Scenarized government and enterprise customer perception insight method, device, equipment and medium

Abstract

The invention discloses a scene-based government and enterprise customer perception insight method, device, equipment and medium, and the method comprises the steps: obtaining a scene-based domain name library of a to-be-served object, carrying out the DNS domain name analysis and http traffic analysis based on domain names in the domain name library, and obtaining the network demand data of the to-be-served object; performing data cleaning on the network demand data through a preset big data analysis platform; filtering and screening the to-be-served object based on a data cleaning result to obtain an object list; and performing service marketing on the target object based on the object list. According to the method, scene characteristics of the user in a network use process can be deeply mined and analyzed, accurate understanding and prediction of customer demands are realized, so that scene perception and demands of customer applications are accurately informed, a scientific basis is provided for optimization of network services and popularization of new products, and the method can be widely applied to the technical field of data processing.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a scenario-based government and enterprise customer perception insight method, device, equipment and medium. Background Art

[0002] With the rapid development of the Internet industry and the digital transformation of various industries, the demands of government and enterprise customers for the network have gradually become richer, and the requirements for operators have gradually increased. In the past, it was only to provide the network and achieve normal network interconnection. Nowadays, the security, stability, high speed and guarantee of the network have become more and more the focus of customers, and the "connection type" has gradually changed to "scenario-based". Telecom operators should keep pace with the times, improve customer service quality, promptly learn about customers' "scenario-based" network perception and potential needs, and actively improve their own service capabilities and levels.

[0003] Traditional customer perception and customer demand insights have the following problems:

[0004] 1. Traditional customer perception analysis relies on network KPIs, i.e., network performance indicators such as optical attenuation, bit error, and latency at the physical layer, which cannot be associated with customer applications and cannot accurately grasp customers' network perception; or through "post-event" methods such as fault reporting and complaints. All of the above are passive and one-sided ways to understand customers' network usage experience, and cannot promptly detect customer perception degradation.

[0005] 2. Traditional customer demand insights are mainly obtained through customer visits, telephone communications, etc., relying on the personal experience of account managers. The success rate of marketing mainly depends on the ability of "people". The marketing volume is extremely unstable, and there are often problems such as untimely discovery of customer needs, low efficiency, and low coverage. As a result, the promotion of new products and new businesses relies on wide-ranging "cast-a-net" marketing, resulting in low marketing efficiency and low conversion rate. Summary of the invention

[0006] The present invention proposes a scenario-based government and enterprise customer perception insight method, device, equipment and medium, aiming to solve one of the technical problems in the related technology at least to a certain extent. The embodiments of the present invention can efficiently and accurately realize scenario-based government and enterprise customer perception insight.

[0007] On the one hand, an embodiment of the present invention provides a scenario-based government and enterprise customer perception insight method, including:

[0008] Obtain the scenario-based domain name library of the service object, perform DNS domain name analysis and http traffic resolution based on the domain names in the domain name library, and obtain the network demand data of the service object;

[0009] Clean network demand data through the preset big data analysis platform;

[0010] Based on the results of data cleaning, filter and screen the service objects to obtain a list of objects;

[0011] Provide service marketing to target objects based on the object list.

[0012] Optionally, obtaining a scenario-based domain name library of the object to be served includes the following steps:

[0013] By capturing packets for analysis and collecting visit information, we can compile a scenario-based domain name library.

[0014] Optionally, performing DNS domain name analysis based on the domain name in the domain name library includes at least one of the following steps:

[0015] Perform local DNS query based on the domain name in the domain name database;

[0016] Perform root DNS query based on the domain name in the domain name database;

[0017] Perform top-level domain DNS query based on the domain name in the domain name database;

[0018] Perform an authoritative DNS server query based on the domain name in the domain name database.

[0019] Optionally, the http traffic parsing is performed on the http traffic data obtained based on the domain names in the domain name library; performing the http traffic parsing based on the domain names in the domain name library includes at least one of the following steps:

[0020] Analyze request headers and response headers based on http traffic data to identify specific behaviors of the service object;

[0021] Analyze the request body and response body based on http traffic data and extract feature information;

[0022] The access mode of the service object is tracked based on http traffic data; wherein the tracking data sources of the access mode include the service quality layer, the link quality layer and the equipment operation quality layer.

[0023] Optionally, performing HTTP traffic resolution based on the domain name in the domain name library further includes the following steps:

[0024] Perform HTTP traffic delay analysis based on HTTP traffic data through the HTTP traffic delay analysis system;

[0025] Among them, the http traffic data includes downlink service flow, uplink service flow, and keep-alive information; the http traffic delay analysis system includes an optical line terminal, a broadband access server, and an optical network unit; the http traffic delay analysis specifically includes the following operations;

[0026] The time delay T2 is collected based on the process of the downlink service flow passing through the optical line terminal;

[0027] The delay T3 is collected based on the process of the upstream service flow passing through the optical line terminal;

[0028] Delay T1 is obtained by summing delay T2 and delay T3;

[0029] The acquisition delay T4 is based on the process of sending keep-alive information from the broadband access server to the optical network unit;

[0030] The collection delay T5 of the process of sending keep-alive information from the optical network unit to the broadband access server;

[0031] The delay T6 is obtained according to the difference between the delay T2 and the delay T4;

[0032] The delay T7 is obtained by integrating the delay T3, the delay T4 and the delay T5.

[0033] Optionally, data cleaning is performed on the network demand data through a preset big data analysis platform, including the following steps:

[0034] Analyze the target data in the network demand data on the big data atomic capability analysis platform to obtain the results of data cleaning.

[0035] Optionally, filtering and screening the objects to be served based on the result of data cleaning to obtain an object list includes the following steps:

[0036] The preset stock objects are taken as positive samples, and the feature data corresponding to the positive samples are obtained by summarizing;

[0037] Based on the feature data, similarity matching is performed on the results of data cleaning, and then the service objects are filtered and screened according to the results of similarity matching to obtain an object list.

[0038] On the other hand, an embodiment of the present invention provides a scenario-based government and enterprise customer perception insight device, including:

[0039] The first module is used to obtain the scenario-based domain name library of the service object, perform DNS domain name analysis and http traffic resolution based on the domain names in the domain name library, and obtain the network demand data of the service object;

[0040] The second module is used to clean the network demand data through a preset big data analysis platform;

[0041] The third module is used to filter and select the service objects based on the results of data cleaning to obtain the object list;

[0042] The fourth module is used to carry out service marketing to target objects based on the object list.

[0043] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store programs; the processor executes the program to implement the above-mentioned scenario-based government and enterprise customer perception insight method.

[0044] On the other hand, an embodiment of the present invention provides a computer storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned scenario-based government and enterprise customer perception insight method.

[0045] The embodiment of the present invention obtains the scenario-based domain name library of the service object, performs DNS domain name analysis and http traffic resolution based on the domain names in the domain name library, and obtains the network demand data of the service object; performs data cleaning on the network demand data through a preset big data analysis platform; filters and selects the service object based on the result of data cleaning to obtain an object list; and performs service-based marketing on the target object based on the object list. The present invention uses DNS domain name analysis and http traffic resolution to perform network feature data analysis, and then through data cleaning and filtering and screening of the list to achieve in-depth mining and analysis of the scenario characteristics of users in the process of network use, to achieve accurate understanding and prediction of customer needs, thereby accurately insight into the customer's application "scenario-based" perception and needs, thereby providing a scientific basis for the optimization of network services and the promotion of new products. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0047] Figure 1 A schematic diagram of an implementation environment for scenario-based government and enterprise customer perception insights provided by an embodiment of the present invention;

[0048] Figure 2 A flowchart of a scenario-based government and enterprise customer perception insight method provided by an embodiment of the present invention;

[0049] Figure 3 A schematic diagram of the architecture logic of a system for tracking user access patterns provided by an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of the architecture logic of http traffic delay analysis provided by an embodiment of the present invention;

[0051] Figure 5 It is a schematic diagram of the classification of steel analysis environment for multiple scenarios of political and enterprise customer needs in the existing technology;

[0052] Figure 6A schematic diagram of the process steps of DNS domain name analysis and http traffic resolution provided by an embodiment of the present invention;

[0053] Figure 7 A schematic diagram of the classification of data analysis on the big data atomic capability analysis platform provided by an embodiment of the present invention;

[0054] Figure 8 A schematic diagram of the steps for classifying time periods for service marketing provided by an embodiment of the present invention;

[0055] Fig. 9 A schematic diagram of the module structure of a scenario-based government and enterprise customer perception and insight device provided by an embodiment of the present invention;

[0056] Fig.10 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0059] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0060] To facilitate the understanding of the technical solution of the present invention, the technical feature terms that may appear in the embodiments of the present invention are first explained:

[0061] DNS (Domain Name System) is a core service of the Internet, which is responsible for converting human-readable domain names into computer-readable IP addresses. This process is called domain name resolution.

[0062] HTTP traffic analysis refers to the process of analyzing HTTP (Hypertext Transfer Protocol) packets transmitted in the network to understand the content, structure and purpose of the packets. HTTP is the most widely used network protocol on the Internet, mainly used to transmit web pages from web servers to local browsers for browsing.

[0063] A big data atomic capability analysis platform refers to an advanced technology platform designed for processing and analyzing big data. It focuses on providing a series of basic and core "atomic" capabilities that can be used alone or combined to support complex data processing tasks. Such platforms usually integrate multiple links such as data collection, storage, processing, analysis and visualization.

[0064] Uplink traffic refers to the amount of data sent from user devices (such as computers and mobile phones) to the Internet during Internet communications. Simply put, when you upload files to cloud storage, send emails, post social media updates, or make video calls, the amount of data transmitted is uplink traffic. Compared with uplink traffic, downlink traffic refers to the amount of data downloaded from the Internet to user devices, such as the traffic consumed by browsing web pages, downloading files, watching online videos, etc.

[0065] Downstream traffic refers to the amount of data transferred from the Internet to user devices (such as personal computers, smartphones or tablets) during Internet communications. This includes all data transfer activities from Internet servers to local devices, such as downloading page content when browsing the web, watching online videos, downloading applications, listening to music, receiving email attachments, etc.

[0066] It is understandable that the scenario-based government and enterprise customer perception insight method provided in the embodiment of the present invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various types of terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server. Optionally, the terminal is a smart phone, tablet computer, laptop computer, desktop computer, etc., but is not limited to this.

[0067] like Figure 1 FIG. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention. Figure 1The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected to a network wirelessly or wired to complete data transmission and exchange.

[0068] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0069] In addition, the server 101 can also be a node server in the blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0070] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 may be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present invention.

[0071] Based on the example Figure 1 In the implementation environment shown, an embodiment of the present invention provides a scenario-based government and enterprise customer perception insight method. The scenario-based government and enterprise customer perception insight method is applied in terminal 102 as an example for explanation below. It can be understood that the scenario-based government and enterprise customer perception insight method can also be applied to server 101.

[0072] Reference Figure 2 , Figure 2 The flowchart of the scenario-based government and enterprise customer perception and insight method applied to the terminal provided by the embodiment of the present invention, the execution subject of the scenario-based government and enterprise customer perception and insight method can be any of the aforementioned computer devices (including servers or terminals). Figure 2 , the method comprises the following steps:

[0073] S100, obtaining a scenario-based domain name library of the object to be served, performing DNS domain name analysis and http traffic resolution based on the domain names in the domain name library, and obtaining network demand data of the object to be served;

[0074] It should be noted that, in some embodiments, obtaining a scenario-based domain name library of an object to be served may include the following steps: obtaining a scenario-based domain name library by analyzing packet capture and collecting visit information.

[0075] For example, in some specific implementations, a complete "scenario-based" domain name library can be summarized and organized through packet capture analysis and field information collection, and corresponding domain name resolution can be performed based on the domain names collected in the domain name library. The secondary domain names in the domain name library can also be dynamically updated in real time, and specific domain names in specific scenarios can be clustered and summarized to ensure that the "customized" domain name library corresponds to the scenario accurately.

[0076] It should also be noted that, in some embodiments, performing DNS domain name analysis based on the domain names in the domain name library may include at least one of the following steps: performing a local DNS query based on the domain names in the domain name library; performing a root DNS query based on the domain names in the domain name library; performing a top-level domain DNS query based on the domain names in the domain name library; and performing an authoritative DNS server query based on the domain names in the domain name library.

[0077] Exemplarily, in some specific implementations, the method steps of DNS domain name analysis include: 1. local DNS query; 2. root DNS query; 3. top-level domain DNS query; 4. authoritative DNS server query.

[0078] It should also be noted that, in some embodiments, http traffic parsing is performed on http traffic data obtained based on the domain names in the domain name library; performing http traffic parsing based on the domain names in the domain name library may include at least one of the following steps: analyzing the request header and response header based on the http traffic data to identify the specific behavior of the object to be served; analyzing the request body and response body based on the http traffic data to extract feature information; tracking the access pattern of the object to be served based on the http traffic data; wherein the tracking data source of the access pattern includes the service quality layer, the link quality layer and the equipment operation quality layer.

[0079] Exemplarily, in some specific implementations, the method steps for http traffic parsing include:

[0080] 1. Analyze request headers and response headers: Using a large amount of http request traffic data as samples, further analyze the classification of new request headers and identify specific behaviors (determine behavioral preferences);

[0081] 2. Analyze the request body and response body:

[0082] Structural processing: divide the request body into different fields and parameters;

[0083] Keyword extraction and association analysis: Use text mining and natural language processing technology to extract keywords from the request body and perform association analysis;

[0084] Binary data parsing and feature extraction are performed on the extracted keywords to extract characteristic information such as the type, size, and modification time of the uploaded file.

[0085] 3. Track user access patterns (reference Figure 3 )include:

[0086] Service quality layer, used for broadband user service quality management;

[0087] Link quality layer, including home network management (statistical identification of WiFi interference, WiFi weak coverage and other issues), network element / network management (statistical identification of peak traffic congestion link errors, optical path weak light / strong light and other issues) and business management system (statistical identification of IDC self-organizing network issues, etc.);

[0088] The equipment operation quality layer statistically identifies corresponding quality issues based on network performance and equipment performance.

[0089] In some optional implementations, performing http traffic resolution based on the domain name in the domain name library may further include the following steps: performing http traffic delay analysis based on the http traffic data through an http traffic delay analysis system;

[0090] Among them, http traffic data includes downstream business flow, upstream business flow, and keep-alive information; the http traffic delay analysis system includes an optical line terminal, a broadband access server, and an optical network unit; the http traffic delay analysis can specifically include the following operations: collecting delay T2 based on the process of downstream business flow passing through the optical line terminal; collecting delay T3 based on the process of upstream business flow passing through the optical line terminal; obtaining delay T1 according to the sum of delay T2 and delay T3; collecting delay T4 based on the process of sending keep-alive information from the broadband access server to the optical network unit; collecting delay T5 based on the process of sending keep-alive information from the optical network unit to the broadband access server; obtaining delay T6 based on the difference between delay T2 and delay T4; obtaining delay T7 based on the integration of delay T3, delay T4 and delay T5.

[0091] For example, in some specific implementations, the http traffic delay analysis system includes: a user terminal, an ONU (Optical Network Unit), an OLT (Optical Line Terminal), a BRAS (Broadband Remote Access Server), a city export CR, a soft probe front-end and a service SIP (Session initialization Protocol), refer to Figure 4 :

[0092] Delay T1: obtained by T2+T3.

[0093] Delay T2: When the downstream service flow passes through the OLT, the ASA (Adaptive Security Appliance) mirrors it and timestamps it locally with a timestamp of a. When the service flow reaches the terminal, the terminal receives the confirmation packet sent upward. When passing through the OLT, the ASA mirrors it and timestamps it locally with a timestamp of b. The ACK sequence number at the TCP level of this data packet is used to reversely find the corresponding downstream SEQ packet, and ba is used to obtain T2.

[0094] Delay T3: When the upstream service flow passes through the OLT, the ASA mirrors it and timestamps it locally with a time stamp of a. When the service flow reaches the server, it receives the confirmation packet sent downward. When it passes through the OLT, the ASA mirrors it and timestamps it locally with a time stamp of b. The ACK sequence number of the TCP layer of this data packet is used to reversely find the corresponding upstream SEQ packet, and ba is used to get T3. T4 is that after the optical modem successfully establishes the PPPoE connection, it regularly sends a keep-alive message to the BRAS. The ONT will send it to the BRAS, and the BRAS will also send it to the ONT. The frequency of sending this keep-alive message can be configured. Usually, it is sent once every 20 seconds or once every 1 minute on the Internet.

[0095] Delay T4: BRAS sends a keep-alive message to ONT. This message is timestamped a when entering OLT. ONT responds to this keep-alive message back to BRAS through OLT, and ASA mirrors it and timestamps b. We use ba to get the RTT delay of T4. This delay is usually very small, usually around 1.1 ms. However, it may reach tens of ms or even hundreds of ms due to problems with the protocol stack processing performance of individual ONTs. We classify these terminals as poor-quality users.

[0096] Delay T5: ONT sends a keep-alive message to BRAS. This message is timestamped a when entering OLT. BRAS responds to this keep-alive message and sends it back to ONT through OLT. ASA mirrors it and timestamps it b. Use ba to get the RTT delay of T5. This delay is usually very small, usually around 1ms. However, there are some longer delays due to occasional degradation of BRAS port forwarding performance, reaching several ms or tens of ms. If this phenomenon is common and regular, it can be considered that there is a problem with the port forwarding performance of the upstream BRAS.

[0097] Delay T6: T4 is usually relatively stable. Therefore, the in-home delay T6 per user per terminal per service can be obtained by subtracting the T4 delay from the T2 delay per user per terminal per service.

[0098] Delay T7: The T7 delay of the backbone + content source above BRAS is T3-T5.

[0099] The advantages of the above system delay are:

[0100] A. Delay segmentation and quantification: By segmenting the HTTP traffic delay analysis into multiple delay indicators such as T1 to T7, it can accurately measure the delay time of each link from the user terminal to the Internet content source, thereby achieving the effect of all-round monitoring of network performance. Finally, it can quickly locate network delay problems and improve network optimization efficiency;

[0101] B. By calculating T6 (T2-T4), i.e. the intra-home delay, it can directly reflect the delay status of the user's home network environment, which helps to identify possible problems with the home network configuration or hardware devices, thereby providing users with targeted home network optimization suggestions and improving the end user's Internet experience;

[0102] C. By analyzing the T5 delay, the forwarding performance of the upstream BRAS port can be monitored, and the delay increase caused by the degradation of the port forwarding performance can be discovered in time, which helps network maintenance personnel to quickly identify and solve the bottleneck at the BRAS level, and ultimately ensure the smooth transmission of user upstream data;

[0103] D. Using T7 latency (T3-T5), we can evaluate the latency of backbone networks and content sources above BRAS, provide data support for optimizing network architecture layout and selecting better content distribution paths, and ultimately improve the overall speed and experience of users accessing Internet content.

[0104] E. By analyzing the abnormal values ​​in T4 latency, it is possible to identify high latency caused by performance issues of terminal devices (such as ONTs), helping service providers to mark these "poor quality user" devices and take corresponding measures to optimize or replace them, thereby ensuring service quality and user satisfaction.

[0105] S200, performing data cleaning on network demand data through a preset big data analysis platform;

[0106] It should be noted that, in some embodiments, data cleaning of network demand data through a preset big data analysis platform may include the following steps: analyzing target data in the network demand data on the big data atomic capability analysis platform to obtain data cleaning results.

[0107] For example, in some specific implementations, data cleaning is performed by classification and judgment on a big data analysis platform. Specifically, the following data can be analyzed on a big data atomic capability analysis platform (data base):

[0108] (1) Behavioral preferences: high-frequency and low-frequency users: those who visit the specific domain name more than three times in a week (high frequency);

[0109] (2) Customer information: enterprise size, business information, package rates, and marketing cluster area;

[0110] (3) Customer network quality: access network quality, core network quality, and customer intranet quality;

[0111] (4) Terminal status: PC terminal, mobile terminal;

[0112] (5) Fault reporting and complaints;

[0113] (6) Traffic conditions: upstream traffic and downstream traffic.

[0114] S300, filtering and screening the service objects based on the result of data cleaning to obtain an object list;

[0115] It should be noted that in some embodiments, filtering and screening the objects to be served based on the results of data cleaning to obtain a list of objects can include the following steps: taking preset stock objects as positive samples, and summarizing to obtain feature data corresponding to the positive samples; performing similarity matching on the results of data cleaning based on the feature data, and then filtering and screening the objects to be served based on the results of the similarity matching to obtain a list of objects.

[0116] For example, in some specific implementations, the existing "scenario" users are used as positive samples, the relevant characteristics of users in each scenario are summarized, and the list of target potential customers is further filtered (for example, through similarity analysis) to provide a more "precise" list for marketing by front-end account managers:

[0117] (1) Analyze the traffic characteristics of existing users; for example, in the international potential customer scenario, most users have higher traffic at night;

[0118] (2) Observe the industry types of existing users and summarize their characteristics; for example, in the international potential customer scenario, most customers are from the cultural tourism and industrial manufacturing industries;

[0119] (3) Information on the size and operating conditions of related companies, with a focus on medium-sized and high-end customers or above.

[0120] S400: Conduct service marketing for target objects based on the object list.

[0121] For example, in some specific implementations, a list is sent in batches for visits: service marketing is performed on customers. In a specific implementation, the following steps are used:

[0122] L1. Fixed IP user scenario: Target broadband customers, recommend customers to use premium dedicated lines to improve customer experience;

[0123] L2. Determine through DNS domain name analysis, http traffic analysis, etc. that the customer is indeed using software with intranet penetration and dynamic domain name resolution functions (such as "xx shell" software);

[0124] L3. Combine the 163 backend call records with the uplink traffic data and distinguish the specific purpose through the uplink traffic. If the uplink traffic is large, it is judged that the customer uses it for dynamic domain name resolution. If the uplink traffic is small, it is judged that the user's main purpose is to penetrate the intranet.

[0125] L4. Determine whether the operator needs to proactively provide network optimization services based on network quality, fault reporting, complaints, and the customer's current business scale;

[0126] L5. Regularly collect the lists issued in batches, evaluate the results for the customers on the lists, summarize the corresponding problems that always arise during the marketing visits, and provide reference for subsequent lists.

[0127] In order to explain the principle of the technical solution of the present invention in detail, the overall process of the present invention is described below in combination with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and cannot be regarded as a limitation of the present invention.

[0128] First of all, it should be noted that Figure 5 As shown in the figure, traditional customer perception analysis relies on network KPIs, i.e., network performance indicators such as optical attenuation, bit error, and latency at the physical layer. It cannot be associated with customer applications and cannot accurately grasp the customer's network perception; or through "post-event discovery" methods such as fault reporting and complaints. All of the above are passive and one-sided ways to understand the customer's network experience, and cannot timely discover the deterioration of customer perception. In addition, traditional customer demand insights are mainly obtained through customer visits, telephone communications, etc., relying on the personal experience of account managers. The success rate of marketing mainly depends on the ability of "people", and the marketing volume is extremely unstable. There are often problems such as untimely discovery of customer needs, low efficiency, and low coverage, which leads to the promotion of new products and new services relying on wide "cast-net" marketing, resulting in low marketing efficiency and low conversion rate.

[0129] In view of this, the present invention provides a scenario-based government and enterprise customer perception insight method, comprising the following specific steps:

[0130] S1. Build a model to identify users in multiple scenarios, perform DNS domain name analysis and HTTP traffic analysis on the identified scenarios, preliminarily locate customer preferences, and identify potential customer network needs;

[0131] The model here is obtained based on the integration of multi-dimensional data and is used to gain insights into customer perceptions in different scenarios;

[0132] Step 1:

[0133] (1) Through packet capture analysis and field information collection, a complete set of "scenario-based" domain name database is summarized and sorted out, and corresponding domain name resolution is performed based on the domain names collected in the database;

[0134] (2) Real-time dynamic update of the secondary domain names in the domain name library, etc., clustering and summarizing specific domain names in specific scenarios, and ensuring that the "customized" domain name library corresponds to the correct scenario;

[0135] Step 2: If Figure 6 As shown, DNS domain name analysis and http traffic analysis:

[0136] (1) The method and steps of DNS domain name analysis include:

[0137] 1. Local DNS query;

[0138] 2. Root DNS query;

[0139] 3. Top-level domain DNS query;

[0140] 4. Query the authoritative DNS server;

[0141] (2) The method and steps for HTTP traffic parsing include:

[0142] 1. Analyze request headers and response headers: Using a large amount of http request traffic data as samples, further analyze the classification of new request headers and identify specific behaviors (determine behavioral preferences);

[0143] 2. Analyze the request body and response body:

[0144] Structural processing: divide the request body into different fields and parameters;

[0145] Keyword extraction and association analysis: Use text mining and natural language processing technology to extract keywords from the request body and perform association analysis;

[0146] Perform binary data parsing and feature extraction on the extracted keywords to extract feature information such as the type, size, and modification time of the uploaded file;

[0147] 3. Track user access patterns (reference Figure 3 )include:

[0148] Service quality layer, used for broadband user service quality management;

[0149] Link quality layer, including home network management (statistical identification of WiFi interference, WiFi weak coverage and other issues), network element / network management (statistical identification of peak traffic congestion link errors, optical path weak light / strong light and other issues) and business management system (statistical identification of IDC self-organizing network issues, etc.);

[0150] Equipment operation quality layer, which statistically identifies corresponding quality issues based on network performance and equipment performance;

[0151] (3) The http traffic delay analysis system includes: user terminal, ONU (Optical Network Unit), OLT (Optical Line Terminal), BRAS (Broadband Remote Access Server), city export CR, soft probe front-end and service SIP (Session Initialization Protocol). Figure 4 :

[0152] Delay T1: obtained by T2+T3.

[0153] Delay T2: When the downstream service flow passes through the OLT, the ASA (Adaptive Security Appliance) mirrors it and timestamps it locally with a timestamp of a. When the service flow reaches the terminal, the terminal receives the confirmation packet sent upward. When passing through the OLT, the ASA mirrors it and timestamps it locally with a timestamp of b. The ACK sequence number at the TCP level of this data packet is used to reversely find the corresponding downstream SEQ packet, and ba is used to obtain T2.

[0154] Delay T3: When the upstream service flow passes through the OLT, the ASA mirrors it and timestamps it locally with a time stamp of a. When the service flow reaches the server, it receives the confirmation packet sent downward. When it passes through the OLT, the ASA mirrors it and timestamps it locally with a time stamp of b. The ACK sequence number of the TCP layer of this data packet is used to reversely find the corresponding upstream SEQ packet, and ba is used to get T3. T4 is that after the optical modem successfully establishes the PPPoE connection, it regularly sends a keep-alive message to the BRAS. The ONT will send it to the BRAS, and the BRAS will also send it to the ONT. The frequency of sending this keep-alive message can be configured. Usually, it is sent once every 20 seconds or once every 1 minute on the Internet.

[0155] Delay T4: BRAS sends a keep-alive message to ONT. This message is timestamped a when entering OLT. ONT responds to this keep-alive message back to BRAS through OLT, and ASA mirrors it and timestamps b. We use ba to get the RTT delay of T4. This delay is usually very small, usually around 1.1 ms. However, it may reach tens of ms or even hundreds of ms due to problems with the protocol stack processing performance of individual ONTs. We classify these terminals as poor-quality users.

[0156] Delay T5: ONT sends a keep-alive message to BRAS. This message is timestamped a when entering OLT. BRAS responds to this keep-alive message and sends it back to ONT through OLT. ASA mirrors it and timestamps it b. Use ba to get the RTT delay of T5. This delay is usually very small, usually around 1ms. However, there are some longer delays due to occasional degradation of BRAS port forwarding performance, reaching several ms or tens of ms. If this phenomenon is common and regular, it can be considered that there is a problem with the port forwarding performance of the upstream BRAS.

[0157] Delay T6: T4 is usually relatively stable. Therefore, the in-home delay T6 per user per terminal per service can be obtained by subtracting the T4 delay from the T2 delay per user per terminal per service.

[0158] Delay T7: The T7 delay of the backbone + content source above BRAS is T3-T5.

[0159] The advantages of the above system delay are:

[0160] A. Delay segmentation and quantification: By segmenting the HTTP traffic delay analysis into multiple delay indicators such as T1 to T7, it can accurately measure the delay time of each link from the user terminal to the Internet content source, thereby achieving the effect of all-round monitoring of network performance. Finally, it can quickly locate network delay problems and improve network optimization efficiency;

[0161] B. By calculating T6 (T2-T4), i.e. the intra-home delay, it can directly reflect the delay status of the user's home network environment, which helps to identify possible problems with the home network configuration or hardware devices, thereby providing users with targeted home network optimization suggestions and improving the end user's Internet experience;

[0162] C. By analyzing the T5 delay, the forwarding performance of the upstream BRAS port can be monitored, and the delay increase caused by the degradation of the port forwarding performance can be discovered in time, which helps network maintenance personnel to quickly identify and solve the bottleneck at the BRAS level, and ultimately ensure the smooth transmission of user upstream data;

[0163] D. Using T7 latency (T3-T5), we can evaluate the latency of backbone networks and content sources above BRAS, provide data support for optimizing network architecture layout and selecting better content distribution paths, and ultimately improve the overall speed and experience of users accessing Internet content.

[0164] E. By analyzing the abnormal values ​​in T4 latency, it is possible to identify high latency caused by performance issues of terminal devices (such as ONTs), helping service providers to mark these "poor quality user" devices and take corresponding measures to optimize or replace them, thereby ensuring service quality and user satisfaction.

[0165] S2. Perform data cleaning by classification and judgment on the big data analysis platform;

[0166] In some specific implementations, the following is an example logic of the relevant data cleaning script used in the present invention:

[0167]

[0168]

[0169] For example, Figure 7 As shown, the following data are analyzed on the big data atomic capability analysis platform (data base): (1) Behavioral preferences: high- and low-frequency users: visiting the specific type of domain name more than three times in a week (high frequency);

[0170] (2) Customer information: enterprise size, business information, package rates, and marketing cluster area;

[0171] (3) Customer network quality: access network quality, core network quality, and customer intranet quality;

[0172] (4) Terminal status: PC terminal, mobile terminal;

[0173] (5) Fault reporting and complaints;

[0174] (6) Traffic conditions: upstream traffic and downstream traffic.

[0175] S3. Take the existing "scenario" users as positive samples, summarize the relevant characteristics of users in each scenario, further filter and screen the list of target potential customers (for example, through similarity analysis), and provide a more "precise" list for front-end account managers to market:

[0176] (1) Analyze the traffic characteristics of existing users; for example, in the international potential customer scenario, most users have higher traffic at night;

[0177] (2) Observe the industry types of existing users and summarize their characteristics; for example, in the international potential customer scenario, most customers are from the cultural tourism and industrial manufacturing industries;

[0178] (3) Information on the size and operating conditions of related companies, with a focus on medium-sized and high-end customers or above.

[0179] S4. List batch distribution visit: provide service marketing to customers, including Figure 8 The following is an example of the steps for classifying time periods for service marketing.

[0180] In a specific embodiment, the following steps are used:

[0181] L1. Fixed IP user scenario: Target broadband customers, recommend customers to use premium dedicated lines to improve customer experience;

[0182] L2. Determine through DNS domain name analysis, http traffic analysis, etc. that the customer is indeed using software with intranet penetration and dynamic domain name resolution functions (such as "xx shell" software);

[0183] L3. Combine the 163 backend call records with the uplink traffic data and distinguish the specific purpose through the uplink traffic. If the uplink traffic is large, it is judged that the customer uses it for dynamic domain name resolution. If the uplink traffic is small, it is judged that the user's main purpose is to penetrate the intranet.

[0184] L4. Determine whether the operator needs to proactively provide network optimization services based on network quality, fault reporting, complaints, and the customer's current business scale;

[0185] L5. Regularly collect the lists issued in batches, evaluate the results for the customers on the lists, summarize the corresponding problems that always arise during the marketing visits, and provide reference for subsequent lists.

[0186] Among them, the following Table 1 is the table data of the scenario model corresponding analysis example:

[0187] Table 1

[0188]

[0189]

[0190] In summary, the present invention utilizes network feature big data analysis technology to achieve accurate understanding and prediction of customer needs by deeply mining and analyzing the user's behavior patterns, preferences, and scenario characteristics during network use, thereby accurately understanding the customer's application "scenario-based" perception and needs, and can highly personalize the identification of users' specific needs at different times, places, and situations, thereby providing a scientific basis for the optimization of network services and the promotion of new products. Specifically, the present invention not only improves the user experience by deeply mining network feature big data, but also provides operators and Internet companies with more efficient and targeted product development and market strategies, objectively promoting the innovative development of network services and related industries.

[0191] Compared with the prior art, the present invention has at least the following beneficial effects:

[0192] 1. The present invention constructs a model for multi-scenario identification, and combines DNS domain name analysis with http traffic analysis to preliminarily locate customer network preferences and identify potential needs, thereby achieving preliminary customization of personalized services and improving the pertinence and predictability of services.

[0193] 2. The present invention establishes a dynamically updated "scenario-based" domain name library mechanism, which ensures accurate scenario division by clustering and summarizing secondary domain names. This can reflect market changes in real time, enable service strategies to be dynamically adjusted in line with customer needs, and improve the timeliness and accuracy of customer perception.

[0194] 3. The present invention divides the delay calculation method in detail in the http traffic delay analysis system, sets accurate timestamp capture and analysis processes for each key network node (including ONU, OLT, etc.) from the user terminal to the BRAS and even the content source, and can monitor and quantify the delay of each link in the network in detail, so as to achieve the effect of in-depth diagnosis of the delay in the home network, the performance of the upstream BRAS port and the backbone network status. This method not only helps to quickly locate the network bottleneck and improve the accuracy and efficiency of troubleshooting, but also can tailor network optimization solutions for the specific conditions of different users, terminals and services, and ultimately achieve a significant improvement in user network experience and an overall improvement in service quality.

[0195] 4. The present invention integrates multi-dimensional data such as user behavior, network quality, terminal status, etc. through a big data analysis platform, which can comprehensively and deeply analyze customer characteristics, provide customers with more refined service suggestions, enhance user experience, and promote efficient allocation of enterprise resources.

[0196] 5. The present invention utilizes the analysis of existing user data to screen out target potential customers with similar characteristics and form a precision marketing list, thereby effectively improving the accuracy and success rate of marketing activities, reducing resource waste and increasing customer conversion rate.

[0197] 6. The present invention not only provides personalized optimization solutions through customized service recommendations for fixed IP users, analysis of specific software usage, and comprehensive network status evaluation, but also establishes a regular evaluation mechanism for visit marketing effects, continuously provides feedback to optimize marketing strategies, forms a closed loop of continuous improvement, and ultimately achieves the effect of improving overall service quality and customer satisfaction.

[0198] On the other hand, Fig. 9 As shown, an embodiment of the present invention provides a scenario-based government and enterprise customer perception insight device 900, including:

[0199] The first module 901 is used to obtain a scenario-based domain name library of the object to be served, perform DNS domain name analysis and http traffic resolution based on the domain names in the domain name library, and obtain network demand data of the object to be served;

[0200] The second module 902 is used to clean the network demand data through a preset big data analysis platform;

[0201] The third module 903 is used to filter and select the service objects based on the result of data cleaning to obtain an object list;

[0202] The fourth module 904 is used to perform service marketing for the target object based on the object list.

[0203] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0204] On the other hand, an embodiment of the present invention further provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above sensitive information method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0205] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0206] like Fig.10 As shown, Fig.10 A specific example of the hardware structure of an electronic device 1000 according to an embodiment is shown. The electronic device 1000 includes:

[0207] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0208] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the network node population optimization method of the embodiment of the present invention;

[0209] Input / output interface 1003, used to implement information input and output;

[0210] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0211] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0212] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0213] The electronic device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0214] The contents of the method embodiments of the present invention are all applicable to the electronic device embodiments. The functions specifically implemented by the electronic device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0215] Another aspect of an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0216] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read to Only Memory, CD to ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0217] The contents of the method embodiments of the present invention are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0218] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0219] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0220] It should be noted that, although several modules of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0221] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD to ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0222] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0223] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0224] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0225] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution device, apparatus or device (such as a computer-based device, a device including a processor, or other device that can fetch instructions from an instruction execution device, apparatus or device and execute the instructions), or in conjunction with such instruction execution device, apparatus or device. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution device, apparatus or device, or in conjunction with such instruction execution device, apparatus or device.

[0226] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0227] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0228] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0229] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0230] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A scenario-based government and enterprise customer perception insight method, characterized in that: The following steps are involved: Obtain a scenario-based domain name library of the object to be served, perform DNS domain name analysis and http traffic resolution based on the domain names in the domain name library, and obtain network demand data of the object to be served; Cleaning the network demand data through a preset big data analysis platform; Filter and screen the objects to be served based on the result of the data cleaning to obtain an object list; Service marketing is performed on the target objects based on the object list.

2. The scenario-based government and enterprise customer perception insight method according to claim 1 is characterized in that: The step of obtaining the scenario-based domain name library of the object to be served includes the following steps: By capturing packets for analysis and collecting visit information, the scenario-based domain name library is compiled.

3. The scenario-based government and enterprise customer perception insight method according to claim 1 is characterized in that: The DNS domain name analysis based on the domain name in the domain name library includes at least one of the following steps: Performing a local DNS query based on the domain name in the domain name library; Perform a root DNS query based on the domain name in the domain name library; Performing a top-level domain DNS query based on the domain name in the domain name library; An authoritative DNS server query is performed based on the domain name in the domain name library.

4. The scenario-based government and enterprise customer perception insight method according to claim 1 is characterized in that: The http traffic parsing is performed on the http traffic data corresponding to the domain name in the domain name library; the http traffic parsing based on the domain name in the domain name library includes at least one of the following steps: Analyze the request header and the response header based on the http traffic data to identify the specific behavior of the object to be served; Analyze the request body and the response body based on the http traffic data to extract characteristic information; The access mode of the object to be served is tracked based on the http traffic data; wherein the tracking data source of the access mode includes a service quality layer, a link quality layer and a device operation quality layer.

5. The scenario-based government and enterprise customer perception insight method according to claim 4 is characterized in that: The performing of http traffic resolution based on the domain names in the domain name library further includes the following steps: Based on the http traffic data, perform http traffic delay analysis through an http traffic delay analysis system; The http traffic data includes downlink service flow, uplink service flow and keep-alive information; the http traffic delay analysis system includes an optical line terminal, a broadband access server and an optical network unit; the http traffic delay analysis specifically includes the following operations; Collecting the time delay T2 based on the process of the downlink service flow passing through the optical line terminal; Collecting the delay T3 based on the process of the uplink service flow passing through the optical line terminal; Obtaining the delay T1 according to the sum of the delay T2 and the delay T3; A collection delay T4 based on the process of sending the keep-alive information from the broadband access server to the optical network unit; The optical network unit sends the keep-alive information to the broadband access server based on the process collection delay T5; Obtaining a delay T6 according to a difference between the delay T2 and the delay T4; The time delay T7 is obtained by integrating the time delay T3, the time delay T4 and the time delay T5.

6. The scenario-based government and enterprise customer perception insight method according to claim 1 is characterized in that: The data cleaning of the network demand data by using a preset big data analysis platform includes the following steps: The target data in the network demand data is analyzed on a big data atomic capability analysis platform to obtain the data cleaning result.

7. The scenario-based government and enterprise customer perception insight method according to claim 1 is characterized in that: The filtering and screening of the objects to be served based on the result of the data cleaning to obtain an object list includes the following steps: Taking the preset stock objects as positive samples, summarizing and obtaining the feature data corresponding to the positive samples; Based on the characteristic data, similarity matching is performed on the result of the data cleaning, and then the objects to be served are filtered and screened according to the result of the similarity matching to obtain the object list.

8. A scenario-based government and enterprise customer perception and insight device, characterized in that: include: The first module is used to obtain a scenario-based domain name library of the object to be served, perform DNS domain name analysis and http traffic resolution based on the domain names in the domain name library, and obtain network demand data of the object to be served; The second module is used to clean the network demand data through a preset big data analysis platform; The third module is used to filter and select the objects to be served based on the result of the data cleaning to obtain an object list; The fourth module is used to carry out service marketing to the target objects based on the object list.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images