Network service quality optimization method and device, electronic equipment and storage medium

Abstract

The invention provides a network service quality optimization method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a network state in response to the condition that an execution result of a previous optimization strategy does not meet a network quality demand of a user, carrying out the analysis of the network state to obtain an influence factor of the network service quality, and carrying out the optimization of the network service quality. The target optimization strategy is regenerated according to the influence factors of the network service quality, the execution result of the target optimization strategy is monitored in the execution process of the target optimization strategy, and the target optimization strategy continues to be dynamically adjusted under the condition that it is determined that the execution result of the target optimization strategy does not meet the network quality requirement of a user. According to the invention, a dynamic adjustment mechanism for optimizing the QoS guarantee strategy is realized, and long-term effective QoS guarantee is also realized.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a network service quality optimization method and device, electronic equipment and storage medium. BACKGROUND

[0002] With the acceleration of global digital transformation, in the face of complex network environment, network service quality (Quality of Service, QoS) integrates network state perception, service demand analysis, intelligent policy generation and cross-domain collaborative execution, and builds an end-to-end regulation system, and realizes the transition from the traditional network best effort extensive service mode to the intelligent network precise adaptation fine service mode.

[0003] In the related art, the service quality optimization process is as follows: the business operation support system (Business Operation Support System, BOSS) notifies the policy control function (Policy Control Function, PCF) to configure the user guarantee package, and the user triggers the PCF to execute the decision landing through the network data analysis function (Network Data Analytics Function, NWDAF), session management function (Session Management Function, SMF) and user plane function (User Plane Function, UPF), wherein the NWDAF generates a guarantee policy in combination with congestion and guaranteed bit rate (Guaranteed Bit Rate, GBR) resources, and the NWDAF feeds back data to the BOSS.

[0004] However, the guarantee policy generated by the NWDAF in the related art is terminated after only one adjustment during the network service quality guarantee period, and even if the QoS guarantee policy effect is unstable or does not meet the expectation, the optimization process of the QoS guarantee policy will not be started again within the network service quality guarantee period. SUMMARY

[0005] The present disclosure provides a network service quality optimization method and device, electronic equipment and storage medium to solve the problems in the related art. When it is determined that the execution result of the last optimization policy does not meet the network quality demand of the user, the influence factors of network QoS are judged based on the network state, and the optimization policy is dynamically adjusted based on the influence factors until the execution result of the adjusted optimization policy meets the network quality demand of the user, thereby realizing the dynamic adjustment mechanism of the optimization QoS guarantee policy and realizing the long-term effective QoS guarantee.

[0006] According to a first aspect of the embodiments of the present disclosure, a network service quality optimization method is provided, comprising:

[0007] In response to the execution result of the previous optimization strategy not meeting the network quality requirement of the user, a network state is acquired, and an influencing factor of network service quality is analyzed according to the network state;

[0008] According to the influencing factor of network service quality, a target optimization strategy is regenerated, wherein the target optimization strategy contains at least one optimization resource for optimizing the influencing factor;

[0009] During execution of the target optimization strategy, the execution result of the target optimization strategy is monitored;

[0010] In a case where it is determined that the execution result of the target optimization strategy does not meet the network quality requirement of the user, the target optimization strategy is continuously dynamically adjusted until the execution result of the adjusted optimization strategy meets the network quality requirement of the user.

[0011] In some embodiments of the present disclosure, the analysis of the influencing factor of network service quality according to the network state comprises:

[0012] Based on the user identification information, a corresponding service portrait is acquired, and the service portrait at least includes service use habits and service preference settings;

[0013] The service portrait and the network state are subjected to correlation analysis processing by a pre-trained analysis model to obtain at least one influencing factor of network service quality;

[0014] It is determined whether the at least one influencing factor of network service quality meets a respective preset service quality threshold;

[0015] In a case where it is determined that there is one or more influencing factors that do not meet the respective preset service quality threshold, it is determined that the guarantee index is not met;

[0016] In a case where it is determined that the at least one influencing factor of network service quality meets the respective preset service quality threshold, it is determined that the guarantee index is met.

[0017] In some embodiments of the present disclosure, the correlation analysis processing of the service portrait, the network state and the feedback information by the pre-trained analysis model to obtain the influencing factor of network service quality comprises:

[0018] Feedback information of the user on the execution result of the previous optimization strategy is acquired;

[0019] The service portrait, the network state and the feedback information are subjected to correlation analysis processing by a pre-trained analysis model to obtain the influencing factor of network service quality.

[0020] In some embodiments of the present disclosure, the step of regenerating the target optimization strategy according to the influencing factor of the network service quality comprises:

[0021] In the case where it is determined that the guarantee index is not met, determining at least one optimization resource related to the influencing factor of the network service quality;

[0022] Adjusting the at least one optimization resource to obtain the target optimization strategy.

[0023] In some embodiments of the present disclosure, the step of regenerating the target optimization strategy according to the influencing factor of the network service quality comprises:

[0024] In the case where it is determined that the guarantee index is met and the network quality requirement of the user contains a continuous optimization indication, determining at least one optimization resource related to the influencing factor of the network service quality;

[0025] Adjusting the at least one optimization resource to obtain the target optimization strategy.

[0026] In some embodiments of the present disclosure, the method further comprises:

[0027] In the case where it is determined that the guarantee index is met and the network quality requirement of the user does not contain a continuous optimization indication, exiting the optimization of the network service quality.

[0028] In some embodiments of the present disclosure, after the step of regenerating the target optimization strategy according to the influencing factor of the network service quality, the method further comprises:

[0029] Monitoring whether there is a change in network performance and network quality requirement of the user;

[0030] In the case where it is determined that there is a change in the network performance and / or the network quality requirement of the user, dynamically adjusting the target optimization strategy to obtain an adjusted optimization strategy.

[0031] In some embodiments of the present disclosure, the execution of the target optimization strategy comprises:

[0032] Sending, by a network data analysis module, the target optimization strategy to a policy control module;

[0033] Sending, by the policy control module, the target optimization strategy to a session management module, a user plane module and a radio access network module in a preset sending order;

[0034] Adjusting, by the session management module, parameters of a user session according to the target optimization strategy;

[0035] adjusting, by the user plane module, priority and rate of data transmission according to the target optimization strategy;

[0036] optimizing, by the radio access network module, network coverage and performance according to the target optimization strategy.

[0037] In some embodiments of the present disclosure, the monitoring of the execution result of the target optimization strategy comprises:

[0038] monitoring the network state in real time;

[0039] monitoring in real time whether feedback information of the user on the execution result of the target optimization strategy is received.

[0040] In some embodiments of the present disclosure, the method further comprises:

[0041] in response to the received network quality guarantee instruction, parsing the network quality guarantee instruction to obtain an instruction parsing result;

[0042] performing intent recognition on the instruction parsing result to determine the network quality demand, wherein the network quality demand at least comprises user identification information, guaranteed service type, guarantee requirement and continuous optimization indication.

[0043] In some embodiments of the present disclosure, the intent recognition on the instruction parsing result to determine the network quality demand comprises:

[0044] the pre-trained analysis model performs task planning on the network quality demand to obtain a data collection task, a data analysis task, a strategy generation task, a strategy execution and monitoring task.

[0045] According to a second aspect of the present disclosure, an apparatus for optimizing network service quality is provided, comprising:

[0046] an obtaining unit configured to, in response to an execution result of a previous optimization strategy not meeting network quality demand of a user, obtain a network state;

[0047] an analysis unit configured to analyze the network state to obtain an influencing factor of network service quality;

[0048] a generation unit configured to, according to the influencing factor of network service quality, regenerate a target optimization strategy, wherein the target optimization strategy contains at least one optimization resource for optimizing the influencing factor;

[0049] a first monitoring unit configured to, in an execution process of the target optimization strategy, monitor an execution result of the target optimization strategy;

[0050] The first adjustment unit is used to continuously adjust the target optimization strategy dynamically when it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

[0051] In some embodiments of this disclosure, the analysis unit includes:

[0052] The acquisition module is used to acquire the corresponding business profile based on user identification information. The business profile includes at least business usage habits and business preference settings.

[0053] The analysis module is used to perform correlation analysis on the business profile and the network status using a pre-trained analysis model to obtain at least one factor affecting network service quality.

[0054] The judgment module is used to determine whether the at least one network service quality influencing factor meets its respective preset service quality threshold.

[0055] The first determining module is used to determine that the guarantee index is not met when it is determined that there are one or more influencing factors that do not meet their respective preset service quality thresholds.

[0056] The second determining module is used to determine whether the guarantee index is met when all the influencing factors of the at least one network service quality meet their respective preset service quality thresholds.

[0057] In some embodiments of this disclosure, the analysis module includes:

[0058] The acquisition submodule is used to acquire user feedback information on the execution result of the previous optimization strategy;

[0059] The analysis submodule is used to perform correlation analysis on the business profile, the network status, and the feedback information using a pre-trained analysis model to obtain the influencing factors of the network service quality.

[0060] In some embodiments of this disclosure, the generation unit includes:

[0061] The third determining module is used to determine at least one optimized resource related to the influencing factors of the network service quality when it is determined that the guarantee indicators are not met.

[0062] The first adjustment module is used to adjust the at least one optimization resource to obtain the target optimization strategy.

[0063] In some embodiments of this disclosure, the generation unit further includes:

[0064] The fourth determining module is used to determine at least one optimization resource related to the influencing factors of the network service quality when it is determined that the guarantee index is met and the user's network quality requirements include a continuous optimization instruction.

[0065] The second adjustment module is used to adjust the at least one optimization resource to obtain the target optimization strategy.

[0066] In some embodiments of this disclosure, the apparatus further includes:

[0067] The exit unit is used to exit the optimization of network service quality when it is determined that the guarantee indicators are met and the user's network quality requirements do not include a continuous optimization instruction.

[0068] In some embodiments of this disclosure, the apparatus further includes:

[0069] The second monitoring unit is used to monitor whether there are any changes in network performance and user network quality requirements after the generation unit regenerates the target optimization strategy based on the factors affecting network service quality.

[0070] The second adjustment unit is used to dynamically adjust the target optimization strategy when it is determined that there are changes in the network performance and / or the user's network quality requirements, so as to obtain the adjusted optimization strategy.

[0071] In some embodiments of this disclosure, the first monitoring unit includes:

[0072] The first sending module is used to send the target optimization strategy from the network data analysis module to the strategy control module;

[0073] The second sending module is used by the policy control module to send the target optimization policy to the session management module, user plane module and wireless access network module in a preset sending order;

[0074] The third adjustment module is used by the session management module to adjust the parameters of the user session according to the target optimization strategy.

[0075] The fourth adjustment module is used by the user plane module to adjust the priority and rate of data transmission according to the target optimization strategy;

[0076] An optimization module is used by the wireless access network module to optimize network coverage and performance according to the target optimization strategy.

[0077] In some embodiments of this disclosure, the first monitoring unit further includes:

[0078] The first monitoring module is used to monitor the network status in real time;

[0079] The second monitoring module is used to monitor in real time whether feedback information from the user regarding the execution result of the target optimization strategy is received.

[0080] In some embodiments of this disclosure, the apparatus further includes:

[0081] The parsing unit is used to parse the received network quality assurance command in response to the command and obtain the command parsing result.

[0082] The identification unit is used to identify the intent of the instruction parsing result and determine the network quality requirements, wherein the network quality requirements include at least: user identification information, guaranteed service type, guarantee requirements and continuous optimization instructions.

[0083] In some embodiments of this disclosure, the identification unit is further configured to perform task planning on the network quality requirements using a pre-trained analysis model, thereby obtaining data acquisition tasks, data analysis tasks, policy generation tasks, policy execution and monitoring tasks.

[0084] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0085] At least one processor; and

[0086] A memory communicatively connected to the at least one processor; wherein,

[0087] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect embodiment.

[0088] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect of the present disclosure.

[0089] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in the first aspect of the preceding embodiments.

[0090] In summary, according to the network service quality optimization method, apparatus, electronic device, and storage medium provided in this disclosure, the method includes, in response to the fact that the execution result of the previous optimization strategy does not meet the user's network quality requirements, obtaining the network status, analyzing the influencing factors of network service quality based on the network status, regenerating the target optimization strategy based on the influencing factors of network service quality, wherein the target optimization strategy includes at least one optimization resource related to the influencing factors, monitoring the execution result of the target optimization strategy during the execution of the target optimization strategy, and, if it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, continuing to dynamically adjust the target optimization strategy until the execution result of the adjusted optimization strategy meets the user's network quality requirements. The disclosed solution, in response to the failure of the previous optimization strategy to meet the user's network quality requirements, obtains the network status and analyzes the factors influencing network service quality based on the network status. Based on these factors, a new target optimization strategy is generated, which includes at least one optimization resource related to the influencing factors. During the execution of the target optimization strategy, the execution result is monitored. If it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, the target optimization strategy is dynamically adjusted until the execution result of the adjusted optimization strategy meets the user's network quality requirements. Similarly, if it is determined that the execution result of the previous optimization strategy does not meet the user's network quality requirements, the factors influencing network QoS are determined based on the network status, and the optimization strategy is dynamically adjusted based on these factors until the execution result of the adjusted optimization strategy meets the user's network quality requirements. This achieves a dynamic adjustment mechanism for optimizing QoS guarantee strategies and provides long-term effective QoS guarantee.

[0091] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0092] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0093] Figure 1 A flowchart illustrating a method for optimizing network service quality provided in an embodiment of this disclosure;

[0094] Figure 2 A schematic diagram illustrating an optimization of network service quality provided in an embodiment of this disclosure;

[0095] Figure 3 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0096] Figure 4 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0097] Figure 5 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0098] Figure 6 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0099] Figure 7 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0100] Figure 8 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0101] Figure 9 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0102] Figure 10 A flowchart illustrating another method for optimizing network service quality provided in this embodiment of the disclosure;

[0103] Figure 11 A flowchart illustrating a real-time monitoring, evaluation, and feedback process provided in this embodiment of the disclosure;

[0104] Figure 12 A schematic diagram of the structure of a network service quality optimization device provided in an embodiment of this disclosure;

[0105] Figure 13 A schematic diagram of another network service quality optimization device provided in an embodiment of this disclosure;

[0106] Figure 14 A schematic block diagram of an example electronic device 1400 provided for embodiments of this disclosure. Detailed Implementation

[0107] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0108] With the acceleration of global digital transformation and the complex network environment, Quality of Service (QoS) integrates functions such as network status awareness, business demand analysis, intelligent policy generation, and cross-domain collaborative execution to build an end-to-end control system. This enables a shift from the traditional best-effort, extensive service model to a refined service model that is precisely adapted to intelligent networks.

[0109] In related technologies, the service quality optimization process is as follows: The Business Operation Support System (BOSS) notifies the Policy Control Function (PCF) to configure user protection packages. After a user triggers the PCF, the Network Data Analytics Function (NWDAF), Session Management Function (SMF), and User Plane Function (UPF) execute the decision and implement it. Among them, NWDAF combines congestion and Guaranteed Bit Rate (GBR) resources to generate protection policies, and NWDAF feeds back data to BOSS.

[0110] However, in related technologies, the guarantee policy generated by NWDAF is only adjusted once during the network service quality guarantee period and then terminated. Even if the effect of the QoS guarantee policy is unstable or does not meet expectations, the optimization process of the QoS guarantee policy will not be restarted again during a network service quality guarantee period.

[0111] Therefore, in order to solve the problems existing in the related technologies, this disclosure proposes a method for optimizing network service quality. The method includes: in response to the fact that the execution result of the previous optimization strategy does not meet the user's network quality requirements, obtaining the network status, analyzing the influencing factors of network service quality based on the network status, regenerating the target optimization strategy based on the influencing factors of network service quality, wherein the target optimization strategy includes at least one optimization resource for optimizing the influencing factors, monitoring the execution result of the target optimization strategy during the execution process, and, if it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, continuing to dynamically adjust the target optimization strategy until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

[0112] The disclosed solution, in response to the failure of the previous optimization strategy to meet the user's network quality requirements, obtains the network status and analyzes the factors influencing network service quality based on the network status. Based on these factors, a new target optimization strategy is generated, which includes at least one optimization resource related to the influencing factors. During the execution of the target optimization strategy, the execution result is monitored. If it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, the target optimization strategy is dynamically adjusted until the execution result of the adjusted optimization strategy meets the user's network quality requirements. Similarly, if it is determined that the execution result of the previous optimization strategy does not meet the user's network quality requirements, the factors influencing network QoS are determined based on the network status, and the optimization strategy is dynamically adjusted based on these factors until the execution result of the adjusted optimization strategy meets the user's network quality requirements. This achieves a dynamic adjustment mechanism for optimizing QoS guarantee strategies and provides long-term effective QoS guarantee.

[0113] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0114] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0115] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0116] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0117] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0118] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0119] The prefixes such as "first" and "second" in the embodiments of this disclosure are only for distinguishing different descriptive objects and do not constitute restrictions on the position, order, priority, number or content of the descriptive objects. For the description of the descriptive objects, please refer to the description in the claims or the context of the embodiments. The use of prefixes should not constitute unnecessary restrictions.

[0120] In the embodiments disclosed herein, "multiple" refers to two or more.

[0121] In the embodiments disclosed herein, terms such as “import”, “input”, and “read in” can be used interchangeably.

[0122] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0123] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0124] Figure 1 A flowchart illustrating a method for optimizing network service quality provided in this embodiment of the disclosure is shown below. Figure 1 As shown, the method for optimizing network service quality includes steps 101-104.

[0125] Step 101: In response to the fact that the execution result of the previous optimization strategy does not meet the user's network quality requirements, obtain the network status, and analyze the factors affecting network service quality based on the network status.

[0126] In this embodiment of the disclosure, when the execution result of the previous optimization strategy does not meet the user's network quality requirements, NWDAF will call the SMF's application programming interface (API) to subscribe to and obtain the poor quality data reported by UPF. The poor quality data reflects the user's network experience during the use of services. At the same time, NWDAF will also obtain wireless cell data through the wireless workbench. The wireless cell data includes, but is not limited to, base station status, signal strength, interference level, etc.

[0127] The NWDAF performs preliminary cleaning and formatting of the collected poor-quality data and wireless cell data using any of the relevant technologies or algorithms. The resulting structured, high-quality raw dataset is then stored in the AIAgent's memory component, the Analytic Data Repository Function (ADRF). The ADRF can be any data repository function in the 5G Core Network (5GC).

[0128] When the results of the previous optimization strategy do not meet the user's expected network quality requirements, NWDAF can not only accurately locate the root cause of QoS anomalies and shorten the fault tracing time by acquiring network status and analyzing factors affecting QoS network service quality, but also dynamically capture the network environment.

[0129] It should be noted that the previous optimization strategy can be the initial optimization strategy or any optimization strategy after adjusting the initial optimization strategy. Specifically, the timing of the generation of the previous optimization strategy is not limited in the embodiments of this disclosure.

[0130] Step 102: Based on the factors affecting network service quality, regenerate the target optimization strategy, wherein the target optimization strategy includes at least one optimization resource related to the factors affecting the network service quality.

[0131] In this embodiment of the disclosure, based on the factors affecting QoS network service quality, NWDAF uses AI algorithms (including but not limited to reinforcement learning, deep learning, etc.) based on AI Agent to regenerate the QoS target optimization strategy for users. The target optimization strategy includes at least one optimization resource for optimizing the factors affecting QoS. The optimization resource includes but is not limited to adjusting the GBR value, optimizing the allocation of wireless resources, improving network coverage, etc.

[0132] As one implementation approach, a target optimization strategy is regenerated based on the factors influencing QoS network service quality.

[0133] As another implementation method, the previous optimization strategy is dynamically adjusted based on the factors affecting QoS network service quality to obtain the target optimization strategy.

[0134] Alternatively, the target optimization strategy can be obtained through any of the related technologies.

[0135] By regenerating target optimization strategies through QoS network service quality influencing factors, a network control closed loop with targeted optimization capabilities is constructed. Based on the user's network quality requirements, at least one optimization resource related to the influencing factors can be dynamically adjusted.

[0136] Step 103: During the execution of the target optimization strategy, the execution result of the target optimization strategy is monitored.

[0137] In the implementation of the target optimization strategy in this embodiment, the NWDAF notifies the PCF of the regenerated QoS guarantee strategy, which is then distributed by the PCF to the SMF, UPF, and Radio Access Network (RAN).

[0138] NWDAF monitors network status and user experience in real time to evaluate the effectiveness of QoS guarantees.

[0139] By breaking through the static limitations of traditional network optimization through data-driven real-time feedback, QoS assurance is transformed from passive response to proactive predictive optimization, ultimately achieving a dual improvement in network resource efficiency and user experience.

[0140] Step 104: If it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, the target optimization strategy is dynamically adjusted until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

[0141] In this embodiment of the disclosure, when it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, the AI ​​Agent continuously makes dynamic adjustments until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

[0142] By continuously and dynamically adjusting the target optimization strategy, the accuracy and efficiency of QoS assurance have been improved, achieving long-term QoS assurance.

[0143] like Figure 2 As shown in the illustration, this disclosure provides a schematic diagram of network service quality optimization, including NWDAF, AIAgent, BOSS, PCF, SMF, UPF, and RAN. Each component communicates through a standard interface and works collaboratively to achieve intelligent QoS assurance. By analyzing network status and obtaining factors affecting network service quality such as QoS Flow Identifier (QFI), QoS Class Identifier (QCI), Guaranteed Flow Bit Rate (GFBR), and Maximum Flow Bit Rate (MFBR), the target optimization strategy is dynamically adjusted until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

[0144] In summary, the network service quality optimization method provided in this disclosure includes, in response to the fact that the execution result of the previous optimization strategy does not meet the user's network quality requirements, obtaining the network status, analyzing the influencing factors of network service quality based on the network status, regenerating the target optimization strategy based on the influencing factors of network service quality, wherein the target optimization strategy includes at least one optimization resource related to the influencing factors, monitoring the execution result of the target optimization strategy during the execution process, and, if it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, continuing to dynamically adjust the target optimization strategy until the execution result of the adjusted optimization strategy meets the user's network quality requirements. The disclosed solution, in response to the failure of the previous optimization strategy to meet the user's network quality requirements, obtains the network status and analyzes the factors influencing network service quality based on the network status. Based on these factors, a new target optimization strategy is generated, which includes at least one optimization resource related to the influencing factors. During the execution of the target optimization strategy, the execution result is monitored. If it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, the target optimization strategy is dynamically adjusted until the execution result of the adjusted optimization strategy meets the user's network quality requirements. Similarly, if it is determined that the execution result of the previous optimization strategy does not meet the user's network quality requirements, the factors influencing network QoS are determined based on the network status, and the optimization strategy is dynamically adjusted based on these factors until the execution result of the adjusted optimization strategy meets the user's network quality requirements. This achieves a dynamic adjustment mechanism for optimizing QoS guarantee strategies and provides long-term effective QoS guarantee.

[0145] Figure 3 A flowchart illustrating a method for optimizing network service quality provided in an embodiment of this disclosure. Figure 3 This may include the following steps:

[0146] Step 301: In response to the received network quality assurance command, parse the network quality assurance command to obtain the command parsing result.

[0147] In this embodiment of the disclosure, the BOSS sends a QoS assurance instruction to the NWDAF via the PCF through the User Equipment (UE) and Application Function (AF). The QoS assurance instruction includes two forms. The first form is that the UE transmits natural language through the Non-Access Stratum (NAS), such as "to ensure the xx experience for user xx during xx period in xx area". The second form is transmitted through signaling, wherein the signaling carries, but is not limited to, user identification information (e.g., user ID), the type of service to be guaranteed (e.g., video conferencing, live streaming, games, etc.), the expected QoS level (e.g., different QoS levels correspond to different services), etc.

[0148] NWDAF parses QoS assurance instructions through a built-in AI Agent. The AI ​​Agent has AI capabilities such as machine learning, deep learning, and large models. The AI ​​Agent parses the received QoS assurance instructions. The QoS assurance instruction parsing includes two forms. The first form is to convert natural language into capability-opening related signaling, including but not limited to the conversion of key information such as time and location. The second form is to directly parse the signaling. These two forms of QoS assurance instruction parsing correspond to the two forms of QoS assurance instructions, and the QoS assurance instruction parsing results are obtained.

[0149] The process of parsing QoS guarantee instructions is similar to how a network system understands and makes decisions about instructions. It is not only a prerequisite for achieving QoS guarantees at the technical level, but also an important link in supporting differentiated services, network automation, and industry applications at the business level.

[0150] Step 302: Perform intent recognition on the instruction parsing result to determine the network quality requirements, wherein the network quality requirements include at least: user identification information, guaranteed service type, guarantee requirements, and continuous optimization instructions.

[0151] The QoS assurance command parsing results are used to identify the user's QoS assurance intent. The QoS assurance intent includes the judgment of user identification information (to ensure certain users), the identification of the service type (to ensure certain services), and the explicitness of the assurance requirements (the standard for ensuring a certain location at a certain time period) and the indication of continuous optimization (whether multiple rounds of continuous optimization are needed), thereby determining the user's network quality requirements.

[0152] Intent recognition of the parsing results of QoS assurance commands not only saves resources for resource scheduling optimization, but also enables business assurance to have semantic-level intelligence, achieving multi-dimensional optimization of user experience, business efficiency, and network costs.

[0153] To further optimize network service quality, during step 302, the user's network quality requirements can be determined, and the process also includes: a pre-trained analysis model performing task planning on the network quality requirements to obtain data acquisition tasks, data analysis tasks, strategy generation tasks, strategy execution and monitoring tasks.

[0154] Based on the identified QoS guarantee intent, the AI ​​Agent uses AI algorithms to plan tasks by calling any inference function module in NWDAF in 5GC. Task planning includes, but is not limited to, the types of data to be collected, the dimensions of data to be analyzed, and the methods for generating guarantee strategies.

[0155] The tasks planned in the task planning are broken down into multiple executable tasks, such as data acquisition tasks, data analysis tasks, strategy generation tasks, strategy execution tasks, real-time monitoring, evaluation and feedback tasks, and continuous optimization tasks. Based on the QoS guarantee instruction parsing results, each task in the task planning needs to set clear goals and goal outputs.

[0156] The data acquisition task is used to determine network quality requirements in steps 301 and 302. The data analysis task is used to analyze the influencing factors of network service quality based on network status in step 101. The strategy generation task is used to regenerate the target optimization strategy in step 102. The strategy execution task and real-time monitoring, evaluation, and feedback task are used to execute the target optimization strategy in step 103 and monitor the execution results. The continuous optimization task is used in step 104 to dynamically adjust the target optimization strategy if the execution results do not meet the user's network quality requirements, until the execution results of the adjusted optimization strategy meet the user's network quality requirements. Transforming complex network quality requirements into standardized execution processes not only improves the efficiency of guaranteeing single scenarios but also builds a scalable network intelligence system.

[0157] Figure 4 A flowchart of a method for optimizing network service quality proposed in an embodiment of this disclosure is further shown.

[0158] based on Figure 1 The illustrated embodiment further explains step 101. Figure 4 This may include the following steps:

[0159] Step 401: Obtain the corresponding business profile based on user identification information. The business profile includes at least business usage habits and business preference settings.

[0160] In this embodiment of the disclosure, NWDAF extracts poor quality data and wireless cell data from ADRF, and uses the service profile and network profile built into AIAgent to perform in-depth analysis of the data to identify data patterns, trends and potential correlations. The service profile reflects the user's service usage habits (such as peak daily traffic periods and service usage duration), service preference settings (such as video clarity preference and application priority), etc., while the network profile reflects the network status and performance.

[0161] Build digital profiles of users' business usage habits and preferences to transform abstract user network quality needs into quantifiable and actionable criteria for network optimization.

[0162] Step 402: Perform correlation analysis on the business profile and the network status using a pre-trained analysis model to obtain at least one influencing factor of network service quality.

[0163] Network status refers to the current network operating environment and optimized resource status, which is the basis for analyzing network quality requirements. By analyzing the service profile and network status through a pre-trained analysis model, the influencing factors of QoS network service quality are obtained. Among them, the influencing factors of QoS network service quality include, but are not limited to, network congestion, signal interference, equipment failure, etc.

[0164] By constructing a causal mapping between users' network quality needs and network status, we can achieve accurate problem localization, mine factors affecting network service quality from massive amounts of data, and directly link network problems with user experience, thus avoiding the limitations of traditional network management that only focuses on equipment indicators and ignores the actual user experience.

[0165] Step 403: Determine whether all at least one factor affecting network service quality meets its corresponding preset service quality threshold.

[0166] The system assesses at least one factor influencing network service quality and determines whether all factors meet the preset service quality thresholds corresponding to at least one factor.

[0167] For example, when judging the factors affecting network service quality, consider whether network congestion meets the user's service quality expectations, whether network congestion still exists, whether signal interference affects the user's normal use, and whether equipment malfunctions. It should be noted that the above examples are illustrative for ease of understanding and are not intended to limit the specific content.

[0168] It should be noted that the preset service quality thresholds vary depending on the factors affecting the quality of different types of network services. This disclosure will not provide examples of each preset service quality threshold.

[0169] Step 404: If it is determined that there are one or more influencing factors that do not meet their respective preset service quality thresholds, it is determined that the guarantee index is not met.

[0170] If any one or more of the factors affecting network service quality fail to meet their respective preset service quality thresholds, then the guarantee indicators are deemed not to be met.

[0171] In some embodiments, when the protection indicator is triggered for the first time or multiple times, if it is determined that the protection indicator is not met, the protection indicator is set to 0 to indicate that the protection indicator is not met.

[0172] Step 405: If all the factors affecting the quality of network services meet their respective preset service quality thresholds, then the guarantee index is satisfied.

[0173] If all factors affecting network service quality are satisfied and their respective preset service quality thresholds are met, the guarantee indicator is set to 1, indicating that the guarantee indicator is met.

[0174] Figure 5 A flowchart of a method for optimizing network service quality proposed in an embodiment of this disclosure is further shown.

[0175] based on Figure 4 The illustrated embodiment further explains step 402. Figure 5 This may include the following steps:

[0176] Step 501: Obtain user feedback on the execution result of the previous optimization strategy.

[0177] In this embodiment of the disclosure, feedback information reflecting the influencing factors of QoS network service quality is obtained by acquiring the user's previous optimization strategy execution result. Please continue reading. Figure 2 Feedback information includes, but is not limited to, QFI values, QCI values, GFBR values, MFBR values, etc.

[0178] By collecting user feedback on the results of optimization strategy implementation, a closed-loop process of strategy formulation, execution, feedback, and iteration is formed, ensuring that network service quality optimization is always based on real user experience rather than relying on technical indicators.

[0179] Step 502: The service profile, the network status, and the feedback information are correlated and analyzed using a pre-trained analysis model to obtain the influencing factors of the network service quality.

[0180] By analyzing business profiles, network status, and feedback information using a pre-trained analytical model, the influencing factors of QoS network service quality are obtained.

[0181] This enables the derivation of systemic influencing factors from fragmented data, providing a scientific and dynamic basis for decision-making in optimizing network service quality.

[0182] Figure 6 A flowchart of a method for optimizing network service quality proposed in an embodiment of this disclosure is further shown.

[0183] based on Figure 4 The illustrated embodiment further explains step 102. Figure 6 This may include the following steps:

[0184] Step 601: If it is determined that the guarantee index is not met, at least one optimized resource related to the factors affecting the quality of network service is identified.

[0185] In this embodiment of the disclosure, if it is determined that the guarantee index is not met, at least one optimized resource related to the influencing factors of network service quality is identified, and an influencing factor is processed through the corresponding at least one optimized resource.

[0186] Effectively match the most relevant optimization resources to factors affecting network service quality, improve processing efficiency, and reasonably optimize network service quality.

[0187] Step 602: Adjust the at least one optimized resource to obtain the target optimization strategy.

[0188] Adjustments are made to at least one optimized resource. If the adjusted QoS guarantee policy is unstable or does not meet expectations, or if the implemented policy is ineffective or network conditions change, AIAgent will dynamically adjust and continuously generate new policies, and continuously approach the optimal target optimization policy through iterative optimization.

[0189] The AI ​​Agent dynamically adjusts and iteratively optimizes to continuously approach the optimal target. There are two scenarios for the optimization strategy. The first scenario includes a continuous optimization instruction and the guarantee indicator is marked as 0. This indicates that the strategy implemented under long-term optimization tasks is not effective, and the guarantee is no longer met after a period of time due to changes in network conditions or the unstable effect of the implemented strategy. The second scenario does not include a continuous optimization instruction and the guarantee indicator is 0. This indicates that the strategy implemented under non-long-term optimization tasks is not as effective as expected.

[0190] Based on the factors affecting network service quality, at least one optimized resource is dynamically adjusted. Through continuous learning and experience accumulation, the QoS guarantee strategy can achieve a leap from rule-driven to intelligent evolution in meeting users' service quality needs.

[0191] Figure 7 A flowchart illustrating a method for optimizing network service quality provided in this embodiment of the disclosure, based on... Figure 4 The embodiment shown, Figure 7 This may include the following steps:

[0192] Step 701: If the guarantee index is met and the user's network quality requirements include a continuous optimization instruction, determine at least one optimization resource related to the factors affecting the network service quality.

[0193] When the guarantee index is 1 and the user's network quality requirements include an indication that continuous optimization is needed, the factors affecting network service quality are identified and processed by at least one corresponding optimization resource to achieve long-term continuous optimization.

[0194] Step 702: Adjust the at least one optimized resource to obtain the target optimization strategy.

[0195] Adjustments are made to at least one optimized resource. If the adjusted QoS guarantee policy is unstable or does not meet expectations, or if the implemented policy is ineffective or network conditions change, the AI ​​Agent will dynamically adjust and continuously generate new policies, and continuously approach the optimal target optimization policy through iterative optimization.

[0196] To further optimize network quality requirements, step 405 further includes: if it is determined that the guarantee indicators are met and the user's network quality requirements do not include a continuous optimization instruction, then the optimization of network service quality is exited, i.e., the continued optimization process of network service quality is terminated.

[0197] Figure 8 A flowchart illustrating a method for optimizing network service quality provided in this embodiment of the disclosure, based on... Figure 1 The embodiment shown, Figure 8 This may include the following steps:

[0198] Step 801: Monitor network performance and whether there are any changes in the user's network quality requirements.

[0199] In this embodiment of the disclosure, the dynamic changes of network performance indicators and user quality requirements are monitored to observe whether network performance and user network quality requirements change.

[0200] Step 802: If it is determined that there are changes in the network performance and / or the user's network quality requirements, the target optimization strategy is dynamically adjusted to obtain the adjusted optimization strategy.

[0201] If changes are detected in network performance and user network quality requirements, the target optimization strategy will be dynamically adjusted. If no changes are detected, monitoring will continue. A score of 1 is recorded when network performance and user network quality requirements meet the guarantee indicators, and a score of 0 is recorded when network performance and user network quality requirements do not meet the guarantee indicators.

[0202] When network performance and user network quality requirements change, the target optimization strategy is dynamically adjusted to build a flexible and adaptable network service mechanism. This ensures that network performance meets user needs in real time, while achieving efficient resource allocation, rapid response to user service switching, improved user experience, stable service operation, and accurate resource allocation.

[0203] Figure 9 A flowchart of a method for optimizing network service quality proposed in an embodiment of this disclosure is further shown.

[0204] based on Figure 1 The illustrated embodiment further explains step 103. Figure 9 This may include the following steps:

[0205] Step 901: The network data analysis module sends the target optimization strategy to the strategy control module.

[0206] In this embodiment of the disclosure, NWDAF sends the generated target optimization strategy to the PCF policy control module.

[0207] Clearly define the roles of each module to ensure that optimization strategies can be accurately and efficiently translated into actual network device operations.

[0208] Step 902: The policy control module sends the target optimization policy to the session management module, user plane module, and wireless access network module in a preset sending order.

[0209] The target optimization policy received by the PCF is sent to the SMF, then the target optimization policy received by the SMF is sent to the UPF, and finally the target optimization policy received by the UPF is sent to the RAN.

[0210] This ensures the precise implementation of optimization strategies across the core network and access network, avoiding execution conflicts and redundant operations, thereby improving strategy execution efficiency and success rate. Simultaneously, standardized execution processes enhance network management stability, reduce operational risks, and promote deep collaboration between modules, achieving coordinated optimization across the entire link from session establishment to data transmission, ultimately comprehensively improving network performance and user experience.

[0211] Step 903: The session management module adjusts the parameters of the user session according to the target optimization strategy.

[0212] SMF is responsible for session management, adjusting user session parameters according to policies. By dynamically configuring session-level parameters, it accurately matches users' real-time network quality requirements and network status, ensuring efficient and stable data transmission.

[0213] Step 904: The user plane module adjusts the priority and rate of data transmission according to the target optimization strategy.

[0214] UPF is responsible for processing user data, adjusting the priority and rate of data transmission according to policies, dynamically adjusting data transmission resources, ensuring service quality, and customizing transmission strategies for different users and service types to enhance service competitiveness.

[0215] Step 905: The wireless access network module optimizes network coverage and performance according to the target optimization strategy.

[0216] The RAN is responsible for the allocation and scheduling of wireless resources, optimizing network coverage and performance according to policies. By adjusting base station parameters and optimizing signal transmission mechanisms, it solves problems such as signal blind spots, interference, and insufficient capacity, ensuring that users obtain stable and high-quality network services in the wireless access stage, and realizing efficient utilization of wireless access network resources and a comprehensive upgrade of user experience.

[0217] Figure 10 A flowchart of a method for optimizing network service quality according to an embodiment of this disclosure is further shown. Based on Figure 9 The illustrated embodiment further explains step 103. Figure 10 This may include the following steps:

[0218] Step 1001: Monitor the network status in real time.

[0219] NWDAF monitors network status in real time, and the indicators monitored include, but are not limited to, measuring network latency, packet loss rate, throughput, etc., to achieve real-time monitoring of users' network quality requirements.

[0220] Step 1002: Monitor in real time whether feedback information from the user regarding the execution result of the target optimization strategy is received.

[0221] The NWDAF monitors and receives feedback from users on the results of the target optimization strategy in real time. If the feedback results are unsatisfactory, the NWDAF will adjust the target optimization strategy in a timely manner and notify the PCF, SMF, UPF and RAN to make corresponding adjustments.

[0222] By validating the effectiveness of strategies using real user experience data, we can promptly identify discrepancies between network service quality and user needs. Based on feedback, we can quickly adjust parameters or optimize solutions to improve optimization efficiency, convey a user-centric service philosophy, enhance satisfaction and loyalty, accumulate optimization experience data, provide historical references for subsequent strategy formulation, promote continuous improvement in network service quality, and ultimately achieve a deep alignment between network optimization and user network quality needs.

[0223] like Figure 11 As shown in the flowchart of a real-time monitoring, evaluation, and feedback process provided in this embodiment, the process constructs a closed loop for continuous network optimization: First, real-time monitoring, evaluation, and feedback are conducted, acquiring multi-dimensional data such as network performance and user behavior through data collection, and then using Agent and NIDAF for in-depth analysis to identify problems and evaluate strategies; then, continuous optimization is implemented, based on the results of in-depth analysis, combined with goals and requirements to generate assurance strategies, which are pushed to network modules for execution, adjusting parameters, rates, etc., forming a closed loop of monitoring-analysis-generation-execution, iteratively improving network performance and user experience, and adapting to changes in business and requirements.

[0224] The embodiments disclosed herein can achieve the following beneficial effects:

[0225] 1. AI-driven intelligent decision-making: Utilizing AI technology to achieve intelligent parsing of QoS guarantee instructions and intelligent generation and optimization of policies, thereby improving decision-making efficiency and accuracy.

[0226] 2. Comprehensive data collection and analysis: Combining business profiles and network profiles, we conduct in-depth analysis of multi-dimensional data to accurately identify key factors affecting QoS.

[0227] 3. Dynamic policy adjustment and optimization: Through real-time monitoring and feedback mechanisms, the policy can be dynamically adjusted and optimized to ensure the continuous effectiveness of QoS guarantee.

[0228] 4. Long-term continuous optimization: The AI ​​Agent continuously learns and accumulates experience to achieve continuous optimization of algorithms and models, thereby improving the long-term stability and efficiency of QoS assurance.

[0229] Figure 12 This is a schematic diagram of the structure of a network service quality optimization device provided in an embodiment of this disclosure, as shown below. Figure 11 As shown, it includes: an acquisition unit 121, an analysis unit 122, a generation unit 123, a first monitoring unit 124, and a first adjustment unit 125.

[0230] The acquisition unit 121 is used to acquire the network status in response to the fact that the execution result of the previous optimization strategy does not meet the user's network quality requirements;

[0231] Analysis unit 122 is used to analyze the factors affecting network service quality based on the network status;

[0232] The generation unit 123 is configured to regenerate a target optimization strategy based on the factors affecting network service quality, wherein the target optimization strategy includes at least one optimization resource for optimizing the factors affecting network service quality.

[0233] The first monitoring unit 124 is used to monitor the execution result of the target optimization strategy during the execution of the target optimization strategy;

[0234] The first adjustment unit 125 is used to continue to dynamically adjust the target optimization strategy when it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

[0235] In summary, according to the network service quality optimization apparatus provided in this disclosure, the apparatus includes, in response to the fact that the execution result of the previous optimization strategy does not meet the user's network quality requirements, acquiring the network status, analyzing the factors affecting network service quality based on the network status, regenerating the target optimization strategy based on the factors affecting network service quality, wherein the target optimization strategy includes at least one optimization resource related to the factors affecting the network service quality, monitoring the execution result of the target optimization strategy during the execution of the target optimization strategy, and, if it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, continuing to dynamically adjust the target optimization strategy until the execution result of the adjusted optimization strategy meets the user's network quality requirements. The disclosed solution, in response to the failure of the previous optimization strategy to meet the user's network quality requirements, obtains the network status and analyzes the factors influencing network service quality based on the network status. Based on these factors, a new target optimization strategy is generated, which includes at least one optimization resource related to the influencing factors. During the execution of the target optimization strategy, the execution result is monitored. If it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, the target optimization strategy is dynamically adjusted until the execution result of the adjusted optimization strategy meets the user's network quality requirements. Similarly, if it is determined that the execution result of the previous optimization strategy does not meet the user's network quality requirements, the factors influencing network QoS are determined based on the network status, and the optimization strategy is dynamically adjusted based on these factors until the execution result of the adjusted optimization strategy meets the user's network quality requirements. This achieves a dynamic adjustment mechanism for optimizing QoS guarantee strategies and provides long-term effective QoS guarantee.

[0236] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the analysis unit 122 includes:

[0237] The acquisition module 1221 is used to acquire a corresponding business profile based on user identification information. The business profile includes at least business usage habits and business preference settings.

[0238] Analysis module 1222 is used to perform correlation analysis on the business profile and the network status through a pre-trained analysis model to obtain at least one factor affecting network service quality.

[0239] The judgment module 1223 is used to determine whether the at least one network service quality influencing factor meets its respective preset service quality threshold.

[0240] The first determining module 1224 is used to determine that the guarantee index is not met when it is determined that there are one or more influencing factors that do not meet their respective preset service quality thresholds.

[0241] The second determining module 1225 is used to determine whether the guarantee index is met when all the influencing factors of the at least one network service quality meet their respective preset service quality thresholds.

[0242] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the analysis module 1222 includes:

[0243] The acquisition submodule 12221 is used to acquire user feedback information on the execution result of the previous optimization strategy;

[0244] The analysis submodule 12222 is used to perform correlation analysis on the service profile, the network status and the feedback information through a pre-trained analysis model to obtain the influencing factors of the network service quality.

[0245] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the generation unit 123 includes:

[0246] The third determining module 1231 is used to determine at least one optimized resource related to the influencing factors of the network service quality when it is determined that the guarantee indicators are not met.

[0247] The first adjustment module 1232 is used to adjust the at least one optimization resource to obtain the target optimization strategy.

[0248] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13As shown, the generation unit 123 further includes:

[0249] The fourth determining module 1233 is used to determine at least one optimization resource related to the influencing factors of the network service quality when it is determined that the guarantee index is met and the user's network quality requirements include a continuous optimization instruction.

[0250] The second adjustment module 1234 is used to adjust the at least one optimization resource to obtain the target optimization strategy.

[0251] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the device further includes:

[0252] The exit unit 126 is used to exit the optimization of network service quality when it is determined that the guarantee index is met and the user's network quality requirements do not include a continuous optimization instruction.

[0253] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, after the generation unit 123, the device further includes:

[0254] The second monitoring unit 127 is used to monitor whether there are changes in network performance and user network quality requirements after the generation unit 123 regenerates the target optimization strategy based on the influencing factors of network service quality.

[0255] The second adjustment unit 128 is used to dynamically adjust the target optimization strategy when it is determined that there are changes in the network performance and / or the user's network quality requirements, so as to obtain the adjusted optimization strategy.

[0256] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the first monitoring unit 124 includes:

[0257] The first sending module 1241 is used to send the target optimization strategy to the strategy control module by the network data analysis module;

[0258] The second sending module 1242 is used by the policy control module to send the target optimization policy to the session management module, the user plane module and the wireless access network module in a preset sending order.

[0259] The third adjustment module 1243 is used by the session management module to adjust the parameters of the user session according to the target optimization strategy;

[0260] The fourth adjustment module 1244 is used by the user plane module to adjust the priority and rate of data transmission according to the target optimization strategy;

[0261] The optimization module 1245 is used by the wireless access network module to optimize network coverage and performance according to the target optimization strategy.

[0262] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the first monitoring unit 124 further includes:

[0263] The first monitoring module 1246 is used to monitor the network status in real time;

[0264] The second monitoring module 1247 is used to monitor in real time whether feedback information from the user regarding the execution result of the target optimization strategy is received.

[0265] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the device further includes:

[0266] The parsing unit 129 is configured to parse the received network quality assurance command in response to the network quality assurance command, and obtain the command parsing result;

[0267] The identification unit 1210 is used to identify the intent of the instruction parsing result and determine the network quality requirements, wherein the network quality requirements include at least: user identification information, guaranteed service type, guarantee requirements and continuous optimization instructions.

[0268] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 13 As shown, the identification unit 1210 is also used to perform task planning on the network quality requirements by the pre-trained analysis model to obtain data acquisition tasks, data analysis tasks, policy generation tasks, policy execution and monitoring tasks.

[0269] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0270] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0271] Figure 14A schematic block diagram of an example electronic device 1400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0272] like Figure 14 As shown, the electronic device 1400 includes a computing unit 1401, which can perform various appropriate actions and processes according to a computer program stored in ROM (Read-Only Memory) 1402 or loaded from storage unit 1408 into RAM (Random Access Memory) 1403. The RAM 1403 may also store various programs and data required for the operation of the electronic device 1400. The computing unit 1401, ROM 1402, and RAM 1403 are interconnected via bus 1404. An I / O (Input / Output) interface 1405 is also connected to bus 1404.

[0273] Multiple components in electronic device 1400 are connected to I / O interface 1405, including: input unit 1406, such as keyboard, mouse, etc.; output unit 1407, such as various types of monitors, speakers, etc.; storage unit 1408, such as disk, optical disk, etc.; and communication unit 1409, such as network card, modem, wireless transceiver, etc. Communication unit 1409 allows electronic device 1400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0274] The computing unit 1401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 1401 performs the various methods and processes described above, such as methods for optimizing network service quality. For example, in some embodiments, the methods for optimizing network service quality can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 1408. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1400 via ROM 1402 and / or communication unit 1409. When the computer program is loaded into RAM 1403 and executed by the computing unit 1401, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 1401 may be configured to perform the aforementioned network service quality optimization method by any other suitable means (e.g., by means of firmware).

[0275] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0276] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0277] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0278] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0279] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0280] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0281] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0282] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0283] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for optimizing network service quality, characterized in that, include: If the execution result of the previous optimization strategy does not meet the user's network quality requirements, the network status is obtained, and the factors affecting network service quality are analyzed based on the network status. Based on the factors affecting network service quality, a new target optimization strategy is generated, wherein the target optimization strategy includes at least one optimization resource for optimizing the factors affecting network service quality. During the execution of the target optimization strategy, the execution result of the target optimization strategy is monitored; If it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, the target optimization strategy will continue to be dynamically adjusted until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

2. The method according to claim 1, characterized in that, The factors influencing network service quality obtained from the network state analysis include: Based on user identification information, a corresponding business profile is obtained, which includes at least business usage habits and business preference settings; The business profile and the network status are correlated and analyzed using a pre-trained analytical model to obtain at least one factor affecting network service quality. Determine whether all at least one factor affecting network service quality meets its respective preset service quality threshold. If it is determined that there are one or more influencing factors that do not meet their respective preset service quality thresholds, it is determined that the guarantee index is not met; If all factors affecting network service quality meet their respective preset service quality thresholds, then the guarantee index is deemed to be satisfied.

3. The method according to claim 2, characterized in that, The step of performing correlation analysis on the business profile and the network status using a pre-trained analysis model to obtain the influencing factors of the network service quality includes: Obtain user feedback on the execution results of the previous optimization strategy; The business profile, network status, and feedback information are correlated and analyzed using a pre-trained analytical model to obtain the influencing factors of the network service quality.

4. The method according to claim 2, characterized in that, The step of regenerating the target optimization strategy based on the factors affecting network service quality includes: If it is determined that the guarantee indicators are not met, at least one optimized resource related to the factors affecting the quality of network service is identified. The target optimization strategy is obtained by adjusting the at least one optimization resource.

5. The method according to claim 2, characterized in that, The step of regenerating the target optimization strategy based on the factors affecting network service quality includes: If the guarantee indicators are met and the user's network quality requirements include a continuous optimization instruction, at least one optimization resource related to the factors affecting the network service quality is identified. The target optimization strategy is obtained by adjusting the at least one optimization resource.

6. The method according to claim 2, characterized in that, The method further includes: If the guarantee indicators are met and the user's network quality requirements do not include a continuous optimization instruction, the optimization of the network service quality will be terminated.

7. The method according to claim 1, characterized in that, After regenerating the target optimization strategy based on the factors affecting network service quality, the method further includes: Monitor network performance and whether there are any changes in users' network quality requirements; If the network performance and / or the user's network quality requirements are determined to change, the target optimization strategy is dynamically adjusted to obtain the adjusted optimization strategy.

8. The method according to claim 1, characterized in that, The execution of the target optimization strategy includes: The network data analysis module sends the target optimization strategy to the strategy control module; The policy control module sends the target optimization policy to the session management module, user plane module, and wireless access network module in a preset sending order; The session management module adjusts the parameters of the user session according to the target optimization strategy. The user plane module adjusts the priority and rate of data transmission according to the target optimization strategy. The wireless access network module optimizes network coverage and performance according to the target optimization strategy.

9. The method according to claim 8, characterized in that, The monitoring of the execution results of the target optimization strategy includes: The network status is monitored in real time; Real-time monitoring is conducted to determine whether user feedback on the execution results of the target optimization strategy is received.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: In response to the received network quality assurance command, the network quality assurance command is parsed to obtain the command parsing result; The intent of the instruction parsing result is identified to determine the network quality requirements, wherein the network quality requirements include at least: user identification information, guaranteed service type, guarantee requirements, and continuous optimization instructions.

11. The method according to claim 10, characterized in that, The step of performing intent recognition on the instruction parsing results to determine the network quality requirements includes: The pre-trained analysis model performs task planning for the network quality requirements, resulting in data acquisition tasks, data analysis tasks, policy generation tasks, policy execution and monitoring tasks.

12. A device for optimizing network service quality, characterized in that, include: The acquisition unit is used to acquire the network status in response to the fact that the execution result of the previous optimization strategy does not meet the user's network quality requirements; The analysis unit is used to analyze the factors affecting network service quality based on the network status. A generation unit is configured to regenerate a target optimization strategy based on the factors affecting network service quality, wherein the target optimization strategy includes at least one optimization resource for optimizing the factors affecting network service quality. The first monitoring unit is used to monitor the execution result of the target optimization strategy during the execution process. The first adjustment unit is used to continuously adjust the target optimization strategy dynamically when it is determined that the execution result of the target optimization strategy does not meet the user's network quality requirements, until the execution result of the adjusted optimization strategy meets the user's network quality requirements.

13. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

14. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-11.

15. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-11.

Images