Telecommunication service integrated automatic auditing method and device and readable storage medium

Abstract

The invention provides a telecommunication service integrated automatic auditing method and device and a readable storage medium, and the method specifically comprises the steps: obtaining to-be-audited original data; performing data processing on the original data to obtain preprocessed data; auditing the preprocessed data to obtain auditing abnormal data; and performing feature dimension reduction and classification identification on the auditing abnormal data based on principal component analysis and a support vector machine to obtain an abnormal problem type. According to the telecommunication service integrated automatic auditing method provided by the invention, the principal component analysis is combined with the support vector machine, feature dimension reduction and classification identification are performed on the auditing abnormal data, and automatic auditing and positioning of the abnormal data are realized, so that service data auditing is more accurate and efficient.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a method, device and readable storage medium for integrated automatic auditing of telecommunication services. Background Art

[0002] Business data audit refers to the process of checking, verifying and reviewing the data generated in the business activities of an enterprise or organization. Its purpose is to ensure the accuracy, completeness and compliance of the data, thereby ensuring the transparency and efficiency of the enterprise's operations.

[0003] At present, there are several data auditing methods, such as: (1) Sampling audit: a portion of a large amount of data is selected for inspection. (2) Comprehensive audit: a comprehensive inspection of all relevant data.

[0004] However, current auditing methods generally have problems such as large manual workload and low accuracy. Summary of the invention

[0005] The technical problem to be solved by the present application is to provide a method, device and readable storage medium for integrated automatic audit of telecommunication services in view of the above-mentioned deficiencies in the prior art, so as to solve the problems existing in the prior art.

[0006] In a first aspect, the present application provides a method for integrated automatic auditing of telecommunication services, the method comprising:

[0007] S1. Obtain the original data to be audited;

[0008] S2, processing the original data to obtain preprocessed data;

[0009] S3, auditing the preprocessed data to obtain audit abnormal data;

[0010] S4. Based on principal component analysis and support vector machine, feature dimension reduction and classification identification are performed on the audit abnormal data to obtain the abnormal problem type.

[0011] In some embodiments, S4 includes:

[0012] Performing dimensionality reduction processing on the audit abnormal data through principal component analysis to obtain dimensionality reduced abnormal data;

[0013] The reduced-dimensional abnormal data is classified and identified by a support vector machine to obtain the abnormal problem type.

[0014] In some embodiments, S3 includes:

[0015] The pre-processed data is audited through a relational data model to obtain audit exception data, wherein the relational data model stores audit rules.

[0016] In some embodiments, S3 includes:

[0017] If the original data is real-time streaming data, it is audited and processed through Hadoop and Flink;

[0018] If the original data is non-real-time streaming data, it is audited and processed through Hadoop and Spark.

[0019] In some embodiments, in S2, the data processing includes at least one of data cleaning, filtering, labeling, and precipitation.

[0020] In some embodiments, in S1, the original data is obtained through data collection, and the data collection method includes at least one of FTP / SFTP, SHELL, and dataX.

[0021] In some embodiments, it also includes:

[0022] Generate corresponding rectification task work orders based on the abnormal problem types obtained and send them to the corresponding departments.

[0023] In a second aspect, the present application provides a telecommunications service integrated automatic audit device, the device comprising:

[0024] A data acquisition module, which is configured to acquire the original data to be audited;

[0025] A preprocessing module, which is configured to process the raw data to obtain preprocessed data;

[0026] A data audit module, which is configured to audit the preprocessed data to obtain audit abnormal data;

[0027] The dimension reduction classification module is configured to perform feature dimension reduction and classification identification on the audit abnormal data based on principal component analysis and support vector machine to obtain the abnormal problem type.

[0028] In a third aspect, the present application provides an integrated automatic audit device for telecommunication services, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the integrated automatic audit method for telecommunication services described in the first aspect above.

[0029] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the integrated automatic audit method for telecommunication services described in the first aspect above is implemented.

[0030] The present application provides an integrated automatic audit method, device and readable storage medium for telecommunications services. Specifically, the method includes: obtaining original data to be audited; performing data processing on the original data to obtain pre-processed data; auditing the pre-processed data to obtain audit abnormality data; and performing feature dimension reduction and classification identification on the audit abnormality data based on principal component analysis and support vector machine to obtain abnormal problem types. The present application provides an integrated automatic audit method for telecommunication services. The present application supports unified collection of multi-mode and multi-source data, provides multiple collection methods such as FTP / SFTP, SHELL, dataX, etc., to meet the needs of audit data collection capabilities; provides FLINK cluster real-time streaming data processing capabilities; can support real-time audit functions; can support real-time interaction with the headquarters audit system; introduces AI word segmentation technology, and maintenance personnel configure abnormal problem processing rules based on experience, and the system automatically calls related processing procedures; completes the full life cycle automated audit monitoring of telecommunication services, and realizes a complete set of telecommunication business audit capabilities such as business acceptance, activation, guarantee, and customer service; uses principal component analysis combined with support vector machines to perform feature dimensionality reduction on audit abnormal data, and classifies and identifies them, to realize automatic audit positioning of abnormal data, thereby making business data audit more accurate and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0032] Figure 1 A schematic diagram of the technical architecture of the integrated automatic audit method for telecommunication services provided in the embodiment of the present application;

[0033] Figure 2 A schematic diagram of the application deployment of the integrated automatic audit method for telecommunication services provided in an embodiment of the present application;

[0034] Figure 3 A schematic diagram of a data audit system for a telecommunications service integrated automatic audit method provided in an embodiment of the present application;

[0035] Figure 4 A schematic diagram of a data audit system provided in an embodiment of the present application having a data repair function;

[0036] Figure 5 A schematic diagram of the work order flow management process of the data audit system provided in the embodiment of the present application;

[0037] Figure 6 A schematic diagram of an integrated automatic audit method for telecommunication services provided in an embodiment of the present application;

[0038] Figure 7A schematic diagram of the business compliance audit function provided in an embodiment of the present application;

[0039] Figure 8 A schematic diagram of the structure of an integrated automatic audit device for telecommunication services provided in an embodiment of the present application;

[0040] Fig. 9 A schematic diagram of the structure of another integrated automatic audit device for telecommunication services provided in an embodiment of the present application.

[0041] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0042] In order to enable those skilled in the art to better understand the technical solution of the present application, the implementation mode of the present application will be further described in detail below with reference to the accompanying drawings.

[0043] It should be understood that the specific embodiments and drawings described herein are only used to explain the present application, rather than to limit the present application.

[0044] It can be understood that, in the absence of conflict, the various embodiments in the present application and the various features in the embodiments can be combined with each other.

[0045] It can be understood that, for the convenience of description, the drawings of the present application only show the parts related to the present application, while the parts unrelated to the present application are not shown in the drawings.

[0046] It can be understood that each unit and module involved in the embodiments of the present application may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.

[0047] It can be understood that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0048] It is understandable that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present application may occur in an order different from that marked in the drawings.

[0049] It is understood that the flowcharts and block diagrams of the present application illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present application. Among them, each box in the flowchart or block diagram may represent a unit, module, program segment, code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or by a combination of hardware and computer instructions.

[0050] It can be understood that the units and modules involved in the embodiments of the present application can be implemented by software or hardware, for example, the units and modules can be located in a processor.

[0051] At present, the shortcomings of existing technologies include: single audit business type, large manual workload, low accuracy, inability to support abnormal modifications while business auditing, inability to dispatch audit tasks between systems, and difficulty in configuring audit indicators.

[0052] Based on the above shortcomings, the main ideas of this application are:

[0053] (1) Continuously expand automated audit points to achieve integrated and automated auditing of telecommunications services;

[0054] (2) Audit control must effectively play an important role in connecting the upper and lower levels and opening up horizontal and vertical data sources. In terms of audit capability provision, it is necessary to more flexibly implement service-driven data input and output;

[0055] (3) Improve the closed-loop management of business and the work order transfer function, and truly establish an effective audit system that is fully automated, coordinated and unified within the internal and inter-system processes;

[0056] (4) Automated audit task configuration, support for optimized configuration ideas and interfaces to reduce configuration difficulty, and launch a simplified version for front-line auditors in the market to lower the user threshold;

[0057] (5) Upgrade the audit system to the cloud platform of Tiangong based on Hadoop+spark technology architecture to solve the shortcomings of the system in terms of expansion, processing performance, and information sharing;

[0058] (6) Provide real-time audit computing capabilities to improve audit business response speed and processing capabilities;

[0059] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0060] The present application provides an integrated automatic audit method for telecommunication services. The working process of the method can be implemented by electronic devices, such as computers, handheld smart terminals, etc. For ease of explanation, the embodiments of the present application are described with the method execution subject being a computer.

[0061] Figure 1 A schematic diagram of the technical architecture of the integrated automatic audit method for telecommunication services provided in the embodiment of the present application is shown in FIG. Figure 1 As shown in the figure, the technical architecture is roughly divided into six parts: data collection, data calculation and storage, data services, application services, data management and system management, among which:

[0062] Data collection: supports unified collection of multi-mode and multi-source data, and provides multiple collection methods such as FTP / SFTP, SHELL, dataX, etc. to meet the needs of audit data collection capabilities.

[0063] Data computing and storage: It adopts a mature hybrid storage architecture, provides real-time stream processing and batch processing capabilities, and meets the data computing and storage requirements of different business scenarios.

[0064] Data service: Provides component capabilities for various methods such as data exchange and data sharing involved in various data sharing processes.

[0065] Application service: Adopt the current mainstream front-end service technology components to meet the front-end and audit application and display needs.

[0066] Data management: Adopting a microservice architecture, it provides relevant technical capabilities such as data development, data governance, model training, and data exploration to meet the platform's needs for data management.

[0067] System management: Provides security, single sign-on, microservices and other components to meet the platform's needs for system management and operation and maintenance.

[0068] Figure 2 A schematic diagram of the application deployment of the integrated automatic audit method for telecommunication services provided in the embodiment of the present application is shown in FIG. Figure 2 As shown, the Web application service layer is deployed on Tiangong, and the underlying application service layer is deployed in the system.

[0069] Figure 3 A schematic diagram of a data audit system for a telecommunications service integrated automatic audit method provided in an embodiment of the present application, such as Figure 3As shown in the figure, the entire framework is divided into five layers: data layer, basic component layer, business component layer, presentation layer, and business process layer. The basic component layer and the business component layer implement the core business logic, and can also be collectively referred to as the business logic layer. The framework architecture of the telecommunications billing data audit system has a clear hierarchical relationship. The implementation of the functions of the upper-level components requires the calling of the lower-level components (the arrows between the component levels in the figure indicate the calling relationship between the components between the layers). The lower-level components provide the calling interface for the upper layer. The upper-level components do not need to understand the internal implementation details of the lower-level components, but only need to call the clearly defined interfaces provided by the lower-level components to realize their own functions. In the actual system development process, the top-level system layer can also directly call the lower-level components without relying on the hierarchical relationship (the light gray arrow pointing to the system layer in the figure indicates the direct calling relationship between the system layer and the lower-level components), thereby realizing component-level software reuse.

[0070] In this application, the data model of the data audit system adopts a relational data model to store the audit data, audit rules, database metadata of the business support system, and management information of the system required in the audit system. The main data model contents in the data audit system include:

[0071] ①Business support system metadata storage table (Bossmetadata)

[0072] The business support system metadata storage table Boss_metadata stores various business support system table structure metadata, which can be used for the definition, interpretation, and analysis of audit rules. Audit rules are calculated based on audit indicators. When defining audit indicators, it is necessary to use the business support system metadata to obtain the corresponding basic data from the business support system for processing.

[0073] ②Data entity (Boss_data)

[0074] The data entity table Boss data is used to store various business source data involved in the audit rules. It is usually obtained by processing the basic data in the support system, such as aggregation, classification, and averaging.

[0075] ③Audit rules table (Audit_rules)

[0076] The audit rule table defines the audit rules for various types of audits, including the audit calculation rules for the data entities involved in the audit rules.

[0077] ④Audit result table (Audit_value)

[0078] The audit rule table is used to store the result data of various audit services.

[0079] ⑤Indicator threshold table (Audit threshold)

[0080] The indicator threshold monitoring in the monitoring system is mainly used to audit the rationality of some indicator values. The indicator threshold table defines the alarm thresholds of these indicators that need to be monitored. For example, the account balance of prepaid users is generally greater than 10 yuan and less than 500 yuan.

[0081] ⑥System user table (Audit_user)

[0082] All user information for accessing the system, including basic attributes and roles.

[0083] ⑦Audit log table (Audit_log)

[0084] The audit log table stores the audit history of audits performed according to audit rules and the monitoring history of threshold monitoring, including the executed audit rules, the time when the audit behavior occurred, and the results.

[0085] In this application, the data model is designed to have the function of audit data analysis. Specifically, the audit data is analyzed based on SPARK+Hadoop and Hadoop+flink algorithms. After the original data of the peripheral system is loaded into the audit system, the system generates audit analysis data through the data preprocessing module.

[0086] Data source: Provides various data sources that need to be processed for the audit system.

[0087] Data processing: perform data cleaning, filtering, labeling, sedimentation and other tasks on the collected data to facilitate subsequent data processing.

[0088] Data processing: includes two types of data processing capabilities: ① offline batch data processing, using hadoop+spark big data processing; ② real-time streaming data processing, using hadoop+flink big data processing.

[0089] Self-service reporting: Through a series of self-service configurations at the front desk, data collection and processing are used to obtain visual reports.

[0090] Automation of operation and maintenance: For various data repair scenarios that require manual operation and maintenance, automated data repair can be achieved by calling the repair platform tools.

[0091] Audit asset library: collects and summarizes various types of knowledge generated during the audit process to form valuable information.

[0092] In this application, the data audit system of the integrated automatic audit method for telecommunication services has a data repair function. Figure 4 A schematic diagram of a data audit system provided in an embodiment of the present application having a data repair function, such as Figure 4As shown, the system provides a repair platform function, which can register repair scenarios infinitely. According to the requirements of the Patching Platform, write the repair SQL and register it in the repair scenario. Instantiate the repair conditions, call the data repair platform interface through the repair process, and repair the data. After the data repair is completed, it supports real-time collection of the repaired data and analyzes whether the repaired data meets the requirements.

[0093] In this application, the data audit system of the integrated automatic audit method for telecommunications services has the function of configuring audit tasks, specifically, the functions of adding, deleting, modifying, and checking audit points and exporting query results. The prerequisites include: creating the dimension table and table field definitions required for audit point configuration. When uploading audit data to the dimension table required for audit point configuration, if the audit point configuration selection fields involve multiple tables (≥2), it is necessary to configure the relationship between the dimension tables in advance.

[0094] In this application, the data audit system of the integrated automatic audit method for telecommunications services has the function of audit work order circulation.

[0095] Figure 5 A schematic diagram of the work order flow management process of the data audit system provided in the embodiment of the present application, such as Figure 5 As shown in the figure, the audit system has four levels of collaborative work order processes at the headquarters, provinces, cities, districts and counties, realizing data dual communication. During the work order circulation process, the data comparison system automatically triggers the task, automatically collects and compares data to produce difference results, and the management personnel of the telecommunications company confirm the correctness and effectiveness of the data differences analyzed by the system, and then submits them to the business department. The business department distributes the difference data results to the information processing center and issues data rectification task orders. Different work orders are generated according to the difference results, assigned to different task types, and distributed to relevant departments and counties for processing. After each department completes the work order, the information processing center will fill in the results of the data rectification and reply to the rectification status of the task order. The provincial data maintenance department confirms the distribution of the difference data, cleans the data, and automatically rectify the data through the access of the CRM system. The results of the data rectification are filled in and the task order is replied to the business department. If there is a rectification error, it will be transferred to manual work. Finally, the business department archives the task orders returned by the branch and provincial data maintenance departments, and closes the task order.

[0096] Figure 6 A schematic diagram of the integrated automatic audit method for telecommunication services provided in the embodiment of the present application is shown in FIG. Figure 6 As shown, the present application provides a method for automatic auditing of integrated telecommunication services based on the data auditing system of the above-mentioned method for automatic auditing of integrated telecommunication services, and the method includes S1-S4, which are as follows:

[0097] S1. Obtain the original data to be audited;

[0098] In some embodiments, in S1, the original data is obtained through data collection, and the data collection method includes at least one of FTP / SFTP, SHELL, and dataX.

[0099] Among them, FTP (File Transfer Protocol) is a standard protocol for transferring files on the Internet. It is based on the client-server model and allows users to transfer files from one computer to another via the Internet. FTP does not encrypt data when transferring, so the security is relatively low.

[0100] SFTP (Secure File Transfer Protocol) is a secure version of FTP. It uses SSH (Secure Shell) encrypted tunnel when transferring files to ensure the security of data transmission. SFTP encrypts data during file transfer to prevent data from being stolen or tampered with.

[0101] SHELL usually refers to the command line interface (CLI) of the operating system, which allows users to execute programs or access system resources by entering commands. In terms of data collection, SHELL is often used to execute scripts that can automatically extract data from databases, log files, or other data sources. For example, you can use bash scripts in Linux systems to process and collect data through specific commands (such as grep, awk, sed, etc.).

[0102] dataX is an open source data synchronization tool from Alibaba, which is mainly used to solve the problem of synchronizing large amounts of data. dataX supports data exchange between multiple data sources, including relational databases (such as MySQL, Oracle, SQL Server, etc.), non-relational databases (such as MongoDB, HBase, etc.), big data computing systems (such as Hadoop Hive, Spark, etc.) and file systems (such as FTP, HDFS, etc.).

[0103] DataX supports data transmission between different data sources by implementing different Readers (reading modules) and Writers (writing modules). Users can configure task scripts in JSON format, specify information such as data source, target, field mapping, etc., to achieve full or incremental data synchronization.

[0104] S2, processing the original data to obtain preprocessed data;

[0105] In some embodiments, in S2, the data processing includes at least one of data cleaning, filtering, labeling, and precipitation.

[0106] Specifically, data cleaning refers to the process of identifying and correcting (or deleting) erroneous, duplicate, incomplete, inconsistent or abnormal records in a data set.

[0107] Data filtering refers to filtering out relevant data subsets from a data set based on specific criteria or conditions. This process helps focus analysis or processing on the most interesting or relevant data.

[0108] Data labeling refers to the process of assigning one or more labels to each element in a dataset. These labels are often used in machine learning tasks as a reference for training models.

[0109] Data Sedimentation usually refers to storing cleaned, filtered and labeled data in a database, data warehouse or other data storage system for long-term preservation and use.

[0110] S3, auditing the preprocessed data to obtain audit abnormal data;

[0111] In some embodiments, S3 includes: auditing the preprocessed data through a relational data model to obtain audit exception data, wherein the relational data model stores audit rules. For example, Figure 7 A schematic diagram of the business compliance audit function provided in an embodiment of the present application.

[0112] In some embodiments, S3 includes: if the original data is real-time streaming data, audit processing is performed through hadoop and flink; if the original data is non-real-time streaming data, audit processing is performed through hadoop and spark.

[0113] S4. Based on principal component analysis and support vector machine, feature dimension reduction and classification identification are performed on the audit abnormal data to obtain the abnormal problem type.

[0114] In this step, principal component analysis is combined with support vector machine to reduce the dimension of the audit abnormal data and classify and identify it, so as to realize automatic audit and location of abnormal data.

[0115] Among them, Principal Component Analysis (PCA) is a statistical method that transforms a set of possibly correlated variables into a set of linearly uncorrelated variables through orthogonal transformation. This set of variables is called principal components. The main purpose of PCA is to extract the most important features from high-dimensional data, simplify the complexity of the data by reducing the dimensionality, and retain the important information in the original data as much as possible.

[0116] Support Vector Machine (SVM) is a supervised learning algorithm for classification and regression analysis. SVM is very popular in pattern recognition, classification, and regression analysis because it has strong generalization ability and can perform well even with a small number of training samples. The basic model of SVM is to find a decision boundary in the feature space that can separate different categories of data as best as possible. This boundary is called the maximum margin hyperplane.

[0117] In some embodiments, S4 includes: performing dimensionality reduction processing on the audit abnormal data through principal component analysis to obtain reduced-dimensional abnormal data; performing classification and identification processing on the reduced-dimensional abnormal data through a support vector machine to obtain abnormal problem types.

[0118] Among them, for the dimensionality reduction of abnormal data by principal component analysis, in machine learning, features can be represented by numbers, samples can be represented by vectors composed of numbers, and sample sets can be represented by matrices. The dimension here refers to the length of the vector, or the number of features of the sample. Because high-dimensional data is not conducive to calculation and storage, dimensionality reduction is required. Dimensionality reduction is to reduce high-dimensional sample data to low dimensions. The goal of dimensionality reduction method research is to maintain some characteristics of the original sample during the dimensionality reduction process, or to make the reduced-dimensional data have some better properties.

[0119] For ease of explanation, let’s start with a few symbols that will be used in this article. n ]∈R D×n It represents a matrix composed of n original data of D dimension, with Y = [y1, y2, ..., y n ]∈R d×n Represents the matrix composed of points in the d-dimensional space after dimensionality reduction, W∈R D×d is the projection matrix and I is the identity matrix.

[0120] PCA completes the dimensionality reduction task by finding a projection matrix, that is, Y = W T X, Y∈R d×n is the matrix composed of each sample after dimensionality reduction, d is the number of dimensions after dimensionality reduction, requiring W∈R D×dis the unit projection matrix, the modulus of each column is 1, and the inner values ​​of different columns are 0, that is, W T W = I. The optimization goal of PCA is to maximize the projection variance. It hopes that each sample will be as dispersed as possible after projection, and uses variance to measure the degree of dispersion. The expression of PCA is as follows:

[0121]

[0122] Using the Lagrange multiplier method to solve, we can get:

[0123] L(W,λ)=tr(W T XX T W)+tr[λ(IW T W)]

[0124] Let the partial derivative of the above formula be 0, that is:

[0125]

[0126] From the above formula, we can get:

[0127]

[0128] From this we can see that each column of W is XX T is an eigenvector of , the diagonal element corresponding to λ is the corresponding eigenvalue, and then substituting the above formula into:

[0129] tr(W T XX T W)=tr(W T Wλ)=tr(λ)

[0130] For the support vector machine to classify abnormal data, support vector machine classification refers to finding a hyperplane in a feature space that maximizes the distance between two categories. For a two-classification problem, given a sample set {x i ,y i}, x i ∈R n ,y i ∈{±1} is the class label, i=1,2,...,n is the number of samples. Its classification function is set as:

[0131]

[0132] In the above formula, α i is a scalar constant, b is the classification threshold, k(x i ,x j ) is the kernel function. On this basis, the α in the above classification surface function is calculated according to the above formula i The optimal solution set is:

[0133]

[0134] In the above formula, C is the upper limit set by the Lagrange multiplier, C>0. In the optimal solution set obtained, select α i >0 (i=1,2,...,s,s<n) as the corresponding samples, so the decision function of the constructed recognizer is:

[0135]

[0136] Classify abnormal data and locate the type of problem.

[0137] In some embodiments, it also includes: generating a corresponding rectification task work order according to the obtained abnormal problem type, and issuing it to the corresponding department.

[0138] The present application provides an integrated automatic audit method for telecommunication services. The present application supports unified collection of multi-mode and multi-source data, provides multiple collection methods such as FTP / SFTP, SHELL, dataX, etc., to meet the needs of audit data collection capabilities; provides FLINK cluster real-time streaming data processing capabilities; can support real-time audit functions; can support real-time interaction with the headquarters audit system; introduces AI word segmentation technology, and maintenance personnel configure abnormal problem processing rules based on experience, and the system automatically calls related processing procedures; completes the full life cycle automated audit monitoring of telecommunication services, and realizes a complete set of telecommunication business audit capabilities such as business acceptance, activation, guarantee, and customer service; uses principal component analysis combined with support vector machines to perform feature dimensionality reduction on audit abnormal data, and classifies and identifies them, to realize automatic audit positioning of abnormal data, thereby making business data audit more accurate and efficient.

[0139] It should be understood that, although the various steps in the flowcharts in the above-described embodiments are sequentially displayed according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily to be carried out sequentially, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0140] Figure 8 A schematic diagram of a telecommunications service integrated automatic auditing device provided in an embodiment of the present application, such as Figure 8 As shown, the present application provides a telecommunication service integrated automatic auditing device, the device comprising:

[0141] A data acquisition module 11, which is configured to acquire the original data to be audited;

[0142] A preprocessing module 12, which is configured to process the raw data to obtain preprocessed data;

[0143] A data audit module 13, which is configured to audit the preprocessed data to obtain audit abnormal data;

[0144] The dimension reduction classification module 14 is configured to perform feature dimension reduction and classification identification on the audit abnormality data based on principal component analysis and support vector machine to obtain the abnormal problem type.

[0145] Regarding the limitation of the integrated automatic audit device for telecommunication services, reference may be made to the limitation of the integrated automatic audit method for telecommunication services in the above-mentioned embodiments of the present application, which will not be elaborated in detail in this embodiment.

[0146] Fig. 9 Another schematic diagram of the integrated automatic auditing device for telecommunication services provided in the embodiment of the present application is as follows Fig. 9 As shown, in some embodiments, the present application provides an integrated automatic audit device for telecommunication services, comprising a memory 22 and a processor 21, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the integrated automatic audit method for telecommunication services in the above-mentioned embodiments of the present application.

[0147] The memory is connected to the processor, the memory may be a flash memory or a read-only memory or other memory, and the processor may be a central processing unit or a single-chip microcomputer.

[0148] In some embodiments, the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the integrated automatic audit method for telecommunication services in the above-mentioned embodiments of the present application is implemented.

[0149] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, computer program modules or other data). Computer-readable storage media include, but are not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable read only memory), flash memory or other memory technology, CD-ROM (Compact Disc Read-Only Memory), digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0150] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present application, but the present application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of the present application, and these modifications and improvements are also considered to be within the scope of protection of the present application.

Claims

1. A method for automatic auditing of integrated telecommunication services, characterized in that: The method comprises: S1. Obtain the original data to be audited; S2, processing the original data to obtain preprocessed data; S3, auditing the preprocessed data to obtain audit abnormal data; S4. Based on principal component analysis and support vector machine, feature dimension reduction and classification identification are performed on the audit abnormal data to obtain the abnormal problem type.

2. The integrated automatic audit method for telecommunication services according to claim 1, characterized in that: S4, including: Performing dimensionality reduction processing on the audit abnormal data through principal component analysis to obtain dimensionality reduced abnormal data; The reduced-dimensional abnormal data is classified and identified by a support vector machine to obtain the abnormal problem type.

3. The integrated automatic audit method for telecommunication services according to claim 1, characterized in that: S3, including: The pre-processed data is audited through a relational data model to obtain audit exception data, wherein the relational data model stores audit rules.

4. The integrated automatic audit method for telecommunication services according to claim 1, characterized in that: S3, including: If the original data is real-time streaming data, it is audited and processed through Hadoop and Flink; If the original data is non-real-time streaming data, it is audited and processed through Hadoop and Spark.

5. The integrated automatic audit method for telecommunication services according to claim 1, characterized in that: In S2, the data processing includes at least one of data cleaning, filtering, labeling, and precipitation.

6. The integrated automatic audit method for telecommunication services according to claim 1, characterized in that: In S1, the original data is obtained through data collection, and the data collection method includes at least one of FTP / SFTP, SHELL, and dataX.

7. The integrated automatic audit method for telecommunication services according to any one of claims 1 to 6, characterized in that: Also includes: Generate corresponding rectification task work orders based on the abnormal problem types obtained and send them to the corresponding departments.

8. An integrated automatic audit device for telecommunication services, characterized in that: The device comprises: A data acquisition module, which is configured to acquire the original data to be audited; A preprocessing module, which is configured to process the raw data to obtain preprocessed data; A data audit module, which is configured to audit the preprocessed data to obtain audit abnormal data; The dimension reduction classification module is configured to perform feature dimension reduction and classification identification on the audit abnormal data based on principal component analysis and support vector machine to obtain the abnormal problem type.

9. An integrated automatic audit device for telecommunication services, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the integrated automatic audit method for telecommunication services as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the integrated automatic audit method for telecommunication services according to any one of claims 1 to 7 is implemented.

Images