WO2024036954A1

WO2024036954A1 - Intent processing method, electronic device, and storage medium

Info

Publication number: WO2024036954A1
Application number: PCT/CN2023/083143
Authority: WO
Inventors: 詹勇
Original assignee: 中兴通讯股份有限公司
Priority date: 2022-08-18
Filing date: 2023-03-22
Publication date: 2024-02-22
Also published as: CN117640376A

Abstract

The present application provides an intent processing method, an electronic device, and a storage medium. The method comprises: acquiring a first intent (S110); performing policy optimization processing on the first intent on the basis of a preset digital twin network to determine optimized policy information, the digital twin network comprising intent configuration information, and the intent configuration information being used for representing a second intent (S120); performing intent conflict detection on the first intent and the second intent on the basis of the digital twin network, the intent configuration information, and the optimized policy information to determine conflict detection information (S130); determining an intent monitoring range according to the first intent, and determining intent monitoring information according to the intent monitoring range and the digital twin network (S140); and sending the optimized policy information, the conflict detection information, and the intent monitoring information (S150).

Description

Intent processing methods, electronic devices and storage media

Cross-references to related applications

This application is filed based on the Chinese patent application with application number 202210990918.

Technical field

The present application relates to, but is not limited to, the field of communication technology, and in particular, to an intent processing method, electronic device and storage medium.

Background technique

Intent-Driven Network (IDN) refers to a network with intent processing capabilities, which can automatically convert, verify, deploy, configure and optimize according to the user's intent to achieve the target network state and provide automation, high reliability and closed loop Optimized network services.

Currently, in intent-driven networks, in order to achieve intentions, the system needs to traverse various strategies to find the optimal strategy, resulting in low efficiency in intention processing. In addition, the system cannot effectively determine intention conflicts and monitor intention achievement, resulting in users being unable to effectively adjust Intention, reduce user experience.

Contents of the invention

The following is an overview of the topics described in detail in this article. This summary is not intended to limit the scope of the claims.

Embodiments of the present application provide an intent processing method, electronic device, and storage medium.

In the first aspect, embodiments of the present application provide an intention processing method, which includes: obtaining a first intention; based on a preset digital twin network, performing strategy optimization processing on the first intention to determine optimization strategy information, wherein, The digital twin network includes intention configuration information, and the intention configuration information is used to represent the second intention; based on the digital twin network, the intention configuration information and the optimization strategy information, the first intention and the The second intention performs intention conflict detection and determines the conflict detection information; determines the intention monitoring range according to the first intention, and determines the intention monitoring information according to the intention monitoring range and the digital twin network; sends the optimization strategy information, the the conflict detection information and the intent monitoring information.

In a second aspect, this application also provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the first step above is implemented. Intent handling methods described in aspects.

In a third aspect, the application also provides a computer-readable storage medium that stores a computer-executable program, and the computer-executable program is used to cause the computer to execute the intention described in the first aspect. Approach.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the application. The objectives and other advantages of the application may be realized and obtained by the structure particularly pointed out in the specification, claims and appended drawings.

Description of the drawings

The drawings are used to provide a further understanding of the technical solution of the present application and constitute a part of the specification. They are used to explain the technical solution of the present application together with the embodiments of the present application and do not constitute a limitation of the technical solution of the present application.

Figure 1 is a flow chart of an intent processing method provided by an embodiment of the present application;

Figure 2 is a flow chart of a method for obtaining a digital twin network provided by another embodiment of the present application;

Figure 3 is a flow chart of a method for determining optimization strategy information provided by another embodiment of the present application;

Figure 4 is a flow chart of a method for determining a target policy provided by another embodiment of the present application;

Figure 5 is a flow chart of a method for obtaining a utility function provided by another embodiment of the present application;

Figure 6 is a flow chart of a method for determining conflict detection information provided by another embodiment of the present application;

Figure 7 is a flow chart for determining intent monitoring information provided by another embodiment of the present application;

Figure 8 is a flow chart for determining the intended monitoring range provided by another embodiment of the present application;

Figure 9 is a structural diagram of an electronic device provided by another embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the embodiments described here are only used to explain the present application and are not used to limit the present application.

It should be noted that although the functional modules are divided in the device schematic diagram and the logical sequence is shown in the flow chart, in some cases, the modules can be divided into different modules in the device or the order in the flow chart can be executed. The steps shown or described. The terms "first", "second", etc. in the description, claims or the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

Aiming at the problem that the access network equipment cannot determine the network slice to which the message is sent according to the usage requirements of the application program, this application provides an intent processing method, an electronic device, and a storage medium. The intent processing method includes: obtaining the first intent. ; Based on the preset digital twin network, perform strategy optimization processing on the first intention and determine the optimization strategy information. The digital twin network includes intention configuration information, and the intention configuration information is used to represent the second intention; based on the digital twin network, intention Configure information and optimization strategy information, perform intention conflict detection on the first intention and the second intention, and determine the conflict detection information; determine the intention monitoring range based on the first intention, and determine the intention monitoring information based on the intention monitoring range and the digital twin network; send optimization policy information, conflict detection information, and intent monitoring information. According to the solution provided by the embodiment of this application, in order to achieve the first intention in the intention-driven network, the first intention is subjected to strategic optimization processing through the digital twin network, which can quickly determine the optimization strategy information and improve the efficiency of intention processing, and then through the digital twin network Perform intention conflict detection on the first intention and the second intention to determine the conflict detection information. In addition, determine the intention monitoring range of the first intention, and determine the intention monitoring information in combination with the digital twin network. The intention processing module of the intention-driven network can receive optimization Policy information, conflict detection information and intention monitoring information. The intention processing module effectively determines the intention conflict between the first intention and the second intention through the conflict detection information, and effectively monitors the first intention within the intention monitoring range through the intention monitoring information. Intent fulfillment, thereby improving user experience.

First, let’s analyze some terms involved in this application:

Mean Opinion Score (MOS) is an indicator for measuring the voice quality of communication systems;

Physical Resource Block (PRB) refers to the resources of 12 consecutive carriers in the frequency domain.

The embodiments of the present application will be further described below with reference to the accompanying drawings.

The intent processing method provided by the embodiment of the present application can be applied in a terminal or a server, or can be software running in the terminal or the server.

As shown in Figure 1, Figure 1 is a flow chart of an intention processing method provided by an embodiment of the present application. This intent processing method includes but is not limited to the following steps:

Step S110, obtain the first intention;

Step S120: Based on the preset digital twin network, perform strategy optimization processing on the first intention and determine the optimization strategy information, where the digital twin network includes intention configuration information, and the intention configuration information is used to represent the second intention;

Step S130: Based on the digital twin network, intention configuration information and optimization strategy information, perform intention conflict detection on the first intention and the second intention, and determine the conflict detection information;

Step S140, determine the intention monitoring range according to the first intention, and determine the intention monitoring information according to the intention monitoring range and the digital twin network;

Step S150: Send optimization strategy information, conflict detection information and intention monitoring information.

It can be understood that the intention-driven network includes an intention processing module. The digital twin network is generated by the digital twin module. The intention processing module sends the translated first intention to the digital twin module. The translated first intention is used to represent what the system needs to achieve. The goal or delivered service, as well as related constraints and conditions, then, in the digital twin network, determine the second intention through the intention configuration information, perform strategy optimization processing on the first intention, determine the optimization strategy information, and strategy optimization processing It is used to determine the strategy to maximize the probability of achieving the first intention through preset expert-defined rules or machine learning algorithms without reducing the probability of achieving all second intentions; and then determine the first intention through the digital twin network Whether there is a conflict between the intention and the second intention, the conflict detection information is obtained. When there is no conflict between the first intention and the second intention, it means that the first intention and the second intention can be achieved at the same time. When there is a conflict between the first intention and the second intention, It is equivalent to the fact that the first intention and the second intention cannot be achieved at the same time, and the second intention needs to be deleted to achieve the first intention; then the intention monitoring information is determined through the digital twin network, and then the intention achievement is effectively monitored. In addition, the user can obtain information through the intention monitoring information. Know the modification suggestions of the first intention and improve the user experience; based on this, in order to achieve the first intention in the intention-driven network, the first intention is strategically optimized through the digital twin network, which can quickly determine the optimization strategy information and improve the efficiency of intention processing. , and then perform intention conflict detection on the first intention and the second intention through the digital twin network to determine the conflict detection information. In addition, determine the intention monitoring range of the first intention, and determine the intention monitoring information combined with the digital twin network. The intention drives the network's intention. The processing module can receive optimization strategy information, conflict detection information and intention monitoring information. The intention processing module effectively determines the intention conflict between the first intention and the second intention through the conflict detection information, and effectively monitors the first intention through the intention monitoring information. Intent achievement within the intent monitoring range, thereby improving user experience.

It should be noted that the intent processing module can be set in the network management system, base station or server; the digital twin module is usually set in the server, and the digital twin module can also be set in the base station; information can be exchanged between the intent processing module and the digital twin module. Interaction can transmit information such as first intention, optimization strategy information, conflict detection information, and intention monitoring information.

It is worth noting that the first intention and the second intention can be intentions with a clear path, for example, "turn on VoLTE service for area A", or they can be intentions with an unclear path, for example, "the 5G base station in area B will The average energy consumption does not exceed 100kWh."

It should be noted that the intention configuration information can determine that the physical network corresponding to the digital twin network does not maintain an activated intention, or maintains at least one activated second intention. An activated intention refers to an active intention in the physical network. The intention of the state.

In addition, referring to Figure 2, in one embodiment, the first intention includes target network object information; before step S120 in the embodiment shown in Figure 1, the following steps are also included but are not limited to:

Step S210: Obtain multiple historical network information and intent configuration information of the physical network, where the historical network information corresponds to the target network object information, and the intent configuration information corresponds to the historical network information;

Step S220: Perform digital twin processing on the physical network based on each historical network information and intent configuration information to obtain a digital twin network.

It can be understood that the digital twin module digitally creates a virtual twin of the physical network entity, that is, generates a digital twin network, in which the operation of the physical network can be simulated; the target network object information is used to represent the driving object of the physical network , the physical network is an intent-driven network, and the historical network information corresponds to the target network object information. The historical network information refers to the software configuration information, hardware configuration information, status information, attribute information, Physical network information such as user terminal information, business information and mobile channel environment information, through multiple historical network information of the physical network, can determine the corresponding physical network information of the physical network in a certain historical time period, and then use all physical network information, Perform digital twin processing on the physical network to obtain the digital twin network, which is equivalent to reproducing the physical network; in addition, the intent configuration information is determined based on the intent maintained by the physical network at this historical time point. Therefore, the intent configuration information is consistent with the historical network Information correspondence, through the intention configuration information, it can be determined that the physical network corresponding to the digital twin network does not maintain an activated intention, or maintains at least one activated second intention, ensuring the accuracy and reliability of the digital twin network.

It should be noted that historical network information is collected from each network element of the physical network; the type and collection quantity of historical network information can be set according to actual needs and are not limited here.

In addition, referring to Figure 3, in one embodiment, step S120 in the embodiment shown in Figure 1 includes but is not limited to the following steps:

Step S310: Determine multiple update strategies based on the preset digital twin network, where the update strategies are used to update network parameters of the digital twin network;

Step S320, determine the target strategy in each update strategy based on the preset optimization algorithm, digital twin network, first intention and second intention;

Step S330: Determine optimization strategy information based on the target strategy and the first intention.

It can be understood that the digital twin network includes multiple network parameters, and the update strategy is used to update each network parameter. The adjustment range of all network parameters determines the number of update strategies. In the digital twin network, the strategy optimization process is through the optimization algorithm , determine the target strategy. The target strategy refers to the strategy that maximizes the probability of achieving the first intention without reducing the probability of achieving the second intention. Then, combined with the first intention to determine the optimization strategy information, the user can optimize The strategy information obtains the optimization information of the first intention.

In addition, referring to Figure 4, in one embodiment, step S320 in the embodiment shown in Figure 3 includes but is not limited to the following steps:

Step S410: Obtain the utility function based on the digital twin network, the first intention, the second intention and the update strategy;

Step S420: Based on the preset optimization algorithm and preset constraint conditions, the utility function is maximized to determine the target strategy in each update strategy.

It can be understood that by obtaining the utility function and using the optimization algorithm to maximize the utility function under the premise of satisfying the constraints, and then determine the target strategy, the target strategy can be quickly determined and the efficiency of intent processing can be improved.

In addition, referring to Figure 5, in one embodiment, the first intention includes a goal achievement probability, and the intention configuration information is used to represent multiple second intentions in an activated state; step S410 in the embodiment shown in Figure 4 includes but does not Limited to the following steps:

Step S510: For any second intention, based on the digital twin network, determine the first achievement probability of the second intention according to the second intention;

Step S520, update the digital twin network according to the update strategy;

Step S530: For any second intention, based on the updated digital twin network, determine the second achievement probability of the second intention according to the second intention, where the second achievement probability corresponds to the first achievement probability one-to-one;

Step S540: Based on the updated digital twin network, determine the current probability of achieving the first intention according to the first intention;

Step S550: Decrease the quotient of the current achievement probability and the target achievement probability minus one to obtain the first expression;

Step S560: For any second intention, the difference between the second achievement probability and the corresponding first achievement probability is reduced to zero to obtain a second expression;

Step S570, calculate the sum of all second expressions to obtain the third expression;

Step S580: Calculate the sum of the first expression and the third expression to obtain the utility function.

It can be understood that the establishment process of the utility function is limited, the utility function is obtained by summing the first expression and the third expression, and the third expression is obtained by summing each second expression; the first expression is used in Determine the achievement of the first intention when the first intention is activated. If the current achievement probability is greater than or equal to the target achievement probability, the value of the first expression is 1, which is equivalent to the first intention being completely achieved. If the current achievement probability is less than the target achievement Probability, the value of the first expression is less than 1, the first intention is not fully achieved; the second expression is used to determine whether the second achievement probability of the second intention meets the requirements. When the second achievement probability is greater than or equal to the first achievement probability, The value of the first expression is 0, which is equivalent to the second achievement probability of the second intention meeting the demand. When the second achievement probability is less than the first achievement probability, the value of the first expression is less than 0, which is equivalent to the second achievement probability of the second intention. The achievement probability does not meet the requirements; on the premise that the constraints are met, the optimization algorithm is used to maximize the utility function, which is equivalent to finding the target strategy from each update strategy.

It should be noted that when the first intention does not indicate a specific goal attainment probability, the goal attainment probability of the first intention is determined as 100%, and subsequently the utility function is obtained based on the goal attainment probability being 100%.

It is worth noting that the first attainment probability is equivalent to the attainment probability of the second intention before activating the first intention, and the second attainment probability is equivalent to the attainment probability of the second intention after activating the first intention. Therefore, in the utility function, It is limited that after activating the first intention, the probability of achieving the second intention will not be reduced.

In some embodiments, the utility function is formulated as follows:
min(p ₁ /p ₀ ,1)+∑ _n min(p _n -p′ _n ,0),

Among them, p ₁ refers to the current achievement probability of the first intention, p ₀ refers to the goal achievement probability, p _n refers to the second achievement probability of the n-th second intention, and p′ _n refers to the n-th second intention. The first achievement probability, n is the total number of second intentions.

In addition, in one embodiment, the optimization algorithm includes at least one of the following: a genetic algorithm, a particle swarm algorithm, or an ant colony algorithm search algorithm; the constraint condition is that the second achievement probability is greater than or equal to the corresponding first achievement probability.

It can be understood that the genetic algorithm, particle swarm algorithm and ant colony algorithm search algorithms can all search for strategies that maximize the utility function. Compared with traversing each update strategy, using the genetic algorithm, particle swarm algorithm and ant colony algorithm search algorithms can Improve efficiency and improve intent processing efficiency; maximize the utility function through optimization algorithms and constraints, achieving the goal of maximizing the value of the first expression while ensuring that the value of the second expression is not less than 0.

It should be noted that the constraint is that after activating the first intention, the probability of achieving the second intention will not decrease.

In addition, referring to Figure 6, in one embodiment, step S130 in the embodiment shown in Figure 1 includes but is not limited to the following steps:

Step S610, determine the optimization intention based on the optimization strategy information and the first intention;

Step S620: Based on the digital twin network and intent configuration information, perform intent conflict detection on the optimization intent and the second intent, and determine the conflict detection information.

It can be understood that the optimization intention is determined through the optimization strategy information and the first intention; for the first intention and the optimization intention, the target driving object, target indicator, target indicator value range and intention constraints are all the same, but the first intention and the optimization intention are the same. The probability of achieving the optimization intention can be different, and then the intention conflict detection is performed on the optimization intention and the second intention to determine the conflict detection information, that is, to determine whether there is a conflicting second intention, which is used to subsequently obtain intention modification suggestions.

It should be noted that if the priority intention conflicts with any second intention, the priority of the priority intention is lower than that of the second intention.

In addition, referring to Figure 7, in one embodiment, step S140 in the embodiment shown in Figure 1 includes but is not limited to the following steps:

Step S710, determine the intention monitoring range according to the first intention;

Step S720, determine the monitoring strategy in each update strategy based on the optimization algorithm, digital twin network and intended monitoring scope;

Step S730: Determine the intention monitoring information according to the monitoring strategy and the intention monitoring scope.

It can be understood that the intention monitoring range is determined through the first intention, and the intention monitoring range is used to characterize multiple intentions to be monitored. Then, in the digital twin network, the monitoring strategy is determined through the strategy optimization process of the optimization algorithm. The monitoring strategy refers to Without reducing the probability of achieving all second intentions, a strategy is used to maximize the probability of achieving the intention to be monitored corresponding to the intention monitoring range. Then, the intention monitoring information is determined based on the intention to be monitored, and the user can effectively monitor through the intention monitoring information. The achievement of the first intention within the scope of intention monitoring.

In addition, referring to Figure 8, in one embodiment, the first intention includes target indicator information, intention constraint information and target indicator value range information of the target indicator information; step S710 in the embodiment shown in Figure 7 includes but is not limited to There are following steps:

Step S810, determine the indicator value monitoring range based on the target indicator value range information and the preset first threshold;

Step S820, determine the achievement probability monitoring range according to the target achievement probability and the preset second threshold;

Step S830, determine the intention restriction monitoring range according to the intention restriction information and the preset third threshold;

Step S840: Determine the intention monitoring range according to the indicator value monitoring range, the achievement probability monitoring range and the intention constraint monitoring range.

It can be understood that the intention monitoring range is determined by the first intention, and the intention monitoring range can be determined by the indicator value monitoring range, the achievement probability monitoring range and the intention constraint monitoring range; the indicator value monitoring range is determined by the target indicator value range information and the third intention monitoring range. Determined by a threshold, the first threshold can be the change rate of the target indicator value range information. For example, the value corresponding to the target indicator value range information is 4, and the first threshold is reduced by 25%. The calculated indicator value monitoring range The monitoring value is 3; the achievement probability monitoring range is determined by the target achievement probability and the second threshold. The second threshold can be the change rate of the target achievement probability. For example, the target achievement probability is 100%, and the second threshold is reduced by 5%. Calculate The monitoring probability of obtaining the achievement probability monitoring range is 95%; the intention constraint monitoring range is determined by the intention constraint information and the third threshold. The third threshold can be the change rate of the constraint index value range in the intention constraint information, for example, the intention constraint information The value of the value range of the medium constraint index is 100%, and the second threshold is reduced by 20%. The calculated monitoring value of the constraint index value range in the intention constraint monitoring range is 80%.

In some embodiments, the intent processing process is as follows: obtain the translated first intent; then, obtain the historical network information corresponding to the driving object within a certain time period, and then generate a digital twin network; then, in the digital twin network, Perform strategic optimization on the first intention, generate a utility function, and maximize the utility function, which is equivalent to defining an optimization problem: the objective function is to maximize the current probability of achieving the first intention, and the constraint condition is after activating the first intention. , the probability of achieving the second intention will not be reduced. The variables that need to be solved for the optimization problem are the values of the network parameters in the digital twin network. The optimization problem is a mixed integer non-linear programming (Mixed Integer Non-Linear Programming, MINLP) problem. Digital The twin module obtains the target strategy by solving the MINLP problem, and then determines the optimization strategy information. Then, it determines the optimization intention through the optimization strategy information; then, it performs intention conflict detection on the optimization intention and the second intention to determine the conflict detection information; then, through Determine the intent monitoring scope, then determine the intent monitoring information, and obtain modification suggestions for the first intent through the intent monitoring information;

For example, the translated first intention can determine the following: the driving object is "all 5G base stations in the first area", the intention requirement is "100% probability of the MOS value of VR video being greater than or equal to 4", and the intention constraint is "start immediately" ; In the intent requirement, the target indicator is "MOS value of VR video", the target indicator value range is "4", and the target achievement probability is "100%"; then, obtain all 5G base stations in the first area within the last month Base station portrait information and user portrait information, and evenly sampled 10,000 classic moments according to time for digital twin processing to obtain a digital twin network; through strategic optimization processing, it was determined that the optimization intention was "Start immediately, for all 5G base stations in the first area ", the probability that the MOS value of VR video is greater than or equal to 4 is 82%"; and, through intention conflict detection, it is determined that the optimization intention and the second intention do not conflict; finally, the modification suggestions that users can get through the intention monitoring information are: 1. For all 5G base stations in the first area, when the uplink and downlink PRB utilization rates in the first area are both less than 50%, there is a 99% probability that the MOS value of the VR video is greater than or equal to 4; 2. For all 5G base stations in the first area, when the When the uplink and downlink PRB utilization in a region are both less than 80%, the 95% probability of the MOS value of the VR video is greater than or equal to 3.5; 3. For all 5G base stations in the first region, the uplink or downlink PRB utilization in the first region is greater than At 80%, the 95% probability of the MOS value of the VR video is greater than or equal to 3;

For example, the translated first intention can determine the following content: the driving object is "all 4G base stations and 5G base stations in the second area", and the intention requirement is "the average daily energy consumption of all 4G base stations and 5G base stations in the second area does not exceed 100kWh, The intention constraint is to start immediately, and the average uplink and downlink PRB utilization in the second area is less than 30%"; in the intention requirement, the target indicator is "the average daily energy consumption of all 4G base stations and 5G base stations in the second area", the target indicator The value range is "100kWh", and the target achievement probability is "100%"; then, obtain the base station portrait information and user portrait information of all 5G networks in the second area in the past week, and uniformly sample 604800 at 1s intervals Perform digital twin processing at a classic moment to obtain a digital twin network; through strategic optimization processing, it is determined that the optimization intention is "Start immediately. For all 4G base stations and 5G base stations in the second area, the average uplink and downlink PRB utilization of the second area is less than At 30%, there is a 98% probability that the daily average energy consumption of all 4G base stations and 5G base stations in the second area does not exceed 100kWh"; and, through intention conflict detection, it is determined that the optimization intention conflicts with one of the second intentions, and the second intention is regarded as Conflict intention, the information that users can get through the conflict detection information is: the conflict intention is "when the average uplink and downlink PRB utilization in the second area is less than 50%, 99% probability of the downlink user rate is not less than 100kbps", the optimization intention The priority is lower than the conflicting intention. If there is no need to force the conflicting intention to be satisfied, the priority intention can be achieved.

It can be understood that the base station portrait information and user portrait information are used to indicate software configuration information, hardware configuration information, status information, attribute information, user terminal information, service information and mobile channel environment information.

In addition, referring to FIG. 9 , an embodiment of the present application also provides an electronic device.

In some embodiments, the electronic device includes: one or more processors and memories. Figure 9 takes one processor and memory as an example. The processor and the memory can be connected through a bus or other means. Figure 9 takes the connection through a bus as an example.

As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer executable programs, such as the intended processing method in the above embodiments of the present application. The processor implements the above intention processing method in the embodiment of the present application by running non-transient software programs and programs stored in the memory.

The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system and an application program required for at least one function; the storage data area may store data required to execute the intention processing method in the embodiments of the present application. wait. In addition, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may include memory located remotely from the processor, and these remote memories may be connected to the electronic device through a network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.

The non-transitory software programs and programs required to implement the above-mentioned intent processing methods in the embodiments of the present application are stored in the memory. When executed by one or more processors, the above-mentioned intent processing methods in the embodiments of the present application are executed, for example, Execute the above-described method steps S110 to S150 in Figure 1, method steps S210 to S220 in Figure 2, method steps S310 to S330 in Figure 3, method steps S410 to S420 in Figure 4, Figure 5 The method steps S510 to S580 in FIG. 6 , the method steps S610 to S620 in FIG. 6 , the method steps S710 to S730 in FIG. 7 , the method steps S810 to S840 in FIG. 8 , by obtaining the first intention; based on the preset The digital twin network is designed to perform strategy optimization processing on the first intention and determine the optimization strategy information. The digital twin network includes intention configuration information, and the intention configuration information is used to represent the second intention; based on the digital twin network, intention configuration information and Optimize the strategy information, perform intention conflict detection on the first intention and the second intention, and determine the conflict detection information; determine the intention monitoring range based on the first intention, and determine the intention monitoring information based on the intention monitoring range and the digital twin network; send the optimization strategy information, Conflict detection information and intent monitoring information. Based on this, in order to achieve the first intention in the intention-driven network, strategic optimization processing of the first intention is performed through the digital twin network, which can quickly determine the optimization strategy information and improve the efficiency of intention processing. Then, the first intention and the third intention are processed through the digital twin network. The second intention performs intention conflict detection and determines the conflict detection information. In addition, the intention monitoring range of the first intention is determined, and the intention monitoring information is determined in conjunction with the digital twin network. The intention processing module of the intention-driven network can receive optimization strategy information and conflict detection information. and intention monitoring information. The intention processing module effectively determines the intention conflict between the first intention and the second intention through the conflict detection information, and effectively monitors the achievement of the first intention within the intention monitoring range through the intention monitoring information, thereby improving user experience.

In addition, one embodiment of the present application also provides a computer-readable storage medium that stores computer-executable instructions, and the computer-executable instructions are executed by a processor or controller, for example, by the above-mentioned Execution of a processor in the electronic device embodiment can cause the above-mentioned processor to perform the intended processing method in the above-described embodiment, for example, perform the above-described method steps S110 to S150 in Figure 1 and method steps S210 to S210 in Figure 2 Step S220, method steps S310 to step S330 in Figure 3, method steps S410 to step S420 in Figure 4, method steps S510 to step S580 in Figure 5, method steps S610 to step S620 in Figure 6, method steps S610 to step S620 in Figure 7 The method steps S710 to S730 and the method steps S810 to S840 in Figure 8 obtain the first intention; based on the preset digital twin network, perform strategy optimization processing on the first intention to determine the optimization strategy information, where, The digital twin network includes intent configuration information, and the intent configuration information is used to represent the second intent; based on the digital twin network, intent configuration information, and optimization strategy information, intent conflict detection is performed on the first intent and the second intent, and the conflict detection information is determined; according to First intention determines intention Map monitoring range, and determine intent monitoring information based on the intent monitoring range and digital twin network; send optimization strategy information, conflict detection information, and intent monitoring information. Based on this, in order to achieve the first intention in the intention-driven network, strategic optimization processing of the first intention is performed through the digital twin network, which can quickly determine the optimization strategy information and improve the efficiency of intention processing. Then, the first intention and the third intention are processed through the digital twin network. The second intention performs intention conflict detection and determines the conflict detection information. In addition, determines the intention monitoring range of the first intention and determines the intention monitoring information in combination with the digital twin network. The intention processing module of the intention-driven network can receive optimization strategy information and conflict detection information. and intention monitoring information. The intention processing module effectively determines the intention conflict between the first intention and the second intention through the conflict detection information, and effectively monitors the achievement of the first intention within the intention monitoring range through the intention monitoring information, thereby improving user experience.

Embodiments of the present application include: obtaining the first intention; based on a preset digital twin network, performing strategy optimization processing on the first intention to determine optimization strategy information, wherein the digital twin network includes intention configuration information, and the Intent configuration information is used to represent the second intention; based on the digital twin network, the intention configuration information and the optimization strategy information, perform intention conflict detection on the first intention and the second intention, and determine the conflict detection information ; Determine the intention monitoring range according to the first intention, and determine the intention monitoring information according to the intention monitoring range and the digital twin network; send the optimization strategy information, the conflict detection information and the intention monitoring information. According to the solution provided by the embodiments of this application, in order to achieve the first intention, the first intention is processed through strategic optimization through the digital twin network, which can quickly determine the optimization strategy information, improve the efficiency of intention processing, and optimize the first intention through the digital twin network. Conducting intention conflict detection with the second intention and determining the conflict detection information can effectively determine the intention conflict between the first intention and the second intention. In addition, the intention monitoring range of the first intention is determined, and the intention monitoring is determined in conjunction with the digital twin network. Information can effectively monitor the achievement of intentions and improve user experience.

Those of ordinary skill in the art can understand that all or some steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit . Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As is known to those of ordinary skill in the art, the term computer storage media includes volatile and nonvolatile media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. removable, removable and non-removable media. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disk (DVD) or other optical disk storage, magnetic cassettes, tapes, disk storage or other magnetic storage devices, or may Any other medium used to store the desired information and that can be accessed by a computer. Additionally, it is known to those of ordinary skill in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

The above describes some implementations of the present application, but the present application is not limited to the above-mentioned embodiments. Those skilled in the art can also make various equivalent modifications or substitutions without departing from the scope of the present application. These equivalents All modifications and substitutions are within the scope defined by the claims of this application.

Claims

An intent handling method that includes:

Get the first intention;

Based on the preset digital twin network, perform strategy optimization processing on the first intention and determine optimization strategy information, wherein the digital twin network includes intention configuration information, and the intention configuration information is used to represent the second intention;

Based on the digital twin network, the intention configuration information and the optimization strategy information, perform intention conflict detection on the first intention and the second intention, and determine the conflict detection information;

Determine the intention monitoring range according to the first intention, and determine the intention monitoring information according to the intention monitoring range and the digital twin network;

The optimization strategy information, the conflict detection information and the intention monitoring information are sent.
The method according to claim 1, wherein the first intention includes target network object information; before performing strategy optimization processing on the first intention based on a preset digital twin network and determining the optimization strategy information, Also includes:

Obtain a plurality of historical network information of the physical network and the intention configuration information, wherein the historical network information corresponds to the target network object information, and the intention configuration information corresponds to the historical network information;

According to each of the historical network information and the intended configuration information, digital twin processing is performed on the physical network to obtain a digital twin network.
The method according to claim 1, wherein said performing strategy optimization processing on said first intention based on a preset digital twin network and determining optimization strategy information includes:

Determine multiple update strategies according to the preset digital twin network, wherein the update strategies are used to update network parameters of the digital twin network;

Determine a target strategy in each of the update strategies according to the preset optimization algorithm, the digital twin network, the first intention and the second intention;

Optimization strategy information is determined according to the target strategy and the first intention.
The method according to claim 3, wherein the target strategy is determined in each of the update strategies according to the preset optimization algorithm, the digital twin network, the first intention and the second intention, including :

Obtain a utility function according to the digital twin network, the first intention, the second intention and the update strategy;

Based on the preset optimization algorithm and preset constraint conditions, the utility function is maximized to determine the target strategy in each of the update strategies.
The method according to claim 4, wherein the first intention includes a goal achievement probability, and the intention configuration information is used to characterize a plurality of the second intentions in an activated state; according to the digital twin network, The utility function obtained from the first intention, the second intention and the update strategy includes:

For any of the second intentions, based on the digital twin network, determine a first probability of achieving the second intention according to the second intention;

Update the digital twin network according to the update strategy;

For any second intention, based on the updated digital twin network, determine a second achievement probability of the second intention according to the second intention, wherein the second achievement probability is the same as the first achievement probability. Achieve one-to-one correspondence between probabilities;

Based on the updated digital twin network, determine the current probability of achieving the first intention according to the first intention;

The quotient of the current achievement probability and the target achievement probability is reduced to one to obtain a first expression;

For any of the second intentions, the difference between the second achievement probability and the corresponding first achievement probability is reduced to zero to obtain a second expression;

Calculate the sum of all said second expressions to obtain a third expression;

The sum of the first expression and the third expression is calculated to obtain a utility function.
The method according to claim 5, wherein the optimization algorithm includes at least one of the following: a genetic algorithm, a particle swarm algorithm, or an ant colony algorithm search algorithm; the constraint condition is that the second reaching probability is greater than or equal to the corresponding The first achievement probability of .
The method according to claim 1, wherein based on the digital twin network, the intention configuration information and the optimization strategy information, intention conflict detection is performed on the first intention and the second intention, and it is determined that Conflict detection information, including:

Determine the optimization intention according to the optimization strategy information and the first intention;

Based on the digital twin network and the intent configuration information, intent conflict detection is performed on the optimization intent and the second intent, and conflict detection information is determined.
The method according to claim 3, wherein determining the intention monitoring range according to the first intention and determining the intention monitoring information according to the intention monitoring range and the digital twin network includes:

Determine the intention monitoring range according to the first intention;

Determine a monitoring strategy in each of the update strategies according to the optimization algorithm, the digital twin network and the intended monitoring scope;

Intent monitoring information is determined according to the monitoring strategy and the intention monitoring range.
The method according to claim 8, wherein the first intention includes target indicator information, intention constraint information and target indicator value range information of the target indicator information; the intention monitoring range is determined according to the first intention ,include:

Determine the indicator value monitoring range according to the target indicator value range information and the preset first threshold;

Determine the achievement probability monitoring range according to the target achievement probability and the preset second threshold;

Determine the intention restriction monitoring range according to the intention restriction information and the preset third threshold;

The intention monitoring range is determined according to the indicator value monitoring range, the achievement probability monitoring range and the intention constraint monitoring range.
An electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements as described in any one of claims 1 to 9 Intention processing method.
A computer-readable storage medium stores a computer-executable program, and the computer-executable program is used to cause a computer to execute the intention processing method according to any one of claims 1 to 9.