CN112203272B - Abnormality diagnosis method, device and computing equipment for moving HSS (home subscriber server) user - Google Patents
Abnormality diagnosis method, device and computing equipment for moving HSS (home subscriber server) user Download PDFInfo
- Publication number
- CN112203272B CN112203272B CN201910609185.9A CN201910609185A CN112203272B CN 112203272 B CN112203272 B CN 112203272B CN 201910609185 A CN201910609185 A CN 201910609185A CN 112203272 B CN112203272 B CN 112203272B
- Authority
- CN
- China
- Prior art keywords
- data
- hss
- test data
- reconstruction
- kpi
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/18—Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data
- H04W8/20—Transfer of user or subscriber data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L65/00—Network arrangements, protocols or services for supporting real-time applications in data packet communication
- H04L65/10—Architectures or entities
- H04L65/1016—IP multimedia subsystem [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the invention relates to the technical field of communication, and discloses an abnormality diagnosis method, an abnormality diagnosis device and a calculation device for moving an HSS user, wherein the method comprises the following steps: acquiring KPI data of a source HSS and KPI data of a target HSS in the moving process of the HSS user; combining the KPI data of the source HSS and the KPI data of the target HSS to obtain test data; inputting the test data into a reconstruction model to obtain reconstruction test data, wherein the reconstruction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a source HSS and KPI data of a target HSS in a normal state of the HSS user relocation process; calculating a reconstruction error between the reconstructed test data and the test data; and when the reconstruction error is larger than a preset threshold value, determining that the moving process of the HSS user is abnormal. Through the mode, the embodiment of the invention realizes the abnormality diagnosis of the moving of the HSS user.
Description
Technical Field
The embodiment of the invention relates to the technical field of communication, in particular to an abnormality diagnosis method, an abnormality diagnosis device and a calculation device for moving HSS users.
Background
The HSS user relocation is a type of cutover with higher difficulty and higher risk in the cutover of the HSS network element, and the existing abnormal detection in the HSS user relocation process is mainly realized by a mode of respectively setting thresholds for KPI operation indexes of a source HSS and a target HSS.
The inventors found that: in the cutting process, as key index fluctuation is large, operation and maintenance personnel often close or shield the alarm, and as for index fluctuation, normal fluctuation and abnormal fluctuation in the moving process of the HSS user are difficult to distinguish, so that abnormality in the moving process of the HSS user cannot be found in time, and the abnormality in the moving process can be determined only after the cutting is completed and problems are encountered in the service test, so that abnormality in the moving process of the existing HSS user is difficult to find or untimely to find.
Disclosure of Invention
In view of the above problems, embodiments of the present invention provide an anomaly diagnosis method, apparatus and computing device for HSS user relocation, which overcome or at least partially solve the above problems.
According to an aspect of the embodiment of the present invention, there is provided an anomaly diagnosis method for HSS user relocation, the method including: acquiring KPI data of a source HSS and KPI data of a target HSS in the moving process of the HSS user; combining the KPI data of the source HSS and the KPI data of the target HSS to obtain test data; inputting the test data into a reconstruction model to obtain reconstruction test data, wherein the reconstruction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a source HSS and KPI data of a target HSS in a normal state of the HSS user relocation process; calculating a reconstruction error between the reconstructed test data and the test data; and when the reconstruction error is larger than a preset threshold value, determining that the moving process of the HSS user is abnormal.
In an alternative way, after obtaining the test data, the method further comprises: normalizing the test data to obtain standard test data; inputting the test data into a reconstruction model to obtain reconstructed test data, including: and inputting the standard test data into a reconstruction model to obtain reconstruction test data.
In an alternative manner, the test data is normalized according to the following formula to obtain standard test data:
wherein X is std Is a group of standard test data, X is a group of test data, X max And X min Respectively, the maximum and minimum values of the set of test data.
In an alternative way, calculating a reconstruction error between the reconstructed test data and the test data comprises: calculating a reconstruction error between the reconstructed test data and the test data according to the formula:
wherein x is i Represents the ith KPI data in the test data,and (3) representing the ith KPI data in the reconstructed test data, and n represents the total number of KPI data in the test data.
In an alternative, the method further comprises: constructing a self-coding neural network model; and training the self-coding neural network model according to the plurality of groups of training data to obtain a reconstruction model.
In an alternative manner, the constructing the self-encoding neural network model includes: constructing a self-coding neural network model comprising an input layer, an output layer and ten hidden layers, wherein the ten hidden layers comprise five encoder layers and five decoder layers, and the five encoder layers are used for compressing and reducing dimensions of training data to obtain characteristic data; and the four decoder layers are used for restoring and reconstructing the characteristic data to obtain reconstructed training data.
In an optional manner, training the self-coding neural network model according to the multiple sets of training data to obtain a reconstructed model, including: obtaining the weight of the self-coding neural network model according to the plurality of groups of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a reconstruction model according to the weight with the minimum loss function value.
According to another aspect of the embodiment of the present invention, there is provided an abnormality diagnosis apparatus for HSS subscriber relocation, including: the system comprises an acquisition module, a merging module, a calculation module and a determination module, wherein the acquisition module is used for acquiring KPI data of a source HSS and KPI data of a target HSS in the moving process of the HSS user. And the merging module is used for merging the KPI data of the source HSS and the KPI data of the target HSS to obtain test data. The input module is used for inputting the test data into a reconstruction model to obtain reconstruction test data, the reconstruction model is obtained through training of a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a source HSS and KPI data of a target HSS in a normal state of the HSS user relocation process. And the calculation module is used for calculating the reconstruction error between the reconstruction test data and the test data. And the determining module is used for determining that the moving process of the HSS user is abnormal when the reconstruction error is larger than a preset threshold value.
In an optional manner, the device further comprises a normalization module, which is used for normalizing the test data to obtain standard test data. The input module is further used for inputting the standard test data into the reconstruction model to obtain reconstruction test data.
In an alternative way, the normalization module is further configured to: normalizing the test data according to the following formula to obtain standard test data:
X std ＝X sca ×(X max -X min )+X min
wherein X is std Is a group of standard test data, X is a group of test data, X max And X min Respectively, the maximum and minimum values of the set of test data.
In an alternative, the computing module is further to: calculating a reconstruction error between the reconstructed test data and the test data according to the formula:
wherein x is i Represents the ith KPI data in the test data,and (3) representing the ith KPI data in the reconstructed test data, and n represents the total number of KPI data in the test data.
In an alternative, the apparatus further comprises: the system comprises a construction module and a training module, wherein the construction module is used for constructing a self-coding neural network model. The training module is used for training the self-coding neural network model according to multiple groups of training data to obtain a reconstruction model.
In an alternative way, the building block is further configured to: constructing a self-coding neural network model comprising an input layer, an output layer and ten hidden layers, wherein the ten hidden layers comprise five encoder layers and five decoder layers, and the five encoder layers are used for compressing and reducing dimensions of training data to obtain characteristic data; and the four decoder layers are used for restoring and reconstructing the characteristic data to obtain reconstructed training data.
In an optional manner, the training module is further configured to obtain weights of the self-coding neural network model according to the multiple sets of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a reconstruction model according to the weight with the minimum loss function value.
According to yet another aspect of an embodiment of the present invention, there is provided a computing device including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus; the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the abnormality diagnosis method for the HSS user to move.
According to still another aspect of the embodiments of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, where the executable instruction causes a processor to perform operations corresponding to an abnormality diagnosis method for HSS user relocation as described above.
In the embodiment of the invention, the abnormal diagnosis is carried out on the moving process of the HSS user through the reconstruction error between the reconstruction test data and the test data, the reconstruction test data is obtained according to the reconstruction model, the reconstruction model is obtained through training of a plurality of groups of KPI data comprising the source HSS and the target HSS in the normal state of the moving process of the HSS user, the reconstruction error between the reconstruction test data and the test data is small for the test data in the normal state of the moving process of the HSS user, and the reconstruction error between the reconstruction test data and the test data is large for the test data in the abnormal state of the moving process of the HSS user, and the threshold value is set according to the reconstruction error in the normal state of the moving process of the HSS user, so that the abnormal condition occurring in the moving process of the HSS user can be effectively diagnosed.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present invention can be more clearly understood, and the following specific embodiments of the present invention are given for clarity and understanding.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a schematic diagram of an anomaly diagnosis method for HSS user relocation according to an embodiment of the present invention;
FIG. 2 shows a flowchart of an anomaly diagnosis method for HSS user relocation provided by an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a self-coding neural network in an anomaly diagnosis method for HSS user relocation according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of an abnormality diagnostic device for HSS user relocation provided by an embodiment of the present invention;
FIG. 5 illustrates a schematic diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
An application scenario of an embodiment of the present invention is HSS subscriber relocation, HSS (Home Subscriber Server) is a primary subscriber database supporting IMS network entities for handling calls/sessions. The HSS contains the user profile, performs authentication and authorization of the user, and may provide information about the physical location of the user. As the amount of subscribers increases, the original HSS cannot withstand the increasing amount of subscribers, and therefore, it is necessary to move part of the subscriber source HSS to a new HSS. When the user is moved, the source HSS sends MAP_RESET information to VLR and SGSN registered by the user in the source HSS through operation, after the VLR and SGSN receive the information, the VLR and SGSN mark the user belonging to the source HSS and trigger the position of the source HSS to update to the new HSS, and as each network element data has modified the user in the source HSS to the new HSS, the part of the modified user can be moved to the new HSS, and when the user is moved, the user needing to be moved in the source HSS is determined according to the user number section. HSS subscriber relocation generally comprises the steps of: (1) determining a user needing to be moved; (2) Deriving user data corresponding to a user to be moved from a source HSS according to the number segment; (3) collating the user data; (4) importing the collation data into the target HSS; (5) After the cutting is completed, the signaling network side modifies the routing data of the user needing to be moved and points to the target HSS; (6) The accounting side modifies the service direction and synchronizes the service issuing to the target HSS; (7) The source HSS sends a RESET instruction to the VLR/SGSN/MME to inform the user of finishing interaction and synchronization with the new HSS when the next position is updated. The schematic diagram of the abnormality diagnosis method for the HSS user relocation in the embodiment of the invention is shown in fig. 1, and by merging the acquired real-time KPI of the source HSS and the real-time KPI of the target HSS in the HSS user relocation process and inputting the merged real-time KPI into the rebuilding model, whether the HSS user relocation is abnormal or not is judged according to the relation between the output and the input of the rebuilding model. The following describes an abnormality diagnosis method for HSS user relocation in the whole process by means of embodiments.
FIG. 2 is a flowchart of an embodiment of an abnormality diagnosis method for HSS subscriber relocation according to the present invention, as shown in FIG. 2, the method includes the steps of:
step 110: and acquiring KPI data of a source HSS and KPI data of a target HSS in the moving process of the HSS user.
The source HSS refers to the HSS where the user of a certain number segment is located before relocation, and the target HSS refers to the destination HSS where the user of the number segment needs to be relocated. The KPI data of the source HSS and the KPI data of the target HSS are manually defined by those skilled in the art when implementing the embodiment of the invention, and in some implementations, the KPI data of the source HSS and the KPI data of the target HSS each include 58 features, and the number of KPI data to be acquired is 58, which respectively include: the 58 KPI data includes a route attempt number, a route success number, a roaming number attempt number, a roaming number success number, a call unknown user number, a call subscriber unreachable number, a call restriction number, a CAMEL subscriber call number, a call forwarding number, a call system failure number, a location update attempt number, a location update success number, a send forward check supplementary service indication message number, a location update unknown user number, a location update prohibition number, a location update system failure number, a CAMEL subscriber location update number, a location cancel attempt number, a location cancel success number, an insert subscriber data attempt number, an insert subscriber data success number, a delete subscriber data attempt number, a delete subscriber data success number, a send authentication information attempt number, a send authentication information success number, an authentication request return null number, a request authentication triplet number, a return authentication quintuple number, a WCN authentication failure report number, a WCN authentication success number, and a WCN CS location update success number. In order to detect abnormal conditions in the relocation process in real time, the KPI data of the source HSS and the KPI data of the target HSS are periodically acquired, and the time corresponding to a specific period is manually defined by a person skilled in the art when implementing the embodiment of the invention, and the embodiment of the invention does not limit the specific value of the period.
Step 120: and combining the KPI data of the source HSS and the KPI data of the target HSS to obtain test data.
And combining the KPI data of the 58 source HSS with the KPI data of the 58 target HSS to obtain test data containing 116 KPI data.
Step 130: and inputting the test data into a reconstruction model to obtain reconstruction test data.
The rebuilding model is obtained through training of multiple sets of training data, and each set of the multiple sets of training data comprises KPI data of a source HSS and KPI data of a target HSS in a normal state of the moving process of the HSS user. After the training data is obtained, the training data is marked, and the marking mode can be defined by a person skilled in the art, for example, a group of training data in a normal state of the moving process of the HSS user is marked as 0, and a group of training data in an abnormal state of the moving process of the HSS user is marked as 1, so that the training data in the normal state of the moving process of the HSS user is conveniently selected as the training data of the training reconstruction model.
In some embodiments, the test data is normalized to obtain standard test data before being input into the reconstruction model, and the obtained standard test data is input into the reconstruction model to obtain the reconstruction test data. Normalization is the scaling of test data to fall within a particular interval to eliminate order of magnitude differences between different kinds of test data. In a specific embodiment, the specified interval is generally [0,1], and in a specific embodiment, the standard test data is obtained according to the following formula:
wherein X is std Is a group of standard test data, X is a group of test data, X max And X min Respectively, the maximum and minimum values of the set of test data.
It can be understood that, in the process of training the reconstruction model, standard training data corresponding to the training data is obtained through normalization, and the reconstruction model is trained according to the standard training data.
In some embodiments, the self-encoding neural network is trained by constructing a self-encoding neural network model, and multiple sets of training data to obtain a reconstructed model. The self-coding neural network compresses input data, decompresses and reconstructs the input data, and performs reverse transfer by comparing errors between the reconstructed data and the input data, so that the accuracy of the self-coding neural network is improved. The framework of the constructed self-coding neural network model can be designed by those skilled in the art when implementing the embodiments of the present invention, which are not limited thereto.
In a specific embodiment, the constructed self-coding neural network model is a self-coding neural network model comprising an input layer, an output layer and ten hidden layers, wherein the ten hidden layers comprise five encoder layers and five decoder layers, which are all full connection layers, and the five encoder layers are used for compressing and reducing dimensions of training data to obtain characteristic data; the five decoder layers are used for restoring and reconstructing the characteristic data to obtain reconstructed training data. Constructed self-encoding neural networkThe specific structure of the complex is shown in FIG. 3, wherein the number of neurons arranged in the input layer is 116, x 1 To x 116 The number of neurons set by the output layer is 116 corresponding to 116 KPI data input respectively, and the number of neurons set by the output layer is 116 corresponding to 116 KPI data reconstructed through a self-coding neural network model. The five encoders reduce the original 116-dimensional data to 8-dimensional data when compressing and reducing the dimension of the training data. The first layer of hidden layer corresponds to the first encoder, the number of set neurons is 116, the activation function is selected as a 'tanh' function, the second layer of hidden layer corresponds to the second encoder, the number of set neurons is 58, the selected activation function is a 'relu' function, the third layer of hidden layer corresponds to the third encoder, the number of set neurons is 29, the selected activation function is a 'relu' function, the fourth layer of hidden layer corresponds to the fourth encoder, the number of set neurons is 15, and the selected activation function is a 'relu' function. The fifth hidden layer corresponds to the fifth encoder, the number of neurons set is 8, and the selected activation function is the "relu" function. The five decoders correspond to the five encoders, the number of neurons corresponding to the first decoder is 8, the selected activation function is a 'tanh' function, the number of neurons corresponding to the second decoder is 15, the selected activation function is a 'tanh' function, the number of neurons corresponding to the third decoder is 29, the selected activation function is a 'tanh' function, the number of neurons corresponding to the fourth decoder is 58, the selected activation function is a 'relu' function, and the number of neurons corresponding to the fifth layer decoder is 116.
The process of self-encoding neural network training is as follows: obtaining the weight of the self-coding neural network model according to the multiple groups of training data; calculating a loss function value according to the weight; repeatedly updating the weights according to the optimization algorithm until the loss function value is minimum; and obtaining a reconstruction model according to the weight with the minimum loss function value. The loss function may be selected by those skilled in the art during the implementation of embodiments of the present invention, which are not limited to the specific form of the loss function. In a specific embodiment, the loss function is a mean square error loss function MSE (Mean Squared Error), and the Adam algorithm is selected to repeatedly update the weights until the loss function is minimal. In the specific implementation process, the training round number is set to 500, namely epochs=500, the batch processing size is set to 32, namely batch_size=32, the loss function value gradually decreases along with the increase of the training round number, the model gradually converges, the training is completed, and the weight obtained by the training is derived, so that the reconstruction model is obtained.
Step 140: and calculating reconstruction errors between the reconstructed test data and the test data.
The rebuilding test data is obtained by a rebuilding model which is obtained by training KPI data under the normal state of the relocation process of the HSS user, so that the rebuilding error is small for the test data under the normal state of the relocation process of the HSS user, the rebuilding error is large for the test data under the abnormal state of the relocation process of the HSS user, and whether the relocation process of the HSS user is abnormal or not can be judged according to the size of the rebuilding error.
In a specific embodiment, the reconstruction error is the square of the absolute value of the difference between the reconstructed test data and the test data, and the specific calculation formula of the reconstruction error is:
wherein x is i Represents the ith KPI data in the test data,and (3) representing the ith KPI data in the reconstructed test data, and n represents the total number of KPI data in the test data.
Step 150: and when the reconstruction error is larger than a preset threshold value, determining that the moving process of the HSS user is abnormal.
In this step, the preset threshold is set according to the reconstruction error, for example, when the reconstruction model is trained, if the maximum value of the reconstruction error for the normal state of the HSS user during the relocation is a, the preset threshold is set to a. When the test is carried out, the reestablishment error of the abnormal state of the moving process of the HSS user is larger than a, when the reestablishment error is larger than a preset threshold value, the moving process of the HSS user is abnormal, and when the reestablishment error is not larger than the preset threshold value, the moving process of the HSS user is normal. In the specific implementation process, the PRC curve is used for determining the optimal value of a preset threshold, the curve takes the accuracy rate and the recall rate as axes, after the reconstruction model is trained, a plurality of groups of training data are input into the reconstruction model, the relation curve between the accuracy rate and the recall rate is drawn according to different thresholds, the larger the area under the curve is, the more ideal the trained model is, and the threshold corresponding to the highest recall rate is used as the preset threshold under the condition of setting reasonable accuracy rate.
In the embodiment of the invention, the abnormal diagnosis is carried out on the moving process of the HSS user through the reconstruction error between the reconstruction test data and the test data, the reconstruction test data is obtained according to the reconstruction model, the reconstruction model is obtained through training of a plurality of groups of KPI data comprising the source HSS and the target HSS in the normal state of the moving process of the HSS user, the reconstruction error between the reconstruction test data and the test data is small for the test data in the normal state of the moving process of the HSS user, and the reconstruction error between the reconstruction test data and the test data is large for the test data in the abnormal state of the moving process of the HSS user, and the threshold value is set according to the reconstruction error in the normal state of the moving process of the HSS user, so that the abnormal condition occurring in the moving process of the HSS user can be effectively diagnosed.
FIG. 4 is a functional block diagram of an embodiment of an abnormality diagnostic device for HSS subscriber relocation in accordance with the present invention. As shown in fig. 4, the apparatus includes: the system comprises an acquisition module 310, a combination module 320, an input module 330, a calculation module 340 and a determination module 350, wherein the acquisition module 310 is configured to acquire KPI data of a source HSS and KPI data of a target HSS in the process of moving the HSS user. And a merging module 320, configured to merge the KPI data of the source HSS and the KPI data of the target HSS to obtain test data. The input module 330 is configured to input the test data into a reconstruction model, to obtain reconstructed test data, where the reconstruction model is obtained by training multiple sets of training data, and each set of the multiple sets of training data includes KPI data of a source HSS and KPI data of a target HSS in a normal state of the HSS user relocation process. A calculation module 340, configured to calculate a reconstruction error between the reconstructed test data and the test data. A determining module 350, configured to determine that the HSS user relocation process is abnormal when the rebuilding error is greater than a preset threshold.
In an alternative manner, the device further includes a normalization module 360, configured to normalize the test data to obtain standard test data. The input module 330 is further configured to input the standard test data into a reconstruction model to obtain reconstructed test data.
In an alternative way, the normalization module 360 is further configured to: normalizing the test data according to the following formula to obtain standard test data:
wherein X is std Is a group of standard test data, X is a group of test data, X max And X min Respectively, the maximum and minimum values of the set of test data.
In an alternative approach, the computing module 340 is further to: calculating a reconstruction error between the reconstructed test data and the test data according to the formula:
wherein x is i Represents the ith KPI data in the test data,and (3) representing the ith KPI data in the reconstructed test data, and n represents the total number of KPI data in the test data.
In an alternative, the apparatus further comprises: a construction module 370 and a training module 380, the construction module 370 is used to construct a self-encoding neural network model. The training module 380 is configured to train the self-coding neural network model according to multiple sets of training data, so as to obtain a reconstructed model.
In an alternative approach, the build module 370 is further to: constructing a self-coding neural network model comprising an input layer, an output layer and ten hidden layers, wherein the ten hidden layers comprise five encoder layers and five decoder layers, and the five encoder layers are used for compressing and reducing dimensions of training data to obtain characteristic data; and the four decoder layers are used for restoring and reconstructing the characteristic data to obtain reconstructed training data.
In an alternative manner, training module 380 is further configured to obtain weights of the self-encoding neural network model according to the plurality of sets of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a reconstruction model according to the weight with the minimum loss function value.
In the embodiment of the invention, the calculation module 340 calculates the reconstruction error between the reconstruction test data and the test data, and carries out abnormal diagnosis on the relocation process of the HSS user according to the reconstruction error, wherein the reconstruction test data is obtained according to the reconstruction model, the reconstruction model is obtained by training a plurality of groups of KPI data comprising the source HSS and the target HSS in the normal state of the relocation process of the HSS user, the reconstruction error between the reconstruction test data and the test data is small for the test data in the normal state of the relocation process of the HSS user, and the reconstruction error between the reconstruction test data and the test data is large for the test data in the abnormal state of the relocation process of the HSS user, and the threshold value is set according to the reconstruction error in the normal state of the relocation process of the HSS user, thereby effectively diagnosing the abnormal condition occurring in the relocation process of the HSS user.
The embodiment of the invention provides a non-volatile computer storage medium, which stores at least one executable instruction, and the computer executable instruction can execute the operation corresponding to the abnormality diagnosis method for moving the HSS user.
An embodiment of the present invention provides a computer program product, where the computer program product includes a computer program stored on a computer storage medium, where the computer program includes program instructions, when executed by a computer, cause the computer to execute operations corresponding to the foregoing abnormality diagnosis method for HSS user relocation.
FIG. 5 illustrates a schematic diagram of one embodiment of a computing device, and embodiments of the invention are not limited to a particular implementation of a computing device.
As shown in fig. 5, the computing device may include: a processor 402, a communication interface (Communications Interface) 404, a memory 406, and a communication bus 408.
Wherein: processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically execute relevant steps in the foregoing embodiment of the HSS subscriber relocation procedure abnormality diagnosis method.
In particular, program 410 may include program code including computer-operating instructions.
The processor 402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 406 for storing programs 410. Memory 406 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Program 410 may be specifically operable to cause processor 402 to: acquiring KPI data of a source HSS and KPI data of a target HSS in the moving process of the HSS user; combining the KPI data of the source HSS and the KPI data of the target HSS to obtain test data; inputting the test data into a reconstruction model to obtain reconstruction test data, wherein the reconstruction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a source HSS and KPI data of a target HSS in a normal state of the HSS user relocation process; calculating a reconstruction error between the reconstructed test data and the test data; and when the reconstruction error is larger than a preset threshold value, determining that the moving process of the HSS user is abnormal.
In an alternative, program 410 may be specifically operative to cause processor 402 to perform the following operations: normalizing the test data to obtain standard test data; inputting the test data into a reconstruction model to obtain reconstructed test data, including: and inputting the standard test data into a reconstruction model to obtain reconstruction test data.
In an alternative, program 410 may be specifically operative to cause processor 402 to perform the following operations: normalizing the test data according to the following formula to obtain standard test data:
wherein X is std Is a group of standard test data, X is a group of test data, X max And X min Respectively, the maximum and minimum values of the set of test data.
In an alternative, program 410 may be specifically operative to cause processor 402 to perform the following operations: calculating a reconstruction error between the reconstructed test data and the test data according to the formula:
wherein x is i Represents the ith KPI data in the test data,represents the ith KPI data in the reconstructed test data, and n represents the test dataTotal number of KPI data.
In an alternative, program 410 may be specifically operative to cause processor 402 to perform the following operations: constructing a self-coding neural network model; and training the self-coding neural network model according to the plurality of groups of training data to obtain a reconstruction model.
In an alternative, program 410 may be specifically operative to cause processor 402 to perform the following operations: constructing a self-coding neural network model comprising an input layer, an output layer and ten hidden layers, wherein the ten hidden layers comprise five encoder layers and five decoder layers, and the five encoder layers are used for compressing and reducing dimensions of training data to obtain characteristic data; and the four decoder layers are used for restoring and reconstructing the characteristic data to obtain reconstructed training data.
In an alternative, program 410 may be specifically operative to cause processor 402 to perform the following operations: obtaining the weight of the self-coding neural network model according to the plurality of groups of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a reconstruction model according to the weight with the minimum loss function value.
In the embodiment of the invention, the abnormal diagnosis is carried out on the moving process of the HSS user through the reconstruction error between the reconstruction test data and the test data, the reconstruction test data is obtained according to the reconstruction model, the reconstruction model is obtained through training of a plurality of groups of KPI data comprising the source HSS and the target HSS in the normal state of the moving process of the HSS user, the reconstruction error between the reconstruction test data and the test data is small for the test data in the normal state of the moving process of the HSS user, and the reconstruction error between the reconstruction test data and the test data is large for the test data in the abnormal state of the moving process of the HSS user, and the threshold value is set according to the reconstruction error in the normal state of the moving process of the HSS user, so that the abnormal condition occurring in the moving process of the HSS user can be effectively diagnosed.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (10)
1. An anomaly diagnosis method for HSS user relocation, the method comprising:
acquiring KPI data of a source HSS and KPI data of a target HSS in the moving process of the HSS user;
combining the KPI data of the source HSS and the KPI data of the target HSS to obtain test data;
inputting the test data into a reconstruction model to obtain reconstruction test data, wherein the reconstruction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a source HSS and KPI data of a target HSS in a normal state of the HSS user relocation process;
calculating a reconstruction error between the reconstructed test data and the test data;
when the reconstruction error is greater than a preset threshold value, determining that the HSS user relocation process is abnormal; wherein, the PRC curve is utilized to determine the optimal value of the preset threshold.
2. The method of claim 1, wherein after obtaining the test data, the method further comprises:
normalizing the test data to obtain standard test data;
inputting the test data into a reconstruction model to obtain reconstructed test data, including:
and inputting the standard test data into a reconstruction model to obtain reconstruction test data.
3. The method of claim 2, wherein normalizing the test data to obtain standard test data comprises: normalizing the test data according to the following formula to obtain standard test data:
wherein X is std Is a group of standard test data, X is a group of test data, X max And X min Respectively, the maximum and minimum values of the set of test data.
4. The method of claim 1, wherein calculating a reconstruction error between the reconstructed test data and the test data comprises:
calculating a reconstruction error between the reconstructed test data and the test data according to the formula:
wherein x is i Represents the ith KPI data in the test data,and (3) representing the ith KPI data in the reconstructed test data, and n represents the total number of KPI data in the test data.
5. The method of claim 1, wherein prior to obtaining the test data, the method further comprises:
constructing a self-coding neural network model;
and training the self-coding neural network model according to the plurality of groups of training data to obtain a reconstruction model.
6. The method of claim 5, wherein constructing the self-encoding neural network model comprises:
constructing a self-coding neural network model comprising an input layer, an output layer and ten hidden layers, wherein the ten hidden layers comprise five encoder layers and five decoder layers, and the five encoder layers are used for compressing and reducing dimensions of training data to obtain characteristic data; the five decoder layers are used for restoring and reconstructing the characteristic data to obtain reconstructed training data.
7. The method of claim 5, wherein training the self-encoding neural network model based on the plurality of sets of training data results in a reconstructed model, comprising:
obtaining the weight of the self-coding neural network model according to the plurality of groups of training data;
calculating a loss function value according to the weight;
repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum;
and obtaining a reconstruction model according to the weight with the minimum loss function value.
8. An abnormality diagnosis device for HSS subscriber relocation, the device comprising:
the acquisition module is used for acquiring KPI data of a source HSS and KPI data of a target HSS in the moving process of the HSS user;
the merging module is used for merging the KPI data of the source HSS and the KPI data of the target HSS to obtain test data;
the input module is used for inputting the test data into a reconstruction model to obtain reconstruction test data, the reconstruction model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a source HSS and KPI data of a target HSS in a normal state of the HSS user relocation process;
the calculation module is used for calculating the reconstruction error between the reconstruction test data and the test data;
the determining module is used for determining that the moving process of the HSS user is abnormal when the reconstruction error is larger than a preset threshold value; wherein, the PRC curve is utilized to determine the optimal value of the preset threshold.
9. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform operations corresponding to an abnormality diagnosis method for HSS subscriber relocation according to any one of claims 1 to 7.
10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to an abnormality diagnosis method for HSS user relocation according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609185.9A CN112203272B (en) | 2019-07-08 | 2019-07-08 | Abnormality diagnosis method, device and computing equipment for moving HSS (home subscriber server) user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609185.9A CN112203272B (en) | 2019-07-08 | 2019-07-08 | Abnormality diagnosis method, device and computing equipment for moving HSS (home subscriber server) user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112203272A CN112203272A (en) | 2021-01-08 |
| CN112203272B true CN112203272B (en) | 2023-09-08 |
Family
ID=74004449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910609185.9A Active CN112203272B (en) | 2019-07-08 | 2019-07-08 | Abnormality diagnosis method, device and computing equipment for moving HSS (home subscriber server) user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112203272B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106817415A (en) * | 2017-01-16 | 2017-06-09 | 吉林吉大通信设计院股份有限公司 | A kind of synchronous migration method that HLR/HSS user data is derived and imported online |
| CN108287782A (en) * | 2017-06-05 | 2018-07-17 | 中兴通讯股份有限公司 | A kind of multidimensional data method for detecting abnormality and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7996541B2 (en) * | 2007-06-15 | 2011-08-09 | Tekelec | Methods, systems, and computer program products for identifying a serving home subscriber server (HSS) in a communications network |
-
2019
- 2019-07-08 CN CN201910609185.9A patent/CN112203272B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106817415A (en) * | 2017-01-16 | 2017-06-09 | 吉林吉大通信设计院股份有限公司 | A kind of synchronous migration method that HLR/HSS user data is derived and imported online |
| CN108287782A (en) * | 2017-06-05 | 2018-07-17 | 中兴通讯股份有限公司 | A kind of multidimensional data method for detecting abnormality and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112203272A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378487B (en) | Method, device, equipment and medium for verifying model parameters in horizontal federal learning | |
| CN110874744B (en) | Data anomaly detection method and device | |
| CN111277469B (en) | Network diagnosis processing method and device, network system and server | |
| CN110704231A (en) | Fault processing method and device | |
| CN106656536A (en) | Method and device for processing service invocation information | |
| CN111460312A (en) | Method and device for identifying empty-shell enterprise and computer equipment | |
| CN108269087A (en) | The processing method and processing device of location information | |
| CN111192130B (en) | Method, system, device and storage medium for determining fault source in transaction monitoring | |
| CN110149223B (en) | Fault positioning method and equipment | |
| CN110263628B (en) | Obstacle detection method, obstacle detection device, electronic apparatus, and storage medium | |
| CN111679968A (en) | Interface calling abnormity detection method and device, computer equipment and storage medium | |
| CN111538951A (en) | Abnormity positioning method and device | |
| CN113379238A (en) | Risk assessment method and device and electronic equipment | |
| CN117151726A (en) | Fault repairing method, repairing device, electronic equipment and storage medium | |
| CN114185900B (en) | Service data processing method, device, computer equipment and storage medium | |
| CN112203272B (en) | Abnormality diagnosis method, device and computing equipment for moving HSS (home subscriber server) user | |
| CN107067354A (en) | Based on the task of supervision treating method and apparatus for controlling grid altogether | |
| CN114297735A (en) | Data processing method and related device | |
| CN111258968B (en) | Enterprise redundant data cleaning method and device and big data platform | |
| CN115934484B (en) | Diffusion model data enhancement-based anomaly detection method, storage medium and apparatus | |
| US20230325956A1 (en) | Method, device and system for calculating danger degree of event scene | |
| CN114416814B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN112202625B (en) | Network element abnormality diagnosis method, device, computing equipment and computer storage medium | |
| CN209055959U (en) | Customs inspection system | |
| CN115408182A (en) | Service system fault positioning method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |