A message processing method, device, equipment and computer storage medium

Through the interface call time series model and performance indicators, the NFV system's performance degradation problem is solved when facing a large number of messages, and the stable operation of the system is achieved.

CN113971093BActive Publication Date: 2024-11-15CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010714270.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-07-22
Publication Date
2024-11-15
Estimated Expiration
2040-07-22

AI Technical Summary

Technical Problem

The existing network function virtualization (NFV) management and orchestration network management system (MANO) system cannot effectively handle the message storm when faced with a large number of bursts of authentication messages and resource change messages, resulting in a message storm, resulting in performance degradation and system operation instability.

Method used

By obtaining historical message data of each type of interface, training the interface call volume time series model, monitoring the interface call volume and performance indicators in real time, determining the target exception interface, and performing flow control processing on it, establishing a message cache queue to process the trapped messages. Reduce the impact of message storms on the system.

Benefits of technology

The message storm of authentication messages and resource change messages effectively discovers and processes the message storm, ensures the timeliness of message processing in the NFV network, avoids resource consumption, and ensures the normal operation of the MANO system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113971093B_ABST
    Figure CN113971093B_ABST
Patent Text Reader

Abstract

The present invention provides a message processing method, including: obtaining historical message data of each type of interface and performing model training on the historical message data to obtain a time series model of interface call volume of each type; obtaining the first real-time interface call volume of the interface to be monitored at multiple moments; determining a target abnormal interface from the interface to be monitored based on the interface call volume time series model, the first real-time interface call volume and the performance index of the interface; obtaining the retained messages of the target abnormal interface and the real-time messages of the target abnormal interface; and performing flow control processing on the target abnormal interface based on the retained messages and the real-time messages. The present invention also provides a message processing device, equipment and computer storage medium, which realizes the discovery and processing of message storms of authentication messages and resource change messages, thereby ensuring the timeliness of message processing and the normal operation of the MANO system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to message processing technology in the communication field, and in particular to a message processing method, device, equipment and computer storage medium. Background Art

[0002] The network characteristics of the network architecture of Network Function Virtualization (NFV) make the changes of resource information such as virtual network elements and virtual machines more flexible, so as to realize the flexible construction of the network and the dynamic allocation of resources. The specification of NFV's Management and Orchestration (MANO) introduces the real-time push of resource change messages to the upper-level network management through the restful interface. After receiving the resource change message, the upper-level network management can start the relevant resource data collection work in real time. This network resource data collection method causes the data collection platform to send a large number of authentication messages and resource change messages to each application module. At this time, if a network failure or abnormal situation occurs, it will cause a sudden burst of authentication messages and resource change messages, resulting in a message storm.

[0003] However, the related technology mainly detects and processes message storms for alarm messages, but cannot detect and process message storms for authentication messages and resource change messages, resulting in consumption of resources on the data collection platform or various application platforms, causing the performance of the MANO system to decline, and even affecting the normal operation of the MANO system. Summary of the invention

[0004] In view of this, the present invention hopes to provide a message processing method, apparatus, device and computer storage medium, which realizes the discovery and processing of message storms of authentication messages and resource change messages, ensures the timeliness of message processing in the NFV network, avoids resource consumption, and ensures the normal operation of the network and MANO system.

[0005] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0006] In a first aspect, a message processing method is provided, the method comprising:

[0007] Obtaining historical message data of each type of interface and performing model training on the historical message data to obtain a time series model of the call volume of each type of interface;

[0008] Obtaining the first real-time interface call volume of the interface to be monitored at multiple moments;

[0009] Determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the performance indicator of the interface;

[0010] Acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface;

[0011] Based on the retained message and the real-time message, flow control processing is performed on the target abnormal interface.

[0012] Optionally, the acquiring of historical message data of each type of interface and performing model training on the historical message data to obtain a time series model of the call volume of each type of interface includes:

[0013] Acquire historical message data of the interface, and classify the historical message data of the interface to obtain historical message data of each type of interface, wherein the historical message data includes authentication message data and / or resource change message data;

[0014] Preprocessing the historical message data of each type of interface to obtain an interface call volume data sequence of each type of interface;

[0015] Time series modeling is performed based on the interface call volume data series to obtain a time series model of each type of interface call volume.

[0016] Optionally, determining a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the performance indicator of the interface includes:

[0017] Determine a reference abnormal interface from the interfaces to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored;

[0018] From the performance indicators, obtaining a reference performance indicator of the reference abnormal interface, wherein the performance indicator indicates a message retention degree of the interface;

[0019] The target abnormal interface is determined from the reference abnormal interface based on the second real-time interface call volume of the reference abnormal interface and the reference performance indicator.

[0020] Optionally, determining a reference abnormal interface from the interfaces to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored includes:

[0021] Analyze the interface call volume time series model corresponding to the type of the interface to be monitored to obtain a reference interface call volume;

[0022] Based on the reference interface call volume and the first real-time interface call volume, the reference abnormal interface is determined from the interfaces to be monitored.

[0023] Optionally, determining the reference abnormal interface from the interfaces to be monitored based on the reference interface call volume and the first real-time interface call volume includes:

[0024] Calculate the difference between each of the first real-time interface call amount and the reference interface call amount;

[0025] Standardizing the difference to obtain a standardized residual of the interface to be monitored;

[0026] If the standardized residual is greater than a preset reference value, the interface to be monitored is determined to be the reference abnormal interface.

[0027] Optionally, the determining the target abnormal interface from the reference abnormal interface based on the second real-time interface call volume of the reference abnormal interface and the reference performance indicator includes:

[0028] Using a sliding average algorithm, calculate a first moving average value of the second real-time interface call amount and a second moving average value of the reference performance indicator;

[0029] The target abnormal interface is determined from the reference abnormal interfaces based on the first moving average value and the second moving average value.

[0030] Optionally, determining the target abnormal interface from the reference abnormal interfaces based on the first moving average value and the second moving average value includes:

[0031] Based on the first moving average value and the first preset threshold value, normalizing the first moving average value to obtain a first normalized value of the second real-time interface call amount;

[0032] Based on the second moving average value of each of the reference performance indicators and the first preset threshold, normalizing the second moving average value of each of the reference performance indicators to obtain a second normalized value of each of the reference performance indicators;

[0033] Calculate the message storm index of the reference abnormal interface based on the first normalized value, the first preset weight of the second real-time interface call amount, the second normalized value of each of the reference performance indicators, and the second preset weight of each of the reference performance indicators;

[0034] If the message storm index is greater than a second preset threshold, the reference abnormal interface is determined to be the target abnormal interface.

[0035] Optionally, the performing flow control processing on the target abnormal interface based on the retained message and the real-time message includes:

[0036] Establishing a message cache queue, wherein the message cache queue is used to store the stranded message;

[0037] If there is a message matching the real-time message in the retained messages, the retained message matching the real-time message is deleted, and the real-time message is stored in the message cache queue.

[0038] Optionally, establishing a message cache queue includes:

[0039] Determining the capacity of the message cache queue based on the first message storm index of the target abnormal interface;

[0040] The message cache queue is established based on the capacity of the message cache queue.

[0041] Optionally, if there is a message matching the real-time message in the retained message, deleting the retained message matching the real-time message, and storing the real-time message in the message cache queue includes:

[0042] Calculating a hash value of the real-time message; and detecting whether the hash value of the real-time message is the same as the hash value of the retained message, wherein the hash value of the retained message is stored in the message cache queue;

[0043] If they are the same, based on a preset resource matching library, detecting whether the resource corresponding to the stranded message is the same as the resource corresponding to the real-time message;

[0044] If they are the same, the retained message with the same resource as that corresponding to the real-time message is deleted, and the real-time message and the hash value of the real-time message are stored in the message cache queue.

[0045] Optionally, the method further includes:

[0046] Calculate a second message storm index of the target abnormal interface;

[0047] If the second message storm index is less than or equal to a third preset threshold, the message cache queue is deleted.

[0048] Optionally, the method further includes:

[0049] The resource information associated with the target abnormal interface is subjected to resource correlation analysis to determine the cause of the network failure and / or the failure point of the network.

[0050] Optionally, performing resource correlation analysis on the resource information associated with the target abnormal interface to determine the cause of the network failure and / or the network failure point includes:

[0051] If the resource information associated with the target abnormal interface is derived from resource information associated with the network element layer, virtual layer and physical layer in the NFV architecture, it is determined that the cause of the network failure is the association between the network element layer, virtual layer and physical layer; and / or

[0052] If the resource information associated with the target abnormal interface is derived from resource information of a network element group having multiple network elements at the network element layer in the NFV architecture, it is determined that the fault point of the network is the network element group; and / or

[0053] If the resource information associated with the target abnormal interface comes from the resource information of a network element node group having multiple network element nodes in the network element of the NFV architecture, it is determined that the failure point of the network is the network element node group.

[0054] Optionally, the method further includes:

[0055] Comparing the number of stranded messages in the message cache queue with the capacity of the message cache queue to obtain a comparison result;

[0056] Based on the comparison result, the relationship between the first message storm index and the capacity of the message cache queue is adjusted.

[0057] Optionally, the method further includes:

[0058] Monitor the first system resource information and the second system resource information, and compare the first system resource information and the second system resource information, wherein the first system resource information is the system resource information before the message cache queue is established; and the second system resource information is the system resource information after the message cache queue is established.

[0059] In a second aspect, a message processing device is provided, the device comprising: a generating unit, a first acquiring unit, a first determining unit, a second acquiring unit and a processing unit, wherein:

[0060] A generating unit, used to obtain historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the call volume of each type of interface;

[0061] A first acquisition unit, used to acquire a first real-time interface call volume of the interface to be monitored at multiple moments;

[0062] A first determining unit is used to determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume and the performance index of the interface;

[0063] A second acquisition unit, used to acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface;

[0064] A processing unit is used to perform flow control processing on the target abnormal interface based on the retained message and the real-time message.

[0065] In a third aspect, a message processing device is provided, the device comprising: a processor, a memory, and a communication bus;

[0066] The communication bus is used to realize the communication connection between the processor and the memory;

[0067] The processor is used to execute the message processing program in the memory to implement the following steps:

[0068] Obtaining historical message data of each type of interface and performing model training on the historical message data to obtain a time series model of the call volume of each type of interface;

[0069] Obtaining the first real-time interface call volume of the interface to be monitored at multiple moments;

[0070] Determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the performance indicator of the interface;

[0071] Acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface;

[0072] Based on the retained message and the real-time message, flow control processing is performed on the target abnormal interface.

[0073] In a fourth aspect, a computer storage medium is provided, characterized in that the computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the message processing method described above.

[0074] The message processing method, device, equipment and computer storage medium provided by the present invention obtain historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of interface call volume of each type; obtain the first real-time interface call volume of the interface to be monitored at multiple moments; determine the target abnormal interface from the interface to be monitored based on the interface call volume time series model, the first real-time interface call volume and the performance index of the interface; obtain the retained message of the target abnormal interface and the real-time message of the target abnormal interface; perform flow control processing on the real-time message based on the retained message and the real-time message, so that the interface call volume time series model generated based on the authentication message data and the resource change message data can be used to determine the target abnormal interface that generates the message storm, and perform flow control processing on the message of the target abnormal interface, thereby realizing the discovery and processing of the message storm of the authentication message and the resource change message, thereby ensuring the timeliness of the message processing of the NFV network, avoiding the consumption of resources, and ensuring the normal operation of the network and the MANO system. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 A flowchart of a message processing method provided by an embodiment of the present invention;

[0076] Figure 2 A flowchart of another message processing method provided by an embodiment of the present invention;

[0077] Figure 3 A flowchart of another message processing method provided by an embodiment of the present invention;

[0078] Figure 4 A schematic diagram of the structure of a message processing system provided by an embodiment of the present invention;

[0079] Figure 5 A schematic diagram of the structure of another message processing device provided by an embodiment of the present invention;

[0080] Figure 6 A schematic diagram of the structure of another message processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0081] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0082] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0083] The present invention provides a message processing method, which can be applied to a message processing device, referring to Figure 1 As shown, the method comprises the following steps:

[0084] Step 101: Obtain historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the call volume of each type of interface.

[0085] In an embodiment of the present invention, in the NFV network architecture, for interfaces that receive authentication messages and resource change messages, the interfaces can be classified according to the type of message content. The types of interfaces can include interfaces of the network element layer, interfaces of the virtual layer, interfaces of the physical layer, and interfaces of the core network, transmission network, and wireless network associated with the three layers, etc., and these interfaces can be further classified according to more detailed types of message content. Among them, the method of discovering and processing the message storm of each type of interface is the same.

[0086] Step 102: Obtain the first real-time interface call volume of the interface to be monitored at multiple moments.

[0087] In an embodiment of the present invention, the first real-time interface call volume may be the number of interface calls of the interface to be monitored at multiple moments. In a feasible implementation, the first real-time interface call volume may be stored in the form of a data sequence, which is arranged in chronological order of multiple moments.

[0088] Step 103: determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the interface performance index.

[0089] In a feasible implementation, the target abnormal interface is the interface that generates the message storm. The performance indicator of each type of interface can be one or more indicators, each indicator includes data of multiple moments of the indicator, and each indicator can be stored in the form of a data sequence, which is arranged in the order of multiple moments.

[0090] Step 104: Acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface.

[0091] In the embodiment of the present invention, when a large number of messages burst on the interface, these messages cannot be processed in time, which will cause message blocking of the interface, causing the interface to generate a message storm and become a target abnormal interface. These messages that cause the interface to generate a message storm are the stranded messages of the target abnormal interface. The message of the target abnormal interface at the current moment after the moment when the message storm occurs is the real-time message of the target abnormal interface.

[0092] Step 105: Based on the retained messages and the real-time messages, flow control is performed on the target abnormal interface.

[0093] In the embodiment of the present invention, after a message storm occurs, the timeliness of real-time message processing is ensured by flow control processing of the target abnormal interface, thereby reducing the consumption of system resources by the message storm and further alleviating the system pressure.

[0094] The message processing method provided by the present invention obtains historical message data of each type of interface and performs model training on the historical message data to obtain a time series model of interface call volume of each type; obtains the first real-time interface call volume of multiple moments of the interface to be monitored; determines the target abnormal interface from the interface to be monitored based on the interface call volume time series model, the first real-time interface call volume and the performance index of the interface; obtains the retained message of the target abnormal interface and the real-time message of the target abnormal interface; performs flow control processing on the real-time message based on the retained message and the real-time message, so that the interface call volume time series model generated based on the authentication message data and the resource change message data can be used to determine the target abnormal interface that generates the message storm, and perform flow control processing on the message of the target abnormal interface, thereby realizing the discovery and processing of the message storm of the authentication message and the resource change message, thereby ensuring the timeliness of the message processing of the NFV network system, avoiding the consumption of resources, and ensuring the normal operation of the network and the MANO system.

[0095] Based on the above embodiments, the present invention provides a message processing method, which can be applied to a message processing device. Figure 2 As shown, the method may include the following steps:

[0096] Step 201: Acquire historical message data of an interface, and classify the historical message data of the interface to obtain historical message data of each type of interface.

[0097] The historical message data includes authentication message data and / or resource change message data.

[0098] In a feasible implementation, classifying the historical message data may include classifying the historical message data according to the type of interface.

[0099] It should be noted that the historical message data may be authentication message data and / or resource change message data within a certain historical period; in a feasible implementation, the historical message data of 10 days before the current time may be obtained for each type of interface.

[0100] Step 202: pre-process the historical message data of each type of interface to obtain a data sequence of the interface call volume of each type of interface.

[0101] In a feasible implementation, preprocessing may include cleaning, deduplication, statistics and interpolation. Cleaning may include removing unnecessary fields, unifying the data formats of the same fields and removing illegal values. Deduplication may include retaining only one piece of data at each moment and removing redundant data at each moment. Statistics may include statistically analyzing the historical message data of each type of interface that has been cleaned and deduplicated to obtain the interface call frequency data at each moment corresponding to each type of interface. Interpolation may include calculating the data missing ratio of the interface call frequency data, and then interpolating the historical message data whose missing ratio is less than a preset ratio value by linear interpolation or other methods. The preset ratio value may be 10%, or it may be set and adjusted according to the actual application situation. After interpolation, a data sequence of interface call volume corresponding to each type of interface is obtained.

[0102] Step 203: Perform time series modeling based on the interface call volume data sequence to obtain a time series model of each type of interface call volume.

[0103] In the embodiment of the present invention, the interface call volume in the interface call volume data sequence is modeled as a time series, thereby generating a time series model. Among them, in the related art, any method that can implement the time series modeling of the embodiment of the present invention can be applied in the embodiment of the present invention.

[0104] Step 204: Obtain the first real-time interface call volume of the interface to be monitored at multiple moments.

[0105] Step 205: Determine a reference abnormal interface from the interfaces to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored.

[0106] In the embodiment of the present invention, some reference abnormal interfaces can be preliminarily determined to narrow the scope of interfaces where abnormalities occur. These reference abnormal interfaces can include interfaces where message storms occur and "noise" interfaces, wherein the "noise" interface may be an interface where message storms occur temporarily within a short period of time.

[0107] Wherein, step 205 can be implemented by steps 205a-205b:

[0108] Step 205a: Analyze the interface call volume time series model corresponding to the type of interface to be monitored to obtain a reference interface call volume.

[0109] In a feasible implementation, the interface call volume in the interface call volume time series model can conform to the normal distribution; in the normal distribution curve, the interface call volume corresponding to the peak value is used as the reference interface call volume; wherein each type of interface to be monitored corresponds to a reference interface call volume.

[0110] Step 205b: Determine a reference abnormal interface from the interfaces to be monitored based on the reference interface call volume and the first real-time interface call volume.

[0111] In an embodiment of the present invention, the reference interface call volume and the first real-time interface call volume are first compared, and then the comparison result is compared with a preset reference value to obtain a comparison result. Based on the comparison result, a reference abnormal interface is determined from the interface to be monitored.

[0112] Step 206: Obtain a reference performance indicator of the reference abnormal interface from the performance indicators.

[0113] Among them, the performance indicator indicates the message retention degree of the interface.

[0114] In a feasible implementation, the performance indicator may include one or more indicators such as: network traffic of the interface, CPU usage of the interface, memory occupancy of the interface, etc. The performance indicator of the reference abnormal interface is the reference performance indicator.

[0115] Step 207: Determine a target abnormal interface from the reference abnormal interfaces based on the second real-time interface call volume and the reference performance indicator of the reference abnormal interface.

[0116] In a feasible implementation, when the performance indicator can be multiple indicators, the reference performance indicator can also be multiple. Using multiple reference performance indicators to determine the target abnormal interface can further improve the accuracy of determining the target abnormal interface, that is, improve the accuracy of determining the occurrence of a message storm.

[0117] Wherein, step 207 can be implemented by steps 207a-207b:

[0118] Step 207a: Use a sliding average algorithm to calculate a first moving average value of the second real-time interface call volume and a second moving average value of the reference performance indicator.

[0119] In a feasible implementation, the first moving average value and the second moving average value may be calculated using an exponential moving average algorithm. The first moving average value and the second moving average value are calculated in the same way; a represents a smoothing parameter, 0≤a≤1; n represents the size of the time sliding window, n is a natural number, y T-i represents the reference performance index at i moments before moment T; The second moving average value of the reference performance index at time T or time T+1. When the reference performance index is multiple indexes, the second moving average value of each index is calculated respectively. The calculation formula for the second moving average value of the reference performance index can be shown as formula (1):

[0120]

[0121] It should be noted that when using formula (1) to calculate the first moving average, in formula (1), y T-i Indicates the second real-time interface call volume at time i before time T; Indicates the first moving average of the reference abnormal interface call volume at time T or time T+1. Other parameters remain unchanged.

[0122] It should be noted that if It can be used as the first moving average of the second real-time interface call volume at time T+1 and the second moving average of the reference performance indicator. The predicted first moving average value and the predicted second moving average value are predicted; at this time, based on the predicted moving average value, the target abnormal interface is predicted from the reference abnormal interface; it should be noted that the predicted target abnormal interface refers to the interface where abnormalities may occur.

[0123] Step 207b: Determine a target abnormal interface from reference abnormal interfaces based on the first moving average value and the second moving average value.

[0124] In the embodiment of the present invention, the moving average value can reduce the influence of other factors on the second real-time interface call volume and the reference performance index, so that the determined target abnormal interface is more accurate.

[0125] Step 208: Acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface.

[0126] Step 209: Based on the retained message and the real-time message, flow control is performed on the target abnormal interface.

[0127] In the embodiment of the present invention, flow control processing can be performed on the real-time message by comparing the relationship between the retained message and the real-time message.

[0128] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0129] The message processing method provided by the present invention adopts an interface call volume time series model generated based on authentication message data and resource change message data, can determine the target abnormal interface that generates the message storm, and perform flow control processing on the messages of the target abnormal interface, thereby realizing the discovery and processing of the message storm of the authentication message and the resource change message, thereby ensuring the timeliness of the NFV network system message processing, avoiding the consumption of resources, and ensuring the normal operation of the network and the MANO system.

[0130] Based on the above embodiments, the present invention provides a message processing method, which can be applied to a message processing device. Figure 3 As shown, the method may include the following steps:

[0131] Step 301: Acquire historical message data of an interface, and classify the historical message data of the interface to obtain historical message data of each type of interface.

[0132] Step 302: pre-process the historical message data of each type of interface to obtain a data sequence of interface call volume of each type of interface.

[0133] Step 303: Perform time series modeling based on the interface call volume data sequence to obtain a time series model of each type of interface call volume.

[0134] Step 304: Obtain the first real-time interface call volume of the interface to be monitored at multiple moments.

[0135] Step 305: Analyze the interface call volume time series model corresponding to the type of the interface to be monitored to obtain a reference interface call volume;

[0136] Step 306: Calculate the difference between each first real-time interface call amount and the reference interface call amount.

[0137] In a feasible implementation, the first real-time interface call amount can be used as a subtrahend and the reference interface call amount as a minuend to calculate the difference; wherein res represents the difference, that is, the residual; C true Indicates the first real-time interface call volume; C pre represents the reference interface call volume; at this time, the calculation formula of the difference between the first real-time interface call volume and the reference interface call volume can be shown as formula (2):

[0138] res=C true -C pre (2)

[0139] Step 307: Standardize the difference to obtain a standardized residual of the interface to be monitored.

[0140] In a feasible implementation, nres represents the standardized residual; mean(res) represents the mean of the residual; sd(res) represents the standard deviation of the residual. The standardized residual follows the standard normal distribution N(0, 1) with a mean of 0 and a variance of 1; at this time, the calculation formula for standardizing the difference can be shown as formula (3):

[0141]

[0142] Step 308: If the standardized residual is greater than a preset reference value, the interface to be monitored is determined to be a reference abnormal interface.

[0143] The preset reference value can be the upper α quantile u of the standard normal distribution. α , compare the standardized residual with the upper α quantile u α For comparison, if nres>u α , it can be considered that the first real-time interface call volume corresponding to the standardized residual has an abnormality, and the interface to be monitored corresponding to the first real-time interface call volume is the reference abnormal interface. It should be noted that the value of α can be set and adjusted according to the actual application situation; when α=0.92, nres>u 0.92 The probability is 0.08; if nres>u 0.92 , it can be considered that the first real-time interface call amount corresponding to the standardized residual has an abnormality.

[0144] Step 309: Obtain a reference performance indicator of the reference abnormal interface from the performance indicators.

[0145] Step 310: Use a sliding average algorithm to calculate a first moving average value of the second real-time interface call volume and a second moving average value of the reference performance indicator.

[0146] Step 311: Based on the first moving average value and the first preset threshold value, the first moving average value is normalized to obtain a first normalized value of the second real-time interface call amount.

[0147] In a feasible implementation, the first moving average value is compared with a first preset threshold value, and the first preset threshold value is (Q d , Q u ), the first moving average is greater than Q u When , the first moving average value is assigned 1, and the first moving average value is less than Q d , assign 0 to the first moving average value to obtain the first normalized value.

[0148] Step 312: Based on the second moving average value of each reference performance indicator and the first preset threshold value, normalize the second moving average value of each reference performance indicator to obtain a second normalized value of each reference performance indicator.

[0149] In a feasible implementation, the normalization processing method for the first moving average value and the second moving average value is the same. If the reference performance index includes multiple indicators, the second moving average value of each reference performance index is compared with the first preset threshold value, and the first preset threshold value is (Q d , Q u ), the second moving average is greater than Q u When , the second moving average value is assigned 1, and the second moving average value is less than Q d When , the second moving average value is assigned 0, and the second normalized value of each reference performance indicator is obtained. u In the case of Q, it can be considered that the reference abnormal interface call volume or reference performance indicator corresponding to the moving average value is abnormal, and the moving average value is less than Q d In the case of the moving average value, the reference abnormal interface call volume or the reference performance index corresponding to the moving average value can be considered normal. It should be noted that the first preset threshold value can be set and adjusted according to actual applications.

[0150] Step 313: Calculate the message storm index of the reference abnormal interface based on the first normalized value, the first preset weight of the second real-time interface call volume, the second normalized value of each reference performance indicator, and the second preset weight of each reference performance indicator.

[0151] In an embodiment of the present invention, if the reference performance index is a plurality of indexes, for each reference performance index, the second normalized value of the reference performance index and its corresponding second preset weight are multiplied to obtain a product, and at the same time, the first normalized value and the first preset weight value are multiplied to obtain a product, and finally all the obtained products are added to obtain the message storm index; in a feasible implementation method, if the second real-time interface call amount is used as an index in the reference performance index, the message storm index can be calculated using formula (4):

[0152]

[0153] Among them, Storm represents the message storm index; K represents the number of reference performance indicators, K is a positive integer; j represents the label corresponding to the reference performance indicator, j is a natural number; v j represents the normalized value of the reference performance indicator labeled j; w j Indicates the preset weight of the reference performance indicator labeled j.

[0154] It should be noted that the preset weights of the reference performance indicators can be set and adjusted according to actual application conditions.

[0155] Step 314: If the message storm index is greater than the second preset threshold, determine the reference abnormal interface as the target abnormal interface.

[0156] It should be noted that the second preset threshold can be set and adjusted according to actual application conditions.

[0157] Step 315: Obtain the retained message of the target abnormal interface and the real-time message of the target abnormal interface.

[0158] Step 316: Establish a message cache queue.

[0159] The message cache queue is used to store stranded messages.

[0160] In the embodiment of the present invention, when it is determined that a message storm has occurred after the target abnormal interface is determined, a message cache queue is established.

[0161] In a feasible implementation method, when establishing a message cache queue, it is necessary to first determine the capacity of the message cache queue. The capacity can be a preset capacity based on the actual application, or it can be a capacity determined by calculating the first message storm index of the target abnormal interface.

[0162] Wherein, step 316 can be implemented by steps 316a-316b:

[0163] Step 316a: Determine the capacity of the message cache queue based on the first message storm index of the target abnormal interface.

[0164] Step 316b: Establish a message cache queue based on the capacity of the message cache queue.

[0165] In the embodiment of the present invention, among the message storm indexes, a message storm index greater than the second preset threshold is a first message storm index, that is, a first message storm index of the target abnormal interface.

[0166] In a feasible implementation, the capacity of the message cache queue can be determined through the functional relationship size=f(Storm') between the first message storm index and the capacity of the message cache queue, and then the message cache queue is established based on the capacity.

[0167] Among them, size represents the capacity of the message cache queue; Storm' represents the first message storm index; the functional relationship may include a linear functional relationship, that is, the higher the first message storm index is, the larger the capacity is.

[0168] Step 317: If there is a message matching the real-time message in the retained messages, delete the retained message matching the real-time message, and store the real-time message in the message cache queue.

[0169] In the embodiment of the present invention, the retained messages are filtered by checking whether the real-time messages are the same as the retained messages, thereby avoiding the loss of real-time messages and avoiding repeated processing of expired retained messages, thereby ensuring the timeliness of the retained message processing and further ensuring the timeliness of the message processing.

[0170] In a feasible implementation, since a plurality of retained messages identical to the real-time message may be stored in the cache queue, it is possible to detect one by one whether the retained messages are identical to the real-time message.

[0171] In a feasible implementation, if there is no message identical to the real-time message in the retained messages, the real-time message is stored in the message cache queue.

[0172] Wherein, step 317 can be implemented by steps 317a-317c:

[0173] Step 317a, calculate the hash value of the real-time message; and detect whether the hash value of the real-time message is the same as the hash value of the retained message; wherein the hash value of the retained message is stored in the message cache queue.

[0174] In the embodiment of the present invention, the hash value of the retained message may be calculated after the retained message is obtained, and the cache queue stores the retained message and its hash value together.

[0175] In a feasible implementation, the hash value of the retained message is calculated by using the combination of the type of resource corresponding to the retained message and the unique identifier of the resource as a key, and the algorithm for calculating the hash value includes but is not limited to the modulus algorithm. The method for calculating the hash value of the retained message is the same as the method for calculating the hash value of the real-time message.

[0176] Step 317b: If they are the same, based on the preset resource matching library, detect whether the resource corresponding to the retained message is the same as the resource corresponding to the real-time message.

[0177] In a feasible implementation, the preset resource matching library stores information such as the type of interface, the type of resource corresponding to the message, the field of the resource, and the detection method of the same resource. Further, the type of the target abnormal interface, the resource corresponding to the stranded message, and the resource corresponding to the real-time message are matched with the information in the preset resource matching library, and after matching, the resource corresponding to the stranded message and the resource corresponding to the real-time message are detected according to the detection method of the same resource to see whether they are the same.

[0178] In a feasible implementation, if the hash value of the real-time message is different from the hash value of the retained message, the real-time message and the hash value of the real-time message are stored in a message cache queue.

[0179] Step 317c: If they are the same, delete the retained message with the same resource as the real-time message, and store the real-time message and the hash value of the real-time message in the message cache queue.

[0180] It should be noted that there is no order in which step 311 and step 312 are executed.

[0181] The message processing method provided by the present invention adopts an interface call volume time series model generated based on authentication message data and resource change message data, can determine the target abnormal interface that generates the message storm, and perform flow control processing on the messages of the target abnormal interface, thereby realizing the discovery and processing of the message storm of the authentication message and the resource change message, thereby ensuring the timeliness of the NFV network system message processing, avoiding the consumption of resources, and ensuring the normal operation of the network and the MANO system.

[0182] Based on the above embodiment, in other embodiments of the present invention, after step 316, steps 401-402 may be further performed:

[0183] Step 401: Calculate the second message storm index of the target abnormal interface.

[0184] In the embodiment of the present invention, the second message storm index is calculated in the same manner as the message storm index in step 312, except that the second message storm index is calculated after flow control is performed on the target abnormal interface.

[0185] Step 402: If the second message storm index is less than or equal to the third preset threshold, the message cache queue is deleted.

[0186] In the embodiment of the present invention, if the second message storm index is less than or equal to the third preset threshold value, the target abnormal interface is converted to a normal interface, that is, the message storm of the target abnormal interface is eliminated, and at this time, the real-time messages of the normal interface can be processed normally. After all the stranded messages in the message cache queue are processed, the message cache queue can be deleted.

[0187] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0188] Based on the foregoing embodiment, in other embodiments of the present invention, the method may further include the following steps:

[0189] Step 501: Compare the number of retained messages in the message cache queue with the capacity of the message cache queue to obtain a comparison result.

[0190] Step 502: Based on the comparison result, adjust the relationship between the first message storm index and the capacity of the message cache queue.

[0191] In a feasible implementation, if the capacity of the message cache queue is calculated based on a functional relationship between the first message storm index and the capacity of the message cache queue, the functional relationship can be adjusted according to the comparison result.

[0192] In a feasible implementation, when the number of stranded messages in the message cache queue is greater than or equal to the capacity of the message cache queue, a cache overflow will occur. At this time, the functional relationship between the first message storm index and the capacity of the message cache queue can be adjusted and optimized, so that when the subsequent message cache queue is established, the capacity of the message cache queue is adjusted to avoid cache overflow. When the ratio of the maximum value of the number of stranded messages in the message cache queue to the capacity of the message cache queue is less than a fourth preset threshold, the functional relationship between the first message storm index and the capacity of the message cache queue can be adjusted and optimized, so that when the subsequent message cache queue is established, the capacity of the message cache queue is adjusted to avoid occupying space due to excessive capacity.

[0193] Based on the foregoing embodiment, in other embodiments of the present invention, the method may further include the following steps:

[0194] Step 601: monitor first system resource information and second system resource information, and compare the first system resource information and the second system resource information.

[0195] The first system resource information is the system resource information before the message cache queue is established; the second system resource information is the system resource information after the message cache queue is established.

[0196] In the embodiment of the present invention, the first system resource information and the second system resource information are both system resource information of the MANO system. By monitoring the first system resource information and the second system resource information, the operating status of the MANO system and the performance status of the system before and after the message cache queue is established can be compared.

[0197] Based on the foregoing embodiment, in other embodiments of the present invention, the method may further include the following steps:

[0198] Step 701: Perform resource relevance analysis on resource information associated with the target abnormal interface to determine the network failure point.

[0199] In the embodiment of the present invention, the resource information associated with the target abnormal interface can be used to locate the fault point of the network, thereby determining the root cause of the message storm caused by the target abnormal interface, so as to timely eliminate the fault point and ensure the normal operation of the network.

[0200] It should be noted that the above step 701 can be performed before or after step 104 , step 208 and step 315 , or after step 105 , step 209 and step 317 .

[0201] Wherein, step 701 may be implemented by steps 701a, 701b and / or 701c:

[0202] Step 701a: If the resource information associated with the target abnormal interface comes from resource information associated with the network element layer, virtual layer and physical layer in the NFV architecture, it is determined that the cause of the network failure is the association between the network element layer, virtual layer and physical layer.

[0203] In an embodiment of the present invention, if the resource information corresponding to the retained message and the real-time message of the target abnormal interface is derived from the first resource information in the network element layer, the virtual layer and / or the physical layer, and the first resource information is associated with the second resource information in the three layers, further, if the second resource information is associated with the third resource information in the three layers, then due to the association between the network element layer, the virtual layer and the physical layer, a network failure is generated, which in turn causes a message storm on the interface. The first resource information, the second resource information and the third resource information may respectively include one or more resource information.

[0204] In a feasible implementation, the professional network management equipment at the network element layer frequently obtains identity authentication token information from the upper-layer integrated network management, and it is believed that the virtual network card information at the virtual layer changes frequently. The reason for such frequent changes may be the unstable connection of a switch at the physical layer. Therefore, it is believed that the association between the network element layer, the physical layer and the virtual layer causes the network failure.

[0205] Step 701b: If the resource information associated with the target abnormal interface comes from the resource information of a network element group having multiple network elements at the network element layer in the NFV architecture, it is determined that the fault point of the network is the network element group.

[0206] In an embodiment of the present invention, multiple network elements constituting a network element group have an association relationship. If the resource information associated with the target abnormal interface comes from the network element group of the network element layer in the NFV architecture, it can be determined that the network element group composed of multiple network elements is the fault point of the network.

[0207] In a feasible implementation, the failure of the network element group may include a failure in a signaling link of the network element group, a failure in an unreachable network route of the network element group, or a failure in which network elements in the network element group are simultaneously overloaded.

[0208] Step 701c: If the resource information associated with the target abnormal interface comes from the resource information of a network element node group having multiple network element nodes in the network element of the NFV architecture, it is determined that the fault point of the network is the network element node group.

[0209] In a feasible implementation method, after determining the cause of the network failure and the fault point of the network, the network element information that caused the network failure can be obtained, and the fault diagnosis can be performed based on the network element information. The fault diagnosis can include fault diagnosis through various professional fault management systems, and / or going to the on-site computer room or base station to troubleshoot the fault based on the network element information.

[0210] In a feasible implementation, the message processing method of the embodiment of the present invention can be applied to Figure 4 In the system shown, the system may include: a raw data module, an application and system indicator module, a data analysis preprocessing module, a model training and message storm confirmation module, a flow control processing module, a preset resource matching library, a training model library and an application module. Among them, the raw data module includes raw data, which may include interface authentication messages and resource change messages. Specifically:

[0211] First, the interface authentication message and the resource change message are classified and preprocessed by the data analysis preprocessing module; wherein the preprocessing may include data processing through a data cleaning submodule, a data deduplication submodule, a data statistics submodule and a data interpolation submodule; in a feasible implementation method, the interface authentication message and the resource change message may refer to the historical interface authentication message and the resource change message; of course, the interface authentication message and the resource change message may also include the interface authentication message and the resource change message generated by the interface in real time.

[0212] Secondly, after preprocessing, the interface call volume data sequence of each type of interface is obtained. Based on the algorithm in the model training library, the interface call volume data sequence is trained in the model training and message storm confirmation module to obtain the interface call volume time series model, and the interface call volume time series is stored in the training model library.

[0213] Then, the model training and message storm confirmation module can determine the reference abnormal interface among the interfaces to be monitored based on the interface call volume time series model and the real-time interface call volume.

[0214] Again, the data analysis submodule of the flow control processing module determines the target abnormal interface from the reference abnormal interface according to the various indicators in the application and system indicator modules, that is, determines the interface where the message storm occurs. After that, the data analysis submodule calls the traffic policy configuration execution submodule. The traffic policy configuration execution submodule performs flow control processing on the stranded messages and real-time messages of the target abnormal interface through the message cache queue based on the preset resource matching library; at the same time, the policy execution management submodule monitors the cache overflow of the message cache queue, and compares and analyzes the system resource information before and after the flow control processing. When the message storm of the target abnormal interface is eliminated, the policy execution management submodule instructs the traffic policy configuration execution submodule to release the flow control processing and restore the normal interface message processing flow.

[0215] Finally, the network hidden danger investigation submodule in the application module investigates network fault hidden dangers according to the resource information associated with the target abnormal interface, and the capability output submodule can output information such as the message type and interface details of the target abnormal interface that generates the message storm.

[0216] It should be noted that, for the description of the same steps and the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0217] The message processing method provided by the present invention can determine the target abnormal interface that generates the message storm based on the interface call volume time series model generated by the authentication message data and the resource change message data, and then perform flow control processing on the messages of the target abnormal interface to realize the discovery and processing of the message storm of the authentication message and the resource change message, thereby ensuring the timeliness of the NFV network system message processing, avoiding the consumption of resources, and ensuring the normal operation of the network and the MANO system.

[0218] The present invention provides a message processing device, which can be applied to Figures 1 to 3 In a corresponding message processing method, refer to Figure 5 As shown, the device may include: a generating unit 81, a first acquiring unit 82, a first determining unit 83, a second acquiring unit 84 and a processing unit 85, wherein:

[0219] A generating unit 81 is used to obtain historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the call volume of each type of interface;

[0220] A first acquisition unit 82 is used to acquire a first real-time interface call volume of the interface to be monitored at multiple moments;

[0221] A first determining unit 83 is used to determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume and the interface performance index;

[0222] A second acquisition unit 84 is used to acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface;

[0223] The processing unit 85 is used to perform flow control processing on the target abnormal interface based on the retained message and the real-time message.

[0224] In other embodiments of the present invention, the generating unit 81 may include: an acquiring module, a processing module and a generating module.

[0225] An acquisition module, used to acquire historical message data of an interface, and classify the historical message data of the interface to obtain historical message data of each type of interface, wherein the historical message data includes authentication message data and / or resource change message data;

[0226] A processing module, used for preprocessing the historical message data of each type of interface to obtain a data sequence of the interface call volume of each type of interface;

[0227] A generation module is used to perform time series modeling based on the interface call volume data series to obtain a time series model of each type of interface call volume.

[0228] In other embodiments of the present invention, the first determining unit 83 may include: a first determining module, an acquiring module and a second determining module.

[0229] A first determination module is used to determine a reference abnormal interface from the interface to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored;

[0230] An acquisition module, used to acquire a reference performance indicator of a reference abnormal interface from the performance indicators, wherein the performance indicator indicates a message retention degree of the interface;

[0231] The second determination module is used to determine a target abnormal interface from the reference abnormal interface based on a second real-time interface call volume and a reference performance indicator of the reference abnormal interface.

[0232] The first determination module is specifically used to implement the following steps:

[0233] Analyze the interface call volume time series model corresponding to the type of interface to be monitored to obtain a reference interface call volume;

[0234] Based on the reference interface call volume and the first real-time interface call volume, a reference abnormal interface is determined from the interfaces to be monitored.

[0235] The first determining module is further specifically used to implement the following steps:

[0236] Calculate the difference between each first real-time interface call amount and the reference interface call amount;

[0237] The difference is standardized to obtain the standardized residual of the interface to be monitored;

[0238] If the standardized residual is greater than the preset reference value, the interface to be monitored is determined to be a reference abnormal interface.

[0239] The second determining module is specifically used to implement the following steps:

[0240] Using a sliding average algorithm, calculate a first moving average value of the second real-time interface call volume and a second moving average value of the reference performance indicator;

[0241] A target abnormal interface is determined from reference abnormal interfaces based on the first moving average value and the second moving average value.

[0242] The second determining module is further specifically used to implement the following steps:

[0243] Based on the first moving average value and the first preset threshold value, the first moving average value is normalized to obtain a first normalized value of the second real-time interface call amount;

[0244] Based on the second moving average value of each reference performance indicator and the first preset threshold value, normalizing the second moving average value of each reference performance indicator to obtain a second normalized value of each reference performance indicator;

[0245] Calculate a message storm index of a reference abnormal interface based on the first normalized value, the first preset weight of the second real-time interface call amount, the second normalized value of each reference performance indicator, and the second preset weight of each reference performance indicator;

[0246] If the message storm index is greater than a second preset threshold, the reference abnormal interface is determined to be the target abnormal interface.

[0247] In other embodiments of the present invention, the processing unit 85 may include: a creation module and a filtering module.

[0248] A creation module is used to establish a message cache queue, wherein the message cache queue is used to store stranded messages;

[0249] The filtering module is used to delete the retained messages matching the real-time messages if there are retained messages matching the real-time messages, and store the real-time messages in the message cache queue.

[0250] The creation module is specifically used to implement the following steps:

[0251] Determine the capacity of the message cache queue based on the first message storm index of the target abnormal interface;

[0252] A message cache queue is established based on the capacity of the message cache queue.

[0253] The filtering module is specifically used to implement the following steps:

[0254] Calculate the hash value of the real-time message; and detect whether the hash value of the real-time message is the same as the hash value of the retained message, wherein the hash value of the retained message is stored in the message cache queue;

[0255] If they are the same, based on the preset resource matching library, check whether the resource corresponding to the stranded message is the same as the resource corresponding to the real-time message;

[0256] If they are the same, delete the stranded message with the same resource as the real-time message, and store the real-time message and the hash value of the real-time message in the message cache queue.

[0257] In other embodiments of the present invention, the message processing device further includes: a calculation unit and a detection unit.

[0258] A calculation unit, used for calculating a second message storm index of a target abnormal interface;

[0259] The detection unit is configured to delete the message cache queue if the second message storm index is less than or equal to a third preset threshold.

[0260] In other embodiments of the present invention, the message processing device further includes: a second determining unit.

[0261] The second determining unit is used to perform resource correlation analysis on the resource information associated with the target abnormal interface to determine the cause of the network failure and / or the failure point of the network.

[0262] The second determining unit is specifically used to implement the following steps:

[0263] If the resource information associated with the target abnormal interface is derived from resource information associated with the network element layer, virtual layer, and physical layer in the NFV architecture, it is determined that the cause of the network failure is the association between the network element layer, virtual layer, and physical layer; and / or

[0264] If the resource information associated with the target abnormal interface is derived from the resource information of a network element group having multiple network elements at the network element layer in the NFV architecture, it is determined that the fault point of the network is the network element group; and / or

[0265] If the resource information associated with the target abnormal interface is derived from the resource information of a network element node group having multiple network element nodes in the network element of the NFV architecture, it is determined that the fault point of the network is the network element node group.

[0266] In other embodiments of the present invention, the message processing device further includes: a comparison unit and an adjustment unit.

[0267] A comparison unit, used to compare the number of stranded messages in the message cache queue with the capacity of the message cache queue to obtain a comparison result;

[0268] The adjusting unit is used to adjust the relationship between the first message storm index and the capacity of the message cache queue based on the comparison result.

[0269] In other embodiments of the present invention, the message processing device further includes: a monitoring unit.

[0270] The monitoring unit is used to monitor the first system resource information and the second system resource information, and compare the first system resource information and the second system resource information, wherein the first system resource information is the system resource information before the message cache queue is established; the second system resource information is the system resource information after the message cache queue is established.

[0271] The message processing device provided by the present invention can determine the target abnormal interface that generates the message storm based on the interface call volume time series model generated by the authentication message data and the resource change message data, and then perform flow control processing on the messages of the target abnormal interface to realize the discovery and processing of the message storm of the authentication message and the resource change message, thereby ensuring the timeliness of the NFV network system message processing, avoiding the consumption of resources, and ensuring the normal operation of the network and the MANO system.

[0272] Based on the above embodiments, the present invention provides a message processing device 9, which can be applied to Figures 1 to 3 In a corresponding message processing method, refer to Figure 6 As shown, the device may include: a processor 91, a memory 92 and a communication bus 93, wherein:

[0273] The communication bus 93 is used to realize the communication connection between the processor 91 and the memory 92;

[0274] The processor 91 is used to execute the message processing program stored in the memory 92 to implement the following steps:

[0275] Obtain the historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the call volume of each type of interface;

[0276] Obtaining the first real-time interface call volume of the interface to be monitored at multiple moments;

[0277] Determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the interface performance indicator;

[0278] Obtain the retained message of the target abnormal interface and the real-time message of the target abnormal interface;

[0279] Based on the retained messages and real-time messages, flow control is performed on the target abnormal interface.

[0280] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 to obtain historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the interface call volume of each type, so as to implement the following steps:

[0281] Acquire historical message data of the interface, and classify the historical message data of the interface to obtain historical message data of each type of interface, wherein the historical message data includes authentication message data and / or resource change message data;

[0282] Preprocess the historical message data of each type of interface to obtain the interface call volume data sequence of each type of interface;

[0283] Time series modeling is performed based on the interface call volume data series to obtain a time series model of each type of interface call volume.

[0284] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 based on the interface call volume time series model, the first real-time interface call volume, and the interface performance index, and determine the target abnormal interface from the interface to be monitored to implement the following steps:

[0285] Determine a reference abnormal interface from the interfaces to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored;

[0286] From the performance indicators, obtain a reference performance indicator of a reference abnormal interface, wherein the performance indicator indicates a message retention degree of the interface;

[0287] Based on the second real-time interface call volume and the reference performance indicator of the reference abnormal interface, a target abnormal interface is determined from the reference abnormal interface.

[0288] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92, based on the first real-time interface call volume and the interface call volume time series model corresponding to the type of the interface to be monitored, to determine a reference abnormal interface from the interface to be monitored, so as to implement the following steps:

[0289] Analyze the interface call volume time series model corresponding to the type of interface to be monitored to obtain a reference interface call volume;

[0290] Based on the reference interface call volume and the first real-time interface call volume, a reference abnormal interface is determined from the interfaces to be monitored.

[0291] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92, and determine a reference abnormal interface from the interfaces to be monitored based on the reference interface call amount and the first real-time interface call amount, so as to implement the following steps:

[0292] Calculate the difference between each first real-time interface call amount and the reference interface call amount;

[0293] The difference is standardized to obtain the standardized residual of the interface to be monitored;

[0294] If the standardized residual is greater than the preset reference value, the interface to be monitored is determined to be a reference abnormal interface.

[0295] In other embodiments of the present invention, the processor 91 is further configured to execute the second real-time interface call volume and the reference performance index based on the reference abnormal interface of the message processing program stored in the memory 92, and determine the target abnormal interface from the reference abnormal interface to implement the following steps:

[0296] Using a sliding average algorithm, calculate a first moving average value of the second real-time interface call volume and a second moving average value of the reference performance indicator;

[0297] A target abnormal interface is determined from reference abnormal interfaces based on the first moving average value and the second moving average value.

[0298] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92, based on the first moving average value and the second moving average value, to determine the target abnormal interface from the reference abnormal interface, so as to implement the following steps:

[0299] Based on the first moving average value and the first preset threshold value, the first moving average value is normalized to obtain a first normalized value of the second real-time interface call amount;

[0300] Based on the second moving average value of each reference performance indicator and the first preset threshold value, normalizing the second moving average value of each reference performance indicator to obtain a second normalized value of each reference performance indicator;

[0301] Calculate a message storm index of a reference abnormal interface based on the first normalized value, the first preset weight of the second real-time interface call amount, the second normalized value of each reference performance indicator, and the second preset weight of each reference performance indicator;

[0302] If the message storm index is greater than a second preset threshold, the reference abnormal interface is determined to be the target abnormal interface.

[0303] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92, and perform flow control processing on the target abnormal interface based on the retained message and the real-time message, so as to implement the following steps:

[0304] Establishing a message cache queue, wherein the message cache queue is used to store stranded messages;

[0305] If there is a message matching the real-time message in the retained message, the retained message matching the real-time message is deleted, and the real-time message is stored in the message cache queue.

[0306] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 to establish a message cache queue, so as to implement the following steps:

[0307] Determine the capacity of the message cache queue based on the first message storm index of the target abnormal interface;

[0308] A message cache queue is established based on the capacity of the message cache queue.

[0309] In other embodiments of the present invention, the processor 91 is further configured to execute a message processing program stored in the memory 92, if there is a message matching the real-time message in the retained message, delete the retained message matching the real-time message, and store the real-time message in the message cache queue, so as to implement the following steps:

[0310] Calculate the hash value of the real-time message; and detect whether the hash value of the real-time message is the same as the hash value of the retained message, wherein the hash value of the retained message is stored in the message cache queue;

[0311] If they are the same, based on the preset resource matching library, check whether the resource corresponding to the stranded message is the same as the resource corresponding to the real-time message;

[0312] If they are the same, delete the stranded message with the same resource as the real-time message, and store the real-time message and the hash value of the real-time message in the message cache queue.

[0313] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 to implement the following steps:

[0314] Calculate the second message storm index of the target abnormal interface;

[0315] If the second message storm index is less than or equal to the third preset threshold, the message cache queue is deleted.

[0316] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 to implement the following steps:

[0317] Perform resource correlation analysis on the resource information associated with the target abnormal interface to determine the cause of the network failure and / or the network failure point.

[0318] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 to perform resource correlation analysis on the resource information associated with the target abnormal interface, determine the cause of the network failure and / or the failure point of the network, so as to implement the following steps:

[0319] If the resource information associated with the target abnormal interface is derived from resource information associated with the network element layer, virtual layer, and physical layer in the NFV architecture, it is determined that the cause of the network failure is the association between the network element layer, virtual layer, and physical layer; and / or

[0320] If the resource information associated with the target abnormal interface is derived from the resource information of a network element group having multiple network elements at the network element layer in the NFV architecture, it is determined that the fault point of the network is the network element group; and / or

[0321] If the resource information associated with the target abnormal interface is derived from the resource information of a network element node group having multiple network element nodes in the network element of the NFV architecture, it is determined that the fault point of the network is the network element node group.

[0322] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 to implement the following steps:

[0323] Compare the number of stranded messages in the message cache queue with the capacity of the message cache queue to obtain a comparison result;

[0324] Based on the comparison result, the relationship between the first message storm index and the capacity of the message cache queue is adjusted.

[0325] In other embodiments of the present invention, the processor 91 is further configured to execute the message processing program stored in the memory 92 to implement the following steps:

[0326] Monitor the first system resource information and the second system resource information, and compare the first system resource information and the second system resource information, wherein the first system resource information is the system resource information before the message cache queue is established; and the second system resource information is the system resource information after the message cache queue is established.

[0327] The message processing device provided by the present invention can determine the target abnormal interface that generates the message storm based on the interface call volume time series model generated by the authentication message data and the resource change message data, and then perform flow control processing on the messages of the target abnormal interface to realize the discovery and processing of the message storm of the authentication message and the resource change message, thereby ensuring the timeliness of the NFV network system message processing, avoiding the consumption of resources, and ensuring the normal operation of the network and the MANO system.

[0328] Based on the above embodiments, the present invention provides a computer storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the following steps:

[0329] Obtain the historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the call volume of each type of interface;

[0330] Obtaining the first real-time interface call volume of the interface to be monitored at multiple moments;

[0331] Determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the interface performance indicator;

[0332] Obtain the retained message of the target abnormal interface and the real-time message of the target abnormal interface;

[0333] Based on the retained messages and real-time messages, flow control is performed on the target abnormal interface.

[0334] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to obtain historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the interface call volume of each type, so as to implement the following steps:

[0335] Acquire historical message data of the interface, and classify the historical message data of the interface to obtain historical message data of each type of interface, wherein the historical message data includes authentication message data and / or resource change message data;

[0336] Preprocess the historical message data of each type of interface to obtain the interface call volume data sequence of each type of interface;

[0337] Time series modeling is performed based on the interface call volume data series to obtain a time series model of each type of interface call volume.

[0338] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the performance index of the interface, so as to implement the following steps:

[0339] Determine a reference abnormal interface from the interfaces to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored;

[0340] From the performance indicators, obtain a reference performance indicator of a reference abnormal interface, wherein the performance indicator indicates a message retention degree of the interface;

[0341] Based on the second real-time interface call volume and the reference performance indicator of the reference abnormal interface, a target abnormal interface is determined from the reference abnormal interface.

[0342] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when determining a reference abnormal interface from the interface to be monitored based on the first real-time interface call volume and the interface call volume time series model corresponding to the type of the interface to be monitored:

[0343] Analyze the interface call volume time series model corresponding to the type of interface to be monitored to obtain a reference interface call volume;

[0344] Based on the reference interface call volume and the first real-time interface call volume, a reference abnormal interface is determined from the interfaces to be monitored.

[0345] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when determining a reference abnormal interface from the interfaces to be monitored based on the reference interface call amount and the first real-time interface call amount:

[0346] Calculate the difference between each first real-time interface call amount and the reference interface call amount;

[0347] The difference is standardized to obtain the standardized residual of the interface to be monitored;

[0348] If the standardized residual is greater than the preset reference value, the interface to be monitored is determined to be a reference abnormal interface.

[0349] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when determining a target abnormal interface from the reference abnormal interface based on the second real-time interface call volume and the reference performance indicator of the reference abnormal interface:

[0350] Using a sliding average algorithm, calculate a first moving average value of the second real-time interface call volume and a second moving average value of the reference performance indicator;

[0351] A target abnormal interface is determined from reference abnormal interfaces based on the first moving average value and the second moving average value.

[0352] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when determining a target abnormal interface from a reference abnormal interface based on the first moving average value and the second moving average value:

[0353] Based on the first moving average value and the first preset threshold value, the first moving average value is normalized to obtain a first normalized value of the second real-time interface call amount;

[0354] Based on the second moving average value of each reference performance indicator and the first preset threshold value, normalizing the second moving average value of each reference performance indicator to obtain a second normalized value of each reference performance indicator;

[0355] Calculate a message storm index of a reference abnormal interface based on the first normalized value, the first preset weight of the second real-time interface call amount, the second normalized value of each reference performance indicator, and the second preset weight of each reference performance indicator;

[0356] If the message storm index is greater than a second preset threshold, the reference abnormal interface is determined to be the target abnormal interface.

[0357] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to perform flow control processing on the target abnormal interface based on the retained message and the real-time message to implement the following steps:

[0358] Establishing a message cache queue, wherein the message cache queue is used to store stranded messages;

[0359] If there is a message matching the real-time message in the retained message, the retained message matching the real-time message is deleted, and the real-time message is stored in the message cache queue.

[0360] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to establish a message cache queue to implement the following steps:

[0361] Determine the capacity of the message cache queue based on the first message storm index of the target abnormal interface;

[0362] A message cache queue is established based on the capacity of the message cache queue.

[0363] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps if there is a message identical to the real-time message in the retained message, delete the retained message identical to the real-time message, and store the real-time message in the message cache queue:

[0364] Calculate the hash value of the real-time message; and detect whether the hash value of the real-time message is the same as the hash value of the retained message, wherein the hash value of the retained message is stored in the message cache queue;

[0365] If they are the same, based on the preset resource matching library, check whether the resource corresponding to the stranded message is the same as the resource corresponding to the real-time message;

[0366] If they are the same, delete the stranded message with the same resource as the real-time message, and store the real-time message and the hash value of the real-time message in the message cache queue.

[0367] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when the message processing method is executed:

[0368] Calculate the second message storm index of the target abnormal interface;

[0369] If the second message storm index is less than or equal to the third preset threshold, the message cache queue is deleted.

[0370] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when the message processing method is executed:

[0371] Perform resource correlation analysis on the resource information associated with the target abnormal interface to determine the cause of the network failure and / or the network failure point.

[0372] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to perform resource correlation analysis on the resource information associated with the target abnormal interface, and determine the cause of the network failure and / or the network failure point, so as to implement the following steps:

[0373] If the resource information associated with the target abnormal interface is derived from resource information associated with the network element layer, virtual layer, and physical layer in the NFV architecture, it is determined that the cause of the network failure is the association between the network element layer, virtual layer, and physical layer; and / or

[0374] If the resource information associated with the target abnormal interface is derived from the resource information of a network element group having multiple network elements at the network element layer in the NFV architecture, it is determined that the fault point of the network is the network element group; and / or

[0375] If the resource information associated with the target abnormal interface is derived from the resource information of a network element node group having multiple network element nodes in the network element of the NFV architecture, it is determined that the fault point of the network is the network element node group.

[0376] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when the message processing method is executed:

[0377] Compare the number of stranded messages in the message cache queue with the capacity of the message cache queue to obtain a comparison result;

[0378] Based on the comparison result, the relationship between the first message storm index and the capacity of the message cache queue is adjusted.

[0379] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to implement the following steps when the message processing method is executed:

[0380] Monitor the first system resource information and the second system resource information, and compare the first system resource information and the second system resource information, wherein the first system resource information is the system resource information before the message cache queue is established; and the second system resource information is the system resource information after the message cache queue is established.

[0381] It should be noted that the specific implementation process of the steps executed by the processor in the present invention can refer to Figures 1 to 3 The implementation process of the message processing method provided by the corresponding embodiment will not be repeated here.

[0382] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0383] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0384] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0385] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products of the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0386] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A message processing method, It is characterized in that The method comprises: Obtaining historical message data of each type of interface and performing model training on the historical message data to obtain a time series model of the call volume of each type of interface; Obtaining the first real-time interface call volume of the interface to be monitored at multiple moments; Determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the performance indicator of the interface; Acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface; Based on the retained message and the real-time message, flow control processing is performed on the target abnormal interface.

2. The method according to claim 1, It is characterized in that The acquiring of historical message data of each type of interface and performing model training on the historical message data to obtain a time series model of the call volume of each type of interface includes: Acquire historical message data of the interface, and classify the historical message data of the interface to obtain historical message data of each type of interface, wherein the historical message data includes authentication message data and / or resource change message data; Preprocessing the historical message data of each type of interface to obtain an interface call volume data sequence of each type of interface; Time series modeling is performed based on the interface call volume data series to obtain a time series model of each type of interface call volume.

3. The method according to claim 1 or 2, It is characterized in that The determining a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the performance indicator of the interface includes: Determine a reference abnormal interface from the interfaces to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored; From the performance indicators, obtaining a reference performance indicator of the reference abnormal interface, wherein the performance indicator indicates a message retention degree of the interface; The target abnormal interface is determined from the reference abnormal interface based on the second real-time interface call volume of the reference abnormal interface and the reference performance indicator.

4. The method according to claim 3, It is characterized in that The determining a reference abnormal interface from the interface to be monitored based on the first real-time interface call volume and an interface call volume time series model corresponding to the type of the interface to be monitored includes: Analyze the interface call volume time series model corresponding to the type of the interface to be monitored to obtain a reference interface call volume; Based on the reference interface call volume and the first real-time interface call volume, the reference abnormal interface is determined from the interfaces to be monitored.

5. The method according to claim 4, It is characterized in that The determining the reference abnormal interface from the interface to be monitored based on the reference interface call amount and the first real-time interface call amount includes: Calculate the difference between each of the first real-time interface call amount and the reference interface call amount; Standardizing the difference to obtain a standardized residual of the interface to be monitored; If the standardized residual is greater than a preset reference value, the interface to be monitored is determined to be the reference abnormal interface.

6. The method according to claim 3, It is characterized in that The determining the target abnormal interface from the reference abnormal interface based on the second real-time interface call amount of the reference abnormal interface and the reference performance indicator comprises: Using a sliding average algorithm, calculate a first moving average value of the second real-time interface call amount and a second moving average value of the reference performance indicator; The target abnormal interface is determined from the reference abnormal interfaces based on the first moving average value and the second moving average value.

7. The method according to claim 6, It is characterized in that The determining the target abnormal interface from the reference abnormal interface based on the first moving average value and the second moving average value comprises: Based on the first moving average value and a first preset threshold, normalizing the first moving average value to obtain a first normalized value of the second real-time interface call amount; Based on the second moving average value of each of the reference performance indicators and the first preset threshold, normalizing the second moving average value of each of the reference performance indicators to obtain a second normalized value of each of the reference performance indicators; Calculate the message storm index of the reference abnormal interface based on the first normalized value, the first preset weight of the second real-time interface call amount, the second normalized value of each of the reference performance indicators, and the second preset weight of each of the reference performance indicators; If the message storm index is greater than a second preset threshold, the reference abnormal interface is determined to be the target abnormal interface.

8. The method according to claim 7, It is characterized in that The performing flow control processing on the target abnormal interface based on the retained message and the real-time message includes: Establishing a message cache queue, wherein the message cache queue is used to store the stranded message; If there is a message matching the real-time message in the retained messages, the retained message matching the real-time message is deleted, and the real-time message is stored in the message cache queue.

9. The method according to claim 8, It is characterized in that The step of establishing a message cache queue comprises: Determining the capacity of the message cache queue based on the first message storm index of the target abnormal interface; The message cache queue is established based on the capacity of the message cache queue.

10. The method according to claim 8 or 9, It is characterized in that If there is a message matching the real-time message in the retained message, deleting the retained message matching the real-time message, and storing the real-time message in the message cache queue, comprising: Calculating a hash value of the real-time message; and detecting whether the hash value of the real-time message is the same as the hash value of the retained message, wherein the hash value of the retained message is stored in the message cache queue; If they are the same, based on a preset resource matching library, detecting whether the resource corresponding to the stranded message is the same as the resource corresponding to the real-time message; If they are the same, the retained message with the same resource as that corresponding to the real-time message is deleted, and the real-time message and the hash value of the real-time message are stored in the message cache queue.

11. The method according to claim 8, It is characterized in that The method further comprises: Calculate a second message storm index of the target abnormal interface; If the second message storm index is less than or equal to a third preset threshold, the message cache queue is deleted.

12. The method according to claim 1, It is characterized in that The method further comprises: The resource information associated with the target abnormal interface is subjected to resource correlation analysis to determine the cause of the network failure and / or the failure point of the network.

13. The method according to claim 12, It is characterized in that The performing resource correlation analysis on the resource information associated with the target abnormal interface to determine the cause of the network failure and / or the network failure point includes: If the resource information associated with the target abnormal interface is derived from resource information associated with the network element layer, virtual layer and physical layer in the NFV architecture, it is determined that the cause of the network failure is the association between the network element layer, virtual layer and physical layer; and / or If the resource information associated with the target abnormal interface is derived from resource information of a network element group having multiple network elements at the network element layer in the NFV architecture, it is determined that the fault point of the network is the network element group; and / or If the resource information associated with the target abnormal interface comes from the resource information of a network element node group having multiple network element nodes in the network element of the NFV architecture, it is determined that the failure point of the network is the network element node group.

14. The method according to claim 9, It is characterized in that The method further comprises: Comparing the number of stranded messages in the message cache queue with the capacity of the message cache queue to obtain a comparison result; Based on the comparison result, the relationship between the first message storm index and the capacity of the message cache queue is adjusted.

15. The method according to claim 8, It is characterized in that The method further comprises: Monitor the first system resource information and the second system resource information, and compare the first system resource information and the second system resource information, wherein the first system resource information is the system resource information before the message cache queue is established; and the second system resource information is the system resource information after the message cache queue is established.

16. A message processing device, It is characterized in that The device comprises: a generating unit, a first acquiring unit, a first determining unit, a second acquiring unit and a processing unit, wherein: A generating unit, used to obtain historical message data of each type of interface and perform model training on the historical message data to obtain a time series model of the call volume of each type of interface; A first acquisition unit, used to acquire a first real-time interface call volume of the interface to be monitored at multiple moments; A first determining unit is used to determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume and the performance index of the interface; A second acquisition unit, used to acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface; A processing unit is used to perform flow control processing on the target abnormal interface based on the retained message and the real-time message.

17. A message processing device, It is characterized in that The device comprises: a processor, a memory and a communication bus; The communication bus is used to realize the communication connection between the processor and the memory; The processor is used to execute the message processing program in the memory to implement the following steps: Obtaining historical message data of each type of interface and performing model training on the historical message data to obtain a time series model of the call volume of each type of interface; Obtaining the first real-time interface call volume of the interface to be monitored at multiple moments; Determine a target abnormal interface from the interfaces to be monitored based on the interface call volume time series model, the first real-time interface call volume, and the performance indicator of the interface; Acquire the retained message of the target abnormal interface and the real-time message of the target abnormal interface; Based on the retained message and the real-time message, flow control processing is performed on the target abnormal interface.

18. A computer storage medium, It is characterized in that The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the message processing method according to any one of claims 1 to 15.