Data classification method and device, equipment, medium and product

Abstract

The invention provides a data classification method and device, equipment, a medium and a product, and relates to the technical field of data processing, and the method comprises the steps: converting a data feature vector used for QSVM model training into a quantum state corresponding to the data feature vector through a quantum circuit; calculating a quantum kernel function based on the inner product of the quantum state, and constructing a corresponding dual optimization objective function; and determining parameters of an optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function so as to complete construction of the QSVM model, performing quantum state mapping on the to-be-tested data feature vector by the constructed QSVM model through a quantum processor, and calculating a classification decision boundary by using a quantum kernel function so as to output a corresponding classification result. According to the embodiment of the invention, the nonlinear correlation between the data feature vectors is more accurately captured, the calculation efficiency of the QSVM model is improved based on the quantum kernel function, and the classification reliability and accuracy of the data feature vectors are also improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a data classification method, apparatus, device, medium, and product. Background Art

[0002] With the rapid development of wireless communication technology, modern communication networks are becoming increasingly complex. This is especially true in 5G and future 6G networks, where the number of communication nodes, such as base stations and cells, has increased significantly. The topology and dynamic nature of these nodes present numerous challenges to network operations and maintenance. The stable operation of communication networks is crucial for ensuring mission-critical services. However, frequent cell failures can lead to widespread network service disruptions, a decline in user experience, and even financial losses.

[0003] In related technologies, classic machine learning algorithms are used to classify and process communication network data in cell fault detection scenarios. However, the computational complexity of high-dimensional feature data is high, making it difficult to quickly converge in complex multi-dimensional scenarios. Furthermore, existing root cause fault location methods remain at the static analysis stage, making it difficult to dynamically capture nonlinear correlations between features.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0005] The present disclosure aims to provide a data classification method, apparatus, device, medium and product for overcoming the problems caused by the limitations and defects of the related art at least to a certain extent.

[0006] According to a first aspect of an embodiment of the present disclosure, a data classification method is provided, comprising: converting a data feature vector used for QSVM model training into a quantum state corresponding to the data feature vector through a quantum circuit; calculating a quantum kernel function based on an inner product of the quantum state, and constructing a corresponding dual optimization objective function; determining parameters of an optimal classification hyperplane in the QSVM model based on an optimal solution of the dual optimization objective function to complete construction of the QSVM model; performing quantum state mapping on the data feature vector to be tested using a quantum processor on the constructed QSVM model, and calculating a classification decision boundary using the quantum kernel function to output a corresponding classification result.

[0007] In an exemplary embodiment of the present disclosure, calculating a quantum kernel function based on the inner product of the quantum state and constructing a corresponding dual optimization objective function includes: Calculating a quantum kernel function based on the inner product of the quantum state and constructing an optimization objective function of the QSVM model; The optimization objective function is transformed into a dual optimization objective function represented by a quantum kernel function by introducing Lagrange multipliers.

[0008] In an exemplary embodiment of the present disclosure, the expression of the optimization objective function includes , the N represents the number of the data feature vectors, the Characterizing the regularization term, represents the classification error term, b represents the classification bias, and represents the slack variable corresponding to the i-th data eigenvector, and C represents the regularization parameter.

[0009] In an exemplary embodiment of the present disclosure, the constraint condition corresponding to the optimization objective function is

[0010] Among them, the Characterizes the label of the i-th data feature vector, the Characterize the quantum feature map corresponding to the i-th data feature vector, the quantum feature map By parameterizing quantum circuits implementation, wherein the quantum circuit It consists of a single quantum bit rotation gate and a controlled entanglement gate. Encoded into quantum states .

[0011] In an exemplary embodiment of the present disclosure, the expression of the dual optimization objective function includes , , wherein the Characterize the jth Lagrange multiplier, the Characterize the i-th Lagrange multiplier, the Characterize the label of the jth data feature vector, the Characterization pair and The quantum kernel function is used to calculate the square of the module of the inner product of two quantum states. Characterize the quantum state of the i-th data feature vector, Characterize the quantum state of the j-th data eigenvector.

[0012] In an exemplary embodiment of the present disclosure, the quantum kernel function is implemented by executing a quantum circuit. And measure the ground state probability estimate, the Characterization of the Perform Hermitian conjugation.

[0013] In an exemplary embodiment of the present disclosure, the quantum kernel function is verified by sampling statistics, the sampling statistics including quantum state tomography and / or SWAP test estimation, the quantum kernel function is configured to satisfy the Mercer condition, and the Gram matrix of the quantum kernel function is semi-positive-definite corrected after being measured by quantum hardware.

[0014] In an exemplary embodiment of the present disclosure, a quantum-classical hybrid algorithm is used to solve the dual optimization objective function. The quantum-classical hybrid algorithm runs on a variational quantum eigensolver. The quantum hardware in the variational quantum eigensolver is used to calculate the kernel matrix terms of the dual optimization objective function, and the classical device in the variational quantum eigensolver is used to calculate the gradient and update the Lagrange multiplier until the convergence condition is met.

[0015] In an exemplary embodiment of the present disclosure, the constraints of the dual optimization objective function include .

[0016] In an exemplary embodiment of the present disclosure, determining the parameters of the optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model includes: Determining Lagrange multipliers and support vectors based on an optimal solution of the dual optimization objective function; Calculating the weight vector according to the Lagrange multiplier, the label of the data eigenvector, and the quantum eigenmap corresponding to the data eigenvector; The classification bias is calculated according to the support vector, the label of the data feature vector and the quantum kernel function.

[0017] In an exemplary embodiment of the present disclosure, the expression for calculating the weight vector according to the Lagrange multiplier, the label of the data feature vector and the quantum feature map corresponding to the data feature vector includes: .

[0018] In an exemplary embodiment of the present disclosure, the expression for calculating the classification bias according to the support vector, the label of the data feature vector and the quantum kernel function includes: , wherein the represents the support vector, the k represents the index of the support vector, the S A set of indices representing the support vectors.

[0019] In an exemplary embodiment of the present disclosure, the encoding mode of the quantum circuit is an angle encoding mode or an amplitude encoding mode, and converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit includes: The data feature vector is mapped into a quantum state of the data feature vector by adopting an angle encoding method or an amplitude encoding method.

[0020] In an exemplary embodiment of the present disclosure, the expression for mapping the data feature vector to the rotation angle of the quantum bit using angle encoding includes: , wherein the R represents a revolving door around the coordinate axis of the rectangular coordinate system, the coordinate axis is the x-axis or the y-axis or the z-axis, the d represents the dimension of the data feature vector, the Characterize the quantum state of the data feature vector, the Characterize the tensor product operator, the Characterizes the normalization processing result of the data feature vector.

[0021] In an exemplary embodiment of the present disclosure, it further includes: The constructed QSVM model is verified using a validation data set corresponding to the data feature vector; According to the verification results, the QSVM model is adjusted or the test data set is tested. The result includes at least one of accuracy, precision, recall and F1 score, and the parameter adjustment processing includes at least one of adjusting the feature mapping method, increasing the number of quantum bits, optimizing the parameters in the feature mapping circuit and adding a regularization factor to the quantum kernel function.

[0022] In an exemplary embodiment of the present disclosure, before converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit, the method further includes: Standardizing the collected data features, wherein the standardization is normalization or conversion into a normal distribution; The standardized data features are vectorized to obtain the data feature vectors.

[0023] In an exemplary embodiment of the present disclosure, the expression for normalizing the collected data features includes: , wherein the Characterize the nth column eigenvalue, and stated Respectively represent the maximum and minimum values in the nth column eigenvalues, the Characterizes the nth eigenvalue of the mth sample.

[0024] In an exemplary embodiment of the present disclosure, before converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit, the method further includes: The data feature vectors are divided into a training data set, a validation data set and a test data set according to a preset ratio. The training data set is used to train the QSVM model, the validation data set is used to verify the QSVM model, and the test data set is used to test the QSVM model training.

[0025] In an exemplary embodiment of the present disclosure, it further includes: Inputting the data feature vector to be tested into the decision function of the constructed QSVM model for classification to generate the classification result; In response to determining, according to the classification result, that the category of the data feature vector to be tested is a fault warning category, calculating the contribution corresponding to each fault root cause according to the support vector and the quantum kernel function; The root cause of the fault corresponding to the data feature vector to be tested is determined according to the ranking result of the contribution degree.

[0026] In an exemplary embodiment of the present disclosure, the expression of the decision function includes , Characterize the data feature vector to be tested, the Characterization When the support vector is greater than 0, the sign Representation symbol function.

[0027] In an exemplary embodiment of the present disclosure, the expression for calculating the contribution degree includes: .

[0028] According to a second aspect of an embodiment of the present disclosure, a data classification method for a communication network is provided, comprising: collecting communication indicators in the communication network; The communication indicator is determined as a data feature, and the data feature is calculated using the data classification method described in any of the above technical solutions to determine a data classification result of the communication indicator.

[0029] According to a third aspect of an embodiment of the present disclosure, there is provided a data classification device, comprising: A conversion module, configured to convert the data feature vector used for QSVM model training into a quantum state corresponding to the data feature vector through a quantum circuit; A construction module is configured to calculate a quantum kernel function based on the inner product of the quantum state and construct a corresponding dual optimization objective function; The classification module is configured to determine the parameters of the optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model. The constructed QSVM model uses a quantum processor to perform quantum state mapping on the data feature vector to be tested, and uses a quantum kernel function to calculate the classification decision boundary to output the corresponding classification result.

[0030] According to a fourth aspect of an embodiment of the present disclosure, a data classification device for a communication network is provided, comprising: A collection module, configured to collect communication indicators in the communication network; The calculation module is configured to determine the communication indicator as a data feature, and calculate the data feature using the data classification method described in any of the above technical solutions to determine a data classification result of the communication indicator.

[0031] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute any one of the methods described above based on instructions stored in the memory.

[0032] According to a sixth aspect of the present disclosure, a computer-readable storage medium is provided, on which a program is stored. When the program is executed by a processor, the data classification method or the data classification method for a communication network as described in any one of the above items is implemented.

[0033] According to a seventh aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the data classification method or the communication network data classification method as described in any one of the above.

[0034] In an embodiment of the present disclosure, a data feature vector used for QSVM model training is converted into a quantum state corresponding to the data feature vector through a quantum circuit, a quantum kernel function is calculated based on the inner product of the quantum state, and a corresponding dual optimization objective function is constructed. The parameters of the optimal classification hyperplane in the QSVM model are determined based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model. The constructed QSVM model performs quantum state mapping on the data feature vector to be tested through a quantum processor, and calculates the classification decision boundary using the quantum kernel function to output the corresponding classification result, thereby realizing the mapping of the data feature vector to a high-dimensional quantum state, which is conducive to more accurately capturing the nonlinear correlation between the data feature vectors. Not only is the efficiency of the QSVM model calculation improved based on the computational characteristics of the quantum kernel function, but also the reliability and accuracy of the QSVM model in classifying the data feature vectors is improved.

[0035] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0037] Figure 1 A schematic diagram showing an exemplary system architecture to which a data classification solution according to an embodiment of the present invention may be applied; Figure 2 is a flow chart of a data classification method in an exemplary embodiment of the present disclosure; Figure 3 is a flow chart of another data classification method in an exemplary embodiment of the present disclosure; Figure 4 is a block diagram of a data classification device in an exemplary embodiment of the present disclosure; Figure 5 is a block diagram of another data classification device in an exemplary embodiment of the present disclosure; Figure 6 is a block diagram of an electronic device in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present disclosure will be more comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or that other methods, components, devices, steps, etc. may be employed. In other cases, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0039] The accompanying drawings are merely schematic illustrations of the present disclosure. Identical reference numerals in the drawings denote identical or similar components, and thus their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0040] Figure 1 A schematic diagram showing an exemplary system architecture to which the data classification solution according to an embodiment of the present invention can be applied.

[0041] like Figure 1 As shown, system architecture 100 may include one or more terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing a communication link between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0042] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as needed. For example, the server 105 may be a server cluster consisting of multiple servers.

[0043] Users can use terminal devices 101, 102, 103 to interact with server 105 via network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, etc.

[0044] In some embodiments, the data classification method provided by the embodiments of the present invention is generally executed by server 105. Accordingly, the data classification device is generally provided in terminal device 103 (which may also be terminal device 101 or 102). In other embodiments, certain terminals may have similar functions to the server device to execute the present method.

[0045] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

[0046] Figure 2 is a flow chart of a data classification method in an exemplary embodiment of the present disclosure.

[0047] refer to Figure 2 , data classification methods can include: Step S202, converting the data feature vector used for QSVM model training into a quantum state corresponding to the data feature vector through a quantum circuit; Step S204, calculating a quantum kernel function based on the inner product of the quantum state, and constructing a corresponding dual optimization objective function; Step S206: Determine the parameters of the optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model. The constructed QSVM model uses a quantum processor to perform quantum state mapping on the data feature vector to be tested, and uses a quantum kernel function to calculate the classification decision boundary to output the corresponding classification result.

[0048] The disclosed embodiment converts the data feature vectors used for QSVM model training into quantum states corresponding to the data feature vectors through a quantum circuit, calculates the quantum kernel function based on the inner product of the quantum state, and constructs a corresponding dual optimization objective function. The parameters of the optimal classification hyperplane in the QSVM model are determined based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model. The constructed QSVM model performs quantum state mapping on the data feature vectors to be tested through a quantum processor, and calculates the classification decision boundary using the quantum kernel function to output the corresponding classification result, thereby realizing the mapping of the data feature vectors to high-dimensional quantum states, which is conducive to more accurately capturing the nonlinear correlation between the data feature vectors. Not only is the efficiency of the QSVM model calculation improved based on the computational characteristics of the quantum kernel function, but also the reliability and accuracy of the QSVM model in classifying the data feature vectors is improved.

[0049] Below, each step of the data classification method is described in detail.

[0050] In an exemplary embodiment of the present disclosure, calculating a quantum kernel function based on the inner product of the quantum state and constructing a corresponding dual optimization objective function includes: Calculating a quantum kernel function based on the inner product of the quantum state and constructing an optimization objective function of the QSVM (Quantum Support Vector Machine) model; The optimization objective function is transformed into a dual optimization objective function represented by a quantum kernel function by introducing Lagrange multipliers.

[0051] In the above embodiment, the optimization objective function is transformed into a dual optimization objective function represented by a quantum kernel function by introducing Lagrange multipliers. The complex weights in the original optimization objective function are w and slack variables is eliminated and converted to optimize only The problem of further replacing the traditional inner product with the quantum kernel function not only retains the consistency of the problem form, but also realizes the solution of efficiently processing high-dimensional feature mapping.

[0052] In an exemplary embodiment of the present disclosure, the expression of the optimization objective function includes , the N represents the number of the data feature vectors, the Characterizing the regularization term, represents the classification error term, b represents the classification bias, and represents the slack variable corresponding to the i-th data eigenvector, and C represents the regularization parameter.

[0053] In an exemplary embodiment of the present disclosure, the constraint condition corresponding to the optimization objective function is

[0054] Among them, the Characterizes the label of the i-th data feature vector, the Characterize the quantum feature map corresponding to the i-th data feature vector, the quantum feature map By parameterizing quantum circuits implementation, wherein the quantum circuit It consists of a single quantum bit rotation gate and a controlled entanglement gate. Encoded into quantum states .

[0055] In an exemplary embodiment of the present disclosure, the expression of the dual optimization objective function includes , , wherein the Characterize the jth Lagrange multiplier, the Characterize the i-th Lagrange multiplier, the Characterize the label of the jth data feature vector, the Characterization pair and The quantum kernel function for performing the calculation, Characterize the quantum state of the i-th data feature vector, Characterize the quantum state of the j-th data eigenvector.

[0056] In an exemplary embodiment of the present disclosure, the quantum kernel function is implemented by executing a quantum circuit. And measure the estimated ground state probability, U ( ) is a parameter xj The generated unitary matrix (quantum gate) acts on the quantum state, Characterization of the Perform Hermitian conjugation operation, that is, take the parameter xi Conjugate transpose (inverse operation) of the resulting unitary matrix.

[0057] In an exemplary embodiment of the present disclosure, the quantum kernel function is verified by sampling statistics, the sampling statistics including quantum state tomography and / or SWAP test estimation, the quantum kernel function is configured to satisfy the Mercer condition, and the Gram matrix of the quantum kernel function is semi-positive-definite corrected after being measured by quantum hardware.

[0058] In the above embodiment, by verifying the quantum kernel function through sampling statistics, the noise impact on the quantum computing device in the current NISQ era is reduced.

[0059] In an exemplary embodiment of the present disclosure, a quantum-classical hybrid algorithm is used to solve the dual optimization objective function. The quantum-classical hybrid algorithm runs on a variational quantum eigensolver. The quantum hardware in the variational quantum eigensolver is used to calculate the kernel matrix term of the dual optimization objective function. Term, the classical device in the variational quantum eigensolver is used to calculate the gradient and update the Lagrange multiplier until the convergence condition is met.

[0060] In an exemplary embodiment of the present disclosure, the constraints of the dual optimization objective function include .

[0061] In an exemplary embodiment of the present disclosure, determining the parameters of the optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model includes: Determining Lagrange multipliers and support vectors based on an optimal solution of the dual optimization objective function; Calculating the weight vector according to the Lagrange multiplier, the label of the data eigenvector, and the quantum eigenmap corresponding to the data eigenvector; The classification bias is calculated according to the support vector, the label of the data feature vector and the quantum kernel function.

[0062] In an exemplary embodiment of the present disclosure, the expression for calculating the weight vector according to the Lagrange multiplier, the label of the data feature vector and the quantum feature map corresponding to the data feature vector includes: .

[0063] In an exemplary embodiment of the present disclosure, the expression for calculating the classification bias according to the support vector, the label of the data feature vector and the quantum kernel function includes: , wherein the represents the support vector, the k represents the index of the support vector, the S A set of indices representing the support vectors.

[0064] In an exemplary embodiment of the present disclosure, the encoding mode of the quantum circuit is an angle encoding mode or an amplitude encoding mode, and converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit includes: The data feature vector is mapped into a quantum state of the data feature vector by adopting an angle encoding method or an amplitude encoding method.

[0065] In an exemplary embodiment of the present disclosure, the expression for mapping the data feature vector to the rotation angle of the quantum bit using angle encoding includes: , wherein the R represents a revolving door around the coordinate axis of the rectangular coordinate system, the coordinate axis is the x-axis or the y-axis or the z-axis, the d represents the dimension of the data feature vector, the Characterize the quantum state of the data feature vector, the Characterize the tensor product operator, the Characterizes the normalization processing result of the data feature vector.

[0066] In an exemplary embodiment of the present disclosure, it further includes: The constructed QSVM model is verified using a validation data set corresponding to the data feature vector; According to the verification results, the QSVM model is adjusted or the test data set is tested. The result includes at least one of accuracy, precision, recall and F1 score, and the parameter adjustment processing includes at least one of adjusting the feature mapping method, increasing the number of quantum bits, optimizing the parameters in the feature mapping circuit and adding a regularization factor to the quantum kernel function.

[0067] In an exemplary embodiment of the present disclosure, before converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit, the method further includes: Standardizing the collected data features, wherein the standardization is normalization or conversion into a normal distribution; The standardized data features are vectorized to obtain the data feature vectors.

[0068] In an exemplary embodiment of the present disclosure, the expression for normalizing the collected data features includes: , wherein the Characterize the nth column eigenvalue, and stated Respectively represent the maximum and minimum values in the nth column eigenvalues, the Characterizes the nth eigenvalue of the mth sample.

[0069] In an exemplary embodiment of the present disclosure, before converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit, the method further includes: The data feature vectors are divided into a training data set, a validation data set and a test data set according to a preset ratio. The training data set is used to train the QSVM model, the validation data set is used to verify the QSVM model, and the test data set is used to test the QSVM model training.

[0070] In an exemplary embodiment of the present disclosure, it further includes: Inputting the data feature vector to be tested into the decision function of the constructed QSVM model for classification to generate the classification result; In response to determining, according to the classification result, that the category of the data feature vector to be tested is a fault warning category, calculating the contribution corresponding to each fault root cause according to the support vector and the quantum kernel function; The root cause of the fault corresponding to the data feature vector to be tested is determined according to the ranking result of the contribution degree.

[0071] In an exemplary embodiment of the present disclosure, the expression of the decision function includes , Characterize the data feature vector to be tested, the Characterization When the support vector is greater than 0, the sign Representation symbol function.

[0072] In an exemplary embodiment of the present disclosure, the expression for calculating the contribution degree includes: .

[0073] Figure 3 The present invention is a flowchart of a data classification method for a communication network in an exemplary embodiment of the present disclosure.

[0074] refer to Figure 3 , the data classification method of the communication network may include: Step S302, collecting communication indicators in the communication network; Step S304: Determine the communication indicator as a data feature, and calculate the data feature using the data classification method described in any of the above technical solutions to determine a data classification result of the communication indicator.

[0075] Corresponding to the above method embodiments, the present disclosure also provides a data classification device that can be used to execute the above method embodiments.

[0076] Figure 4 It is a block diagram of a data classification device in an exemplary embodiment of the present disclosure.

[0077] refer to Figure 4 , the data classification device 400 may include: A conversion module 402 is configured to convert the data feature vector used for QSVM model training into a quantum state corresponding to the data feature vector through a quantum circuit; A construction module 404 is configured to calculate a quantum kernel function based on the inner product of the quantum state and construct a corresponding dual optimization objective function; The classification module 406 is configured to determine the parameters of the optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model. The constructed QSVM model uses a quantum processor to perform quantum state mapping on the data feature vector to be tested, and uses a quantum kernel function to calculate the classification decision boundary to output the corresponding classification result.

[0078] In an exemplary embodiment of the present disclosure, the construction module 404 is further configured to: Calculating a quantum kernel function based on the inner product of the quantum state and constructing an optimization objective function of the QSVM model; The optimization objective function is transformed into a dual optimization objective function represented by a quantum kernel function by introducing Lagrange multipliers.

[0079] In an exemplary embodiment of the present disclosure, the expression of the optimization objective function includes , the N represents the number of the data feature vectors, the Characterizing the regularization term, represents the classification error term, b represents the classification bias, and represents the slack variable corresponding to the i-th data eigenvector, and C represents the regularization parameter.

[0080] In an exemplary embodiment of the present disclosure, the constraint condition corresponding to the optimization objective function is .

[0081] Among them, the label representing the i-th data feature vector, the Characterize the quantum feature map corresponding to the i-th data feature vector, the quantum feature map By parameterizing quantum circuits implementation, wherein the quantum circuit It consists of a single quantum bit rotation gate and a controlled entanglement gate. Encoded into quantum states .

[0082] In an exemplary embodiment of the present disclosure, the expression of the dual optimization objective function includes , , wherein the Characterize the jth Lagrange multiplier, the Characterize the i-th Lagrange multiplier, the Characterize the label of the jth data feature vector, the Characterization pair and The quantum kernel function for performing the calculation, Characterize the quantum state of the i-th data feature vector, Characterize the quantum state of the j-th data eigenvector.

[0083] In an exemplary embodiment of the present disclosure, the quantum kernel function is implemented by executing a quantum circuit. And measure the ground state probability estimate, the Characterization of the Perform Hermitian conjugation.

[0084] In an exemplary embodiment of the present disclosure, the quantum kernel function is verified by sampling statistics, the sampling statistics including quantum state tomography and / or SWAP test estimation, the quantum kernel function is configured to satisfy the Mercer condition, and the Gram matrix of the quantum kernel function is semi-positive-definite corrected after being measured by quantum hardware.

[0085] In an exemplary embodiment of the present disclosure, a quantum-classical hybrid algorithm is used to solve the dual optimization objective function, and the quantum-classical hybrid algorithm runs on a variational quantum eigensolver, and the quantum hardware in the variational quantum eigensolver is used to calculate Term, the classical device in the variational quantum eigensolver is used to calculate the gradient and update the Lagrange multiplier until the convergence condition is met.

[0086] In an exemplary embodiment of the present disclosure, the constraints of the dual optimization objective function include .

[0087] In an exemplary embodiment of the present disclosure, the classification module 406 is further configured to: Determining Lagrange multipliers and support vectors based on an optimal solution of the dual optimization objective function; Calculating the weight vector according to the Lagrange multiplier, the label of the data eigenvector, and the quantum eigenmap corresponding to the data eigenvector; The classification bias is calculated according to the support vector, the label of the data feature vector and the quantum kernel function.

[0088] In an exemplary embodiment of the present disclosure, the expression for calculating the weight vector according to the Lagrange multiplier, the label of the data feature vector and the quantum feature map corresponding to the data feature vector includes: .

[0089] In an exemplary embodiment of the present disclosure, the expression for calculating the classification bias according to the support vector, the label of the data feature vector and the quantum kernel function includes: Among them, the represents the support vector, the k represents the index of the support vector, the S A set of indices representing the support vectors.

[0090] In an exemplary embodiment of the present disclosure, the construction module 404 is configured to: The data feature vector is mapped into a quantum state of the data feature vector by adopting an angle encoding method or an amplitude encoding method.

[0091] In an exemplary embodiment of the present disclosure, the expression for mapping the data feature vector to the rotation angle of the quantum bit using angle encoding includes: , wherein the R represents a revolving door around the coordinate axis of the rectangular coordinate system, the coordinate axis is the x-axis or the y-axis or the z-axis, the d represents the dimension of the data feature vector, the Characterize the quantum state of the data feature vector, the Characterize the tensor product operator, the Characterizes the normalization processing result of the data feature vector.

[0092] In an exemplary embodiment of the present disclosure, the data classification device 400 is further configured to: The constructed QSVM model is verified using a validation data set corresponding to the data feature vector; According to the verification results, the QSVM model is adjusted or the test data set is tested. The result includes at least one of accuracy, precision, recall and F1 score, and the parameter adjustment processing includes at least one of adjusting the feature mapping method, increasing the number of quantum bits, optimizing the parameters in the feature mapping circuit and adding a regularization factor to the quantum kernel function.

[0093] In an exemplary embodiment of the present disclosure, the data classification device 400 is further configured to: Standardizing the collected data features, wherein the standardization is normalization or conversion into a normal distribution; The standardized data features are vectorized to obtain the data feature vectors.

[0094] In an exemplary embodiment of the present disclosure, the expression for normalizing the collected data features includes: , wherein the Characterize the nth column eigenvalue, and stated Respectively represent the maximum and minimum values in the nth column eigenvalues, the Characterizes the nth eigenvalue of the mth sample.

[0095] In an exemplary embodiment of the present disclosure, the data classification device 400 is further configured to: The data feature vectors are divided into a training data set, a validation data set and a test data set according to a preset ratio. The training data set is used to train the QSVM model, the validation data set is used to verify the QSVM model, and the test data set is used to test the QSVM model training.

[0096] In an exemplary embodiment of the present disclosure, the data classification device 400 is further configured to: Inputting the data feature vector to be tested into the decision function of the constructed QSVM model for classification to generate the classification result; In response to determining, according to the classification result, that the category of the data feature vector to be tested is a fault warning category, calculating the contribution corresponding to each fault root cause according to the support vector and the quantum kernel function; The root cause of the fault corresponding to the data feature vector to be tested is determined according to the ranking result of the contribution degree.

[0097] In an exemplary embodiment of the present disclosure, the expression of the decision function includes , Characterize the data feature vector to be tested, the Characterization When the support vector is greater than 0, the sign Representation symbol function.

[0098] In an exemplary embodiment of the present disclosure, the expression for calculating the contribution degree includes: .

[0099] Another data classification device in an exemplary embodiment of the present disclosure includes a data acquisition module, a data normalization module, a data segmentation module, a quantum feature mapping module, a QSVM model training module, a QSVM model evaluation module, a fault prediction module, and a root cause location module. The specific process is as follows: Step 1: The data collection module collects historical indicator data and marks whether a fault occurs. The data set is defined as D={( xi,yi )|i=1,2,…,N}, where, xi=[xi1,xi2,…,xid ] is the feature vector of the i-th sample, yi is the label of the i-th sample, -1 indicates no fault and +1 indicates fault.

[0100] Step 2: The data normalization module scales the eigenvalues to the [0, 1] interval or standard normal distribution to improve the convergence speed of the model.

[0101] Step 3: The data segmentation module divides the data into training, validation, and test datasets according to a certain ratio. The training dataset is used to train the QSVM model, the validation dataset is used to evaluate the QSVM model, and the test dataset is used for fault prediction and root cause location. The three datasets are used in the following order: training, validation, and test.

[0102] Step 4: The quantum feature mapping module maps each sample xi into a quantum state , ,in It is a quantum circuit that constructs quantum states through classical features. Common feature mapping methods include angle encoding and amplitude encoding.

[0103] Step 5: The training goal of the QVSM model training module is to find the optimal classification hyperplane. First, define the optimization goal. The original optimization problem is: , the constraints are: Then, it is transformed into a dual problem, and the dual optimization problem is solved by the quantum kernel function Expressed as: , the constraints are: Next, we use quantum computing resources to calculate the quantum kernel function: ,in and is the quantum state. Finally, N Lagrange multipliers are solved by optimization , determine the optimal classification hyperplane parameters, weights , classification bias , where k is the index of the support vector.

[0104] Step 6: The QSVM model evaluation module uses the validation dataset to check the performance of the QSVM model to ensure its generalization ability to unknown data. The evaluation content generally includes accuracy, precision, recall, F1 score, etc. If the above evaluation content does not meet the requirements, it returns to the quantum feature mapping module for parameter adjustment and optimization. For example, adjusting the feature mapping method, increasing the number of quantum bits, optimizing the parameters in the feature mapping circuit, adding regularization factors to the quantum kernel function to reduce overfitting, etc. The parameter adjustment and optimization process stops when the requirements of the QSVM model evaluation module are met, which includes the following: (1) The verification data set is preprocessed by the data normalization module to ensure that the eigenvalues are scaled to the [0, 1] interval or the standard normal distribution, and the eigenvectors of the verification data set are converted into quantum states by the quantum feature mapping module; (2) The data after quantum feature mapping is input into the QSVM model for evaluation. The support vector is calculated by the quantum kernel function, and the optimal classification hyperplane is found. According to the dual optimization problem, the Lagrange multiplier is optimized, the support vector is determined by the Lagrange multiplier, and finally the classification bias is determined.

[0105] (3) The QSVM model evaluation module calculates the model performance on the validation dataset using accuracy (the proportion of samples correctly classified by the model), precision (the proportion of samples predicted to be positive that are actually positive), recall (the proportion of samples actually positive that are predicted to be positive), and F1 score (the harmonic mean of precision and recall, which comprehensively considers both precision and recall).

[0106] If the standard is not met, it is necessary to return to the quantum feature mapping module for parameter adjustment and optimization, including modifying the mapping method (such as changing from angle encoding to amplitude encoding), increasing the number of quantum bits (the number of quantum bits used can be increased by a power of 2), optimizing the parameters in the quantum circuit (optimizing the control gate parameters in the quantum circuit, rotating the angle, gate operation order, etc. to improve mapping efficiency), and adding a regularization factor to the quantum kernel function. Through appropriate regularization, the model's ability to generalize to new data can be improved and overfitting can be avoided.

[0107] (4) After adjusting the parameters, repeat steps 5 and 6 until the requirements of step 6 are met.

[0108] Step 7: The fault prediction module uses the test dataset to perform fault prediction. , use the decision function for classification: , the judgment rule is: if f ( )>0, it is predicted as a possible fault category (+1), and a fault warning is output. ) is normalized and converted into a probability value to characterize the possibility of failure; if f( )≤0, the prediction is low failure probability category (-1), the process ends, and restarts from step 1.

[0109] Step 8: If the prediction in step 7 is a possible fault category (+1), after outputting the fault warning, the root cause location module uses the support vector and quantum kernel functions , analyze which features contribute most to the classification decision and calculate the contribution , output the root cause contribution ranking, locate the feature with the largest contribution as the root cause of the fault, perform time embedding analysis on the historical indicator data, locate the time node when the root cause of the fault occurred, end the process, and start again from step 1.

[0110] Figure 5 The present invention is a block diagram of a data classification device for a communication network according to an exemplary embodiment of the present disclosure.

[0111] refer to Figure 5 , the data classification device 500 of the communication network may include: A collection module 502 is configured to collect communication indicators in the communication network; The calculation module 504 is configured to determine the communication indicator as a data feature, and calculate the data feature using the data classification method described in any of the above technical solutions to determine a data classification result of the communication indicator.

[0112] The following uses 5G wireless cell data indicators as the research object. Based on the data feature classification scheme in the communication network described above, the intelligent QSVM method is used to predict wireless cell faults and locate their root causes. By combining the high-dimensional feature mapping capabilities of quantum computing, the bottleneck problem of traditional methods in processing nonlinear complex relationships and high-dimensional data is solved. The specific steps are as follows: Step 1: The data collection module collects the operator's existing network indicator data of 5,000 wireless cells in a city from January to July 2024, including the following key performance indicators: cell ID, PRRUId, average uplink PRB occupancy of the cell, PDCCH channel occupancy, average number of RRC connected users, maximum number of RRC connected users, uplink RLC layer user plane traffic, downlink RLC layer user plane traffic, average actual cell transmit power, maximum actual cell transmit power, RRU / AAU actual average transmit power, RRU / AAU actual maximum transmit power, NG interface user plane maximum transmission rate, etc., but not limited to these.

[0113] Among them, historical data is recorded by hour, and whether the cell has experienced a fault during the time period is marked, forming a data set D={( xi,yi )|i=1,2,…,N}, where, xi= [ xi1,xi2,…,xid] is the feature vector of the i-th sample, yi is the label of the i-th sample, -1 indicates no fault, +1 indicates fault; Step 2: The data normalization module normalizes the features in the dataset and uses the min-max normalization method to map each feature value to the [0, 1] interval to eliminate the dimensional differences between features and improve the model training efficiency. The normalization formula is: , where max( ) and min( ) represent the characteristics The maximum and minimum values of .

[0114] Step 3: The data segmentation module divides the data into training, validation, and test datasets in a ratio of 7:2:1. The training dataset contains 35,000 samples and is used to train the QSVM model; the validation dataset contains 10,000 samples and is used to evaluate and optimize the QSVM model; and the test dataset contains 5,000 samples and is used for fault prediction and root cause location. The three datasets are used in the following order: training, validation, and test.

[0115] Step 4: The quantum feature mapping module maps the classical feature vector xi to a quantum state , ,in It is a quantum circuit. This embodiment uses angle encoding to map the eigenvalue to the rotation angle of the quantum bit: ,in, is a revolving door around the y-axis, and d is the dimension of the feature vector. Through quantum circuits, high-dimensional feature mapping is completed.

[0116] Step 5: The training goal of the QVSM model training module is to find the optimal classification hyperplane, transform the original optimization problem into a dual problem, and use the quantum kernel function to solve the problem. Calculate the similarity between samples: , calculate the Lagrange multiplier using the training data set , determine the optimal classification hyperplane parameters and , where k is the index of the support vector.

[0117] Step 6: The QSVM model evaluation module uses the validation dataset to calculate indicators such as accuracy, precision, recall, and F1 score. If the above evaluation contents do not meet the standards, it returns to the quantum feature mapping module to start parameter adjustment and optimization. The F1 score of the model on the validation dataset is stable at 97.8%, meeting the requirements of the evaluation module.

[0118] Step 7: Add new data points to the test dataset Input the trained QSVM model and use the decision function to calculate the classification results: , the results show that f >0, it is predicted as a possible fault category, a fault warning is output, and the fault probability is obtained by normalization.

[0119] After substituting the above scheme into the test dataset, the fault prediction accuracy reached 96.3% and the F1 score was 97.6%, which are higher than the traditional neural network model used for comparison (accuracy 93.1%, F1 score 91.2%).

[0120] Step 8: For samples predicted to be faulty, use support vectors and quantum kernel functions to analyze the contribution of features to decision making. ,In the test dataset, PDCCH channel occupancy and the maximum number of RRC ,connected users were repeatedly identified as the main factors leading to cell ,overload.

[0121] By analyzing the time series of the above two indicators, we further pinpointed the time of the fault. For cell ID 692047, the PDCCH channel occupancy rate exceeded 96% at 4:00 PM on June 24, 2024. At the same time, the maximum number of RRC connected users reached its peak, causing cell signaling overload.

[0122] Since the functions of the data classification device 400 and the communication network data classification device 500 have been described in detail in their corresponding method embodiments, the present disclosure will not elaborate on them here.

[0123] Compared with existing optimization methods, the embodiments of the present disclosure have the following innovations, including but not limited to: 1. Designed for wireless cell fault prediction and root cause location scenarios. Using QSVM for wireless cell fault prediction and root cause location fully leverages the high dynamics and spatiotemporal correlation of multidimensional data in wireless communication networks. This makes the trained QSVM model more customized and more tailored to the actual needs of communication network operations and maintenance. A single QSVM model can achieve both fault prediction and root cause location, making it more intelligent, efficient, and faster than classic prediction methods. 2. Data classification is more targeted, and model training is optimized based on wireless data evaluation metrics. To address the high-dimensional, sparse, and multi-scale characteristics of wireless cell data, the data is standardized and divided into three categories for model training, verification, and testing, respectively. This improves the accuracy of data feature representation and the generalization of the model. A model evaluation module is added, leveraging wireless data metrics to incorporate model assessment and other indicators for comprehensive assessment of model effectiveness. The model's expressive power is enhanced by optimizing quantum mapping methods and QSVM model parameter tuning.

[0124] 3. Existing technology frameworks are mostly general-purpose fault prediction designs, making them difficult to adapt to the multi-dimensional time-series fault data characteristics of wireless cells. This paper innovatively proposes a quantum support vector machine model that combines spatiotemporal characteristics with communication network characteristics. Leveraging the parallelism of quantum computing and its improved similarity analysis capabilities in high-dimensional data, this model enables more efficient, intelligent, and rapid fault prediction and root cause location.

[0125] 4. Existing technologies are limited to classification tasks. The present invention innovatively expands classification into an integrated solution for prediction and root cause location, achieving full-link innovation from data classification to scenario application, and enhancing the functional depth and value of the technical solution.

[0126] 5. It does not rely on powerful quantum computing resources and can be achieved using both real quantum computing machines and quantum computing simulators in the NISQ era.

[0127] It should be noted that although several modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0128] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0129] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Therefore, various aspects of the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, microcode, etc.), or in a combination of hardware and software, collectively referred to herein as "circuits," "modules," or "systems."

[0130] Refer to the following Figure 6 An electronic device 600 according to this embodiment of the present invention will be described. Figure 6 The electronic device 600 shown is merely an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0131] like Figure 6 As shown, electronic device 600 is implemented as a general-purpose computing device. Components of electronic device 600 may include, but are not limited to, the aforementioned at least one processing unit 610, the aforementioned at least one storage unit 620, and a bus 630 connecting various system components (including storage unit 620 and processing unit 610).

[0132] The storage unit stores program code that can be executed by the processing unit 610, causing the processing unit 610 to perform the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section above. For example, the processing unit 610 can perform the method described in the embodiments of the present disclosure.

[0133] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0134] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0135] Bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0136] The electronic device 600 can also communicate with one or more external devices 640 (e.g., a keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 600, and / or any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication can occur via an input / output (I / O) interface 650. Furthermore, the electronic device 600 can communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via a network adapter 660. As shown, the network adapter 660 communicates with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 600, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0137] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for enabling a computing device (such as a personal computer, server, terminal device, or network device) to execute the methods according to the embodiments of the present disclosure.

[0138] In exemplary embodiments of the present disclosure, a computer-readable storage medium is also provided, on which is stored a program product capable of implementing the aforementioned methods of this specification. In some possible implementations, various aspects of the present invention may also be implemented in the form of a program product comprising program code. When the program product is executed on a terminal device, the program code is configured to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the "Exemplary Methods" section of this specification.

[0139] The program product for implementing the above-described method according to an embodiment of the present invention may be a portable compact disc read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0140] The readable medium may be a readable signal medium or a readable storage medium. The 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 thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable 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 thereof.

[0141] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0142] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0143] In an exemplary embodiment of the present disclosure, a computer program product is also provided. The computer program product can be loaded or stored using any combination of one or more readable media, and the program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0144] Furthermore, the above-described figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes illustrated in the above-described figures do not indicate or limit the temporal order of these processes. Furthermore, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0145] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the claims.

Claims

1. A data classification method, characterized in that: include: The data feature vector used for QSVM model training is converted into the quantum state corresponding to the data feature vector through the quantum circuit; Calculating a quantum kernel function based on the inner product of the quantum state and constructing a corresponding dual optimization objective function; Based on the optimal solution of the dual optimization objective function, the parameters of the optimal classification hyperplane in the QSVM model are determined to complete the construction of the QSVM model. The constructed QSVM model performs quantum state mapping on the data feature vector to be tested through a quantum processor, and calculates the classification decision boundary using a quantum kernel function to output the corresponding classification result.

2. The data classification method according to claim 1, wherein: Calculating the quantum kernel function based on the inner product of the quantum state and constructing the corresponding dual optimization objective function include: Calculating a quantum kernel function based on the inner product of the quantum state and constructing an optimization objective function of the QSVM model; The optimization objective function is transformed into the dual optimization objective function by introducing Lagrange multipliers.

3. The data classification method according to claim 2, wherein: The expression of the optimization objective function includes , the N represents the number of the data feature vectors, the Characterizing the regularization term, represents the classification error term, b represents the classification bias, and represents the slack variable corresponding to the i-th data eigenvector, and C represents the regularization parameter.

4. The data classification method according to claim 3, wherein: The constraints corresponding to the optimization objective function are: ; Among them, the Characterizes the label of the i-th data feature vector, the Characterize the quantum feature map corresponding to the i-th data feature vector, the quantum feature map By parameterizing quantum circuits implementation, wherein the quantum circuit It consists of a single quantum bit rotation gate and a controlled entanglement gate. Encoded into quantum states .

5. The data classification method according to claim 4, wherein: The expression of the dual optimization objective function includes , , Among them, the Characterize the jth Lagrange multiplier, Characterize the i-th Lagrange multiplier, the Characterize the label of the jth data feature vector, the Characterization pair and The quantum kernel function is used to calculate the square of the module of the inner product of two quantum states. Characterize the quantum state of the i-th data feature vector, Characterize the quantum state of the j-th data eigenvector.

6. The data classification method according to claim 5, wherein: The quantum kernel function is implemented by executing a quantum circuit And measure the ground state probability estimate, the Characterization of the Perform Hermitian conjugation.

7. The data classification method according to claim 5, wherein: The quantum kernel function is verified by sampling statistics, which include quantum state tomography and / or SWAP test estimation. The quantum kernel function is configured to satisfy the Mercer condition, and the Gram matrix of the quantum kernel function is semi-positive-definite corrected after being measured by quantum hardware.

8. The data classification method according to claim 5, wherein: A quantum-classical hybrid algorithm is used to solve the dual optimization objective function. The quantum-classical hybrid algorithm runs on a variational quantum eigensolver. The quantum hardware in the variational quantum eigensolver is used to calculate the kernel matrix terms of the dual optimization objective function, and the classical device in the variational quantum eigensolver is used to calculate the gradient and update the Lagrange multiplier until the convergence condition is met.

9. The data classification method according to claim 5, wherein: The constraints of the dual optimization objective function include .

10. The data classification method according to claim 5, wherein: Determining the parameters of the optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model includes: Determining Lagrange multipliers and support vectors based on an optimal solution of the dual optimization objective function; Calculating the regularization term based on the Lagrange multiplier, the label of the data eigenvector, and the quantum eigenmap corresponding to the data eigenvector; The classification bias is calculated according to the support vector, the label of the data feature vector and the quantum kernel function.

11. The data classification method according to claim 10, wherein: The expression for calculating the regularization term according to the Lagrange multiplier, the label of the data feature vector and the quantum feature map corresponding to the data feature vector includes: .

12. The data classification method according to claim 10, wherein: The expression for calculating the classification bias according to the support vector, the label of the data feature vector and the quantum kernel function includes: , wherein the represents the support vector, the k represents the index of the support vector, the S A set of indices representing the support vectors.

13. The data classification method according to claim 10, wherein: The encoding mode of the quantum circuit is an angle encoding mode or an amplitude encoding mode. Converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit includes: The data feature vector is mapped into a quantum state of the data feature vector by using the angle encoding method or the amplitude encoding method.

14. The data classification method according to claim 13, wherein: The expression for mapping the data feature vector to the rotation angle of the quantum bit using angle encoding includes: , wherein the R represents a revolving door around the coordinate axis of the rectangular coordinate system, the coordinate axis is the x-axis or the y-axis or the z-axis, the d represents the dimension of the data feature vector, the Characterize the quantum state of the data feature vector, the Characterize the tensor product operator, the Characterizes the normalization processing result of the data feature vector.

15. The data classification method according to any one of claims 1 to 14, characterized in that: Also includes: The constructed QSVM model is verified using a validation data set corresponding to the data feature vector; According to the verification results, the QSVM model is adjusted or the test data set is tested. The result includes at least one of accuracy, precision, recall and F1 score, and the parameter adjustment processing includes at least one of adjusting the feature mapping method, increasing the number of quantum bits, optimizing the parameters in the feature mapping circuit and adding a regularization factor to the quantum kernel function.

16. The data classification method according to any one of claims 1 to 14, characterized in that: Before converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit, it also includes: Standardizing the collected data features, wherein the standardization is normalization or conversion into a normal distribution; The standardized data features are vectorized to obtain the data feature vectors.

17. The data classification method according to claim 16, wherein: The expressions for standardizing the collected data features include , wherein the Characterize the nth column eigenvalue, and stated Respectively represent the maximum and minimum values in the nth column eigenvalues, the Characterizes the nth eigenvalue of the mth sample.

18. The data classification method according to any one of claims 1 to 14, characterized in that: Before converting the data feature vector used for QSVM model training into the quantum state corresponding to the data feature vector through the quantum circuit, it also includes: The data feature vectors are divided into a training data set, a validation data set and a test data set according to a preset ratio. The training data set is used to train the QSVM model, the validation data set is used to verify the QSVM model, and the test data set is used to test the QSVM model training.

19. The data classification method according to any one of claims 10 to 14, characterized in that: Also includes: Inputting the data feature vector to be tested into the decision function of the constructed QSVM model for classification to generate the classification result; In response to determining, according to the classification result, that the category of the data feature vector to be tested is a fault warning category, calculating the contribution corresponding to each fault root cause according to the support vector and the quantum kernel function; The root cause of the fault corresponding to the data feature vector to be tested is determined according to the ranking result of the contribution degree.

20. The data classification method according to claim 19, wherein: The expression of the decision function includes , Characterize the data feature vector to be tested, the Characterization When the support vector is greater than 0, the sign Representation symbol function.

21. The data classification method according to claim 19, wherein: The expression for calculating the contribution includes .

22. A data classification method for a communication network, characterized in that: include: collecting communication indicators in the communication network; The communication indicator is determined as a data feature, and the data feature is calculated using the data classification method according to any one of claims 1 to 21 to determine a data classification result of the communication indicator.

23. A data classification device, characterized in that: include: A conversion module, configured to convert the data feature vector used for QSVM model training into a quantum state corresponding to the data feature vector through a quantum circuit; A construction module is configured to calculate a quantum kernel function based on the inner product of the quantum state and construct a corresponding dual optimization objective function; The classification module is configured to determine the parameters of the optimal classification hyperplane in the QSVM model based on the optimal solution of the dual optimization objective function to complete the construction of the QSVM model. The constructed QSVM model uses a quantum processor to perform quantum state mapping on the data feature vector to be tested, and uses a quantum kernel function to calculate the classification decision boundary to output the corresponding classification result.

24. A data classification device for a communication network, characterized in that: include: A collection module, configured to collect communication indicators in the communication network; The calculation module is configured to determine the communication indicator as a data feature, and calculate the data feature using the data classification method according to any one of claims 1 to 21 to determine a data classification result of the communication indicator.

25. An electronic device, characterized in that: include: Memory; as well as A processor coupled to the memory, the processor being configured to execute the data classification method according to any one of claims 1 to 21 or the data classification method for a communication network according to claim 22 based on instructions stored in the memory.

26. A computer-readable storage medium having a program stored thereon, wherein when the program is executed by a processor, the program implements the data classification method according to any one of claims 1 to 21 or the data classification method for a communication network according to claim 22.

27. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the data classification method according to any one of claims 1 to 21 or the data classification method for a communication network according to claim 22 is implemented.

Images