CMTS network operation and maintenance method and device based on big data analysis and readable storage medium

Abstract

The invention relates to the technical field of computer networks, in particular to a CMTS network operation and maintenance method and device based on big data analysis and a readable storage medium, and the method comprises the following steps: establishing a data automatic scheduling and collection task, and carrying out data connection and collection through a big data platform; auditing and cleaning the collected data, and establishing a network terminal view of network resources and user services; performing multi-dimensional analysis and judgment on the user equipment by using the data analysis model, and establishing health degree data of the user equipment; performing intelligent operation and maintenance task scheduling according to a preset strategy matching rule to form task distribution data, and issuing the task distribution data to a corresponding channel; and performing tracking analysis on the execution condition of the issued task, and performing marketing and maintenance work order effect evaluation and optimization based on a task execution analysis result. According to the method and the device, the problem that fault processing cannot be timely distributed and the effective effect of the process cannot be evaluated in the network fault maintenance process in the existing network operation and maintenance technology is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer networks, and particularly to a CMTS network operation and maintenance method, device and readable storage medium based on big data analysis. Background Art

[0002] The CMTS network is a data communication system based on the Internet protocol, used to provide broadcast, video, audio and other high-speed data transmission services. The system consists of a network controller based on the Internet protocol and a synchronous optical fiber transmission system, and uses dedicated hardware and software to ensure the efficiency and reliability of data transmission. The working principle of the CMTS network is to perform filtering, forwarding and routing operations by introducing a service compliance device into the network. After the device appears, all users in the network will be automatically routed to the CMTS network, regardless of whether they are working on a wired or wireless network. Therefore, in the CMTS network, all users have the same type of service, including the same service level, service protocol and data transmission speed. The advantages of the CMTS network are mainly reflected in its high-speed data transmission, broadcast, audio and video and other media applications.

[0003] Currently, there are still a large number of CMTS network users in the field of radio and television network technology. In order to ensure the normal operation of the equipment, perform operation and maintenance on the CMTS network, and analyze and maintain the network faults of users are the keys to improving user satisfaction and service quality. The existing method of network operation and maintenance is to obtain relevant data in the network operation state through a network operation and maintenance tool, thereby generating a network operation log. When it is found that the user's network operation is abnormal, the management personnel are notified to perform manual anomaly location, that is, the management personnel manually extract the key information of the network anomaly based on the network operation log, and then locate the network problem based on the extracted key information, and finally notify the maintenance personnel to perform maintenance processing on the network. The foregoing network operation and maintenance method cannot timely dispatch the fault handling and effectively evaluate the process effect during the network fault maintenance process. During the data distribution process, personal information such as customers is involved, and there is a problem of the risk of leakage of customer personal information. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a CMTS network operation and maintenance method, device and readable storage medium based on big data analysis, so as to at least solve the problem that in the existing network operation and maintenance technology, it is impossible to timely dispatch the fault handling and effectively evaluate the process effect during the network fault maintenance process.

[0005] The present invention solves the above technical problems through the following technical means:

[0006] In a first aspect, an embodiment of the present invention provides a CMTS network operation and maintenance method based on big data analysis, including the following steps:

[0007] Establish an automatic data scheduling and collection task, and use the big data platform for data docking and collection;

[0008] Audit and clean the collected data, and establish a network terminal view of network resources and user services;

[0009] Use the data analysis model to perform multi-dimensional analysis and judgment on user equipment, and establish the health data of user equipment;

[0010] According to the preset policy matching rules, perform intelligent operation and maintenance task scheduling to form task dispatch data, and send the task dispatch data to the corresponding channels;

[0011] Track and analyze the execution status of the dispatched tasks, and evaluate and optimize the operation and maintenance work order effect based on the task execution analysis results.

[0012] Combined with the first aspect, in some embodiments, the data docking and collection includes collecting network element data of the ARRIS system, ITMS system, OSS system, BOSS system, and professional network management system, as well as collecting user equipment information and equipment performance indicators, and collecting user service information.

[0013] Combined with the first aspect, in some embodiments, the equipment performance indicators include software version, signal-to-noise ratio, downlink received level, uplink received level, uplink transmitted level, downlink error rate, uplink error rate, downlink correctable error rate, uplink correctable error rate, downlink signal-to-noise ratio, uplink signal-to-noise ratio, and uplink and downlink traffic;

[0014] The user service information includes service status, handling time, complaints, fault reports, packages, grids, addresses, terminal types, viewing, and network topology information; the user equipment information includes equipment status information, attribution region information, and equipment coding information.

[0015] Combined with the first aspect, in some embodiments, the auditing and cleaning of the collected data and establishing a network terminal view of network resources and user services includes:

[0016] Create data cleaning and auditing rules, and the data cleaning and auditing rules include service consistency, location consistency, and status consistency of equipment;

[0017] According to the data cleaning and auditing rules, find the inconsistent data between the user equipment information in the data and the equipment information recorded in the service, and eliminate the inconsistent data;

[0018] Use the collected user equipment information to associate with the user service information to form a data set with the user ID as the only index, and store it in the data warehouse.

[0019] In combination with the first aspect, in some embodiments, the multi-dimensional analysis and judgment of the user equipment by using the data analysis model to establish the health data of the user equipment includes:

[0020] Judging the operation trend of the user equipment within a certain period according to the equipment performance indicators, and analyzing the health data of the user equipment through a time series model, a decision tree model, and a collaborative filtering model;

[0021] Combining the user equipment data with relatively low health with business information to match the corresponding grid information, business information, and community manager information of the user equipment;

[0022] Solidify the analysis and judgment model into a daily customized execution data program, and calculate the health data of the user equipment according to the algorithm of the analysis and judgment model.

[0023] In combination with the first aspect, in some embodiments, the intelligent operation and maintenance task scheduling includes the following steps:

[0024] Form a policy matching library according to the pre-set business rules, and match different disposal policies and distribution channels according to the health of the user equipment;

[0025] During the task distribution process, it is necessary to provide the detailed business information and business usage of the user for front-line personnel to make business judgments;

[0026] According to different distribution channels, connect to different systems and data interfaces to form the distribution or warning of operation and maintenance tasks;

[0027] Push the matching mechanism activity of the business rules and the task data push mechanism to generate production scheduling tasks on the big data platform, and generate and push tasks every day according to this data model algorithm.

[0028] In combination with the first aspect, in some embodiments, the tracking and analysis of the execution situation of the issued tasks, and the evaluation and optimization of the operation and maintenance work order effect based on the task execution analysis results include:

[0029] Push the marketing activity content to the single-soldier system or the DingTalk system through the socket interface, and save the pushed data into the table of the Oracle database;

[0030] During the execution process, write the task execution results into the Oracle database table in real time, and feedback to the big data platform through the socket interface for update and summary;

[0031] [[ID=3,6]]Analyze according to the feedback data during the whole task execution process, display the completion progress of the whole task and the execution situation of each branch company, and generate a task execution report;

[0032] After the completion of the entire task, cooperate with business personnel and data analysis specialists to conduct a post-evaluation of the entire task and adjust and optimize the implementation of the operation and maintenance tasks.

[0033] In a second aspect, the present invention also provides a CMTS network operation and maintenance device based on big data analysis, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described in the first aspect above are implemented.

[0034] In a third aspect, the present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect above are implemented.

[0035] The CMTS network operation and maintenance method based on big data analysis of the present invention first obtains the terminal performance index data, service data, resource data, and behavior data of users; and mines and analyzes the user data information to establish a data view and a health model around the user resource system. Then, according to the requirements and preset policies on the service side, corresponding operation and maintenance activity events are determined based on the device health, and then, according to the operation and maintenance activity events, data tags are used to generate the customer groups and distribution channels corresponding to the operation and maintenance events, determine the service types that need to be operated and maintained for the user group, and then distribute them to different channels for execution. During the execution process, real-time monitoring and post-event analysis and summary of the operation and maintenance activities are carried out, and the demand positioning, policy matching, and execution deviation are dynamically corrected to achieve accurate judgment of target user faults and intelligent distribution of tasks, thereby improving the service efficiency of maintenance events. The present invention can monitor the operation and maintenance activities and conduct effective effect evaluation, and there is no risk of leakage of customer personal information during the data distribution process. Description of the Drawings

[0036] Figure 1 is a flowchart of the CMTS network operation and maintenance method based on big data analysis;

[0037] Figure 2 is a flow block diagram of the CMTS network operation and maintenance method based on big data analysis. Detailed Embodiments

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0039] In the description of the specification and claims in this document, terms such as "first" and "second" are used to distinguish different objects, rather than to describe a specific order of objects. In the description of the embodiments of this application, unless otherwise specified, the meaning of "a plurality of" refers to two or more. For example, a plurality of processing units refers to two or more processing units, and a plurality of elements refers to two or more elements, etc.

[0040] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0041] The ARRIS system is a comprehensive airdrop platform designed to simplify and enhance Web3 on-chain interactions, which addresses challenges such as long cycles, uncertainties, and traffic creation in interactive airdrop projects. The ITMS system (Integrated Terminal Management System) is a technology platform for network terminal device management, mainly applied to scenarios such as home gateways and optical network devices. The OSS system (Operation Support System) is the core platform for telecommunications operators to monitor, control, analyze, and manage communication networks, integrating functions such as network management, billing, and customer service to achieve multi-service automated operation. The BOSS system is the abbreviation of the Business Operation Support System, and OSS / BSS is an integrated and information resource-sharing support system for telecommunications operators.

[0042] Such as Figure 1 and Figure 2 As shown, the big data analysis-based CMTS network operation and maintenance method in this embodiment mainly includes automatic data collection and scheduling, service auditing, data modeling analysis, intelligent operation and maintenance task distribution, and operation and maintenance effect evaluation and optimization, specifically including the following steps:

[0043] Step 110: Establish an automatic data scheduling and collection task, and use the big data platform for data docking and collection;

[0044] Step 120: Audit and clean the collected data, and establish a network terminal view of network resources and user services;

[0045] Step 130: Use the data analysis model to perform multi-dimensional analysis and judgment on user equipment, and establish the health data of user equipment;

[0046] Step 140: Perform intelligent operation and maintenance task scheduling according to the preset policy matching rules to form task dispatch data, and send the task dispatch data to the corresponding channels.

[0047] Step 150: Track and analyze the execution status of the dispatched tasks, and evaluate and optimize the operation and maintenance work order effect based on the task execution analysis results.

[0048] To better understand the above technical solution, the above technical solution will be described in detail below in combination with the accompanying drawings of the specification and specific implementation manners.

[0049] In step 110, establish an automatic data scheduling and collection task, and use the big data platform to connect and collect relevant data resources including but not limited to the ARRIS system, ITMS system, OSS system, BOSS system, and professional network management system, and establish a data resource ground with the device MAC as the primary key. The data connection and collection include but not limited to collecting network element data of the ARRIS system, ITMS system, OSS system, BOSS system, and professional network management system, as well as collecting user device information, device performance indicators, and user service information.

[0050] Device performance indicators include software version, signal-to-noise ratio, downlink received level, uplink received level, uplink transmitted level, downlink error rate, uplink error rate, downlink correctable error rate, uplink correctable error rate, downlink signal-to-noise ratio, uplink signal-to-noise ratio, uplink and downlink traffic, etc. User service information includes service status, handling time, complaints, fault reports, packages, grids, addresses, terminal types, viewing, network topology information, etc. User device information includes device type information, device status information, affiliated region information, device coding information, etc.

[0051] In step 120, data cleansing audit rules are first created. These rules cover device service consistency, location consistency, and status consistency. Audit content includes device legitimacy, service consistency, and service description. Device legitimacy refers to determining whether the device is activated by the service side; service consistency refers to determining whether the status is consistent with the service system; service descriptions include complaints, repair reports, and fault reports. A terminal view is then created based on the collected device performance indicator information. Next, the device's physical and logical channels are divided based on the device's network topology information. Physical channels are determined based on CMTS information and CM type, while logical channels are determined based on IP and port information. Based on the data cleansing audit rules, the MAC information recorded in the service information is correlated with the device indicator information to verify service consistency, device legitimacy, and attribution consistency. (If the device status information is inconsistent with the status information recorded in the service system, a refresh authorization is required to ensure that the service status is consistent with the service system data.) Any inconsistent user device information in the data, such as device status information, attribution region information, and device code information, is identified and removed. Finally, the collected user device information is associated with the user's business information to form a data set with the user ID as the unique indicator, which is used to store records of the device performance indicators, corresponding channels, ports and other data, and stored in the data warehouse.

[0052] In step 130, the user device's operational trends over a certain period are determined based on device performance indicators. The user device's health data is analyzed using models such as time series models, decision tree models, and collaborative filtering models. The user device's health data is derived from cycles, parameters, models, results, and tasks. Cycles refer to daily, weekly, and monthly executions; parameters refer to diagnostic rule trees; models refer to models such as time series models, decision tree models, and collaborative filtering models; results refer to the generation of various device fault or warning datasets; and tasks refer to detailed datasets such as device anomaly indicators, grid addresses, and user information. User device data with low health is combined with service information to match the corresponding grid information, service information, and community manager information for the user device. The analysis and judgment model is solidified into a daily customized execution data program, and the user device's health data is calculated using the analysis and judgment model algorithm. Based on multiple device performance indicators collected hourly from the user device, a time series data is generated to compare the fluctuations of these indicators with normal values. A scoring matrix is formed using a collaborative filtering algorithm. The sum of each value in this matrix constitutes the device's health data.

[0053] In step 140, according to the preset policy matching rules, intelligent operation and maintenance task scheduling is performed to form task distribution data, and the task distribution data is sent to the corresponding channels. Specifically, the policy matching rules include but are not limited to those based on fault types, distribution channels, business information, priorities, etc. The fault type refers to judging the fault type and location based on algorithms, the distribution channel refers to matching the channel type according to resource metadata, the business information refers to matching business data according to the content of the distributed tasks, and the priority refers to judgments such as user business usage and ARPU value.

[0054] A policy matching library is formed according to the pre-set business rules. For example, if it is judged that the CMTS occurrence rule is violated, the on-duty personnel in the machine room are called online to be informed; if a fault occurs in the CMTS channel, the corresponding operation and maintenance center is called online to be informed; if a single user device fails, corresponding work orders are distributed according to the area corresponding to the device, and different disposal strategies and distribution channels are matched according to the health of the user device; during the process of task distribution, the detailed business information and business usage of the user need to be provided for front-line personnel to make business judgments; according to different distribution channels, different systems and data interfaces are connected to form the distribution or warning of operation and maintenance tasks; the matching mechanism activities of business rules and the task data push mechanism generate production scheduling tasks on the big data platform, and tasks are generated and pushed every day according to this data model algorithm.

[0055] Using various mining and analysis algorithms such as machine learning, TF-IDF, normalization, and collaborative filtering to analyze the performance indicators of the device, and classifying them into different operation and maintenance tasks according to business relevance. Exemplarily, the TF-IDF algorithm is used to calculate the weight of device fault indicators every day, and the calculation method is as follows:

[0056]

[0057] In the above formula, i represents the duration of a certain indicator's failure; j represents the online duration of the device.

[0058] Considering that this indicator will change over time, the start time of this indicator calculation starts from the day when the indicator is abnormal.

[0059]

[0060] In the above formula, TF-IDFn represents the indicator fault weight value on the nth day, and Xn represents the label weight value corresponding to pushing back n days.

[0061] After obtaining the weight values of index faults through TF-IDF, since the weight data is a value in the range of [0, +∞), it is necessary to standardize the data to a measurable range. Therefore, normalization is required to calculate the weight values using a scalar in the range of [0, 1], so as to form the data of a certain dimension in the device health degree and be used for subsequent data analysis and judgment.

[0062] Classify the tags according to the business line system into different types of operation and maintenance tasks: trunk line fault work orders, user equipment fault work orders, computer room fault work orders, large-area fault work orders, etc. Based on the prefabricated task distribution strategy, automatically distribute tasks of different levels to different channels. Referring to the execution requirements of operation and maintenance tasks, use the information such as the grid information, services, and performance index trends matched according to the device MAC information to distribute the generated operation and maintenance task data to the execution tools of operation and maintenance personnel such as individual soldiers and DingTalk. Develop different push strategies and simultaneous channels according to the types of operation and maintenance tasks. Match corresponding strategies for the above activities, establish operation and maintenance activities according to the strategies, and associate the marketing activities with the customer groups. Create a marketing activity template, including: type, execution channel, execution frequency, etc.; cycle, whether to execute according to hours, days, weeks or a one-time task; time, the start and end times of the activity; channel, the corresponding channel for publishing this activity; region, the applicable region or subsidiary company of this activity; description, the main business purpose and operation and maintenance content of the activity. Generate a production scheduling task for the operation and maintenance and marketing activities and task data that have passed the audit and verification on the big data platform, and perform the production and push of tasks according to this data model algorithm every day.

[0063] In step 150, track and analyze the execution situation of the issued tasks, and evaluate and optimize the effect of operation and maintenance work orders based on the task execution analysis results. Specifically, push the marketing activity content to the individual soldier system or DingTalk system through the socket interface, and save the pushed data into the table in the Oracle database; the management personnel on the individual soldier side execute the tasks according to the received operation and maintenance task data, and distribute the task data to the task sheets of community managers in each grid according to the grid; during the task execution process of the community manager, select the execution situation of each task, and select and submit the reasons for the success or failure of the task through the following options, write the task execution results into the Oracle database table in real time, and feedback to the big data platform through the socket interface for update and summary, marking the execution results and reasons of each piece of data, and the feedback data of the executed tasks can be displayed in real time on the individual soldier system side; the big data platform analyzes according to the feedback data during the whole task execution process, displays the completion progress of the whole task and the execution situation of each subsidiary company, and generates an execution report of the task; after the whole task is completed, cooperate with business personnel and data analysis specialists to conduct a post-evaluation of the whole task, adjust and optimize the execution situation of the operation and maintenance tasks, and provide data reference for the execution of the same type of tasks next time.

[0064] Another embodiment of the present invention provides a CMTS network operation and maintenance device based on big data analysis, including: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a CMTS network operation and maintenance method program based on big data analysis. When the processor executes the computer program, the steps in the above-mentioned various embodiments of the CMTS network operation and maintenance method based on big data analysis are implemented, such as Figure 1 the steps.

[0065] Exemplarily, the above computer program can be divided into one or more modules / units. One or more modules / units are stored in the memory and executed by the processor to complete the present invention. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions. The instruction segments are used to describe the execution process of the computer program in the CMTS network operation and maintenance device based on big data analysis. For example, the computer program can be divided into a data acquisition module, a data auditing and cleaning module, a data modeling and analysis module, an operation and maintenance task generation and distribution module, and an evaluation and optimization module. The specific functions of each module are as follows:

[0066] The data acquisition module is used to establish an automatic data scheduling and acquisition task and perform data docking and acquisition using a big data platform;

[0067] The data auditing and cleaning module is used to audit and clean the acquired data and establish a network terminal view of network resources and user services;

[0068] The data modeling and analysis module is used to perform multi-dimensional analysis and judgment on user devices using a data analysis model and establish health data of user devices;

[0069] The operation and maintenance task generation and distribution module is used to perform intelligent operation and maintenance task scheduling according to preset policy matching rules, form task distribution data, and send the task distribution data to the corresponding channels;

[0070] The evaluation and optimization module is used to track and analyze the execution situation of the issued tasks and perform operation and maintenance work order effect evaluation and optimization based on the task execution analysis results.

[0071] The CMTS network operation and maintenance device based on big data analysis can be computing devices such as a desktop computer, a notebook, a palm computer, and a cloud server. The CMTS network operation and maintenance device based on big data analysis may include, but is not limited to, a processor and a memory. For example, it may also include an output device, a network access device, a bus, etc.

[0072] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can also be any conventional processor, etc. The processor is the control center of the CMTS network operation and maintenance device based on big data analysis, and connects all parts of the CMTS network operation and maintenance device based on big data analysis through various interfaces and lines.

[0073] The memory can be used to store computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory, the processor realizes various functions of the CMTS network operation and maintenance device based on big data analysis.

[0074] If the modules / units integrated in the CMTS network operation and maintenance device based on big data analysis are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each embodiment of the above-mentioned CMTS network operation and maintenance method based on big data analysis can be realized.

[0075] Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0076] 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 preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention. The technologies, shapes, and structures not described in detail in the present invention are all well-known technologies.

Claims

1. A CMTS network operation and maintenance method based on big data analysis, characterized in that, It includes the following steps: Establish an automatic data scheduling and collection task, and use the big data platform for data docking and collection; Audit and clean the collected data, and establish a network terminal view of network resources and user services; Use the data analysis model to conduct multi-dimensional analysis and judgment on user devices, and establish the health data of user devices; According to the preset policy matching rules, perform intelligent operation and maintenance task scheduling to form task dispatch data, and send the task dispatch data to the corresponding channels; Track and analyze the execution status of the dispatched tasks, and evaluate and optimize the operation and maintenance work order effect based on the task execution analysis results.

2. The CMTS network operation and maintenance method based on big data analysis according to claim 1, characterized in that The data docking and collection includes collecting network element data of the ARRIS system, ITMS system, OSS system, BOSS system, and professional network management system, collecting user device information and device performance indicators, and collecting user service information.

3. The CMTS network operation and maintenance method based on big data analysis according to claim 2, characterized in that, The device performance indicators include software version, signal-to-noise ratio, downlink received level, uplink received level, uplink transmitted level, downlink error rate, uplink error rate, downlink correctable error rate, uplink correctable error rate, downlink signal-to-noise ratio, uplink signal-to-noise ratio, and uplink and downlink traffic; The user service information includes service status, handling time, complaints, fault reports, packages, grids, addresses, terminal types, viewing, and network topology information; The user device information includes device type information, device status information, attribution region information, and device coding information.

4. The CMTS network operation and maintenance method based on big data analysis according to claim 1, characterized in that The auditing and cleaning of the collected data and the establishment of a network terminal view of network resources and user services include: Create data cleaning and auditing rules; According to the data cleaning and auditing rules, find out the inconsistent data between the user device information in the data and the device information recorded in the service, and eliminate the inconsistent data; Associate the collected user device information with the user's service information to form a data set with the user ID as the only index, and store it in the data warehouse.

5. The CMTS network operation and maintenance method based on big data analysis according to claim 1, wherein, The use of the data analysis model to conduct multi-dimensional analysis and judgment on user devices and establish the health data of user devices includes: Judge the operation trend of user devices within a certain period according to the device performance indicators, and analyze the health data of user devices through time series models, decision tree models, and collaborative filtering models; Combine the user device data with lower health levels with service information to match the corresponding grid information, service information, and community manager information of the user device; Solidify the analysis and judgment model into a daily customized execution data program, and calculate the health data of user devices according to the analysis and judgment model algorithm.

6. The CMTS network operation and maintenance method based on big data analysis according to claim 1, wherein, The intelligent operation and maintenance task scheduling includes the following steps: Form a policy matching library according to the pre-set business rules, and match different disposal strategies and dispatch channels according to the health of user devices; During the task dispatch process, it is necessary to provide the detailed service information and service usage of the user for front-line personnel to make business judgments; According to different dispatch channels, connect to different systems and data interfaces to form the dispatch or warning of operation and maintenance tasks; Push the matching mechanism activities and task data push mechanism of the business rules to generate production scheduling tasks on the big data platform, and generate and push tasks every day according to this data model algorithm.

7. The CMTS network operation and maintenance method based on big data analysis according to claim 1, wherein Tracking and analyzing the execution status of the assigned tasks, and evaluating and optimizing the effectiveness of operation and maintenance work orders based on the task execution analysis results, including: Pushing the marketing campaign content to the single-soldier system or DingTalk system through the socket interface, and saving the pushed data into a table in the Oracle database; During the execution process, writing the task execution results into the Oracle database table in real time, and feeding back to the big data platform through the socket interface for update and summary; Analyzing according to the feedback data during the whole task execution process, displaying the completion progress of the whole task and the execution status of each branch company, and generating an execution report of the task; After the whole task is completed, collaborating with business personnel and data analysis specialists to conduct a post-evaluation of the whole task, and adjusting and optimizing the execution status of the operation and maintenance tasks.

8. The CMTS network operation and maintenance device based on big data analysis includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1-7.

Images