Method and device for detecting abnormal occupation of wideband port, readable storage medium and product

Abstract

The application discloses a broadband port abnormal occupation detection method and device, a readable storage medium and a computer program product. The method comprises the following steps: acquiring physical characteristic data of each terminal port in a target broadband network, wherein the physical characteristic data comprises a port name and a port occupation state; determining an occupied terminal port in the target broadband network and whether the occupied terminal port is associated with a broadband user based on the physical characteristic data; and if the target occupied terminal port is not associated with a broadband user, determining that the target occupied terminal port is a physical state abnormal occupation port.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a wideband port abnormal occupation detection method and device, readable storage medium and computer program product. BACKGROUND

[0002] With the development of fiber broadband network technology, current passive fiber networking technology has become the mainstream of network transmission technology, and with the gradual popularization of gigabit broadband, current broadband network access is mostly in the mode of fiber to the home. Wideband installation generally requires a section of optical cable to connect the end port of the splitter in the optical distribution box corresponding to the broadband user with the indoor optical network terminal, and after network opening configuration, the use of fiber broadband network is realized.

[0003] Due to the dumb resource characteristics of fiber broadband network, the end port of the splitter will not return real-time data, and the end port data needs to be manually maintained and updated in the resource management system. However, in actual situations, various abnormal factors of the end port may cause the data in the resource management system to mismatch the real data of the end port on site, which increases the difficulty and cost of subsequent broadband installation and broadband maintenance. To solve this problem, when troubleshooting the broadband, the installation and maintenance personnel need to use a detector to detect abnormal occupation of each port, which is high in labor cost and low in efficiency. SUMMARY

[0004] The purpose of the embodiments of the present application is to provide a wideband port abnormal occupation detection method and device, readable storage medium and computer program product, to solve the problem of low efficiency of wideband port abnormal occupation detection.

[0005] In order to solve the above technical problems, the present specification is implemented as follows:

[0006] In a first aspect, a wideband port abnormal occupation detection method is provided, comprising:

[0007] Obtaining physical characteristic data of each end port in a target broadband network, the physical characteristic data including port name and port occupation state;

[0008] Based on the physical characteristic data, determining the occupied end port in the target broadband network and whether the occupied end port is associated with a broadband user;

[0009] If the target end port is not associated with a broadband user, determining that the target end port is a physical state abnormal port.

[0010] Optionally, the method further comprises:

[0011] Based on whether the port occupancy status in the physical feature data is occupied or unoccupied, it is determined to be an occupied end port in the target broadband network;

[0012] Based on the mapping relationship between port names and broadband users, it is determined whether the occupied end port corresponding to the port name in the physical feature data is associated with a broadband user.

[0013] Optionally, determining whether an occupied terminal port corresponding to a port name in the physical feature data is associated with a broadband user based on the mapping relationship between port names and broadband users includes:

[0014] Based on the relationship data between port name and home customer products, determine whether the target occupied end port is associated with a home customer user;

[0015] If so, then determine the broadband user associated with the terminal port occupied by the target;

[0016] Otherwise, based on the relationship data between port names and leased line products, determine whether the target occupied end port is associated with a leased line user;

[0017] If so, then determine the broadband user associated with the terminal port occupied by the target;

[0018] Otherwise, it is determined that the terminal port occupied by the target is not associated with a broadband user.

[0019] Optionally, it also includes:

[0020] If the occupied target terminal port is associated with a broadband user, then obtain the service characteristic data of the associated broadband user.

[0021] Based on the aforementioned business characteristic data, determine whether the associated broadband user is a dormant user;

[0022] If so, then the target terminal port is determined to be an abnormal port occupied by a silent user.

[0023] Optionally, determining whether the associated broadband user is a dormant user based on the service characteristic data includes:

[0024] The business feature data is input into a prediction model based on the isolated forest algorithm. The prediction model is trained using the business feature data of different broadband users as samples and whether different broadband users are silent users as labels.

[0025] Based on the prediction results output by the prediction model, it is determined whether the associated broadband user is a dormant user.

[0026] Optionally, it also includes:

[0027] Obtain the broadband disconnection work order data of the target terminal port. The broadband disconnection work order data includes the port information corresponding to the disconnected broadband.

[0028] Based on the port information, determine whether the target terminal port is a disconnect port;

[0029] Based on whether the target terminal port is a disconnect port, determine the occupancy anomaly type corresponding to the target terminal port.

[0030] Optionally, determining the occupancy anomaly type corresponding to the target terminal port based on whether the target terminal port is a disconnect port includes:

[0031] If the target terminal port is a dismantled port and is a port with an abnormal physical state, the target terminal port is determined to be the first type of abnormal occupancy.

[0032] If the target terminal port is a disconnect port and is an abnormal port occupied by a silent user, then the target terminal port is determined to be the second type of abnormal occupancy.

[0033] If the target terminal port is a disconnected port and the associated broadband user is not a silent user, then the target terminal port is determined to be a third type of abnormal occupancy.

[0034] If the target terminal port is not a disconnected port and is a port with a physical state of abnormal occupancy, then the target terminal port is determined to be the fourth type of abnormal occupancy.

[0035] If the target terminal port is not a disconnect port and is an abnormal port occupied by a silent user, then the target terminal port is determined to be the fifth type of abnormal occupancy.

[0036] Optionally, it also includes:

[0037] Mark the occupied end ports as occupied abnormally;

[0038] Output a list of ports in the target broadband network that are marked with abnormal occupancy types.

[0039] In a second aspect, a broadband port abnormal occupancy detection device is provided, comprising a processor and a memory, wherein the memory stores a program or instructions that can run on the processor, and the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect.

[0040] Thirdly, a readable storage medium is provided that stores a program or instructions which, when executed by a processor, implement the steps of the method described in the first aspect.

[0041] Fourthly, a computer program product is provided, comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform the steps of the method described in the first aspect.

[0042] In this embodiment, physical characteristic data of each terminal port in the target broadband network is acquired. This physical characteristic data includes the port name and port occupancy status. Based on this physical characteristic data, it is determined whether the occupied terminal port in the target broadband network is associated with a broadband user. If the occupied terminal port is not associated with a broadband user, it is determined to be a port with abnormal physical occupancy. This allows for timely and accurate detection of abnormal port occupancy during broadband troubleshooting by combining the physical characteristic data of the broadband port with the association with broadband users, even in situations where the client has no power or the fiber optic cable is faulty. It also avoids the need for installation and maintenance personnel to use detectors to check for abnormal occupancy port by port, reducing detection costs. Furthermore, it is highly practical and flexible, with greater adaptability to the application scenarios of installation and maintenance personnel, improving the efficiency of abnormal port occupancy detection and reducing the difficulty and cost of subsequent broadband installation and maintenance. Attached Figure Description

[0043] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0044] Figure 1 This is one of the flowcharts illustrating the broadband port abnormal occupancy detection method according to an embodiment of this application.

[0045] Figure 2 This is the second flowchart of the broadband port abnormal occupancy detection method according to an embodiment of this application.

[0046] Figure 3 This is a schematic diagram of the process for predicting silent users according to an embodiment of this application.

[0047] Figure 4 This is the third flowchart of the broadband port abnormal occupancy detection method according to an embodiment of this application.

[0048] Figure 5 This is a structural block diagram of a broadband port abnormal occupancy detection device according to an embodiment of this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. The drawing numbers in this application are only used to distinguish the various steps in the solution and are not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.

[0050] To address the problems existing in the prior art, embodiments of this application provide a method for detecting abnormal broadband port occupancy, such as... Figure 1 As shown, the process includes steps 102 to 106.

[0051] Step 102: Obtain the physical characteristic data of each terminal port in the target broadband network. The physical characteristic data includes the port name and port occupancy status.

[0052] Here, the term "end port" refers to the port of the optical splitter located in the broadband network optical fiber distribution box that connects to the user's indoor optical network terminal. The physical characteristic data of the end port can be obtained from the operator's resource management system, mainly including the port name, port occupancy status (including occupied / unoccupied status), the optical splitter to which the port belongs, and the optical splitter mode (including primary / secondary status), etc.

[0053] Step 104: Based on the physical feature data, determine the occupied end ports in the target broadband network and whether the occupied end ports are associated with broadband users.

[0054] During broadband installation, the splitter's terminal port is connected to the corresponding broadband user's indoor optical network terminal via optical cable. Network activation configuration is performed, and the port occupancy status of the corresponding terminal port's physical characteristic data is updated to occupied. During broadband cancellation, the network logical port is removed in the resource management system, and the port occupancy status of the corresponding terminal port's physical characteristic data is updated to unoccupied.

[0055] Based on the solution provided in the above embodiments, optionally, in step 104 above, determining the occupied end port in the target broadband network and whether the occupied end port is associated with a broadband user based on the physical feature data includes: determining the occupied end port in the target broadband network based on whether the port occupancy status in the physical feature data is occupied or unoccupied; and determining whether the occupied end port corresponding to the port name in the physical feature data is associated with a broadband user based on the mapping relationship between the port name and the broadband user.

[0056] By obtaining occupancy status information from the physical characteristic data of the operator's resource management system, it can be determined whether each end port in the target broadband network has been canceled or is currently in normal use. If the occupancy status of the target end port in the physical characteristic data is "occupied," then the target end port is identified as an occupied end port. Therefore, all currently occupied end ports in the target broadband network can be screened out.

[0057] When a broadband user signs up for a target broadband product, a mapping relationship is established between the end port used by the user and the user, and this relationship is stored in a database. Therefore, by retrieving the mapping relationship record corresponding to the signed broadband product from the port names of the occupied end ports in the target broadband network, it is possible to determine whether each occupied end port is actually associated with a signed broadband user. Broadband users include home broadband users and dedicated line users, and the methods for querying whether an end port is associated with a different type of broadband user are different.

[0058] Specifically, determining whether the occupied terminal port corresponding to the port name in the physical feature data is associated with a broadband user based on the mapping relationship between port names and broadband users includes: determining whether the target occupied terminal port is associated with a home customer user based on the relationship data between port names and home customer products; if so, then the target occupied terminal port is associated with a broadband user; otherwise, determining whether the target occupied terminal port is associated with a dedicated line user based on the relationship data between port names and dedicated line products; if so, then the target occupied terminal port is associated with a broadband user; otherwise, the target occupied terminal port is not associated with a broadband user.

[0059] Step 106: If the occupied target terminal port is not associated with a broadband user, then the target terminal port is determined to be a physically occupied abnormal port.

[0060] In other words, the occupancy status information of the terminal port obtained from the operator's resource management system indicates that the corresponding terminal port is occupied. However, the terminal port is not actually associated with a broadband user. Therefore, the data of the resource management system does not match the actual data of the terminal port on site. The above steps can detect whether the terminal port is a physically occupied abnormal port or a physically occupied false port.

[0061] Combination Figure 2 The above embodiments will now be described. Figure 2 As shown, it includes the following steps:

[0062] Step 202: Obtain the physical characteristic data of all optical splitter end ports from the operator's resource management system, and combine the optical splitter information to which each end port belongs to distinguish whether the optical splitter is a first-level optical splitting mode or a second-level optical splitting mode.

[0063] Step 204: Based on the end port occupancy status information in the splitter, determine whether the corresponding port service status is occupied. If yes, proceed to step 208; otherwise, proceed to step 206.

[0064] Step 206: Unoccupied ports, i.e., the end ports of broadband that are in normal use, are not used as target ports;

[0065] Step 208: Obtain the association data of the home customer product instances corresponding to the port names of the terminal ports;

[0066] Step 210: Use the relationship data to determine whether each terminal port is associated with a home customer product. If yes, proceed to step 212; otherwise, proceed to step 214.

[0067] Step 212: Output a list of corresponding broadband (enterprise) users (i.e., residential users and enterprise dedicated line users);

[0068] Step 214: Using the affiliation relationship between corporate customers (i.e., group customers) leased line users and passive optical network (PON), obtain the association data of corporate customers connected to the splitter end port under the optical line terminal (OLT) of PON.

[0069] Step 216: Using the correlation data, determine whether the corresponding terminal port is connected to a dedicated customer line user. If yes, proceed to step 212; otherwise, proceed to step 218.

[0070] Step 218: Determine the corresponding terminal port as a port with an abnormal physical state (e.g., false occupancy).

[0071] In one embodiment, after step 104, the method further includes: if the occupied target terminal port is associated with a broadband user, then obtaining the service characteristic data of the associated broadband user; based on the service characteristic data, determining whether the associated broadband user is a silent user; if so, determining that the target terminal port is an abnormal port occupied by a silent user.

[0072] In the above embodiments, if step 104 determines that the occupied end port is associated with a broadband user, for example, step 210 determines that the end port is associated with a home customer product, and / or step 216 determines that the end port is associated with a corporate customer dedicated line, then the broadband user list output in step 212 can be combined to obtain the service characteristic data of the corresponding broadband user on the list, and further used to determine whether the corresponding end port is abnormally occupied.

[0073] Specifically, the service characteristic data of broadband users after they join the network, including residential users and corporate dedicated line users, is obtained. This mainly includes: basic broadband attribute characteristics, basic broadband service usage characteristics, and broadband service usage derived characteristics. Specific characteristics are shown in Table 1 below:

[0074] Table 1

[0075]

[0076]

[0077] Based on the acquired service characteristic data, it can be determined whether the broadband user associated with the occupied terminal port is a dormant user. This allows for the differentiation between whether the corresponding terminal port is physically occupied abnormally or is being occupied by a broadband user who has been dormant for an extended period, thus completing the detection and analysis of abnormally occupied ports.

[0078] Identifying whether a broadband user is a dormant user can be achieved using a pre-trained prediction model and broadband user service characteristic data.

[0079] Specifically, in one embodiment, determining whether the associated broadband user is a dormant user based on the service feature data includes: inputting the service feature data into a prediction model based on the isolated forest algorithm, wherein the prediction model is trained using the service feature data of different broadband users as samples and whether different broadband users are dormant users as labels; and determining whether the associated broadband user is a dormant user based on the prediction results output by the prediction model.

[0080] When training the prediction model, broadband users connected to the end ports of the broadband network can be used as target samples, and the service feature data corresponding to each broadband user can be obtained. Known inactive and non-inactive users are used as labels. The core idea of ​​the Isolation Forest algorithm is to randomly select service features of multiple broadband users, and then randomly select a feature value between the maximum and minimum values ​​of the selected feature to split the data points. This process of recursively dividing inactive users continues until all inactive users are isolated. First, a binary tree is constructed. Using the idea of ​​ensemble learning, samples and features are extracted multiple times to complete the construction of multiple trees and model training. The core parameters of the prediction model are as follows:

[0081] Set the number of binary trees in the prediction model training to 100 (n_estimators = 100); the number of broadband user samples extracted each time is 256 (max_samples = 256); the maximum depth of the tree is: max_depth = int(np.ceil(np.log2(max(max_samples, 2)))).

[0082] Using the trained prediction model, the service characteristics corresponding to the target broadband user in the full broadband user list are predicted, and the prediction result of whether the target broadband user is a dormant user is output. The implementation process of dormant user prediction is as follows: Figure 3 As shown, it includes the following steps:

[0083] Step 302: Using the broadband users corresponding to the occupied ports as samples, obtain the service feature data corresponding to each sample;

[0084] Step 304: Clean the broadband user's service feature data through service feature normalization processing.

[0085] Step 306: Perform feature correlation analysis using the distance correlation coefficient and remove features with high correlation.

[0086] Step 308: Train the prediction model based on the Isolation Forest model using an anomaly detection algorithm;

[0087] Step 310: For broadband users on the broadband user list output in step 212, identify abnormal users based on the abnormality flag and abnormality score output by the prediction model, determine whether they are silent users, and make a full target broadband user determination.

[0088] Step 312: Determine whether the target broadband user is an abnormal user based on the abnormal score. If so, proceed to step 316; otherwise, proceed to step 318.

[0089] Step 316: Identify abnormal users as inactive users;

[0090] Step 318: Determine non-abnormal users as non-silent users.

[0091] If the target broadband user is determined to be a silent user, then the associated terminal port of the target broadband user is determined to be an abnormal port occupied by the silent user.

[0092] In one embodiment, the method further includes: obtaining broadband disconnection work order data for the target terminal port, the broadband disconnection work order data including port information corresponding to the disconnected broadband; determining whether the target terminal port is a disconnection port based on the port information; and determining the occupancy anomaly type corresponding to the target terminal port based on whether the target terminal port is a disconnection port.

[0093] In the above embodiments, after determining that the occupied target terminal port is an abnormal port occupied by an unassociated broadband user, or an abnormal port occupied by a silent user associated with a broadband user, or an associated broadband user who is not a silent user, the broadband disconnection work order data of the target terminal port can be combined to further determine whether the target terminal port has been removed from the network logical port in the operator's resource management system, i.e., broadband disconnection.

[0094] When cancelling a broadband subscription, simply follow the cancellation work order and remove the network logical port in the resource management system. To save labor costs, on-site end ports are usually removed in batches on a regular basis. This can result in the broadband network being logically removed, but the end port of the optical splitter in the fiber optic distribution box may still be occupied, causing false port occupancy and reducing the effective utilization rate of the port.

[0095] To address this, for the aforementioned types of target terminal ports, broadband disconnection work order data is retrieved to obtain the port information corresponding to the disconnected broadband, such as the port name. This information is then matched with the port name of the target terminal port to determine whether the target terminal port is a disconnected port. If a broadband disconnection work order data is matched, the target terminal port is a disconnected port; otherwise, it is a port that has not been disconnected.

[0096] Furthermore, based on whether the target terminal port is a disconnected port, the corresponding occupancy anomaly type of the target terminal port is determined. Specifically, if the target terminal port is a disconnected port and a port with a physical state occupancy anomaly, the target terminal port is determined to be a first occupancy anomaly type; if the target terminal port is a disconnected port and a port occupied by a silent user, the target terminal port is determined to be a second occupancy anomaly type; if the target terminal port is a disconnected port and the associated broadband user is not a silent user, the target terminal port is determined to be a third occupancy anomaly type; if the target terminal port is not a disconnected port and a port with a physical state occupancy anomaly type, the target terminal port is determined to be a fourth occupancy anomaly type; if the target terminal port is not a disconnected port and a port occupied by a silent user, the target terminal port is determined to be a fifth occupancy anomaly type.

[0097] If the target terminal port is determined to be physically occupied, it is classified into two types based on whether it is a disconnected port: 1. Port with abnormal physical status; 2. Port with abnormal physical status and disconnected. If the target terminal port is determined to be occupied by a silent user, it is classified into two types based on whether it is a disconnected port: 1. Port with abnormal status occupied by a silent user; 2. Port with abnormal status occupied by a silent user and disconnected. If the target terminal port is determined to be a disconnected port but the connected broadband user is not a silent user, it is classified into one type: 1. Port with abnormal status occupied by a non-silent user and disconnected.

[0098] After detecting different types of abnormal occupancy of end ports, the method further includes: marking the occupancy anomaly type of the occupied end ports; and outputting a list of occupancy anomaly ports in the target broadband network that are marked with the abnormal occupancy type.

[0099] The list of abnormally occupied ports can be detected periodically and proactively pushed to frontline city and prefecture-level personnel. City and prefecture-level installation and maintenance personnel can then use this list to remove and clean up broadband terminal ports, ensuring data consistency in the resource management system and at the installation site.

[0100] The broadband port anomaly occupancy detection method in this application integrates multi-dimensional data such as the physical characteristics of broadband ports, the business characteristics of broadband market development, and broadband disconnection work orders to assess whether the occupancy of broadband terminal ports is abnormal. It is not limited to the performance data of the broadband port equipment itself, but further considers the actual business data after the broadband port is connected to the network, making it more consistent with the actual situation of network resource construction. Based on multi-dimensional features, it utilizes a combination of machine learning prediction models and business rules for optimization, ensuring the accuracy of port anomaly detection.

[0101] Combination Figure 4 The broadband port abnormal occupancy detection method of this application embodiment is described by combining multi-dimensional data.

[0102] like Figure 4 As shown, the physical characteristics 10 of the full broadband ports, the relationship between the ports and home customer product resource instances 20, and the relationship between the ports and OLT-attached enterprise users 30 are obtained. Combining the characteristics and relationships obtained above, the system jointly identifies whether the ports occupied by the physical status are connected to broadband users 40.

[0103] For broadband ports that are physically occupied but not connected to any broadband users, they are detected as abnormally occupied ports (port 50). For broadband ports that are physically occupied but connected to broadband users, the service characteristics (60) of the connected broadband users are obtained, and the anomaly detection algorithm (70) of the isolated forest is used to identify whether the connected broadband users are inactive. If they are inactive users, the corresponding broadband port is detected as an abnormally occupied port (port 80).

[0104] Obtain broadband disconnection work order data to get basic data 90 for disconnection ports. Combined with the detected abnormal physical status occupancy ports 50, abnormal occupancy ports by silent users 80, and non-silent users, determine whether the corresponding port is a disconnection port. Then, mark the ports with different abnormal occupancy types and output a full list of abnormally occupied ports 100.

[0105] In this embodiment, physical characteristic data of each terminal port in the target broadband network is acquired. This physical characteristic data includes the port name and port occupancy status. Based on this physical characteristic data, it is determined whether the occupied terminal port in the target broadband network is associated with a broadband user. If the occupied terminal port is not associated with a broadband user, it is determined to be a port with abnormal physical occupancy. This allows for timely and accurate detection of abnormal port occupancy during broadband troubleshooting by combining the physical characteristic data of the broadband port with the association with broadband users, even in situations where the client has no power or the fiber optic cable is faulty. It also avoids the need for installation and maintenance personnel to use detectors to check for abnormal occupancy port by port, reducing detection costs. Furthermore, it is highly practical and flexible, with greater adaptability to the application scenarios of installation and maintenance personnel, improving the efficiency of abnormal port occupancy detection and reducing the difficulty and cost of subsequent broadband installation and maintenance.

[0106] Optionally, such as Figure 5 As shown in the figure, this application embodiment also provides a broadband port abnormal occupancy detection device 2000, including a processor 2400 and a memory 2200. The memory 2200 stores a program or instructions that can run on the processor 2400. When the program or instructions are executed by the processor 2400, they implement the various steps of the above-described broadband port abnormal occupancy detection method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0107] This application also provides a readable storage medium storing a program or instructions. When executed by a processor, the program or instructions implement the various processes of any of the above-described broadband port abnormal occupancy detection method embodiments, achieving the same technical effect. To avoid repetition, further details are omitted here. The readable storage medium includes computer-readable storage media, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0108] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to enable a computer to execute the various processes of any of the above-described broadband port abnormal occupancy detection method embodiments and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0109] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0110] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0111] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for detecting abnormal occupancy of a broadband port, characterized in that, include: Obtain the physical characteristic data of each terminal port in the target broadband network. The physical characteristic data includes the port name and port occupancy status. Based on the physical characteristic data, determine the occupied end ports in the target broadband network and whether the occupied end ports are associated with broadband users; If the target terminal port that is occupied is not associated with a broadband user, then the target terminal port is determined to be a physically occupied abnormal port.

2. The method according to claim 1, characterized in that, The step of determining, based on the physical feature data, the occupied end ports in the target broadband network and whether the occupied end ports are associated with broadband users includes: Based on whether the port occupancy status in the physical feature data is occupied or unoccupied, it is determined to be an occupied end port in the target broadband network; Based on the mapping relationship between port names and broadband users, it is determined whether the occupied end port corresponding to the port name in the physical feature data is associated with a broadband user.

3. The method according to claim 2, characterized in that, The step of determining whether an occupied terminal port corresponding to a port name in the physical feature data is associated with a broadband user, based on the mapping relationship between port names and broadband users, includes: Based on the relationship data between port name and home customer products, determine whether the target occupied end port is associated with a home customer user; If so, then determine the broadband user associated with the terminal port occupied by the target; Otherwise, based on the relationship data between port names and leased line products, determine whether the target occupied end port is associated with a leased line user; If so, then determine the broadband user associated with the terminal port occupied by the target; Otherwise, it is determined that the terminal port occupied by the target is not associated with a broadband user.

4. The method according to claim 1, characterized in that, Also includes: If the occupied target terminal port is associated with a broadband user, then obtain the service characteristic data of the associated broadband user. Based on the aforementioned business characteristic data, determine whether the associated broadband user is a dormant user; If so, then the target terminal port is determined to be an abnormal port occupied by a silent user.

5. The method according to claim 4, characterized in that, The step of determining whether the associated broadband user is a dormant user based on the service characteristic data includes: The business feature data is input into a prediction model based on the isolated forest algorithm. The prediction model is trained using the business feature data of different broadband users as samples and whether different broadband users are silent users as labels. Based on the prediction results output by the prediction model, it is determined whether the associated broadband user is a dormant user.

6. The method according to claim 4, characterized in that, Also includes: Obtain the broadband disconnection work order data of the target terminal port. The broadband disconnection work order data includes the port information corresponding to the disconnected broadband. Based on the port information, determine whether the target terminal port is a disconnect port; Based on whether the target terminal port is a disconnect port, determine the occupancy anomaly type corresponding to the target terminal port.

7. The method according to claim 6, characterized in that, The step of determining the occupancy anomaly type of the target terminal port based on whether the target terminal port is a disconnect port includes: If the target terminal port is a dismantled port and is a port with an abnormal physical state, the target terminal port is determined to be the first type of abnormal occupancy. If the target terminal port is a disconnect port and is an abnormal port occupied by a silent user, then the target terminal port is determined to be the second type of abnormal occupancy. If the target terminal port is a disconnected port and the associated broadband user is not a silent user, then the target terminal port is determined to be a third type of abnormal occupancy. If the target terminal port is not a disconnected port and is a port with a physical state of abnormal occupancy, then the target terminal port is determined to be the fourth type of abnormal occupancy. If the target terminal port is not a disconnect port and is an abnormal port occupied by a silent user, then the target terminal port is determined to be the fifth type of abnormal occupancy.

8. The method according to claim 7, characterized in that, Also includes: Mark the occupied end ports as occupied abnormally; Output a list of ports in the target broadband network that are marked with abnormal occupancy types.

9. A broadband port abnormal occupancy detection device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the method as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 8.

11. A computer program product, characterized in that, The computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform the steps of the method as claimed in any one of claims 1 to 8.

Images