Service node performance prediction method, device, equipment, readable medium and product

Abstract

The embodiment of the invention discloses a service node performance prediction method and device, equipment, a readable medium and a product. According to one specific embodiment, the method comprises the steps that historical performance data sequences corresponding to service nodes in a service node set within a preset time period are obtained, the historical performance data sequences are obtained, the service node set corresponds to calling link information, and historical performance data in the historical performance data sequences correspond to historical moments; generating a spatial incidence matrix corresponding to the service node set according to the calling link information; generating spatial feature vector information of the service node set corresponding to each historical moment according to each acquired historical performance data sequence and the spatial incidence matrix; and according to the spatial feature vector information, generating a time feature vector of the service node set corresponding to the target moment as prediction performance data. The embodiment is related to service performance monitoring, the service delay time can be shortened, and the accuracy of predicting the operation condition of each service is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a service node performance prediction method, apparatus, device, readable medium, and product. Background Art

[0002] The application system may have various services, and the operation of the system may be monitored by the performance indicators of the various services. At present, when monitoring the performance indicators of services, the commonly used method is: observing the performance indicators of a service by manual inspection to monitor the operation of the service.

[0003] However, when the above method is adopted, the following technical problems often occur: when an abnormality is detected in the operation of a service, an online problem has already occurred in the service and the service needs to be taken offline for maintenance, resulting in a long service delay; the operation of the service cannot be predicted based on the performance indicators of other related services, resulting in an inability to accurately predict the operation of each service.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose a service node performance prediction method, apparatus, electronic device, computer-readable medium, and computer program product to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a service node performance prediction method, the method comprising: obtaining a historical performance data sequence corresponding to each service node in a service node set within a preset time period, and obtaining each historical performance data sequence, wherein the above-mentioned service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to historical moments; generating a spatial association matrix corresponding to the above-mentioned service node set based on the above-mentioned call link information; generating spatial feature vector information corresponding to each historical moment of the above-mentioned service node set based on the obtained historical performance data sequences and the above-mentioned spatial association matrix; generating a time feature vector corresponding to the target moment of the above-mentioned service node set as predicted performance data based on the above-mentioned spatial feature vector information.

[0008] Optionally, after obtaining the historical performance data sequence corresponding to each service node in the service node set within the preset time period, the method further includes: for each historical performance data sequence obtained, in response to determining that there is missing data in the historical performance data sequence, performing data filling processing on the historical performance data sequence.

[0009] Optionally, after obtaining the historical performance data sequence corresponding to each service node in the service node set within the preset time period, the method further includes: performing data smoothing processing on each historical performance data sequence obtained.

[0010] Optionally, generating a spatial association matrix corresponding to the service node set according to the call link information includes: for each service node in the service node set, performing the following steps: determining the service node as a target service node; determining whether the target service node is associated with each service node in the service node set according to the call link information; for each service node in the service node set, in response to determining that the target service node is associated with the service node, determining an association identifier as a matrix element, or in response to determining that the target service node is not associated with the service node, determining a non-association identifier as a matrix element; combining the obtained matrix elements into a column vector corresponding to the target service node; and determining the combined column vectors as a spatial association matrix corresponding to the service node set.

[0011] Optionally, the above-mentioned generation of spatial feature vector information corresponding to each historical moment of the above-mentioned service node set based on each acquired historical performance data sequence and the above-mentioned spatial association matrix includes: for each of the above-mentioned historical moments, performing the following steps: combining each historical performance data corresponding to the above-mentioned historical moment in the above-mentioned historical performance data sequence as input data; inputting the above-mentioned input data and the above-mentioned spatial association matrix into the spatial feature extraction layer included in the pre-trained service node performance prediction model to obtain the spatial feature vector of the above-mentioned service node set corresponding to the above-mentioned historical moment; and determining each obtained spatial feature vector as spatial feature vector information.

[0012] Optionally, the above-mentioned service node performance prediction model also includes a time feature extraction layer; and the above-mentioned generation of the time feature vector corresponding to the target moment of the above-mentioned service node set as the predicted performance data based on the above-mentioned spatial feature vector information includes: determining the preset time feature vector as the associated time feature vector; determining the first historical moment among the above-mentioned historical moments as the target historical moment; based on the target historical moment and the associated time feature vector, executing the following loop steps: inputting the associated time feature vector and the spatial feature vector corresponding to the target historical moment in the above-mentioned spatial feature vector information into the above-mentioned time feature extraction layer to obtain an initial time feature vector; in response to determining that the target historical moment is the last historical moment among the above-mentioned historical moments, determining the initial time feature vector as the time feature vector corresponding to the target moment of the above-mentioned service node set.

[0013] Optionally, the above-mentioned loop step also includes: in response to determining that the target historical moment is not the last historical moment among the above-mentioned historical moments, determining the initial time feature vector as the associated time feature vector to update the associated time feature vector, and determining the next historical moment of the target historical moment among the above-mentioned historical moments as the target historical moment to update the target historical moment; based on the updated target historical moment and the updated associated time feature vector, executing the above-mentioned loop step again.

[0014] Optionally, the method further includes: in response to determining that the above-mentioned predicted performance data meets preset warning conditions, generating warning prompt information based on the above-mentioned predicted performance data; and sending the above-mentioned warning prompt information to an associated terminal device.

[0015] In a second aspect, some embodiments of the present disclosure provide a service node performance prediction device, the device comprising: an acquisition unit, configured to acquire a historical performance data sequence corresponding to each service node in a service node set within a preset time period, and obtain each historical performance data sequence, wherein the above-mentioned service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to a historical moment; a first generation unit, configured to generate a spatial association matrix corresponding to the above-mentioned service node set according to the above-mentioned call link information; a second generation unit, configured to generate spatial feature vector information corresponding to each historical moment of the above-mentioned service node set according to the acquired historical performance data sequences and the above-mentioned spatial association matrix; a third generation unit, configured to generate a time feature vector corresponding to the target moment of the above-mentioned service node set as predicted performance data according to the above-mentioned spatial feature vector information.

[0016] Optionally, after the acquisition unit, the service node performance prediction device further includes: a filling unit configured to perform data filling processing on each acquired historical performance data sequence in response to determining that there is missing data in the historical performance data sequence.

[0017] Optionally, after the acquisition unit, the service node performance prediction device further includes: a smoothing unit configured to perform data smoothing processing on each acquired historical performance data sequence.

[0018] Optionally, the first generation unit is further configured to: for each service node in the above-mentioned service node set, perform the following steps: determine the above-mentioned service node as a target service node; determine whether the above-mentioned target service node is associated with each service node in the above-mentioned service node set according to the above-mentioned call link information; for each service node in the above-mentioned service node set, in response to determining that the above-mentioned target service node is associated with the above-mentioned service node, determine an association identifier as a matrix element, or in response to determining that the above-mentioned target service node is not associated with the above-mentioned service node, determine a non-association identifier as a matrix element; combine the obtained matrix elements into a column vector corresponding to the above-mentioned target service node; and determine the combined column vectors as a spatial association matrix corresponding to the above-mentioned service node set.

[0019] Optionally, the generation unit is further configured to: for each of the above-mentioned historical moments, perform the following steps: combine the various historical performance data corresponding to the above-mentioned historical moments in the above-mentioned historical performance data sequences as input data; input the above-mentioned input data and the above-mentioned spatial association matrix into the spatial feature extraction layer included in the pre-trained service node performance prediction model to obtain the spatial feature vector of the above-mentioned service node set corresponding to the above-mentioned historical moment; and determine the obtained various spatial feature vectors as spatial feature vector information.

[0020] Optionally, the above service node performance prediction model also includes a time feature extraction layer.

[0021] Optionally, the third generation unit is further configured to: determine a preset time feature vector as an associated time feature vector; determine the first historical moment among the above-mentioned historical moments as the target historical moment; based on the target historical moment and the associated time feature vector, perform the following loop steps: input the associated time feature vector and the spatial feature vector corresponding to the target historical moment in the above-mentioned spatial feature vector information into the above-mentioned time feature extraction layer to obtain an initial time feature vector; in response to determining that the target historical moment is the last historical moment among the above-mentioned historical moments, determine the initial time feature vector as the time feature vector corresponding to the target moment of the above-mentioned service node set.

[0022] Optionally, the above-mentioned loop step also includes: in response to determining that the target historical moment is not the last historical moment among the above-mentioned historical moments, determining the initial time feature vector as the associated time feature vector to update the associated time feature vector, and determining the next historical moment of the target historical moment among the above-mentioned historical moments as the target historical moment to update the target historical moment; based on the updated target historical moment and the updated associated time feature vector, executing the above-mentioned loop step again.

[0023] Optionally, the service node performance prediction device further includes: a warning prompt information generation unit and a sending unit. The warning prompt information generation unit is configured to generate warning prompt information according to the predicted performance data in response to determining that the predicted performance data meets a preset warning condition. The sending unit is configured to send the warning prompt information to an associated terminal device.

[0024] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0025] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.

[0026] In a fifth aspect, some embodiments of the present disclosure provide a computer program product, including a computer program, which implements the method described in any implementation manner of the above-mentioned first aspect when executed by a processor.

[0027] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the service node performance prediction method of some embodiments of the present disclosure, the service delay time can be shortened and the accuracy of predicting the operation of each service can be improved. Specifically, the reason for the long service delay time and the inability to accurately predict the operation of each service is that when the operation of the service is monitored to be abnormal, the online problem of the service has occurred and the service needs to be offline for maintenance, resulting in a long service delay time; the operation of the service cannot be predicted based on the performance indicators of other related services, resulting in the inability to accurately predict the operation of each service. Based on this, the service node performance prediction method of some embodiments of the present disclosure, first, obtains the historical performance data sequence corresponding to each service node in the service node set within a preset time period, and obtains each historical performance data sequence, wherein the above-mentioned service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to historical moments. Thus, the historical performance data sequence of each service node with a call relationship can be obtained. Then, according to the above-mentioned call link information, a spatial association matrix corresponding to the above-mentioned service node set is generated. Thus, the call relationship between each service node can be quantitatively represented in the form of a matrix. Next, based on the acquired historical performance data sequences and the above-mentioned spatial association matrix, the spatial feature vector information corresponding to each historical moment of the above-mentioned service node set is generated. In this way, the association characteristics of the historical performance data of each service node in the call space can be captured. Finally, based on the above-mentioned spatial feature vector information, the time feature vector corresponding to the target moment of the above-mentioned service node set is generated as the predicted performance data. In this way, the time correlation feature can be further captured on the basis of the spatial correlation feature to predict the performance data at future moments. Also, because the spatiotemporal correlation of the time series information is captured, the accuracy of the predicted performance index is improved. Also, because the performance data of each service node in the future can be predicted in advance, it is conducive to judging the problems of each service node in advance, and thus the service delay duration can be shortened. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0029] Figure 1 is an architectural diagram of an exemplary system in which some embodiments of the present disclosure may be applied;

[0030] Figure 2 is a flow chart of some embodiments of the service node performance prediction method according to the present disclosure;

[0031] Figure 3 is a schematic diagram of a service node call link of a service node performance prediction method according to some embodiments of the present disclosure;

[0032] Figure 4 is a flow chart of other embodiments of the service node performance prediction method according to the present disclosure;

[0033] Figure 5 is a schematic diagram of the structure of some embodiments of the service node performance prediction device according to the present disclosure;

[0034] Figure 6 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0035] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0036] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0037] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0038] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0039] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0040] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0041] Figure 1 An exemplary system architecture 100 is shown to which a service node performance prediction method or a service node performance prediction apparatus according to some embodiments of the present disclosure may be applied.

[0042] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0043] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0044] Terminal devices 101, 102, 103 can be hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens and supporting information display, including but not limited to smart phones, tablet computers, e-book readers, laptop portable computers, desktop computers, etc. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules for providing distributed services, for example, or they can be implemented as a single software or software module. No specific limitation is made here.

[0045] The server 105 may be a server that provides various services, such as a background server that provides support for information displayed on the terminal devices 101, 102, and 103. The background server may analyze and process the received request and other data, and feed back the processing results to the terminal device.

[0046] It should be noted that the service node performance prediction method provided in the embodiments of the present disclosure may be executed by the server 105. Accordingly, the service node performance prediction device may be disposed in the server 105.

[0047] It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules for providing distributed services, or it can be implemented as a single software or software module. No specific limitation is made here.

[0048] Continue to refer Figure 2 , shows a process 200 of some embodiments of the service node performance prediction method according to the present disclosure. The service node performance prediction method comprises the following steps:

[0049] Step 201: Obtain a historical performance data sequence corresponding to each service node in a service node set within a preset time period to obtain each historical performance data sequence.

[0050] In some embodiments, the execution subject of the service node performance prediction method (for example Figure 1 The server shown in the figure) can obtain the historical performance data sequence corresponding to each service node in the service node set within the preset time period from the database. Among them, the above-mentioned preset time period can be a preset historical time period. For example, the preset time period can be a time period corresponding to the past month. The above-mentioned service node set can represent various services provided by the system. The service node can be a pre-packaged interface. The above-mentioned database can store the performance data of the service nodes of the system. The performance data can include but is not limited to the query rate per second. The performance data can have a time granularity. For example, the time granularity of the query rate per second can be one minute, that is, the query rate per second can be the QPS size of the interface per minute. The historical performance data sequence can be each performance data of the service node within the preset time period. Each historical performance data sequence can correspond to a service node. Each historical performance data in the historical performance data sequence can be arranged in ascending order of time. The historical performance data in the historical performance data sequence can correspond to a historical moment, that is, the collection moment of the historical performance data. The above-mentioned service node set can correspond to call link information. The call link information can represent the call relationship between the service nodes in the above-mentioned service node set. For example, the call link information can include each group of call relationship information. The call relationship information can include the first service node and the second service node. The first service node may be a service node that performs the call. The second service node may be a service node that is called. For example, the call link information may include: first service node B, second service node A; first service node A, second service node C; first service node C, second service node D. For another example, two service nodes may call each other. As an example, the call relationship between service nodes A, B, C, and D can refer to Figure 3 . Figure 3 In the example, service nodes B and A have a calling relationship. Service nodes A and C have a calling relationship. Service nodes C and D have a calling relationship.

[0051] Optionally, for each historical performance data sequence obtained, the execution entity may perform data filling processing on the historical performance data sequence in response to determining that there is missing data in the historical performance data sequence. In practice, for each missing data in the historical performance data sequence, the execution entity may select a preset number of historical performance data before the missing data from the historical performance data sequence, and select a preset number of historical performance data after the missing data from the historical performance data sequence. Then, the mean of each selected historical performance data may be determined as the filling data corresponding to the missing data. Then, the missing data may be filled with the filling data. In this way, the missing data may be filled to ensure the integrity of the data.

[0052] Optionally, for each historical performance data sequence obtained, the execution subject may perform data smoothing on the historical performance data sequence. In practice, the execution subject may use a smoothing algorithm to perform data smoothing on the historical performance data sequence. The smoothing algorithm may include, but is not limited to, an autoregressive model, exponential smoothing, and a low-pass filter. Thus, the accuracy of the predicted performance data may be improved.

[0053] Step 202: Generate a spatial association matrix of a corresponding service node set according to the call link information.

[0054] In some embodiments, the execution subject may generate a spatial association matrix corresponding to the service node set according to the call link information. The spatial association matrix may be a matrix for characterizing the call relationship between different service nodes. In practice, the execution subject may construct an empty matrix whose number of rows and columns is the number of service nodes included in the service node set. Each row of the empty matrix corresponds to each service node in the service node set. Each column of the empty matrix corresponds to each service node in the service node set. For each element in the empty matrix, in response to determining that a call relationship exists between two service nodes corresponding to the row and column where the element is located, the element may be updated to a first identifier, and in response to determining that a call relationship does not exist between two service nodes corresponding to the row and column where the element is located, the element may be updated to a second identifier. The first identifier may represent the existence of a call relationship. The second identifier may represent the absence of a call relationship.

[0055] For example, the first identifier may be 1. The second identifier may be 0. For example, in the example of the embodiment corresponding to step 201, there is a call relationship between service nodes A and B, and the identifier of the corresponding element may be 1. There is no call relationship between service nodes A and D, and the identifier of the corresponding element may be 0. The spatial association matrix corresponding to service nodes A, B, C, and D may be

[0056] In some optional implementations of some embodiments, the execution subject may generate a spatial association matrix corresponding to the service node set according to the call link information through the following steps:

[0057] In the first step, for each service node in the above service node set, perform the following steps:

[0058] The first sub-step is to determine the above service node as the target service node.

[0059] The second sub-step is to determine whether the target service node is associated with each service node in the service node set according to the call link information. There is a direct call relationship between the two associated service nodes, and there is no direct call relationship between the two unassociated service nodes.

[0060] In a third sub-step, for each service node in the service node set, in response to determining that the target service node is associated with the service node, an association identifier is determined as a matrix element, or in response to determining that the target service node is not associated with the service node, a non-association identifier is determined as a matrix element. The association identifier may represent the existence of an association relationship. The non-association identifier may represent the absence of an association relationship. For example, the association identifier may be 1. The non-association identifier may be 0.

[0061] The fourth sub-step is to combine the obtained matrix elements into a column vector corresponding to the target service node. For example, when the target service node is service node A, the corresponding column vector can be

[0062] The second step is to determine the combined column vectors as the spatial association matrix corresponding to the above service node set. For example, the spatial association matrix composed of the column vectors can be Therefore, the task of constructing the spatial correlation matrix can be refined to the column dimension.

[0063] Step 203: Generate spatial feature vector information of the service node set corresponding to each historical moment according to each acquired historical performance data sequence and the spatial association matrix.

[0064] In some embodiments, the above-mentioned execution subject may generate the spatial feature vector information of the above-mentioned service node set corresponding to each historical moment based on the acquired historical performance data sequences and the above-mentioned spatial association matrix. Among them, the spatial feature vector information may include each spatial feature vector. The spatial feature vector may be a vector representing the spatial correlation of each service node in the service node set corresponding to the same historical moment. In practice, for each historical moment in each historical moment, the above-mentioned execution subject may combine each historical performance data corresponding to each historical moment in each historical performance data sequence as input data. Then, the above-mentioned execution subject may input the input data and the spatial association matrix into a pre-trained graph convolutional neural network to obtain the spatial feature vector of the service node set corresponding to the above-mentioned historical moment. Finally, the obtained spatial feature vectors may be combined into spatial feature vector information.

[0065] Step 204: Generate a time feature vector of the service node set corresponding to the target time as predicted performance data based on the spatial feature vector information.

[0066] In some embodiments, the above-mentioned execution subject can generate the time feature vector of the above-mentioned service node set corresponding to the target moment as the predicted performance data based on the above-mentioned spatial feature vector information. Among them, the time feature vector can be a vector composed of the performance data of each service node in the predicted service node set at the target moment. The target moment can be a future moment. For example, the target moment can be the next moment of the current moment. In practice, the above-mentioned execution subject can input the spatial feature vector information into a pre-trained performance data prediction model to obtain the time feature vector corresponding to the target moment as the predicted performance data. The performance data prediction model can be a neural network model that takes the spatial feature vector information as input and the time feature vector of the target moment as output. For example, the performance data prediction model can be an LSTM.

[0067] Optionally, the execution subject may generate warning prompt information according to the predicted performance data in response to determining that the predicted performance data meets the preset warning condition. The warning condition may be that there is performance data greater than the corresponding performance warning threshold value in each performance data included in the predicted performance data. Each service node may correspond to a performance warning threshold. Each performance data included in the predicted performance data corresponds to a service node. In practice, for each performance data greater than the corresponding performance warning threshold value, the execution subject may determine the difference between the performance data and the corresponding performance warning threshold value as a performance overload value, and then the performance overload value, the performance data, the node name of the service node corresponding to the performance data and the warning mark may be combined into a warning prompt information. The warning mark may characterize a performance warning event. For example, the warning mark may be "performance warning". Then, the warning prompt information may be sent to an associated terminal device. For example, the terminal device may be a terminal device used by a service node manager. Thus, the service node may be notified in a timely manner in the form of a warning prompt information that the future operating state may be overloaded, so that the service node manager can execute a response strategy.

[0068] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the service node performance prediction method of some embodiments of the present disclosure, the service delay time can be shortened and the accuracy of predicting the operation of each service can be improved. Specifically, the reason for the long service delay time and the inability to accurately predict the operation of each service is that when the operation of the service is monitored to be abnormal, the online problem of the service has occurred and the service needs to be offline for maintenance, resulting in a long service delay time; the operation of the service cannot be predicted based on the performance indicators of other related services, resulting in the inability to accurately predict the operation of each service. Based on this, the service node performance prediction method of some embodiments of the present disclosure, first, obtains the historical performance data sequence corresponding to each service node in the service node set within a preset time period, and obtains each historical performance data sequence, wherein the above-mentioned service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to historical moments. Thus, the historical performance data sequence of each service node with a call relationship can be obtained. Then, according to the above-mentioned call link information, a spatial association matrix corresponding to the above-mentioned service node set is generated. Thus, the call relationship between each service node can be quantitatively represented in the form of a matrix. Next, based on the acquired historical performance data sequences and the above-mentioned spatial association matrix, the spatial feature vector information corresponding to each historical moment of the above-mentioned service node set is generated. In this way, the association characteristics of the historical performance data of each service node in the call space can be captured. Finally, based on the above-mentioned spatial feature vector information, the time feature vector corresponding to the target moment of the above-mentioned service node set is generated as the predicted performance data. In this way, the time correlation feature can be further captured on the basis of the spatial correlation feature to predict the performance data at future moments. Also, because the spatiotemporal correlation of the time series information is captured, the accuracy of the predicted performance index is improved. Also, because the performance data of each service node in the future can be predicted in advance, it is conducive to judging the problems of each service node in advance, and thus the service delay duration can be shortened.

[0069] Further references Figure 4 , which shows a process 400 of another embodiment of a service node performance prediction method. The process 400 of the service node performance prediction method includes the following steps:

[0070] Step 401, obtaining a historical performance data sequence corresponding to each service node in a service node set within a preset time period, and obtaining each historical performance data sequence.

[0071] Step 402: Generate a spatial association matrix of a corresponding service node set according to the call link information.

[0072] In some embodiments, the specific implementation of steps 401-402 and the technical effects brought about can be referred to Figure 2 The corresponding steps 201-202 in the embodiments are not described in detail here.

[0073] Step 403: for each historical moment in each historical moment, perform the following steps:

[0074] Step 4031, combining each historical performance data corresponding to the historical moment in each historical performance data sequence into input data.

[0075] In some embodiments, the execution subject of the service node performance prediction method (for example Figure 1 The server shown in the figure can combine the historical performance data corresponding to the above historical moments in the above historical performance data sequences as input data. Thus, the performance data can be sorted according to the time dimension of the same historical moment.

[0076] Step 4032, input the input data and the spatial association matrix into the spatial feature extraction layer included in the pre-trained service node performance prediction model to obtain the spatial feature vector of the service node set corresponding to the historical moment.

[0077] In some embodiments, the execution subject may input the input data and the spatial association matrix into the spatial feature extraction layer included in the pre-trained service node performance prediction model to obtain the spatial feature vector of the service node set corresponding to the historical moment. The service node performance prediction model may be a neural network model that takes the historical performance data of each service node at each historical moment and the spatial association matrix as input and the predicted performance data at the target moment as output. The service node performance prediction model may include a spatial feature extraction layer and a temporal feature extraction layer. The spatial feature extraction layer may include a diffusion convolutional network. The temporal feature extraction layer may include a gated recurrent unit. The diffusion convolutional network may be used to capture the spatial correlation of the performance data of each service node at the call relationship level. The gated recurrent unit may be used to further capture the temporal correlation of the performance data of each service node. The input of the gated recurrent unit may include the output of the diffusion convolutional network at the current moment and the output of the gated recurrent unit at the previous moment.

[0078] The diffusion convolution network uses the diffusion convolution in the image signal and filters

[0079]

[0080] f θ The definition of d can be: W = ReLU (EE T )+α||W′||. θ1 and θ2 can be filter parameters. * can be the graph convolution symbol. D I The adjacency matrix W can be TThe in-degree matrix of D O It can be the out-degree matrix of the adjacency matrix W. O -1 W and can be a diffusion migration matrix. E can be a randomly initialized node embedding, N can be the number of service nodes included in the service node set. d and P can be the feature dimension size of the service node embedding expression. When the performance data only includes QPS, it can be 1. W′ can be the spatial correlation matrix. α can be the coefficient. X ：，p It can be the historical performance data of each service node corresponding to the same historical moment, that is, input data. ：，p*g f θ It can represent the result of diffusion convolution, that is, the spatial feature vector of a service node set corresponding to a historical moment. In the above formula, "local prior knowledge" is added to the learned matrix to avoid overfitting. W' is a prior adjacency matrix constructed according to the call relationship. Similar to the regularization technology, it can be intuitively understood that it severely punishes weight vectors with high values ​​and prefers more dispersed weight vectors.

[0081] The gated recurrent unit can be controlled by X (t) and H t-1 To obtain the two gate states. (t) It can be the input feature of the gated recurrent unit at the current moment, that is, the output X of the diffusion convolutional network ：，p*g f θ .H t-1 It can be the hidden state passed down by the gated recurrent unit at the previous moment. The forget gate and memory gate of the gated recurrent unit can be expressed as:

[0082] r t =σ(W([X (t) ,H t-1 ])+b r )

[0083] u t =σ(W([X (t) ,H t-1 ])+b u )W in this formula is the parameter weight matrix. After the gating signal is determined by the parameter weight matrix, H can be obtained. (t-1)′ =r t ⊙H t-1 , and compare this value with X (t) splicing, and then normalized to the range of -1 to 1 to get C t =tanh(W[X (t) , H (t-1)′ ]+b C ). tThe current hidden state is input at the current moment. This step is to save the state information of the previous moment. Finally, update and save the important information first, filter out the information with weak relevance, and get the final output Y t+T Among them, Y t+T =u t ⊙H t-1 +(1-u t )⊙C t For example, Y t+T The output format can be It represents the performance data of the four service nodes at the future time T (for example, T=1 minute) predicted based on the data at the previous time t.

[0084] Step 404: determine each obtained spatial feature vector as spatial feature vector information.

[0085] In some embodiments, the execution entity may determine the obtained spatial feature vectors as spatial feature vector information.

[0086] Step 405: determine the preset time feature vector as the associated time feature vector.

[0087] In some embodiments, the execution subject may determine a preset time feature vector as the associated time feature vector. The preset time feature vector may be an empty vector. The dimension of the preset time feature vector may be the number of each service node included in the service node set.

[0088] Step 406: determine the first historical moment among the historical moments as the target historical moment.

[0089] In some embodiments, the execution subject may determine the first historical moment among the historical moments as the target historical moment. The first historical moment among the historical moments may be the earliest historical moment.

[0090] Step 407, based on the target historical moment and the associated time feature vector, execute the following loop steps:

[0091] Step 4071, input the spatial feature vector corresponding to the target historical moment in the associated time feature vector and spatial feature vector information into the time feature extraction layer to obtain an initial time feature vector.

[0092] In some embodiments, the execution subject may input the associated time feature vector and the spatial feature vector corresponding to the target historical moment in the spatial feature vector information into the time feature extraction layer to obtain an initial time feature vector. When the loop step is executed for the first time, the associated time feature vector may be the preset time feature vector. When the loop step is executed later, the associated time feature vector may be the initial time feature vector obtained by the last execution of the loop step. The initial time feature vector may be the performance data of each service node at the current moment predicted by the time feature extraction layer.

[0093] Step 4072, in response to determining that the target historical moment is the last historical moment among the historical moments, determining the initial time feature vector as the time feature vector of the service node set corresponding to the target moment.

[0094] In some embodiments, the execution subject may determine the initial time feature vector as the time feature vector of the target time corresponding to the service node set in response to determining that the target historical moment is the last historical moment among the historical moments. Thus, after traversing the input data, the time feature vector corresponding to the target time may be output.

[0095] Step 4073, in response to determining that the target historical moment is not the last historical moment among the historical moments, determines the initial time feature vector as the associated time feature vector to update the associated time feature vector, and determines the next historical moment of the target historical moment among the historical moments as the target historical moment to update the target historical moment.

[0096] In some embodiments, the execution subject may determine the initial time feature vector as the associated time feature vector in response to determining that the target historical moment is not the last historical moment among the above historical moments, so as to update the associated time feature vector, and determine the next historical moment of the target historical moment among the above historical moments as the target historical moment, so as to update the target historical moment. Thus, when the input data is not traversed completely, the initial time feature vector obtained at the current moment may be used as the hidden state vector, and the time dimension of the input data required at the next moment may be determined.

[0097] Step 4074, based on the updated target historical moment and the updated associated time feature vector, execute the loop step again.

[0098] In some embodiments, the execution subject may execute the loop step again based on the updated target historical moment and the updated associated time feature vector. Thus, the initial time feature vector obtained at the current moment may be input as a hidden state vector into the next gated loop unit, and the loop step may be executed according to the time dimension of the input data required at the next moment.

[0099] from Figure 4 It can be seen that Figure 2 Compared with the description of some corresponding embodiments, Figure 4 The process 400 of the service node performance prediction method in some corresponding embodiments embodies the steps of expanding the generation of spatial feature information and temporal feature vectors. Therefore, the schemes described in these embodiments can use the spatiotemporal network to capture the spatiotemporal correlation of time series information, further improving the accuracy of predicting performance indicators.

[0100] Further references Figure 5 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a service node performance prediction device. These device embodiments are similar to Figure 2 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0101] like Figure 5 As shown, the service node performance prediction device 500 of some embodiments includes: an acquisition unit 501, a first generation unit 502, a second generation unit 503 and a third generation unit 504. The acquisition unit 501 is configured to acquire the historical performance data sequence corresponding to each service node in the service node set within a preset time period to obtain each historical performance data sequence, wherein the service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to a historical moment; the first generation unit 502 is configured to generate a spatial association matrix corresponding to the service node set according to the call link information; the second generation unit 503 is configured to generate the spatial feature vector information corresponding to each historical moment of the service node set according to the acquired historical performance data sequences and the spatial association matrix; the third generation unit 504 is configured to generate the time feature vector corresponding to the target moment of the service node set as the predicted performance data according to the spatial feature vector information.

[0102] Optionally, after the acquisition unit 501, the service node performance prediction device 500 may further include: a filling unit (not shown in the figure), which is configured to perform data filling processing on the above historical performance data sequence for each historical performance data sequence acquired in response to determining that there is missing data in the above historical performance data sequence.

[0103] Optionally, after the acquisition unit 501, the service node performance prediction device 500 may further include: a smoothing unit (not shown in the figure), configured to perform data smoothing processing on each acquired historical performance data sequence.

[0104] Optionally, the first generation unit 502 can be further configured to: for each service node in the above-mentioned service node set, perform the following steps: determine the above-mentioned service node as a target service node; determine whether the above-mentioned target service node is associated with each service node in the above-mentioned service node set according to the above-mentioned call link information; for each service node in the above-mentioned service node set, in response to determining that the above-mentioned target service node is associated with the above-mentioned service node, determine the association identifier as a matrix element, or in response to determining that the above-mentioned target service node is not associated with the above-mentioned service node, determine the non-association identifier as a matrix element; combine the obtained matrix elements into a column vector corresponding to the above-mentioned target service node; and determine the combined column vectors as a spatial association matrix corresponding to the above-mentioned service node set.

[0105] Optionally, the generation unit 503 can be further configured to: for each of the above-mentioned historical moments, perform the following steps: combine the various historical performance data corresponding to the above-mentioned historical moments in the above-mentioned historical performance data sequences as input data; input the above-mentioned input data and the above-mentioned spatial association matrix into the spatial feature extraction layer included in the pre-trained service node performance prediction model to obtain the spatial feature vector of the above-mentioned service node set corresponding to the above-mentioned historical moment; and determine the obtained various spatial feature vectors as spatial feature vector information.

[0106] Optionally, the above service node performance prediction model also includes a time feature extraction layer.

[0107] Optionally, the third generation unit 504 can be further configured to: determine a preset time feature vector as an associated time feature vector; determine the first historical moment among the above-mentioned historical moments as the target historical moment; based on the target historical moment and the associated time feature vector, perform the following loop steps: input the associated time feature vector and the spatial feature vector corresponding to the target historical moment in the above-mentioned spatial feature vector information into the above-mentioned time feature extraction layer to obtain an initial time feature vector; in response to determining that the target historical moment is the last historical moment among the above-mentioned historical moments, determine the initial time feature vector as the time feature vector corresponding to the target moment of the above-mentioned service node set.

[0108] Optionally, the above-mentioned loop step also includes: in response to determining that the target historical moment is not the last historical moment among the above-mentioned historical moments, determining the initial time feature vector as the associated time feature vector to update the associated time feature vector, and determining the next historical moment of the target historical moment among the above-mentioned historical moments as the target historical moment to update the target historical moment; based on the updated target historical moment and the updated associated time feature vector, executing the above-mentioned loop step again.

[0109] Optionally, the service node performance prediction device 500 may further include: a warning prompt information generation unit and a sending unit (not shown in the figure). The warning prompt information generation unit is configured to generate warning prompt information according to the predicted performance data in response to determining that the predicted performance data meets the preset warning condition. The sending unit is configured to send the warning prompt information to the associated terminal device.

[0110] It is understood that the units described in the device 500 are similar to those described in the reference Figure 2 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 500 and the units included therein, and will not be described in detail here.

[0111] Reference below Figure 6 , which shows an electronic device 600 (eg, Figure 1 A schematic diagram of the structure of the server in FIG. Figure 6 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0112] like Figure 6 As shown, the electronic device 600 may include a processing device 601 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0113] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 6 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 6 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0114] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0115] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0116] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0117] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the historical performance data sequence corresponding to each service node in the service node set within a preset time period, and obtains each historical performance data sequence, wherein the service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to historical moments; generates a spatial association matrix corresponding to the service node set based on the call link information; generates spatial feature vector information corresponding to each historical moment of the service node set based on the acquired historical performance data sequences and the spatial association matrix; generates a time feature vector corresponding to the target moment of the service node set as predicted performance data based on the spatial feature vector information.

[0118] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0119] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a first generation unit, a second generation unit, and a third generation unit. The names of these units do not constitute limitations on the units themselves in certain circumstances, for example, the acquisition unit may also be described as "a unit for obtaining a historical performance data sequence corresponding to each service node in a service node set within a preset time period, and obtaining each historical performance data sequence".

[0121] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0122] Some embodiments of the present disclosure further provide a computer program product, including a computer program, which implements any of the above-mentioned service node performance prediction methods when executed by a processor.

[0123] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A service node performance prediction method, comprising: Obtaining a historical performance data sequence corresponding to each service node in a service node set within a preset time period, and obtaining each historical performance data sequence, wherein the service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to a historical moment; Generate a spatial association matrix corresponding to the service node set according to the call link information; Generate spatial feature vector information of the service node set corresponding to each historical moment according to each acquired historical performance data sequence and the spatial association matrix; According to the spatial feature vector information, a time feature vector of the service node set corresponding to the target time is generated as predicted performance data.

2. The method according to claim 1, wherein: After obtaining the historical performance data sequence corresponding to each service node in the service node set within the preset time period, the method further includes: For each acquired historical performance data sequence, in response to determining that there is missing data in the historical performance data sequence, data filling processing is performed on the historical performance data sequence.

3. The method according to claim 1, wherein: After obtaining the historical performance data sequence corresponding to each service node in the service node set within the preset time period, the method further includes: For each acquired historical performance data sequence, data smoothing processing is performed on the historical performance data sequence.

4. The method according to claim 1, wherein: The generating, according to the call link information, a spatial association matrix corresponding to the service node set includes: For each service node in the service node set, perform the following steps: Determining the service node as a target service node; Determining, according to the call link information, whether the target service node is associated with each service node in the service node set; For each service node in the set of service nodes, in response to determining that the target service node is associated with the service node, determining an association identifier as a matrix element, or in response to determining that the target service node is not associated with the service node, determining a non-association identifier as a matrix element; Combining the obtained matrix elements into a column vector corresponding to the target service node; The combined column vectors are determined as a spatial association matrix corresponding to the service node set.

5. The method according to claim 1, wherein: The step of generating spatial feature vector information of the service node set corresponding to each historical moment according to each acquired historical performance data sequence and the spatial association matrix includes: For each of the historical moments, perform the following steps: Combining the historical performance data corresponding to the historical moments in the historical performance data sequences into input data; Inputting the input data and the spatial association matrix into a spatial feature extraction layer included in a pre-trained service node performance prediction model to obtain a spatial feature vector of the service node set corresponding to the historical moment; The obtained spatial feature vectors are determined as spatial feature vector information.

6. The method according to claim 5, wherein: The service node performance prediction model also includes a time feature extraction layer; And generating, according to the spatial feature vector information, a time feature vector of the service node set corresponding to a target time as predicted performance data, comprises: Determining a preset time feature vector as a correlation time feature vector; Determine the first historical moment among the historical moments as the target historical moment; Based on the target historical moment and the associated time feature vector, the following loop steps are performed: Inputting the associated time feature vector and the spatial feature vector corresponding to the target historical moment in the spatial feature vector information into the time feature extraction layer to obtain an initial time feature vector; In response to determining that the target historical moment is the last historical moment among the historical moments, the initial time feature vector is determined as the time feature vector of the service node set corresponding to the target moment.

7. The method according to claim 6, wherein: The cycle step also includes: In response to determining that the target historical moment is not the last historical moment among the historical moments, determining the initial time feature vector as the associated time feature vector to update the associated time feature vector, and determining the next historical moment of the target historical moment among the historical moments as the target historical moment to update the target historical moment; Based on the updated target historical moment and the updated associated time feature vector, the loop step is executed again.

8. The method according to claim 1, wherein: The method further comprises: In response to determining that the predicted performance data meets a preset warning condition, generating warning prompt information according to the predicted performance data; The warning prompt information is sent to the associated terminal device.

9. A service node performance prediction device, comprising: An acquisition unit is configured to acquire a historical performance data sequence corresponding to each service node in a service node set within a preset time period, and obtain each historical performance data sequence, wherein the service node set corresponds to call link information, and the historical performance data in the historical performance data sequence corresponds to a historical moment; A first generating unit is configured to generate a spatial association matrix corresponding to the service node set according to the call link information; A second generating unit is configured to generate spatial feature vector information of the service node set corresponding to each historical moment according to each acquired historical performance data sequence and the spatial association matrix; The third generating unit is configured to generate a time feature vector of the service node set corresponding to a target time as predicted performance data according to the spatial feature vector information.

10. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images