Gateway identification methods, gateway identification devices, storage media and electronic devices

Abstract

This disclosure provides a gateway identification method, gateway identification device, storage medium, and electronic device, relating to the field of broadband access technology. The gateway identification method includes: extracting preset dimension data from the network data of a target user; the preset dimension data includes: gateway MAC prefix, fixed-line broadband user status, number of successful authentications within a first preset period, and number of abnormal disconnections within a first preset period; preprocessing the preset dimension data to form the target user's identification feature data; and processing the identification feature data using a pre-trained machine learning model to obtain the gateway identification result of the target user. This disclosure can detect more fault scenarios while saving manpower and time costs.

Description

Technical Field

[0001] This disclosure relates to the field of broadband access technology, and in particular to a gateway identification method, a gateway identification device, a computer-readable storage medium, and an electronic device. Background Technology

[0002] With the continuous growth of fixed-line broadband users, a large number of gateway devices from different manufacturers and models have been introduced into the market. The quality of these gateway devices varies greatly, and the number of fault reports and complaints caused by gateway quality issues is also increasing.

[0003] In related technologies, the operation and maintenance department and customer service department lack effective means to identify substandard gateway devices. Handling such work orders requires a lot of manpower and resources and it is difficult to curb the growth of related fault reports / complaints. Summary of the Invention

[0004] This disclosure provides a gateway identification method, gateway identification device, computer-readable storage medium, and electronic device, which can detect more fault scenarios at least to a certain extent while saving manpower and time costs.

[0005] According to a first aspect of this disclosure, a gateway identification method is provided, comprising:

[0006] Extract preset dimension data from the network data of the target user to be identified; the preset dimension data includes: gateway MAC prefix, fixed broadband user status, number of successful authentications within a first preset period, and number of abnormal disconnections within a first preset period.

[0007] The preset dimension data is preprocessed to form the target user's feature data to be identified;

[0008] The target user's gateway identification result is obtained by processing the feature data to be identified using a pre-trained machine learning model.

[0009] In one implementation, the number of abnormal disconnections within the first preset period includes the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period, and the step of extracting preset dimension data from the network data of the target user to be identified includes: extracting the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period from the network data of the target user to be identified.

[0010] In one implementation, the number of abnormal disconnections within the first preset period includes the total number of abnormal disconnections within the first preset period. The step of extracting preset dimension data from the network data of the target user to be identified further includes: obtaining the total number of abnormal disconnections within the first preset period based on the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period.

[0011] In one embodiment, the step of preprocessing the preset dimension data to form the target user's feature data includes: forming a data group from the preset dimension data within each first preset period according to the user identifier of the target user, and combining multiple data groups from the first preset period to form the target user's feature data.

[0012] In one implementation, the user identifier of the target user includes the gateway MAC prefix of the target user.

[0013] In one embodiment, before processing the feature data to be identified using a pre-trained machine learning model to obtain the gateway identification result of the target user, the method further includes: extracting sample data of a preset dimension from the user network data of the sample user, preprocessing it to form sample feature data, and obtaining gateway identification tag data corresponding to the sample feature data based on the fault reporting work order processing data of the sample user; constructing a training dataset and a test dataset based on the sample feature data and the gateway identification tag data; training the machine learning model using the training dataset, and testing the machine learning model using the test dataset, until the test result of the machine learning model meets a predetermined requirement, and determining that the training of the machine learning model is complete.

[0014] In one implementation, the gateway identification label data is a first value indicating that the gateway of the sample user is abnormal, and a second value indicating that the gateway of the sample user is not abnormal; the step of constructing a training dataset and a test dataset based on the sample feature data and the gateway identification label data includes: constructing the training dataset using the gateway identification label data with the first value and its corresponding sample feature data; and constructing the test dataset using the gateway identification label data with the first value and its corresponding sample feature data, and the gateway identification label data with the second value and its corresponding sample feature data.

[0015] According to a second aspect of this disclosure, a gateway identification device is provided, comprising: a preset dimension data extraction module configured to extract preset dimension data from the network data of a target user to be identified; the preset dimension data including: gateway MAC prefix, fixed broadband user status, number of successful authentications within a first preset period, and number of abnormal disconnections within a first preset period; a preprocessing module configured to preprocess the preset dimension data to form the target user's identification feature data; and a gateway identification module configured to process the identification feature data using a pre-trained machine learning model to obtain the gateway identification result of the target user.

[0016] According to a third aspect of this disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the gateway identification method of the first aspect and its possible implementations.

[0017] According to a fourth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the gateway identification method of the first aspect and possible implementations thereof by executing the executable instructions.

[0018] The technical solution disclosed herein has the following beneficial effects:

[0019] This solution extracts preset dimension data from the target user's network data. The preset dimension data includes: gateway MAC prefix, fixed-line broadband user status, number of successful authentications within a first preset period, and number of abnormal disconnections within the first preset period. The preset dimension data is preprocessed to form the target user's identification feature data. A pre-trained machine learning model is then used to process the identification feature data to obtain the target user's gateway identification result. On one hand, by using preset dimension data, the data is more comprehensive, including not only user status and gateway information but also authentication data. This allows for the detection of authentication failure scenarios, enabling the detection of more failure scenarios and thus improving the accuracy of the gateway identification result. On the other hand, by preprocessing the preset dimension data, the trained machine learning model can be directly used for gateway identification, thus eliminating reliance on manual labor and saving labor and time costs. Attached Figure Description

[0020] Figure 1 A schematic diagram of a system architecture in this exemplary embodiment is shown;

[0021] Figure 2 This diagram illustrates a gateway identification method according to an exemplary embodiment.

[0022] Figure 3 This example embodiment shows a flowchart of the machine learning model training process.

[0023] Figure 4 This example implementation shows a flowchart of dataset construction;

[0024] Figure 5 This diagram illustrates the structure of an intent recognition device according to this exemplary embodiment.

[0025] Figure 6 A schematic diagram of the structure of an electronic device in this exemplary embodiment is shown. Detailed Implementation

[0026] Exemplary embodiments of this disclosure will be described more fully below with reference to the accompanying drawings.

[0027] The accompanying drawings are schematic illustrations of this disclosure and are not necessarily drawn to scale. Some block diagrams shown in the drawings may be functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in hardware modules or integrated circuits, or in networks, processors, or microcontrollers. Implementations can be carried out in various forms and should not be construed as limited to the examples set forth herein. The features, structures, or characteristics described in this disclosure can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough description of embodiments of this disclosure. However, those skilled in the art will recognize that one or more specific details may be omitted when implementing the technical solutions of this disclosure, or other methods, components, apparatuses, steps, etc., may be used to replace one or more specific details.

[0028] With the continuous growth of fixed-line broadband users, a large number of gateway devices from different manufacturers and models have been introduced into the market. The quality of these gateway devices varies greatly, and the number of fault reports and complaints caused by gateway quality issues is also increasing.

[0029] In related technologies, the operation and maintenance department and customer service department lack effective means to identify substandard gateway devices. Handling such work orders requires a lot of manpower and resources and it is difficult to curb the growth of related fault reports / complaints.

[0030] In view of the above problems, the exemplary embodiments of this disclosure first provide a gateway identification method for outputting gateway identification results of feature data to be identified.

[0031] The following is combined with Figure 1 The system architecture and application scenarios of the operating environment of this exemplary implementation are described in an exemplary manner.

[0032] Figure 1 A schematic diagram of the system architecture is shown. This system architecture 100 may include a terminal 110 and a server 120. The server 120 can generally refer to a backend system that provides a gateway identification method, and may be a single server or a cluster of multiple servers. The terminal 110 and the server 120 can be connected via a wired or wireless communication link to exchange data.

[0033] In one implementation, terminal 110 acquires the network data of the target user to be identified. Then, terminal 110 can send the network data of the target user to server 120, and server 120 executes the gateway identification method described above to obtain the gateway identification result of the target user.

[0034] In one implementation, this exemplary implementation can also be implemented independently based on terminal 110. For example, after obtaining the network data of the target user to be identified, terminal 110 obtains the gateway identification result of the target user by executing the above-described gateway identification method.

[0035] In one implementation, this exemplary implementation can also be implemented independently based on server 120. For example, after server 120 obtains the network data of the target user to be identified, it obtains the gateway identification result of the target user by executing the above-described gateway identification method.

[0036] As can be seen from the above, in this exemplary embodiment, the intent recognition method can be executed by the terminal 110 or the server 120. This disclosure does not limit this.

[0037] The following is combined with Figure 2 The gateway identification method in this exemplary embodiment will be described. Figure 2 An exemplary flow of the gateway identification method is shown, which may include the following steps S210 to S240:

[0038] Step S210: Extract preset dimension data from the network data of the target user to be identified.

[0039] The preset dimension data includes: gateway MAC prefix, fixed broadband user status, number of successful authentications within the first preset period, and number of abnormal disconnections within the first preset period.

[0040] Step S220: Preprocess the preset dimension data to form the target user's feature data to be identified;

[0041] Step S230: Use a pre-trained machine learning model to process the feature data to be identified, and obtain the gateway identification result of the target user.

[0042] In the aforementioned gateway identification method, preset dimension data is extracted from the target user's network data. This preset dimension data includes: gateway MAC prefix, fixed-line broadband user status, number of successful authentications within a first preset period, and number of abnormal disconnections within the first preset period. The preset dimension data is preprocessed to form the target user's identification feature data. A pre-trained machine learning model is then used to process this feature data to obtain the target user's gateway identification result. On one hand, by using preset dimension data, the data is more comprehensive, including not only user status and gateway information but also authentication data. This allows for the detection of authentication failure scenarios, enabling the detection of more failure scenarios and thus improving the accuracy of the gateway identification result. On the other hand, by preprocessing the preset dimension data, the trained machine learning model can be directly used for gateway identification, thus eliminating reliance on manual labor and saving labor and time costs.

[0043] The following is about Figure 2 Each step in the process will be explained in detail.

[0044] refer to Figure 2 In step S210, preset dimension data is extracted from the network data of the target user to be identified.

[0045] The preset dimension data includes: gateway MAC prefix, fixed broadband user status, number of successful authentications within the first preset period, and number of abnormal disconnections within the first preset period.

[0046] The network data of the user to be identified includes fixed broadband service information data, authentication record data, online / offline list data, and mapping data between MAC prefixes and gateway manufacturers and models.

[0047] The gateway MAC prefix in the preset dimension data can be extracted from the mapping data between the MAC prefix and the gateway manufacturer and model in the network data of the user to be identified; the fixed broadband user status in the preset dimension data can be extracted from the fixed broadband service information data in the network data of the user to be identified; the number of successful authentications within the first preset period in the preset dimension data can be extracted from the authentication record data in the network data of the user to be identified; the number of abnormal disconnections within the first preset period in the preset dimension data can be extracted from the online / offline list data in the network data of the user to be identified; The gateway MAC prefix is ​​the prefix of the gateway MAC address, for example: aa:bb: cc:11:22:33; Fixed-line broadband user status represents the user's status in using fixed-line broadband, such as: normal (meaning the user can use fixed-line broadband normally); The number of successful authentications within the first preset period is used to measure the online status of the same / different users. For example, if user A successfully authenticates twice within the first preset period, it means that user A did not go online on the first successful authentication, or went online successfully but then went offline abnormally; The number of abnormal disconnections within the first preset period represents the number of times a user is forced offline within the first preset period. For example, if user B has 60 abnormal disconnections within the first preset period, it means that user B was forced offline 60 times within the first preset period.

[0048] The first preset period can be determined according to actual conditions; in one implementation, the first preset period can be one week or one month, and there is no limitation here.

[0049] Continue to refer to Figure 2 In step S220, the preset dimension data is preprocessed to form the target user's feature data to be identified.

[0050] The purpose of preprocessing is to transform the preset dimension data into data that is easy for machines to recognize. In one implementation, the preset dimension data can be preprocessed into a matrix. For example, if the gateway MAC prefix is ​​A1:B1:C1, the fixed broadband user status is normal (0 represents normal), the number of successful authentications in the first preset period is 30, and the number of abnormal disconnections in the second preset period is 30, the above preset dimension data can be preprocessed into a matrix [A1:B1:C1 0 30 30].

[0051] In step S220, the number of successful authentications within the first preset period is used as one of the feature data, which adds the detection of terminal failure scenarios where there is only authentication but no online status, further improving the detection scenario and enhancing the prediction accuracy.

[0052] Continue to refer to Figure 2 In step S230, a pre-trained machine learning model is used to process the feature data to be identified, and the gateway identification result of the target user is obtained.

[0053] The pre-trained machine learning model is a machine learning model that is trained using training and test datasets and is capable of identifying gateways. Here, the training dataset can use inferior gateways and their corresponding preset dimension data; the test dataset can use some abnormal gateways and their corresponding preset dimension data, as well as some normal gateways and their corresponding preset dimension data.

[0054] In one implementation, a pre-trained machine learning model can use frameworks such as NumPy and Pandas to load a training dataset and use TensorFlow tools to train the model.

[0055] In one implementation, abnormal disconnections are caused by multiple reasons. Therefore, the number of abnormal disconnections within a first preset period can include the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period. Specifically, step S210 above can include the following steps:

[0056] Extract the number of abnormal disconnections corresponding to various abnormal disconnection codes within a first preset period from the network data of the target user to be identified.

[0057] The number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period can be extracted from the online / offline list data in the network data of the user to be identified.

[0058] Abnormal disconnection codes refer to the codes corresponding to the cause of an abnormal disconnection. According to RADIUS protocol 49, there are 18 types of BAS disconnection codes. Among them, codes 2, 8, 9, 10, and 11 belong to abnormal disconnections, as shown in Table 1 below:

[0059]

[0060] Table 1

[0061] The above indicators are explained in Table 2 below:

[0062]

[0063]

[0064] Table 2

[0065] According to RADIUS protocol 49 and fault reporting work order processing data, the abnormal disconnection codes used in this embodiment are: 2, 3, 8, 9, 10, and 11, as shown in Table 3 below:

[0066]

[0067]

[0068] Table 3

[0069] In one implementation, abnormal disconnections are caused by multiple reasons; therefore, the number of abnormal disconnections within the first preset period may include the total number of abnormal disconnections within the first preset period. Specifically, step S210 above may include the following steps:

[0070] Based on the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period, the total number of abnormal disconnections within the first preset period is obtained.

[0071] The total number of abnormal disconnections within the first preset period is obtained by summing the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period. For example, the number of disconnections corresponding to carrier loss, service loss, port error, NAS error, NAS restart, and port no longer needed within the first preset period are 10, 2, 3, 8, 7, and 20 respectively. Then, summing 10, 2, 3, 8, 7, and 20 gives the total number of abnormal disconnections within the first preset period as 50.

[0072] In one implementation, preprocessing may involve combining preset dimension data within a first preset period into a data group. Specifically, step S220 above may include the following steps:

[0073] According to the user identifier of the target user, the preset dimension data in each first preset period are formed into a data group, and the data groups of multiple first preset periods are combined to form the target user's feature data to be identified.

[0074] The user identifier of the target user is data that can identify the target user. In one implementation, the user identifier of the target user includes the gateway MAC prefix of the target user.

[0075] Preset dimension data within a preset period forms a data group. If there are multiple first preset periods, multiple data groups are formed. For example, if there are two first preset periods, the preset dimension data within each of the two first preset periods forms a data group. Here, the preset dimension data within the first preset period includes the gateway MAC prefix, fixed broadband user status, number of successful authentications within the first preset period, and number of abnormal disconnections within the first preset period.

[0076] The data for the first preset period can be combined in two ways: either by using a preset dimension as the row and the first preset period as the column, or by using the first preset period as the row and the preset dimension as the column. There is no limitation here.

[0077] The feature data to be identified is obtained by combining multiple preset dimension data within a first preset period. In one implementation, the feature data to be identified can be a matrix, for example:

[0078]

[0079] In this table, column x1 represents the gateway MAC prefix; column x2 represents the broadband user status; column x3 represents the number of successful authentications for a given gateway within a week; column x4 represents the number of times a given gateway with disconnection code 2 has been offline within a week; column x5 represents the number of times a given gateway with disconnection code 3 has been offline within a week; column x6 represents the number of times a given gateway with disconnection code 8 has been offline within a week; column x7 represents the number of times a given gateway with disconnection code 9 has been offline within a week; column x8 represents the number of times a given gateway with disconnection code 10 has been offline within a week; and column x9 represents the number of times a given gateway with disconnection code 11 has been offline within a week.

[0080] In one implementation, the training dataset includes feature data and label data; wherein the label data can be determined based on fault report processing data. Specifically, refer to... Figure 3 As shown, prior to step S230 above, the method may include the following steps S310 to S330:

[0081] Step S310: Extract sample data of preset dimensions from the user network data of the sample users, perform preprocessing to form sample feature data, and obtain gateway identification tag data corresponding to the sample feature data based on the fault reporting work order processing data of the sample users.

[0082] Among them, the sample users can be selected from any region; for example, a city, a district, or a county, without any restrictions.

[0083] The preprocessing is the same as in step S220 above, and will not be repeated here. The method for obtaining the sample feature data is the same as that for obtaining the feature data to be identified in step S220 above, and will not be repeated here.

[0084] Fault report processing data refers to the pending data displayed in fault report or complaint reports. Based on this data, the problem with the gateway can be identified; for example, gateway quality issues, network cable connection problems, etc., without limitation. In one implementation, if the fault report or complaint report determines that the problem is a gateway quality issue, the gateway can be identified as a faulty gateway; if the fault report or complaint report determines that the problem is not a gateway quality issue, the gateway can be identified as a normal gateway.

[0085] Gateway identification tag data can be represented using numbers, letters, etc., without limitation. For example, if the fault report processing data indicates that the gateway is abnormal, the number 1 can be used as the gateway identification tag data; if the fault report processing data indicates that the gateway is normal, the number 0 can be used as the gateway identification tag data. In one implementation, the gateway identification tag data can be a matrix, such as:

[0086]

[0087] Where y represents the gateway identification tag data; 1 indicates that the gateway has a quality problem; 0 indicates that the gateway is normal and there is no quality problem.

[0088] Step S320: Based on the sample feature data and gateway identification label data, construct the training dataset and the test dataset.

[0089] Both the training and testing datasets include sample feature data and corresponding gateway identification label data. Since abnormal gateways are the main maintenance targets of the operation and maintenance and customer service departments in actual work, the training dataset can use sample feature data and corresponding gateway identification label data of abnormal gateways. The testing dataset can use sample feature data and corresponding gateway identification label data of some abnormal gateways and sample feature data and corresponding gateway identification label data of some normal gateways to prevent overfitting of the test machine learning model.

[0090] In one implementation, the training dataset may comprise 80% of the sample data, and the test dataset may comprise 20% of the sample data.

[0091] Step S330: Train the machine learning model using the training dataset and test the machine learning model using the test dataset until the test results of the machine learning model meet the predetermined requirements, and determine that the training of the machine learning model is complete.

[0092] The predetermined requirement refers to the prediction success rate reaching the expected value. In one implementation, the machine learning model can be trained through the following process: first, the machine learning model is trained with a training dataset until the loss function converges; second, the machine learning model is validated with a test dataset until the prediction success rate of the machine learning model reaches the expected value.

[0093] In one implementation, since the sample feature data is numerical, it is preferable to use numbers to represent the gateway identification tag data. Specifically, refer to... Figure 4 As shown, step S320 above may include steps S410 and S420:

[0094] Step S410: Construct a training dataset using the gateway identification label data with the first value and its corresponding sample feature data.

[0095] The first value can be any value, and there is no limitation here; for example, when the fault report work order processing data indicates that the gateway is an abnormal gateway, the number 1 is used as the gateway identification tag data.

[0096] Step S420: Construct a test dataset using gateway identification label data with a first value and its corresponding sample feature data, and gateway identification label data with a second value and its corresponding sample feature data.

[0097] The second value can be any value different from the first value, and there is no limitation here. For example, if the fault report processing data indicates that the gateway is an abnormal gateway, the number 1 is used as the gateway identification tag data; then, if the fault report processing data indicates that the gateway is a normal gateway, the number 0 can be used as the gateway identification tag data.

[0098] Exemplary embodiments of this disclosure also provide a gateway identification device. (See reference...) Figure 5 As shown, the gateway identification device 500 may include:

[0099] The preset dimension data extraction module 510 is configured to extract preset dimension data from the network data of the target user to be identified; the preset dimension data includes: gateway MAC prefix, fixed broadband user status, number of successful authentications within the first preset period, and number of abnormal disconnections within the first preset period.

[0100] The preprocessing module 520 is configured to preprocess the preset dimension data to form the target user's feature data to be identified.

[0101] The gateway identification module 530 is configured to use a pre-trained machine learning model to process the feature data to be identified, and obtain the gateway identification result of the target user.

[0102] In one implementation, the number of abnormal disconnections within a first preset period includes the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period. The preset dimension data extraction module 510 is configured to extract the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period from the network data of the target user to be identified.

[0103] In one implementation, the number of abnormal disconnections within the first preset period includes the total number of abnormal disconnections within the first preset period. The preset dimension data extraction module 510 is configured to obtain the total number of abnormal disconnections within the first preset period based on the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period.

[0104] In one embodiment, the preprocessing module 520 is configured to: form a data group from the preset dimension data in each first preset period according to the user identifier of the target user, and combine the data groups of multiple first preset periods to form the target user's feature data to be identified.

[0105] In one implementation, the target user's user identifier includes the target user's gateway MAC prefix.

[0106] In one embodiment, the gateway identification device 500 further includes a model training module 540, which is configured to: extract sample data of a preset dimension from the user network data of the sample users, preprocess the data to form sample feature data, and obtain gateway identification tag data corresponding to the sample feature data based on the fault reporting work order data of the sample users; construct a training dataset and a test dataset based on the sample feature data and the gateway identification tag data; train a machine learning model using the training dataset and test the machine learning model using the test dataset until the result of testing the machine learning model meets the predetermined requirements, and determine that the training of the machine learning model is complete.

[0107] In one implementation, the gateway identification label data is a first value indicating that the gateway of the sample user is abnormal, and a second value indicating that the gateway of the sample user is not abnormal. The above-mentioned model training module 540 is configured to: construct a training dataset using the gateway identification label data with the first value and its corresponding sample feature data; and construct a test dataset using the gateway identification label data with the first value and its corresponding sample feature data, as well as the gateway identification label data with the second value and its corresponding sample feature data.

[0108] The specific details of each part of the above-mentioned device have been described in detail in the method section of the implementation plan. For any undisclosed details, please refer to the implementation plan of the method section, and therefore will not be repeated here.

[0109] Exemplary embodiments of this disclosure also provide a computer-readable storage medium that can be implemented as a program product including program code, which, when run on an electronic device, causes the electronic device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. In an alternative embodiment, the program product can be implemented as a portable compact disc read-only memory (CD-ROM) including program code and can run on an electronic device, such as a personal computer. However, the program product of this disclosure is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0110] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0111] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0112] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0113] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0114] Exemplary embodiments of this disclosure also provide an electronic device, which may include a processor and a memory. The memory stores executable instructions of the processor, such as program code. The processor executes the executable instructions to perform the gateway identification method in this exemplary embodiment, such as executable... Figure 2 The method and steps.

[0115] The following is for reference. Figure 6 The electronic device is illustrated by way of a general-purpose computing device. It should be understood that... Figure 6 The electronic device 600 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0116] like Figure 6 As shown, the electronic device 600 may include: a processor 610, a memory 620, a bus 630, an I / O (input / output) interface 640, and a network adapter 650.

[0117] The memory 620 may include volatile memory, such as RAM 621 and cache unit 622, and may also include non-volatile memory, such as ROM 623. The memory 620 may also include one or more program modules 624, including but not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of the network environment. For example, program module 624 may include the modules in the gateway identification device 500 described above.

[0118] Bus 630 is used to connect different components of electronic device 600 and may include a data bus, an address bus and a control bus.

[0119] Electronic device 600 can communicate with one or more external devices 1000 (such as keyboard, mouse, external controller, etc.) through I / O interface 640.

[0120] Electronic device 600 can communicate with one or more networks via network adapter 650. For example, network adapter 650 can provide mobile communication solutions such as 3G / 4G / 5G, or wireless communication solutions such as wireless LAN, Bluetooth, and near-field communication. Network adapter 650 can communicate with other modules of electronic device 600 via bus 630.

[0121] although Figure 6 Other hardware and / or software modules, including but not limited to: displays, microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, may also be configured in electronic device 600.

[0122] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to exemplary embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0123] Those skilled in the art will understand that various aspects of this disclosure can be implemented as systems, methods, or program products. Therefore, various aspects of this disclosure can be embodied in entirely hardware implementations, entirely software implementations (including firmware, microcode, etc.), or implementations combining hardware and software aspects, collectively referred to herein as “circuit,” “module,” or “system.” Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0124] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is defined only by the appended claims.

Claims

1. A gateway identification method, characterized in that, include: Extract preset dimension data from the network data of the target user to be identified; The network data of the user to be identified includes fixed broadband service information data, authentication record data, online / offline list data, and mapping data between MAC prefix and gateway manufacturer and model. The preset dimension data includes: gateway MAC prefix, fixed broadband user status, number of successful authentications within the first preset period, and number of abnormal disconnections within the first preset period. According to the user identifier of the target user, the preset dimension data in each first preset period is formed into a data group, and multiple data groups in the first preset period are combined to form the target user's feature data to be identified. Sample data of a preset dimension is extracted from the user network data of the sample users, preprocessed to form sample feature data, and gateway identification tag data corresponding to the sample feature data is obtained based on the fault reporting work order processing data of the sample users. Based on the sample feature data and the gateway identification label data, a training dataset and a test dataset are constructed; The gateway identification tag data is a first value indicating that the sample user's gateway is abnormal, and a second value indicating that the sample user's gateway is not abnormal; The construction of training and testing datasets based on the sample feature data and the gateway identification label data includes: The training dataset is constructed using the gateway identification label data with the first value and its corresponding sample feature data; The test dataset is constructed using the gateway identification tag data and its corresponding sample feature data of the first value, and the gateway identification tag data and its corresponding sample feature data of the second value; The machine learning model is trained using the training dataset and tested using the test dataset until the test results of the machine learning model meet the predetermined requirements, at which point the training of the machine learning model is considered complete. The pre-trained machine learning model is used to process the feature data to be identified to obtain the gateway identification result of the target user; the gateway identification result indicates whether the gateway of the target user is a normal gateway or an abnormal gateway, and the abnormal gateway indicates that the gateway has quality problems.

2. The gateway identification method according to claim 1, characterized in that, The number of abnormal disconnections within the first preset period includes the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period. The step of extracting preset dimension data from the network data of the target user to be identified includes: Extract the number of abnormal disconnections corresponding to various abnormal disconnection codes within a first preset period from the network data of the target user.

3. The gateway identification method according to claim 1, characterized in that, The number of abnormal disconnections within the first preset period includes the total number of abnormal disconnections within the first preset period. The step of extracting preset dimension data from the network data of the target user to be identified further includes: The total number of abnormal disconnections within the first preset period is obtained based on the number of abnormal disconnections corresponding to various abnormal disconnection codes within the first preset period.

4. The gateway identification method according to claim 1, characterized in that, The user identifier of the target user includes the gateway MAC prefix of the target user.

5. A gateway identification device, characterized in that, include: The preset dimension data extraction module is configured to extract preset dimension data from the target user's network data to be identified; The network data of the user to be identified includes fixed broadband service information data, authentication record data, online / offline list data, and mapping data between MAC prefix and gateway manufacturer and model. The preset dimension data includes: gateway MAC prefix, fixed broadband user status, number of successful authentications within the first preset period, and number of abnormal disconnections within the first preset period. The preprocessing module is configured to preprocess the preset dimension data to form the target user's feature data to be identified; The preprocessing module is configured to form a data group from the preset dimension data within each first preset period according to the user identifier of the target user, and to combine multiple data groups from the first preset period to form the target user's feature data to be identified. The gateway identification module is configured to extract sample data of a preset dimension from the user network data of the sample user, perform preprocessing to form sample feature data, and obtain gateway identification tag data corresponding to the sample feature data based on the fault reporting work order processing data of the sample user. Based on the sample feature data and the gateway identification label data, a training dataset and a test dataset are constructed; The machine learning model is trained using the training dataset and tested using the test dataset until the test results of the machine learning model meet the predetermined requirements, at which point the training of the machine learning model is considered complete. Furthermore, the pre-trained machine learning model is used to process the feature data to be identified to obtain the gateway identification result of the target user; the gateway identification result indicates whether the gateway of the target user is a normal gateway or an abnormal gateway, and the abnormal gateway indicates that the gateway has quality problems; The gateway identification tag data is a first value indicating that the sample user's gateway is abnormal, and a second value indicating that the sample user's gateway is not abnormal; The gateway identification module is configured to construct the training dataset using the gateway identification label data of the first value and its corresponding sample feature data. The test dataset is constructed using the gateway identification tag data and its corresponding sample feature data of the first value, and the gateway identification tag data and its corresponding sample feature data of the second value.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 4.

7. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1 to 4 by executing the executable instructions.

Images