A method for analyzing communication performance based on space-time-frequency resources

Abstract

The application discloses a communication performance analysis method based on space-time-frequency resources, and belongs to the technical field of communication performance analysis, which collects space-time-frequency resource types and communication performance analysis indexes, and then generates a communication performance analysis test task according to the space-time-frequency resource types and the communication performance analysis indexes; after the communication performance analysis test task is executed, the relationship between the actual values of the space-time-frequency resource types and the actual values of the communication performance analysis indexes can be learned through artificial intelligence, so that the communication performance analysis indexes can be analyzed in a predictive manner through the actual values of the space-time-frequency resource types in a subsequent process, and the allocation of the space-time-frequency resources can be quickly adjusted according to requirements by the staff.

Description

Technical Field

[0001] This invention belongs to the field of communication performance analysis technology, specifically relating to a communication performance analysis method based on spatiotemporal frequency resources. Background Technology

[0002] With the emergence of new scenarios such as vehicle-to-everything (V2X) and drone networking, integrated communication and sensing systems have received widespread attention in recent years. Through integrated design, these systems achieve both data transmission and target detection functions based on the same hardware and spectrum resources, reducing hardware costs and improving system integration and spectrum resource utilization performance. Spatiotemporal frequency resources refer to the concept of effectively managing and utilizing time, space, and frequency resources in communication and network technologies. These resources are particularly important in wireless communication and networks, especially in 5G and future communication technologies. In existing technologies, communication performance analysis often uses a single indicator, lacks predictability, and makes it difficult to adjust system communication performance in advance. Summary of the Invention

[0003] This invention provides a communication performance analysis method based on spatiotemporal frequency resources, which solves the problem that existing technologies use a single indicator for analysis, lack foresight, and make it difficult to adjust the system's communication performance in advance.

[0004] A communication performance analysis method based on spatiotemporal frequency resources, comprising:

[0005] The system obtains the spatiotemporal frequency resource types and communication performance analysis indicators input by the staff, and generates a communication performance analysis test task based on the spatiotemporal frequency resource types and communication performance analysis indicators.

[0006] The communication performance analysis test task is executed to obtain the actual values ​​corresponding to the communication performance analysis indicators by executing the sample values ​​corresponding to the spatiotemporal resource types.

[0007] An artificial intelligence model is used to construct a communication performance analysis model. The model is optimized by taking the sample values ​​of spatiotemporal frequency resource types as input and the actual values ​​of the corresponding communication performance analysis indicators as expected output.

[0008] The allocation values ​​corresponding to the spatiotemporal frequency resource types are collected, and the optimized communication performance analysis model is used to identify the allocation values ​​corresponding to the spatiotemporal frequency resource types to obtain the communication performance analysis results.

[0009] Furthermore, the spatiotemporal frequency resource types and communication performance analysis indicators input by staff are obtained, and a communication performance analysis test task is generated based on the spatiotemporal frequency resource types and communication performance analysis indicators, including:

[0010] Retrieve the spatiotemporal frequency resource types input by staff; each spatiotemporal frequency resource type has its corresponding upper and lower limits;

[0011] Based on the premise that each spatiotemporal frequency resource type has its corresponding upper and lower limits, the numerical interval corresponding to the spatiotemporal frequency resource type is divided into a fixed number of parts using the equal division method, resulting in multiple numerical division points corresponding to each spatiotemporal frequency resource type.

[0012] Arrange and combine multiple numerical division points corresponding to all spatiotemporal frequency resource types to obtain sample values ​​corresponding to multiple spatiotemporal frequency resource types;

[0013] For each spatiotemporal frequency resource type, a task to be executed is generated based on the sample value.

[0014] Further, the communication performance analysis test task is executed to obtain the actual values ​​corresponding to the communication performance analysis indicators by executing sample values ​​corresponding to the spatiotemporal frequency resource types, including:

[0015] The communication performance analysis test task is executed to use the sample values ​​corresponding to the time, space, and frequency resource types as the control parameters of the communication system to be analyzed, and to obtain the actual values ​​corresponding to the communication performance analysis indicators of the communication system to be analyzed.

[0016] Furthermore, an artificial intelligence model is used to construct a communication performance analysis model, including: using a CNN model to construct a communication performance analysis model.

[0017] Furthermore, using sample values ​​of spatiotemporal frequency resource types as input and the actual values ​​of the corresponding communication performance analysis indicators as the expected output, the communication performance analysis model is optimized to obtain the optimized communication performance analysis model, including:

[0018] For the hyperparameters of the communication performance analysis model, the hyperparameters are initialized and encoded into vectors to obtain hyperparameter vectors. At the same time, multiple different hyperparameter vectors are obtained.

[0019] For any hyperparameter vector, take the sample values ​​of the spatiotemporal frequency resource type as input and the actual values ​​of the corresponding communication performance analysis indicators as the expected output to obtain the loss function value corresponding to the hyperparameter vector.

[0020] The optimal hyperparameter vector is determined based on the loss function values ​​corresponding to all hyperparameter vectors.

[0021] For any hyperparameter vector, based on the optimal hyperparameter vector, a first local search is performed on the hyperparameter vector using a local personalized search strategy to obtain the hyperparameter vector after the first local search.

[0022] For any hyperparameter vector obtained after the first local search, a second local search is performed on the hyperparameter vector based on the optimal hyperparameter vector using a nonlinear local search strategy to obtain the hyperparameter vector obtained after the second local search.

[0023] For the hyperparameter vector after the second local search, a reverse global greedy search strategy is used to perform a first global search on the hyperparameter vector to obtain the hyperparameter vector after the first global search.

[0024] For the hyperparameter vector after the first global search, a random global greedy search strategy is used to perform a second global search on the hyperparameter vector to obtain the hyperparameter vector after the second global search.

[0025] Determine whether the optimization termination condition is met. If so, re-obtain the optimal hyperparameter vector based on the hyperparameter vector after the second global search, and apply the parameters in the optimal hyperparameter vector to the communication performance analysis model to obtain the optimized communication performance analysis model. Otherwise, return to the step of obtaining the loss function value.

[0026] Furthermore, for any hyperparameter vector, based on the optimal hyperparameter vector, and using a local personalized search strategy, a first local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the first local search, including:

[0027] Based on the current number of optimization iterations, generate an adaptively decreasing weight control factor;

[0028] Based on the weight control factor and the optimal hyperparameter vector, the optimal direction search is performed on the hyperparameter vector to obtain the optimal information search term;

[0029] Obtain the center vector of all hyperparameter vectors, and perform a comprehensive directional search on the hyperparameter vectors based on the weight control factor and the center vector to obtain the comprehensive information search item;

[0030] Based on the optimal information search term and the comprehensive information search term, a first local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the first local search.

[0031] Furthermore, for any hyperparameter vector obtained after the first local search, a second local search is performed on the hyperparameter vector using a nonlinear local search strategy based on the optimal hyperparameter vector, to obtain the hyperparameter vector obtained after the second local search, including:

[0032] For any hyperparameter vector after the first local search, obtain the cosine information search term between the hyperparameter vector and the optimal hyperparameter vector;

[0033] Based on the cosine information search term and the weight control factor, a second local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the second local search.

[0034] Furthermore, for the hyperparameter vector after the second local search, a reverse global greedy search strategy is used to perform a first global search on the hyperparameter vector, resulting in the hyperparameter vector after the first global search, including:

[0035] Based on the current number of optimizations, a nonlinear perturbation factor is obtained, and the hyperparameter vector after the second local search is perturbed by the nonlinear perturbation factor to generate a perturbation information vector.

[0036] A reference information vector is generated based on the nonlinear perturbation factor, and a global search is performed on the hyperparameter vector based on the reference information vector and the perturbation information vector to obtain a first global search vector.

[0037] Determine whether the loss function value of the first global search vector decreases. If so, use the first global search vector as the hyperparameter vector after the first global search. Otherwise, use the hyperparameter vector after the original second local search directly as the hyperparameter vector after the first global search.

[0038] Furthermore, for the hyperparameter vector obtained after the first global search, a second global search is performed on the hyperparameter vector using a randomized global greedy search strategy, resulting in the hyperparameter vector obtained after the second global search, including:

[0039] For the hyperparameter vector after the first global search, a random flight individual is generated based on the optimal hyperparameter vector.

[0040] Based on the random flight individuals corresponding to the hyperparameter vector, a second global search is performed on the hyperparameter vector using the cosine function to obtain the second global search vector.

[0041] Determine whether the loss function value of the second global search vector decreases. If so, use the second global search vector as the hyperparameter vector after the second global search. Otherwise, use the original hyperparameter vector after the first global search directly as the hyperparameter vector after the second global search.

[0042] Further, determine whether the optimization termination condition is met, including:

[0043] Determine if the current number of optimization attempts is greater than or equal to the maximum number of optimization attempts. If so, the optimization termination condition is met; otherwise, the optimization termination condition is not met.

[0044] This invention provides a communication performance analysis method based on spatiotemporal frequency resources. It collects spatiotemporal frequency resource types and communication performance analysis indicators, then generates communication performance analysis test tasks based on these indicators. After executing the test tasks, artificial intelligence can be used to learn the relationship between the actual values ​​of the spatiotemporal frequency resource types and the actual values ​​of the communication performance analysis indicators. This allows for predictive analysis of the communication performance indicators based on the actual values ​​of the spatiotemporal frequency resource types in subsequent processes, enabling staff to quickly adjust the allocation of spatiotemporal frequency resources according to needs. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0046] Figure 1 A flowchart illustrating a communication performance analysis method based on spatiotemporal frequency resources provided in an embodiment of the present invention.

[0047] The accompanying drawings have illustrated specific embodiments of the invention, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0049] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0050] like Figure 1 As shown, this embodiment of the invention provides a communication performance analysis method based on spatiotemporal frequency resources, including:

[0051] S1. Obtain the spatiotemporal frequency resource type and communication performance analysis indicators input by the staff, and generate a communication performance analysis test task based on the spatiotemporal frequency resource type and communication performance analysis indicators;

[0052] Spatiotemporal frequency resources refer to the concept of effectively managing and utilizing time, space, and frequency resources in communication and network technologies. These resources are core components of wireless communication and networks, especially in 5G, 6G, and future communication technologies. Spatiotemporal frequency resources often impact communication performance. Therefore, after determining the type of spatiotemporal frequency resources input by the staff, a communication performance analysis test task can be generated based on the value range of that resource type, thereby obtaining the actual values ​​of communication performance analysis indicators.

[0053] S2. Execute the communication performance analysis test task to obtain the actual values ​​corresponding to the time-space-frequency resource types by executing the sample values.

[0054] Communication performance analysis and testing tasks can be combined tests of various spatiotemporal frequency resources. These spatiotemporal frequency resources can be applied to the communication system, and the actual values ​​corresponding to the communication performance analysis indicators can be obtained. By analyzing and learning from these data, the impact of spatiotemporal frequency resources on communication performance can be determined.

[0055] S3. An artificial intelligence model is used to construct a communication performance analysis model. The sample values ​​of the spatiotemporal frequency resource type are used as input, and the actual values ​​of the corresponding communication performance analysis indicators are used as the expected output. The communication performance analysis model is then optimized to obtain the optimized communication performance analysis model.

[0056] Artificial intelligence models are a core component in the field of artificial intelligence (AI). They refer to a collection of algorithms and mathematical models. Therefore, this embodiment of the invention uses artificial intelligence models to construct a communication performance analysis model. Factors can learn the relationship between sample values ​​of spatiotemporal frequency resource types and actual values ​​of communication performance analysis indicators through artificial intelligence.

[0057] S4. Collect the allocation values ​​corresponding to the spatiotemporal frequency resource types, and use the optimized communication performance analysis model to identify the allocation values ​​corresponding to the spatiotemporal frequency resource types to obtain the communication performance analysis results.

[0058] After the communication performance analysis model is optimized, it has the ability to identify the allocation values ​​corresponding to the spatiotemporal frequency resource types. Therefore, after the staff formulates the allocation scheme for spatiotemporal frequency resources, they can conduct a preliminary analysis of the communication performance corresponding to the allocation scheme, which makes it convenient for the staff to optimize the allocation scheme for spatiotemporal frequency resources.

[0059] This invention provides a communication performance analysis method based on spatiotemporal frequency resources. It collects spatiotemporal frequency resource types and communication performance analysis indicators, then generates communication performance analysis test tasks based on these indicators. After executing the test tasks, artificial intelligence can be used to learn the relationship between the actual values ​​of the spatiotemporal frequency resource types and the actual values ​​of the communication performance analysis indicators. This allows for predictive analysis of the communication performance indicators based on the actual values ​​of the spatiotemporal frequency resource types in subsequent processes, enabling staff to quickly adjust the allocation of spatiotemporal frequency resources according to needs.

[0060] In this embodiment of the invention, the spatiotemporal frequency resource type and communication performance analysis indicators input by staff are obtained, and a communication performance analysis test task is generated based on the spatiotemporal frequency resource type and communication performance analysis indicators, including:

[0061] Retrieve the spatiotemporal frequency resource types input by staff; each spatiotemporal frequency resource type has its corresponding upper and lower limits;

[0062] For example, spatiotemporal frequency resources can include transmission rate, beam scheduling, and time allocation, etc. For any communication system, there can be corresponding upper and lower limits for spatiotemporal frequency resources. If the spatiotemporal frequency resources are a few fixed options, then the numerical division points of such spatiotemporal frequency resources are those fixed options. For example, if the spatiotemporal frequency resources are of type A1, A2, and A3, then the numerical division points are A1, A2, and A3.

[0063] Based on the premise that each spatiotemporal frequency resource type has its corresponding upper and lower limits, the numerical interval corresponding to the spatiotemporal frequency resource type is divided into a fixed number of parts using the equal division method, resulting in multiple numerical division points corresponding to each spatiotemporal frequency resource type (e.g., if the transmission rate interval is (B,C), then (B,C) can be divided into N sub-intervals, and each boundary is a numerical division point).

[0064] Arrange and combine multiple numerical division points corresponding to all spatiotemporal frequency resource types to obtain sample values ​​corresponding to multiple spatiotemporal frequency resource types;

[0065] For each spatiotemporal frequency resource type, a task to be executed is generated based on the sample value.

[0066] For example, if there are numerical partitioning points for spatiotemporal frequency resource A as a1 and a2, and numerical partitioning points for spatiotemporal frequency resource B as b1, b2, and b3, then the sample values ​​corresponding to the spatiotemporal frequency resource types can be (a1, b1), (a1, b2), (a1, b3), (a2, b1), (a2, b2), and (a2, b3). Any sample value can be input into the communication system to obtain the actual value of the corresponding communication performance analysis index, thereby obtaining sample data for optimizing the artificial intelligence model.

[0067] In this embodiment of the invention, the communication performance analysis test task is executed to obtain the actual values ​​corresponding to the communication performance analysis indicators by executing sample values ​​corresponding to the spatiotemporal resource types.

[0068] The communication performance analysis test task is executed to use the sample values ​​corresponding to the time, space, and frequency resource types as the control parameters of the communication system to be analyzed, and to obtain the actual values ​​corresponding to the communication performance analysis indicators of the communication system to be analyzed.

[0069] In this embodiment of the invention, the communication performance analysis model is constructed using an artificial intelligence model, including: constructing the communication performance analysis model using a CNN (Convolutional Neural Network) model. It is worth noting that other artificial intelligence models can also be used to construct the communication performance analysis model.

[0070] In this embodiment of the invention, the communication performance analysis model is optimized using sample values ​​of spatiotemporal frequency resource types as input and the actual values ​​of the corresponding communication performance analysis indicators as the expected output, resulting in an optimized communication performance analysis model, including:

[0071] For the hyperparameters of the communication performance analysis model, the hyperparameters are initialized and encoded into vectors to obtain hyperparameter vectors. At the same time, multiple different hyperparameter vectors are obtained.

[0072] For example, the hyperparameters of a communication performance analysis model generally have upper and lower limits, and can be randomly initialized between these limits to obtain a hyperparameter vector.

[0073] For any hyperparameter vector, using sample values ​​of spatiotemporal frequency resource types as input and the actual values ​​of the corresponding communication performance analysis indicators as the expected output, the loss function value corresponding to the hyperparameter vector can be obtained; for example, the root mean square error function value or the cross-entropy error function value can be obtained.

[0074] The optimal hyperparameter vector is determined based on the loss function values ​​corresponding to all hyperparameter vectors.

[0075] For any hyperparameter vector, based on the optimal hyperparameter vector, a first local search is performed on the hyperparameter vector using a local personalized search strategy to obtain the hyperparameter vector after the first local search.

[0076] For any hyperparameter vector obtained after the first local search, a second local search is performed on the hyperparameter vector based on the optimal hyperparameter vector using a nonlinear local search strategy to obtain the hyperparameter vector obtained after the second local search.

[0077] For the hyperparameter vector after the second local search, a reverse global greedy search strategy is used to perform a first global search on the hyperparameter vector to obtain the hyperparameter vector after the first global search.

[0078] For the hyperparameter vector after the first global search, a random global greedy search strategy is used to perform a second global search on the hyperparameter vector to obtain the hyperparameter vector after the second global search.

[0079] Determine whether the optimization termination condition is met. If so, re-obtain the optimal hyperparameter vector based on the hyperparameter vector after the second global search, and apply the parameters in the optimal hyperparameter vector to the communication performance analysis model to obtain the optimized communication performance analysis model. Otherwise, return to the step of obtaining the loss function value.

[0080] In existing technologies, gradient descent algorithms are often used to optimize the hyperparameters of artificial intelligence models, but this often suffers from the problem of easily getting trapped in local optima. Therefore, this invention provides an intelligent optimization algorithm to solve the technical problems existing in the prior art and improve the predictive ability of communication performance.

[0081] In this embodiment of the invention, for any hyperparameter vector, based on the optimal hyperparameter vector, a first local search is performed on the hyperparameter vector using a local personalized search strategy to obtain the hyperparameter vector after the first local search, including:

[0082] Based on the current number of optimization iterations, the adaptively decreasing weight control factor is generated as follows: Where ω represents the weight control factor, π represents pi, sin represents the sine function, T represents the maximum number of optimizations, and t represents the current number of optimizations;

[0083] Based on the weight control factor and the optimal hyperparameter vector, an optimal direction search is performed on the hyperparameter vector to obtain the optimal information search term: in, Let Δ represent the i-th hyperparameter vector in the t-th optimization process, where i = 1, 2, ..., I, and I represents the total number of hyperparameter vectors. best Let r1 represent the optimal information search term, and r1 represent a random number between (0,1). Represents the optimal hyperparameter vector;

[0084] Obtain the center vector of all hyperparameter vectors (i.e., the vector composed of the mean of each dimension), and perform a comprehensive directional search on the hyperparameter vectors based on the weight control factor and the center vector to obtain the comprehensive information search term: Where, Δ zx This represents a comprehensive information search term, where r2 represents a random number between (0,1). Represents the center vector of all hyperparameter vectors;

[0085] Based on the optimal information search term and the comprehensive information search term, a first local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the first local search: in, Represents the hyperparameter vector after the first local search.

[0086] The local personalized search strategy provided in this embodiment of the invention can maintain the diversity of hyperparameter vectors during the algorithm search process, thereby effectively avoiding the algorithm from getting stuck in local optima. At the same time, learning from the optimal hyperparameter vector can effectively improve the convergence speed of the algorithm. In the later stage of the algorithm, the weight control factor decreases nonlinearly, which can gradually improve the convergence accuracy of the algorithm.

[0087] In this embodiment of the invention, for any hyperparameter vector obtained after a first local search, a second local search is performed on the hyperparameter vector using a nonlinear local search strategy based on the optimal hyperparameter vector to obtain the hyperparameter vector after the second local search, including:

[0088] For any hyperparameter vector obtained after the first local search, the search term for obtaining the cosine information between the hyperparameter vector and the optimal hyperparameter vector is: Where r4 represents a random number between (0,1), and r5 represents a random number between (0,1). Let represent the hyperparameter vector after the j-th first local search, where j = 1, 2, ..., I;

[0089] Based on the cosine information search term and the weight control factor, a second local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the second local search: in, Represents the hyperparameter vector after the second local search.

[0090] The nonlinear local search strategy provided in this invention can enable all hyperparameter vectors to perform a nonlinear search around the optimal position, which can effectively improve the convergence speed and convergence accuracy of the algorithm.

[0091] In this embodiment of the invention, for the hyperparameter vector after the second local search, a reverse global greedy search strategy is used to perform a first global search on the hyperparameter vector to obtain the hyperparameter vector after the first global search, including:

[0092] Based on the current number of optimization iterations, the nonlinear perturbation factor is obtained as follows: Where δ represents the nonlinear perturbation factor, and T represents the preset maximum number of optimization attempts;

[0093] Furthermore, for the hyperparameter vector after the second local search, a nonlinear perturbation factor is used to perturb the hyperparameter vector, generating a perturbation information vector as follows: in, Let n = 1, 2, ..., I, and denote the hyperparameter vector after the nth second local search in the t-th optimization process. Represents the disturbance information vector;

[0094] A reference information vector is generated based on the nonlinear perturbation factor, and a global search is performed on the hyperparameter vector based on the reference information vector and the perturbation information vector to obtain the first global search vector: Where r6 represents a random number between (0,1), lb represents the upper bound vector corresponding to the hyperparameter vector, and ub represents the lower bound vector corresponding to the hyperparameter vector. Represents the first global search vector;

[0095] Determine whether the loss function value of the first global search vector decreases. If so, use the first global search vector as the hyperparameter vector after the first global search. Otherwise, use the hyperparameter vector after the original second local search directly as the hyperparameter vector after the first global search.

[0096] The reverse global greedy search strategy provided in this embodiment of the invention can perform reverse search on each hyperparameter vector, thereby improving the search efficiency of unknown regions and effectively improving the traversability of the solution space, thus avoiding getting trapped in local optima.

[0097] In this embodiment of the invention, for the hyperparameter vector after the first global search, a random global greedy search strategy is used to perform a second global search on the hyperparameter vector to obtain the hyperparameter vector after the second global search, including:

[0098] Given the hyperparameter vector after the first global search, a random flight individual is generated based on the optimal hyperparameter vector: in, Indicates a randomly flying individual. Indicates except Other random individuals, Let represent the hyperparameter vector after the m-th first global search in the t-th optimization process, where m = 1, 2, ..., I, α represents the random flight coefficient, u represents the first normally distributed random number, v represents the second normally distributed random number, and β represents the constant term;

[0099] Based on the random flight individuals corresponding to the hyperparameter vectors, a second global search is performed on the hyperparameter vectors using the cosine function, resulting in the second global search vector: in, Let r7 represent the second global search vector, r8 represent the random number between (0,1), and π represent the mathematical constant pi.

[0100] Determine whether the loss function value of the second global search vector decreases. If so, use the second global search vector as the hyperparameter vector after the second global search. Otherwise, use the original hyperparameter vector after the first global search directly as the hyperparameter vector after the second global search.

[0101] The second global search provided in this embodiment of the invention can enable the algorithm to effectively escape local optima, providing powerful global search capabilities, thereby improving hyperparameter search capabilities.

[0102] Optionally, after each search of the hyperparameter vector, out-of-bounds handling can be performed on the hyperparameter vector to ensure the effectiveness of the algorithm.

[0103] In this embodiment of the invention, determining whether the optimization termination condition is met includes:

[0104] Determine if the current number of optimization attempts is greater than or equal to the maximum number of optimization attempts. If so, the optimization termination condition is met; otherwise, the optimization termination condition is not met.

[0105] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. It should be understood that the invention is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A communication performance analysis method based on spatiotemporal frequency resources, characterized in that, include: The system obtains the spatiotemporal frequency resource types and communication performance analysis indicators input by the staff, and generates a communication performance analysis test task based on the spatiotemporal frequency resource types and communication performance analysis indicators. The communication performance analysis test task is executed to obtain the actual values ​​corresponding to the communication performance analysis indicators by executing the sample values ​​corresponding to the spatiotemporal resource types. An artificial intelligence model is used to construct a communication performance analysis model. The model is optimized by taking the sample values ​​of spatiotemporal frequency resource types as input and the actual values ​​of the corresponding communication performance analysis indicators as expected output. The allocation values ​​corresponding to the spatiotemporal frequency resource types are collected, and the optimized communication performance analysis model is used to identify the allocation values ​​corresponding to the spatiotemporal frequency resource types to obtain the communication performance analysis results. Using sample values ​​of spatiotemporal frequency resource types as input and the actual values ​​of the corresponding communication performance analysis indicators as the expected output, the communication performance analysis model is optimized to obtain the optimized communication performance analysis model, including: For the hyperparameters of the communication performance analysis model, the hyperparameters are initialized and encoded into vectors to obtain hyperparameter vectors. At the same time, multiple different hyperparameter vectors are obtained. For any hyperparameter vector, take the sample values ​​of the spatiotemporal frequency resource type as input and the actual values ​​of the corresponding communication performance analysis indicators as the expected output to obtain the loss function value corresponding to the hyperparameter vector. The optimal hyperparameter vector is determined based on the loss function values ​​corresponding to all hyperparameter vectors. For any hyperparameter vector, based on the optimal hyperparameter vector, a first local search is performed on the hyperparameter vector using a local personalized search strategy to obtain the hyperparameter vector after the first local search. For any hyperparameter vector obtained after the first local search, a second local search is performed on the hyperparameter vector based on the optimal hyperparameter vector using a nonlinear local search strategy to obtain the hyperparameter vector obtained after the second local search. For the hyperparameter vector after the second local search, a reverse global greedy search strategy is used to perform a first global search on the hyperparameter vector to obtain the hyperparameter vector after the first global search. For the hyperparameter vector after the first global search, a random global greedy search strategy is used to perform a second global search on the hyperparameter vector to obtain the hyperparameter vector after the second global search. Determine whether the optimization termination condition is met. If so, re-obtain the optimal hyperparameter vector based on the hyperparameter vector after the second global search, and apply the parameters in the optimal hyperparameter vector to the communication performance analysis model to obtain the optimized communication performance analysis model. Otherwise, return to the step of obtaining the loss function value.

2. The communication performance analysis method based on spatiotemporal frequency resources according to claim 1, characterized in that, The system acquires the spatiotemporal frequency resource types and communication performance analysis indicators input by staff, and generates a communication performance analysis test task based on the spatiotemporal frequency resource types and communication performance analysis indicators, including: Retrieve the spatiotemporal frequency resource types input by staff; each spatiotemporal frequency resource type has its corresponding upper and lower limits; Based on the premise that each spatiotemporal frequency resource type has its corresponding upper and lower limits, the numerical interval corresponding to the spatiotemporal frequency resource type is divided into a fixed number of parts using the equal division method, resulting in multiple numerical division points corresponding to each spatiotemporal frequency resource type. Arrange and combine multiple numerical division points corresponding to all spatiotemporal frequency resource types to obtain sample values ​​corresponding to multiple spatiotemporal frequency resource types; For each spatiotemporal frequency resource type, a task to be executed is generated based on the sample value.

3. The communication performance analysis method based on spatiotemporal frequency resources according to claim 1, characterized in that, Executing the communication performance analysis test task involves executing sample values ​​corresponding to the spatiotemporal frequency resource types to obtain the actual values ​​corresponding to the communication performance analysis indicators, including: The communication performance analysis test task is executed to use the sample values ​​corresponding to the time, space, and frequency resource types as the control parameters of the communication system to be analyzed, and to obtain the actual values ​​corresponding to the communication performance analysis indicators of the communication system to be analyzed.

4. The communication performance analysis method based on spatiotemporal frequency resources according to claim 1, characterized in that, Artificial intelligence models are used to construct communication performance analysis models, including: using CNN models to construct communication performance analysis models.

5. The communication performance analysis method based on spatiotemporal frequency resources according to claim 1, characterized in that, For any hyperparameter vector, based on the optimal hyperparameter vector, and using a local personalized search strategy, a first local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the first local search, including: Based on the current number of optimization iterations, generate an adaptively decreasing weight control factor; Based on the weight control factor and the optimal hyperparameter vector, the optimal direction search is performed on the hyperparameter vector to obtain the optimal information search term; Obtain the center vector of all hyperparameter vectors, and perform a comprehensive directional search on the hyperparameter vectors based on the weight control factor and the center vector to obtain the comprehensive information search item; Based on the optimal information search term and the comprehensive information search term, a first local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the first local search.

6. The communication performance analysis method based on spatiotemporal frequency resources according to claim 5, characterized in that, For any hyperparameter vector obtained after the first local search, a second local search is performed on the hyperparameter vector based on the optimal hyperparameter vector using a nonlinear local search strategy, resulting in a hyperparameter vector obtained after the second local search, including: For any hyperparameter vector after the first local search, obtain the cosine information search term between the hyperparameter vector and the optimal hyperparameter vector; Based on the cosine information search term and the weight control factor, a second local search is performed on the hyperparameter vector to obtain the hyperparameter vector after the second local search.

7. The communication performance analysis method based on spatiotemporal frequency resources according to claim 6, characterized in that, For the hyperparameter vector after the second local search, a reverse global greedy search strategy is used to perform a first global search on the hyperparameter vector, resulting in the hyperparameter vector after the first global search, including: Based on the current number of optimizations, a nonlinear perturbation factor is obtained, and the hyperparameter vector after the second local search is perturbed by the nonlinear perturbation factor to generate a perturbation information vector. A reference information vector is generated based on the nonlinear perturbation factor, and a global search is performed on the hyperparameter vector based on the reference information vector and the perturbation information vector to obtain a first global search vector. Determine whether the loss function value of the first global search vector decreases. If so, use the first global search vector as the hyperparameter vector after the first global search. Otherwise, use the hyperparameter vector after the original second local search directly as the hyperparameter vector after the first global search.

8. The communication performance analysis method based on spatiotemporal frequency resources according to claim 7, characterized in that, For the hyperparameter vector obtained after the first global search, a second global search is performed using a randomized global greedy search strategy to obtain the hyperparameter vector after the second global search, including: For the hyperparameter vector after the first global search, a random flight individual is generated based on the optimal hyperparameter vector. Based on the random flight individuals corresponding to the hyperparameter vector, a second global search is performed on the hyperparameter vector using the cosine function to obtain the second global search vector. Determine whether the loss function value of the second global search vector decreases. If so, use the second global search vector as the hyperparameter vector after the second global search. Otherwise, use the original hyperparameter vector after the first global search directly as the hyperparameter vector after the second global search.

9. The communication performance analysis method based on spatiotemporal frequency resources according to claim 1, characterized in that, Determine whether the optimization termination conditions are met, including: Determine if the current number of optimization attempts is greater than or equal to the maximum number of optimization attempts. If so, the optimization termination condition is met; otherwise, the optimization termination condition is not met.

Images