Network health examination method, system and device and storage medium

Abstract

The embodiment of the invention provides a network health examination method, system and device and a storage medium. The method comprises the following steps: extracting original network data from a network layer, and obtaining key data based on the original network data; one or more preset service systems respectively carry out network service abnormity judgment based on the key data; and determining a network health examination result based on the network service abnormity judgment result output by the one or more service systems. The scheme of the embodiment is automatically executed, human interference is not needed, rapid and efficient network health inspection is achieved, cost reduction and efficiency improvement are achieved, operation and maintenance personnel can conveniently handle found problems in time, and therefore healthy operation of the network is guaranteed.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of communication, in particular to a network health check method, system, device and storage medium. BACKGROUND

[0002] With the development of communication network, the network networking complexity is increasing, and the check work for network operation health is gradually complex. At present, although some periodic network check actions exist in part of the communication network, too much manual intervention is still needed, which has certain skill requirements for operation and maintenance personnel, and the check period is too long, some communication network problems cannot be discovered in time, and it is difficult to guarantee the stability of the communication network operation. SUMMARY

[0003] Embodiments of the present disclosure provide a network health check method, system, device and storage medium.

[0004] In a first aspect, the embodiments of the present disclosure provide a network health check method, the method comprising:

[0005] extracting original network data from a network layer, and obtaining key data based on the original network data;

[0006] performing network service exception judgment by one or more preset business systems based on the key data, respectively;

[0007] determining a network health check result based on network service exception judgment results output by the one or more business systems.

[0008] In a second aspect, the embodiments of the present disclosure provide a network health check system, comprising a network layer, a data layer and a business layer;

[0009] the data layer is configured to extract original network data from the network layer, and obtain key data based on the original network data;

[0010] the business layer is configured to perform network service exception judgment by one or more preset business systems based on the key data, respectively;

[0011] the business layer is further configured to determine a network health check result based on network service exception judgment results output by the one or more business systems.

[0012] In a third aspect, the embodiments of the present disclosure provide a network health check device, comprising:

[0013] one or more processors;

[0014] a memory having stored thereon one or more programs, when executed by the one or more processors, cause the one or more processors to implement the network health check method;

[0015] one or more input / output (I / O) interfaces connected between the processor and the memory, configured to realize information interaction of the processor and the memory.

[0016] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, the computer-readable storage medium having stored thereon a computer program, the computer program being executed by a processor to implement the network health check method.

[0017] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, comprising a computer program, the computer program being executed by a processor to implement the network health check method.

[0018] The embodiments of the present disclosure extract original network data from a network layer and extract key data from the original network data, which guarantees the accuracy and effectiveness of the data; one or more preset business systems perform respective network service exception judgments based on the key data, and a network health check result is determined based on network service exception judgment results output by the one or more business systems, which realizes automatic network health check without human intervention, can quickly and efficiently complete network health check, realizes cost reduction and efficiency improvement, facilitates operation and maintenance personnel to timely process discovered problems, guarantees the stability of network operation, and realizes network healthy operation. BRIEF DESCRIPTION OF DRAWINGS

[0019] In the drawings of the embodiments of the present disclosure:

[0020] Figure 1 a network health check method flowchart provided by the embodiments of the present disclosure;

[0021] Figure 2 a network health check method schematic diagram provided by the embodiments of the present disclosure;

[0022] Figure 3 a display interface schematic diagram provided by the embodiments of the present disclosure;

[0023] Figure 4 a network health check management schematic diagram provided by the embodiments of the present disclosure;

[0024] Figure 5 a network health check system composition block diagram provided by the embodiments of the present disclosure;

[0025] Figure 6 a network health check system schematic diagram provided by the embodiments of the present disclosure;

[0026] Figure 7 A network health check device according to an embodiment of the present disclosure is shown in a block diagram. DETAILED DESCRIPTION

[0027] For those skilled in the art to better understand the technical solutions of the present disclosure, the communication-aware data processing method and the computer readable storage medium provided by the embodiments of the present disclosure are described in detail below in combination with the drawings.

[0028] The present disclosure will be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the present disclosure are shown. The present disclosure may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0029] The accompanying drawings, which are included to provide a further understanding of the embodiments of the present disclosure and constitute a part of the specification, illustrate the embodiments of the present disclosure and together with the detailed description serve to explain the present disclosure. The above and other features and advantages of the present disclosure will become more apparent from the following detailed description, taken in conjunction with the accompanying drawings.

[0030] The present disclosure can be described with reference to plan views and / or cross-sectional views by idealized schematic illustrations of the present disclosure. Therefore, the example illustrations can vary depending on the manufacturing technology and / or tolerances.

[0031] The embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict if not otherwise stated.

[0032] The terms used in the present disclosure are only used to describe specific embodiments and are not intended to limit the present disclosure. As used in the present disclosure, the term "and / or" includes any and all combinations of one or more of the associated listed items. As used in the present disclosure, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. As used in the present disclosure, the terms "comprises," "comprising," "consists of," and "consisting of" specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0033] Unless otherwise defined, all terms used in the present disclosure, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0034] With the development of communication networks, the network networking complexity is increasing, and the network operation health degree checking work is gradually complicated. At present, although some periodic network checking actions exist in some communication networks, too much manual intervention is still needed, the operation and maintenance personnel have certain skill requirements, and the checking period is too long, some communication network problems cannot be discovered in time, and it is difficult to guarantee the stability of the communication network operation.

[0035] The embodiment of the present disclosure extracts original network data from the network layer, and extracts key data from the original network data, which guarantees the accuracy and effectiveness of the data; one or more preset business systems perform respective network service exception judgments based on the key data, and determine a network health checking result based on the network service exception judgment results output by the one or more business systems, which realizes automatic network health checking, does not need human intervention, can quickly and efficiently complete network health checking, realizes cost reduction and efficiency improvement, facilitates operation and maintenance personnel to timely process the discovered problems, guarantees the stability of network operation, and realizes network healthy operation.

[0036] The network health checking method of the embodiment of the present disclosure can be applied to any terminal device, which can include but is not limited to: a vehicle-mounted device, a user equipment (UE), a mobile device, a computing device, a wearable device, etc., for example, including but not limited to a cellular phone, a cordless phone, a personal digital assistant (PDA), a portable computer, etc. The network health checking method can be realized by a processor calling computer readable program instructions stored in a memory, or can be realized by a server.

[0037] The network health checking method of the embodiment of the present disclosure can be applied to but is not limited to network health checking of a wireless communication network (for example, a wireless commercial communication network).

[0038] The following will introduce the embodiment scheme of the present disclosure in detail.

[0039] The embodiment of the present disclosure provides a network health checking method, as shown in Figure 1 、 Figure 2 The method comprises steps S11-S13:

[0040] S11, extracting original network data from a network layer, and obtaining key data based on the original network data.

[0041] In the embodiment of the present disclosure, extracting original network data from the network layer can include:

[0042] The original network data is extracted from the network layer in the form of command interaction, and a preset remote access protocol is used.

[0043] In the embodiments of the present disclosure, the network layer can include any network in the wireless communication network, and the network layer can include any one or more of the following: a wireless communication core network, a transport network, and an access network.

[0044] In the embodiments of the present disclosure, the network layer can include various hardware in the field of wireless communication, and can also include network management software in the field of wireless communication. For example, the network layer can include, but is not limited to, any one or more of the following: a UME (Unified Management Expert), an EMS (Element Management System), a base station, a network device (such as a controller and other network devices), and the like.

[0045] In the embodiments of the present disclosure, the remote access protocol can include, but is not limited to, any one or more of the following: SSH, Telnet, and Syslog. The SSH (Secure Shell) is a network protocol, which is mainly used to implement secure remote login and file transfer. The Telnet is a network protocol, which is used to remotely log in to another computer and execute commands. The Syslog is a standard for passing logging messages in Internet Protocol (TCP / IP) networks.

[0046] In the embodiments of the present disclosure, the key data can be extracted from the original network data by keyword recognition, or the key data can be calculated based on the original network data. The details of the key data are not limited herein, and the key data can be defined according to different original network data, different network health check business requirements, and the like.

[0047] In the embodiments of the present disclosure, for example, in an embodiment of detecting a user call success rate (percentage) in network performance, the original network data extracted can be user call data in a certain period (for example, one week or one month), and the key data can be a user call success rate calculated based on user call success data extracted from the user call data.

[0048] In the embodiments of the present disclosure, for example, in an embodiment of base station link fault checking in fault checking, the original network data extracted can be base station transmission link operation data in a certain period (for example, one day, one week, or one month), and the key data can be a number of base station transmission links whose link congestion duration exceeds a preset duration threshold, which is extracted based on the base station transmission link operation data.

[0049] In the embodiments of the present disclosure, for example, in the embodiment of checking high-load network elements in load evaluation, the extracted original network data can be network element load data in a certain period (for example, one day or one week), and the key data can be the number of network elements whose network element load exceeds a preset load threshold based on the network element load data.

[0050] In the embodiments of the present disclosure, after obtaining the original network data, the original network data can be preprocessed (for example, can include but is not limited to data cleaning and data screening) first, the key data is obtained based on the preprocessed original network data, and data filtering, data storage and necessary log recording in the entire data processing process are completed. Data processing can include but is not limited to data cleaning, data screening, data extraction, data filtering and data storage described above.

[0051] S12, network service anomaly judgment is performed by the preset one or more service systems based on the key data respectively.

[0052] In the embodiments of the present disclosure, one or more service systems can be established in advance according to different service requirements, different service systems perform different types of network health check services respectively, and any software and hardware related to the network health check service are checked accordingly.

[0053] In the embodiments of the present disclosure, the network health check service can include but is not limited to any one or more of the following:

[0054] Performance check, fault check, load check (such as high-load check), running state check, disaster recovery backup check, mains and backup battery check, in-service and delisting equipment check, software and hardware version check, and end-to-end link quality check.

[0055] In the embodiments of the present disclosure, each network health check service described above can be executed through the preset one or more service service groups, and here the detailed services of the service service group are not limited, and any one or more service groups currently existing can be selected to form a corresponding service service group according to requirements. For example, it can include but is not limited to service service group A (which can include service A1, service A2, …, service An, n is a positive integer), service service group B (which can include service B1, service B2, …, service Bm, m is a positive integer), service service group C (which can include service C1, service C2, …, service Ck, k is a positive integer).

[0056] In the embodiments of the present disclosure, network service anomaly judgment is performed by the preset one or more service systems based on the key data respectively, including: for any one of the service systems, the following operations are performed:

[0057] The key data is compared with a preset at least one data threshold, and the network health degree is determined according to a level corresponding to a data threshold satisfied by the key data.

[0058] In the embodiments of the present disclosure, in each business system, one or more data thresholds of different levels can be set in advance according to business requirements, and each level of data threshold can correspond to a network health degree.

[0059] In the embodiments of the present disclosure, the data threshold can be an experience parameter formed by a network expert, and the experience parameter corresponding to the data threshold can be modified accordingly for different networks to achieve better personalized adaptation.

[0060] In the embodiments of the present disclosure, the network health degree can include but is not limited to being represented in the form of scoring. For example, the network health degree can be judged with a full score of 100 points, for example, the score of the network health degree corresponding to the first level of numerical threshold can be set to 60 points or below, the score of the network health degree corresponding to the second level of numerical threshold can be set to 80 points or below, the score of the network health degree corresponding to the third level of numerical threshold can be set to 100 points or below, and the score of the network health degree corresponding to the fourth level of numerical threshold can be set to 100 points. That is, if the key data does not satisfy the first level of numerical threshold, the network health degree can be scored 60 points or below; if the key data satisfies the first level of numerical threshold and does not satisfy the second level of numerical threshold, the network health degree can be scored 60 points or above and 80 points or below; if the key data satisfies the first level of numerical threshold and the second level of numerical threshold and does not satisfy the third level of numerical threshold, the network health degree can be scored 80 points or above and 100 points or below.

[0061] In the embodiments of the present disclosure, the network health degree is determined according to a level corresponding to a data threshold satisfied by the key data, including:

[0062] In the case that the key data satisfies any level of data threshold, the key data is compared with a next level of data threshold until the key data satisfies all data thresholds, and the network health degree is determined to be completely healthy.

[0063] In the embodiments of the present disclosure, in the case that the data threshold is one level, the network health degree can be directly judged according to whether the key data satisfies this level of data threshold, that is, if the key data satisfies this level of data threshold, it can be determined that the network of the business type corresponding to the current business system is healthy, and a normal detail corresponding to the business system can be generated. If the key data does not satisfy this level of data threshold, it can be determined that the network of the business type corresponding to the current business system is unhealthy.

[0064] In the embodiments of the present disclosure, in the case that the data threshold is multi-level, the key data can be compared with the data threshold in increasing levels from the lowest level of data threshold, and in the case that the key data meets each level of data threshold, the network health degree of the business type corresponding to the business system is determined as completely healthy, which can be expressed in the form of scoring as 100 points, and the normal details corresponding to the business system can be generated.

[0065] In the embodiments of the present disclosure, for example, for the business system 1, assuming that it is used to perform business X, the first data threshold, the second data threshold and the third data threshold can be set, and the levels of the first data threshold, the second data threshold and the third data threshold are increased in levels, the key data can be compared with the first data threshold first, in the case that the first data threshold is met, the key data can be compared with the second data threshold, in the case that the second data threshold is met, the key data can be compared with the third data threshold, and if the key data also meets the third data threshold, it means that the key data meets all the data thresholds of the business system 1, and it can be determined that the network health degree corresponding to the business X in the business system 1 is completely healthy, i.e. 100 points.

[0066] In the embodiments of the present disclosure, according to the level corresponding to the data threshold met by the key data, the network health degree is determined, which can further include:

[0067] In the case that the key data does not meet any level of data threshold, the network abnormal business type corresponding to the unmet data threshold is obtained, and the abnormal reason is drilled down based on the network abnormal business type, and the corresponding network health degree is determined according to the abnormal reason drilling down result.

[0068] In the embodiments of the present disclosure, in the case that the data threshold is multi-level, the key data can be compared with the data threshold in increasing levels from the lowest level of data threshold, and in the case that the key data does not meet any level of data threshold, the network abnormal business type corresponding to this level of data threshold can be determined, and the abnormal reason is automatically drilled down, the corresponding network health degree is determined according to the abnormal reason drilling down result, which can be expressed in the form of scoring as 100 points.

[0069] In the embodiments of the present disclosure, for example, for the business system 2, assuming that it is used to perform the business Y, the fourth data threshold, the fifth data threshold and the sixth data threshold can be set, and the levels of the fourth data threshold, the fifth data threshold and the sixth data threshold increase gradually, the key data can be compared with the fourth data threshold first, in the case that the fourth data threshold is met, the key data can be compared with the fifth data threshold, in the case that the key data does not meet the fourth data threshold, the network abnormal business type (the business Y) corresponding to the fourth data threshold can be determined, and the abnormal reason is drilled down for the network abnormal business type (the business Y), and the network health degree corresponding to the business Y is obtained.

[0070] In the embodiments of the present disclosure, for example, for the business system 3, assuming that it is used to perform the business Z, the seventh data threshold, the eighth data threshold and the ninth data threshold can be set, and the levels of the seventh data threshold, the eighth data threshold and the ninth data threshold increase gradually, the key data can be compared with the seventh data threshold first, in the case that the seventh data threshold is met, the key data can be compared with the eighth data threshold, in the case that the key data meets the eighth data threshold, the key data can be compared with the ninth data threshold, in the case that the key data does not meet the ninth data threshold, the network abnormal business type (the business Z) corresponding to the ninth data threshold can be determined, and the abnormal reason is drilled down for the network abnormal business type (the business Z), and the network health degree corresponding to the business Z is obtained.

[0071] In the embodiments of the present disclosure, the user call success rate (percentage) in the network performance is taken as an example to illustrate the embodiments of the present disclosure, wherein the closer to the 100% index, the better, specifically, the first level data threshold I is “the day level index reaches 99.7% for three consecutive days”, the second level data threshold II is “the hour level index reaches 99.5% for 24 consecutive hours”, and the third level data threshold III is “the fluctuation of the hour level index is less than 2% for 24 consecutive hours”. If the data thresholds of the above three levels are all met, it indicates that the network health degree is 100 points, and the network normal details can be automatically generated, such as “the user call success rate index is stable and has no fluctuation”. If any one of the data thresholds of the above three levels is not met, the network abnormal business type is determined, and the abnormal details are automatically drilled down, for example, if the third level data threshold III is not met, the network abnormal business type is “the user call success rate index is abnormal, and the abnormal reason is that the fluctuation of the hour level index is too large”, and the abnormal reason is drilled down: “the main reason 1 is that the transmission packet loss rate is too high, accounting for 86%, the main reason 2 is that the cell service is withdrawn, accounting for 13%, and the other reasons account for 1%”. For the above abnormal situation, the network health degree can be given as 90 points.

[0072] In the embodiments of the present disclosure, the network abnormal service type and the abnormal reason drilling down can form an abnormal detail, for example: "the user call success rate index is abnormal, the abnormal reason is that the hour-level index fluctuation is too large; the main root cause 1 is that the transmission packet loss rate is too high, accounting for 86%, the main root cause 2 is that the cell is out of service, accounting for 13%, and other reasons accounting for 1%"; and the network health degree is 90 points.

[0073] In the embodiments of the present disclosure, the network service abnormality judgment based on the key data by the preset one or more service systems can further include:

[0074] Inputting the key data into a service abnormality judgment model corresponding to the service system;

[0075] Performing network service abnormality judgment based on the key data by the service abnormality judgment model;

[0076] The service abnormality judgment model is a model obtained by training a preset first neural network with feature data labeled with a network health label, and the network health label indicates the network health degree of the labeled data.

[0077] In the embodiments of the present disclosure, the network service abnormality judgment by each service system can also be implemented by a pre-trained service abnormality judgment model. For different service systems, corresponding service abnormality judgment models can be set respectively, and the service abnormality judgment models used by different service systems can implement different service abnormality judgment functions.

[0078] In the embodiments of the present disclosure, for each service abnormality judgment model, a large amount of original network data can be collected in advance, for example, a large amount of operator data can be collected, and for the current service system, a large amount of key data corresponding to the original network data can be extracted, the key data is labeled, and the labeled key data is used as training data to iteratively train a pre-set first neural network. When the first loss value of the first neural network meets the first preset requirement, it is confirmed that the service abnormality judgment model is successfully trained. The network service abnormality judgment can be directly performed on the received key data based on the service abnormality judgment model, and the network service abnormality judgment result is output.

[0079] In the embodiments of the present disclosure, the detailed structure of the first neural network is not limited here, and can be defined by itself according to different needs, and a suitable neural network structure can be selected from the existing neural network structures.

[0080] S13, determining a network health check result based on the network service abnormality judgment result output by the one or more service systems.

[0081] In the embodiments of the present disclosure, determining the network health check result based on the network service exception determination result output by the one or more business systems can include:

[0082] The network health degrees output by the one or more business systems are summarized, and a health check report about the one or more business systems is generated.

[0083] In the embodiments of the present disclosure, when there are multiple business systems, each business system can execute a respective network service exception determination scheme in parallel, and output the network health degree of the respective business system after completing the network service exception determination. The normal details or the abnormal details corresponding to the network health degree can also be output.

[0084] In the embodiments of the present disclosure, the network health degrees output by the one or more business systems are summarized, and a health check report about the one or more business systems is generated based on the network health degrees of the different business systems and the weights of the different business systems, the network health degree of the entire network corresponding to all the business systems is obtained by weighted calculation, and the health check report is generated based on the network health degree of the entire network and the normal details or the abnormal details corresponding to the network health degree output by each business system.

[0085] In the embodiments of the present disclosure, after determining the network health check result based on the network service exception determination result output by the one or more business systems, the method can further include:

[0086] The network health check result is displayed through a preset display interface and / or a display platform.

[0087] In the embodiments of the present disclosure, the health check report described above can be displayed on the preset display interface and / or the display platform.

[0088] In the embodiments of the present disclosure, the display platform can include but is not limited to a mobile applet, a PC (personal computer) browser, a mail system (which can push emails), and the like.

[0089] In the embodiments of the present disclosure, the display interface can display the overall overview of the network health and the evaluation of each business system. The display interface can be divided into but is not limited to three parts: a menu part, a title part, and a detail part.

[0090] In the disclosed embodiment, the menu section may include an overall overview and clickable icons for each business system. The menu section allows the user to select the overall network health report or the network health report for each business system to view. By clicking the overall overview clickable icon, the overall overview of the current network health report for the entire network can be displayed on the display interface. By clicking the clickable icon for a specific business system, the network health report corresponding to that business system can be displayed on the display interface.

[0091] In the embodiment of the present disclosure, the clickable icons of each business system may include but are not limited to the following charts: performance check, fault check, high load check, operation status check, disaster recovery backup check, AC power and backup battery check, maintenance and delisting check, software and hardware version check, end-to-end link quality check, etc.

[0092] In the embodiment of the present disclosure, the title part refers to the overall overview or the title of each business system displayed in the blocks corresponding to the overall overview and each business system in the area outside the menu part, which is used to clarify the display position of the overall overview and its various business systems.

[0093] In the embodiment of the present disclosure, the details portion refers to the detailed network health report content corresponding to each title portion.

[0094] In the embodiment of the present disclosure, Figure 3 As shown, taking the overall situation as an example, the details section allows you to view the overall achievement, with a network health score. This score can be displayed in different colors based on the score range, giving users intuitive prompts. For example, scores above 90 are green, 80-90 are light green, 70-80 are orange, 60-70 are yellow, and scores below 60 are red. If the current overall network health score is 95, it will be displayed in green.

[0095] In the embodiment of the present disclosure, Figure 3 As shown, taking the overall situation as an example, the details section can display the overall abnormality details (or abnormal events) in a list format. The abnormality details may include but are not limited to: network abnormal service type (which can be simply referred to as abnormality type), severity, event description, and occurrence time. For example: Abnormal service type: indicator analysis, severity: medium, event description: F0 call establishment success rate is lower than the normal value, occurrence time: 1 hour ago; Abnormal type: fault analysis, severity: high, event description: 193 base station transmission links are abnormal, occurrence time: 23 hours ago; Abnormal type: high-load network element, severity: low, event description: 8 sites have high user load, occurrence time: 8 hours ago.

[0096] In the embodiment of the present disclosure, Figure 3As shown, taking the overall situation as an example, different blocks can be divided in the details part for different business systems, and the main detailed contents in the network health degree and the corresponding abnormal details output by each business system are displayed in the respective blocks. For example, key information of the analysis situation of each business system is displayed, such as key indicators of performance checking, key alarms of fault checking, and balance situation of high load checking.

[0097] In the embodiments of the present disclosure, for example, the fault checking can include TOP10 (top 10) alarms determined for a plurality of checking targets, for example, the TOP alarms of the first checking target include: 1, 160 times of transmission unreachable, 2, 1.88 times of excessive standing wave ratio, …; the TOP alarms of the second checking target include: 1, 360 times of network element disconnection, 2, 1.89 times of excessive standing wave ratio, ….

[0098] In the embodiments of the present disclosure, for example, the high load checking can include the network element load, peak load and average load determined for a plurality of network elements (such as network element 1, network element 2 and network element 3). For example: network element 1 load 80%, peak load 95%, average load 75%; network element 2 load 85%, peak load 98%, average load 79%; network element 3 load 88%, peak load 98%, average load 82%.

[0099] In the embodiments of the present disclosure, for the currently displayed health checking report, an export function and a refresh function can also be set.

[0100] In the embodiments of the present disclosure, before extracting the original network data from the network layer, the method can further include:

[0101] determining the selected network health checking mode;

[0102] In the case where the selected network health checking mode is the automatic mode, the process of extracting the original network data from the network layer is entered.

[0103] In the embodiments of the present disclosure, as shown, Figure 4 Before the network health checking is performed, the user can be provided with a starting interface of the network health checking task, and a plurality of network health checking modes can be set in the starting interface, for example, the manual mode and the automatic mode can be included, and the automatic mode means that the network health checking is automatically performed based on the steps S11 to S13 in the above-mentioned scheme of the embodiments of the present disclosure, and the network health checking result is output. The network health checking scheme of the embodiments of the present disclosure can be implemented as a control template.

[0104] In the embodiments of the present disclosure, after the network health checking result is determined based on the network service abnormal judgment result output by one or more business systems, the method can further include:

[0105] determining whether the network health check result is normal;

[0106] in a case where it is determined that the network health check result is normal, issuing a notification that the network health check result is normal;

[0107] in a case where it is determined that the network health check result is abnormal, notifying whether a false positive phenomenon occurs, in a case where it is confirmed that the false positive phenomenon occurs, re-performing the network health check, and in a case where it is confirmed that the false positive phenomenon does not occur, issuing a processing notification.

[0108] In the embodiments of the present disclosure, after obtaining the network health check result, in order to ensure the effectiveness of the network health check result, it can be first determined whether the network health check result is normal, if it is determined that the network health check result is normal, a notification that the network health check result is normal can be issued to notify the associated personnel to close the current network health check mode, and the network health check task ends. If it is determined that the network health check result is abnormal, it can be first determined whether the network health check result is a false positive, if it is a false positive, the network health check can be re-performed, that is, the associated personnel are notified to restart the network health check mode to re-execute the network health check task. If it is not a false positive, the associated personnel need to be notified to handle in time.

[0109] In the embodiments of the present disclosure, determining whether the network health check result is normal can check whether the result data is abnormal, if the result data obviously exceeds the preset numerical range and obviously does not conform to the common sense, it can be confirmed that the network health check result is determined to be abnormal.

[0110] In the embodiments of the present disclosure, determining whether the network health check result is normal can include:

[0111] inputting the network health check result into a preset result judgment model;

[0112] judging whether the network health check result is normal by the result judgment model;

[0113] The result judgment model is a model obtained by training a preset second neural network with a network health check result labeled with a result judgment label as training data, in a case where a second loss value meets a second preset requirement. The result judgment label indicates whether the labeled network health check result is normal.

[0114] In the embodiments of the present disclosure, the result judgment model can also be used to determine whether the network health check result is normal.

[0115] In the embodiments of the present disclosure, for the result judgment model described above, a large number of network health check results (such as network health check reports) can be collected in advance, the network health check results are labeled (whether the network health check result is normal), the network health check results after labeling are used as training data to iteratively train the second neural network set in advance, until the second loss value of the second neural network meets the second preset requirement, and then it is confirmed that the result judgment model training is successful, the network health check result received can be directly judged based on the result judgment model whether it is normal, and the judgment result is output.

[0116] In the embodiments of the present disclosure, the detailed structure of the second neural network is not limited here, and can be defined by itself according to different needs, and a neural network structure suitable for the existing neural network structure can be selected.

[0117] In the embodiments of the present disclosure, the associated personnel described above generally refers to the operation and maintenance personnel of the communication network, which can refer to the network health check result (or report) to process and track the network problems involved.

[0118] In the embodiments of the present disclosure, through the automatic mode, the network health degree check can be periodically completed by using the embodiments of the present disclosure automatically, and when necessary, manual intervention can be performed by participating in software judgment, so as to avoid the abnormality of the network health check result.

[0119] In the embodiments of the present disclosure, the embodiments of the present disclosure at least include the following advantages:

[0120] 1. The embodiments of the present disclosure automatically extract the key data in the network (such as a wireless commercial communication network), improve the efficiency and accuracy of the health check report, summarize, refine, analyze, evaluate and give the check conclusion of the extracted key information, and transmit the check conclusion and the key information to the network operation and maintenance personnel in real time, so as to achieve the purpose of automatically maintaining the healthy operation of the network.

[0121] 2. The embodiments of the present disclosure are automatically executed and do not need human intervention, can quickly and efficiently complete the check, realize cost reduction and efficiency improvement, and facilitate the operation and maintenance personnel to timely process the problems found, so as to ensure the healthy operation of the network.

[0122] 3. In many network construction scenes such as network addition, network relocation, network upgrade and the like, the network health check function of the embodiments of the present disclosure provides a visual solution, clearly and efficiently judges and displays the problems by means of graphical means, so that the user can quickly locate the network problems, liberate manpower to the greatest extent, and quickly and continuously improve the network health degree.

[0123] 4. The embodiment of the present disclosure can integrate the network health detection tool (for example, a software tool based on the network health detection method of the embodiment of the present disclosure) into the daily maintenance work of the communication network, realize the digitalization of the network health management, analysis and traceability, and realize the collaboration and efficiency of the discovery, reminder, processing and problem closing of the network health problems.

[0124] The embodiment of the present disclosure also provides a network health check system 100, as shown in Figure 5 、 Figure 6 which can include a network layer 101, a data layer 102 and a service layer 103.

[0125] The data layer 102 can be configured to extract original network data from the network layer 101 and obtain key data based on the original network data.

[0126] The service layer 103 can be configured to perform network service exception judgment based on the key data by one or more preset service systems, wherein different service systems perform different types of network health check services.

[0127] The service layer 103 can also be configured to determine the network health check result based on the network service exception judgment result output by the one or more service systems.

[0128] In the embodiment of the present disclosure, the data layer 102 can also be configured to perform data filtering and data storage on the key data, and log record the data processing process; the data processing includes data extraction, data filtering and data storage on the key data.

[0129] In the embodiment of the present disclosure, the network health check system 100 can also include an application layer 104.

[0130] The application layer can be configured to provide a service group for supporting the service layer 103 to complete data processing.

[0131] In the embodiment of the present disclosure, the network health check system 100 can also include a user layer 105.

[0132] The user layer 105 can be configured to realize the management of the network health check process by the user and the query and processing of the network health check result. The processing of the network health check result includes but is not limited to editing (for example, deleting, modifying) and / or exporting.

[0133] In the embodiment of the present disclosure, the network layer 105 includes any one or more of the following: a wireless communication core network, a transmission network and an access network.

[0134] In the embodiments of the present disclosure, any of the foregoing network health check methods can be applied to the network health check system, and thus will not be repeated here.

[0135] The embodiments of the present disclosure also provide a network health check device 200, as shown in the following table, which can include: Figure 7

[0136] one or more processors 201;

[0137] a memory 202, having one or more computer programs stored thereon, when the one or more computer programs are executed by the one or more processors 201, the one or more processors 201 implement the network health check method.

[0138] The embodiments of the present disclosure also provide a computer readable storage medium, having a computer program stored thereon, when the computer program is executed by a processor, the network health check method is implemented.

[0139] The embodiments of the present disclosure also provide a computer program product, comprising a computer program, when the computer program is executed by a processor, the network health check method is implemented.

[0140] Those skilled in the art can understand that all or some of the function modules / units disclosed above can be implemented as software, firmware, hardware and their appropriate combinations.

[0141] In the hardware implementation, the division between the function modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be executed by several physical components in cooperation.

[0142] ​Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit (CPU), a digital signal processor, or a microprocessor, or hardware, or a combination of software and / or hardware. Such software can be distributed on computer readable media, which can comprise computer storage media (or non-transitory media), and communication media (or transitory media). Computer storage media, as used herein, includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, random access memory (RAM), such as SDRAM, DDR, or other RAM, read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory, or other memory technology, compact disc read only memory (CD-ROM), digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. Further, it should be appreciated by those skilled in the art that computer storage media generally includes computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Accordingly, the disclosure is not limited to entirely software based embodiments implemented using computers other embodiments can be implemented using hardware, firmware, software, or any combination thereof.

[0143] The present disclosure has disclosed example embodiments, and although the specific terms are employed, they are used in a generic descriptive sense only and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that features, characteristics or / and elements described in connection with a particular embodiment can be used in conjunction with other embodiments unless otherwise explicitly stated, or in the alternative, used in isolation. Accordingly, it will be understood by those skilled in the art that various changes in form and details can be made without departing from the scope of the present disclosure as set forth in the appended claims.

Claims

1. A network health check method, characterized by, The method comprises: extracting original network data from a network layer, and obtaining key data based on the original network data; performing network service exception judgment based on the key data by one or more preset service systems respectively; wherein different service systems perform different types of network health check services respectively; determining a network health check result based on network service exception judgment results output by the one or more service systems.

2. The network health check method of claim 1, wherein, The method of extracting original network data from a network layer comprises: extracting the original network data from the network layer in the form of command interaction through a preset remote access protocol.

3. The network health check method of claim 1, wherein, The method of performing network service exception judgment based on the key data by one or more preset service systems respectively comprises: comparing the key data with at least one preset data threshold, and determining a network health degree according to a level corresponding to the data threshold satisfied by the key data.

4. The network health check method of claim 3, wherein, The method of determining a network health degree according to a level corresponding to the data threshold satisfied by the key data comprises: in the case that the key data satisfies any one of the data thresholds, comparing the key data with a next level data threshold until the key data satisfies all the data thresholds, and determining that the network health degree is completely healthy.

5. The network health check method of claim 3, wherein, The method of determining a network health degree according to a level corresponding to the data threshold satisfied by the key data comprises: in the case that the key data does not satisfy any one of the data thresholds, obtaining a network exception service type corresponding to the unsatisfied data threshold, and performing exception reason drilling based on the network exception service type, and determining a corresponding network health degree according to the exception reason drilling result.

6. The network health check method of claim 1, wherein, The method of performing network service exception judgment based on the key data by one or more preset service systems respectively comprises: inputting the key data into a service exception judgment model corresponding to the service system; performing network service exception judgment based on the key data by the service exception judgment model; The service exception judgment model is a model obtained by training a preset first neural network with feature data labeled with a network health label as training data, wherein the first loss value satisfies a first preset requirement.

7. The network health check method of claim 3, wherein, The method of determining a network health check result based on network service exception judgment results output by the one or more service systems comprises: summarizing the network health degrees output by one or more service systems, and generating a health check report about one or more service systems.

8. The network health check method according to any one of claims 1 to 7, characterized in that: The network health check service comprises any one or more of the following: performance check, fault check, load check, running state check, disaster recovery backup check, mains and backup battery check, in-service and delisting equipment check, software and hardware version check, and end-to-end link quality check.

9. The network health check method of claim 1, wherein, After determining a network health check result based on network service exception judgment results output by the one or more service systems, the method further comprises: The network health check result is displayed through a preset display interface and / or a display platform.

10. The network health checking method of claim 1, wherein, Before extracting the original network data from the network layer, the method further comprises: determining the selected network health check mode; in the case that the selected network health check mode is an automatic mode, entering the process of extracting the original network data from the network layer.

11. The network health checking method of claim 1, wherein, After determining the network health check result based on the network service exception judgment result output by the one or more business systems, the method further comprises: judging whether the network health check result is normal; in the case that the network health check result is determined to be normal, issuing a notification that the network health check result is normal; in the case that the network health check result is determined to be abnormal, notifying whether a false alarm phenomenon occurs, in the case that the false alarm phenomenon is confirmed to occur, re-performing network health check, and in the case that the false alarm phenomenon is confirmed not to occur, issuing a processing notification.

12. The network health check method of claim 11, wherein, The judgment of whether the network health check result is normal comprises: inputting the network health check result into a preset result judgment model; judging whether the network health check result is normal by the result judgment model; The result judgment model is a model obtained by training a preset second neural network with network health check results labeled with result judgment labels as training data, in the case that a second loss value meets a second preset requirement. The result judgment label indicates whether the labeled network health check result is normal.

13. A network health check system, characterized by, comprises: a network layer, a data layer, and a business layer; The data layer is configured to extract original network data from the network layer and obtain key data based on the original network data; The business layer is configured to perform network service exception judgment by one or more preset business systems based on the key data, respectively; wherein different business systems perform different types of network health check services; The business layer is further configured to determine the network health check result based on the network service exception judgment result output by the one or more business systems.

14. The network health check system of claim 13, wherein, The data layer is further configured to perform data filtering and data storage on the key data, and log records the data processing process; the data processing includes data extraction, data filtering and data storage of the key data.

15. The network health check system of claim 14, wherein, Further comprising: an application layer; The application layer is configured to provide a group of business services for supporting the business layer to complete the data processing.

16. The network health check system of claim 13, wherein, Further comprising: a user layer; The user layer is configured to realize user management of the network health check process and query and processing of the network health check result.

17. The network health check system of claim 13, wherein, The network layer comprises any one or more of the following: a wireless communication core network, a transmission network, and an access network.

18. A network health check apparatus, characterized by, comprises: one or more processors; a memory having one or more computer programs stored thereon, when the one or more computer programs are executed by the one or more processors, the one or more processors implement the network health check method of any one of claims 1-12.

19. A computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the network health checking method according to any one of claims 1-12.

20. A computer program product, comprising a computer program which, when executed by a processor, implements the network health checking method according to any one of claims 1-12.

Images