Fault mode determination method and apparatus, and electronic device

Abstract

The invention discloses a fault mode determination method and device and electronic equipment. The method comprises the following steps: receiving alarm information which is used for indicating that signal interference exists in at least one wireless network channel connected with an integrated access device (IAD); analyzing the alarm information to obtain a signal quality evaluation parameter which is used for evaluating the signal quality of the wireless network channel; the signal quality evaluation parameters are analyzed and processed through a fault mode prediction model, an output result of the signal quality evaluation parameters is obtained, the output result is a fault mode of the wireless network channel, and the fault mode is used for indicating the interference degree of the wireless network channel. According to the method and the device, the technical problem that the evaluation result is inaccurate due to the fact that the communication quality of the wireless communication channel is evaluated in a manual mode in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of wireless network technology, and in particular to a method and device for determining a failure mode, and an electronic device. Background Art

[0002] With the popularity of smart homes and mobile devices, wireless networks (such as Wi-Fi) are becoming increasingly important in home and office environments. Users are also increasingly demanding network performance and stability. However, the performance of wireless networks is often affected by various interference sources. For example, other nearby wireless networks, microwave ovens, wireless phones, etc. can all be considered as interference sources for wireless networks. These interference sources can cause channel conflicts, signal weakening, and reduce wireless communication efficiency. In related technologies, the operation and maintenance of wireless networks mainly relies on the subjective experience of the operation and maintenance personnel. Usually, the operation and maintenance personnel judge the status of the wireless communication channel through the status of the wireless communication channel and the communication quality indicators, thereby evaluating the communication quality of the wireless communication channel. Therefore, there is a problem of being unable to accurately evaluate the status of the wireless communication channel.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a method and device for determining a fault mode, and an electronic device, so as to at least solve the technical problem of inaccurate evaluation results caused by manually evaluating the communication quality of a wireless communication channel in the related art.

[0005] According to one aspect of an embodiment of the present application, a method for determining a fault mode is provided, comprising: receiving alarm information, wherein the alarm information is used to indicate the presence of signal interference in at least one wireless network channel connected to an integrated access device IAD; parsing the alarm information to obtain signal quality assessment parameters, wherein the signal quality assessment parameters are used to assess the signal quality of the wireless network channel, and the signal quality assessment parameters include at least: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the alarm information; using a fault mode prediction model to analyze and process the signal quality assessment parameters to obtain an output result of the signal quality assessment parameters, wherein the output result is a fault mode of the wireless network channel, the fault mode is used to indicate the degree of interference to the wireless network channel, and the fault mode prediction model is trained using historical signal quality assessment parameters of multiple wireless network channels as training data.

[0006] Optionally, a fault mode prediction model is used to analyze and process the signal quality assessment parameters to obtain an output result of the signal quality assessment parameters, including: comparing a first value of the received signal strength with a preset value to obtain a comparison result, wherein the first value is an actual measured value of the received signal strength, the preset value is a predicted value of the received signal strength determined during the training process of the fault mode prediction model, and the preset value is updated during the training process of the fault mode prediction model; when the comparison result indicates that the first value is greater than the preset value, a first type of fault mode judgment strategy is used to analyze and process the channel interference ratio to obtain an output result; when the comparison result indicates that the first value is less than or equal to the preset value, a second type of fault mode judgment strategy is used to analyze and process the timestamp to obtain an output result.

[0007] Optionally, the channel interference ratio is analyzed and processed using a first-class fault mode judgment strategy to obtain an output result, including: determining a second value of the channel interference ratio, wherein the second value is an actual measured value of the channel interference ratio; determining a first-class value interval to which the second value belongs, wherein the first-class value interval is used to record the channel interference ratio of the wireless network channel under a fault mode, and different first-class value intervals correspond to different fault modes, and the fault modes include: slight interference fault, moderate interference fault, and severe interference fault; and determining the fault mode corresponding to the first-class value interval as the output result.

[0008] Optionally, a second type of fault mode judgment strategy is used to analyze and process the timestamp to obtain an output result, including: determining the moment indicated by the timestamp, wherein the formats of the timestamp and the moment are different; the timestamp is data in the form of a floating point number, and the moment is data in the form of a string; determining the application period corresponding to the moment, wherein the application period includes: a peak period and a non-peak period, the peak period is a period when the frequency of network resources provided by the application wireless network is greater than or equal to the preset network resource application frequency, and the non-peak period is a period when the frequency of network resources provided by the application wireless network is less than the preset network resource application frequency; determining the fault mode corresponding to the application period as the output result, wherein different application periods correspond to different fault modes.

[0009] Optionally, the historical signal quality evaluation parameters include: historical received signal strength, historical channel interference ratio and historical timestamp measured on the wireless network channel before the current moment, the historical timestamp is used to indicate the moment when the historical signal quality evaluation parameters are obtained; the fault mode prediction model is trained by the following method: all channel identifiers contained in the training data are stored in the root node of the decision tree, wherein each channel identifier corresponds to a wireless network channel; the root node is split into multiple first child nodes according to the historical received signal strength, wherein the first child node is used to store multiple channel identifiers, and different first child nodes store different channel identifiers; for each first child node, a first evaluation index of the historical channel interference ratio relative to the first child node and a second evaluation index of the historical timestamp relative to the first child node are determined, wherein the first evaluation index is used to indicate the use of the historical channel interference ratio to determine the first child node The accuracy of the fault mode corresponding to the node, the second evaluation indicator is used to indicate the accuracy of determining the fault mode corresponding to the first sub-node using the historical timestamp; when the accuracy indicated by the first evaluation indicator is greater than the accuracy indicated by the second evaluation indicator, the historical channel interference ratio is determined as the splitting condition of the first sub-node; when the accuracy indicated by the first evaluation indicator is less than or equal to the accuracy indicated by the second evaluation indicator, the historical timestamp is determined as the splitting condition of the first sub-node; according to the splitting condition, the first sub-node is split into multiple second sub-nodes, wherein the second sub-node is used to store multiple channel identifiers, different second sub-nodes store different channel identifiers, and the number of channel identifiers stored in each second sub-node is less than or equal to the number of channel identifiers stored in each first sub-node; when the number of channel identifiers stored in each second sub-node is less than a preset number, it is determined that the training is completed.

[0010] Optionally, the root node is split into multiple first sub-nodes according to the historical received signal strength, including: splitting the channel identifier of the wireless network channel corresponding to the historical received signal strength greater than the preset received signal strength into a first sub-node, and splitting the channel identifier of the wireless network channel corresponding to the historical received signal strength less than or equal to the preset received signal strength into another first sub-node; splitting the first sub-node into multiple second sub-nodes according to the splitting condition, including: when the splitting condition is the historical channel interference ratio, splitting the channel identifier of the wireless network channel corresponding to the historical channel interference ratio greater than the preset channel interference ratio into a second sub-node, and splitting the channel identifier of the wireless network channel corresponding to the historical channel interference ratio less than or equal to the preset channel interference ratio into another second sub-node; when the splitting condition is the historical timestamp, splitting the channel identifier of the wireless network channel corresponding to the historical timestamp belonging to the peak period into a second sub-node, and splitting the channel identifier of the wireless network channel corresponding to the historical timestamp belonging to the non-peak period into another second sub-node, wherein the peak period is a period when the frequency of applying the network resources provided by the wireless network is greater than or equal to the preset network resource application frequency, and the non-peak period is a period when the frequency of applying the network resources provided by the wireless network is less than the preset network resource application frequency.

[0011] Optionally, the method also includes: obtaining the channel identifier, received signal strength and channel interference ratio of each wireless network channel connected to the IAD; deleting the channel identifier of the wireless network channel corresponding to the received signal strength less than a first threshold, and deleting the channel identifier of the wireless network channel corresponding to the channel interference ratio greater than a second threshold, to obtain the remaining channel identifiers, wherein the first threshold is a preset minimum received signal strength and the second threshold is a preset maximum channel interference ratio; determining multiple remaining wireless network channels indicated by multiple remaining channel identifiers, and determining a target wireless network channel with the highest received signal strength among the multiple remaining wireless network channels; generating an adjustment strategy based on the target channel identifier of the target wireless network channel, wherein the adjustment strategy is used to indicate that the wireless network channel is changed to the target wireless network channel corresponding to the target channel identifier.

[0012] According to another aspect of an embodiment of the present application, a device for determining a fault mode is also provided, including: a receiving module, used to receive alarm information, wherein the alarm information is used to indicate the presence of signal interference in at least one wireless network channel connected to an integrated access device IAD; a parsing module, used to parse the alarm information to obtain signal quality assessment parameters, wherein the signal quality assessment parameters are used to assess the signal quality of the wireless network channel, and the signal quality assessment parameters include at least: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the alarm information; a processing module, used to analyze and process the signal quality assessment parameters using a fault mode prediction model to obtain an output result of the signal quality assessment parameters, wherein the output result is a fault mode of the wireless network channel, the fault mode is used to indicate the degree of interference to the wireless network channel, and the fault mode prediction model is trained using historical signal quality assessment parameters of multiple wireless network channels as training data.

[0013] According to another aspect of an embodiment of the present application, there is further provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned method for determining a fault mode through the computer program.

[0014] According to another aspect of an embodiment of the present application, a computer program product is further provided, including computer instructions, which implement the steps of the above-mentioned method for determining the fault mode when the computer instructions are executed by a processor.

[0015] In an embodiment of the present application, the following method is adopted: receiving alarm information, wherein the alarm information is used to indicate that there is signal interference in at least one wireless network channel connected to the integrated access device IAD; parsing the alarm information to obtain a signal quality evaluation parameter, wherein the signal quality evaluation parameter is used to evaluate the signal quality of the wireless network channel, and the signal quality evaluation parameter at least includes: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the alarm information; using a fault mode prediction model to analyze and process the signal quality evaluation parameter to obtain an output result of the signal quality evaluation parameter, wherein the output result is a fault mode of the wireless network channel, and the fault mode is used to indicate the degree of interference of the wireless network channel, and the fault mode prediction model is obtained by training with historical signal quality evaluation parameters of multiple wireless network channels as training data, and is obtained by the integrated access device (Integrated Access The invention discloses an invention relates to a wireless network device (IAD) that automatically detects signal interference of a wireless network channel and generates an alarm message with a fault log; by parsing the alarm message and using a pattern matching algorithm to confirm the fault mode of the channel interference, the purpose of accurately evaluating the communication quality of the wireless network is achieved, thereby realizing the technical effect of improving the accuracy and speed of fault identification for the wireless network; in addition, according to the detected fault mode, the wireless network channel is adjusted to quickly respond to changes in the network environment, thereby achieving the purpose of reducing network problems caused by signal interference and realizing the technical effect of optimizing network performance, thereby solving the technical problem of inaccurate evaluation results caused by manually evaluating the communication quality of the wireless communication channel in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 is a hardware structure block diagram of a computer terminal for implementing a method for determining a fault mode according to an embodiment of the present application;

[0018] Figure 2 is a flowchart of a method for determining a fault mode according to an embodiment of the present application;

[0019] Figure 3 It is a structural diagram of a device for determining a fault mode according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0023] Wireless network channel: The transmission medium in various forms of wireless communication networks such as wireless local area network (Wi-Fi) and cellular networks (such as 4G and 5G).

[0024] In the related art, the operation and maintenance personnel are relied on to judge the status of the wireless communication channel, so as to evaluate the communication quality of the wireless communication channel. Therefore, there is a problem that the status of the wireless communication channel cannot be accurately evaluated; in addition, in the related art, the management method of the wireless network mainly relies on manual configuration and local adjustment; for example, the operation and maintenance personnel may need to manually select a channel that is less affected by interference, or adjust the transmission power to optimize network performance; however, the interference source may change at any time, and manual adjustment cannot achieve real-time tracking and optimization. Therefore, there is a problem that the dynamic changes of the network environment cannot be responded to in time. In order to solve this problem, a relevant solution is provided in the embodiment of the present application, which is described in detail below.

[0025] According to an embodiment of the present application, a method embodiment of a method for determining a fault mode is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for determining a fault mode. Figure 1 As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0028] The memory 104 may be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for determining the fault mode in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the method for determining the fault mode described above is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0029] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0030] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0031] The embodiment of the present application provides a method for determining a fault mode that can be operated in the above operating environment. Figure 2 is a flowchart of the steps of the method for determining the fault mode provided in the embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0032] Step S202: receiving alarm information, wherein the alarm information is used to indicate that signal interference exists in at least one wireless network channel connected to the integrated access device IAD.

[0033] The method provided in the embodiment of the present application is implemented by following the remote management protocol (TR-069 protocol) to interact with the IAD device, and the IAD device detects multiple wireless network channels (for example, channels transmitting Wi-Fi) connected to it. When the IAD device detects that there is signal interference in the wireless network channel, it sends an alarm message; in step S202, the IAD device communicates with the IAD device based on the TR-069 protocol to receive the alarm message sent by the IAD device; the method provided in the embodiment of the present application can be executed by an automatic configuration server (Auto Configuration Server, ACS) or a device including an ACS. In addition, before sending the alarm message, the IAD device can first convert the format of the alarm message, or the device executing the method provided in the embodiment of the present application can convert the format of the alarm message before parsing it, for example, converting it into a markup language (XML) format.

[0034] Step S204, parse the alarm information to obtain signal quality evaluation parameters, wherein the signal quality evaluation parameters are used to evaluate the signal quality of the wireless network channel, and the signal quality evaluation parameters at least include: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the alarm information.

[0035] The alarm information sent by the IAD device may include the following information: log ID (serial number of the fault log), device ID (identification of the device connected to the wireless network channel where the signal interference occurs), alarm time (the time when the alarm information is generated), and other detailed information used to evaluate the signal quality of the wireless network channel (i.e., signal quality evaluation parameters). In step S204, the alarm information is parsed to obtain the received signal strength (RSSI) and channel-to-interference ratio (C / I) of the wireless network channel where the signal interference occurs, as well as the timestamp of the time when the alarm information is generated, and other signal quality evaluation parameters of the wireless network channel.

[0036] Step S206, using the fault mode prediction model to analyze and process the signal quality assessment parameters to obtain an output result of the signal quality assessment parameters, wherein the output result is the fault mode of the wireless network channel, and the fault mode is used to indicate the degree of interference to the wireless network channel. The fault mode prediction model is trained using historical signal quality assessment parameters of multiple wireless network channels as training data.

[0037] In step S206, a pre-trained fault mode prediction model is used to analyze and process the data (i.e., signal quality assessment parameters) obtained by parsing in step S204 to obtain the result output by the fault mode prediction model, wherein the result output by the fault mode prediction model is the fault mode of the wireless network channel (e.g., slight interference fault, moderate interference fault, and severe interference fault). In different fault modes, the degree to which the wireless network channel receives signal interference is different; for example, the degree to which a wireless network channel whose fault mode is a slight interference mode is subject to signal interference is less than the degree to which a wireless network channel whose fault mode is a moderate interference mode is subject to signal interference, and the degree to which a wireless network channel whose fault mode is a moderate interference mode is subject to signal interference is less than the degree to which a wireless network channel whose fault mode is a severe interference mode is subject to signal interference. The above-mentioned fault mode prediction model is obtained by training the neural network model using the signal quality evaluation parameters of multiple wireless network channels before the current moment (i.e., historical signal quality evaluation parameters) as training data, wherein the historical signal quality evaluation parameters include: the received signal strength (RSSI) value and the channel-to-interference ratio (C / I) value of each wireless network channel connected to the IAD device before the current moment. The machine learning model can be any neural network model for classification and prediction, such as decision tree, random forest, logistic regression, etc.

[0038] When the fault mode prediction model is used in step S206, the fault mode prediction model can be loaded into the memory. For example, the raw data of the fault mode prediction model can be loaded from the non-volatile memory into the volatile memory so that the processor runs the fault mode prediction model. The raw data of the fault mode prediction model refers to unprocessed data, which usually includes parameters and structural data of the fault mode prediction model. The structural data can be a calculation relationship based on the parameters, such as the forward propagation calculation relationship between the intermediate layers and the neurons. Specifically, the structural data can include code related to the structure of the fault mode prediction model, such as code for performing related calculations between the intermediate layers and the neurons.

[0039] In one embodiment, an area for loading the fault mode prediction model can be divided in the memory, which can include a structure data storage area and a parameter storage area. The structure data storage area is used to store structure-related codes, and the parameters referenced by it can point to the address of a specific parameter in the parameter storage area through a pointer. During the training process of the fault mode prediction model, it may be necessary to frequently update the parameters, and the parameter values ​​in the parameter storage area can be updated.

[0040] Optionally, a fault mode prediction model is used to analyze and process the signal quality assessment parameters to obtain an output result of the signal quality assessment parameters, including: comparing a first value of the received signal strength with a preset value to obtain a comparison result, wherein the first value is an actual measured value of the received signal strength, the preset value is a predicted value of the received signal strength determined during the training process of the fault mode prediction model, and the preset value is updated during the training process of the fault mode prediction model; when the comparison result indicates that the first value is greater than the preset value, a first type of fault mode judgment strategy is used to analyze and process the channel interference ratio to obtain an output result; when the comparison result indicates that the first value is less than or equal to the preset value, a second type of fault mode judgment strategy is used to analyze and process the timestamp to obtain an output result.

[0041] The fault mode prediction model determines the fault mode of the wireless network channel by analyzing and processing the signal quality evaluation parameters obtained by parsing the alarm information. For example, in this embodiment, the fault mode prediction model first determines which fault mode judgment method (including the first type of fault mode judgment strategy and the second type of fault mode judgment strategy) to adopt according to the value of the received signal strength (RSSI) contained in the signal quality evaluation parameter (i.e., the first value), and then determines the fault mode of the wireless network channel by executing the specific fault mode judgment method; wherein, the fault mode prediction model determines the value of the received signal strength (RSSI) by taking the value of the received signal strength (RSSI). When the fault mode prediction model takes the value of the received signal strength (RSSI), the actual measured value of the received signal strength (RSSI) recorded in the alarm information is determined as the value of the received signal strength (RSSI) (i.e., the first value). The preset value is a value used to distinguish the fault mode judgment method. This value is a predicted value of the received signal strength. During the training process of the fault mode prediction model, the accuracy of the output result of the fault mode prediction model is improved by updating and adjusting this value; the preset value is a fixed value after the training of the fault mode prediction model is completed. In this embodiment, when the value of the received signal strength (RSSI) contained in the alarm information (i.e., the first value) is greater than the preset value, the fault mode prediction model adopts a channel interference ratio judgment strategy (i.e., the first type of fault mode judgment strategy) to determine the fault mode of the wireless network channel, wherein, under the first type of fault mode judgment strategy, the fault mode prediction model further processes the channel interference ratio (C / I) data contained in the alarm information; when the value of the received signal strength (RSSI) contained in the alarm information (i.e., the first value) is less than or equal to the preset value, the fault mode prediction model adopts a time period analysis strategy (i.e., the second type of fault mode judgment strategy) to determine the fault mode of the wireless network channel, wherein, under the second type of fault mode judgment strategy, the fault mode prediction model further processes the timestamp data contained in the alarm information. The fault mode prediction model flexibly adjusts the fault mode judgment strategy according to the different received signal strengths, improves the accuracy and efficiency of fault mode prediction, and can more accurately identify fault modes, especially in environments with large signal strength fluctuations, such as mobile communication networks, wireless local area networks, etc.

[0042] According to an optional embodiment of the present application, the channel interference ratio is analyzed and processed using a first-class fault mode judgment strategy to obtain an output result, including: determining a second value of the channel interference ratio, wherein the second value is an actual measured value of the channel interference ratio; determining a first-class value interval to which the second value belongs, wherein the first-class value interval is used to record the channel interference ratio of the wireless network channel under a fault mode, and different first-class value intervals correspond to different fault modes, and the fault modes include: slight interference fault, moderate interference fault and severe interference fault; and determining the fault mode corresponding to the first-class value interval as the output result.

[0043] As mentioned in the above embodiments, when the fault mode prediction model adopts the channel interference ratio judgment strategy (i.e., the first type of fault mode judgment strategy), the channel interference ratio (C / I) data contained in the alarm information is further processed; in this embodiment, the fault mode prediction model processes the channel interference ratio (C / I) data in the following manner to determine the fault mode of the wireless network channel. In the embodiment of the present application, different channel interference ratio (C / I) value ranges and received signal strength (RSSI) value ranges are defined for different fault modes. For example, the channel interference ratio (C / I) value range corresponding to a slight interference fault is defined as [20, 25], the channel interference ratio (C / I) value range corresponding to a moderate interference fault is defined as [15, 20], and the channel interference ratio (C / I) value range corresponding to a severe interference fault is defined as [-∞, 15]. Therefore, the fault mode prediction model can determine the fault mode of the wireless network channel by taking a value of the channel interference ratio (C / I) contained in the alarm information and determining the channel interference ratio value interval (i.e., the first type of value interval) to which the value of the channel interference ratio (C / I) (i.e., the second value) belongs; wherein, when the fault mode prediction model takes a value of the channel interference ratio (C / I), the actual measured value of the channel interference ratio (C / I) contained in the alarm information is used as the value of the channel interference ratio (i.e., the second value).

[0044] According to another optional embodiment of the present application, the second type of fault mode judgment strategy is used to analyze and process the timestamp to obtain an output result, including: determining the moment indicated by the timestamp, wherein the formats of the timestamp and the moment are different; the timestamp is data in the form of a floating point number, and the moment is data in the form of a string; determining the application period corresponding to the moment, wherein the application period includes: a peak period and a non-peak period, the peak period is a period when the frequency of network resources provided by the application wireless network is greater than or equal to the preset network resource application frequency, and the non-peak period is a period when the frequency of network resources provided by the application wireless network is less than the preset network resource application frequency; determining the fault mode corresponding to the application period as the output result, wherein different application periods correspond to different fault modes.

[0045] As mentioned in the above embodiment, when the fault mode prediction model adopts the time period analysis strategy (i.e., the second type of fault mode judgment strategy) to determine the fault mode of the wireless network channel, the timestamp data contained in the alarm information is further processed; in this embodiment, the application period of the wireless network is divided into peak period and non-peak period, wherein the peak period and the non-peak period correspond to different time intervals, the peak period is the period when communication services are intensively used (such as weekend nights), and the non-peak period is other periods except the peak period. During the peak period, the frequency of application of network resources provided by the wireless network is usually greater than or equal to the average application frequency of wireless network resources within a period (e.g., 1 day, 7 days, 30 days) (i.e., the preset network resource application frequency); and during the non-peak period, the frequency of application of network resources provided by the wireless network is usually less than the average application frequency of wireless network resources within a period (e.g., 1 day, 7 days, 30 days) (i.e., the preset network resource application frequency). In this embodiment, the fault mode prediction model can also determine the fault mode of the wireless network channel by determining which time interval the generation time of the alarm information belongs to. Specifically, the generation time of the alarm information is recorded in the timestamp contained in the alarm information. The fault mode prediction model determines the generation time of the alarm information by converting the timestamp in floating point form into a time (universal coordinated time) in string form. For example, timestamp (Timestamp) = 1625152800, then the fault mode prediction model converts it into the corresponding time (00:00:00 on July 1, 2021), and then determines whether this time belongs to the time interval corresponding to the peak period or the time interval corresponding to the non-peak period. If the time represented by the timestamp belongs to the peak period, the fault mode corresponding to the peak period is the fault mode of the wireless network channel recorded in the high alarm information. If the time represented by the timestamp belongs to the non-peak period, the fault mode corresponding to the non-peak period is the fault mode of the wireless network channel recorded in the high alarm information. In this embodiment, the failure mode corresponding to the peak period is severe interference failure, and the failure mode corresponding to the non-peak period is moderate interference failure.

[0046] According to some optional embodiments of the present application, the historical signal quality evaluation parameters include: the historical received signal strength, the historical channel interference ratio and the historical timestamp measured on the wireless network channel before the current moment, and the historical timestamp is used to indicate the moment when the historical signal quality evaluation parameters are obtained; the fault mode prediction model is trained by the following method: all channel identifiers contained in the training data are stored in the root node of the decision tree, wherein each channel identifier corresponds to a wireless network channel; the root node is split into multiple first child nodes according to the historical received signal strength, wherein the first child node is used to store multiple channel identifiers, and different first child nodes store different channel identifiers; for each first child node, a first evaluation index of the historical channel interference ratio relative to the first child node and a second evaluation index of the historical timestamp relative to the first child node are determined, wherein the first evaluation index is used to indicate the use of the historical channel interference ratio Determine the accuracy of the fault mode corresponding to the first sub-node, and the second evaluation indicator is used to indicate the accuracy of determining the fault mode corresponding to the first sub-node using the historical timestamp; when the accuracy indicated by the first evaluation indicator is greater than the accuracy indicated by the second evaluation indicator, determine the historical channel interference ratio as the splitting condition of the first sub-node; when the accuracy indicated by the first evaluation indicator is less than or equal to the accuracy indicated by the second evaluation indicator, determine the historical timestamp as the splitting condition of the first sub-node; split the first sub-node into multiple second sub-nodes according to the splitting condition, wherein the second sub-node is used to store multiple channel identifiers, different second sub-nodes store different channel identifiers, and the number of channel identifiers stored in each second sub-node is less than or equal to the number of channel identifiers stored in each first sub-node; when the number of channel identifiers stored in each second sub-node is less than a preset number, determine that the training is completed.

[0047] As mentioned in step S206, when training the fault mode prediction model, the historical signal quality evaluation parameters of multiple wireless network channels connected to the IAD device are used as training data, wherein the historical signal quality data are signal quality evaluation parameters of multiple wireless network channels connected to the IAD device at multiple times before the current time, for example, the received signal strength of the wireless network channel before the current time (i.e., the historical received signal strength), the channel interference ratio of the wireless network channel before the current time (i.e., the historical channel interference ratio), and the timestamp contained in the alarm information received before the current time (i.e., the historical timestamp). The fault mode prediction model is obtained by training any neural network model (e.g., a decision tree) that can realize classification and prediction functions using the above historical signal evaluation parameters. During the training process, for the root node of the decision tree, the value of the received signal strength (RSSI) is used as the splitting condition of the root node, and the root node is split into multiple child nodes (i.e., the first child node) directly connected to it according to the value of RSSI; in the above scheme, splitting the root node means classifying the channel identifiers stored in the root node for representing the wireless network channel into multiple sets according to the value of RSSI of each wireless network channel, wherein each set is stored as a first child node. Furthermore, according to the splitting condition corresponding to each first sub-node, each first sub-node is split into multiple nodes directly connected thereto (i.e., second sub-nodes), each second sub-node represents a fault mode, and the splitting condition is the prediction basis of the decision tree. After the decision tree predicts the fault mode of a wireless network channel, it determines the second sub-node representing the fault mode, and stores the channel identifier of the wireless network channel therein. For example, if the decision tree predicts that the fault mode of the wireless network channel represented by the channel identifier A is a slight interference fault, the channel identifier A is stored in the second sub-node representing the slight interference fault. Finally, the output result of the decision tree is the fault mode corresponding to each input channel identifier. In the above process, the prediction basis that the decision tree relies on when predicting the failure mode of a wireless network channel is the splitting condition of the first child node. The splitting conditions of the first child node include: the value of the (historical) signal-to-interference ratio (C / I) and the (historical) timestamp. The specific splitting condition adopted by each first child node is further determined by the following method: During the training process, the decision tree splits the first child node for each first child node using the (historical) signal-to-interference ratio (C / I) and the (historical) timestamp as splitting conditions, respectively, to obtain a preliminary prediction result (the failure mode corresponding to each input channel identifier); Next, the test data is used to determine the accuracy of the preliminary prediction result output when the (historical) signal-to-interference ratio (C / I) is used as the splitting condition (i.e., the first evaluation index), and the accuracy of the step prediction result output when the (historical) timestamp is used as the splitting condition (i.e., the second evaluation index), and the one with a higher accuracy is determined as the splitting condition of the first child node.The test data in the above solution is the failure mode information carried by the channel identifier (in the training process, since the failure mode of each wireless network channel is known, each channel identifier can carry the failure mode of the wireless network channel it represents). When determining the first evaluation index, the (historical) signal-to-interference ratio is used as a splitting condition, and the channel identifier contained in the first subnode is split into multiple second subnodes, and the accuracy of each second subnode is jointly determined according to the fault mode represented by the second subnode, the channel identifier contained in the second subnode, and the fault mode information carried by the channel identifier contained in the second subnode; when determining the second evaluation index, the (historical) timestamp is used as a splitting condition, and the channel identifier contained in the first subnode is split into multiple second subnodes, and the accuracy of each second subnode is jointly determined according to the fault mode represented by the second subnode, the channel identifier contained in the second subnode, and the fault mode information carried by the channel identifier contained in the second subnode; if a second subnode is obtained by splitting, the accuracy of this second subnode is the evaluation index of the (historical) signal-to-interference ratio (i.e., the first evaluation index); if multiple second subnodes are obtained by splitting, the average accuracy of these multiple second subnodes is the evaluation index of the (historical) signal-to-interference ratio (i.e., the first evaluation index). The accuracy of each second sub-node is determined by the following method: first, a preliminary prediction result output by the decision tree for the second sub-node is obtained (which is the failure mode of each channel identifier contained in the second sub-node), and then the actual failure mode of the second sub-node is determined, and the ratio of the preliminary prediction result to the actual failure mode is determined as the first evaluation index; wherein the actual failure mode of each second sub-node is the failure mode carried by the channel identifier contained in each second sub-node; for example, a first sub-node contains three channel identifiers: channel identifier 1, channel identifier 2 and channel identifier 3. During training, the decision tree uses the (historical) signal-to-interference ratio as a prediction basis to predict the wireless networks represented by channel identifier 1, channel identifier 2 and channel identifier 3 respectively. If the failure modes of the channels are all slight interference failures, then channel identifier 1, channel identifier 2 and channel identifier 3 will be stored in the second child node representing slight interference failures, and slight interference failures are the preliminary prediction results of the decision tree for channel identifier 1, channel identifier 2 and channel identifier 3; next, during the test, it is obtained that the failure mode information carried by channel identifier 1 and channel identifier 2 is slight interference failure, while the failure mode information carried by channel identifier 3 is moderate interference failure. Then, the accuracy of the preliminary prediction result output when the (historical) signal-to-interference ratio is used as the splitting condition of the first child node is: the ratio of the number of correctly predicted channel identifiers to the total number of channel identifiers = 2 / 3≈66.7% (that is, the first evaluation index is 66.7%). Iterative training is performed by the above method until the number of channel identifiers stored in each second child node is less than a preset number value (that is, the preset number), and the training is determined to be completed.

[0048] Optionally, the root node is split into multiple first sub-nodes according to the historical received signal strength, including: splitting the channel identifier of the wireless network channel corresponding to the historical received signal strength greater than the preset received signal strength into a first sub-node, and splitting the channel identifier of the wireless network channel corresponding to the historical received signal strength less than or equal to the preset received signal strength into another first sub-node; splitting the first sub-node into multiple second sub-nodes according to the splitting condition, including: when the splitting condition is the historical channel interference ratio, splitting the channel identifier of the wireless network channel corresponding to the historical channel interference ratio greater than the preset channel interference ratio into a second sub-node, and splitting the channel identifier of the wireless network channel corresponding to the historical channel interference ratio less than or equal to the preset channel interference ratio into another second sub-node; when the splitting condition is the historical timestamp, splitting the channel identifier of the wireless network channel corresponding to the historical timestamp belonging to the peak period into a second sub-node, and splitting the channel identifier of the wireless network channel corresponding to the historical timestamp belonging to the non-peak period into another second sub-node, wherein the peak period is a period when the frequency of applying the network resources provided by the wireless network is greater than or equal to the preset network resource application frequency, and the non-peak period is a period when the frequency of applying the network resources provided by the wireless network is less than the preset network resource application frequency.

[0049] As mentioned in the above example, during the training process, first, when the root node is split into multiple child nodes (i.e., the first child node) directly connected to it according to the RSSI value, specifically, the channel identifiers are classified according to the (historical) received signal strength of the wireless network channel represented by each channel identifier: the channel identifiers corresponding to the (historical) received signal strength greater than the set received signal strength (i.e., the preset received signal strength) are determined, these channel identifiers are classified into a data set, a child node (i.e., the first child node) storing the data set is generated, and the remaining channel identifiers corresponding to the (historical) received signal strength less than / equal to the set received signal strength (i.e., the preset received signal strength) are classified into another data set, and another (first) child node storing the data set is generated; wherein, the value of the preset received signal strength used when splitting the root node is the preset value used for comparison with the value of the received signal strength (i.e., the first value) when the fault mode prediction model is used, and the preset received signal strength is continuously updated and adjusted during the training process, and after the completion of this training, it is fixed before the start of the next training. In addition, when the first sub-node is split into multiple second sub-nodes, it is divided into two cases: using the (historical) signal-to-interference ratio as the splitting condition and using the (historical) timestamp as the classification condition. Among them, when using the (historical) signal-to-interference ratio as the splitting condition, classification is performed according to the value of the (historical) signal-to-interference ratio. The decision tree predicts that the wireless network channels represented by the (historical) signal-to-interference ratio that is greater than the preset channel interference ratio are the same fault mode. Therefore, the channel identifiers of the wireless network channels represented by the (historical) signal-to-interference ratio that is greater than the preset channel interference ratio are classified into one second sub-node; the decision tree predicts that the wireless network channels represented by the (historical) signal-to-interference ratio that is less than and equal to the preset channel interference ratio are the same fault mode. Therefore, the channel identifiers of the wireless network channels represented by the (historical) signal-to-interference ratio that is less than the preset channel interference ratio and the channel identifiers of the wireless network channels represented by the (historical) signal-to-interference ratio that is equal to the preset channel interference ratio are classified into another second sub-node. If the (historical) timestamp is used as the splitting condition, the channel identifiers contained in the first sub-node are classified according to the time period to which the (historical) timestamp belongs, and the channel identifiers corresponding to the (historical) timestamps belonging to the peak time period are classified into a second sub-node, and the wireless network channels represented by these channel identifiers are predicted to be a failure mode; the channel identifiers corresponding to the (historical) timestamps belonging to the non-peak time period are classified into another second sub-node, and the wireless network channels represented by these channel identifiers are predicted to be another failure mode.

[0050] Next, an example is given to illustrate the prediction process of the fault mode prediction model. The trained fault mode prediction model is in the form of a decision tree, which includes a root node, multiple nodes directly connected to the root node (i.e., first sub-nodes), and multiple nodes directly connected to the first sub-node (i.e., second sub-nodes); wherein each first sub-node represents a different received signal strength (RSSI) value range. For example, the fault mode prediction model includes four first sub-nodes, namely, a first sub-node representing an RSSI value range of [-∞, -85], a first sub-node representing an RSSI value range of [-85, -75], a first sub-node representing an RSSI value range of [-75, -65], and a first sub-node representing an RSSI value range of [-65, +∞]. Each second sub-node represents a fault mode. For example, the fault mode prediction model includes three types of second sub-nodes, namely, a second sub-node representing a slight interference fault, a second sub-node representing a moderate interference fault, and a second sub-node representing a severe interference fault. After receiving the alarm information sent by the IAD device, the device executing the method provided in the embodiment of the present application parses the alarm information to obtain the received signal strength (RSSI), signal-to-interference ratio (C / I) and timestamp of the wireless network channel that is alarmed. If only one wireless network channel is alarmed, only one set of the above information is obtained by parsing. After the above information obtained by parsing the alarm information is input into the fault mode prediction model, the fault mode prediction model takes the value of the received signal strength (RSSI), and then compares the value of the received signal strength (RSSI) with the RSSI prediction value (i.e., the preset value) to determine whether to use the signal-to-interference ratio (C / I) or the timestamp to determine the fault mode. The above RSSI prediction value (i.e., the preset value) is saved as a model parameter after the training is completed. When the value of the received signal strength (RSSI) is greater than the RSSI prediction value (i.e., the preset value), the signal-to-interference ratio (C / I) is used to determine the fault mode. Specifically, the signal-to-interference ratio (C / I) contained in the alarm information is valued to determine which signal-to-interference ratio value interval the value result of the signal-to-interference ratio (C / I) belongs to, and the fault mode represented by the signal-to-interference ratio value interval to which the value result of the signal-to-interference ratio (C / I) belongs is determined as the fault mode of the wireless network channel corresponding to the alarm information. When the value of the received signal strength (RSSI) is less than or equal to the RSSI prediction value (i.e., the preset value), the fault mode is determined by the timestamp. Specifically, it is determined whether the timestamp contained in the alarm information belongs to a peak period or a non-peak period; when the timestamp contained in the alarm information belongs to a peak period, the fault mode of the wireless network channel alarmed by the alarm information is determined to be a severe interference fault, and when the timestamp contained in the alarm information belongs to a non-peak period, the fault mode of the wireless network channel alarmed by the alarm information is determined to be a moderate interference fault.In addition, if the fault mode prediction model obtains the value of the RSSI contained in the alarm information in the first step, and the value result does not belong to any of the four RSSI value intervals of [-∞, -85], [-85, -75], [-75, -65] and [-65, +∞], it is judged that there is a possibility of IAD false alarm, and the fault mode prediction model outputs "no interference fault". For example, the input data is channel identifier (Channel) = 6, timestamp (Timestamp) = 1625152800, received signal light (RSSI) = -80, signal interference ratio (C / I) = 15. When the fault mode prediction model analyzes, it judges according to the value of RSSI at the root node, where -70 is the preset value, and the input RSSI = -80, which is less than -70, then enters the first child node for judgment using the timestamp, and judges at the first child node that the input timestamp "1625152800" is not in the peak period; then the output result is "moderate interference".

[0051] According to some other optional embodiments of the present application, the method also includes: obtaining the channel identifier, received signal strength and channel interference ratio of each wireless network channel connected to the IAD; deleting the channel identifier of the wireless network channel corresponding to the received signal strength less than a first threshold, and deleting the channel identifier of the wireless network channel corresponding to the channel interference ratio greater than a second threshold, to obtain the remaining channel identifiers, wherein the first threshold is a preset minimum received signal strength and the second threshold is a preset maximum channel interference ratio; determining multiple remaining wireless network channels indicated by multiple remaining channel identifiers, and determining a target wireless network channel with the highest received signal strength among the multiple remaining wireless network channels; generating an adjustment strategy based on the target channel identifier of the target wireless network channel, wherein the adjustment strategy is used to indicate that the wireless network channel is changed to the target wireless network channel corresponding to the target channel identifier.

[0052] In the method provided by the embodiment of the present application, after determining the failure mode of the wireless network channel, an adjustment strategy corresponding to the failure mode is also generated, wherein the adjustment strategy includes: a strategy for adjusting the channel bandwidth, a strategy for adjusting the transmission power, and a strategy for replacing the wireless network channel; for example, when the failure mode is a minor interference failure, a strategy for adjusting the channel bandwidth is adopted, or a strategy for adjusting the transmission power is adopted to adjust the bandwidth or signal transmission power of the wireless network channel indicated by the alarm information; when the failure mode is a moderate interference failure and a severe interference failure, a strategy for replacing the wireless network channel is adopted. When adopting the strategy of replacing the wireless network channel, the wireless network channel with the best signal quality is selected as the replacement target (i.e., the target wireless network channel). In this embodiment, the replacement target (i.e., the target wireless network channel) is determined by the following method. Specifically, the minimum value of the RSSI value (i.e., the first threshold) and the maximum value of the C / I value (i.e., the second threshold) are pre-set. When screening the wireless network channel with the best signal quality among the multiple wireless network channels connected to the IAD device, first, according to RSSI and C / I, multiple high-quality wireless network channels with RSSI values ​​greater than the first threshold and C / I values ​​less than the second threshold are screened out from the multiple wireless network channels connected to the IAD device, and the channel identifiers of these high-quality wireless network channels (i.e., the remaining channel identifiers) are retained. Further, the wireless network channel with the best signal quality is determined among the high-quality wireless network channels obtained by the above method. Specifically, the wireless network channel with the largest RSSI value among the high-quality wireless network channels is determined as the wireless network channel with the best signal quality, and the channel identifier of the wireless network channel with the largest RSSI value (i.e., Target channel identifier) ​​to instruct the user to switch the wireless network channel to the wireless network channel indicated by the target channel identifier. In addition, after determining the high-quality wireless network channel, the channel identifiers of the high-quality wireless network channels can be sorted in descending order according to the RSSI values ​​to obtain a sequence composed of the channel identifiers of the wireless network channels, and the sequence is output to the user, and the user chooses to change the target according to the sequence. If the strategy of adjusting the channel bandwidth is adopted, the adjusted bandwidth is determined according to the signal interference of all wireless network channels connected to the IAD device, and the signal interference of all wireless network channels connected to the IAD device is detected. If it is detected that there are fewer wireless network channels with signal interference (such as less than 60%) and the device supports a larger bandwidth, a bandwidth of 40 megahertz (MHz) or 80MHz is selected; if more interference is detected (such as greater than 60%), or the device performance is limited, a bandwidth of 20MHz is selected; the bandwidth of the channel is adjusted by setting the channel bandwidth parameter (channelWidth) in the configuration file of the wireless network channel.When the transmission power adjustment strategy is adopted, the signal interference of all wireless network channels connected to the IAD device is detected. If it is detected that there are fewer wireless network channels with signal interference (such as less than 80%), it is determined to be a large open area, and a higher transmission power, such as 100 megawatts (mW) or 200mW, is selected; if it is detected that there are more wireless network channels with signal interference (such as greater than 80%), it is determined to be an area with dense equipment, and a lower transmission power, such as 20mW or 50mW, is selected; the transmission power is adjusted by setting the transmission power parameter (transmitPower) of the channel in the configuration file of the wireless network channel. According to the above-mentioned target channel identifier, bandwidth, or transmission power, a configuration change instruction is generated, which is sent to the IAD device through the TR-069 protocol to instruct the IAD device to execute the configuration change. The management system inside the IAD device monitors the execution status of the configuration change to ensure the effectiveness and success of the change process. If a problem occurs during the change process, the device will record an error log and report to the device (such as ACS) executing the embodiment of the present application. After the configuration change is completed, the IAD device will start the self-check mechanism to detect whether the new configuration is effective and monitor the operation status of the wireless network. The self-check mechanism includes but is not limited to the following: Check the status of the wireless network channel to ensure that it has switched to the new channel; check key performance indicators such as the received signal strength (RSSI) and the signal-to-interference ratio (C / I value). Detect the status of the connected device to ensure that the device can connect and communicate normally. Status report generation: The IAD device will generate a detailed status report based on the self-check results and the current operating status. The report content includes but is not limited to: the execution result of the configuration change (success or failure), the current wireless network channel status (interference or no interference), key performance indicators (RSSI, C / I), and the device connection status. Other potential problems or warning information.

[0053] Through the above steps, the status of the wireless network channel connected to the IAD device can be detected in real time. By parsing the fault log and using the trained fault mode prediction model to confirm the fault mode of the wireless network channel, signal interference problems can be discovered and located in time, thereby improving the accuracy and speed of fault identification. This is especially true in scenarios with wide network coverage and dense users, such as city centers and large event venues, which can effectively improve the quality of network services.

[0054] Figure 3 is a structural diagram of a device for determining a fault mode according to an embodiment of the present application, such as Figure 3As shown, the apparatus for determining a fault mode includes: a receiving module 30, for receiving alarm information, wherein the alarm information is used to indicate that there is signal interference in at least one wireless network channel connected to the integrated access device IAD; a parsing module 32, for parsing the alarm information to obtain a signal quality evaluation parameter, wherein the signal quality evaluation parameter is used to evaluate the signal quality of the wireless network channel, and the signal quality evaluation parameter includes at least: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the alarm information; a processing module 34, for analyzing and processing the signal quality evaluation parameter using a fault mode prediction model to obtain an output result of the signal quality evaluation parameter, wherein the output result is a fault mode of the wireless network channel, the fault mode is used to indicate the degree of interference to the wireless network channel, and the fault mode prediction model is obtained by training using historical signal quality evaluation parameters of multiple wireless network channels as training data.

[0055] It should be noted that Figure 3 The preferred implementation of the illustrated embodiment can be found in Figure 2 The relevant description of the illustrated embodiment will not be repeated here.

[0056] An embodiment of the present application further provides a non-volatile storage medium, in which a computer program is stored, wherein the above method for determining a failure mode is executed by running the computer program on a device where the non-volatile storage medium is located.

[0057] The above-mentioned non-volatile storage medium is used to store a program that performs the following functions: receiving alarm information, wherein the alarm information is used to indicate that there is signal interference in at least one wireless network channel connected to the integrated access device IAD; parsing the alarm information to obtain signal quality assessment parameters, wherein the signal quality assessment parameters are used to assess the signal quality of the wireless network channel, and the signal quality assessment parameters at least include: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the alarm information; using a fault mode prediction model to analyze and process the signal quality assessment parameters to obtain an output result of the signal quality assessment parameters, wherein the output result is a fault mode of the wireless network channel, and the fault mode is used to indicate the degree of interference to the wireless network channel, and the fault mode prediction model is trained using historical signal quality assessment parameters of multiple wireless network channels as training data.

[0058] According to an embodiment of the present application, an electronic device is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above method for determining a fault mode through the computer program.

[0059] The processor in the above-mentioned electronic device is used to run a program that performs the following functions: receiving alarm information, wherein the alarm information is used to indicate that there is signal interference in at least one wireless network channel connected to the integrated access device IAD; parsing the alarm information to obtain signal quality assessment parameters, wherein the signal quality assessment parameters are used to assess the signal quality of the wireless network channel, and the signal quality assessment parameters at least include: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the alarm information; using a fault mode prediction model to analyze and process the signal quality assessment parameters to obtain an output result of the signal quality assessment parameters, wherein the output result is a fault mode of the wireless network channel, and the fault mode is used to indicate the degree of interference to the wireless network channel, and the fault mode prediction model is trained using historical signal quality assessment parameters of multiple wireless network channels as training data.

[0060] The embodiment of the present application also provides a computer program product, including computer instructions, which implement the steps of the above method for determining the fault mode when the computer instructions are executed by a processor.

[0061] It should be noted that the various modules in the above-mentioned fault mode determination device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0062] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0063] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0064] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0065] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0066] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0067] If the integrated unit 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 application, or the part that contributes to the relevant technology or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0068] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining a failure mode, characterized in that: include: Receiving alarm information, wherein the alarm information is used to indicate that there is signal interference in at least one wireless network channel connected to the integrated access device IAD; Parsing the warning information to obtain a signal quality assessment parameter, wherein the signal quality assessment parameter is used to assess the signal quality of the wireless network channel, and the signal quality assessment parameter at least includes: received signal strength, channel interference ratio and a timestamp, and the timestamp is used to indicate the generation time of the warning information; A fault mode prediction model is used to analyze and process the signal quality assessment parameters to obtain an output result of the signal quality assessment parameters, wherein the output result is a fault mode of the wireless network channel, and the fault mode is used to indicate the degree of interference to the wireless network channel. The fault mode prediction model is trained using historical signal quality assessment parameters of multiple wireless network channels as training data.

2. The method according to claim 1, characterized in that The signal quality assessment parameter is analyzed and processed using a fault mode prediction model to obtain an output result of the signal quality assessment parameter, including: Compare the first value of the received signal strength with a preset value to obtain a comparison result, wherein the first value is an actual measured value of the received signal strength, the preset value is a predicted value of the received signal strength determined during the training process of the fault mode prediction model, and the preset value is updated during the training process of the fault mode prediction model; When the comparison result indicates that the first value is greater than the preset value, the channel interference ratio is analyzed and processed by using a first type of fault mode judgment strategy to obtain the output result; When the comparison result indicates that the first value is less than or equal to the preset value, the timestamp is analyzed and processed using a second type of fault mode judgment strategy to obtain the output result.

3. The method according to claim 2, characterized in that The channel interference ratio is analyzed and processed by using the first type of fault mode judgment strategy to obtain the output result, including: Determine a second value of the channel-to-interference ratio, wherein the second value is an actual measured value of the channel-to-interference ratio; Determine a first value interval to which the second value belongs, wherein the first value interval is used to record the channel interference ratio of the wireless network channel in the fault mode, and different first value intervals correspond to different fault modes, and the fault modes include: slight interference fault, moderate interference fault, and severe interference fault; The failure mode corresponding to the first type of value interval is determined as the output result.

4. The method according to claim 2, characterized in that: The timestamp is analyzed and processed using the second type of failure mode judgment strategy to obtain the output result, including: Determine the moment indicated by the timestamp, wherein the timestamp and the moment are in different formats; the timestamp is data in the form of a floating point number, and the moment is data in the form of a character string; Determine an application period corresponding to the moment, wherein the application period includes: a peak period and a non-peak period, the peak period is a period when the frequency of applying the network resources provided by the wireless network is greater than or equal to the preset network resource application frequency, and the non-peak period is a period when the frequency of applying the network resources provided by the wireless network is less than the preset network resource application frequency; The failure mode corresponding to the application period is determined as the output result, wherein different application periods correspond to different failure modes.

5. The method according to claim 1, characterized in that The historical signal quality assessment parameters include: historical received signal strength, historical channel interference ratio and historical timestamp measured on the wireless network channel before the current time, and the historical timestamp is used to indicate the time when the historical signal quality assessment parameters are obtained; The failure mode prediction model is trained by the following method: storing all channel identifiers included in the training data into a root node of a decision tree, wherein each channel identifier corresponds to one of the wireless network channels; Splitting the root node into a plurality of first child nodes according to the historical received signal strength, wherein the first child nodes are used to store a plurality of the channel identifiers, and different first child nodes store different channel identifiers; For each of the first subnodes, determining a first evaluation index of the historical channel interference ratio relative to the first subnode and a second evaluation index of the historical timestamp relative to the first subnode, wherein the first evaluation index is used to indicate the accuracy of determining the fault mode corresponding to the first subnode using the historical channel interference ratio, and the second evaluation index is used to indicate the accuracy of determining the fault mode corresponding to the first subnode using the historical timestamp; When the accuracy indicated by the first evaluation indicator is greater than the accuracy indicated by the second evaluation indicator, the historical channel interference ratio is determined as the splitting condition of the first child node; when the accuracy indicated by the first evaluation indicator is less than or equal to the accuracy indicated by the second evaluation indicator, the historical timestamp is determined as the splitting condition of the first child node; Splitting the first sub-node into a plurality of second sub-nodes according to the splitting condition, wherein the second sub-nodes are used to store a plurality of the channel identifiers, different second sub-nodes store different channel identifiers, and the number of the channel identifiers stored in each second sub-node is less than or equal to the number of the channel identifiers stored in each first sub-node; When the number of the channel identifiers stored in each of the second sub-nodes is less than a preset number, it is determined that the training is completed.

6. The method according to claim 5, characterized in that The step of splitting the root node into a plurality of first child nodes according to the historical received signal strength comprises: Splitting the channel identifier of the wireless network channel corresponding to the historical received signal strength greater than the preset received signal strength into one of the first child nodes, and splitting the channel identifier of the wireless network channel corresponding to the historical received signal strength less than or equal to the preset received signal strength into another of the first child nodes; Splitting the first sub-node into a plurality of second sub-nodes according to the splitting condition includes: When the splitting condition is the historical channel interference ratio, splitting the channel identifier of the wireless network channel corresponding to the historical channel interference ratio greater than the preset channel interference ratio into one second sub-node, and splitting the channel identifier of the wireless network channel corresponding to the historical channel interference ratio less than or equal to the preset channel interference ratio into another second sub-node; When the splitting condition is the historical timestamp, the channel identifier of the wireless network channel corresponding to the historical timestamp belonging to the peak period is split into one second sub-node, and the channel identifier of the wireless network channel corresponding to the historical timestamp belonging to the non-peak period is split into another second sub-node, wherein the peak period is a period when the frequency of applying the network resources provided by the wireless network is greater than or equal to the preset network resource application frequency, and the non-peak period is a period when the frequency of applying the network resources provided by the wireless network is less than the preset network resource application frequency.

7. The method according to claim 1, characterized in that The method further comprises: Obtaining a channel identifier, a received signal strength, and a channel interference ratio of each wireless network channel connected to the IAD; Deleting the channel identifier of the wireless network channel corresponding to the received signal strength less than a first threshold, and deleting the channel identifier of the wireless network channel corresponding to the channel interference ratio greater than a second threshold, to obtain the remaining channel identifiers, wherein the first threshold is a preset minimum received signal strength, and the second threshold is a preset maximum channel interference ratio; Determine a plurality of remaining wireless network channels indicated by the plurality of remaining channel identifiers, and determine a target wireless network channel having the highest received signal strength among the plurality of remaining wireless network channels; An adjustment strategy is generated according to the target channel identifier of the target wireless network channel, wherein the adjustment strategy is used to instruct to change the wireless network channel to the target wireless network channel corresponding to the target channel identifier.

8. A device for determining a failure mode, characterized in that: include: A receiving module, configured to receive alarm information, wherein the alarm information is used to indicate that there is signal interference in at least one wireless network channel connected to the integrated access device IAD; A parsing module, used to parse the warning information to obtain a signal quality evaluation parameter, wherein the signal quality evaluation parameter is used to evaluate the signal quality of the wireless network channel, and the signal quality evaluation parameter at least includes: received signal strength, channel interference ratio and timestamp, and the timestamp is used to indicate the generation time of the warning information; A processing module is used to analyze and process the signal quality assessment parameters using a failure mode prediction model to obtain an output result of the signal quality assessment parameters, wherein the output result is a failure mode of the wireless network channel, and the failure mode is used to indicate the degree of interference to the wireless network channel. The failure mode prediction model is trained using historical signal quality assessment parameters of multiple wireless network channels as training data.

9. An electronic device, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method for determining a fault mode according to any one of claims 1 to 7 through the computer program.

10. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method for determining a failure mode according to any one of claims 1 to 7 are implemented.

Images