Self-learning network service rule decoupling method, device, equipment, medium and product

Abstract

The present application relates to the technical field of network communication, and provides a self-intelligent network service rule decoupling method, device, equipment, medium and product.The self-intelligent network service rule decoupling method comprises the following steps: obtaining network data from a database;extracting existing index management rules from the database to obtain an initial index set;configuring a rule engine according to the network data and the initial index set to obtain a new rule engine; wherein the new rule engine comprises at least one of a demand prediction rule, a quality problem identification rule, a quality problem positioning rule, a quality optimization verification rule and a quality evaluation rule; and managing the database according to the new rule engine.Through the above method, the present application can extract the existing rules of the database and establish a new rule engine, realize rule decoupling and flexible configuration, solve the tight coupling status of network operation and maintenance rule algorithm and scene, and adapt to the intelligent development of network operation and maintenance.

Description

Technical Field

[0001] This invention relates to the field of network communication technology, and in particular to methods, apparatus, devices, media, and products for decoupling intelligent network service rules. Background Technology

[0002] The business analysis processes in various scenarios of communication network operation and maintenance are quite complex. Each business analysis process may contain multiple decision points, and each decision point may contain multiple rules. These rules are usually embedded in the business process itself or in the internal implementation of custom Java code. This will lead to the following problems:

[0003] ① Business rule changes take a long time and involve a lot of work: Business rules change more frequently than the business itself, and changing and managing embedded business rules is a complex problem that exceeds the capabilities of most business analysts. Therefore, changes to business rules usually require business analysts and programmers to spend a lot of time to understand the business and for IT to implement the system. Business processes are complex and change rapidly, and system updates cannot respond quickly and promptly.

[0004] ② Business rules are difficult to maintain: Most systems lack a central rule information database, business rules are not visible, and system users cannot obtain business rule information from the system in a timely manner, making it difficult to maintain business rules and promote the use of functions.

[0005] ③Low reusability of business rules: Business rules are implemented separately in each system and implemented at the system code level. There is a problem of repeated development of the same business logic in multiple systems, resulting in redundant business rules that cannot be reused. Summary of the Invention

[0006] This invention provides a method, apparatus, device, medium, and product for decoupling intelligent network service rules, in order to solve the current tight coupling between network operation and maintenance rule algorithms and scenarios, and to adapt to the intelligent development of network operation and maintenance.

[0007] This invention provides a method for decoupling intelligent network service rules, comprising: obtaining network data from a database; extracting existing indicator management rules from the database to obtain an initial indicator set; configuring a rule engine based on the network data and the initial indicator set to obtain a new rule engine; wherein the new rule engine includes at least one of demand prediction rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules; and managing the database according to the new rule engine.

[0008] According to a self-intelligent network service rule decoupling method provided by the present invention, the new rule engine includes demand prediction rules; the rule engine is configured according to network data and an initial indicator set to obtain a new rule engine, including: determining an initial prediction model, an initial predicted value output by the initial prediction model, and an initial warning threshold of the initial predicted value according to network data and an initial indicator set; configuring the parameters of the initial prediction model using a training model to obtain a new prediction model, a new predicted value, and a new warning threshold; and determining demand prediction rules based on the new prediction model, the new predicted value, and the new warning threshold.

[0009] According to a self-intelligent network service rule decoupling method provided by the present invention, the new rule engine includes quality problem identification rules; the rule engine is configured according to network data and an initial indicator set to obtain a new rule engine, including: determining an initial problem identification model according to network data and an initial indicator set; configuring the indicator thresholds, rules, and data periods of the initial problem identification model to achieve quality problem identification, thereby obtaining a problem identification model; the problem identification model is used to output quality problem alarms and / or poor quality results; and obtaining quality problem identification rules according to the problem identification model.

[0010] According to a self-intelligent network business rule decoupling method provided by the present invention, the new rule engine includes quality problem location rules; the rule engine is configured according to network data and an initial indicator set to obtain the new rule engine, including: when a quality problem is determined according to network data and an initial indicator set, a problem location process is generated according to the location process to obtain quality problem location rules; wherein, the location process is obtained based on the following method: adding presentation nodes to the location process, selecting one or more indicators under each node, and configuring the rule algorithm under the selected indicators; wherein, the rule algorithm of each node is configured separately; defining branches for the algorithm results, with different branches pointing to different next-level nodes, thereby constituting the location process.

[0011] According to a self-intelligent network business rule decoupling method provided by the present invention, the new rule engine includes quality optimization verification rules; the rule engine is configured according to network data and an initial indicator set to obtain the new rule engine, including: obtaining quality optimization verification rules according to network data and an initial indicator set; wherein the quality optimization verification rules are used to process and verify the automatic association optimization verification rules of the processed problem work orders to obtain verification results.

[0012] According to the present invention, a method for decoupling intelligent network business rules is provided. The new rule engine includes quality assessment rules. The method involves configuring the rule engine based on network data and an initial indicator set to obtain the new rule engine, including: configuring various indicator evaluation systems based on network data and an initial indicator set; determining statistical analysis of data in each dimension based on various indicator evaluation systems to obtain analysis results, thereby constructing quality assessment rules; wherein the analysis results include at least one of score ranking, poor quality indicators, and indicator trends.

[0013] The present invention also provides a self-intelligent network service rule decoupling device, comprising: an acquisition module for acquiring network data from a database; an extraction module for extracting existing indicator management rules from the database to obtain an initial indicator set; a rule engine configuration module for configuring the rule engine according to the network data and the initial indicator set to obtain a new rule engine; wherein the new rule engine includes at least one of demand prediction rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules; and a management module for managing the database according to the new rule engine.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the self-intelligent network service rule decoupling method as described above.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the self-intelligent network service rule decoupling method as described above.

[0016] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the self-intelligent network service rule decoupling method as described above.

[0017] This invention provides a method, apparatus, device, medium, and product for decoupling intelligent network service rules. The method includes: acquiring network data from a database; extracting existing indicator management rules from the database to obtain an initial indicator set; configuring a rule engine based on the network data and the initial indicator set to obtain a new rule engine; wherein the new rule engine includes at least one of demand prediction rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules; and managing the database according to the new rule engine. Through this method, this invention can extract existing rules from the database and establish a new rule engine, achieving rule decoupling and flexible configuration, solving the current tight coupling between network operation and maintenance rule algorithms and scenarios, and adapting to the intelligent development of network operation and maintenance. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the self-intelligent network service rule decoupling method provided in this embodiment of the invention.

[0020] Figure 2 This is the overall design diagram of the rule engine platform provided in the embodiments of the present invention.

[0021] Figure 3 This is a flowchart illustrating the indicator management process provided in this embodiment of the invention.

[0022] Figure 4 This is a schematic diagram of the structure of the self-intelligent network service rule decoupling device provided in an embodiment of the present invention.

[0023] Figure 5 This is a schematic diagram of the physical structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0025] In the description of the embodiments of the present invention, it should be noted that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of the present invention. In addition, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0026] In the description of the embodiments of the present invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of the present invention based on the specific circumstances.

[0027] In embodiments of the present invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0028] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0029] It should be noted that all actions involving the acquisition of signals, information, or data in this invention are carried out in compliance with the relevant data protection laws and policies of the country where the invention is located, and with authorization from the owner of the relevant device.

[0030] This invention provides a method for decoupling service rules in an intelligent network. Please refer to [link / reference]. Figure 1 , Figure 1 This is a flowchart illustrating the self-intelligent network service rule decoupling method provided in an embodiment of the present invention. In this embodiment, the self-intelligent network service rule decoupling method includes steps S110 to S140, and the specific steps are as follows:

[0031] S110: Retrieve network data from the database.

[0032] S120: Extract existing indicator management rules from the database to obtain the initial indicator set.

[0033] S130: Configure the rule engine based on network data and the initial indicator set to obtain a new rule engine.

[0034] S140: Manage the database according to the new rules engine.

[0035] The new rule engine includes at least one of the following: demand forecasting rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules.

[0036] The rules engine provides unified management of relevant business rules throughout their entire lifecycle, including functions for editing, deploying, running, and monitoring reusable simple rules, decision tables, decision trees, and rule flows, enabling efficient decision management.

[0037] For example, the functionality of a rules engine may include:

[0038] 1) Allow users to create and edit rules using specific syntax or a graphical interface, such as having a clear logical structure that is easy for non-technical personnel to understand and use.

[0039] 2) Provides functionality for organizing, classifying, and maintaining rules, making rule version control and updates simpler.

[0040] 3) Based on the input data and defined rules, reasoning is performed to automatically make decisions and output corresponding results. This process includes rule matching and execution.

[0041] 4) Rules can be quickly adjusted according to changes in business needs, enabling rapid response to user demands.

[0042] 5) By automating the decision-making process, human intervention is reduced, and the speed and accuracy of decision-making are improved.

[0043] In this embodiment, a self-intelligent network refers to a network system that achieves self-optimization, self-management, and self-adjustment through advanced intelligent technologies (such as artificial intelligence, machine learning, and big data analytics). A self-intelligent network not only possesses the connectivity functions of a traditional network but can also intelligently analyze and process data, dynamically adapting to environmental changes and business needs.

[0044] Based on the core scenarios of self-intelligent networks, this embodiment constructs a rule engine technology platform to enable flexible configuration of business rules. It realizes a rule engine for the entire lifecycle of network intelligence, from rule solidification to rule decoupling, rule intelligence injection, and rule self-iteration, in line with the evolution of self-intelligent networks, thus helping the digital transformation of network operation and maintenance.

[0045] Through the above methods, the present invention can extract existing rules from the database and establish a new rule engine, thereby achieving rule decoupling and flexible configuration, solving the current situation of tight coupling between network operation and maintenance rule algorithms and scenarios, and adapting to the intelligent development of network operation and maintenance.

[0046] In some embodiments, the new rule engine includes demand forecasting rules; the step of configuring the rule engine based on network data and an initial metric set to obtain the new rule engine may specifically include:

[0047] The initial prediction model, the initial predicted value output by the initial prediction model, and the initial warning threshold of the initial predicted value are determined based on network data and the initial indicator set. The parameters of the initial prediction model are configured using the training model to obtain a new prediction model, a new predicted value, and a new warning threshold. Demand prediction rules are determined based on the new prediction model, the new predicted value, and the new warning threshold.

[0048] In some embodiments, the new rule engine includes quality issue identification rules; the step of configuring the rule engine based on network data and an initial metric set to obtain the new rule engine may specifically include:

[0049] An initial problem identification model is determined based on network data and an initial indicator set; the indicator thresholds, rules, and data periods of the initial problem identification model are configured to achieve quality problem identification, thus obtaining the problem identification model; the problem identification model is used to output quality problem alarms and / or poor quality results; and quality problem identification rules are obtained based on the problem identification model.

[0050] In some embodiments, the new rule engine includes quality issue localization rules; the step of configuring the rule engine based on network data and an initial metric set to obtain the new rule engine may specifically include:

[0051] When quality issues are identified based on network data and an initial set of indicators, a problem localization process is generated according to the localization process to obtain quality issue localization rules. The localization process is obtained in the following way: a presentation node is added to the localization process, one or more indicators are selected under each node, and the rule algorithm under the selected indicators is configured. The rule algorithm of each node is configured separately. Branches are defined for the algorithm results, and different branches point to different next-level nodes, thus forming the localization process.

[0052] In some embodiments, the new rule engine includes quality optimization verification rules; the step of configuring the rule engine based on network data and an initial metric set to obtain the new rule engine may specifically include:

[0053] Quality optimization verification rules are obtained based on network data and an initial indicator set. These quality optimization verification rules are used to process and verify the automatic association of optimized verification rules with already processed problem work orders, and the verification results are obtained.

[0054] In some embodiments, the new rule engine includes quality assessment rules; the step of configuring the rule engine based on network data and an initial metric set to obtain the new rule engine may specifically include:

[0055] Configure various indicator evaluation systems based on network data and initial indicator sets; determine statistical analysis of data in each dimension based on various indicator evaluation systems, obtain analysis results, and construct quality evaluation rules; the analysis results include at least one of score ranking, poor quality indicators, and indicator trends.

[0056] Please see Figure 2 , Figure 2 This is the overall design diagram of the rule engine platform provided in the embodiments of the present invention; Figure 3 This is a flowchart illustrating the indicator management process provided in this embodiment of the invention.

[0057] In this embodiment, the new network architecture is matched by digital transformation of operation and maintenance, a rule engine is established, and rule decoupling and flexible configuration are achieved. Furthermore, AI learning is introduced to generate a diagnostic rule base. The rule engine will automatically call the rules to perform root cause analysis and diagnosis, thereby accelerating the automation and intelligence of network-wide operation and maintenance.

[0058] exist Figure 2 The technical architecture of the rule engine platform in the self-intelligent network scenario shown can be divided into a data collection layer, an indicator system layer, a rule engine layer, and a self-intelligent network scenario application layer.

[0059] Specifically, the data acquisition layer is the underlying perception layer for realizing digital applications of network operation and maintenance based on massive network data. The data collected by the data acquisition layer can include 4 / 5G DPI data, 4 / 5G PM data, wireless MR data, basic engineering parameter data, and core network OMC data, etc.

[0060] The indicator system layer strengthens the virtual mapping and management organization of data, knowledge, and assets, providing the foundational resources and key tools to support digital operations and maintenance applications. The indicator types in the indicator system layer can include perception indicators, performance indicators, resource indicators, and service indicators, among others.

[0061] The rules engine layer is used for data mining analysis and value transformation, enabling intelligent optimization and decision-making in core processes. Its functions include rule design, rule executor, rule orchestration, business rule configuration, rule reading, rule validation, rule tree generation, and business rule verification.

[0062] The self-intelligent network scenario application layer can build intelligent decision-making application maps, empowering more scenarios, achieving cost reduction and efficiency improvement on the operation and maintenance side, and quality improvement and revenue increase on the operation side. The functions of the self-intelligent network scenario application layer can include business demand prediction, quality problem identification, quality problem location, quality optimization verification, batch complaint prediction, and quality assessment closed loop, etc.

[0063] Indicator management serves as the foundation for rule configuration and application. It is implemented through two methods: automatic extraction and manual entry. Indicators are directly linked to the backend database, supporting the implementation of business rules.

[0064] like Figure 3 As shown, basic indicator information can be configured manually, or indicator standardization information can be automatically extracted, enabling a semi-automatic indicator set assembly process: automatic extraction of indicator dimension sets followed by manual verification. The automatically extracted indicators can include those obtained from the database after metadata extraction, dimension extraction, and dimension relationship mapping.

[0065] The rule engine layer allows for rule engine configuration management, enabling flexible configuration of thresholds, rules, evaluation systems, and delimitation processes for business metrics stored in the database.

[0066] The following is an example of rule engine configuration management:

[0067] ① Demand forecasting:

[0068] It supports custom prediction methods, allowing predictions to be made by configuring fixed growth or decrease rates, and providing early warnings in conjunction with thresholds; or by using the rule engine function to reference AI-trained models, configure the parameters of the prediction model, and output the required prediction results and comparisons with historical data.

[0069] Optionally, the demand forecasting rule configuration provides a variety of forecasting model algorithms to choose from. Model parameters can be manually configured. Multiple forecasting models can be configured for one indicator, and forecasting can be selected according to the actual situation. Each forecasting model supports configuring warning thresholds and crash thresholds, and supports outputting warnings based on the comparison between the forecast results and the thresholds.

[0070] Optionally, the rules engine supports the configuration of different early warning thresholds and crash thresholds for single network elements and multiple network elements in demand prediction scenarios such as 5G data services, 5G voice, SMS, and home broadband.

[0071] ② Quality problem identification:

[0072] Based on a pre-defined set of indicators, the system uses a rule engine to flexibly configure indicator thresholds, rules, and data periods to identify quality issues, output quality issue alarms and poor quality results, and connect to the work order operation system to achieve issue dispatch and tracking loop. It supports the selection of multiple calculation rules, fixed threshold, dynamic threshold, and differentiated threshold settings, and supports the identification of quality issues in scenarios such as 5G data services, 5G voice, SMS, and home broadband.

[0073] Optionally, different quality issue identification calculation formulas can be configured for different object types. The editor supports configuring combined formulas. After configuring the quality issue identification rule formulas, you can choose whether to generate alarms and whether to dispatch issue orders.

[0074] ③ Identifying quality issues:

[0075] A problem localization process is configured for business quality indicators, enabling the identification of issues related to these indicators. Judgment rules for each node are configured individually, including indicator selection and configuration of business logic rules. The backend automatically invokes the process to locate quality issues, presents the localization results, and supports integration with a work order dispatch platform for work order assignment.

[0076] For example, firstly, a presentation node is added to the positioning process. Under each node, one or more indicators can be selected. Using the selected indicators, the rule algorithm under that node is configured. Then, branches are defined for the algorithm results. Different branches point to different next-level nodes, thus forming a complete positioning process.

[0077] ④ Quality optimization verification:

[0078] For various alarms, quality issues, and problem location rules, optimize and verify the rules. By configuring rules such as work order quality inspection keywords, the system automatically associates and processes the optimized verification rules of the work orders that have been processed. It supports displaying the optimization verification conclusions and supports drill-down to display the details of indicator optimization verification and the historical trend of indicators.

[0079] Optionally, the rules engine provides two optimization verification methods: improvement after optimization, configuring a positive percentage increase in the metric; and achieving the target after optimization, configuring a metric verification threshold.

[0080] ⑤ Quality assessment:

[0081] It supports configuring various indicator evaluation systems, including various dimensions within the system, the indicator sets contained in each dimension, and the scoring information for dimensions and indicator weights. Indicator scoring rules support multiple methods such as linear scoring and segmented scoring. Based on the configured evaluation system, it calculates statistical analysis of data for each dimension, including score ranking, quality / poor indicators, and indicator trends. Quality assessment includes configuration of single indicator scoring rules and weight configuration for the evaluation system.

[0082] The single-indicator scoring rule configuration supports configuration through methods such as the interval method (configuring the benchmark value, challenge value interval and corresponding score), the threshold method (configuring the indicator threshold and corresponding score), the threshold equal height method (configuring a single indicator value and corresponding score), and the interval equal height method (configuring the value interval and corresponding score).

[0083] The evaluation system's weight configuration allows users to select indicators with pre-configured scoring rules and configure their weights across each dimension of the evaluation system. The system will calculate the score for each indicator based on the evaluation rules and then calculate the final total score for the indicator system based on its weights.

[0084] In other embodiments, the self-intelligent network service rule decoupling method of the present invention can also utilize D3 technology to intelligently generate decision trees.

[0085] Decision trees are a highly interpretable strategy analysis tool. Essentially, a decision tree is a collection of IF-THEN rules, which align closely with human decision-making habits, making them highly interpretable. Visualizing decision tree models can more effectively help us analyze and solve problems.

[0086] The rule combination in a decision tree model is represented in the form of a tree. The path from the root node to each leaf node constitutes a rule, the features of the intermediate nodes on the path correspond to the conditions of the specific rule, and each leaf node represents the decision result. At the same time, this set of rules has the property of mutual exclusion and completeness, that is, each instance is covered by one and only one path or one rule.

[0087] The CART (Classification and Regression Tree) algorithm is used to solve classification and regression problems. The Gini coefficient is used for feature selection; a smaller Gini coefficient indicates lower impurity and better features. For classification problems, node impurity is measured using the Gini index, and node splitting is evaluated using the Gini index decrease value. For regression problems, node impurity is measured using the variance of the target features, and node splitting is evaluated using the variance decrease value. The algorithm supports handling continuous and missing values.

[0088] The above embodiments provide a method for decoupling service rules in an intelligent network. Based on a rule engine, it implements rule decoupling configuration for general scenarios of intelligent communication networks, and can achieve the following beneficial effects:

[0089] 1) Low-code development of business processes, shortening the business function implementation cycle: Low-code development helps innovative businesses go live quickly. A SQL-based "low-code development" model is built, allowing complex business rules to be quickly implemented without coding through page configuration. Furthermore, the rule engine extracts complex business logic from the business code, significantly reducing the difficulty of implementing business logic. At the same time, the excellent business rule designer provided by the rule engine makes dynamic business rules maintainable and easy to maintain.

[0090] 2) Intelligent rule matching in the rule base improves rule reusability: After defining the rule files according to business requirements, all relevant rule files can be packaged to generate a rule base. The system reads the configuration module to obtain various configuration information from the computer; the business module automatically identifies and calculates the web application based on the read configuration information.

[0091] 3) Multi-scenario business rule orchestration for agile support of business needs: It utilizes rule engine tools to provide eight types of business rule design tools, including rule sets, decision tables, cross-decision tables (decision matrices), decision trees, scorecards, complex scorecards, and rule flows, meeting the needs of complex business rule design from various perspectives. Based on open-source component code, it extends and introduces Java rule engine technology for personalized modifications, creating multi-scenario business rule orchestration capabilities for intelligent networks, alarm monitoring, quality difference analysis, quality assessment, and network element health.

[0092] 4) Improve system stability and reduce development costs: Reduce unnecessary system updates. Separate the business decision-making logic of business decision-makers from the technical decisions of application developers, effectively improving the maintainability of code that implements complex logic. Based on the rule engine, manage business rules under various platforms and thematic applications, changing the dilemma of redundant resource construction and application development, greatly improving R&D efficiency, and effectively reducing human development costs.

[0093] On the other hand, the present invention also provides a self-intelligent network service rule decoupling device. The self-intelligent network service rule decoupling device provided by the present invention will be described below. The self-intelligent network service rule decoupling device described below and the self-intelligent network service rule decoupling method described above can be referred to in correspondence with each other.

[0094] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of the self-intelligent network service rule decoupling device provided in an embodiment of the present invention. In this embodiment, the self-intelligent network service rule decoupling device may include an acquisition module 410, an extraction module 420, a rule engine configuration module 430, and a management module 440.

[0095] The acquisition module 410 is used to retrieve network data from the database.

[0096] The extraction module 420 is used to extract existing indicator management rules from the database to obtain an initial indicator set.

[0097] The rule engine configuration module 430 is used to configure the rule engine based on network data and an initial indicator set to obtain a new rule engine; wherein the new rule engine includes at least one of demand prediction rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules.

[0098] Management module 440 is used to manage the database according to the new rules engine.

[0099] In some embodiments, the new rule engine includes demand forecasting rules; the rule engine configuration module 430 can specifically be used for:

[0100] The initial prediction model, the initial predicted value output by the initial prediction model, and the initial warning threshold of the initial predicted value are determined based on network data and the initial indicator set. The parameters of the initial prediction model are configured using the training model to obtain a new prediction model, a new predicted value, and a new warning threshold. Demand prediction rules are determined based on the new prediction model, the new predicted value, and the new warning threshold.

[0101] In some embodiments, the new rule engine includes quality issue identification rules; the rule engine configuration module 430 can specifically be used for:

[0102] An initial problem identification model is determined based on network data and an initial indicator set; the indicator thresholds, rules, and data periods of the initial problem identification model are configured to achieve quality problem identification, thus obtaining the problem identification model; the problem identification model is used to output quality problem alarms and / or poor quality results; and quality problem identification rules are obtained based on the problem identification model.

[0103] In some embodiments, the new rule engine includes quality issue location rules; the rule engine configuration module 430 can specifically be used for:

[0104] When quality issues are identified based on network data and an initial set of indicators, a problem localization process is generated according to the localization process to obtain quality issue localization rules. The localization process is obtained in the following way: a presentation node is added to the localization process, one or more indicators are selected under each node, and the rule algorithm under the selected indicators is configured. The rule algorithm of each node is configured separately. Branches are defined for the algorithm results, and different branches point to different next-level nodes, thus forming the localization process.

[0105] In some embodiments, the new rule engine includes quality optimization verification rules; the rule engine configuration module 430 can specifically be used for:

[0106] Quality optimization verification rules are obtained based on network data and an initial indicator set. These quality optimization verification rules are used to process and verify the automatic association of optimized verification rules with already processed problem work orders, and the verification results are obtained.

[0107] In some embodiments, the new rule engine includes quality assessment rules; the rule engine configuration module 430 can specifically be used for:

[0108] Configure various indicator evaluation systems based on network data and initial indicator sets; determine statistical analysis of data in each dimension based on various indicator evaluation systems, obtain analysis results, and construct quality evaluation rules; the analysis results include at least one of score ranking, poor quality indicators, and indicator trends.

[0109] The present invention provides an intelligent network service rule decoupling device, comprising: an acquisition module for acquiring network data from a database; an extraction module for extracting existing indicator management rules from the database to obtain an initial indicator set; a rule engine configuration module for configuring the rule engine based on the network data and the initial indicator set to obtain a new rule engine; wherein the new rule engine includes at least one of demand prediction rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules; and a management module for managing the database according to the new rule engine. Through the above method, the present invention can extract existing rules from the database and establish a new rule engine, achieving rule decoupling and flexible configuration, solving the current tight coupling between network operation and maintenance rule algorithms and scenarios, and adapting to the intelligent development of network operation and maintenance.

[0110] On the other hand, embodiments of the present invention also provide an electronic device, please refer to... Figure 5 , Figure 5 This is a schematic diagram of the physical structure of the electronic device provided in the embodiments of the present invention, such as... Figure 5 As shown, the electronic device may include: a memory 520, a processor 510, and a computer program stored in the memory 520 and executable on the processor 510. When the processor 510 executes the program, it implements the self-intelligent network service rule decoupling method provided by the above methods.

[0111] Optionally, the electronic device may further include a communication bus 530 and a communication interface 540, wherein the processor 510, communication interface 540, and memory 520 communicate with each other via the communication bus 530. The processor 510 can call a computer program in the memory 520 to execute a self-intelligent network service rule decoupling method, which may include:

[0112] Retrieve network data from the database; extract existing indicator management rules from the database to obtain an initial indicator set; configure the rule engine based on the network data and the initial indicator set to obtain a new rule engine; the new rule engine includes at least one of demand forecasting rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules; manage the database based on the new rule engine.

[0113] Furthermore, the logical instructions in the aforementioned memory 520 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the self-intelligent network service rule decoupling method provided by the above methods. The steps and principles of the method have been described in detail in the above methods and will not be repeated here.

[0115] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the self-intelligent network service rule decoupling method provided by the above methods. The steps and principles of the method have been described in detail in the above methods and will not be repeated here.

[0116] Non-transitory computer-readable storage media can be any available medium or data storage device that can be accessed by a processor, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0117] In summary, the intelligent network service rule decoupling method, apparatus, device, medium, and product provided by this invention include the following steps: obtaining network data from a database; extracting existing indicator management rules from the database to obtain an initial indicator set; configuring a rule engine based on the network data and the initial indicator set to obtain a new rule engine; wherein the new rule engine includes at least one of demand prediction rules, quality problem identification rules, quality problem location rules, quality optimization verification rules, and quality assessment rules; and managing the database according to the new rule engine. Through this method, this invention can extract existing rules from the database and establish a new rule engine, achieving rule decoupling and flexible configuration, solving the current tight coupling between network operation and maintenance rule algorithms and scenarios, and adapting to the intelligent development of network operation and maintenance.

[0118] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0119] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A self-aware network service rule decoupling method, characterized in that, The method comprises the following steps: obtaining network data from a database; extracting existing index management rules from the database to obtain an initial index set; configuring a rule engine according to the network data and the initial index set to obtain a new rule engine; wherein the new rule engine comprises demand prediction rules, quality problem identification rules, quality problem positioning rules, quality optimization verification rules and quality evaluation rules; managing the database according to the new rule engine; the step of configuring a rule engine according to the network data and the initial index set to obtain a new rule engine comprises: determining an initial prediction model, an initial prediction value output by the initial prediction model and an initial early warning threshold of the initial prediction value according to the network data and the initial index set; configuring parameters of the initial prediction model by using a training model to obtain a new prediction model, a new prediction value and a new early warning threshold; determining the demand prediction rules based on the new prediction model, the new prediction value and the new early warning threshold; the step of configuring a rule engine according to the network data and the initial index set to obtain a new rule engine comprises: determining an initial problem identification model according to the network data and the initial index set; configuring index thresholds, rules and data cycles of the initial problem identification model to realize quality problem identification to obtain a problem identification model; the problem identification model is used to output quality problem alarms and / or quality defect results; obtaining the quality problem identification rules according to the problem identification model; the step of configuring a rule engine according to the network data and the initial index set to obtain a new rule engine comprises: when determining a quality problem according to the network data and the initial index set, generating a problem positioning process according to a positioning process to obtain the quality problem positioning rules; wherein the positioning process is obtained based on the following way: adding presentation nodes to the positioning process, selecting one or more indexes under each node, and configuring rule algorithms under the node using the selected indexes; wherein the rule algorithms of each node are configured separately; defining branches for algorithm results, and different branches pointing to different next-level nodes to form a positioning process.

2. The self-sufficient network service rule decoupling method according to claim 1, characterized in that, the step of configuring a rule engine according to the network data and the initial index set to obtain a new rule engine comprises: obtaining the quality optimization verification rules according to the network data and the initial index set; wherein the quality optimization verification rules are used to automatically associate optimization verification rules for processed problem work orders to perform verification to obtain verification results.

3. The self-sufficient network service rule decoupling method of claim 1, wherein, the step of configuring a rule engine according to the network data and the initial index set to obtain a new rule engine comprises: configuring various index evaluation systems according to the network data and the initial index set; determining dimensional data statistical analysis according to the various index evaluation systems to obtain analysis results to build the quality evaluation rules; wherein the analysis results comprise at least one of score ranking, quality defect indexes and index trends.

4. A self-sovereign network service rule decoupling apparatus, characterized by, The self-intelligent network service rule decoupling device comprises: an acquisition module configured to acquire network data from a database; an extraction module configured to extract existing index management rules from the database to obtain an initial index set; a rule engine configuration module configured to perform rule engine configuration according to the network data and the initial index set to obtain a new rule engine, wherein the new rule engine comprises demand prediction rules, quality problem identification rules, quality problem positioning rules, quality optimization verification rules, and quality evaluation rules; a management module configured to manage the database according to the new rule engine.

5. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the self-intelligent network service rule decoupling method according to any one of claims 1 to 3. 6.A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the self-intelligent network service rule decoupling method according to any one of claims 1 to 3.

7. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the self-intelligent network service rule decoupling method according to any one of claims 1 to 3.

Images