding，relevant)”和“对应的(英文：corresponding)”有时可以混用，应当指出的是，在不强调其区别时，其所要表达的含义是一致的。
需要说明的是，本申请实施例中，“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性的”或者“例如”的任何实施例或设计方案不应被解释为比其他实施例或设计方案更优选或更具优势。确切而言，使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
本申请中，“至少一个”是指一个或者多个。“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a，b，或c中的至少一项(个)，可以表示：a，b，c，a-b，a-c，b-c，或a-b-c，其中a，b，c可以是单个，也可以是多个。另外，为了便于清楚描述本申请实施例的技术方案，在本申请的实施例中，采用了“第一”、“第二”等字样对功能和作用基本相同的相同项或相似项进行区分。本领域技术人员可以理解“第一”、“第二”等字样并不对数量和执行次序进行限定，并且“第一”、“第二”等字样也并不限定一定不同。
本申请实施例描述的系统架构以及业务场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着网络架构的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。

Claims (31)

  1. 一种通信方法，其特征在于，所述方法包括：
    第二数据分析网元接收来自第一数据分析网元的目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；
    所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，其中，当所述目标对象的状态分析结果指示所述目标对象状态异常时，所述第一输入数据不包括所述目标对象对应的数据；
    所述第二数据分析网元根据所述第一输入数据生成所述目标分析类型对应的第一分析结果。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    所述第二数据分析网元向第一网元发送所述第一分析结果和/或第一指示信息，所述第一指示信息用于指示所述第一网元停用第二分析结果或将所述第二分析结果对应的置信度下调至第一置信度，所述第二分析结果是由所述第二数据分析网元根据第二输入数据生成并向所述第一网元发送的所述目标分析类型的分析结果，所述第二输入数据包括所述目标对象对应的数据。
  3. 根据权利要求2所述的方法，其特征在于，所述第二数据分析网元向第一网元发送所述第一分析结果，包括：
    当所述第二数据分析网元确定所述第一分析结果与第二分析结果不同时，所述第二数据分析网元向所述第一网元发送所述第一分析结果。
  4. 根据权利要求2或3所述的方法，其特征在于，方法还包括：
    所述第二数据分析网元获取所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息；
    所述第一输入数据不包括所述目标对象对应的数据，包括：
    所述第一输入数据不包括所述目标对象在所述第一时间信息和/或所述第一区域信息对应的数据。
  5. 根据权利要求2至4任一项所述的方法，其特征在于，所述方法还包括：
    所述第二数据分析网元向所述第一网元发送所述第一指示信息对应的第二时间信息和/或第二区域信息。
  6. 根据权利要求2至5任一所述的方法，其特征在于，方法还包括：
    所述第二数据分析网元向所述第一网元发送所述第一分析结果所适用的第三时间信息和/或第三区域信息。
  7. 根据权利要求2至6任一项所述的方法，其特征在于，所述方法还包括：
    所述第二数据分析网元向所述第一网元发送第一异常原因，所述第一异常原因用于指示发送所述第一分析结果和/或所述第一指示信息的原因。
  8. 根据权利要求1至7任一项所述的方法，其特征在于，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，包括：
    所述第二数据分析网元从已获取的所述目标分析类型对应的第三输入数据中删除所述目标对象对应的数据，得到所述第一输入数据；
    或者，所述第二数据分析网元取消从第二网元处订阅所述目标对象对应的数据，并接收来自第三网元的所述第一输入数据。
  9. 根据权利要求1至8任一项所述的方法，其特征在于，所述目标对象的状态分析结果包括对所述目标对象的状态预测分析结果。
  10. 根据权利要求1至9任一所述的方法，其特征在于，所述方法还包括：
    所述第二数据分析网元接收来自所述第一数据分析网元的所述目标对象的状态分析结果对应的第二置信度；
    所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，包括：
    当所述第二数据分析网元确定所述第二置信度大于第一阈值，且根据所述目标对象的状态分析结果确定所述目标对象状态异常时，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据。
  11. 根据权利要求1至10任一项所述的方法，其特征在于，所述方法还包括：
    所述第二数据分析网元向所述第一网元发送所述第一分析结果对应的第三置信度，所述第三置信度是由所述第二数据分析网元基于所述第一输入数据和所述第二置信度确定的。
  12. 根据权利要求1至11任一项所述的方法，其特征在于，第二数据分析网元接收来自第一数据分析网元的目标对象的状态分析结果，包括：
    所述第二数据分析网元从第四网元中获取所述目标对象的状态分析结果，所述目标对象的状态分析结果是由所述第一数据分析网元发送给所述第四网元。
  13. 根据权利要求1至12任一项所述的方法，其特征在于，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知状态。
  14. 根据权利要求1至13任一项所述的方法，其特征在于，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常程度、异常趋势。
  15. 一种通信装置，其特征在于，所述装置包括：
    接收单元，用于接收来自第一数据分析网元的目标对象的状态分析结果，所述目标对象包括网络设备、网络分域、网络整域、终端设备中的一种或多种；
    处理单元，用于根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据，其中，当所述目标对象的状态分析结果指示所述目标对象状态异常时，所述第一输入数据不包括所述目标对象对应的数据；根据所述第一输入数据生成所述目标分析类型对应的第一分析结果。
  16. 根据权利要求15所述的装置，其特征在于，所述装置还包括：
    发送单元，用于向第一网元发送所述第一分析结果和/或第一指示信息，所述第一指示信息用于指示所述第一网元停用第二分析结果或将所述第二分析结果对应的置信度下调至第一置信度，所述第二分析结果是由所述第二数据分析网元根据第二输入数据生成并向所述第一网元发送的所述目标分析类型的分析结果，所述第二输入数据包括所述目标对象对 应的数据。
  17. 根据权利要求16所述的装置，其特征在于，所述发送单元，具体用于当所述第二数据分析网元确定所述第一分析结果与第二分析结果不同时，所述第二数据分析网元向所述第一网元发送所述第一分析结果。
  18. 根据权利要求16或者17所述的装置，其特征在于，所述接收单元，还用于接收所述目标对象的状态分析结果对应的第一时间信息和/或第一区域信息；
    所述第一输入数据不包括所述目标对象对应的数据，包括：
    所述第一输入数据不包括所述目标对象在所述第一时间信息和/或所述第一区域信息对应的数据。
  19. 根据权利要求16至18任一项所述的装置，其特征在于，所述发送单元，还用于向所述第一网元发送所述第一指示信息对应的第二时间信息和/或第二区域信息。
  20. 根据权利要求16至19任一项所述的装置，其特征在于，所述发送单元，还用于向所述第一网元发送所述第一分析结果所适用的第三时间信息和/或第三区域信息。
  21. 根据权利要求16至20任一项所述的装置，其特征在于，所述发送单元，还用于向所述第一网元发送第一异常原因，所述第一异常原因用于指示发送所述第一分析结果和/或所述第一指示信息的原因。
  22. 根据权利要求15至21任一项所述的装置，其特征在于，所述处理单元，具体用于从已获取的所述目标分析类型对应的第三输入数据中删除所述目标对象对应的数据，得到所述第一输入数据；或者，取消从第二网元处订阅所述目标对象对应的数据，并接收来自第三网元的所述第一输入数据。
  23. 根据权利要求15至22任一项所述的装置，其特征在于，所述目标对象的状态分析结果包括对所述目标对象的状态预测分析结果。
  24. 根据权利要求15至23任一项所述的装置，其特征在于，所述接收单元，还用于接收来自所述第一数据分析网元的所述目标对象的状态分析结果对应的第二置信度；
    所述处理单元，具体用于当所述第二数据分析网元确定所述第二置信度大于第一阈值，且根据所述目标对象的状态分析结果确定所述目标对象状态异常时，所述第二数据分析网元根据所述目标对象的状态分析结果获取目标分析类型对应的第一输入数据。
  25. 根据权利要求16至21任一项所述的装置，其特征在于，所述发送单元，还用于向所述第一网元发送所述第一分析结果对应的第三置信度，所述第三置信度是由所述第二数据分析网元基于所述第一输入数据和所述第二置信度确定的。
  26. 根据权利要求15至25任一项所述的装置，其特征在于，所述接收单元，具体用于从第四网元中获取所述目标对象的状态分析结果，所述目标对象的状态分析结果是由所述第一数据分析网元发送给所述第四网元。
  27. 根据权利要求15至26任一项所述的装置，其特征在于，所述目标对象的状态分析结果包括状态指示信息，所述状态指示信息用于指示所述目标对象处于以下状态的任意一种：正常状态、异常状态、未知状态。
  28. 根据权利要求15至27任一项所述的装置，其特征在于，所述目标对象的状态分析结果包括以下信息中的任意一种或多种：异常类型、异常子类型、第二异常原因、异常 程度、异常趋势。
  29. 一种通信装置，其特征在于，包括处理器和存储器，所述存储器用于存储计算机程序或指令，所述处理器用于执行所述计算机程序或指令，使得权利要求1至14任一所述的方法被执行。
  30. 一种计算机可读存储介质，包括指令或计算机程序，当其在计算机上运行时，使得计算机执行以上权利要求1至14任一所述的方法。
  31. 一种通信系统，其特征在于，所述系统包括用于执行如权利要求1至14任一所述的第二数据分析网元以及用于与所述第二数据分析网元进行通信的第一数据分析网元。
PCT/CN2021/074345 2020-05-22 2021-01-29 一种通信方法、装置及系统 WO2021232849A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP21807898.8A EP4145889A4 (en) 2020-05-22 2021-01-29 COMMUNICATION METHOD, DEVICE AND SYSTEM
BR112022023665A BR112022023665A2 (pt) 2020-05-22 2021-01-29 Método, aparelho, e sistema de comunicação
US17/990,934 US11991049B2 (en) 2020-05-22 2022-11-21 Communication method, apparatus, and system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010441748.0A CN113709776B (zh) 2020-05-22 2020-05-22 一种通信方法、装置及系统
CN202010441748.0 2020-05-22

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/990,934 Continuation US11991049B2 (en) 2020-05-22 2022-11-21 Communication method, apparatus, and system

Publications (1)

Publication Number Publication Date
WO2021232849A1 true WO2021232849A1 (zh) 2021-11-25

Family

ID=78646265

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/074345 WO2021232849A1 (zh) 2020-05-22 2021-01-29 一种通信方法、装置及系统

Country Status (5)

Country Link
US (1) US11991049B2 (zh)
EP (1) EP4145889A4 (zh)
CN (2) CN113709776B (zh)
BR (1) BR112022023665A2 (zh)
WO (1) WO2021232849A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024008318A1 (en) * 2022-07-04 2024-01-11 Lenovo (Singapore) Pte. Ltd Improved analytic generation in a wireless communication network

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116782253A (zh) * 2022-03-08 2023-09-19 华为技术有限公司 一种通信方法和通信装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106603418A (zh) * 2016-12-09 2017-04-26 中国联合网络通信集团有限公司 一种网络拓扑更新方法及流量分析设备
CN108184008A (zh) * 2016-12-08 2018-06-19 中兴通讯股份有限公司 一种终端通信性能评估方法和装置
CN110650034A (zh) * 2018-06-26 2020-01-03 华为技术有限公司 一种信息处理方法及装置
US10545699B2 (en) * 2017-04-11 2020-01-28 International Business Machines Corporation Dynamic retention policies and optional deletes

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11304070B2 (en) * 2013-02-14 2022-04-12 Nokia Solutions And Networks Oy Method of adapting operation of self-organizing network functions
US10678225B2 (en) * 2013-03-04 2020-06-09 Fisher-Rosemount Systems, Inc. Data analytic services for distributed industrial performance monitoring
WO2019158737A1 (en) * 2018-02-16 2019-08-22 NEC Laboratories Europe GmbH Network data analytics for oam
CN110602735B (zh) * 2018-06-13 2021-06-29 华为技术有限公司 一种受限服务的提供方法及通信设备
WO2020001336A1 (zh) * 2018-06-26 2020-01-02 华为技术有限公司 一种信息处理方法及装置
CN110972193B (zh) * 2018-09-28 2021-12-03 华为技术有限公司 一种切片信息处理方法及装置
US10992554B2 (en) * 2018-12-07 2021-04-27 At&T Intellectual Property I, L.P. Intelligent data analytics collectors
US20200202986A1 (en) * 2018-12-19 2020-06-25 Optum, Inc. Systems and methods for parallel execution of program analytics utilizing a common data object
US11425583B2 (en) * 2019-04-02 2022-08-23 Electronics And Telecommunications Research Institute Network data collection method from application function device for network data analytic function
WO2021109452A1 (en) * 2020-05-11 2021-06-10 Zte Corporation Network function monitoring and data collection

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108184008A (zh) * 2016-12-08 2018-06-19 中兴通讯股份有限公司 一种终端通信性能评估方法和装置
CN106603418A (zh) * 2016-12-09 2017-04-26 中国联合网络通信集团有限公司 一种网络拓扑更新方法及流量分析设备
US10545699B2 (en) * 2017-04-11 2020-01-28 International Business Machines Corporation Dynamic retention policies and optional deletes
CN110650034A (zh) * 2018-06-26 2020-01-03 华为技术有限公司 一种信息处理方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4145889A4

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024008318A1 (en) * 2022-07-04 2024-01-11 Lenovo (Singapore) Pte. Ltd Improved analytic generation in a wireless communication network

Also Published As

Publication number Publication date
EP4145889A1 (en) 2023-03-08
CN113709776A (zh) 2021-11-26
EP4145889A4 (en) 2023-10-25
CN117395694A (zh) 2024-01-12
US11991049B2 (en) 2024-05-21
CN113709776B (zh) 2023-11-03
BR112022023665A2 (pt) 2023-01-31
US20230100296A1 (en) 2023-03-30

Similar Documents

Publication Publication Date Title
US11399293B2 (en) System and method of network policy optimization
US20200366567A1 (en) Method, Device and System for Ensuring Service Level Agreement of Application
US20220006707A1 (en) Sharable storage method and system for network data analytics
US12015682B2 (en) Service subscription method and system for reporting service change in communication system
US9071998B2 (en) Optimizing performance information collection
US11991049B2 (en) Communication method, apparatus, and system
US11178000B2 (en) Method and system for processing NF component exception, and device
JP2022527968A (ja) 端末の挙動に関する分析を決定するための方法および装置
US20100029248A1 (en) Method, apparatus and system for managing user access to network
WO2020108002A1 (zh) 一种传输策略确定方法、策略控制方法及装置
US11252583B2 (en) Communication method, related device, and system
US12021695B2 (en) Communication method, apparatus, and system
US12003662B2 (en) Methods, apparatus and computer-readable mediums supporting subscriptions to events in a core network
US20220353746A1 (en) Report information sending method, communication apparatus, and communication system
WO2021208563A1 (zh) 一种通信方法、装置及系统
WO2019096306A1 (zh) 一种处理请求的方法以及相应实体
WO2020192387A1 (zh) 一种请求处理方法、相关装置及系统
US20230146433A1 (en) Evaluating overall network resource congestion before scaling a network slice
WO2019015755A1 (en) METHODS AND NODES FOR PROVIDING OR SELECTING USER TRAFFIC NODE
WO2021218270A1 (zh) 一种通信方法、装置及系统
WO2021159415A1 (zh) 通信方法、装置及系统
RU2772710C2 (ru) Способ обработки запроса и соответствующий объект
US20230403207A1 (en) Smf discoverability management based on connectivity to peer network functions
US11765064B1 (en) Network repository function overload protection
WO2023185850A1 (zh) Ursp规则优化方法、装置、终端、网络侧设备及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21807898

Country of ref document: EP

Kind code of ref document: A1

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112022023665

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 2021807898

Country of ref document: EP

Effective date: 20221129

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 112022023665

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20221121