High-speed rail network fault determination method and device, equipment and storage medium
By acquiring and analyzing the coverage and perception data of this network and the different network, using intelligent models to identify high-speed rail network failures, the problem of low manual identification accuracy is solved, and the precise positioning of high-speed rail network failures is achieved.
Patent Information
- Application Number
- CN202510857504.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-24
- Publication Date
- 2025-09-05
AI Technical Summary
In the prior art, high-speed rail network fault identification mainly relies on manual identification and has poor accuracy.
By obtaining the coverage and perception data of this network and the different network, the pre-trained intelligent model determines the different network perception data, and combining the network and the different network data to determine the fault section, including training intelligent models, building training samples, dimensionality reduction features, pre-processing data, and building fault maps.
It improves the accuracy of fault identification in high-speed rail networks and ensures the accurate location of faulty sections.
Smart Images
Figure CN120602984A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of communication technology, and in particular to a method, apparatus, device, and storage medium for determining a high-speed rail network fault. Background Art
[0002] As time goes by, users' demands for network quality are becoming increasingly stringent. To meet these demands, operators are deploying networks along high-speed rail lines. However, due to the complex nature of the network along high-speed rail lines, current methods for identifying problem points in high-speed rail networks rely primarily on manual identification, resulting in poor accuracy. Summary of the Invention
[0003] The present disclosure provides a high-speed rail network fault determination method, apparatus, device and storage medium, which at least to a certain extent improve the accuracy of high-speed rail network fault identification.
[0004] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.
[0005] According to one aspect of the present disclosure, a method for determining a high-speed rail network fault is provided, comprising:
[0006] Obtain local network coverage data, local network perception data, and other network coverage data;
[0007] Determine the corresponding network perception data based on the pre-trained intelligent model;
[0008] Determine the road section with faults based on the local network coverage data, local network perception data, other network coverage data and other network perception data.
[0009] In one embodiment of the present disclosure, the method further includes:
[0010] The intelligent model is trained based on the network coverage data and the network perception data to obtain a trained intelligent model.
[0011] In one embodiment of the present disclosure, the network coverage data and the network perception data are used to train an intelligent model to obtain a trained intelligent model, including:
[0012] Construct training samples based on local network coverage data and local network perception data;
[0013] The intelligent model is trained based on the training samples, and when the corresponding loss function value converges, a trained intelligent model is obtained.
[0014] In one embodiment of the present disclosure, the network coverage data includes the network's Internet TV (OTT) data and the network's mobile measurement report (MR) data, and the network perception data includes the network's deep packet inspection (DPI) data. An intelligent model is trained based on training samples. When the corresponding loss function value converges, a trained intelligent model is obtained, including:
[0015] Associate the local network MR data and DPI data based on user identification and timestamp;
[0016] Correlate the network's OTT data and MR data based on latitude, longitude and timestamp;
[0017] Perform dimensionality reduction on the associated local MR data, local DPI data, and local OTT construction to obtain the reduced MR features, local DPI features, and local OTT features of the local network;
[0018] Training the intelligent model so that it can convert the OTT features of the local network into the MR features of the local network, and convert the MR features of the local network into the DPI features of the local network;
[0019] When the corresponding loss function value converges, the trained intelligent model is obtained.
[0020] In one embodiment of the present disclosure, the method further includes:
[0021] The network coverage data and the network perception data are preprocessed to remove null values and abnormal data in the network coverage data and the network perception data.
[0022] In one embodiment of the present disclosure, the method further includes:
[0023] Construct a fault map based on the road section with faults, the local network coverage data corresponding to the road section with faults, the local network perception data, and the coverage data of other networks;
[0024] The fault graph is input into the pre-trained graph neural network intelligent model to obtain the root cause of the fault.
[0025] In one embodiment of the present disclosure, determining a road section having a fault based on local network coverage data, local network perception data, foreign network coverage data, and foreign network perception data includes:
[0026] Determine the business ratio of different lines at different time points based on the high-speed rail timetable and high-speed rail lines;
[0027] Determine multiple thresholds based on business proportions;
[0028] Compare the local network coverage data, local network perception data, foreign network coverage data and foreign network perception data with the corresponding thresholds to determine the road section with faults.
[0029] According to another aspect of the present disclosure, a high-speed rail network fault determination device is provided, comprising:
[0030] Acquisition module, used to obtain local network coverage data, local network perception data and other network coverage data;
[0031] A first determination module is used to determine the foreign network perception data corresponding to the foreign network coverage data based on a pre-trained intelligent model;
[0032] The second determination module is used to determine the road section with faults based on the coverage data of the local network, the perception data of the local network, the coverage data of the foreign network and the perception data of the foreign network.
[0033] In one embodiment of the present disclosure, the apparatus further comprises:
[0034] The training module is used to train the intelligent model based on the network coverage data and the network perception data to obtain a trained intelligent model.
[0035] In one embodiment of the present disclosure, the training module includes:
[0036] A construction unit, configured to construct training samples based on the coverage data and the perception data of the network;
[0037] The training unit is used to train the intelligent model based on the training samples, and obtain the trained intelligent model when the corresponding loss function value converges.
[0038] In one embodiment of the present disclosure, the network coverage data includes the network's Internet TV OTT data and the network's mobile measurement report MR data, and the network perception data includes the network's deep packet inspection DPI data;
[0039] Training modules include:
[0040] A first associating subunit is configured to associate the local network MR data and the DPI data based on the user identifier and the timestamp;
[0041] The second association subunit is used to associate the OTT data and MR data of the local network based on latitude and longitude and timestamp;
[0042] The dimensionality reduction subunit is used to reduce the dimensionality of the associated local network MR data, local network DPI data and local network OTT construction to obtain the reduced dimensionality local network MR features, local network DPI features and local network OTT features;
[0043] The conversion subunit is used to train the intelligent model so that the intelligent model can convert the OTT features of the local network into the MR features of the local network, and convert the MR features of the local network into the DPI features of the local network;
[0044] The completion subunit is used to obtain a trained intelligent model when the corresponding loss function value converges.
[0045] In one embodiment of the present disclosure, the apparatus further comprises:
[0046] The preprocessing module is used to preprocess the network coverage data and the network perception data, and remove the null values and abnormal data in the network coverage data and the network perception data.
[0047] In one embodiment of the present disclosure, the second determining module includes:
[0048] A first determining unit is configured to determine the business ratios of different lines at different time points based on the high-speed rail timetable and high-speed rail lines;
[0049] A second determining unit, configured to determine a plurality of thresholds based on the business ratio;
[0050] The third determination unit is used to compare the local network coverage data, the local network perception data, the foreign network coverage data and the foreign network perception data with the corresponding threshold values respectively to determine the road section with the fault.
[0051] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned high-speed rail network fault determination method by executing the executable instructions.
[0052] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned high-speed rail network fault determination method is implemented.
[0053] The high-speed rail network fault determination method, device, equipment and storage medium provided by the embodiments of the present disclosure obtain the coverage data of the current network, the perception data of the current network and the coverage data of other networks, determine the perception data of other networks corresponding to the coverage data of other networks based on a pre-trained intelligent model, determine the section with faults based on the coverage data of the current network, the perception data of the current network, the coverage data of other networks and the perception data of other networks, determine the perception data of other networks through the coverage data of other networks, and then determine the section with faults based on the coverage data of the current network, the perception data of the current network, the coverage data of other networks and the perception data of other networks, thereby improving the accuracy of the determined section with faults.
[0054] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.
[0056] Figure 1 A high-speed rail network fault determination system architecture diagram according to an embodiment of the present disclosure is shown;
[0057] Figure 2 A flow chart of a method for determining a high-speed rail network fault according to an embodiment of the present disclosure is shown;
[0058] Figure 3 A flow chart of another method for determining a high-speed rail network fault according to an embodiment of the present disclosure is shown;
[0059] Figure 4 A flow chart of another method for determining a high-speed rail network fault according to an embodiment of the present disclosure is shown;
[0060] Figure 5 A flow chart of another method for determining a high-speed rail network fault according to an embodiment of the present disclosure is shown;
[0061] Figure 6 A flow chart of another method for determining a high-speed rail network fault according to an embodiment of the present disclosure is shown;
[0062] Figure 7 A flow chart of another method for determining a high-speed rail network fault according to an embodiment of the present disclosure is shown;
[0063] Figure 8 A flow chart of another method for determining a high-speed rail network fault according to an embodiment of the present disclosure is shown;
[0064] Figure 9 A structural diagram of a high-speed rail network fault determination device according to an embodiment of the present disclosure is shown;
[0065] Figure 10 A structural block diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0066] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
[0067] In addition, the accompanying drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0068] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0069] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0070] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".
[0071] It should be pointed out that, in the absence of conflict, the embodiments of the present disclosure and the technical features therein may be combined with each other.
[0072] The specific implementation of the embodiment of the present disclosure is described in detail below with reference to the accompanying drawings.
[0073] Figure 1 A schematic structural diagram of a high-speed rail network fault determination system in an embodiment of the present disclosure is shown. The system can apply the high-speed rail network fault determination method or high-speed rail network fault determination device in various embodiments of the present disclosure.
[0074] like Figure 1As shown, the high-speed rail network fault determination system 10 may include a data acquisition module 101 and a high-speed rail network fault determination module 102. The data acquisition module 101 and the high-speed rail network fault determination module 102 may be located on two different devices. The data acquisition module 101 may be a module on an electronic device with data acquisition capabilities, such as a recording device with sound collection capabilities, a photographic device with image collection capabilities, and a computer with text information collection capabilities. The high-speed rail network fault determination module 102 may be a module on an electronic device with processing capabilities, such as a computer. The data acquisition module 101 and the high-speed rail network fault determination module 102 may be located on the same device. For example, the data acquisition module 101 and the high-speed rail network fault determination module 102 may be an input module and a processing module on a computer or a mobile phone.
[0075] The data acquisition module 101 and the high-speed rail network fault determination module 102 are connected to each other via a network, which may be a wired network or a wireless network.
[0076] Optionally, the wireless network or wired network described above uses standard communication technologies and / or protocols. The network is typically the Internet, but may be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network, or any combination of a virtual private network. In some embodiments, technologies and / or formats including Hypertext Markup Language (HTML) and Extensible Markup Language (XML) are used to represent data exchanged over the network. In addition, conventional encryption technologies such as Secure Sockets Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), and Internet Protocol Security (IPsec) may be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies may be used to replace or supplement the above-mentioned data communication technologies.
[0077] The following describes a situation where the data acquisition module 101 and the high-speed rail network fault determination module 102 are located on two different devices.
[0078] The data acquisition module 101 may be located on a terminal device, which may be various electronic devices, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, wearable devices, augmented reality devices, virtual reality devices, etc.
[0079] Optionally, the client of the application installed in different terminal devices is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile phone client, a PC client, etc.
[0080] The high-speed rail network fault determination module 102 may be located on a high-speed rail network fault determination module. The high-speed rail network fault determination module may be a high-speed rail network fault determination module that provides various services, such as a backend management high-speed rail network fault determination module that provides support for devices operated by users using terminal devices. The backend management high-speed rail network fault determination module may analyze and process received data such as requests, and feed back the processing results to the terminal device.
[0081] Optionally, the high-speed rail network fault determination module can be an independent physical high-speed rail network fault determination module, or it can be a high-speed rail network fault determination module cluster or distributed system composed of multiple physical high-speed rail network fault determination modules, or it can be a cloud high-speed rail network fault determination module that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.
[0082] Those skilled in the art will know that Figure 1 The number of data acquisition modules and high-speed rail network fault determination modules is merely illustrative, and any number of video receiving modules and high-speed rail network fault determination modules may be provided according to actual needs. This disclosure does not limit this.
[0083] In order to solve the above problems, the embodiments of the present disclosure provide a high-speed rail network fault determination method, apparatus, device and storage medium.
[0084] Figure 2 A flow chart of a high-speed rail network fault determination method in an embodiment of the present disclosure is shown.
[0085] like Figure 2 As shown, the method may include:
[0086] S210, obtaining local network coverage data, local network perception data, and foreign network coverage data.
[0087] In some embodiments, the local network coverage data may include coverage data corresponding to the current operator. The local network perception data may include perception data corresponding to the current operator. The foreign network coverage data may include coverage data corresponding to an operator different from the current operator.
[0088] In some embodiments, the network coverage data may include data on signal coverage or service coverage that can be provided within a geographical space or device range.
[0089] In some embodiments, the network coverage data may include network signal coverage range, signal strength distribution, network service availability, mapping relationship between geographic location and coverage area, access status of users or devices in different areas, network Internet TV (Over-The-Top, OTT) data and mobile measurement report (MR) data.
[0090] In some embodiments, perception data refers to indicators of perception-related services, which include Douyin, WeChat messages / calls, FTP uploads and downloads, etc. Its indicators include the number of Douyin freezes, WeChat picture sending delays, FTP download rates, etc.
[0091] In some embodiments, the network perception data may include environmental perception data, device status data, user behavior data, event perception data, and deep packet inspection (DPI) data.
[0092] It should be noted that any operator can only obtain OTT data of other operators.
[0093] S220: Determine the foreign network perception data corresponding to the foreign network coverage data based on a pre-trained intelligent model.
[0094] In some embodiments, foreign network coverage data may be input into a pre-trained intelligent model.
[0095] S230: Determine a road section with a fault based on the local network coverage data, the local network perception data, the foreign network coverage data, and the foreign network perception data.
[0096] In some embodiments, the road section with the fault may be determined based on predetermined judgment rules or a problem point analysis rule base as well as local network coverage data, local network perception data, foreign network coverage data, and foreign network perception data.
[0097] In the embodiment of the present disclosure, the coverage data of the current network, the perception data of the current network and the coverage data of the foreign network are obtained, and the foreign network perception data corresponding to the foreign network coverage data are determined based on a pre-trained intelligent model. The road section with faults is determined based on the coverage data of the current network, the perception data of the current network, the coverage data of the foreign network and the perception data of the foreign network. The foreign network perception data is determined through the coverage data of the foreign network, and then the road section with faults is determined based on the coverage data of the current network, the perception data of the current network, the coverage data of the foreign network and the perception data of the foreign network, thereby improving the accuracy of the determined road section with faults.
[0098] Figure 3 A flow chart of another high-speed rail network fault determination method in an embodiment of the present disclosure is shown.
[0099] like Figure 3 As shown, the method may include:
[0100] S310, obtaining local network coverage data, local network perception data, and foreign network coverage data;
[0101] S320: Train the intelligent model based on the network coverage data and the network perception data to obtain a trained intelligent model.
[0102] In some embodiments, training the intelligent model based on the network coverage data and the network perception data may include training the intelligent model based on the network coverage data and the network perception data to be an intelligent model capable of converting coverage data into perception data.
[0103] In some embodiments, the above-mentioned network coverage data and network perception data can be used as training sample sets to train the above-mentioned intelligent model.
[0104] S330: Determine the alien network perception data corresponding to the alien network coverage data based on a pre-trained intelligent model.
[0105] S340: Determine a road section with a fault based on the local network coverage data, the local network perception data, the foreign network coverage data, and the foreign network perception data.
[0106] In the embodiment of the present disclosure, local network coverage data, local network perception data and foreign network coverage data are obtained, foreign network perception data corresponding to foreign network coverage data is determined based on a pre-trained intelligent model, and a road section with a fault is determined based on the local network coverage data, local network perception data, foreign network coverage data and foreign network perception data. The intelligent model is trained with the local network perception data and the local network coverage data to obtain a trained intelligent model, which can make the trained intelligent model more accurate during data conversion.
[0107] Figure 4 A flow chart of another high-speed rail network fault determination method in an embodiment of the present disclosure is shown.
[0108] like Figure 4 As shown, the method may include:
[0109] S410, obtaining local network coverage data, local network perception data, and foreign network coverage data;
[0110] S420, constructing training samples based on the local network coverage data and the local network perception data;
[0111] S430: Train the intelligent model based on the training samples, and obtain a trained intelligent model when the corresponding loss function value converges.
[0112] In some embodiments, training based on the above-mentioned training samples may include taking the coverage data of the network as input, taking the perception data of the network as the standard value, and then determining the loss function value based on the standard value and the output of the intelligent model. If the loss function value does not converge, the intelligent model is trained multiple times until the loss function value converges.
[0113] S440: Determine the alien network perception data corresponding to the alien network coverage data based on a pre-trained intelligent model.
[0114] S450: Determine a road section with a fault based on the local network coverage data, the local network perception data, the foreign network coverage data, and the foreign network perception data.
[0115] In the embodiment of the present disclosure, local network coverage data, local network perception data and foreign network coverage data are obtained, foreign network perception data corresponding to foreign network coverage data is determined based on a pre-trained intelligent model, and a road section with a fault is determined based on the local network coverage data, local network perception data, foreign network coverage data and foreign network perception data. The intelligent model is trained with the local network perception data and the local network coverage data to obtain a trained intelligent model, which can make the trained intelligent model more accurate during data conversion.
[0116] Figure 5 A flow chart of another high-speed rail network fault determination method in an embodiment of the present disclosure is shown.
[0117] like Figure 5 As shown, the method may include:
[0118] S510, obtaining local network coverage data, local network perception data, and foreign network coverage data;
[0119] S520: Associate the local network MR data and the DPI data based on the user identifier and the timestamp.
[0120] In some embodiments, the local network MR data and DPI data with the same user identifier and the same timestamp may be associated.
[0121] S530: Associating the local network OTT data and MR data based on the latitude, longitude and timestamp.
[0122] In some embodiments, the local network OTT data and MR data with the same timestamp and longitude and latitude differences within a preset range can be associated.
[0123] S540: Perform dimensionality reduction on the associated local network MR data, local network DPI data, and local network OTT construction to obtain the reduced dimensionality local network MR features, local network DPI features, and local network OTT features.
[0124] In some embodiments, the associated local network MR data, local network DPI data and local network OTT construction can be reduced in dimension based on the feature extraction model to obtain the reduced-dimensional local network MR features, local network DPI features and local network OTT features.
[0125] S550: Train the intelligent model so that the intelligent model can convert the OTT features of the local network into the MR features of the local network, and convert the MR features of the local network into the DPI features of the local network;
[0126] S560: When the corresponding loss function value converges, a trained intelligent model is obtained.
[0127] S570, determining the foreign network perception data corresponding to the foreign network coverage data based on the pre-trained intelligent model;
[0128] S580: Determine a road section with a fault based on the local network coverage data, the local network perception data, the foreign network coverage data, and the foreign network perception data.
[0129] In the embodiment of the present disclosure, local network coverage data, local network perception data and foreign network coverage data are obtained, foreign network perception data corresponding to foreign network coverage data is determined based on a pre-trained intelligent model, and a road section with a fault is determined based on the local network coverage data, local network perception data, foreign network coverage data and foreign network perception data. The intelligent model is trained with the local network perception data and the local network coverage data to obtain a trained intelligent model, which can make the trained intelligent model more accurate during data conversion.
[0130] Figure 6 A flow chart of another high-speed rail network fault determination method in an embodiment of the present disclosure is shown.
[0131] like Figure 6 As shown, the method may include:
[0132] S610, obtaining local network coverage data, local network perception data, and foreign network coverage data;
[0133] S620: Pre-process the network coverage data and the network perception data to remove null values and abnormal data in the network coverage data and the network perception data.
[0134] In some embodiments, a range may be set for data based on different types of data covered by the network and different types of data perceived by the network. When the data exceeds the set range corresponding to the current data type, the current data is determined to be abnormal data.
[0135] In some embodiments, null values in the local network coverage data and the local network perception data may be removed based on a null value detection algorithm.
[0136] S630, determining the foreign network perception data corresponding to the foreign network coverage data based on the pre-trained intelligent model;
[0137] S640: Determine a road section with a fault based on the local network coverage data, the local network perception data, the foreign network coverage data, and the foreign network perception data.
[0138] In the embodiment of the present disclosure, local network coverage data, local network perception data and foreign network coverage data are obtained, and foreign network perception data corresponding to the foreign network coverage data is determined based on a pre-trained intelligent model. The road section with faults is determined based on the local network coverage data, local network perception data, foreign network coverage data and foreign network perception data. By removing null values in the local network coverage data and the local network perception data, the trained intelligent model can be made more accurate.
[0139] Figure 7 A flow chart of another high-speed rail network fault determination method in an embodiment of the present disclosure is shown.
[0140] like Figure 7 As shown, the method may include:
[0141] S710, obtaining local network coverage data, local network perception data, and remote network coverage data;
[0142] S720, determining the foreign network perception data corresponding to the foreign network coverage data based on the pre-trained intelligent model;
[0143] S730: Determine the business ratios of different lines at different time points based on the high-speed rail timetable and high-speed rail lines.
[0144] In some embodiments, a high-speed train schedule may include the time points at which the high-speed train arrives at different stations. A high-speed train route may include the locations that the high-speed train passes through. By determining the high-speed train schedule and the high-speed train route, the locations of different high-speed trains at different times can be determined.
[0145] In some embodiments, unlike everyday network environments, high-speed rail networks are time- and location-dependent, requiring significantly different network environments at different times and locations. The service ratios for different lines at different time points are determined based on the high-speed rail schedule and lines.
[0146] S740: Determine multiple thresholds based on the business ratio.
[0147] In some embodiments, determining multiple thresholds based on the business ratio may include setting different thresholds at different time periods at the same location, and setting different thresholds at different locations at the same time period.
[0148] S750: Compare the local network coverage data, local network perception data, foreign network coverage data, and foreign network perception data with corresponding thresholds to determine the road section with the fault.
[0149] In some embodiments, each data may be compared with a threshold value corresponding to the current data. If one or more data exceed a preset threshold value, it is determined that a fault exists on the current road section.
[0150] Figure 8 A flow chart of another high-speed rail network fault determination method in an embodiment of the present disclosure is shown.
[0151] like Figure 8 As shown, the method may include:
[0152] S810, obtaining local network coverage data, local network perception data, and remote network coverage data;
[0153] S820, determining the foreign network perception data corresponding to the foreign network coverage data based on the pre-trained intelligent model;
[0154] S830: Determine a road section with a fault based on the local network coverage data, the local network perception data, the other network coverage data, and the other network perception data.
[0155] S840: Construct a fault map based on the road section with the fault, the local network coverage data corresponding to the road section with the fault, the local network perception data, and the cross-network coverage data.
[0156] In some embodiments, the road section with the fault, the local network coverage data, local network perception data, and foreign network coverage data corresponding to the road section with the fault can be used as nodes. The relationships between road sections can be used as edges to connect the nodes. Alternatively, the presence of identical or similar local network coverage data, local network perception data, and foreign network coverage data can be used as edges to connect different nodes.
[0157] S850 inputs the fault graph into a pre-trained graph neural network intelligent model to obtain the root cause of the fault.
[0158] In some embodiments, the root cause of the fault may include reasons that lead to the failure of multiple road segments.
[0159] Based on the same inventive concept, the present disclosure also provides a high-speed rail network fault determination device, such as the following embodiment. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.
[0160] Figure 9 A structural diagram of a high-speed rail network fault determination device in an embodiment of the present disclosure is shown.
[0161] like Figure 9 As shown, the apparatus 900 may include:
[0162] Acquisition module 910, used to acquire local network coverage data, local network perception data and foreign network coverage data;
[0163] A first determination module 920 is configured to determine, based on a pre-trained intelligent model, the foreign network perception data corresponding to the foreign network coverage data;
[0164] The second determination module 930 is used to determine the road section with fault based on the local network coverage data, the local network perception data, the foreign network coverage data and the foreign network perception data.
[0165] In one embodiment of the present disclosure, the apparatus further comprises:
[0166] The training module is used to train the intelligent model based on the network coverage data and the network perception data to obtain a trained intelligent model.
[0167] In one embodiment of the present disclosure, the training module includes:
[0168] A construction unit, configured to construct training samples based on the coverage data and the perception data of the network;
[0169] The training unit is used to train the intelligent model based on the training samples, and obtain the trained intelligent model when the corresponding loss function value converges.
[0170] In one embodiment of the present disclosure, the network coverage data includes the network's Internet TV OTT data and the network's mobile measurement report MR data, and the network perception data includes the network's deep packet inspection DPI data;
[0171] Training modules include:
[0172] A first associating subunit is configured to associate the local network MR data and the DPI data based on the user identifier and the timestamp;
[0173] The second association subunit is used to associate the OTT data and MR data of the local network based on latitude and longitude and timestamp;
[0174] The dimensionality reduction subunit is used to reduce the dimensionality of the associated local network MR data, local network DPI data and local network OTT construction to obtain the reduced dimensionality local network MR features, local network DPI features and local network OTT features;
[0175] The conversion subunit is used to train the intelligent model so that the intelligent model can convert the OTT features of the local network into the MR features of the local network, and convert the MR features of the local network into the DPI features of the local network;
[0176] The completion subunit is used to obtain a trained intelligent model when the corresponding loss function value converges.
[0177] In one embodiment of the present disclosure, the apparatus further comprises:
[0178] The preprocessing module is used to preprocess the network coverage data and the network perception data, and remove the null values and abnormal data in the network coverage data and the network perception data.
[0179] In one embodiment of the present disclosure, the second determining module includes:
[0180] A first determining unit is configured to determine the business ratios of different lines at different time points based on the high-speed rail timetable and high-speed rail lines;
[0181] A second determining unit, configured to determine a plurality of thresholds based on the business ratio;
[0182] The third determination unit is used to compare the local network coverage data, the local network perception data, the foreign network coverage data and the foreign network perception data with the corresponding threshold values respectively to determine the road section with the fault.
[0183] The high-speed rail network fault determination device provided by the embodiments of the present disclosure obtains the coverage data of the current network, the perception data of the current network and the coverage data of other networks, determines the perception data of other networks corresponding to the coverage data of other networks based on a pre-trained intelligent model, determines the section with faults based on the coverage data of the current network, the perception data of the current network, the coverage data of other networks and the perception data of other networks, determines the perception data of other networks through the coverage data of other networks, and then determines the section with faults based on the coverage data of the current network, the perception data of the current network, the coverage data of other networks and the perception data of other networks, thereby improving the accuracy of the determined section with faults.
[0184] The high-speed rail network fault determination device provided in the embodiment of the present disclosure can be used to execute the high-speed rail network fault determination method provided in the above-mentioned method embodiments. Its implementation principles and technical effects are similar, and for the sake of simplicity, they will not be repeated here.
[0185] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods, or program products. Therefore, various aspects of the present disclosure may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits," "modules," or "systems."
[0186] Refer to the following Figure 10 1000 according to this embodiment of the present disclosure will be described. Figure 10 The electronic device 1000 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present disclosure.
[0187] like Figure 10 As shown, electronic device 1000 is implemented as a general-purpose computing device. Components of electronic device 1000 may include, but are not limited to, the aforementioned at least one processing unit 1010, the aforementioned at least one storage unit 1020, and a bus 1030 connecting various system components (including storage unit 1020 and processing unit 1010).
[0188] The storage unit stores program code, which can be executed by the processing unit 1010, so that the processing unit 1010 performs the steps described in the "Exemplary Method" section above according to various exemplary embodiments of the present disclosure. For example, the processing unit 1010 can perform the following steps of the above method embodiment:
[0189] Obtain local network coverage data, local network perception data, and other network coverage data;
[0190] Determine the corresponding network perception data based on the pre-trained intelligent model;
[0191] Determine the road section with faults based on the local network coverage data, local network perception data, other network coverage data and other network perception data.
[0192] The storage unit 1020 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 10201 and / or a cache memory unit 10202 , and may further include a read-only memory unit (ROM) 10203 .
[0193] The storage unit 1020 may also include a program / utility 10204 having a set (at least one) of program modules 10205, such program modules 10205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0194] Bus 1030 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
[0195] The electronic device 1000 may also communicate with one or more external devices 1040 (e.g., a keyboard, a pointing device, a Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 1000, and / or any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., a router, a modem, etc.). Such communication may occur via an input / output (I / O) interface 1050. Furthermore, the electronic device 1000 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 10100. As shown, the network adapter 10100 communicates with other modules of the electronic device 1000 via a bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1000, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0196] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (such as a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
[0197] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided. The computer-readable storage medium may be a readable signal medium or a readable storage medium. A program product capable of implementing the above-described method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the "Exemplary Methods" section above of this specification.
[0198] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0199] In the present disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0200] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.
[0201] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and the like, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).
[0202] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.
[0203] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.
[0204] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (such as a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
[0205] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the appended claims.
Claims
1. A method for determining a high-speed rail network fault, characterized in that: include: Obtain local network coverage data, local network perception data, and other network coverage data; Determining, based on a pre-trained intelligent model, the foreign network perception data corresponding to the foreign network coverage data; The road section where the fault occurs is determined based on the local network coverage data, the local network perception data, the foreign network coverage data and the foreign network perception data.
2. The method according to claim 1, characterized in that The method further comprises: The intelligent model is trained based on the local network coverage data and the local network perception data to obtain a trained intelligent model.
3. The method according to claim 2, characterized in that The intelligent model is trained based on the local network coverage data and the local network perception data to obtain a trained intelligent model, including: Constructing training samples based on the local network coverage data and local network perception data; The intelligent model is trained based on the training samples, and when the corresponding loss function value converges, a trained intelligent model is obtained.
4. The method according to claim 3, characterized in that The local network coverage data includes local network Internet TV OTT data and local network mobile measurement report MR data, the local network perception data includes local network deep packet inspection DPI data, and the training of the intelligent model based on the training samples, when the corresponding loss function value converges, obtains a trained intelligent model, including: Associate the local network MR data and DPI data based on user identification and timestamp; Correlate the network's OTT data and MR data based on latitude, longitude and timestamp; Performing dimensionality reduction on the associated local MR data, local DPI data, and local OTT construction to obtain the reduced local MR features, local DPI features, and local OTT features; Training the intelligent model so that it can convert the OTT features of the local network into the MR features of the local network, and convert the MR features of the local network into the DPI features of the local network; When the corresponding loss function value converges, the trained intelligent model is obtained.
5. The method according to claim 1 or 3, characterized in that The method further comprises: The local network coverage data and the local network perception data are preprocessed to remove null values and abnormal data in the local network coverage data and the local network perception data.
6. The method according to claim 1, characterized in that The method further comprises: Constructing a fault map based on the road section with the fault, local network coverage data corresponding to the road section with the fault, local network perception data, and foreign network coverage data; The fault graph is input into a pre-trained graph neural network intelligent model to obtain the root cause of the fault.
7. The method according to claim 1, characterized in that The determining of a road section having a fault based on the local network coverage data, the local network perception data, the foreign network coverage data, and the foreign network perception data includes: Determine the business ratio of different lines at different time points based on the high-speed rail timetable and high-speed rail lines; determining a plurality of thresholds based on the business ratio; The local network coverage data, local network perception data, foreign network coverage data and foreign network perception data are respectively compared with corresponding thresholds to determine the road section with faults.
8. A high-speed rail network fault determination device, characterized in that: include: Acquisition module, used to obtain local network coverage data, local network perception data and other network coverage data; A first determination module is configured to determine, based on a pre-trained intelligent model, the foreign network perception data corresponding to the foreign network coverage data; The second determination module is used to determine the road section with fault based on the local network coverage data, the local network perception data, the foreign network coverage data and the foreign network perception data.
9. An electronic device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to execute the high-speed rail network fault determination method according to any one of claims 1 to 7 by executing the executable instructions.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the high-speed rail network fault determination method according to any one of claims 1 to 7 is implemented.