WO2021254461A1 - 通信方法及装置、系统 - Google Patents

通信方法及装置、系统 Download PDF

Info

Publication number
WO2021254461A1
WO2021254461A1 PCT/CN2021/100747 CN2021100747W WO2021254461A1 WO 2021254461 A1 WO2021254461 A1 WO 2021254461A1 CN 2021100747 W CN2021100747 W CN 2021100747W WO 2021254461 A1 WO2021254461 A1 WO 2021254461A1
Authority
WO
WIPO (PCT)
Prior art keywords
intention
knowledge
network element
intent
credibility
Prior art date
Application number
PCT/CN2021/100747
Other languages
English (en)
French (fr)
Inventor
巨敏
李贤明
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 EP21825574.3A priority Critical patent/EP4156735A4/en
Publication of WO2021254461A1 publication Critical patent/WO2021254461A1/zh
Priority to US18/068,808 priority patent/US20230118861A1/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
    • H04L41/02—Standardisation; Integration
    • H04L41/022—Multivendor or multi-standard integration
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/02—Processing of mobility data, e.g. registration information at HLR [Home Location Register] or VLR [Visitor Location Register]; Transfer of mobility data, e.g. between HLR, VLR or external networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5041—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the time relationship between creation and deployment of a service
    • H04L41/5051—Service on demand, e.g. definition and deployment of services in real time
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence

Definitions

  • This application relates to the field of network intelligent management technology, and in particular to a communication method, device, and system.
  • intent-driven management In order to shield equipment manufacturers from achieving differentiation, intent-driven management (IDM) was launched. Only the intent model is reserved in the network management system (NMS), and the intent expression is passed to the element management system (EMS). The intention expression only describes what to do, and does not involve how to do it. The intention design can be completed only by having basic conceptual knowledge in the wireless field, thereby reducing the threshold of operation and maintenance.
  • NMS network management system
  • EMS element management system
  • the EMS After the EMS performs the intention translation, it obtains the intention operation, the intention target and the execution conditions from the intention knowledge base. For example, there are three instruction operations that can be taken after an intent is translated, corresponding to three different execution conditions.
  • the instruction operation corresponding to the first execution condition cannot meet the intention target multiple times.
  • the next time the EMS implements the intention it still cannot avoid selecting the instruction operation corresponding to the first execution condition, which causes the intention and target to be unsatisfied.
  • the present application provides a communication method, device, and system to improve the accuracy of the selection of the first operation for executing the first intention.
  • a communication method includes: a first network element acquires first knowledge of a first intention, and the first knowledge of the first intention includes one or more of the following information: The first degree of credibility of the first intention target and first information, where the first degree of credibility is used to indicate the reliability of achieving the first intention target, and the first information is used to indicate that the first intention operation is The influence of the second intention, the second intention is different from the first intention; and the first network element selects a first operation based on the first knowledge of the first intention, and the first operation is used to execute the The first intention.
  • the first network element can select the first operation according to the credibility of achieving the first intention goal and/or the first information, which can improve the accuracy of the selection of the first operation.
  • the first information includes an event and an impact value
  • the event includes a constraint condition or an intention target or an execution condition of the second intention
  • the impact value is used to indicate an impact on the event influence level
  • the first knowledge is first information
  • the first information includes events and influence values
  • the first information is embodied as the degree of influence of the first operation on the constraint condition or the intention target or execution condition of the second intention.
  • acquiring the first knowledge of the first intention by the first network element includes: determining the first knowledge of the first intention by the first network element; or, the first network element The element receives the first knowledge of the first intention from a second network element, and the second network element is a functional entity such as a network management system NMS, a user, an application program, an operation support system, or a business support system.
  • NMS network management system
  • the second network element is a functional entity such as a network management system NMS, a user, an application program, an operation support system, or a business support system.
  • the first network element may determine the first knowledge internally, or obtain the first knowledge from an external system, such as the second network element.
  • the first network element determining the first knowledge of the first intention includes: the first network element acquiring the intention keyword corresponding to the intention expression of the first intention,
  • the intention keywords include one or more of the following information: the first intention target, the area where the first intention acts, the name of the network element where the first intention acts; and the first network element According to the intention keywords, the first knowledge corresponding to the intention keywords is obtained from the intention knowledge base.
  • the first knowledge is stored in the intent knowledge base, and when the first network element performs intent translation, it can obtain the corresponding first knowledge from the intent knowledge base according to the intent keywords obtained during the translation process.
  • the first network element determining the first knowledge of the first intention includes: the first network element obtains intention performance data from a third network element; the first network element According to the intention performance data, the satisfaction of the first condition of the first intention is determined, where the first condition includes one or more of the following information: the first intention target, the first intention A constraint condition, an execution condition of the first intention; and the first network element determines the first knowledge of the first intention according to the satisfaction of the first condition and the second knowledge of the first intention,
  • the second knowledge of the first intention is the knowledge before the update of the first knowledge of the first intention.
  • the first network element updates the first knowledge according to the satisfaction of the first condition during the execution of the intention and the historical knowledge of the first intention.
  • the first knowledge is the first degree of credibility
  • the first network element determines according to the satisfaction of the first condition and the second knowledge of the first intention
  • the first knowledge of the first intention includes: the goal of the first intention is achieved, and the first degree of credibility is determined to be the sum of the second degree of credibility and the increment of the first degree of credibility; or the first degree of credibility
  • the intention goal is not reached, and the difference between the first achievement situation of the first intention goal and the second achievement situation of the first intention goal is a negative value, and the first degree of credibility is determined to be the second credibility
  • the sum of the second credibility degree and the second credibility degree increment, the second credibility degree increment is less than the first credibility degree increment; or the first intention goal is not achieved, and the first achievement condition is not the same as
  • the difference between the second achievement situation is a positive value
  • the first degree of credibility is determined to be the difference between the second degree of credibility and the third degree of credibility; wherein, the second degree of credibility is determined by The first degree of credibility before the update, the first achievement situation is the absolute
  • the first network element updates the first degree of credibility for achieving the first intention goal based on the current achievement situation and the historical achievement situation of the first intention goal.
  • the influence value is used to indicate the influence value of the first operation on the constraint condition or the intention target or the execution condition of the second intention.
  • the first network element determining the first knowledge of the first intention includes: if the intention goal of the second intention changes from being achieved to unfulfilled, determining the first knowledge The influence value of an operation on the second intention is negative; or if the intention goal of the second intention is that the goal has been achieved and the achievement status has not changed, the influence of the first operation on the second intention is determined The value is zero.
  • the influence value of the first operation on the second intention is determined according to the achievement of the intention goal of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the intention goal of the second intention.
  • the first network element determining the first knowledge of the first intention includes: when the first operation is performed relative to when the first operation is not performed, the second intention When the constraint condition changes from satisfied to unsatisfied, it is determined that the value of the influence of the first operation on the second intention is negative; or when the first operation is executed relative to the first operation not being executed, If the condition that the constraint condition of the second intention has been met has not changed, and the second intention has always been that the constraint condition has been met, it is determined that the value of the influence of the first operation on the second intention is zero.
  • the influence value of the first operation on the second intention is determined according to the satisfaction of the constraint condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the constraint condition of the second intention.
  • the first network element determining the first knowledge of the first intention includes: when the first operation is performed relative to when the first operation is not performed, the second intention If the execution condition of is changed from satisfied to unsatisfied, it is determined that the influence value of the first operation on the second intention is negative; or when the first operation is executed relative to the first operation not being executed, The condition that the execution condition of the second intention has been satisfied has not changed, and the execution condition of the second intention has been satisfied, then it is determined that the value of the influence of the first operation on the second intention is zero.
  • the influence value of the first operation on the second intention is determined according to the satisfaction of the execution condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the execution condition of the second intention.
  • the first network element selecting the first operation according to the first knowledge of the first intention includes: the first network element according to the first achievement status of the first intention target , The second knowledge corresponding to one or more existing intention operations, and the first knowledge of the first intention, the first operation is determined in the one or more existing intention operations.
  • the first operation can be selected from the existing intention operations.
  • a communication method includes: a second network element obtains a first intention operation from a first network element; the second network element determines that the first intention operation affects the second intention , The second intent is different from the first intent; and the second network element sends first information to the first network element, and the first information is used to indicate that the first intent operation affects the The influence of the second intention, the first information is used to select the first operation, and the first operation is used to execute the first intention.
  • the second network element when the second network element obtains that the first network element performs the first intent operation and determines that the first intent operation affects the second intent, the second network element may indicate the first network element to the first network element. The influence of the intention operation on the second intention, so that the first network element can accurately select the first operation.
  • a communication device configured to obtain first knowledge of a first intention, the first knowledge of the first intention including one or more of the following information: A first degree of credibility for achieving the first intention goal and first information, where the first degree of credibility is used to indicate the reliability of reaching the first intention goal, and the first information is used to indicate the first intention operation pair The influence of the second intention, the second intention is different from the first intention; and the processing unit is further configured to select a first operation based on the first knowledge of the first intention, and the first operation is used for Perform the first intention.
  • the first information includes an event and an impact value
  • the event includes a constraint condition or an intention target or an execution condition of the second intention
  • the impact value is used to indicate an impact on the event influence level
  • the processing unit is configured to determine the first knowledge of the first intention; or, the apparatus further includes: a transceiver unit, configured to receive the first knowledge from a second network element
  • the first knowledge of the intention, the second network element is a network management system NMS, a user or an application APP.
  • the processing unit is configured to obtain an intent keyword corresponding to an intent expression of the first intent, and the intent keyword includes one or more of the following information: The first intention target, the area where the first intention acts, the name of the network element where the first intention acts; and the processing unit is also used to obtain the intention key from the intention knowledge base according to the intention keyword The first knowledge corresponding to the word.
  • the transceiving unit is further configured to obtain intent performance data from a third network element; the processing unit is further configured to determine the first intent of the first intent according to the intent performance data Satisfaction of a condition, wherein the first condition includes one or more of the following information: the first intention target, the constraint condition of the first intention, the execution condition of the first intention; and the The processing unit is further configured to determine the first knowledge of the first intention according to the satisfaction of the first condition and the second knowledge of the first intention, and the second knowledge of the first intention is the second knowledge of the first intention.
  • the first knowledge of an intention is the knowledge before the update.
  • the first knowledge is the first degree of credibility; the processing unit is further configured to achieve the first intention goal, and determine that the first degree of credibility is the second degree of credibility.
  • the difference between the second achievement of the target is a negative value, and it is determined that the first degree of credibility is the sum of the second degree of credibility and the second degree of credibility increment, and the second degree of credibility increment is less than all
  • the first degree of credibility is increased; or the processing unit is also used to determine that the first intention goal is not reached, and the difference between the first achievement situation and the second achievement situation is a positive value
  • the first degree of credibility is the difference between the second degree of credibility and the third degree of credibility increment; wherein, the second degree of credibility is the degree of credibility before the first degree of credibility is updated, and the The first achievement situation is the absolute value of the difference between the achievement situation of the first intention goal in the first
  • the influence value is used to indicate the influence value of the first operation on the constraint condition or the intention target or the execution condition of the second intention.
  • the processing unit is further configured to determine the influence value of the first operation on the second intention if the intention goal of the second intention changes from being achieved to not being reached Is a negative value; or the processing unit is further configured to determine that the value of the influence of the first operation on the second intention is zero if the intention goal of the second intention is that the goal has been reached and the achievement status has not changed .
  • the processing unit is further configured to perform the first operation relative to the non-execution of the first operation, when the constraint condition of the second intention changes from being satisfied to unsatisfied, It is determined that the value of the influence of the first operation on the second intention is negative; or the processing unit is further configured to perform the first operation relative to when the first operation is not performed.
  • the condition that the constraint condition of the second intention has been met has not changed, and the second intention has always been that the constraint condition has been met, then it is determined that the value of the influence of the first operation on the second intention is zero.
  • the processing unit is further configured to perform the first operation relative to the non-executing the first operation, when the execution condition of the second intention changes from being met to being unsatisfied, It is determined that the value of the influence of the first operation on the second intention is negative; or the processing unit is further configured to perform the first operation relative to when the first operation is not performed.
  • the condition that the execution condition of the second intention has been met has not changed, and the second intention has always been that the execution condition has been met, then it is determined that the value of the influence of the first operation on the second intention is zero.
  • the processing unit is further configured to operate the corresponding second knowledge according to the first achievement of the first intention goal, one or more existing intentions, and the first The first knowledge of the intention, the first operation is determined in the one or more existing intention operations.
  • a communication device in a fourth aspect, includes: a transceiving unit, configured to obtain a first intention operation from a first network element; and a processing unit, configured to determine that the first intention operation has an impact on a second intention , The second intention is different from the first intention; and the transceiving unit is further configured to send first information to the first network element, where the first information is used to indicate that the first intention operation pair As for the influence of the second intention, the first information is used to select a first operation, and the first operation is used to execute the first intention.
  • a communication device may be the first network element in the first aspect or any possible implementation of the first aspect, or a module applied to the first network element, such as a chip. Or chip system.
  • the communication device includes at least one processor, configured to execute the foregoing first aspect or any possible implementation method of the first aspect.
  • the communication device further includes a memory coupled to the at least one processor, and the at least one processor is configured to execute the foregoing first aspect or any possible implementation method of the first aspect.
  • the memory is used to store program instructions and data.
  • the memory is coupled with the at least one processor, and the at least one processor can call and execute the program instructions stored in the memory for executing the foregoing first aspect or any possible implementation method of the first aspect.
  • the communication device further includes a communication interface, and the communication interface is used for the communication device to communicate with other devices.
  • the communication interface is a transceiver, an input/output interface, or a circuit.
  • the communication device includes: at least one processor and a communication interface, configured to execute the foregoing first aspect or any possible implementation method of the first aspect, specifically including: the at least one processing
  • the communication device uses the communication interface to communicate with the outside; the at least one processor is used to run a computer program, so that the communication device executes the foregoing first aspect or any possible implementation method of the first aspect.
  • the exterior may be an object other than the processor, or an object other than the communication device.
  • the communication device is a chip or a chip system.
  • the communication interface may be an input/output interface, interface circuit, output circuit, input circuit, pin or related circuit on the chip or chip system.
  • the processor can also be embodied as a processing circuit or a logic circuit.
  • a communication device may be the second network element in the second aspect described above, or a module applied to the second network element, such as a chip or a chip system.
  • the communication device includes at least one processor, configured to execute the method in the above second aspect.
  • the communication device further includes a memory coupled with the at least one processor, and the at least one processor is configured to execute the method in the above-mentioned second aspect.
  • the memory is used to store program instructions and data.
  • the memory is coupled with the at least one processor, and the at least one processor can call and execute the program instructions stored in the memory for executing the method in the above second aspect.
  • the communication device further includes a communication interface, and the communication interface is used for the communication device to communicate with other devices.
  • the communication interface is a transceiver, an input/output interface, or a circuit.
  • the communication device includes: at least one processor and a communication interface, configured to execute the method in the above second aspect, specifically including: the at least one processor communicates with the outside by using the communication interface; the At least one processor is used to run a computer program, so that the communication device executes the method in the above second aspect.
  • the exterior may be an object other than the processor, or an object other than the communication device.
  • the communication device is a chip or a chip system.
  • the communication interface may be an input/output interface, interface circuit, output circuit, input circuit, pin or related circuit on the chip or chip system.
  • the processor can also be embodied as a processing circuit or a logic circuit.
  • a communication system including the communication device implemented in any one of the third aspect or the third aspect, the communication device according to the fourth aspect, and a third network element.
  • a computer-readable storage medium stores instructions that, when run on a computer, cause the computer to execute the methods described in the foregoing aspects.
  • a computer program product containing instructions which when running on a computer, causes the computer to execute the methods described in the above aspects.
  • a chip is provided, the chip is coupled with a memory, and executes the communication method described in the first aspect or any one of the first aspects of the embodiments of the present application.
  • a chip is provided, which is coupled with a memory and executes the communication method described in the second aspect or any one of the second aspects of the embodiments of the present application.
  • Coupled in the embodiments of the present application means that two components are directly or indirectly combined with each other.
  • Figure 1 is a schematic diagram of ENI fusion architecture based on intent
  • Figure 2 is a schematic diagram of the internal and external interfaces of the ENI fusion architecture based on intent
  • Figure 3 is a schematic diagram of the structure of an intention-driven management system applicable to this application.
  • Figure 4 is a schematic diagram of the functional modules involved in the intent translation, execution and maintenance phases
  • FIG. 5 is a schematic diagram of the architecture of a communication system to which an embodiment of the application is applicable;
  • Figure 6 is a schematic diagram of adding 4 new interfaces to the intent-based ENI fusion system interface to support intent knowledge management
  • FIG. 7 is a schematic flowchart of a communication method provided by an embodiment of this application.
  • FIG. 8 is a schematic flowchart of a communication method in an intention translation process provided by an embodiment of the application.
  • FIG. 9 is a schematic flowchart of a communication method in the process of intention execution and maintenance.
  • FIG. 10 is a schematic flowchart of yet another communication method in the process of intention execution and maintenance
  • FIG. 11 is a schematic flowchart of yet another communication method in the process of intention execution and maintenance
  • FIG. 12 is a schematic flowchart of yet another communication method in the process of intention execution and maintenance
  • FIG. 13 is a schematic structural diagram of a communication device provided by an embodiment of this application.
  • FIG. 14 is a schematic structural diagram of yet another communication device provided by an embodiment of this application.
  • FIG. 15 is a schematic structural diagram of another communication device provided by an embodiment of this application.
  • Experiential Networked Intelligence is a perceptual network management system architecture defined by the industry standard working group, which uses artificial intelligence and context awareness to optimize and adjust network operations.
  • the ENI system contains 10 functional blocks (FB), which are divided into four categories: input function modules, output function modules, analysis function modules, and decision function modules.
  • FB functional blocks
  • input function modules output function modules
  • analysis function modules analysis function modules
  • decision function modules decision function modules
  • Input function modules data ingestion function modules and normalization function modules, which are responsible for receiving data from external systems and normalizing data.
  • Output function module The output generation function module and the denormalization function module are responsible for converting the internal commands of the system into a format that can be processed by the external system and sending them to the external system.
  • Analysis function modules knowledge management function module, context awareness function module and cognitive management function module, responsible for perceptual analysis of the existing network context and prediction of the future network state.
  • Decision-making function modules policy management function modules, situational awareness function modules and model-driven engineering function modules. Based on the awareness of network status, new policies are generated according to policy objectives And arrange the strategy, and send the operation command to the output module.
  • ENI defines the intent-based ENI fusion architecture, and defines the functional modules related to intent translation and intent protection.
  • Figure 1 shows the schematic diagram of the intent-based ENI fusion architecture. Specifically, the ENI fusion architecture adds an intent knowledge repository to the knowledge management function module, and adds intent policy execution to the policy management function module ( The intent policy fulfillment sub-function module, and an independent intent translation function module is also introduced.
  • the intention translation function module is used to translate the received intention strategy.
  • the intent knowledge base is used to store expert experience and network element information. It can be used as an independent functional module or placed in the knowledge management functional module of ENI's existing architecture.
  • the intention strategy execution function module is used to realize the intention execution and maintenance functions, and is responsible for arranging the intention strategy and continuously meeting the intent requirements of the external system.
  • the intent-based ENI fusion architecture also defines related modules and interfaces for intent translation and intent protection.
  • Figure 2 shows the schematic diagram of the internal and external interfaces of the intent-based ENI fusion architecture.
  • the interface Eoss-eni-pol related to the processing strategy between the operation support system (OSS) and the fusion system
  • the interface Eapp-eni-pol related to the processing strategy between the APP and the fusion system
  • the interface between the intention translation module and the knowledge management module The interface I ITA-KM-CMD
  • the interface I ITA-PM-CMD between the intention translation module and the policy management module.
  • this application is a schematic structural diagram of an intent-driven management system that includes IDM service consumers (IDM service consumers), IDM service producers (IDM service producers), and network infrastructure (network infrastructure). infrastructure).
  • the network infrastructure can be physical (physical) or virtual (virtual).
  • IDM uses a service-oriented interface to achieve the issuance of intent. Specifically, IDM service consumers send their intents to IDM service producers by calling the intent-driven management service (IDMS) interface; IDM service producers translate their intents into specific execution strategies and send them to the network infrastructure , And continuously monitor the network status during the execution of the intention to ensure that the intention is achieved or maintained.
  • IDM service consumers send their intents to IDM service producers by calling the intent-driven management service (IDMS) interface
  • IDM service producers translate their intents into specific execution strategies and send them to the network infrastructure , And continuously monitor the network status during the execution of the intention to ensure that the intention is achieved or maintained.
  • IDMS intent-driven management service
  • IDM service consumers include type A (type A) and type B (type B).
  • Type A including operations and notifications, has nothing to do with the specific type of intent, for example, it is a general operation for intent delivery.
  • Type B intention model
  • the currently given modeling elements should at least contain "actions” and "objects”.
  • an action is composed of an action name and a series of attributes required to complete the action; an object is composed of an object name and a series of attributes used to identify specific object instances. Therefore, the formal expression of the intention model is the following intention expression (for the sake of brevity, Driven is omitted below without causing ambiguity):
  • the intent expression model of "the percentage of users whose data rate is less than 5Mbps is less than 1% and the average data rate is not less than 7Mbps" is shown in Table 1 below:
  • Fig. 4 it is a schematic diagram of the functional modules involved in the intent translation and guarantee phase when the IDM system shown in Fig. 3 is applied to network equipment management.
  • the intent-based ENI fusion system (specifically EMS in Figure 4) architecture supports the translation and protection of intent.
  • the functional modules of ENI can be embedded in the element management system (EMS).
  • a network management system (NMS) sends an intent to the EMS, and the EMS interprets the intent, and sends the finally generated command to an assisted system (also called a network equipment (NE)).
  • NE executes the order and finally achieves its intention.
  • the NMS can be a user (user), an application (application), and an operation support system and a business support system (operation support system-and business support system-like functionality, OSS-and BSS-like functionality).
  • the intent translation FB queries the intent knowledge repository and obtains the intent operations and intents related to the intent.
  • the fulfillment condition also known as the intention goal
  • execution condition execution condition
  • network performance data goes through knowledge management FB, context awareness FB, situational awareness FB, MDE FB, and policy management FB to perform intent performance data interaction, intent achievement status, and intent policy update decisions to generate intent operations and execute intents. .
  • the intention operation, the intention target and the execution conditions are obtained from the intention knowledge base.
  • the instruction operation corresponding to the first execution condition cannot meet the intention achievement condition multiple times.
  • the next time the intention is implemented it is still unavoidable to select the instruction operation corresponding to the first execution condition, resulting in that the intention fulfillment condition cannot be met all the time.
  • the embodiments of the present application provide a communication method, device, and system.
  • the first network element can select the first operation according to the credibility and/or first information to achieve the first intention goal, which can improve the accuracy of the selection of the first operation .
  • FIG. 5 is a schematic diagram of the architecture of a communication system to which an embodiment of this application is applicable.
  • the communication system 100 includes a first network element 200, a second network element 300, and a third network element 400.
  • the second network element 300 transmits the created intention to the first network element 200 for execution.
  • the first network element 200 receives the intent of the second network element 300, translates the intent, obtains the intent operation, the intent target, and the execution conditions from the intent knowledge base, and performs operations such as orchestrating the intent, and arranges it as executable by the third network element 400
  • the command is transmitted to the third network element 400 for execution.
  • the third network element 400 receives the executable command of the first network element 12 and executes the command.
  • the first network element may be an EMS as shown in FIG. 4.
  • the second network element is the creator of the intention, and may be an NMS as shown in FIG. 4.
  • the third network element is an intended actor (infrastructure), and may be an NE as shown in FIG. 4.
  • the intent-based ENI fusion system supports the translation and protection of intent.
  • the EMS can be divided into two stages in the process of performing the above operations: the intention translation stage and the intention guarantee stage.
  • the intent translation stage it involves dataingestion and normalization FB, knowledge management FB, intent translation FB, context awareness FB, situational awareness FB, model-driven engineering FB, policy management FB, and output generation and denormalization FB.
  • the intent translation module in the translation queries from the intent knowledge base (the intent knowledge base can be located in the knowledge management function module) and obtains the intention operation, the intention target and the execution conditions.
  • policy management FB executes the intention.
  • policy management FB can change the intention operation according to the intention performance data, the intention achievement status, and the intention policy update status.
  • Figure 6 shows the four new interfaces added to the intent-based ENI fusion system interface, namely the interface between cognition management FB and knowledge management FB I KM-CM-CMD , cognition management
  • the interface between FB and context awareness FB is I CA-CM-CMD
  • the interface between cognition management FB and policy management FB is I PM-CM-CMD
  • the interface between cognition management FB and model driven engineer FB is I MDE-CM-CMD .
  • the recognition management FB analyzes and infers the knowledge and determines the intention knowledge that needs to be updated, and the intention knowledge management FB performs an update operation on the intent knowledge repository.
  • the intent knowledge repository adds at least one of the following intent knowledge to the intent strategy operation: the first reliability (used to indicate the reliability of achieving the first intent target) and the first information (used to achieve the first intent target).
  • the first information includes events (events) and impact values (impact).
  • the event includes the constraint condition or the intention target or execution condition of the second intention, and the influence value is used to indicate the degree of influence on the event.
  • the first credibility and first information of the intention strategy operation are updated according to the intention performance data, the intention achievement situation and the intention system generation strategy.
  • the intention strategy p For the intention strategy p, the set achievement goal is g, the reliability before the operation o is r, after the operation o, the monitoring current intention target is j, and the intention strategy p can be updated according to the following method when the operation o is used reliability:
  • r1, r2, and r3 can be user-defined, or set by the ENI system based on experience.
  • Impact definition and value impact is used to indicate/evaluate the degree of influence of operation O on the affected intention B, specifically used to indicate the influence value of operation O on the constraint conditions or intention goals or execution conditions of intention B. Its value can be zero and negative. The specific value can be [-1,0].
  • the first network element has not performed the first operation, but the second intention has been executed and the intention goal of the second intention has been achieved. Then, after the first network element performs the first operation, if the intention goal of the second intention changes from being achieved to not being reached, it is determined that the influence value of the first operation on the second intention is negative; or if the intention goal of the second intention is When the goal has been reached and the achievement status has not changed, it is determined that the value of the influence of the first operation on the second intention is zero.
  • the influence value of the first operation on the second intention is determined according to the achievement of the intention goal of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the intention goal of the second intention.
  • the first network element has not performed the first operation, but the second intention has been executed and the constraint condition of the second intention has been satisfied. Then, after the first network element performs the first operation, if the constraint condition of the second intention is changed from satisfied to unsatisfied when the first operation is executed compared to the first operation is not executed, the influence of the first operation on the second intention is determined The value is a negative value; or when the first operation is performed relative to the first operation, the constraint condition of the second intention has not changed, and the second intention has always been in the constraint condition, then it is determined that the first operation is The influence value of the intent is zero. That is, the influence value of the first operation on the second intention is determined according to the satisfaction of the constraint condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the constraint condition of the second intention.
  • the first network element has not performed the first operation, but the second intention has been executed and the execution condition of the second intention has been met. Then, after the first network element performs the first operation, if the execution condition of the second intention is changed from satisfied to unsatisfied when the first operation is executed compared to the first operation is not executed, the influence of the first operation on the second intention is determined The value is negative; or when the first operation is performed compared to the first operation, the execution condition of the second intention has not changed, and the second intention is always in the execution condition is satisfied, then it is determined that the first operation is The influence value of the intent is zero. That is, the influence value of the first operation on the second intention is determined according to the satisfaction of the execution condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the execution condition of the second intention.
  • the value of the influence of the first operation on the second intention can also be determined according to one or more of the foregoing situations.
  • the intention goal of intention A is to ensure a cell throughput of 80, and intention A adopts operation O to increase the downlink power.
  • the intended goal of Intent B is to ensure that the energy consumption of the cell is less than 100. Operation O of Intention A will affect Intention B. After adopting operation O, if the energy consumption of the cell in intention B is currently 120 (the last monitoring result is 90), then impact is -1; if the energy consumption of the cell in intention B is currently 90 (the last monitoring result is 90), then The impact is 0.
  • FIG. 7 it is a schematic flowchart of a communication method provided by an embodiment of this application. The method includes the following steps:
  • the first network element acquires the first knowledge of the first intention.
  • the first network element After the first network element receives the first intent issued by the second network element, it needs to translate the first intent, obtain the first knowledge of the first intent from the intent knowledge base, and perform calculations on the first intent based on the first knowledge.
  • Operations such as orchestration, orchestration are commands executable by the third network element.
  • the first knowledge includes: the first intent operation (intentOperations), the first intent fulfillment condition (intentFulfillmentCriterion) (also called the first intent target).
  • the information structure of the first intention operation is: intentOperations[execution condition (executionConditon), operation type (operationType), operation (operation)].
  • the first intention operation may also include the first degree of credibility to achieve the first intention goal, or the first intention operation may also include first information, or the first intention operation It may also include the first degree of credibility and the first information for achieving the first intended goal.
  • the first degree of credibility is used to indicate the reliability of achieving the first intended goal, that is, it indicates the achievement of the intended goal of the strategy after adopting the intended operation.
  • the first credibility is initialized, and the initial value is 100%.
  • the first credibility level is updated, and the change interval is [0%, 100%].
  • the first intention goal may be achieved, or the first intention goal may not be achieved, but when the first intention goal is close to being achieved, a degree of credibility is added to the original first degree of credibility Increment: After adopting the intention operation, the first intention goal is not achieved, and the first intention goal is far away, and an increase in the credibility level is reduced on the basis of the original first credibility level.
  • the first network element After the first network element executes the first intention operation, it may affect the second intention being executed in the first network element.
  • the second intention is different from the first intention, and may be any intention that is being executed in the first network element except the first intention.
  • the first information is used to indicate the influence of the operation of the first intention on the second intention.
  • the first information includes an event and an influence value
  • the event includes a constraint condition or an intention target or execution condition of the second intention, that is, the first information is used to indicate the constraint condition or intention target of the second intention by the first intention operation.
  • the influence value or degree of the execution condition The influence value can be zero or negative.
  • the first network element has not performed the first operation, but the second intention has been executed and the intended goal of the second intention has been achieved. Then, after the first network element performs the first operation, if the intention goal of the second intention changes from being achieved to not being reached, it is determined that the influence value of the first operation on the second intention is negative; or if the intention goal of the second intention is When the goal has been reached and the achievement status has not changed, it is determined that the value of the influence of the first operation on the second intention is zero. That is, the influence value of the first operation on the second intention is determined according to the achievement of the intention goal of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the intention goal of the second intention.
  • the first network element has not performed the first operation, but the second intention has been executed and the constraint condition of the second intention has been satisfied. Then, after the first network element performs the first operation, when the first operation is performed relative to the first operation is not performed, the constraint condition of the second intention is changed from satisfied to unsatisfied, and the influence value of the first operation on the second intention is determined Negative value; or when the first operation is performed relative to the first operation, the constraint condition of the second intention has not changed, and the second intention has been in the constraint condition has been met, then it is determined that the first operation is for the second intention
  • the influence value of is zero. That is, the influence value of the first operation on the second intention is determined according to the satisfaction of the constraint condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the constraint condition of the second intention.
  • the first network element has not performed the first operation, but the second intention has been executed and the execution condition of the second intention has been met. Then after the first network element performs the first operation, when the first operation is performed relative to the first operation is not performed, the execution condition of the second intention changes from satisfied to unsatisfied, and then the influence value of the first operation on the second intention is determined Negative value; or when the first operation is performed compared to the first operation, the execution condition of the second intention has not changed, and the second intention has been in the execution condition has been met, then it is determined that the first operation is for the second intention
  • the influence value of is zero. That is, the influence value of the first operation on the second intention is determined according to the satisfaction of the execution condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the execution condition of the second intention.
  • the first network element obtains the first knowledge of the first intention, specifically, there may be the following implementation manners:
  • the first network element itself determines the first knowledge of the first intention.
  • the first knowledge obtained in the process of intention creation or intention translation is stored in the intention knowledge base of the first network element.
  • the first network element receives the expression of the first intention from the second network element, performs lexical and grammatical analysis on the expression of the first intention, and obtains the intention keywords corresponding to the expression of the first intention.
  • the intention keyword includes one or more of the following information: the first intention target, the area where the first intention acts, and the name of the network element where the first intention acts.
  • the first network element obtains the first knowledge corresponding to the intent keyword from the intent knowledge base according to the obtained intent keyword.
  • the first network element obtains the intention performance data from the third network element.
  • the first network element determines the satisfaction of the first condition of the first intention according to the acquired intention performance data.
  • the first condition includes one or more of the following information: the first intention target, the constraint condition of the first intention, and the execution condition of the first intention.
  • the first network element determines the first knowledge of the first intention according to the satisfaction of the first condition and the second knowledge of the first intention, where the second knowledge of the first intention is the knowledge before the first knowledge of the first intention is updated .
  • the first knowledge may be the first degree of credibility.
  • the first intention goal is achieved, and the first credibility level is determined to be the sum of the second credibility level and the first credibility level increment; or the first intention goal is not reached, and the first achievement of the first intention goal
  • the difference between the second achievement situation and the first intention goal is a negative value
  • the first credibility level is determined to be the sum of the second credibility level and the second credibility level increment, and the second credibility level increment is less than the first credibility level increment.
  • the first degree of credibility is determined to be the difference between the second degree of credibility and the third degree of credibility Poor; where the second credibility is the credibility before the first credibility is updated, and the first achievement is the absolute value of the difference between the achievement of the first intention goal in the first time period and the first intention goal,
  • the second achievement situation is the absolute value of the difference between the achievement situation of the first intention goal in the second time period and the first intention goal, and the second time period is earlier than the first time period.
  • the determination of the first knowledge of the first intention by the first network element may be understood as that the first network element obtains the first knowledge by updating the second knowledge.
  • the first network element may update the first knowledge to the intent knowledge base.
  • the first network element may receive the first knowledge of the first intention from the second network element, thereby obtaining the first knowledge of the first intention.
  • the first network element receives the first information from the second network element.
  • the second network element is a functional entity such as NMS, user, APP, operation support system, or business support system.
  • the second network element issues the first intent to the first network element, and the first network element may notify the second network element that the operation corresponding to the first intent is the first intent during or after the first intent is executed Operation, so that the second network element can learn the first intended operation.
  • the second network element may also issue the second intent to the first network element before, at the same time or after issuing the first intent. Among them, the second intention is different from the first intention.
  • the second network element After acquiring the first intention operation corresponding to the first intention, the second network element determines that the first intention operation has an influence on the second intention. Specifically, the operation of the first intention has an influence on the constraint condition or the intention target or execution condition of the second intention. After determining that the operation of the first intention has an effect on the second intention, the second network element sends the first information to the first network element.
  • the first information is used to indicate the influence of the operation of the first intention on the second intention.
  • the first network element can receive the first information from the second network element. The first information is used for the selection of the above-mentioned first operation.
  • the first network element selects a first operation according to the first knowledge of the first intention.
  • the first knowledge includes the first credibility and/or first information for achieving the first intention goal, and the first operation can be selected based on the first knowledge.
  • the first operation is used to execute the first intention.
  • the first network element operates according to the first achievement of the first intention goal, the second knowledge corresponding to one or more existing intentions, and the first knowledge of the first intention, in one or more existing intentions.
  • the first operation may be the above-mentioned first intended operation or other operations.
  • the first network element selects the first operation based on the first knowledge.
  • the selection process takes into account the reliability of achieving the first intention goal and/or the influence of the first operation on the second intention, thereby improving the reliability of achieving the first intention goal ⁇ ;
  • the selected first operation avoids the impact of other intentions being executed in the first network element, thereby improving the reliability of achieving multiple intentions in the first network element.
  • the first network element can select the first operation according to the credibility of achieving the first intended goal and/or the first information, which can improve the accuracy of the selection of the first operation.
  • the first stage intent translation stage
  • FIG. 8 it is a schematic diagram of the communication method flow in the intention translation process provided by this embodiment of the application.
  • the method may include the following steps:
  • the second network element sends a create intent invoking request to the ENI system, specifically, sends the create intent invoking request to the data intent and normalization FB of the first network element.
  • the second network element may also be referred to as the intention creator.
  • the second network element can be a functional entity such as NMS, user, APP, operation support system, and business support system. As shown in Figure 8, in general, the second network element is an external system relative to the ENI system (first network element).
  • the intention creation request carries the intention expression of the first intention.
  • the intention expression can refer to the above description.
  • the intention creation initiation request is used to request the creation of the first intention within the first network element.
  • the request is passed through the strategy/intent interface between ENI and the external system.
  • the dataingestion and normalization FB After the dataingestion and normalization FB receives the intention creation initiation request, it performs a data normalization operation and sends the normalized first intent to the knowledge management FB.
  • Knowledge management FB stores the normalized first intention and determines the functional entity that sends the intention.
  • the knowledge management FB determines that the functional entity sending the intent is any one of the functional entities such as NMS, user, APP, operation support system, and business support system.
  • Knowledge management FB sends an intent translation request to intent translation FB.
  • the intention transfer request is used to request translation of the above-mentioned first intention.
  • the intent translation FB recognizes the intent translation request and assigns an intent ID (intent ID) to the intent.
  • the intent identifier is used to identify the first intent.
  • the intent translation FB sends an intent creation initiation request response preparation to the denormalization and output generation FB.
  • Denormalization and output generation FB sends an intent creation initiation request response to the second network element.
  • the response is used to indicate that the above-mentioned intention creation initiation request is received.
  • Intent translation FB performs intent analysis on the first intent.
  • intent analysis includes performing lexical and grammatical analysis on the intent expression of the first intent to obtain the intent keywords corresponding to the intent expression of the first intent, that is, to obtain the intent keywords required for querying the intent knowledge base and the network knowledge base .
  • the intention keyword includes one or more of the following information: the first intention target, the area where the first intention acts, and the network element name of the first intention.
  • step S209 If there is an error in the parsing of the first intent in step S208, the intent translation FB to denormalization
  • Denormalization and output generation FB sends a notice of intention error initiation to the second network element.
  • Intent translation FB updates the first intent parsing error to the intent knowledge repository.
  • step S212 If there is no error in the first intent parsing in step S208, the intent translation FB updates and stores the intent keyword in the intent knowledge repository.
  • Intent translation FB sends an intent knowledge query request to knowledge management FB, carrying the intent keywords in S208, and obtains intent knowledge/network information from the intent knowledge repository sub-FB.
  • the intent knowledge query request is used to request to obtain the first knowledge of the first intent corresponding to the above-mentioned intent keyword. Further, the intent knowledge query request may also be used to request to obtain the network information corresponding to the above-mentioned intent keyword.
  • Knowledge management FB searches the intent knowledge repository sub-FB for the first knowledge corresponding to the intent keyword according to the received intent keywords, and then sends an intent knowledge query request response to the intent translation FB.
  • the intent knowledge query request response carries the above-mentioned intent identifier, the first intent target (intentFulfillment Criterion), and the first intent operation.
  • intentOperations The information contained in the current first intent operation (intentOperations) is: intentOperations[executionConditon, operationType, operation].
  • this embodiment supplements the information contained in the first intention operation.
  • the information contained in the first intention operation may be in the following situations:
  • intentOperations [executionConditon, operationType, operation, reliability]. That is, in this case, the first knowledge: reliability is added to the first intention operation.
  • executionConditon is the execution condition
  • operationType is the operation type
  • operation is the intention operation.
  • the first knowledge of the first intention obtained according to the intent keyword query can be used for the selection of operations in the subsequent process of guaranteeing the first intention.
  • Intent translation FB combines the first knowledge through the syntax tree and semantic analysis, and updates the combined first knowledge to the intent knowledge repository.
  • Intent translation FB sends a notification of completion of intent translation to context awareness FB, and carries the Intent ID, intentFulfillmentCriterion, and intentOperations.
  • the executionConditon of the first intention includes a key performance indicator (KPI), which is used to determine the satisfaction of the execution condition of the first intention in the context information.
  • KPI key performance indicator
  • context awareness FB adds the context information of the first intention, and updates it to knowledge management FB.
  • context awareness FB performs intent context awareness on the above-mentioned information carried in the notice of completion of intent translation, and obtains the context information of the first intent.
  • the context awareness FB sends an intent context awareness end notification to the situational awareness FB, and carries the Intent ID, intentFulfillmentCriterion, intentOperations and added context information. These carried messages contain the first intention goal, which is used to measure the achievement of the first intention goal.
  • situational awareness FB performs intention state awareness based on the information carried in the above-mentioned intention context awareness end notification, and obtains the state information of the first intention.
  • the situational awareness FB sends an intent state awareness end notification to the model driven engineering FB, and carries the Intent ID, intentFulfillmentCriterion, intentOperations, the added context information and the state information of the first intention.
  • the intent state awareness end request is used to request model-driven engineering to generate and execute the first intent corresponding to the Intent ID.
  • the model-driven engineering FB selects the first operation based on the first credibility and/or the first knowledge.
  • model driven engineering FB selects the first operation based on the first degree of credibility.
  • the model driven engineering FB selects the first operation based on the first information.
  • the model driven engineering FB selects the first operation based on the first credibility level and the first information.
  • model-driven engineering FB performs intention operation instruction conversion and updates to knowledge management FB.
  • the model driven engineering FB converts the format of the selected first operation into an operation instruction that can be recognized by the module inside the ENI system.
  • the model-driven engineering FB sends a notification of the completion of the intention command conversion to the policy management FB.
  • the policy management FB performs the type conversion of the intention operation instruction and updates it to the knowledge management FB.
  • the policy management FB converts the format of the first operation into an operation instruction that can be recognized by the external system.
  • the policy management FB sends an intention command generation request to the denormalization and output generation FB.
  • Denormalization and output generation FB sends an intention command execution request to the third network element.
  • the second stage the intention assurance process
  • the first knowledge includes the first degree of credibility to achieve the first intended goal.
  • the method may include the following steps:
  • the context awareness FB sends an intention performance data subscription request preparation to the denormalization and output generation FB.
  • the intention performance data subscription request is prepared to carry the first intention target, the KPI in the executionConditon.
  • Denormalization and output generation FB sends an intention performance data subscription request to the third network element.
  • the third network element sends an intention performance data subscription response to the ENI system, carrying the requested intention performance data.
  • the third network element obtains the achievement status of the first intention target, the satisfaction status of the execution condition of the first intention, and the constraints of the first intention according to the first intention target carried in the intention performance data subscription request, the KPI in the executionConditon Intentional performance data such as the satisfaction of conditions. Then, the third network element sends an intention performance data subscription response to the dataingestion and normalization FB.
  • the intention performance data subscription response carries the above intention performance data.
  • Data ingestion and normalization FB sends the normalized intent performance data to the knowledge management FB.
  • Knowledge management FB stores the received intent performance data in the policy knowledge base.
  • Knowledge management FB obtains the intent strategy from the strategy knowledge base according to the first intent target, and then sends the intent strategy and intent performance data request to the context awareness FB, carrying the intent strategy, and the achievement of the first intent target and the first intent Intent performance data related to the fulfillment of the execution conditions.
  • Context awareness FB updates the context information of the intention according to the received intention policy and intention performance data.
  • the context information of the intention includes KPI information in the execution condition of the first intention.
  • context awareness FB updates the context information of the intention to knowledge management FB.
  • the context awareness FB sends an intention context information awareness end notification to the situational awareness FB, which carries the intention strategy, the context information of the intention, and the intention performance data related to the achievement of the first intention target.
  • Situational awareness FB judges whether the first intention goal is achieved according to the received intention strategy and intention performance data, estimates the achievement of the first intention goal, and updates the intention state information.
  • the intention status information includes the achievement of the first intention goal and the possibility of achievement, and the intention status information is updated to knowledge management FB.
  • Situational awareness FB sends a notification of the end of intent state awareness to model driven engineering FB, which carries intent policy, intent context information, and intent state information.
  • the model driven engineering FB determines the first operation that needs to be performed according to the reliability in the intentOperations of the intent strategy.
  • modeldriven engineeringFB determines the first operation that needs to be performed based on the current possibility of achieving the first intention goal and the historical first degree of credibility to achieve the first intention goal.
  • the first operation may be the first intention operation, or other intention operations obtained from the intention knowledge base based on the intention keywords.
  • the intent translation function module obtains from the intent knowledge base there are three kinds of intent operations corresponding to the intent keywords, and each intent operation corresponds to different intent targets and execution conditions.
  • model driven engineeringFB estimates that the first intention goal cannot be achieved according to the received achievement of the first intention goal compared with the first intention goal, then model-driven engineeringFB selects other intention operations; if the first type of intention operation history has a high first degree of credibility, and situational awareness FB predicts that the first intention goal can be achieved, modeldriven engineeringFB selects the first intention operation.
  • model-driven engineering FB performs intention operation instruction conversion and updates to knowledge management FB.
  • the model driven engineering FB converts the format of the selected first operation into an operation instruction that can be recognized by the module inside the ENI system.
  • the model-driven engineering FB sends a notification of the completion of the conversion of the intended operation instruction to the policy management FB.
  • the policy management FB performs the type conversion of the intention operation instruction, and updates it to the knowledge management FB.
  • the policy management FB converts the format of the first operation into an operation instruction that can be recognized by the external system.
  • the policy management FB sends a notification of the intention operation instruction to the recognition management FB.
  • the notification of the intended operation instruction issuance includes the first operation to be performed.
  • the first operation is the first operation that the policy management FB needs to perform in step S314.
  • the recognition management FB requests the situational awareness FB for the achievement of the first intention target before the execution of the first operation.
  • the situational awareness FB sends a response to the recognition management FB to indicate that the above request is received.
  • situational awareness FB estimates the possibility of achieving the first intention goal based on the intent performance data corresponding to the first intention. Therefore, situational awareness FB can send a response to the recognition management FB, and the response carries the achievement of the first intention goal. Possibility.
  • Cognition management FB analyzes, infers, and evaluates the intention strategy, and determines the first credibility of the update.
  • the first degree of credibility is used to indicate the reliability of achieving the first intended goal.
  • cognition management FB After cognition management FB has obtained the possibility of achieving the first intention goal sent by situational awareness FB, that is, after the first operation is performed, the intention strategy can be analyzed, reasoned, and evaluated, and the first degree of credibility can be regained.
  • the reliability update method is: for example, for the intention strategy p, its achieved goal is g, the currently monitored first intention goal is j, and the reliability update is r.
  • the reliability can be updated according to the following method:
  • the recognition management FB sends an intention knowledge update request to the knowledge management FB, carrying the updated reliability.
  • the knowledge management FB After the knowledge management FB receives the intent knowledge update request, it updates the first knowledge of the first intent in the intent knowledge repository.
  • the knowledge management FB sends an update response to the recognition management FB.
  • the policy management FB sends an intention command execution request to the denormalization and output generation FB.
  • Denormalization and output generation FB sends an intention command execution request to the third network element.
  • the foregoing process 1 and process 2 may be executed in parallel, that is, updating the first credibility and executing the first operation may be executed in parallel, which can improve the execution efficiency of the ENI system.
  • the above-mentioned process one and process two can be executed cyclically, that is, the first credibility level can be continuously updated according to the intent performance data during the execution of the first intention, or continuously
  • the intent strategy corresponding to the first intent is executed until the intent strategy is deactivated or deleted.
  • the first network element can estimate the probability of achieving the first intent target based on the intent performance data corresponding to the first intent, estimate the first degree of credibility for achieving the first intent target, and use the estimated first intent.
  • a credibility level is updated to the intent knowledge base so that the first network element can subsequently select the first operation based on the updated first credibility level, which improves the accuracy of the first operation selection; and in the current selection operation, it can be based on Selecting the first operation for the first credibility of history improves the accuracy of the first operation selection.
  • the first knowledge includes first information.
  • the method may include the following steps:
  • the context awareness FB sends an intention performance data subscription request preparation to the denormalization and output generation FB.
  • the intention performance data subscription request is prepared to carry the first intention target, the KPI in the executionConditon, and the first information.
  • Denormalization and output generation FB sends an intention performance data subscription request to a third network element.
  • the third network element sends an intention performance data subscription response to the ENI system, carrying the requested intention performance data.
  • the third network element obtains the achievement status of the first intention target, the satisfaction status of the execution condition of the first intention, and the constraints of the first intention according to the first intention target carried in the intention performance data subscription request, the KPI in the executionConditon Intentional performance data such as the satisfaction of conditions.
  • the intent performance data subscription request also carries events and impact in the first information to request to obtain the intent performance data of the second intent, so that cognition management FB updates the impact according to the obtained intent performance data of the second intent.
  • the third network element sends an intention performance data subscription response to the dataingestion and normalization FB.
  • the intention performance data subscription response carries the above intention performance data.
  • data ingestion and normalization FB sends the normalized intent performance data to the knowledge management FB.
  • Knowledge management FB stores the received intent performance data in the policy knowledge base.
  • Knowledge management FB obtains the intent strategy from the strategy knowledge base according to the first intent target, and then sends the intent strategy and intent performance data request to the context awareness FB, carrying the intent strategy, and the achievement of the first intent target and the first intent Intentional performance data related to the fulfillment of the execution conditions of, and intent performance data related to the first information.
  • context awareness FB updates the context information of the intent according to the received intent policy and intent performance data.
  • the context information of the intention includes KPI information in the execution condition of the first intention.
  • context awareness FB updates the context information of the intention to knowledge management FB.
  • the context awareness FB sends an intention context information awareness end notification to the situational awareness FB, carrying the intention policy, the context information of the intention, and the intention performance data related to the achievement of the first intention target.
  • Situational awareness FB judges whether the first intention goal is achieved according to the received intention strategy and intention performance data, estimates the achievement of the first intention goal, and updates the intention state information.
  • the intention status information includes the achievement of the first intention goal and the possibility of achievement, and the intention status information is updated to knowledge management FB.
  • the situational awareness FB sends an intent state awareness end notification to the model driven engineering FB, which carries the intent policy, the intent context information, and the intent state information.
  • model-driven engineering FB determines the first operation to be performed according to the events and impact in the intentOperations of the intent strategy.
  • model-driven engineering FB determines the first operation that needs to be performed based on the current possibility of achieving the first intention goal, and the historical first events and impacts that achieve the first intention.
  • the model driven engineering FB determines the first operation that needs to be performed according to the received possibility of achieving the goal of the first intention and the influence value of the operation of the first intention on the second intention. For example, if the first intention operation is performed, the possibility of achieving the first intention goal is low, and/or the influence value of the first intention operation on the second intention is negative, then model driven engineering FB selects other intention keywords corresponding to the The intended operation is the first operation. For another example, if the first intention operation is performed, the possibility of achieving the first intention goal is higher, and/or the influence value of the first intention operation on the second intention is zero, then model driven engineering FB selects the first intention operation as First operation.
  • model-driven engineering FB converts intention operation instructions, and updates to knowledge management FB.
  • the model driven engineering FB converts the format of the selected first operation into an operation instruction that can be recognized by the module inside the ENI system.
  • the model-driven engineering FB sends a notification of the completion of the conversion of the intended operation instruction to the policy management FB.
  • the policy management FB performs the type conversion of the intention operation instruction, and updates it to the knowledge management FB.
  • the policy management FB converts the format of the first operation into an operation instruction that can be recognized by the external system.
  • the policy management FB sends a notification of the intention operation instruction to the recognition management FB.
  • the notification of the intended operation instruction issuance includes the first operation to be performed.
  • the first operation is the first operation that the policy management FB needs to perform in step S414.
  • the recognition management FB requests the context awareness FB for the context of the second intention before the execution of the first operation.
  • the context awareness FB performs context awareness analysis of the first information data, and sends a response to the recognition management FB to indicate that the above request is received.
  • context awareness FB analyzes the impact of events based on context awareness, and sends the impact to the recognition management FB.
  • context awareness FB performs context awareness analysis based on the context information of the first and second intentions, and evaluates the impact of the events, specifically, evaluates the impact value of the execution of the first operation on the intention targets or constraints or execution conditions of the second intention , To obtain the impact of the situational perception results.
  • context awareness FB sends the context awareness result of the impact to the recognition management FB.
  • Cognition management FB analyzes, infers, evaluates the intent strategy of the first intent according to the acquired intent performance data, calculates and updates the impact.
  • Cognition management FB analyzes, infers, evaluates the intention strategy of the first intention, and calculates the impact according to the received performance data of the first intention and the second intention of the intention and the context awareness result of the impact sent by the context awareness FB.
  • the first network element has not performed the first operation, but the second intention has been executed and the intention goal of the second intention has been achieved. Then, after the first network element performs the first operation, if the intention goal of the second intention changes from being achieved to not being reached, it is determined that the influence value of the first operation on the second intention is negative; or if the intention goal of the second intention is When the goal has been reached and the achievement status has not changed, it is determined that the value of the influence of the first operation on the second intention is zero.
  • the first network element has not performed the first operation, but the second intention has been executed and the constraint condition of the second intention has been satisfied. Then, after the first network element performs the first operation, if the constraint condition of the second intention is changed from satisfied to unsatisfied when the first operation is executed compared to the first operation is not executed, the influence of the first operation on the second intention is determined The value is a negative value; or when the first operation is performed relative to the first operation, the constraint condition of the second intention has not changed, and the second intention has always been in the constraint condition, then it is determined that the first operation is The influence value of the intent is zero.
  • the first network element has not performed the first operation, but the second intention has been executed and the execution condition of the second intention has been met. Then, after the first network element performs the first operation, if the execution condition of the second intention is changed from satisfied to unsatisfied when the first operation is executed compared to the first operation is not executed, the influence of the first operation on the second intention is determined The value is negative; or when the first operation is performed compared to the first operation, the execution condition of the second intention has not changed, and the second intention is always in the execution condition is satisfied, then it is determined that the first operation is The influence value of the intent is zero.
  • the value of the influence of the first operation on the second intention can also be determined according to one or more of the foregoing situations.
  • the intention goal of intention A is to ensure a cell throughput of 80, and intention A adopts operation O to increase the downlink power.
  • the intended goal of Intent B is to ensure that the energy consumption of the cell is less than 100. Operation O of Intention A will affect Intention B. After adopting operation O, if the energy consumption of the cell in intention B is currently 120 (the last monitoring result is 90), then impact is -1; if the energy consumption of the cell in intention B is currently 90 (the last monitoring result is 90), then The impact is 0.
  • the recognition management FB sends an intention knowledge update request to the knowledge management FB, where the intention knowledge update request includes the first information.
  • the first information includes the events and the updated impact.
  • the knowledge management FB After receiving the intention knowledge update request, the knowledge management FB updates the first information carried in the intention knowledge update request to the intent knowledge repository.
  • the knowledge management FB sends an update response to the recognition management FB.
  • the policy management FB sends an intention command execution request to the denormalization and output generation FB.
  • Denormalization and output generation FB sends an intention command execution request to the third network element.
  • the foregoing process 1 and process 2 may be executed in parallel, that is, updating the first information and executing the first operation may be executed in parallel, which can improve the execution efficiency of the ENI system.
  • the above-mentioned process 1 and process 2 can be executed cyclically, that is, the first information can be continuously updated according to the intention performance data during the execution of the first intention, or the first information can be continuously executed.
  • the first network element can estimate the impact value of the first operation on the second intention based on the intention performance data corresponding to the second intention, and update the event and the estimated impact value to the intention knowledge base so that The first network element can subsequently select the first operation based on the updated event and impact value, which improves the accuracy of the first operation selection.
  • the method may include the following steps:
  • the context awareness FB sends an intention performance data subscription request preparation to the denormalization and output generation FB.
  • the intention performance data subscription request is prepared to carry the first intention target, the KPI in the executionConditon, and the KPI in the first information.
  • Denormalization and output generation FB sends an intention performance data subscription request to the third network element.
  • the third network element sends an intention performance data subscription response to the ENI system, carrying the requested intention performance data.
  • the third network element obtains the achievement status of the first intention target and the satisfaction status of the execution condition of the first intention and other intention performance data according to the first intention target carried in the intention performance data subscription request and the KPI in the executionConditon.
  • the intent performance data subscription request also carries events and impact in the first information to request to obtain the intent performance data of the second intent, so that cognition management FB updates the impact according to the obtained intent performance data of the second intent.
  • the third network element sends an intention performance data subscription response to the dataingestion and normalization FB.
  • the intention performance data subscription response carries the above intention performance data.
  • Data ingestion and normalization FB sends the normalized intent performance data to the knowledge management FB.
  • Knowledge management FB stores the received intent performance data in the policy knowledge base.
  • Knowledge management FB obtains the intent strategy from the strategy knowledge base according to the first intent target, and then sends the intent strategy and intent performance data request to the context awareness FB, carrying the intent strategy, and the achievement of the first intent target and the first intent Intentional performance data related to the fulfillment of the execution conditions of, and intent performance data related to the first information.
  • Context awareness FB updates the context information of the intent according to the received intent policy and intent performance data.
  • the context information of the intention includes KPI information in the execution condition of the first intention.
  • context awareness FB updates the context information of the intention to knowledge management FB.
  • the context awareness FB sends an intention context information awareness end notification to the situational awareness FB, carrying the intention strategy, the context information of the intention, and the intention performance data related to the achievement of the first intention target.
  • Situational awareness FB judges whether the first intention goal is achieved according to the received intention strategy and intention performance data, estimates the achievement of the first intention goal, and updates the intention status information.
  • the intention status information includes the achievement of the first intention goal and the possibility of achievement, and the intention status information is updated to knowledge management FB.
  • the situational awareness FB sends an intent state awareness end notification to the model driven engineering FB, which carries the intent policy, intent context information, and intent state information.
  • model-driven engineering FB determines the first operation that needs to be performed according to the reliability, events, and impact in the intentOperations of the intent strategy.
  • model-driven engineering FB decides what needs to be executed based on the current possibility of achieving the first intention goal, the first credibility of the historical achievement of the first intention goal, and the historical first event events and impact that achieve the first intention goal.
  • the model driven engineering FB determines the first operation that needs to be performed according to the received possibility of achieving the first intent goal, the historical first credibility of achieving the first intent goal, and the influence value of the first intent operation on the second intent. For example, if the first intention operation is performed, if the first credibility of the history of the first intention operation is low, the possibility of achieving the first intention goal is low, and/or the influence value of the first intention operation on the second intention If it is a negative value, model driven engineering FB selects other intention operations corresponding to the intention keywords as the first operation.
  • model driven engineering FB selects the first intention operation as the first operation.
  • model-driven engineering FB performs intention operation instruction conversion and updates to knowledge management FB.
  • the model driven engineering FB converts the format of the selected first operation into an operation instruction that can be recognized by the module inside the ENI system.
  • the model-driven engineering FB sends a notification of the completion of the conversion of the intended operation instruction to the policy management FB.
  • the policy management FB performs the type conversion of the intention operation instruction, and updates it to the knowledge management FB.
  • the policy management FB converts the format of the first operation into an operation instruction that can be recognized by the external system.
  • the policy management FB sends a notification of the intention operation instruction to the recognition management FB.
  • the notification of the intended operation instruction issuance includes the first operation to be performed.
  • the first operation is the first operation that the policy management FB needs to perform in step S514.
  • the recognition management FB requests the context awareness FB for the context of the second intention before the execution of the first operation.
  • the context awareness FB performs context awareness analysis of the first information data, and sends a response to the recognition management FB to indicate that the above request is received.
  • context awareness FB analyzes the impact of events based on context awareness, and sends the impact to the recognition management FB.
  • context awareness FB performs context awareness analysis based on the context information of the first and second intentions, and evaluates the impact of the events, specifically, evaluates the impact value of the execution of the first operation on the intention targets or constraints or execution conditions of the second intention , To obtain the impact of the situational perception results.
  • context awareness FB sends the context awareness result of the impact to the recognition management FB.
  • the recognition management FB requests the situational awareness FB for the achievement of the first intention target before the execution of the first operation.
  • the situational awareness FB sends a response to the recognition management FB to indicate that the above request is received.
  • situational awareness FB predicts the possibility of achieving the first intention goal based on the intent performance data corresponding to the first intention. Therefore, situational awareness FB can send a response to the recognition management FB, and the response carries the achievement of the first intention goal. Possibility.
  • Cognition management FB analyzes, infers, evaluates, calculates and updates the impact of the intent strategy of the first intent according to the acquired intent performance data; and cognition management FB analyzes, infers, and evaluates the intent strategy to determine the first possible update Degree of trust.
  • the first degree of credibility is used to indicate the reliability of achieving the first intended goal.
  • the cognition management FB sends an intention knowledge update request to the knowledge management FB, where the intention knowledge update request includes the updated first knowledge.
  • the updated first knowledge includes the updated first credibility and first information.
  • the first information includes the events and the updated impact.
  • the knowledge management FB After receiving the intention knowledge update request, the knowledge management FB updates the first knowledge carried in the intention knowledge update request to the intent knowledge repository.
  • the knowledge management FB sends an update response to the recognition management FB.
  • the policy management FB sends an intention command execution request to the denormalization and output generation FB.
  • Denormalization and output generation FB sends an intention command execution request to the third network element.
  • the foregoing process 1 and process 2 may be executed in parallel, that is, updating the first knowledge and executing the first operation may be executed in parallel, which can improve the execution efficiency of the ENI system.
  • the above-mentioned process one and process two can be executed cyclically, that is, the first knowledge can be continuously updated according to the intent performance data during the execution of the first intention, or the first knowledge can be continuously executed.
  • the first network element can recalculate the first knowledge according to the intent performance data corresponding to the second intent, and update the recalculated first knowledge to the intent knowledge base, so that the first network element can subsequently
  • the first operation is selected according to the updated first knowledge, which improves the accuracy of the first operation selection.
  • FIG. 12 it is a schematic flowchart of yet another communication method provided by an embodiment of this application.
  • the method includes the following steps:
  • the second network element obtains the first intended operation from the first network element.
  • the second network element issues the first intent to the first network element, and the first network element arranges the intent, obtains the first knowledge of the first intent from the intent knowledge repository, and selects the first operation based on the first knowledge.
  • the first operation Used to execute the first intent.
  • the first operation is the first intended operation.
  • the second network element may be a user, APP, OSS and other functional entities.
  • the first network element may notify the second network element that the operation corresponding to the first intention is the first intention operation, so that the second network element can learn the first intention operation.
  • the second network element obtains the first intention operation from the policy management FB of the first network element.
  • the second network element determines that the operation of the first intention has an influence on the second intention.
  • the second network element may also issue the second intent to the first network element before, at the same time or after issuing the first intent.
  • the second intention is different from the first intention.
  • the second network element determines that the first intention operation has an influence on the second intention. Specifically, the operation of the first intention has an influence on the constraint condition or the intention target or execution condition of the second intention.
  • the second network element sends an intention knowledge update request to the data ingestion and normalization FB of the first network element.
  • the second network element After the second network element determines that the operation of the first intention has an impact on the second intention, it needs to update the first knowledge of the first intention in the first network element. Specifically, the first information of the first intention is updated.
  • the first information specifically refers to an event, and may not include an influence value.
  • the update request also does not include the first degree of credibility. Because the influence value and the first degree of credibility are evaluation indicators, they need to be evaluated and updated during the operation of the ENI system, and do not need to be updated by an external system (ie, the second network element).
  • the above-mentioned first information can be carried through the intention knowledge update request.
  • the intention knowledge update request is used to request to update the first knowledge of the first intention.
  • the first information is used to indicate the influence of the operation of the first intention on the second intention. Specifically, the first information is used to indicate the influence of the operation of the first intention on the constraint condition or the intention target or execution condition of the second intention.
  • the first information is used for the selection of the first operation.
  • the first operation is used to execute the first intention.
  • the data ingestion and normalization FB forwards the above-mentioned intention knowledge update request to the recognition management FB.
  • the recognition management FB analyzes the first information, and determines whether to update the first information to the intent knowledge repository.
  • cognition management FB After the cognition management FB receives the intention knowledge update request, it obtains the first information carried in the intention knowledge update request, analyzes the first information, and determines whether to update the first information to the intent knowledge repository. Specifically, for example, cognition management FB judges whether the first intention operation has an effect on the constraint condition or intention target or execution condition of the second intention. If the result of the judgment is yes, it is determined that the first information needs to be updated to intent knowledge repository; otherwise, it is determined that the first information does not need to be updated to the intent knowledge repository.
  • the recognition management FB sends an intention knowledge update request to the knowledge management FB, and the intention knowledge update request includes the first information.
  • the intent knowledge update request is used to request to update the first information to the intent knowledge repository.
  • the intent knowledge repository is set in knowledge management FB. Therefore, the recognition management FB sends an intention knowledge update request to the knowledge management FB, and the intention knowledge update request includes the first information.
  • Knowledge management FB updates the first information to the intent knowledge repository.
  • the knowledge management FB sends an intention knowledge update response to the recognition management FB, and the second intention knowledge update response is used to indicate whether the update is successful.
  • the recognition management FB sends an intention knowledge update response to the dataingestion and normalization FB.
  • the recognition management FB sends an intent knowledge update response to the second network element; if it is determined in S605 that it does not need to be updated, the recognition management FB sends an intent knowledge update response to the external system.
  • the intention knowledge update response is used to indicate that no update is required.
  • the first network element After the first network element updates the first information to the intent knowledge repository, the next time when the first intent is executed, it obtains the first knowledge from the intent knowledge repository according to the intent keywords. If the first knowledge includes the above first information, then the first A network element can select the first operation based on the first knowledge. For example, assuming that the first intention operation has a negative influence on the second intention, the first network element avoids selecting the first intention operation; assuming that the first intention operation affects the second intention If the influence of is zero, the first network element can select the first intended operation as the first operation.
  • the second network element when the second network element obtains that the first network element performs the first intention operation and determines that the first intention operation affects the second intention, the second network element can The first network element indicates the influence of the first intention operation on the second intention, so that the first network element accurately selects the first operation.
  • the methods and/or steps implemented by the first network element can also be implemented by components (such as chips or circuits) that can be used for the first network element; those implemented by the second network element
  • the methods and/or steps may also be implemented by components (such as chips or circuits) of the second network element.
  • an embodiment of the present application also provides a communication device, which is used to implement the foregoing various methods.
  • the communication device may be the first network element in the foregoing method embodiment, or a device including the foregoing first network element, or a component that can be used in the first network element; or, the communication device may be the foregoing method embodiment
  • the second network element, or a device including the above-mentioned second network element, or a component that can be used for the second network element includes hardware structures and/or software modules corresponding to each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered as going beyond the scope of this application.
  • the embodiments of the present application may divide the communication device into functional modules according to the foregoing method embodiments.
  • each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module.
  • the above-mentioned integrated modules can be implemented in the form of hardware or software function modules. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.
  • the communication device 500 includes: a processing unit 51, and may also include a transceiver unit 52; wherein:
  • the processing unit 51 is configured to obtain first knowledge of a first intention, and the first knowledge of the first intention includes one or more of the following information: a first degree of credibility and a first degree of credibility to achieve the goal of the first intention Information, the first degree of credibility is used to indicate the reliability of achieving the first intention goal, the first information is used to indicate the influence of the first intention operation on the second intention, and the second intention is related to the The first intention is different;
  • the processing unit 51 is further configured to select a first operation according to the first knowledge of the first intention, and the first operation is used to execute the first intention.
  • the first network element can select the first operation according to the credibility of achieving the first intended goal and/or the first information, which can improve the accuracy of the selection of the first operation.
  • the first information includes an event and an impact value
  • the event includes a constraint condition or an intention target or an execution condition of the second intention
  • the impact value is used to indicate an impact on the event influence level.
  • the first knowledge is first information
  • the first information includes events and influence values
  • the first information is embodied as the degree of influence of the first operation on the constraint condition or the intention target or execution condition of the second intention.
  • the processing unit 51 is configured to determine the first knowledge of the first intention; or,
  • the transceiver unit 52 is configured to receive the first knowledge of the first intention from a second network element, the second network element being a network management system NMS, a user, an application program APP, an operation support system, or a business support system, etc. Functional entity.
  • the first network element may determine the first knowledge internally, or obtain the first knowledge from an external system, such as the second network element.
  • the processing unit 51 is configured to obtain an intent keyword corresponding to the intent expression of the first intent, and the intent keyword includes one or more of the following information: The first intention target, the area where the first intention acts, and the name of the network element where the first intention acts;
  • the processing unit 51 is further configured to obtain the first knowledge corresponding to the intent keyword from the intent knowledge base according to the intent keyword.
  • the first knowledge is stored in the intent knowledge base, and when the first network element performs intent translation, it can obtain the corresponding first knowledge from the intent knowledge base according to the intent keywords obtained during the translation process.
  • the transceiving unit 52 is further configured to obtain the intended performance data from a third network element
  • the processing unit 51 is further configured to determine the satisfaction of the first condition of the first intention according to the intention performance data, wherein the first condition includes one or more of the following information: Intent targets, constraints of the first intent, and execution conditions of the first intent;
  • the processing unit 51 is further configured to determine the first knowledge of the first intention according to the satisfaction of the first condition and the second knowledge of the first intention, and the second knowledge of the first intention is The first knowledge of the first intention is the knowledge before the update.
  • the first network element updates the first knowledge according to the satisfaction of the first condition during the execution of the intention and the historical knowledge of the first intention.
  • the first knowledge is the first credibility
  • the processing unit 51 is further configured to achieve the first intention goal, and determine that the first credibility is the sum of the second credibility and the first credibility increment; or
  • the processing unit 51 is also configured to determine that the first intention goal is not reached, and the difference between the first achievement situation of the first intention goal and the second achievement situation of the first intention goal is a negative value.
  • the first degree of credibility is the sum of the second degree of credibility and a second degree of credibility increment, and the second degree of credibility increment is smaller than the first degree of credibility increment; or
  • the processing unit 51 is also used for determining that the first intention goal is not reached, and the difference between the first achievement situation and the second achievement situation is a positive value, and determining that the first degree of credibility is the first 2.
  • the second degree of credibility is the degree of credibility before the first degree of credibility is updated
  • the first achievement situation is the achievement situation of the first intention goal in the first time period and the first degree of credibility.
  • the absolute value of the difference between the intentional goal, the second achievement situation is the absolute value of the difference between the achievement situation of the first intention goal in the second time period and the first intention goal, and the second time period is earlier than The first time period.
  • the first network element updates the first degree of credibility for achieving the first intention goal based on the current achievement situation and the historical achievement situation of the first intention goal.
  • the influence value is used to indicate the influence value of the first operation on the constraint condition or the intention target or the execution condition of the second intention.
  • processing unit 51 is further configured to determine the influence of the first operation on the second intention if the intention goal of the second intention changes from being achieved to not being reached Value is negative; or
  • the processing unit 51 is further configured to determine that the value of the influence of the first operation on the second intention is zero if the intention goal of the second intention is that the goal has been achieved and the achievement status has not changed.
  • the influence value of the first operation on the second intention is determined according to the achievement of the intention goal of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the intention goal of the second intention.
  • the processing unit 51 is further configured to perform the first operation as opposed to when the first operation is not performed, and the constraint condition of the second intention changes from being satisfied to not being satisfied. , It is determined that the influence value of the first operation on the second intention is negative; or
  • the processing unit 51 is further configured to perform the first operation, compared to the situation where the constraint condition of the second intention is satisfied when the first operation is not performed, and the second intention is always in the condition that the constraint condition is satisfied. , It is determined that the value of the influence of the first operation on the second intention is zero.
  • the influence value of the first operation on the second intention is determined according to the satisfaction of the constraint condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the constraint condition of the second intention.
  • the processing unit 51 is further configured to perform the first operation as opposed to when the first operation is not performed, and the execution condition of the second intention changes from being satisfied to not being satisfied. , It is determined that the influence value of the first operation on the second intention is negative; or
  • the processing unit 51 is further configured to perform the first operation compared to when the first operation is not performed, the condition that the execution condition of the second intention has been met has not changed, and the second intention is always in the execution condition If it is satisfied, it is determined that the value of the influence of the first operation on the second intention is zero.
  • the influence value of the first operation on the second intention is determined according to the satisfaction of the execution condition of the second intention, or in other words, the first knowledge is embodied as the influence of the first operation on the execution condition of the second intention.
  • the processing unit 51 is further configured to operate the corresponding second knowledge according to the first achievement of the first intention goal, one or more existing intentions, and the first A first knowledge of an intention, and the first operation is determined among the one or more existing intention operations.
  • the first operation can be selected from the existing intention operations.
  • the communication device can select the first operation according to the credibility of achieving the first intended goal and/or the first information, which can improve the accuracy of the selection of the first operation.
  • the communication device 600 includes: a transceiver unit 61 and a processing unit 62; among them:
  • the transceiver unit 61 is configured to obtain the first intended operation from the first network element
  • the processing unit 62 is configured to determine that the first intention operation has an influence on a second intention, and the second intention is different from the first intention;
  • the transceiving unit 61 is further configured to send first information to the first network element, where the first information is used to indicate the influence of the first intention operation on the second intention, and the first information is used for For the selection of the first operation, the first operation is used to execute the first intention.
  • transceiver unit 61 and processing unit 62 For the specific implementation of the foregoing transceiver unit 61 and processing unit 62, reference may be made to the related description of the second network element in the communication method shown in FIG. 7 to FIG. 12.
  • the communication device when the communication device acquires that the first network element performs the first intention operation, and determines that the first intention operation has an impact on the second intention, the communication device can send the first intention operation to the first network element.
  • the network element indicates the influence of the first intention operation on the second intention, so that the first network element accurately selects the first operation.
  • a schematic diagram of the hardware structure of a communication device is also provided, and the communication device is used to execute the above-mentioned communication method.
  • Part or all of the above methods can be implemented by hardware, and can also be implemented by software or firmware.
  • the communication device may be a chip or an integrated circuit during specific implementation.
  • the communication device 700 may include:
  • the memory 33 and the processor 34 may be one or more, and one processor is taken as an example in FIG. 15
  • the processor 34 may also include an input device 31 and an output device 32.
  • the input device 31, the output device 32, the memory 33, and the processor 34 may be connected by a bus or other means, wherein the connection by a bus is taken as an example in FIG. 15.
  • the processor 34 is configured to execute the method steps executed by the first network element in FIGS. 7-12.
  • the processor 34 is configured to execute the method steps executed by the second network element in FIGS. 7-12.
  • the program of the foregoing communication method may be stored in the memory 33.
  • the memory 33 may be a physically independent unit, or may be integrated with the processor 34.
  • the memory 33 can also be used to store data.
  • the communication device may also only include a processor.
  • the memory for storing the program is located outside the communication device, and the processor is connected to the memory through a circuit or wire for reading and executing the program stored in the memory.
  • the processor may be a central processing unit (CPU), a network processor (NP), or a WLAN device.
  • CPU central processing unit
  • NP network processor
  • WLAN device a WLAN device
  • the processor may further include a hardware chip.
  • the aforementioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof.
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • the above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a general array logic (generic array logic, GAL), or any combination thereof.
  • CPLD complex programmable logic device
  • FPGA field-programmable gate array
  • GAL general array logic
  • the memory may include a volatile memory (volatile memory), such as random-access memory (RAM); the memory may also include a non-volatile memory (non-volatile memory), such as flash memory (flash memory) , A hard disk drive (HDD) or a solid-state drive (solid-state drive, SSD); the memory may also include a combination of the foregoing types of memory.
  • volatile memory such as random-access memory (RAM)
  • non-volatile memory such as flash memory (flash memory)
  • flash memory flash memory
  • HDD hard disk drive
  • solid-state drive solid-state drive
  • one or more embodiments of the present disclosure may be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of the present disclosure may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, one or more embodiments of the present disclosure may adopt computer programs implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The form of the product.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • An embodiment of the present application further provides a chip system, including: at least one processor and an interface, the at least one processor is coupled to the memory through the interface, and when the at least one processor executes the computer program or instruction in the memory, the above The method in any method embodiment is executed.
  • the chip system may be composed of chips, or may include chips and other discrete devices, which are not specifically limited in the embodiment of the present application.
  • the embodiments of the present application also provide a computer-readable storage medium, and the storage medium may store a computer program, and when the program is executed by a processor, the steps of the communication method described in any embodiment of the present disclosure are realized.
  • the embodiments of the present application also provide a computer program product containing instructions, which when run on a computer, cause the computer to execute the steps of the communication method described in any embodiment of the present disclosure.
  • An embodiment of the present application also provides a communication system, which includes the above-mentioned communication device.
  • words such as “first” and “second” are used to distinguish the same items or similar items with substantially the same function and effect.
  • the words “first”, “second” and the like do not limit the quantity and order of execution, and the words “first” and “second” do not limit the difference.
  • words such as “exemplary” or “for example” are used as examples, illustrations, or illustrations. Any embodiment or design solution described as “exemplary” or “for example” in the embodiments of the present application should not be construed as being more preferable or advantageous than other embodiments or design solutions.
  • words such as “exemplary” or “for example” are used to present related concepts in a specific manner to facilitate understanding.
  • the disclosed system, device, and method can be implemented in other ways.
  • the division of the unit is only a logical function division. In actual implementation, there can be other divisions.
  • multiple units or components can be combined or integrated into another system, or some features can be ignored or not. implement.
  • the displayed or discussed mutual coupling, or direct coupling, or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical, or other forms.
  • the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the computer may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium.
  • the computer instructions can be sent from one website, computer, server, or data center to another via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) A website, computer, server or data center for transmission.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media.
  • the usable medium can be a read-only memory (ROM), or a random access memory (RAM), or a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape, a magnetic disk, or an optical medium, such as , Digital versatile disc (DVD), or semiconductor media, for example, solid state disk (SSD), etc.
  • ROM read-only memory
  • RAM random access memory
  • magnetic medium such as a floppy disk, a hard disk, a magnetic tape, a magnetic disk, or an optical medium, such as , Digital versatile disc (DVD), or semiconductor media, for example, solid state disk (SSD), etc.
  • SSD solid state disk

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请公开了一种通信方法及装置、系统。在本申请中，第一网元获取第一意图的第一知识，该第一意图的第一知识包括以下信息中的一项或多项：达成第一意图目标的第一可信程度和第一信息，该第一可信程度用于指示达成第一意图目标的可靠性，该第一信息用于指示第一意图操作对第二意图的影响，第二意图与所述第一意图不同；以及第一网元根据第一意图的第一知识选择第一操作，该第一操作用于执行第一意图。采用本申请的方案，第一网元可以根据达成第一意图目标的可信程度和/或第一信息选择第一操作，可以提高第一操作的选择的准确性。

Description

通信方法及装置、系统
本申请要求于2020年06月20日提交中国国家知识产权局、申请号为202010569778.X、发明名称为“通信方法及装置、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
本申请涉及网络智能管理技术领域，尤其涉及一种通信方法及装置、系统。
背景技术
为了屏蔽设备厂商实现上的差异化，启动了意图驱动管理(intent driven management，IDM)。网络管理系统(network management system，NMS)中只保留意图(intent)模型，向网元管理系统(element management system，EMS)传递意图表达式。该意图表达式只描述做什么(what)，不涉及怎么(how)做，只需具备无线领域基本的概念知识即可完成意图设计，从而降低了运维门槛。
EMS进行意图转译后，从意图知识库得到意图操作、意图目标和执行条件。例如，某一意图转译后可采取的指令操作有三种，分别对应三种不同的执行条件。在外部系统多次实施该意图时，第一种执行条件对应的指令操作多次不能满足意图目标。然而，EMS在下一次实施该意图时，仍然不能避免选择第一种执行条件对应的指令操作，造成意图目标一直不能满足。
发明内容
本申请提供一种通信方法及装置、系统，以提高用于执行第一意图的第一操作的选择的准确性。
第一方面，提供了一种通信方法，所述方法包括：第一网元获取第一意图的第一知识，所述第一意图的第一知识包括以下信息中的一项或多项：达成第一意图目标的第一可信程度和第一信息，所述第一可信程度用于指示达成所述第一意图目标的可靠性，所述第一信息用于指示第一意图操作对第二意图的影响，所述第二意图与所述第一意图不同；以及所述第一网元根据所述第一意图的第一知识选择第一操作，所述第一操作用于执行所述第一意图。
在该方面中，第一网元可以根据达成第一意图目标的可信程度和/或第一信息选择第一操作，可以提高第一操作的选择的准确性。
在一种可能的实现中，所述第一信息包括事件和影响值，所述事件包括所述第二意图的约束条件或意图目标或执行条件，所述影响值用于指示对所述事件的影响程度。
在该实现中，该第一知识为第一信息，该第一信息包括事件和影响值，该第一信息体现为第一操作对第二意图的约束条件或意图目标或执行条件的影响程度。
在另一种可能的实现中，所述第一网元获取第一意图的第一知识，包括：所述第一网元确定所述第一意图的第一知识；或者，所述第一网元从第二网元接收所述第一意图的第 一知识，所述第二网元为网络管理系统NMS，用户、应用程序APP、运营支撑系统或业务支撑系统等功能实体。
在该实现中，第一网元可以内部确定第一知识，也可以从外部系统，例如第二网元，获取第一知识。
在又一种可能的实现中，所述第一网元确定所述第一意图的第一知识，包括：所述第一网元获取所述第一意图的意图表达式对应的意图关键词，所述意图关键词包括以下信息中的一项或多项：所述第一意图目标、所述第一意图作用的区域、所述第一意图作用的网元名称；以及所述第一网元根据所述意图关键词，从意图知识库获取所述意图关键词对应的所述第一知识。
在该实现中，第一知识存储在意图知识库，第一网元在进行意图转译时，可以根据转译过程中获得的意图关键词从意图知识库获取对应的第一知识。
在又一种可能的实现中，所述第一网元确定所述第一意图的第一知识，包括：所述第一网元从第三网元获取意图性能数据；所述第一网元根据所述意图性能数据，确定所述第一意图的第一条件的满足情况，其中，所述第一条件包括以下一项或多项信息：所述第一意图目标，所述第一意图的约束条件，所述第一意图的执行条件；以及所述第一网元根据所述第一条件的满足情况和所述第一意图的第二知识，确定所述第一意图的第一知识，所述第一意图的第二知识为所述第一意图的第一知识更新前的知识。
在该实现中，第一网元根据意图执行过程中第一条件的满足情况和第一意图的历史知识，对第一知识进行更新。
在又一种可能的实现中，所述第一知识为所述第一可信程度，所述第一网元根据所述第一条件的满足情况和所述第一意图的第二知识，确定所述第一意图的第一知识，包括：所述第一意图目标达成，确定所述第一可信程度为第二可信程度与第一可信程度增量之和；或所述第一意图目标未达成，且所述第一意图目标的第一达成情况与所述第一意图目标的第二达成情况之差为负值，确定所述第一可信程度为所述第二可信程度与第二可信程度增量之和，所述第二可信程度增量小于所述第一可信程度增量；或所述第一意图目标未达成，且所述第一达成情况与所述第二达成情况之差为正值，确定所述第一可信程度为所述第二可信程度与第三可信程度增量之差；其中，所述第二可信程度为所述第一可信程度更新前的可信程度，所述第一达成情况为所述第一意图目标在第一时间段的达成情况与所述第一意图目标之差的绝对值，所述第二达成情况为所述第一意图目标在第二时间段的达成情况与所述第一意图目标之差的绝对值，所述第二时间段早于所述第一时间段。
在该实现中，第一网元根据第一意图目标当前的达成情况和历史的达成情况，对达成第一意图目标的第一可信程度进行更新。
在又一种可能的实现中，所述影响值用于指示所述第一操作对所述第二意图的约束条件或意图目标或执行条件的影响值。
在又一种可能的实现中，所述第一网元确定所述第一意图的第一知识，包括：若所述第二意图的意图目标从已达成变成未达成，则确定所述第一操作对所述第二意图的影响值为负值；或若所述第二意图的意图目标处于目标已达成且达成情况没有改变，则确定所述第一操作对所述第二意图的影响值为零。
在该实现中，第一操作对第二意图的影响值是根据第二意图的意图目标的达成情况确定的，或者说，第一知识体现为第一操作对第二意图的意图目标的影响。
在又一种可能的实现中，所述第一网元确定所述第一意图的第一知识，包括：执行所述第一操作相对于未执行所述第一操作时，所述第二意图的约束条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
在该实现中，第一操作对第二意图的影响值是根据第二意图的约束条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的约束条件的影响。
在又一种可能的实现中，所述第一网元确定所述第一意图的第一知识，包括：执行所述第一操作相对于未执行所述第一操作时，所述第二意图的执行条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的执行条件已满足情况没有改变，所述第二意图一直处于执行条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
在该实现中，第一操作对第二意图的影响值是根据第二意图的执行条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的执行条件的影响。
在又一种可能的实现中，所述第一网元根据所述第一意图的第一知识选择第一操作，包括：所述第一网元根据所述第一意图目标的第一达成情况、一个或多个已存在的意图操作对应的第二知识、和所述第一意图的第一知识，在所述一个或多个已存在的意图操作中确定所述第一操作。
在该实现中，若第一操作对应的第一意图目标可达成，则可以在已存在的意图操作中选择第一操作。
第二方面，提供了一种通信方法，所述方法包括：第二网元从第一网元获取第一意图操作；所述第二网元确定所述第一意图操作对第二意图有影响，所述第二意图与所述第一意图不同；以及所述第二网元向所述第一网元发送第一信息，所述第一信息用于指示所述第一意图操作对所述第二意图的影响，所述第一信息用于第一操作的选择，所述第一操作用于执行所述第一意图。
在该方面中，第二网元在获取到第一网元执行第一意图操作时，且确定第一意图操作对第二意图有影响，则第二网元可以向第一网元指示第一意图操作对第二意图的影响，以使第一网元准确地选择第一操作。
第三方面，提供了一种通信装置，所述装置包括：处理单元，用于获取第一意图的第一知识，所述第一意图的第一知识包括以下信息中的一项或多项：达成第一意图目标的第一可信程度和第一信息，所述第一可信程度用于指示达成所述第一意图目标的可靠性，所述第一信息用于指示第一意图操作对第二意图的影响，所述第二意图与所述第一意图不同；以及所述处理单元，还用于根据所述第一意图的第一知识选择第一操作，所述第一操作用于执行所述第一意图。
在一种可能的实现中，所述第一信息包括事件和影响值，所述事件包括所述第二意图的约束条件或意图目标或执行条件，所述影响值用于指示对所述事件的影响程度。
在另一种可能的实现中，所述处理单元，用于确定所述第一意图的第一知识；或者，所述装置还包括：收发单元，用于从第二网元接收所述第一意图的第一知识，所述第二网元为网络管理系统NMS，用户或应用程序APP。
在又一种可能的实现中，所述处理单元，用于获取所述第一意图的意图表达式对应的意图关键词，所述意图关键词包括以下信息中的一项或多项：所述第一意图目标、所述第一意图作用的区域、所述第一意图作用的网元名称；以及所述处理单元，还用于根据所述意图关键词，从意图知识库获取所述意图关键词对应的所述第一知识。
在又一种可能的实现中，所述收发单元，还用于从第三网元获取意图性能数据；所述处理单元，还用于根据所述意图性能数据，确定所述第一意图的第一条件的满足情况，其中，所述第一条件包括以下一项或多项信息：所述第一意图目标，所述第一意图的约束条件，所述第一意图的执行条件；以及所述处理单元，还用于根据所述第一条件的满足情况和所述第一意图的第二知识，确定所述第一意图的第一知识，所述第一意图的第二知识为所述第一意图的第一知识更新前的知识。
在又一种可能的实现中，所述第一知识为所述第一可信程度；所述处理单元，还用于所述第一意图目标达成，确定所述第一可信程度为第二可信程度与第一可信程度增量之和；或所述处理单元，还用于所述第一意图目标未达成，且所述第一意图目标的第一达成情况与所述第一意图目标的第二达成情况之差为负值，确定所述第一可信程度为所述第二可信程度与第二可信程度增量之和，所述第二可信程度增量小于所述第一可信程度增量；或所述处理单元，还用于所述第一意图目标未达成，且所述第一达成情况与所述第二达成情况之差为正值，确定所述第一可信程度为所述第二可信程度与第三可信程度增量之差；其中，所述第二可信程度为所述第一可信程度更新前的可信程度，所述第一达成情况为所述第一意图目标在第一时间段的达成情况与所述第一意图目标之差的绝对值，所述第二达成情况为所述第一意图目标在第二时间段的达成情况与所述第一意图目标之差的绝对值，所述第二时间段早于所述第一时间段。
在又一种可能的实现中，所述影响值用于指示所述第一操作对所述第二意图的约束条件或意图目标或执行条件的影响值。
在又一种可能的实现中，所述处理单元，还用于若所述第二意图的意图目标从已达成变成未达成，则确定所述第一操作对所述第二意图的影响值为负值；或所述处理单元，还用于若所述第二意图的意图目标处于目标已达成且达成情况没有改变，则确定所述第一操作对所述第二意图的影响值为零。
在又一种可能的实现中，所述处理单元，还用于执行所述第一操作相对于未执行所述第一操作时，所述第二意图的约束条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或所述处理单元，还用于执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
在又一种可能的实现中，所述处理单元，还用于执行所述第一操作相对于未执行所述第一操作时，所述第二意图的执行条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或所述处理单元，还用于执行所述第一操作相对于未执行所述 第一操作时，对所述第二意图的执行条件已满足情况没有改变，所述第二意图一直处于执行条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
在又一种可能的实现中，所述处理单元，还用于根据所述第一意图目标的第一达成情况、一个或多个已存在的意图操作对应的第二知识、和所述第一意图的第一知识，在所述一个或多个已存在的意图操作中确定所述第一操作。
第四方面，提供了一种通信装置，所述装置包括：收发单元，用于从第一网元获取第一意图操作；处理单元，用于确定所述第一意图操作对第二意图有影响，所述第二意图与所述第一意图不同；以及所述收发单元，还用于向所述第一网元发送第一信息，所述第一信息用于指示所述第一意图操作对所述第二意图的影响，所述第一信息用于第一操作的选择，所述第一操作用于执行所述第一意图。
第五方面，提供了一种通信装置，该通信装置可以为上述第一方面或第一方面的任一可能的实现中的第一网元，或者应用于第一网元中的模块，例如芯片或芯片系统。其中，该通信装置包括至少一个处理器，用于执行上述第一方面或第一方面的任一可能的实现中的方法。
示例性地，该通信装置还包括存储器，该存储器与该至少一个处理器耦合，该至少一个处理器用于执行上述第一方面或第一方面的任一可能的实现中的方法。
在一种可能的实现中，该存储器用于存储程序指令和数据。该存储器与该至少一个处理器耦合，该至少一个处理器可以调用并执行该存储器中存储的程序指令，用于执行上述第一方面或第一方面的任一可能的实现中的方法。
示例性地，该通信装置还包括通信接口，该通信接口用于该通信装置与其它设备进行通信。当该通信装置为第一网元时，该通信接口为收发器、输入/输出接口、或电路等。
在一种可能的设计中，该通信装置包括：至少一个处理器和通信接口，用于执行上述第一方面或第一方面的任一可能的实现中的方法，具体地包括：该至少一个处理器利用该通信接口与外部通信；该至少一个处理器用于运行计算机程序，使得该通信装置执行上述第一方面或第一方面的任一可能的实现中的方法。可以理解，该外部可以是处理器以外的对象，或者是该通信装置以外的对象。
在另一种可能的设计中，该通信装置为芯片或芯片系统。该通信接口可以是该芯片或芯片系统上的输入/输出接口、接口电路、输出电路、输入电路、管脚或相关电路等。该处理器也可以体现为处理电路或逻辑电路。
第六方面，提供了一种通信装置，该通信装置可以为上述第二方面中的第二网元，或者应用于第二网元中的模块，例如芯片或芯片系统。其中，该通信装置包括至少一个处理器，用于执行上述第二方面中的方法。
示例性地，该通信装置还包括存储器，该存储器与该至少一个处理器耦合，该至少一个处理器用于执行上述第二方面中的方法。
在一种可能的实现中，该存储器用于存储程序指令和数据。该存储器与该至少一个处理器耦合，该至少一个处理器可以调用并执行该存储器中存储的程序指令，用于执行上述第二方面中的方法。
示例性地，该通信装置还包括通信接口，该通信接口用于该通信装置与其它设备进行 通信。当该通信装置为第二网元时，该通信接口为收发器、输入/输出接口、或电路等。
在一种可能的设计中，该通信装置包括：至少一个处理器和通信接口，用于执行上述第二方面中的方法，具体地包括：该至少一个处理器利用该通信接口与外部通信；该至少一个处理器用于运行计算机程序，使得该通信装置执行上述第二方面中的方法。可以理解，该外部可以是处理器以外的对象，或者是该通信装置以外的对象。
在另一种可能的设计中，该通信装置为芯片或芯片系统。该通信接口可以是该芯片或芯片系统上的输入/输出接口、接口电路、输出电路、输入电路、管脚或相关电路等。该处理器也可以体现为处理电路或逻辑电路。
第七方面，提供了一种通信系统，包括如第三方面或第三方面的任一个实现所述的通信装置，如第四方面所述的通信装置，以及第三网元。
第八方面，提供了一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当其在计算机上运行时，使得计算机执行上述各方面所述的方法。
第九方面，提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述各方面所述的方法。
第十方面，提供了一种芯片，所述芯片与存储器耦合，执行本申请实施例第一方面或第一方面中任一实现所述的通信方法。
第十一方面，提供了一种芯片，所述芯片与存储器耦合，执行本申请实施例第二方面或第二方面中任一实现所述的通信方法。
需要说明的是，本申请实施例中“耦合”是指两个部件彼此直接或间接地结合。
附图说明
图1为基于意图的ENI融合架构示意图；
图2为基于意图的ENI融合架构内外部接口示意图；
图3为本申请适用的意图驱动管理系统的结构示意图；
图4为意图转译、执行和维持阶段涉及的功能模块示意图；
图5为本申请实施例适用的通信系统的架构示意图；
图6为支持意图知识管理在基于意图的ENI融合系统接口中新增4个新的接口的示意图；
图7为本申请实施例提供的一种通信方法的流程示意图；
图8为本申请实施例提供的意图转译过程中的通信方法流程示意图；
图9为意图执行和维持过程中的一种通信方法的流程示意图；
图10为意图执行和维持过程中的又一种通信方法的流程示意图；
图11为意图执行和维持过程中的又一种通信方法的流程示意图；
图12为意图执行和维持过程中的又一种通信方法的流程示意图；
图13为本申请实施例提供的一种通信装置的结构示意图；
图14为本申请实施例提供的又一种通信装置的结构示意图；
图15为本申请实施例提供的又一种通信装置的结构示意图。
具体实施方式
体验式网络智能(Experiential Networked Intelligence，ENI)是行业规范工作组定义的一种感知网络管理系统架构，运用人工智能和上下文感知等技术手段优化和调整网络运营。ENI系统共包含10个功能模块(functional block，FB)，并分为输入功能模块、输出功能模块、分析功能模块以及决策功能模块四大类。模块分类以及各类模块的功能如下所述：
输入功能模块：数据接入(data ingestion)功能模块和标准化(normalization)功能模块，负责接收外部系统的数据以及对数据进行归一化等操作。
输出功能模块：输出产生(output generation)功能模块和反规范化(denormalization)功能模块，负责将系统内部命令转化为外部系统能够处理的格式并发送给外部系统。
分析功能模块：知识管理(knowledge management)功能模块，上下文感知(context awareness)功能模块和认知管理(cognition management)功能模块，负责对现有的网络上下文进行感知分析并且预测未来的网络状态。
决策功能模块：策略管理(policy management)功能模块，状态感知(situational awareness)功能模块和模型驱动工程(model-driven engineering)功能模块，在对网络状态感知的基础上，根据策略目标生成新的策略并对策略进行编排，并将操作命令发送给输出模块。
ENI定义了基于意图的ENI融合架构，并定义了与意图转译和意图保障相关的功能模块。如图1所示的基于意图的ENI融合架构示意图，具体地，该ENI融合架构在知识管理功能模块中加入了意图知识库(intent knowledge repository)，在策略管理功能模块中加入了意图策略执行(intent policy fulfillment)子功能模块，以及还引入了一个独立的意图转译(intent translation)功能模块。
其中，意图转译功能模块，用于将收到的意图策略进行意图转译。
意图知识库，用于存放专家经验以及网元的信息，可以作为一个独立的功能模块，也可以放在ENI现有架构中的知识管理功能模块中。
意图策略执行功能模块，用于实现意图执行及维持功能，负责对意图策略进行编排并持续满足外部系统的意图需求。
基于意图的ENI融合架构在以上三个功能模块增强的基础上，还定义了意图转译和意图保障的相关模块和接口。如图2所示的基于意图的ENI融合架构内外部接口示意图，为了支持意图策略，除了对已有ENI接口进行增强外，还在原有接口的基础上加入了4个新的接口，分别为运营支撑系统(operation support system，OSS)与融合系统间处理策略相关的接口Eoss-eni-pol，APP与融合系统间处理策略相关的接口Eapp-eni-pol，意图转译模块与知识管理模块之间的接口I ITA-KM-CMD，意图转译模块与策略管理模块间的接口I ITA-PM-CMD。
如图3所示，为本申请适用的意图驱动管理系统的结构示意图，该意图驱动管理系统包括IDM服务消费者(IDM service consumer)、IDM服务生产者(IDM service producer)和网络基础设施(network infrastructure)。该网络基础设施可以是物理的(physical)，也可以是虚拟的(virtual)。IDM采用服务化的接口来实现意图的下发。具体地，IDM服务消费者通过调用意图驱动管理服务(intent driven management service，IDMS)接口将意图下发至IDM服务生产者；IDM服务生产者将意图转译为具体的执行策略下发给网络基础设施， 并在意图执行过程中不断监测网络状态以保障意图的达成或维持意图。
其中，IDM服务消费者下发的意图包括类型A(type A)和类型B(type B)两种。
类型A，包括操作和通知，与具体意图类型无关，例如是一个用于意图传递的通用操作。
类型B，意图模型，用于对意图表达中应包含的信息进行建模。目前给出的建模元素至少应包含“动作”和“对象”。
具体地，在意图模型中，动作由一个动作名和完成该动作所需的一系列属性组成；对象则由一个对象名和一系列用于标识具体对象实例的属性组成。因此，意图模型的形式化表达为如下意图表达式(为了表达简洁，下文在不引起歧义的情况下省略Driven)：
<intentExpression>:＝<IntentDrivenAction><IntentDrivenObject>
<IntentDrivenAction>:＝<IntentDrivenActionName><IntentDrivenActionProperties>
<IntentDrivenObject>:＝<IntentDrivenObjectName><IntentDrivenObjectProperties>
例如，“数据速率小于5Mbps的用户百分比小于1％并且平均数据速率不小于7Mbps”的意图表达模型如下表1所示：
表1用户速率优化意图表达
Figure PCTCN2021100747-appb-000001
如图4所示，为图3所示的IDM系统应用于网络设备管理时，意图转译和保障阶段涉及的功能模块示意图。基于意图的ENI融合系统(在图4中具体为EMS)架构中支持对意图的转译和保障。在网络设备管理领域，可以将ENI的功能模块嵌入网元管理系统(element management system，EMS)。网络管理系统(network management system，NMS)向EMS发送意图，EMS对意图进行转译，将最终生成的命令发送给辅助系统(assisted system)(又可以称为网络设备(network equipment，NE))。NE执行完命令，最终达成意图。其中，NMS可以是用户(user)、应用程序(application)、以及运营支撑系统和业务支撑系统等功能实体(operation support system-and business support system-like functionality，OSS-and BSS-like functionality)。
具体地，在意图转译阶段，NMS下发意图实施请求到意图融合系统中后，经过knowledge management FB处理后，intent translation FB从intent knowledge repository中查询并得到意图相关的意图操作(intent operations)、意图达成条件(intent fulfillment criterion)(又称为意图目标)和执行条件(execution condition)，依次经过context awareness FB、situational awareness FB、MDE FB处理，并由policy management FB执行意图。
在意图保障阶段，网络性能数据依次经过knowledge management FB、context awareness FB、situational awareness FB、MDE FB和policy management FB进行意图性能数据交互、 意图达成情况及意图策略更新决策等来产生意图操作并执行意图。
然而，在进行意图转译后，从意图知识库得到意图操作、意图目标和执行条件。例如，某一意图转译后可采取的指令操作有三种，分别对应三种不同的执行条件。在外部系统多次实施该意图时，在第一种执行条件对应的指令操作多次不能满足意图达成条件。然而，在下一次实施该意图时，仍然不能避免选择第一种执行条件对应的指令操作，造成意图达成条件一直不能满足。
本申请实施例提供一种通信方法及装置、系统，第一网元可以根据达成第一意图目标的可信程度和/或第一信息选择第一操作，可以提高第一操作的选择的准确性。
图5为本申请实施例适用的通信系统的架构示意图，该通信系统100包括第一网元200、第二网元300和第三网元400。第二网元300将创建好的意图传输给第一网元200执行。第一网元200接收到第二网元300的意图，转译该意图，从意图知识库得到意图操作、意图目标和执行条件，并对意图进行编排等操作，编排为第三网元400可执行的命令，并传输给第三网元400执行。第三网元400接收到第一网元12的可执行命令，执行该命令。该通信系统应用于网络管理场景时，该第一网元可以是如图4所示的EMS。该第二网元是意图的创建者，可以是如图4所示的NMS。该第三网元是意图的作用者(infrastructure)，可以是如图4所示的NE。
如前所述，基于意图的ENI融合系统支持对意图的转译和保障。EMS在执行上述操作过程中可以分为两个阶段：意图转译阶段、意图保障阶段。在意图转译阶段涉及data ingestion and normalization FB、knowledge management FB、intent translation FB、context awareness FB、situational awareness FB、model-driven engineering FB、policy management FB和output generation and denormalization FB。在意图转译阶段，NMS下发意图实施请求到EMS后，转译中意图转译模块从意图知识库(意图知识库可以位于知识管理功能模块)中查询并得到意图操作、意图目标和执行条件，并由policy management FB执行该意图。在意图保障阶段，policy management FB可根据意图性能数据、意图达成情况以及意图策略更新情况更改意图操作。
为了支持意图知识管理，图6所示为基于意图的ENI融合系统接口中新增了的4个新的接口，分别为cognition management FB与knowledge management FB之间接口I KM-CM-CMD，cognition management FB与context awareness FB之间接口I CA-CM-CMD，cognition management FB与policy management FB之间接口I PM-CM-CMD，cognition management FB与model driven engineer FB之间接口I MDE-CM-CMD。
本申请的实施例中，意图系统中由cognition management FB对知识进行分析和推理并确定需要更新的意图知识，由意图knowledge management FB对intent knowledge repository进行更新操作。
intent knowledge repository中在意图策略操作中增加以下至少一项意图知识：达成第一意图目标的第一可信程度(reliability)(用于指示达成第一意图目标的可靠性)和第一信息(用于指示第一意图操作对第二意图的影响)。其中，第一信息又包括事件(events)和影响值(impact)。其中，事件包括第二意图的约束条件或意图目标或执行条件，影响值用于指示对事件的影响程度。意图转译后可获得以上意图知识。
意图保障时，根据意图性能数据、意图达成情况以及意图系统产生策略更新意图策略操作的第一可信程度和第一信息。
其中，reliability，events和impact的定义如下：
reliability的定义及示例：
定义和取值：reliability是用于评价意图策略在采用某个操作后的意图目标达成情况，初始值为100％，变化区间[0％,100％]。
计算方法：对于意图策略p，其设定的达成目标为g,采用操作o前reliability为r，采用操作o后，监测当前意图目标为j，可以根据以下方法更新意图策略p采用操作o时的reliability：
如果当前意图目标j已经满足达成目标g，reliability在r的基础上增加r1,更新r＝r+r1，r最大为100％。
如果当前意图目标j没有满足达成目标g，但是在接近达成目标g(比较上次的检测结果)，reliability在r的基础上增加r2，更新r＝r+r2，r最大为100％。
如果当前意图目标j没有满足达成目标g，但是在远离达成目标g(比较上次的检测结果)，reliability在r的基础上减少r3，更新r＝r-r3，r最小为0％。
其中，r1、r2和r3可以是用户自定义的，或ENI系统根据经验设置的。
示例：意图目标为保证小区吞吐量为20，操作为提高下行功率，操作发生前reliability为80％，现在操作采用后，根据以下情况更新reliability(r1＝10％,r2＝5％,r3＝10％)：
1.当前小区吞吐量为20，r＝r+r1＝80％+10％＝90％。
2.当前小区吞吐量为18(上次监测结果为15)，r＝r+r2＝80％+5％＝85％。
3.当前小区吞吐量为12(上次监测结果为15)，r＝r-r3＝80％-10％＝70％。
events及其impact的定义及示例：
events的定义：根据不同意图策略之间执行和维持过程中是否有影响决定。假设当前系统存在意图B，在意图B执行过程当中新加入意图A，意图A采用操作O，操作O影响了意图B的意图目标，则采用事件用于指示意图A的操作O对意图B的影响。
impact定义和取值：impact用于指示/评价操作O对受影响的意图B的影响程度，具体用于指示操作O对意图B的约束条件或意图目标或执行条件的影响值。其取值可以是零和负值。具体取值可以为[-1,0]。
impact的计算方法：
一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的意图目标已达成。则第一网元执行第一操作后，若第二意图的意图目标从已达成变成未达成，则确定第一操作对第二意图的影响值为负值；或若第二意图的意图目标处于目标已达成且达成情况没有改变，则确定第一操作对第二意图的影响值为零。第一操作对第二意图的影响值是根据第二意图的意图目标的达成情况确定的，或者说，第一知识体现为第一操作对第二意图的意图目标的影响。
另一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的约束条件已满足。则第一网元执行第一操作后，若执行第一操作相对于未执行第一操作时，第二意图的约束条件从已满足变成未满足，则确定第一操作对第二意图的影响值为负值；或 执行第一操作相对于未执行第一操作时，对第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定第一操作对第二意图的影响值为零。即第一操作对第二意图的影响值是根据第二意图的约束条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的约束条件的影响。
又一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的执行条件已满足。则第一网元执行第一操作后，若执行第一操作相对于未执行第一操作时，第二意图的执行条件从已满足变成未满足，则确定第一操作对第二意图的影响值为负值；或执行第一操作相对于未执行第一操作时，对第二意图的执行条件已满足情况没有改变，第二意图一直处于执行条件已满足，则确定第一操作对第二意图的影响值为零。即第一操作对第二意图的影响值是根据第二意图的执行条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的执行条件的影响。
可以理解的是，也可以根据上述一种或多种情况确定第一操作对第二意图的影响值。
以操作O对意图B的意图目标产生影响为例，意图A的意图目标为保证小区吞吐量为80，意图A采用操作O增大下行功率。意图B的意图目标为保证小区能耗小于100。意图A的操作O会对意图B产生影响。采用操作O后，若意图B中小区能耗当前为120(上次监测结果为90)，则impact为-1；若意图B中小区能耗当前为90(上次监测结果为90)，则impact为0。
下面结合图1至图12，对本申请提供的通信方法进行详细描述：
如图7所示，为本申请实施例提供的一种通信方法的流程示意图，该方法包括以下步骤：
S101、第一网元获取第一意图的第一知识。
第一网元在接收到第二网元下发的第一意图后，需要转译该第一意图，从意图知识库得到第一意图的第一知识，并根据该第一知识对第一意图进行编排等操作，编排为第三网元可执行的命令。其中，第一知识包括：第一意图操作(intentOperations)、第一意图达成条件(intentFulfillmentCriterion)(又称为第一意图目标)。其中，第一意图操作的信息结构为：intentOperations[执行条件(executionConditon)，操作类型(operationType)，操作(operation)]。在本实施例中，该第一意图操作中还可以包括达成第一意图目标的第一可信程度，或者，该第一意图操作中还可以包括第一信息，或者，该第一意图操作中还可以包括达成第一意图目标的第一可信程度和第一信息。
其中，第一可信程度用于指示达成第一意图目标的可靠性，即表示意图策略在采用该意图操作后的意图目标达成情况。在意图创建时，初始化该第一可信程度，初始值为100％。在后续意图保障过程中，更新该第一可信程度，变化区间为[0％，100％]。具体地，采用该意图操作后，可能可以达成第一意图目标，或者没有达成第一意图目标，但是在接近达成该第一意图目标，在原来的第一可信程度基础上增加一个可信程度增量；采用该意图操作后，没有达成第一意图目标，且在远离第一意图目标，在原来的第一可信程度基础上减少一个可信程度增量。
第一网元在执行第一意图操作后，可能对正在第一网元中执行的第二意图产生影响。该第二意图与第一意图不同，可以是第一网元中除第一意图之外的任一正在执行的意图。 其中，第一信息用于指示第一意图操作对第二意图的影响。具体地，该第一信息包括事件和影响值，该事件包括第二意图的约束条件或意图目标或执行条件，即第一信息用于指示第一意图操作对第二意图的约束条件或意图目标或执行条件的影响值或影响程度。该影响值可以为零，负值。
具体地，在一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的意图目标已达成。则第一网元执行第一操作后，若第二意图的意图目标从已达成变成未达成，则确定第一操作对第二意图的影响值为负值；或若第二意图的意图目标处于目标已达成且达成情况没有改变，则确定第一操作对第二意图的影响值为零。即第一操作对第二意图的影响值是根据第二意图的意图目标的达成情况确定的，或者说，第一知识体现为第一操作对第二意图的意图目标的影响。
在另一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的约束条件已满足。则第一网元执行第一操作后，执行第一操作相对于未执行第一操作时，第二意图的约束条件从已满足变成未满足，则确定第一操作对第二意图的影响值为负值；或执行第一操作相对于未执行第一操作时，对第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定第一操作对第二意图的影响值为零。即第一操作对第二意图的影响值是根据第二意图的约束条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的约束条件的影响。
在又一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的执行条件已满足。则第一网元执行第一操作后，执行第一操作相对于未执行第一操作时，第二意图的执行条件从已满足变成未满足，则确定第一操作对第二意图的影响值为负值；或执行第一操作相对于未执行第一操作时，对第二意图的执行条件已满足情况没有改变，第二意图一直处于执行条件已满足，则确定第一操作对第二意图的影响值为零。即第一操作对第二意图的影响值是根据第二意图的执行条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的执行条件的影响。
第一网元获取第一意图的第一知识，具体地，可以有以下实现方式：
在一个实现中，第一网元自身确定第一意图的第一知识。
具体地，意图创建或意图转译过程中获得的第一知识存储在第一网元的意图知识库中。第一网元接收来自第二网元的第一意图的表达式，对该第一意图的表达式进行词法和语法分析，获取第一意图的表达式对应的意图关键词。该意图关键词包括以下信息中的一项或多项：第一意图目标、第一意图作用的区域、第一意图作用的网元名称。第一网元根据获取到的意图关键词，从意图知识库获取意图关键词对应的第一知识。
在意图保障过程中，第一网元从第三网元获取意图性能数据。第一网元根据获取的意图性能数据，确定第一意图的第一条件的满足情况。其中，第一条件包括以下一项或多项信息：第一意图目标，第一意图的约束条件，第一意图的执行条件。第一网元根据第一条件的满足情况和第一意图的第二知识，确定第一意图的第一知识，其中，第一意图的第二知识为第一意图的第一知识更新前的知识。该第一知识可以是第一可信程度。具体地，第一意图目标达成，确定第一可信程度为第二可信程度与第一可信程度增量之和；或第一意图目标未达成，且第一意图目标的第一达成情况与第一意图目标的第二达成情况之差为负 值，确定第一可信程度为第二可信程度与第二可信程度增量之和，第二可信程度增量小于第一可信程度增量；或第一意图目标未达成，且第一达成情况与第二达成情况之差为正值，确定第一可信程度为第二可信程度与第三可信程度增量之差；其中，第二可信程度为第一可信程度更新前的可信程度，第一达成情况为第一意图目标在第一时间段的达成情况与第一意图目标之差的绝对值，第二达成情况为第一意图目标在第二时间段的达成情况与第一意图目标之差的绝对值，第二时间段早于第一时间段。第一网元确定第一意图的第一知识，可以理解为，第一网元通过更新第二知识得到第一知识。第一网元可以将第一知识更新到意图知识库中。
在另一个实现中，第一网元可以从第二网元接收第一意图的第一知识，从而获取第一意图的第一知识。具体地，第一网元从第二网元接收第一信息。该第二网元为NMS，用户、APP、运营支撑系统或业务支撑系统等功能实体。第二网元向第一网元下发第一意图，第一网元在执行第一意图的过程中或执行第一意图后，可以通知第二网元第一意图对应的操作为第一意图操作，从而第二网元可以获知第一意图操作。第二网元在下发第一意图之前、同时或之后，还可以向第一网元下发第二意图。其中，第二意图与第一意图不同。第二网元在获取第一意图对应的第一意图操作之后，确定第一意图操作对第二意图有影响。具体地，第一意图操作对第二意图的约束条件或意图目标或执行条件有影响。第二网元确定第一意图操作对第二意图有影响后，向第一网元发送第一信息。该第一信息用于指示第一意图操作对第二意图的影响。从而，第一网元可以从第二网元接收该第一信息。该第一信息用于上述第一操作的选择。
S102、第一网元根据第一意图的第一知识选择第一操作。
第一网元获取了第一意图的第一知识后，该第一知识包括达成第一意图目标的第一可信程度和/或第一信息，可以根据该第一知识选择第一操作。该第一操作用于执行第一意图。
具体地，第一网元根据第一意图目标的第一达成情况、一个或多个已存在的意图操作对应的第二知识、和第一意图的第一知识，在一个或多个已存在的意图操作中确定第一操作。该第一操作可以是上述第一意图操作，也可以是其它操作。
第一网元根据第一知识选择第一操作，该选择过程考虑了达成第一意图目标的可靠性，和/或第一操作对第二意图的影响，从而提高了达成第一意图目标的可靠性；所选择的第一操作避免了对第一网元中正在执行的其它意图的影响，从而提高了达成第一网元中多个意图的意图目标的可靠性。
根据本申请实施例提供的一种通信方法，第一网元可以根据达成第一意图目标的可信程度和/或第一信息选择第一操作，可以提高第一操作的选择的准确性。
下面具体描述意图转译和意图保障过程中涉及的通信方法流程：
第一阶段：意图转译阶段
如图8所示，为本申请实施例提供的意图转译过程中的通信方法流程示意图，示例性地，该方法可以包括以下步骤：
S201、第二网元向ENI系统发送意图创建发起(createintent invoking)请求，具体地，发送该意图创建发起请求到第一网元的data ingestion and normalization FB。
在这里，第二网元也可以称为意图创建者。第二网元可以是NMS、用户、APP、运营 支撑系统和业务支撑系统等功能实体。如图8所示，总的来说，该第二网元是相对于ENI系统(第一网元)来说的外部系统。
该意图创建发起请求携带第一意图的意图表达式。该意图表达式可以参考上文描述。该意图创建发起请求用于请求在第一网元内部创建第一意图。该请求通过ENI与外部系统的策略/意图接口传递。
S202、data ingestion and normalization FB接收到该意图创建发起请求后，进行数据归一化操作并向knowledge management FB发送归一化后的第一意图。
S203、knowledge management FB存储归一化后的第一意图并确定发送该意图的功能实体。
即knowledge management FB确定发送该意图的功能实体是NMS、用户、APP、运营支撑系统和业务支撑系统等功能实体中的任一个。
S204、knowledge management FB向intent translation FB发送意图转译请求。
该意图转移请求用于请求对上述第一意图进行转译。
S205、intent translation FB识别意图转译请求并给该意图分配意图标识(intent ID)。
该意图标识用于标识第一意图。
S206、intent translation FB向denormalization and output generation FB发送意图创建发起请求响应准备。
S207、denormalization and output generation FB向第二网元发送意图创建发起请求响应。
该响应用于指示接收到上述意图创建发起请求。
S208、intent translation FB对第一意图进行意图解析。
具体地，意图解析包括对第一意图的意图表达式进行词法和语法分析，获取第一意图的意图表达式对应的意图关键词，即获得查询意图知识库以及网络知识库所需要的意图关键字。该意图关键词包括以下信息中的一项或多项：第一意图目标、第一意图作用的区域、第一意图的网元名称。
S209、如果步骤S208第一意图解析存在错误，intent translation FB向denormalization
and output generation FB发送意图错误发起通知准备。
S210、denormalization and output generation FB向第二网元发送意图错误发起通知。
S211、intent translation FB将第一意图解析错误更新到intent knowledge repository中。
S212、如果步骤S208第一意图解析未存在错误，intent translation FB将意图关键词更新并储存到intent knowledge repository中。
S213、intent translation FB向knowledge management FB发送意图知识查询请求，携带S208中的意图关键词，从intent knowledge repository子FB获得意图知识/网络信息。该意图知识查询请求用于请求获取上述意图关键词对应的第一意图的第一知识。进一步地，该意图知识查询请求还可以用于请求获取上述意图关键词对应的网络信息。
S214、knowledge management FB根据接收到的意图关键词，从intent knowledge repository子FB查询到意图关键词对应的第一知识后，向intent translation FB发送意图知识查询请求回应。该意图知识查询请求回应携带上述意图标识、第一意图目标(intentFulfillmentCriterion)和第一意图操作。
目前的第一意图操作(intentOperations)包含的信息为：intentOperations[executionConditon，operationType,operation]。而本实施例对第一意图操作所包含的信息进行了补充。具体地，第一意图操作所包含的信息可以是以下几种情况：
(1)intentOperations[executionConditon，operationType，operation,reliability]。即在这种情况中，在第一意图操作中增加了第一知识：reliability。其中，executionConditon为执行条件；operationType为操作类型；operation为意图操作。
(2)intentOperations[executionConditon，operationType,operation,event,impact]。即在这种情况中，在第一意图操作中增加了第一知识：event和impact。
(3)intentOperations[executionConditon，operationType,operation,reliability,event,impact]。即在这种情况中，在第一意图操作中既增加了reliability，也增加了event和impact。
根据意图关键词查询得到的第一意图的第一知识，可以用于后续第一意图保障过程中的操作的选择。
S215、intent translation FB通过语法树和语义分析对第一知识进行组合，将组合后的第一知识更新到intent knowledge repository。
S216、intent translation FB向context awareness FB发送意图转译结束通知，并携带Intent ID，intentFulfillmentCriterion，intentOperations。其中，第一意图的executionConditon包含关键绩效指标(key performance indicator，KPI)，用于在上下文信息中确定第一意图的执行条件的满足情况。
S217、context awareness FB增加第一意图的上下文信息，并更新到knowledge management FB。
context awareness FB对意图转译结束通知中携带的上述信息进行意图上下文感知，获得第一意图的上下文信息。
S218、context awareness FB向situational awareness FB发送意图上下文感知结束通知，并携带Intent ID，intentFulfillmentCriterion，intentOperations以及增加的上下文信息。这些携带的消息中包含第一意图目标，用于衡量第一意图目标的达成情况。
S219、situational awareness FB增加第一意图的状态信息，并更新到knowledge management FB。
situational awareness FB根据上述意图上下文感知结束通知中携带的信息进行意图状态感知，获得第一意图的状态信息。
S220、situational awareness FB向model driven engineering FB发送意图状态感知结束通知，并携带Intent ID，intentFulfillmentCriterion，intentOperations以及增加的上下文信息和第一意图的状态信息。该意图状态感知结束请求用于请求model driven engineering产生并执行Intent ID对应的第一意图。
S221、model driven engineering FB基于第一可信程度和/或第一知识选择第一操作。
具体地，若第一意图操作中包括第一可信程度，则model driven engineering FB基于第一可信程度选择第一操作。
若第一意图操作中包括第一信息，则model driven engineering FB基于第一信息选择第一操作。
若第一意图操作中包括第一可信程度和第一信息，则model driven engineering FB基于第一可信程度和第一信息选择第一操作。
S222、model driven engineering FB进行意图操作指令转换，并更新到knowledge management FB。
model driven engineering FB对选择的第一操作进行格式转化，转化为ENI系统内部的模块可以识别的操作指令。
S223、model driven engineering FB向policy management FB发送意图指令转换结束通知。
S224、policy management FB进行意图操作指令类型转换，并更新到knowledge management FB。
policy management FB对第一操作进行格式转化，转化为外部系统可以识别的操作指令。
S225、policy management FB向denormalization and output generation FB发送意图指令产生请求。
S226、denormalization and output generation FB向第三网元发送意图指令执行请求。
在本实施例中，意图转译后不仅得到意图策略的指令操作，还包含达成第一意图目标的第一可信程度和/或第一信息，为后续意图保障提供操作选择的依据，并为后续知识更新提供初始化参数。
第二阶段：意图保障过程
如图9所示，为意图保障过程中的一种通信方法的流程示意图。在该方法中，第一知识包括达成第一意图目标的第一可信程度。示例性地，该方法可以包括以下步骤：
S301、context awareness FB向denormalization and output generation FB发送意图性能数据订阅请求准备。该意图性能数据订阅请求准备携带第一意图目标，executionConditon中的KPI。
S302、denormalization and output generation FB向第三网元发送意图性能数据订阅请求。
S303、第三网元向ENI系统发送意图性能数据订阅响应，携带被请求的意图性能数据。
具体地，第三网元根据意图性能数据订阅请求中携带的第一意图目标，executionConditon中的KPI，获取第一意图目标的达成情况、第一意图的执行条件的满足情况、第一意图的约束条件的满足情况等意图性能数据。然后，第三网元向data ingestion and normalization FB发送意图性能数据订阅响应。该意图性能数据订阅响应携带上述意图性能数据。
S304、data ingestion and normalization FB向knowledge management FB发送归一化后的意图性能数据。
S305、knowledge management FB将接收到的意图性能数据存储到策略知识库。
S306、knowledge management FB根据第一意图目标，从策略知识库获取意图策略，然后向context awareness FB发送意图策略和意图性能数据请求，携带意图策略、以及与第一意图目标的达成情况和第一意图的执行条件的满足情况相关的意图性能数据。
S307、context awareness FB根据接收到的意图策略和意图性能数据，更新意图的上下文信息。该意图的上下文信息包括第一意图的执行条件中的KPI信息。context awareness FB 将意图的上下文信息更新到knowledge management FB。
S308、context awareness FB向situational awareness FB发送意图上下文信息感知结束通知，携带意图策略、意图的上下文信息、以及与第一意图目标的达成情况相关的意图性能数据。
S309、situational awareness FB根据接收到的意图策略和意图性能数据，判断第一意图目标是否达成，并预估第一意图目标的达成情况，更新意图状态信息。该意图状态信息包括第一意图目标达成性能以及达成的可能性，将该意图状态信息更新到knowledge management FB。
S310、situational awareness FB向model driven engineering FB发送意图状态感知结束通知，携带意图策略、意图上下文信息和意图状态信息。
S311、model driven engineering FB根据意图策略的intentOperations中的reliability决定需要执行的第一操作。
具体地，model driven engineeringFB根据当前达成第一意图目标的可能性，以及历史的达成第一意图目标的第一可信程度，决定需要执行的第一操作。该第一操作可以是第一意图操作，也可以是根据意图关键词从意图知识库获取的其它意图操作。例如，意图转译功能模块从意图知识库获取到与意图关键词对应的意图操作有三种，每种意图操作对应不同的意图目标和执行条件。若第一种意图操作的历史的第一可信程度较低，且model driven engineeringFB根据接收到的第一意图目标的达成情况与第一意图目标相比，预估第一意图目标不能达成，则model driven engineeringFB选择其它的意图操作；若第一种意图操作的历史的第一可信程度较高，且situational awareness FB预估可以达成第一意图目标，则model driven engineeringFB选择该第一意图操作。
S312、model driven engineering FB进行意图操作指令转换，并更新到knowledge management FB。
model driven engineering FB对选择的第一操作进行格式转化，转化为ENI系统内部的模块可以识别的操作指令。
S313、model driven engineering FB向policy management FB发送意图操作指令转换结束通知。
S314、policy management FB进行意图操作指令类型转换，并更新到knowledge management FB。
policy management FB对第一操作进行格式转化，转化为外部系统可以识别的操作指令。
以下两部分流程(即流程一和流程二)并行执行：
流程一：
S315、policy management FB向cognition management FB发送意图操作指令下发通知。该意图操作指令下发通知包括将要执行的第一操作。
该第一操作为步骤S314中policy management FB需要执行的第一操作。
S316、cognition management FB向situational awareness FB请求第一操作执行前的第一意图目标的达成情况。
S317、situational awareness FB向cognition management FB发送响应，用于指示接收到 上述请求。
如步骤S309中situational awareness FB根据第一意图对应的意图性能数据预估了达成第一意图目标的可能性，因此，可以由situational awareness FB向cognition management FB发送响应，该响应携带达成第一意图目标的可能性。
S318、cognition management FB对意图策略进行分析、推理、评估，确定更新的第一可信程度。该第一可信程度用于指示达成第一意图目标的可靠性。
cognition management FB获得了situational awareness FB发送的达成第一意图目标的可能性后，即执行了一次第一操作后，可以对意图策略进行分析、推理、评估，重新获得第一可信程度。
具体地，reliability的更新方法为：例如，对于意图策略p，其达成目标为g，当前监测的第一意图目标为j，reliability更新前为r，可以根据以下方法更新reliability：
●如果第一意图目标j已经满足达成目标g，reliability在r的基础上增加r1，更新r＝r+r1，r最大为100％。
●如果第一意图目标j没有满足达成目标g，但是在接近达成目标g(比较上次的检测结果)，reliability在r的基础上增加r2，更新r＝r+r2，r最大为100％。
●如果第一意图目标j没有满足达成目标g，但是在远离达成目标g(比较上次的检测结果)，reliability在r的基础上减少r3，更新r＝r-r3，r最小为0％。
S319、cognition management FB向knowledge management FB发送意图知识更新请求，携带更新后的reliability。
S320、knowledge management FB接收到意图知识更新请求后，对intent knowledge repository中的第一意图的第一知识进行更新。
S321、knowledge management FB向cognition management FB发送更新响应。
流程二：
S322、policy management FB向denormalization and output generation FB发送意图指令执行请求。
S323、denormalization and output generation FB向第三网元发送意图指令执行请求。
可以理解的是，如图9所示，上述流程一和流程二可以是并列执行的，即更新第一可信程度与执行第一操作可以是并列执行的，这样可以提高ENI系统的执行效率。
还可以理解的是，如图9所示，上述流程一和流程二可以是循环执行的，即在第一意图执行过程中可以不断地根据意图性能数据更新第一可信程度，或，不断地执行第一意图对应的意图策略，直到该意图策略被去激活或被删除。
在本实施例中，第一网元可以根据第一意图对应的意图性能数据预估达成第一意图目标的可能性，估计达成第一意图目标的第一可信程度，并将估计出的第一可信程度更新到意图知识库，以便于第一网元后续可以根据更新的第一可信程度选择第一操作，提高了第一操作选择的准确性；且在当前选择操作时，可以根据历史的第一可信程度选择第一操作，提高了第一操作选择的准确性。
如图10所示，为意图保障过程中的又一种通信方法的流程示意图。在该方法中，第一知识包括第一信息。示例性地，该方法可以包括以下步骤：
S401、context awareness FB向denormalization and output generation FB发送意图性能数据订阅请求准备。该意图性能数据订阅请求准备携带第一意图目标，executionConditon中的KPI以及第一信息中。
S402、denormalization and output generation FB向第三网元发送意图性能数据订阅请求。
S403、第三网元向ENI系统发送意图性能数据订阅响应，携带被请求的意图性能数据。
具体地，第三网元根据意图性能数据订阅请求中携带的第一意图目标，executionConditon中的KPI，获取第一意图目标的达成情况、第一意图的执行条件的满足情况、第一意图的约束条件的满足情况等意图性能数据。另外，该意图性能数据订阅请求还携带第一信息中的events和impact，以请求获取第二意图的意图性能数据，以便于cognition management FB根据获取到的第二意图的意图性能数据，更新该impact。然后，第三网元向data ingestion and normalization FB发送意图性能数据订阅响应。该意图性能数据订阅响应携带上述意图性能数据。
S404、data ingestion and normalization FB向knowledge management FB发送归一化后的意图性能数据。
S405、knowledge management FB将接收到的意图性能数据存储到策略知识库。
S406、knowledge management FB根据第一意图目标，从策略知识库获取意图策略，然后向context awareness FB发送意图策略和意图性能数据请求，携带意图策略、以及与第一意图目标的达成情况和第一意图的执行条件的满足情况相关的意图性能数据，以及与第一信息相关的意图性能数据。
S407、context awareness FB根据接收到的意图策略和意图性能数据，更新意图的上下文信息。该意图的上下文信息包括第一意图的执行条件中的KPI信息。context awareness FB将意图的上下文信息更新到knowledge management FB。
S408、context awareness FB向situational awareness FB发送意图上下文信息感知结束通知，携带意图策略、意图的上下文信息、以及与第一意图目标的达成情况相关的意图性能数据。
S409、situational awareness FB根据接收到的意图策略和意图性能数据，判断第一意图目标是否达成，并预估第一意图目标的达成情况，更新意图状态信息。该意图状态信息包括第一意图目标达成性能以及达成的可能性，将该意图状态信息更新到knowledge management FB。
S410、situational awareness FB向model driven engineering FB发送意图状态感知结束通知，携带意图策略、意图上下文信息和意图状态信息。
S411、model driven engineering FB根据意图策略的intentOperations中的events以及impact决定需要执行的第一操作。
具体地，model driven engineering FB根据当前达成第一意图目标的可能性，以及历史的达成第一意图的第一事件events以及impact决定需要执行的第一操作。
model driven engineering FB根据接收到的达成第一意图目标的可能性、第一意图操作对第二意图的影响值决定需要执行的第一操作。例如，执行第一意图操作，达成第一意图目标的可能性较低，和/或该第一意图操作对第二意图的影响值为负值，则model driven  engineering FB选择意图关键词对应的其它意图操作作为第一操作。又例如，执行第一意图操作，达成第一意图目标的可能性较高，和/或该第一意图操作对第二意图的影响值为零，则model driven engineering FB选择该第一意图操作作为第一操作。
S412、model driven engineering FB进行意图操作指令转换，并更新到knowledge management FB。
model driven engineering FB对选择的第一操作进行格式转化，转化为ENI系统内部的模块可以识别的操作指令。
S413、model driven engineering FB向policy management FB发送意图操作指令转换结束通知。
S414、policy management FB进行意图操作指令类型转换，并更新到knowledge management FB。
policy management FB对第一操作进行格式转化，转化为外部系统可以识别的操作指令。
以下两部分流程(即流程一和流程二)并行执行：
流程一：
S415、policy management FB向cognition management FB发送意图操作指令下发通知。该意图操作指令下发通知包括将要执行的第一操作。
该第一操作为步骤S414中policy management FB需要执行的第一操作。
S416、cognition management FB向context awareness FB请求第一操作执行前的第二意图的上下文情况。
S417、context awareness FB进行第一信息数据上下文感知分析，向cognition management FB发送响应，用于指示接收到上述请求。
context awareness FB根据情景感知分析events的impact，并将该impact发送给cognition management FB。
context awareness FB根据第一意图、第二意图的上下文信息，进行情景感知分析，评估该events的impact，具体地，评估执行第一操作对第二意图的意图目标或约束条件或执行条件的影响值，获得impact的情景感知结果。context awareness FB将该impact的情景感知结果发送给cognition management FB。
S418、cognition management FB根据获取的意图性能数据对第一意图的意图策略进行分析、推理、评估，计算并更新impact。
cognition management FB根据接收到的第一意图、第二意图的意图性能数据以及context awareness FB发送的impact的情景感知结果，对第一意图的意图策略进行分析、推理、评估，计算impact。
具体地，一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的意图目标已达成。则第一网元执行第一操作后，若第二意图的意图目标从已达成变成未达成，则确定第一操作对第二意图的影响值为负值；或若第二意图的意图目标处于目标已达成且达成情况没有改变，则确定第一操作对第二意图的影响值为零。
另一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的约束条件已满足。则第一网元执行第一操作后，若执行第一操作相对于未执行第一操作时，第 二意图的约束条件从已满足变成未满足，则确定第一操作对第二意图的影响值为负值；或执行第一操作相对于未执行第一操作时，对第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定第一操作对第二意图的影响值为零。
又一种情况下，第一网元未执行第一操作，而第二意图已经执行并且第二意图的执行条件已满足。则第一网元执行第一操作后，若执行第一操作相对于未执行第一操作时，第二意图的执行条件从已满足变成未满足，则确定第一操作对第二意图的影响值为负值；或执行第一操作相对于未执行第一操作时，对第二意图的执行条件已满足情况没有改变，第二意图一直处于执行条件已满足，则确定第一操作对第二意图的影响值为零。
可以理解的是，也可以根据上述一种或多种情况确定第一操作对第二意图的影响值。
以操作O对意图B的意图目标产生影响为例，意图A的意图目标为保证小区吞吐量为80，意图A采用操作O增大下行功率。意图B的意图目标为保证小区能耗小于100。意图A的操作O会对意图B产生影响。采用操作O后，若意图B中小区能耗当前为120(上次监测结果为90)，则impact为-1；若意图B中小区能耗当前为90(上次监测结果为90)，则impact为0。
S419、cognition management FB向knowledge management FB发送意图知识更新请求，该意图知识更新请求包括第一信息。该第一信息包括该events和更新的impact。
S420、knowledge management FB接收到意图知识更新请求后，将该意图知识更新请求携带的第一信息更新到intent knowledge repository中。
S421、knowledge management FB向cognition management FB发送更新响应。
流程二：
S422、policy management FB向denormalization and output generation FB发送意图指令执行请求。
S423、denormalization and output generation FB向第三网元发送意图指令执行请求。
可以理解的是，如图10所示，上述流程一和流程二可以是并列执行的，即更新第一信息与执行第一操作可以是并列执行的，这样可以提高ENI系统的执行效率。
还可以理解的是，如图10所示，上述流程一和流程二可以是循环执行的，即在第一意图执行过程中可以不断地根据意图性能数据更新第一信息，或，不断地执行第一意图对应的意图策略，直到该意图策略被去激活或被删除。
在本实施例中，第一网元可以根据第二意图对应的意图性能数据估计采用第一操作对第二意图的影响值，并将该事件和估计出的影响值更新到意图知识库，以便于第一网元后续可以根据更新的事件和影响值选择第一操作，提高了第一操作选择的准确性。
如图11所示，为意图执行和维持过程中的又一种通信方法流程示意图。在该方法中，第一知识包括达成第一意图目标的第一可信程度和第一信息。示例性地，该方法可以包括以下步骤：
S501、context awareness FB向denormalization and output generation FB发送意图性能数据订阅请求准备。该意图性能数据订阅请求准备携带第一意图目标，executionConditon中的KPI以及第一信息中的KPI。
S502、denormalization and output generation FB向第三网元发送意图性能数据订阅请求。
S503、第三网元向ENI系统发送意图性能数据订阅响应，携带被请求的意图性能数据。
具体地，第三网元根据意图性能数据订阅请求中携带的第一意图目标，executionConditon中的KPI，获取第一意图目标的达成情况和第一意图的执行条件的满足情况等意图性能数据。另外，该意图性能数据订阅请求还携带第一信息中的events和impact，以请求获取第二意图的意图性能数据，以便于cognition management FB根据获取到的第二意图的意图性能数据，更新该impact。然后，第三网元向data ingestion and normalization FB发送意图性能数据订阅响应。该意图性能数据订阅响应携带上述意图性能数据。
S504、data ingestion and normalization FB向knowledge management FB发送归一化后的意图性能数据。
S505、knowledge management FB将接收到的意图性能数据存储到策略知识库。
S506、knowledge management FB根据第一意图目标，从策略知识库获取意图策略，然后向context awareness FB发送意图策略和意图性能数据请求，携带意图策略、以及与第一意图目标的达成情况和第一意图的执行条件的满足情况相关的意图性能数据，以及与第一信息相关的意图性能数据。
S507、context awareness FB根据接收到的意图策略和意图性能数据，更新意图的上下文信息。该意图的上下文信息包括第一意图的执行条件中的KPI信息。context awareness FB将意图的上下文信息更新到knowledge management FB。
S508、context awareness FB向situational awareness FB发送意图上下文信息感知结束通知，携带意图策略、意图的上下文信息、以及与第一意图目标的达成情况相关的意图性能数据。
S509、situational awareness FB根据接收到的意图策略和意图性能数据，判断第一意图目标是否达成，并预估第一意图目标的达成情况，更新意图状态信息。该意图状态信息包括第一意图目标达成性能以及达成的可能性，将该意图状态信息更新到knowledge management FB。
S510、situational awareness FB向model driven engineering FB发送意图状态感知结束通知，携带意图策略、意图上下文信息和意图状态信息。
S511、model driven engineering FB根据意图策略的intentOperations中的reliability、events以及impact决定需要执行的第一操作。
具体地，model driven engineering FB根据当前达成第一意图目标的可能性，历史的达成第一意图目标的第一可信程度，以及历史的达成第一意图的第一事件events以及impact决定需要执行的第一操作。
model driven engineering FB根据接收到的达成第一意图目标的可能性、历史的达成第一意图目标的第一可信程度、第一意图操作对第二意图的影响值决定需要执行的第一操作。例如，执行第一意图操作，若第一意图操作的历史的第一可信程度较低，达成第一意图目标的可能性较低，和/或该第一意图操作对第二意图的影响值为负值，则model driven engineering FB选择意图关键词对应的其它意图操作作为第一操作。又例如，执行第一意图操作，若第一意图操作的历史的第一可信程度较高，达成第一意图目标的可能性较高，和/或该第一意图操作对第二意图的影响值为零，则model driven engineering FB选择该第一意 图操作作为第一操作。
S512、model driven engineering FB进行意图操作指令转换，并更新到knowledge management FB。
model driven engineering FB对选择的第一操作进行格式转化，转化为ENI系统内部的模块可以识别的操作指令。
S513、model driven engineering FB向policy management FB发送意图操作指令转换结束通知。
S514、policy management FB进行意图操作指令类型转换，并更新到knowledge management FB。
policy management FB对第一操作进行格式转化，转化为外部系统可以识别的操作指令。
以下两部分流程(即流程一和流程二)并行执行：
流程一：
S515、policy management FB向cognition management FB发送意图操作指令下发通知。该意图操作指令下发通知包括将要执行的第一操作。
该第一操作为步骤S514中policy management FB需要执行的第一操作。
S516、cognition management FB向context awareness FB请求第一操作执行前的第二意图的上下文情况。
S517、context awareness FB进行第一信息数据上下文感知分析，向cognition management FB发送响应，用于指示接收到上述请求。
context awareness FB根据情景感知分析events的impact，并将该impact发送给cognition management FB。
context awareness FB根据第一意图、第二意图的上下文信息，进行情景感知分析，评估该events的impact，具体地，评估执行第一操作对第二意图的意图目标或约束条件或执行条件的影响值，获得impact的情景感知结果。context awareness FB将该impact的情景感知结果发送给cognition management FB。
S518、cognition management FB向situational awareness FB请求第一操作执行前的第一意图目标的达成情况。
S519、situational awareness FB向cognition management FB发送响应，用于指示接收到上述请求。
如步骤S509中situational awareness FB根据第一意图对应的意图性能数据预估了达成第一意图目标的可能性，因此，可以由situational awareness FB向cognition management FB发送响应，该响应携带达成第一意图目标的可能性。
S520、cognition management FB根据获取的意图性能数据对第一意图的意图策略进行分析、推理、评估，计算并更新impact；以及cognition management FB对意图策略进行分析、推理、评估，确定更新的第一可信程度。该第一可信程度用于指示达成第一意图目标的可靠性。
cognition management FB确定更新的第一可信程度，可参考图9所示实施例的步骤S318；cognition management FB确定更新的impact，可参考图10所示实施例的步骤S418。S521、 cognition management FB向knowledge management FB发送意图知识更新请求，该意图知识更新请求包括更新的第一知识。其中，更新的第一知识包括更新的第一可信程度和第一信息。该第一信息包括该events和更新的impact。
S522、knowledge management FB接收到意图知识更新请求后，将该意图知识更新请求携带的第一知识更新到intent knowledge repository中。
S523、knowledge management FB向cognition management FB发送更新响应。
流程二：
S524、policy management FB向denormalization and output generation FB发送意图指令执行请求。
S525、denormalization and output generation FB向第三网元发送意图指令执行请求。
可以理解的是，如图11所示，上述流程一和流程二可以是并列执行的，即更新第一知识与执行第一操作可以是并列执行的，这样可以提高ENI系统的执行效率。
还可以理解的是，如图11所示，上述流程一和流程二可以是循环执行的，即在第一意图执行过程中可以不断地根据意图性能数据更新第一知识，或，不断地执行第一意图对应的意图策略，直到该意图策略被去激活或被删除。
在本实施例中，第一网元可以根据第二意图对应的意图性能数据重新计算第一知识，并将该重新计算出的第一知识更新到意图知识库，以便于第一网元后续可以根据更新的第一知识选择第一操作，提高了第一操作选择的准确性。
如图12所示，为本申请实施例提供的又一种通信方法的流程示意图。示例性地，该方法包括以下步骤：
S601、第二网元从第一网元获取第一意图操作。
第二网元向第一网元下发第一意图，第一网元进行意图编排，从intent knowledge repository获取第一意图的第一知识，并根据第一知识选择第一操作，该第一操作用于执行第一意图。在本实施例中，第一操作为第一意图操作。
该第二网元可以是用户，APP，OSS等功能实体。
第一网元在执行意图过程中或执行意图后，可以通知第二网元第一意图对应的操作为第一意图操作，从而第二网元可以获知第一意图操作。
具体地，第二网元从第一网元的policy management FB获取第一意图操作。
S602、第二网元确定第一意图操作对第二意图有影响。
第二网元在下发第一意图之前、同时或之后，还可以向第一网元下发第二意图。其中，第二意图与第一意图不同。第二网元在获取第一意图对应的第一意图操作之后，确定第一意图操作对第二意图有影响。具体地，第一意图操作对第二意图的约束条件或意图目标或执行条件有影响。
S603、第二网元向第一网元的data ingestion and normalization FB发送意图知识更新请求。
第二网元确定第一意图操作对第二意图有影响后，需要在第一网元中更新第一意图的第一知识。具体地，更新第一意图的第一信息。该第一信息具体是指事件，而可以不包括影响值。该更新请求也不包括第一可信程度。因为影响值和第一可信程度是评价类指标， 需要在ENI系统的运行过程中进行评价更新，不需要由外部系统(即第二网元)进行更新。
可以通过意图知识更新请求携带上述第一信息。该意图知识更新请求用于请求更新第一意图的第一知识。该第一信息用于指示第一意图操作对第二意图的影响。具体地，该第一信息用于指示第一意图操作对第二意图的约束条件或意图目标或执行条件的影响。该第一信息用于第一操作的选择。该第一操作用于执行第一意图。
S604、data ingestion and normalization FB向cognition management FB转发上述意图知识更新请求。
S605、cognition management FB对第一信息进行分析，判断是否将该第一信息更新到intent knowledge repository。
cognition management FB接收到意图知识更新请求后，获取意图知识更新请求携带的第一信息，并对第一信息进行分析，判断是否将该第一信息更新到intent knowledge repository。具体地，例如，cognition management FB判断第一意图操作对第二意图的约束条件或意图目标或执行条件是否确实会产生影响，若判断的结果为是，则确定需要将第一信息更新到intent knowledge repository；否则，确定不需要将第一信息更新到intent knowledge repository。
S606、如果S605中判断需要更新，cognition management FB向knowledge management FB发送意图知识更新请求，该意图知识更新请求包括第一信息。
该意图知识更新请求用于请求将第一信息更新到intent knowledge repository。该intent knowledge repository设置于knowledge management FB。因而，cognition management FB向knowledge management FB发送意图知识更新请求，该意图知识更新请求包括第一信息。
S607、knowledge management FB将第一信息更新到intent knowledge repository。
S608、knowledge management FB发送意图知识更新响应给cognition management FB，该第二意图知识更新响应用于指示是否更新成功。
S609、cognition management FB向data ingestion and normalization FB发送意图知识更新响应。
S610、data ingestion and normalization FB向第二网元转发意图知识更新响应。
具体地，如果S605中判断需要更新，根据意图知识更新响应，cognition management FB向第二网元发送意图知识更新响应；如果S605判断不需要更新，cognition management FB给外部系统发送意图知识更新响应，该意图知识更新响应用于指示不需要进行更新。
第一网元在将第一信息更新到intent knowledge repository后，下一次在执行第一意图时，根据意图关键词从intent knowledge repository获取第一知识，该第一知识包括上述第一信息，则第一网元可以根据第一知识选择第一操作，例如，假设第一意图操作对第二意图的影响为负，则第一网元避免选择第一意图操作；假设第一意图操作对第二意图的影响为零，则第一网元可以选择该第一意图操作作为第一操作。
根据本申请实施例提供的一种通信方法，第二网元在获取到第一网元执行第一意图操作时，且确定第一意图操作对第二意图有影响，则第二网元可以向第一网元指示第一意图操作对第二意图的影响，以使第一网元准确地选择第一操作。
可以理解的是，以上各个实施例中，由第一网元实现的方法和/或步骤，也可以由可用 于第一网元的部件(例如芯片或者电路)实现；由第二网元实现的方法和/或步骤，也可以由第二网元的部件(例如芯片或者电路)实现。
上述主要从各个网元之间交互的角度对本申请实施例提供的方案进行了介绍。相应的，本申请实施例还提供了通信装置，该通信装置用于实现上述各种方法。该通信装置可以为上述方法实施例中的第一网元，或者包含上述第一网元的装置，或者为可用于第一网元的部件；或者，该通信装置可以为上述方法实施例中的第二网元，或者包含上述第二网元的装置，或者为可用于第二网元的部件。可以理解的是，该通信装置为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法实施例中对通信装置进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
基于上述通信方法的同一构思，如图13所示，本申请实施例还提供了一种通信装置。该通信装置500包括：处理单元51，还可以包括收发单元52；其中：
所述处理单元51，用于获取第一意图的第一知识，所述第一意图的第一知识包括以下信息中的一项或多项：达成第一意图目标的第一可信程度和第一信息，所述第一可信程度用于指示达成所述第一意图目标的可靠性，所述第一信息用于指示第一意图操作对第二意图的影响，所述第二意图与所述第一意图不同；
所述处理单元51，还用于根据所述第一意图的第一知识选择第一操作，所述第一操作用于执行所述第一意图。
由上可知，第一网元可以根据达成第一意图目标的可信程度和/或第一信息选择第一操作，可以提高第一操作的选择的准确性。
在一种可能的实现中，所述第一信息包括事件和影响值，所述事件包括所述第二意图的约束条件或意图目标或执行条件，所述影响值用于指示对所述事件的影响程度。在该实现中，该第一知识为第一信息，该第一信息包括事件和影响值，该第一信息体现为第一操作对第二意图的约束条件或意图目标或执行条件的影响程度。
在另一种可能的实现中，所述处理单元51，用于确定所述第一意图的第一知识；或者，
所述收发单元52，用于从第二网元接收所述第一意图的第一知识，所述第二网元为网络管理系统NMS，用户、应用程序APP、运营支撑系统或业务支撑系统等功能实体。在该实现中，第一网元可以内部确定第一知识，也可以从外部系统，例如第二网元，获取第一知识。
在又一种可能的实现中，所述处理单元51，用于获取所述第一意图的意图表达式对应的意图关键词，所述意图关键词包括以下信息中的一项或多项：所述第一意图目标、所述 第一意图作用的区域、所述第一意图作用的网元名称；
所述处理单元51，还用于根据所述意图关键词，从意图知识库获取所述意图关键词对应的所述第一知识。
在该实现中，第一知识存储在意图知识库，第一网元在进行意图转译时，可以根据转译过程中获得的意图关键词从意图知识库获取对应的第一知识。
在又一种可能的实现中，所述收发单元52，还用于从第三网元获取意图性能数据；
所述处理单元51，还用于根据所述意图性能数据，确定所述第一意图的第一条件的满足情况，其中，所述第一条件包括以下一项或多项信息：所述第一意图目标，所述第一意图的约束条件，所述第一意图的执行条件；
所述处理单元51，还用于根据所述第一条件的满足情况和所述第一意图的第二知识，确定所述第一意图的第一知识，所述第一意图的第二知识为所述第一意图的第一知识更新前的知识。
在该实现中，第一网元根据意图执行过程中第一条件的满足情况和第一意图的历史知识，对第一知识进行更新。
在又一种可能的实现中，所述第一知识为所述第一可信程度；
所述处理单元51，还用于所述第一意图目标达成，确定所述第一可信程度为第二可信程度与第一可信程度增量之和；或
所述处理单元51，还用于所述第一意图目标未达成，且所述第一意图目标的第一达成情况与所述第一意图目标的第二达成情况之差为负值，确定所述第一可信程度为所述第二可信程度与第二可信程度增量之和，所述第二可信程度增量小于所述第一可信程度增量；或
所述处理单元51，还用于所述第一意图目标未达成，且所述第一达成情况与所述第二达成情况之差为正值，确定所述第一可信程度为所述第二可信程度与第三可信程度增量之差；
其中，所述第二可信程度为所述第一可信程度更新前的可信程度，所述第一达成情况为所述第一意图目标在第一时间段的达成情况与所述第一意图目标之差的绝对值，所述第二达成情况为所述第一意图目标在第二时间段的达成情况与所述第一意图目标之差的绝对值，所述第二时间段早于所述第一时间段。
在该实现中，第一网元根据第一意图目标当前的达成情况和历史的达成情况，对达成第一意图目标的第一可信程度进行更新。
在又一种可能的实现中，所述影响值用于指示所述第一操作对所述第二意图的约束条件或意图目标或执行条件的影响值。
在又一种可能的实现中，所述处理单元51，还用于若所述第二意图的意图目标从已达成变成未达成，则确定所述第一操作对所述第二意图的影响值为负值；或
所述处理单元51，还用于若所述第二意图的意图目标处于目标已达成且达成情况没有改变，则确定所述第一操作对所述第二意图的影响值为零。
在该实现中，第一操作对第二意图的影响值是根据第二意图的意图目标的达成情况确定的，或者说，第一知识体现为第一操作对第二意图的意图目标的影响。
在又一种可能的实现中，所述处理单元51，还用于执行所述第一操作相对于未执行所述第一操作时，所述第二意图的约束条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或
所述处理单元51，还用于执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
在该实现中，第一操作对第二意图的影响值是根据第二意图的约束条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的约束条件的影响。
在又一种可能的实现中，所述处理单元51，还用于执行所述第一操作相对于未执行所述第一操作时，所述第二意图的执行条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或
所述处理单元51，还用于执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的执行条件已满足情况没有改变，所述第二意图一直处于执行条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
在该实现中，第一操作对第二意图的影响值是根据第二意图的执行条件的满足情况确定的，或者说，第一知识体现为第一操作对第二意图的执行条件的影响。
在又一种可能的实现中，所述处理单元51，还用于根据所述第一意图目标的第一达成情况、一个或多个已存在的意图操作对应的第二知识、和所述第一意图的第一知识，在所述一个或多个已存在的意图操作中确定所述第一操作。
在该实现中，若第一操作对应的第一意图目标可达成，则可以在已存在的意图操作中选择第一操作。
有关上述处理单元51和收发单元52的具体实现可参考图7至图12所示的通信方法中第一网元的相应描述，在此不再赘述。
根据本申请实施例提供的一种通信装置，该通信装置可以根据达成第一意图目标的可信程度和/或第一信息选择第一操作，可以提高第一操作的选择的准确性。
基于上述通信方法的同一构思，如图14所示，本申请实施例还提供了一种通信装置。该通信装置600包括：收发单元61和处理单元62；其中：
收发单元61，用于从第一网元获取第一意图操作；
处理单元62，用于确定所述第一意图操作对第二意图有影响，所述第二意图与所述第一意图不同；
所述收发单元61，还用于向所述第一网元发送第一信息，所述第一信息用于指示所述第一意图操作对所述第二意图的影响，所述第一信息用于第一操作的选择，所述第一操作用于执行所述第一意图。
有关上述收发单元61和处理单元62的具体实现可参考图7至图12所示的通信方法中第二网元的相关描述。
根据本申请实施例提供的一种通信装置，该通信装置在获取到第一网元执行第一意图操作时，且确定第一意图操作对第二意图有影响，则该通信装置可以向第一网元指示第一意图操作对第二意图的影响，以使第一网元准确地选择第一操作。
如图15所示，还提供了一种通信装置的硬件结构示意图，该通信装置用于执行上述通信方法。上述方法中的部分或全部可以通过硬件来实现，也可以通过软件或固件来实现。
可选的，该通信装置在具体实现时可以是芯片或者集成电路。
可选的，当上述实施例的通信方法中的部分或全部通过软件或固件来实现时，可以通过图15提供的一种通信装置700来实现。如图15所示，该通信装置700可包括：
存储器33和处理器34(装置中的处理器34可以是一个或多个，图15中以一个处理器为例)，还可以包括输入装置31、输出装置32。在本实施例中，输入装置31、输出装置32、存储器33和处理器34可通过总线或其它方式连接，其中，图15中以通过总线连接为例。
其中，在一个实施例中，处理器34用于执行图7～图12中第一网元所执行的方法步骤。
在另一个实施例中，处理器34用于执行图7～图12中第二网元所执行的方法步骤。
可选的，上述通信方法的程序可以存储在存储器33中。该存储器33可以是物理上独立的单元，也可以与处理器34集成在一起。该存储器33也可以用于存储数据。
可选的，当上述实施例的通信方法中的部分或全部通过软件实现时，该通信装置也可以只包括处理器。用于存储程序的存储器位于该通信装置之外，处理器通过电路或电线与存储器连接，用于读取并执行存储器中存储的程序。
处理器可以是中央处理器(central processing unit，CPU)，网络处理器(network processor，NP)，或WLAN设备。
处理器还可以进一步包括硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。
存储器可以包括易失性存储器(volatile memory)，例如随机存取存储器(random-access memory，RAM)；存储器也可以包括非易失性存储器(non-volatile memory)，例如快闪存储器(flash memory)，硬盘(hard disk drive，HDD)或固态硬盘(solid-state drive，SSD)；存储器还可以包括上述种类的存储器的组合。
本领域技术人员应明白，本公开一个或多个实施例可提供为方法、系统或计算机程序产品。因此，本公开一个或多个实施例可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本公开一个或多个实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请实施例还提供了一种芯片系统，包括：至少一个处理器和接口，该至少一个处理器通过接口与存储器耦合，当该至少一个处理器执行存储器中的计算机程序或指令时，使得上述任一方法实施例中的方法被执行。可选的，该芯片系统可以由芯片构成，也可以包含芯片和其他分立器件，本申请实施例对此不作具体限定。
本申请实施例还提供一种计算机可读存储介质，该存储介质上可以存储有计算机程序，所述程序被处理器执行时实现本公开任一实施例描述的通信方法的步骤。
本申请实施例还提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行本公开任一实施例描述的通信方法的步骤。
本申请实施例还提供一种通信系统，该通信系统包括上述的通信装置。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
应理解，在本申请的描述中，除非另有说明，“/”表示前后关联的对象是一种“或”的关系，例如，A/B可以表示A或B；其中A，B可以是单数或者复数。并且，在本申请的描述中，除非另有说明，“多个”是指两个或多于两个。“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。同时，在本申请实施例中，“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它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，便于理解。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，该单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如，多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。所显示或讨论的相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
在上述实施例中，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。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。该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该计算机程序指令时，全部或部分地产生按照本申请实施例的流程或功能。该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。该计算机指令可以存储在计算机可读存储介质中，或者通过该计算机可读存储介质进行传输。该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(digital subscriber line，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。该计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含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。该可用介质可以是只读存储器(read-only memory，ROM)，或随机接入存储器(random access memory，RAM)，或磁性介质，例如，软盘、硬盘、磁带、磁碟、或光介质，例如，数字通用光盘(digital versatile disc，DVD)、或者半导体介质，例如，固态硬盘(solid state disk，SSD)等。

Claims (25)

  1. 一种通信方法，其特征在于，所述方法包括：
    第一网元获取第一意图的第一知识，所述第一意图的第一知识包括以下信息中的一项或多项：达成第一意图目标的第一可信程度和第一信息，所述第一可信程度用于指示达成所述第一意图目标的可靠性，所述第一信息用于指示第一意图操作对第二意图的影响，所述第二意图与所述第一意图不同；
    所述第一网元根据所述第一意图的第一知识选择第一操作，所述第一操作用于执行所述第一意图。
  2. 根据权利要求1所述的方法，其特征在于，所述第一信息包括事件和影响值，所述事件包括所述第二意图的约束条件或意图目标或执行条件，所述影响值用于指示对所述事件的影响程度。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第一网元获取第一意图的第一知识，包括：
    所述第一网元确定所述第一意图的第一知识；或者，
    所述第一网元从第二网元接收所述第一意图的第一知识，所述第二网元为网络管理系统NMS，用户或应用程序APP。
  4. 根据权利要求3所述的方法，其特征在于，所述第一网元确定所述第一意图的第一知识，包括：
    所述第一网元获取所述第一意图的意图表达式对应的意图关键词，所述意图关键词包括以下信息中的一项或多项：所述第一意图目标、所述第一意图作用的区域、所述第一意图作用的网元名称；
    所述第一网元根据所述意图关键词，从意图知识库获取所述意图关键词对应的所述第一知识。
  5. 根据权利要求3或4所述的方法，其特征在于，所述第一网元确定所述第一意图的第一知识，包括：
    所述第一网元从第三网元获取意图性能数据；
    所述第一网元根据所述意图性能数据，确定所述第一意图的第一条件的满足情况，其中，所述第一条件包括以下一项或多项信息：所述第一意图目标，所述第一意图的约束条件，所述第一意图的执行条件；
    所述第一网元根据所述第一条件的满足情况和所述第一意图的第二知识，确定所述第一意图的第一知识，所述第一意图的第二知识为所述第一意图的第一知识更新前的知识。
  6. 根据权利要求5所述的方法，其特征在于，所述第一知识为所述第一可信程度，所述第一网元根据所述第一条件的满足情况和所述第一意图的第二知识，确定所述第一意图的第一知识，包括：
    所述第一意图目标达成，确定所述第一可信程度为第二可信程度与第一可信程度增量之和；或
    所述第一意图目标未达成，且所述第一意图目标的第一达成情况与所述第一意图目标的第二达成情况之差为负值，确定所述第一可信程度为所述第二可信程度与第二可信程度增量之和，所述第二可信程度增量小于所述第一可信程度增量；或
    所述第一意图目标未达成，且所述第一达成情况与所述第二达成情况之差为正值，确定所述第一可信程度为所述第二可信程度与第三可信程度增量之差；
    其中，所述第二可信程度为所述第一可信程度更新前的可信程度，所述第一达成情况为所述第一意图目标在第一时间段的达成情况与所述第一意图目标之差的绝对值，所述第二达成情况为所述第一意图目标在第二时间段的达成情况与所述第一意图目标之差的绝对值，所述第二时间段早于所述第一时间段。
  7. 根据权利要求3～6任一项所述的方法，其特征在于，所述影响值用于指示所述第一操作对所述第二意图的约束条件或意图目标或执行条件的影响值。
  8. 根据权利要求7所述的方法，其特征在于，所述第一网元确定所述第一意图的第一知识，包括：
    若所述第二意图的意图目标从已达成变成未达成，则确定所述第一操作对所述第二意图的影响值为负值；或
    若所述第二意图的意图目标处于目标已达成且达成情况没有改变，则确定所述第一操作对所述第二意图的影响值为零。
  9. 根据权利要求7或8所述的方法，其特征在于，所述第一网元确定所述第一意图的第一知识，包括：
    执行所述第一操作相对于未执行所述第一操作时，所述第二意图的约束条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或
    执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
  10. 根据权利要求7～9任一项所述的方法，其特征在于，所述第一网元确定所述第一意图的第一知识，包括：
    执行所述第一操作相对于未执行所述第一操作时，所述第二意图的执行条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或
    执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的执行条件已满足 情况没有改变，所述第二意图一直处于执行条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
  11. 根据权利要求6～10任一项所述的方法，其特征在于，所述第一网元根据所述第一意图的第一知识选择第一操作，包括：
    所述第一网元根据所述第一意图目标的第一达成情况、一个或多个已存在的意图操作对应的第二知识、和所述第一意图的第一知识，在所述一个或多个已存在的意图操作中确定所述第一操作。
  12. 一种通信方法，其特征在于，所述方法包括：
    第二网元从第一网元获取第一意图操作；
    所述第二网元确定所述第一意图操作对第二意图有影响，所述第二意图与所述第一意图不同；
    所述第二网元向所述第一网元发送第一信息，所述第一信息用于指示所述第一意图操作对所述第二意图的影响，所述第一信息用于第一操作的选择，所述第一操作用于执行所述第一意图。
  13. 一种通信装置，其特征在于，所述装置包括：
    处理单元，用于获取第一意图的第一知识，所述第一意图的第一知识包括以下信息中的一项或多项：达成第一意图目标的第一可信程度和第一信息，所述第一可信程度用于指示达成所述第一意图目标的可靠性，所述第一信息用于指示第一意图操作对第二意图的影响，所述第二意图与所述第一意图不同；
    所述处理单元，还用于根据所述第一意图的第一知识选择第一操作，所述第一操作用于执行所述第一意图。
  14. 根据权利要求13所述的通信装置，其特征在于，所述第一信息包括事件和影响值，所述事件包括所述第二意图的约束条件或意图目标或执行条件，所述影响值用于指示对所述事件的影响程度。
  15. 根据权利要求13或14所述的通信装置，其特征在于，所述处理单元，用于确定所述第一意图的第一知识；或者，
    所述装置还包括：
    收发单元，用于从第二网元接收所述第一意图的第一知识，所述第二网元为网络管理系统NMS，用户或应用程序APP。
  16. 根据权利要求15所述的通信装置，其特征在于，所述处理单元，用于获取所述第一意图的意图表达式对应的意图关键词，所述意图关键词包括以下信息中的一项或多项：所述第一意图目标、所述第一意图作用的区域、所述第一意图作用的网元名称；
    所述处理单元，还用于根据所述意图关键词，从意图知识库获取所述意图关键词对应的所述第一知识。
  17. 根据权利要求15或16所述的通信装置，其特征在于：
    所述收发单元，还用于从第三网元获取意图性能数据；
    所述处理单元，还用于根据所述意图性能数据，确定所述第一意图的第一条件的满足情况，其中，所述第一条件包括以下一项或多项信息：所述第一意图目标，所述第一意图的约束条件，所述第一意图的执行条件；
    所述处理单元，还用于根据所述第一条件的满足情况和所述第一意图的第二知识，确定所述第一意图的第一知识，所述第一意图的第二知识为所述第一意图的第一知识更新前的知识。
  18. 根据权利要求17所述的通信装置，其特征在于，所述第一知识为所述第一可信程度；
    所述处理单元，还用于所述第一意图目标达成，确定所述第一可信程度为第二可信程度与第一可信程度增量之和；或
    所述处理单元，还用于所述第一意图目标未达成，且所述第一意图目标的第一达成情况与所述第一意图目标的第二达成情况之差为负值，确定所述第一可信程度为所述第二可信程度与第二可信程度增量之和，所述第二可信程度增量小于所述第一可信程度增量；或
    所述处理单元，还用于所述第一意图目标未达成，且所述第一达成情况与所述第二达成情况之差为正值，确定所述第一可信程度为所述第二可信程度与第三可信程度增量之差；
    其中，所述第二可信程度为所述第一可信程度更新前的可信程度，所述第一达成情况为所述第一意图目标在第一时间段的达成情况与所述第一意图目标之差的绝对值，所述第二达成情况为所述第一意图目标在第二时间段的达成情况与所述第一意图目标之差的绝对值，所述第二时间段早于所述第一时间段。
  19. 根据权利要求15～18任一项所述的通信装置，其特征在于，所述影响值用于指示所述第一操作对所述第二意图的约束条件或意图目标或执行条件的影响值。
  20. 根据权利要求19所述的通信装置，其特征在于：
    所述处理单元，还用于若所述第二意图的意图目标从已达成变成未达成，则确定所述第一操作对所述第二意图的影响值为负值；或
    所述处理单元，还用于若所述第二意图的意图目标处于目标已达成且达成情况没有改变，则确定所述第一操作对所述第二意图的影响值为零。
  21. 根据权利要求19或20所述的通信装置，其特征在于：
    所述处理单元，还用于执行所述第一操作相对于未执行所述第一操作时，所述第二意图的约束条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值； 或
    所述处理单元，还用于执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的约束条件已满足情况没有改变，第二意图一直处于约束条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
  22. 根据权利要求19～21任一项所述的通信装置，其特征在于：
    所述处理单元，还用于执行所述第一操作相对于未执行所述第一操作时，所述第二意图的执行条件从已满足变成未满足，则确定所述第一操作对所述第二意图的影响值为负值；或
    所述处理单元，还用于执行所述第一操作相对于未执行所述第一操作时，对所述第二意图的执行条件已满足情况没有改变，所述第二意图一直处于执行条件已满足，则确定所述第一操作对所述第二意图的影响值为零。
  23. 根据权利要求18～22任一项所述的通信装置，其特征在于，所述处理单元，还用于根据所述第一意图目标的第一达成情况、一个或多个已存在的意图操作对应的第二知识、和所述第一意图的第一知识，在所述一个或多个已存在的意图操作中确定所述第一操作。
  24. 一种通信装置，其特征在于，所述装置包括：
    收发单元，用于从第一网元获取第一意图操作；
    处理单元，用于确定所述第一意图操作对第二意图有影响，所述第二意图与所述第一意图不同；
    所述收发单元，还用于向所述第一网元发送第一信息，所述第一信息用于指示所述第一意图操作对所述第二意图的影响，所述第一信息用于第一操作的选择，所述第一操作用于执行所述第一意图。
  25. 一种通信系统，其特征在于，包括如权利要求13～23任一项所述的通信装置以及如权利要求24所述的通信装置。
PCT/CN2021/100747 2020-06-20 2021-06-17 通信方法及装置、系统 WO2021254461A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21825574.3A EP4156735A4 (en) 2020-06-20 2021-06-17 COMMUNICATION METHOD AND APPARATUS, AND SYSTEM
US18/068,808 US20230118861A1 (en) 2020-06-20 2022-12-20 Communication method, apparatus, and system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010569778.X 2020-06-20
CN202010569778.XA CN113825128B (zh) 2020-06-20 2020-06-20 通信方法及装置、系统

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/068,808 Continuation US20230118861A1 (en) 2020-06-20 2022-12-20 Communication method, apparatus, and system

Publications (1)

Publication Number Publication Date
WO2021254461A1 true WO2021254461A1 (zh) 2021-12-23

Family

ID=78924826

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/100747 WO2021254461A1 (zh) 2020-06-20 2021-06-17 通信方法及装置、系统

Country Status (4)

Country Link
US (1) US20230118861A1 (zh)
EP (1) EP4156735A4 (zh)
CN (1) CN113825128B (zh)
WO (1) WO2021254461A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116419293A (zh) * 2021-12-29 2023-07-11 华为技术有限公司 意图冲突处理的方法及其装置
CN116419261B (zh) * 2021-12-30 2024-06-11 华为技术有限公司 意图执行方法及通信装置
CN116781516A (zh) * 2022-03-08 2023-09-19 华为技术有限公司 一种更新知识的方法和通信装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109245916A (zh) * 2018-08-15 2019-01-18 西安电子科技大学 一种意图驱动的云化接入网系统及方法
US20190179894A1 (en) * 2017-12-12 2019-06-13 International Business Machines Corporation Contextual automation of information technology change services
CN110278111A (zh) * 2019-05-29 2019-09-24 西安电子科技大学 一种意图驱动网络通用架构及其意图驱动网络转译方法
CN111277442A (zh) * 2020-01-21 2020-06-12 赣江新区智慧物联研究院有限公司 无线意图驱动网络的管理方法、装置及系统

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI590617B (zh) * 2014-09-16 2017-07-01 科勞簡尼克斯股份有限公司 以彈性地定義之通信網路控制器為基礎之網路控制、操作及管理
US20160149760A1 (en) * 2014-11-20 2016-05-26 Cisco Technology, Inc. Multi-stage convergence and intent revocation in a network environment
WO2019120543A1 (en) * 2017-12-21 2019-06-27 Telefonaktiebolaget Lm Ericsson (Publ) A method and apparatus for dynamic network configuration and optimisation using artificial life
CN110611578B (zh) * 2018-06-15 2021-08-27 华为技术有限公司 用于分配网络资源的方法及装置
CN109739961A (zh) * 2018-12-24 2019-05-10 科大讯飞股份有限公司 一种人机语言交互方法及装置
CN110166305B (zh) * 2019-06-04 2020-04-21 电子科技大学 一种基于意图的应用QoE管理方法及系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190179894A1 (en) * 2017-12-12 2019-06-13 International Business Machines Corporation Contextual automation of information technology change services
CN109245916A (zh) * 2018-08-15 2019-01-18 西安电子科技大学 一种意图驱动的云化接入网系统及方法
CN110278111A (zh) * 2019-05-29 2019-09-24 西安电子科技大学 一种意图驱动网络通用架构及其意图驱动网络转译方法
CN111277442A (zh) * 2020-01-21 2020-06-12 赣江新区智慧物联研究院有限公司 无线意图驱动网络的管理方法、装置及系统

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"3rd Generation Partnership Project; Technical Specification Group Services and System Aspects; Telecommunication management; Study on scenarios for Intent driven management services for mobile networks (Release 16)", 3GPP STANDARD; TECHNICAL REPORT; 3GPP TR 28.812, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG5, no. V0.10.0, 27 March 2020 (2020-03-27), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , pages 1 - 48, XP051861148 *
See also references of EP4156735A4

Also Published As

Publication number Publication date
EP4156735A4 (en) 2023-12-06
US20230118861A1 (en) 2023-04-20
CN113825128B (zh) 2022-12-30
CN113825128A (zh) 2021-12-21
EP4156735A1 (en) 2023-03-29

Similar Documents

Publication Publication Date Title
WO2021254461A1 (zh) 通信方法及装置、系统
US10762390B2 (en) Computer-based visualization of machine-learning models and behavior
US11455306B2 (en) Query classification and processing using neural network based machine learning
US11055407B2 (en) Distribution-based analysis of queries for anomaly detection with adaptive thresholding
US11657612B2 (en) Method and apparatus for identifying video
CN103513983A (zh) 用于预测性警报阈值确定工具的方法和系统
US11494559B2 (en) Hybrid in-domain and out-of-domain document processing for non-vocabulary tokens of electronic documents
KR101965277B1 (ko) 하이퍼그래프 데이터 분석 시스템 및 방법과, 이를 위한 컴퓨터 프로그램
KR102443872B1 (ko) 순항 제어 방법, 장치, 전자 기기, 차량, 저장 매체 및 프로그램
US20230132545A1 (en) Methods and Systems for Approximating Embeddings of Out-Of-Knowledge-Graph Entities for Link Prediction in Knowledge Graph
CN110309318B (zh) 信息通信网络的意图表征系统及方法、信息数据处理终端
CN112925857A (zh) 基于谓语类型预测关联的数字信息驱动的系统和方法
US20160364650A1 (en) Domain Specific Languages and Complex Event Handling for Mobile Health Machine Intelligence Systems
EP4179539A1 (en) Genomic information compression by configurable machine learning-based arithmetic coding
US12028217B2 (en) Communication method, apparatus, and system
US20240028621A1 (en) Systems, methods, and graphical user interfaces for taxonomy-based classification of unlabeled structured datasets
CN111061763B (zh) 用于生成规则引擎的规则执行计划的方法及装置
CN115981804A (zh) 一种工业大数据计算任务调度管理系统
Fang et al. Gaugllm: Improving graph contrastive learning for text-attributed graphs with large language models
CN117807121A (zh) 基于知识图谱的电网知识关联方法、装置、设备及介质
CN116127400B (zh) 基于异构计算的敏感数据识别系统、方法及存储介质
CN114258035A (zh) 通信方法及装置、系统
WO2018228667A1 (en) Automatic feature selection in machine learning
CN114722388A (zh) 一种数据库数据信息安全监视方法
JP7029347B2 (ja) 情報処理方法、プログラムおよび情報処理装置

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: 21825574

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021825574

Country of ref document: EP

Effective date: 20221222

NENP Non-entry into the national phase

Ref country code: DE