Signal optimization method and device, computer equipment and storage medium

Abstract

The invention discloses a signal optimization method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining an initial signal, and dividing an available frequency band of the initial signal into a plurality of sub-frequency bands; according to an interference evaluation model, obtaining interference degrees between different sub-frequency bands, and obtaining an interference evaluation result; dynamically adjusting a frequency range corresponding to each sub-band according to the interference evaluation result; wherein the interference evaluation model is constructed based on a support vector machine and / or a random forest. Therefore, a new signal optimization strategy can be provided, and the signals can be dynamically allocated to adapt to a dynamically changing signal environment.

Description

Technical Field

[0001] The present application belongs to the field of communication technology, and in particular, relates to a signal optimization method and device, computer equipment, and storage medium. Background Art

[0002] In urban environments with dense high-rise buildings, signal confusion is a common problem, especially in the field of wireless communications. With the rapid development of wireless communication technology, spectrum resources are becoming increasingly scarce, and the overlap of different signal sources in the same frequency band is becoming increasingly serious, resulting in signal interference and affecting communication quality.

[0003] In the prior art, frequency band allocation mostly adopts a static allocation method, which is difficult to adapt to the dynamically changing signal environment.

[0004] Therefore, a new signal optimization strategy is urgently needed to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects, the present application provides a new signal optimization strategy, which can dynamically allocate signals to adapt to the dynamically changing signal environment.

[0006] To solve the above problems, in the first aspect, the present application provides a signal optimization method, which includes: obtaining an initial signal, and dividing the available frequency band of the initial signal into multiple sub-frequency bands; obtaining the degree of interference between different sub-frequency bands according to an interference assessment model to obtain an interference assessment result; according to the interference assessment result, dynamically adjusting the frequency range corresponding to each sub-frequency band; wherein the interference assessment model is constructed based on a support vector machine and / or a random forest.

[0007] In an optional embodiment, dynamically adjusting the frequency range corresponding to each of the sub-frequency bands according to the interference assessment result includes: calculating the total interference degree of the plurality of sub-frequency bands; dynamically adjusting the frequency range corresponding to each sub-frequency band so that the value corresponding to the total interference degree is minimized; the total interference degree A is obtained based on the following formula: Where M is the number of sub-bands, I ij is the degree of interference between the i-th sub-band and the j-th sub-band.

[0008] In an optional embodiment, the dynamic adjustment of the frequency range corresponding to each of the sub-frequency bands includes: generating an initial population, each individual in the initial population represents a frequency band allocation scheme; obtaining a fitness function, and evaluating each of the individuals according to the fitness function; performing genetic operations on the initial population to obtain a next-generation population, and using the next-generation population as the initial population; repeatedly performing the genetic operation on the initial population to obtain the next-generation population until an optimal solution to the fitness function is obtained; obtaining the individual corresponding to the optimal solution as the adjusted frequency range of each of the sub-frequency bands; wherein the fitness function is determined based on minimizing interference and / or maximizing communication quality.

[0009] In an optional embodiment, the frequency range corresponding to each of the sub-frequency bands is dynamically adjusted based on a reinforcement learning model, and the reinforcement learning model is constructed based on the following steps: defining a state space, wherein the state in the state space includes at least one of the following: current frequency band allocation, signal strength, and interference level; defining an action space, wherein the actions in the action space include strategies for adjusting frequency band allocation; defining a reward function, wherein the reward function is used to evaluate the pros and cons of each of the actions; and constructing the reinforcement learning model using a reinforcement learning algorithm.

[0010] In an optional embodiment, the reward function R(s,a) can be expressed as the following formula:

[0011] R(s,a)=γ×(L0–L1)+δ×(B1–B0);

[0012] Among them, γ and δ are weight coefficients, L0 is the current interference level, L1 is the adjusted interference level, B1 is the adjusted communication quality score, and B0 is the current communication quality score.

[0013] In an optional embodiment, the frequency range corresponding to each of the sub-frequency bands is dynamically adjusted based on at least one of the following principles: preferentially adjusting the sub-frequency bands with interference levels higher than a threshold; ensuring that the bandwidth requirements of each of the sub-frequency bands are met; and using a smooth transition strategy for dynamic adjustment.

[0014] In an optional embodiment, the interference assessment model obtains the degree of interference between different sub-frequency bands according to a target feature, and the target feature includes at least one of the following: average signal strength, interference frequency, and signal fluctuation range.

[0015] In the second aspect, the present application provides a signal optimization device, which includes: a signal division module, used to obtain an initial signal and divide the available frequency band of the initial signal into multiple sub-frequency bands; an interference assessment module, used to obtain the degree of interference between different sub-frequency bands according to an interference assessment model to obtain an interference assessment result; an adjustment module, used to dynamically adjust the frequency range corresponding to each sub-frequency band according to the interference assessment result; wherein the interference assessment model is constructed based on a support vector machine and / or a random forest.

[0016] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the program can implement the steps of any one of the above methods when executed by the processor.

[0017] In a fourth aspect, the present application also provides a storage medium for storing a computer program, which, when executed by a computer or a processor, implements the steps of any of the methods described above.

[0018] Compared with the prior art, the technical solution of the embodiment of the present application has the following beneficial effects:

[0019] The signal optimization method of the embodiment of the present application can construct an interference assessment model through a support vector machine and / or a random forest, analyze the signal mixing degree of each sub-frequency band in the initial signal in real time and accurately, accurately identify the frequency band with serious signal mixing, and provide a reliable basis for subsequent frequency band optimization allocation. This can provide a new signal optimization strategy that can dynamically allocate signals to adapt to dynamically changing signal environments.

[0020] Furthermore, dynamic adjustment can reduce signal interference and optimize spectrum resource utilization, thereby improving user communication experience and network performance. The technical solution of the present invention can not only effectively cope with complex and changeable signal environments, but also provide strong support for the development of future intelligent wireless communication systems.

[0021] Furthermore, intelligent scheduling algorithms can be introduced to optimize the frequency band allocation strategy. Specific algorithms include: genetic algorithm, reinforcement learning, and continuous learning environment feedback to adjust the frequency band allocation strategy and improve communication quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of a flow chart of a signal optimization method according to an embodiment of the present application;

[0023] Figure 2 A schematic diagram of a flow chart of a signal optimization solution for a signal optimization scenario of a high-rise building in a commercial area according to an embodiment of the present application;

[0024] Figure 3 for Figure 1A flowchart of a specific embodiment of step S103;

[0025] Figure 4 A schematic diagram of a process for constructing a reinforcement learning model according to an embodiment of the present application;

[0026] Figure 5 A schematic diagram of the structure of a signal optimization device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] As mentioned in the background technology, the technical problem to be solved by the present application is how to provide a new signal optimization strategy that can dynamically allocate signals to adapt to the dynamically changing signal environment.

[0028] In addition, traditional frequency band management methods lack intelligent scheduling mechanisms and cannot effectively optimize spectrum resource utilization. These problems not only reduce user experience, but also limit the overall performance improvement of wireless communication systems. Therefore, how to solve the high-level signal mixing problem through dynamic frequency allocation technology has become an important issue that needs to be solved in the current wireless communication field.

[0029] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods and effects of the signal optimization method and device, computer equipment, and storage medium proposed in the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0030] First, see Figure 1 The present application provides a signal optimization method, which may include the following steps S101 to S103, each of which is described in detail as follows.

[0031] Step S101: acquiring an initial signal, and dividing an available frequency band of the initial signal into a plurality of sub-frequency bands.

[0032] An optional embodiment for the initial signal is provided below. The initial signal can be collected by a deployed signal monitoring device.

[0033] For complex environments with dense high-rise buildings, signal monitoring equipment with high sensitivity and wide-band coverage capabilities can be selected, such as spectrum analyzers, Wireless Sensor Networks (WSN), etc.

[0034] Furthermore, the signal monitoring equipment collects key data such as signal strength, interference level, signal-to-noise ratio (SNR) of each frequency band in real time. The collection frequency can be set to once per second to ensure the real-time and accuracy of the data.

[0035] Furthermore, these devices are deployed on different floors and key locations (such as rooftops and near windows) of high-rise buildings to ensure full coverage of the monitoring area.

[0036] The following provides another optional embodiment for the initial signal, wherein the initial signal may be a signal obtained by preprocessing the signal collected by the signal detection device, and the preprocessing may include at least one of the following: removing outliers; removing noise interference; standardizing the data format of the signal to ensure the consistency and comparability of the data; and dividing the signal.

[0037] In an optional embodiment of step S101, the available frequency band of the initial signal is divided into a plurality of sub-frequency bands, each of which corresponds to a specific signal source or device type. The division is based on the transmission characteristics, bandwidth requirements, and interference characteristics of the signal source. Further, an initial frequency range can be allocated to each sub-frequency band based on historical data and preliminary analysis to ensure preliminary frequency isolation.

[0038] For example, in the signal optimization scenario of high-rise buildings in commercial areas, the available frequency band of the initial signal is 2.4GHZ, which is divided into four sub-bands corresponding to different types of wireless devices, such as Wi-Fi, Bluetooth, Zigbee, etc. The initial frequency range is set as: sub-band 1 (2.4GHz to 2.412GHz), sub-band 2 (2.412GHz to 2.424GHz), sub-band 3 (2.424GHz to 2.436GHz), sub-band 4 (2.436GHz to 2.448GHz).

[0039] Step S102: Obtain the interference levels between the different sub-frequency bands according to the interference assessment model to obtain an interference assessment result.

[0040] Among them, the interference assessment model can be constructed based on a support vector machine (SVM) and / or a random forest (RF), so that the law of signal mixing can be learned through training data.

[0041] Step S103: dynamically adjusting the frequency range corresponding to each of the sub-frequency bands according to the interference evaluation result.

[0042] In an optional embodiment, the input of the interference assessment model can be characteristic parameters of multiple sub-frequency band signals, and the output is a signal confusion degree score of each sub-frequency band, and the score is used as the interference assessment result. Thus, the sub-frequency band with severe confusion can be identified according to the signal confusion degree score, and the higher the signal confusion degree score, the more severe the confusion.

[0043] Furthermore, a threshold may be set, and when the signal confusion score of a certain sub-frequency band exceeds the threshold, the sub-frequency band is marked as a frequency band that needs to be optimized.

[0044] pass Figure 1 The signal optimization method can construct an interference assessment model through support vector machines and / or random forests, analyze the signal mixing degree of each sub-band in the initial signal in real time and accurately, accurately identify the frequency bands with serious signal mixing, and provide a reliable basis for subsequent frequency band optimization allocation. Furthermore, dynamic adjustment can reduce signal interference and optimize spectrum resource utilization, thereby improving user communication experience and network performance. The technical solution of the present invention can not only effectively cope with complex and changeable signal environments, but also provide strong support for the development of future intelligent wireless communication systems.

[0045] In an optional embodiment, the interference assessment model obtains the degree of interference between different sub-frequency bands according to a target feature, and the target feature includes at least one of the following: average signal strength, interference frequency, and signal fluctuation range.

[0046] Specifically, characteristic parameters of the signal data of each sub-frequency may be extracted, such as average signal strength, interference frequency, signal fluctuation range, etc.

[0047] The signal strength mean calculation formula is as follows (1):

[0048]

[0049] represents the mean signal strength; S i represents the signal strength of the i-th acquisition; N represents the number of acquisitions.

[0050] The signal fluctuation range calculation formula is as follows (2):

[0051] ΔS=S max -S min (2)

[0052] ΔS represents the signal fluctuation range; S max and S min Represent the maximum and minimum signal strengths respectively.

[0053] The interference assessment model can be expressed as the following formula (3):

[0054]

[0055] Score represents the signal confounding score; It represents the mean or average index of a variable; ΔS represents the change of the variable, that is, the difference between the maximum and minimum values; f represents the model function; SNR is the signal-to-noise ratio, which is usually used to evaluate signal quality or data reliability.

[0056] In addition, sliding window technology is also used to calculate statistical data within a certain time window, such as mean and variance, which can also be used as target features.

[0057] In a specific example, the above signal optimization method is applied to the signal optimization scenario of high-rise buildings in commercial areas, which may include: Figure 2 Several steps in:

[0058] S201, equipment deployment. In a 30-story building in a commercial area, a spectrum analyzer is deployed every 5 floors, with one on the roof and one on the ground floor, for a total of 7 devices.

[0059] S202, data collection. The device collects signal data once per second for 24 hours, and obtains 86,400 sets of data.

[0060] S203, data preprocessing. Remove obviously abnormal data points, such as records where the signal strength suddenly drops to zero. Standardize the data format and use the unified unit of decibel milliwatt (dBm).

[0061] S204, target feature extraction. Calculate the signal intensity mean and fluctuation range within each 10-minute window. Extract target features such as signal-to-noise ratio.

[0062] S205, signal congestion identification. Use the random forest model, input feature parameters, and output a signal congestion score; set the threshold to 0.7, and mark the frequency bands with a score exceeding 0.7 as frequency bands that need to be optimized.

[0063] S206, dynamic frequency band adjustment. According to the identification results, the frequency band allocation strategy is adjusted to give priority to optimizing the frequency bands with high scores. Through the real-time feedback mechanism, the optimization effect is verified and the strategy is further adjusted.

[0064] Through the above scheme, signal monitoring equipment is deployed to collect data such as signal strength and interference level of each frequency band in real time; big data analysis technology is used to process the collected signal data and identify the frequency bands with serious signal congestion. As a result, a dynamic frequency allocation method can be provided to solve the signal congestion problem in a high-rise building dense environment, systematically monitor and analyze signal data, accurately identify the frequency bands with serious signal congestion, provide a reliable basis for subsequent frequency band optimization allocation, and improve the quality of wireless communication.

[0065] In an alternative embodiment, see again Figure 1In step S103, dynamically adjusting the frequency range corresponding to each of the sub-frequency bands according to the interference evaluation result includes: calculating the total interference degree of the plurality of sub-frequency bands; dynamically adjusting the frequency range corresponding to each of the sub-frequency bands so that the value corresponding to the total interference degree is minimized; wherein the total interference degree A is obtained based on the following formula (4):

[0066]

[0067] Where M is the number of sub-bands, I ij is the degree of interference between the i-th sub-band and the j-th sub-band.

[0068] Optionally, the interference degree I between the sub-bands in formula (4) is ij It can be calculated based on the following formula (5):

[0069]

[0070] Among them, S ik and S jk They represent the signal strength of sub-bands i and j at the kth sampling time, and N represents the number of sampling times.

[0071] For example, the interference level between sub-band 1 and sub-band 2 is calculated as follows:

[0072]

[0073] Optionally, an interference matrix between sub-frequency bands may be constructed, where the matrix elements are the interference degrees between the sub-frequency bands.

[0074] It should be noted that the minimum value corresponding to the total interference level is a dynamic adjustment target shown in the present application, and the dynamic adjustment target achieved by dynamically adjusting the frequency range corresponding to each of the sub-frequency bands in step S103 may also be set to other values ​​as needed.

[0075] In an optional embodiment, the frequency range corresponding to each of the sub-frequency bands is dynamically adjusted based on at least one of the following principles: preferentially adjusting the sub-frequency bands with interference levels higher than a threshold, thereby reducing signal overlap and minimizing interference; ensuring that the bandwidth requirements of each of the sub-frequency bands are met, avoiding insufficient bandwidth due to frequency adjustment, and ensuring bandwidth; and using a smooth transition strategy for dynamic adjustment. During the adjustment process, a smooth transition strategy is used to avoid signal interruption caused by frequency mutations.

[0076] In an alternative embodiment, see Figure 3 , Figure 3 for Figure 1The flowchart of a specific embodiment of step S103 in step S103 is shown in FIG. The step S103 dynamically adjusting the frequency range corresponding to each of the sub-frequency bands may include the following steps S301 to S305, each of which is described in detail as follows.

[0077] Step S301: generating an initial population, wherein each individual in the initial population represents a frequency band allocation scheme.

[0078] Optionally, the individual encoding method may be binary or real number encoding. The size of the initial population may be set to N, for example, N=100.

[0079] Step S302, obtaining a fitness function, and evaluating each individual according to the fitness function.

[0080] The fitness function is determined based on minimizing interference and / or maximizing communication quality, and can be used to evaluate the quality of each individual.

[0081] In a specific example, the fitness function F of each individual can be expressed as the following formula (6):

[0082]

[0083] Among them, α and β are weight coefficients, which are adjusted according to actual needs; the total interference degree can be obtained based on the above formula (4); the communication quality score represents the comprehensive communication quality index.

[0084] Step S303, performing genetic operations on the initial population to obtain a next generation population, and using the next generation population as the initial population.

[0085] The genetic operation may include at least one of a selection operation, a crossover operation and a mutation operation.

[0086] The selection operation specifically involves selecting excellent individuals based on the fitness function. Common selection methods include roulette selection, tournament selection, etc. The crossover operation specifically involves randomly selecting two individuals for crossover to generate new offspring individuals. The crossover rate is set to P c , for example, P c =0.8. The mutation operation refers to the random mutation of individuals to increase population diversity. The mutation rate is set to P m , for example P m =0.1.

[0087] Step S304, repeatedly performing the step of performing genetic operations on the initial population to obtain the next generation population, until the optimal solution of the fitness function is obtained.

[0088] Step S303 and step S304 include multiple iterations, each iteration performs genetic operations based on the current population to obtain the next generation population, wherein the first current population is set as the initial population. The number of iterations can be set to G, for example, G = 200. Each iteration includes operations such as selection, crossover, and mutation.

[0089] Step S305: obtaining the individual corresponding to the optimal solution as the adjusted frequency range of each sub-frequency band.

[0090] Figure 3 A solution is provided to dynamically adjust the frequency range corresponding to the sub-band using a genetic algorithm (GA). The genetic algorithm gradually optimizes the frequency band allocation scheme by simulating natural selection and genetic mechanisms. Its core idea is to use population iteration and genetic operations (selection, crossover, mutation) to search for the optimal solution. The genetic algorithm is suitable for multi-objective optimization problems and can find a better frequency band allocation scheme in a complex signal environment.

[0091] The following shows a Figure 3 Application of signal optimization scheme in high-rise buildings in commercial areas: Generate initial population, generate 100 random frequency band allocation schemes, each scheme is an individual in the initial population; design fitness function, weight coefficient α=0.6, β=0.4; perform 200 iterations, and perform selection, crossover and mutation operations in each iteration. Finally, the optimal frequency band allocation scheme is obtained to reduce signal interference.

[0092] In an alternative embodiment, Figure 1 Step S103 specifically includes: dynamically adjusting the frequency range corresponding to each of the sub-frequency bands based on the reinforcement learning model. Figure 4 , wherein the reinforcement learning model can be constructed based on the following steps S401 to S404, and each step is described in detail as follows.

[0093] Step S401, defining a state space, where the state in the state space includes at least one of the following: current frequency band allocation, signal strength, and interference level.

[0094] Example of state vector S: S = [f1,f2,…,f M ,S1,S2,…,S M ,I1,I2,…,I M ], where f i represents the frequency of the ith sub-band, S i Indicates the signal strength of the i-th sub-band, I i represents the interference level of the i-th sub-band.

[0095] Step S402: defining an action space, where the actions in the action space include strategies for adjusting frequency band allocation.

[0096] Action a example: a=[a1,a2,…,a M ], where a i Indicates the frequency adjustment amount for the i-th sub-band.

[0097] Step S403: defining a reward function, wherein the reward function is used to evaluate the quality of each of the actions.

[0098] Among them, the reward function can be defined as a comprehensive indicator of signal interference reduction and communication quality improvement.

[0099] In a specific embodiment, the reward function R can be expressed as the following formula (7):

[0100] R(s,a)=γ×(L0 –L1 )+δ×(B1 –B0 ) (7)

[0101] Among them, γ and δ are weight coefficients, L0 is the current interference level, L1 is the adjusted interference level, B1 is the adjusted communication quality score, and B0 is the current communication quality score. Furthermore, the current interference level and the adjusted interference level represent the interference level before and after the adjustment, respectively. The current communication quality score and the adjusted communication quality score represent the communication quality before and after the adjustment, respectively.

[0102] Step S404: construct the reinforcement learning model using a reinforcement learning (RL) algorithm.

[0103] Among them, the appropriate reinforcement learning algorithm can be selected, such as Q-learning, Deep Q-Network (DQN), Policy Gradient, etc. Taking DQN as an example, a neural network model is constructed, a state vector is input, and an action value function is output.

[0104] Specifically, during the training process of the reinforcement learning algorithm, the number of learning times L is set, for example, L = 1000. Each time the learning process selects an action according to the current state, observes the environmental feedback, and updates the parameters of the reinforcement learning model. The optimal strategy is recorded as the final frequency band allocation strategy.

[0105] Reinforcement learning learns the optimal strategy through the interaction between the agent and the environment. The agent continuously adjusts its behavior based on environmental feedback (rewards or penalties) to maximize the long-term cumulative rewards. Figure 4 The constructed reinforcement learning model can be applied to decision-making problems in dynamic environments and can dynamically adjust the frequency band allocation strategy based on real-time feedback.

[0106] The following shows a construction Figure 4 A specific example of a reinforcement learning model: define the state space and action space, where the state vector includes frequency band allocation, signal strength, interference level, etc.; design a reward function with weight coefficients γ = 0.7 and δ = 0.3; use the DQN algorithm to build a neural network model and perform 1,000 learning cycles; and finally obtain the optimal frequency band allocation strategy to improve communication quality.

[0107] In an optional embodiment, the signal optimization method of the present application may also include an update mechanism, which may include: establishing a real-time feedback mechanism to collect user communication quality feedback, and further optimizing the scheme for dynamically adjusting the frequency range corresponding to each of the sub-frequency bands; regularly iterating and updating the scheme for dynamically adjusting the frequency range corresponding to each of the sub-frequency bands to ensure that the system adapts to the ever-changing signal environment.

[0108] In a specific embodiment, the construction of the real-time feedback mechanism may include the following steps:

[0109] Step 1: Building feedback channels. This may include at least one of the following:

[0110] A user-friendly feedback interface can be developed to allow users to report communication problems such as weak signal, dropped calls, network delays, etc.; an automatic monitoring system can be deployed to track network performance indicators in real time, such as download speed, upload speed, connection stability, etc.; a data analysis platform can be established to integrate user feedback and network performance data for comprehensive analysis.

[0111] Step 2, feedback data processing, which may include data cleaning and / or data classification. Data cleaning refers to cleaning the collected feedback data to remove irrelevant information and erroneous data. Data classification refers to classifying the feedback data into categories such as signal problems, connection problems, speed problems, etc., for targeted analysis.

[0112] Step 3, feedback data analysis, can specifically include statistical analysis and / or correlation analysis. Statistical analysis of feedback data can identify patterns and trends of communication quality issues; correlation analysis refers to analyzing the relationship between feedback data and frequency band allocation strategies to identify policy factors that may cause problems.

[0113] In a specific embodiment, the periodic iterative update may include the steps of policy evaluation, policy optimization and iterative update.

[0114] Among them, strategy evaluation includes effect evaluation and problem identification. Effect evaluation refers to evaluating the communication effect of the current frequency band allocation strategy, including indicators such as signal quality, connection stability, and data transmission rate. Problem identification refers to identifying problems and deficiencies in the strategy based on feedback analysis results.

[0115] Strategy optimization includes parameter adjustment and algorithm optimization. Parameter adjustment refers to adjusting the parameters of the frequency band allocation strategy, such as frequency range, bandwidth allocation, interference threshold, etc., based on the evaluation results. Algorithm optimization refers to improving the intelligent scheduling algorithm, such as the crossover rate and mutation rate of the genetic algorithm, and the reward function design of the reinforcement learning algorithm.

[0116] Iterative updates include setting a policy update cycle, such as monthly or quarterly updates, to ensure the timeliness of the policy. Iterative updates also include update implementation, which means implementing the updated policy in the actual system and conducting small-scale tests to verify the effectiveness of the policy.

[0117] Through the above-mentioned update mechanism, an effective real-time feedback mechanism can be established, and the frequency band allocation strategy can be continuously optimized based on the feedback results to ensure that the system adapts to the ever-changing signal environment and improves communication quality.

[0118] The following provides an update mechanism for optimizing the signal of high-rise buildings in commercial areas, which specifically includes the following steps:

[0119] Step 1: Feedback channel construction. Develop mobile applications and web platforms for users to submit communication quality feedback. Deploy a network monitoring system to track network performance indicators in real time.

[0120] Step 2: Feedback data processing: Clean user feedback data, remove irrelevant information and error reports; classify feedback data, such as signal problems, connection problems, etc.

[0121] Step 3: Feedback analysis: Statistically analyze user feedback to identify hotspots and time periods with signal quality issues; correlate feedback data with frequency band allocation strategies to identify strategic factors that may cause problems.

[0122] Step 4: Strategy evaluation: Evaluate the communication effect of the current frequency band allocation strategy, such as signal strength, connection stability, etc.; identify problems in the strategy, such as insufficient signal coverage in some areas.

[0123] Step 5: Strategy optimization: Adjust the parameters of the frequency band allocation strategy, such as increasing the frequency bandwidth in weak signal areas; improve the intelligent scheduling algorithm, such as increasing the mutation rate of the genetic algorithm, to explore more strategic possibilities.

[0124] Step 6: Iterative update: Set a monthly update of the frequency band allocation strategy; test the updated strategy on a small scale to ensure the effectiveness of the strategy, and then implement the update in full.

[0125] The present invention effectively solves the signal mixing problem in densely populated environments of high-rise buildings and significantly improves the quality of wireless communication through key technical steps such as signal monitoring and data analysis, frequency band optimization allocation, intelligent scheduling algorithm, real-time feedback and iterative optimization. This technical solution is not only highly practical and innovative, but also lays a solid foundation for the further development of future intelligent wireless communication systems.

[0126] In the second aspect of this application, see Figure 5 , and further provides a signal optimization device 50, comprising:

[0127] A signal division module 501 is used to obtain an initial signal and divide an available frequency band of the initial signal into a plurality of sub-frequency bands;

[0128] An interference assessment module 502 is used to obtain the interference degree between different sub-frequency bands according to the interference assessment model to obtain an interference assessment result;

[0129] An adjustment module 503, configured to dynamically adjust the frequency range corresponding to each of the sub-frequency bands according to the interference evaluation result;

[0130] Wherein, the interference assessment model is constructed based on support vector machine and / or random forest.

[0131] In an optional embodiment, the adjustment module 503 may include:

[0132] A total interference degree calculation unit, used to calculate the total interference degree of the plurality of sub-frequency bands;

[0133] An adjustment unit, configured to dynamically adjust the frequency range corresponding to each sub-frequency band so as to minimize the value corresponding to the total interference degree;

[0134] The total interference level A is obtained based on the following formula: Where M is the number of sub-bands, I ij is the degree of interference between the i-th sub-band and the j-th sub-band.

[0135] In an optional embodiment, the adjustment module 503 may include:

[0136] A population initialization unit, used to generate an initial population, each individual in the initial population represents a frequency band allocation scheme;

[0137] A fitness function acquisition unit, used to acquire a fitness function and evaluate each individual according to the fitness function;

[0138] A genetic operation execution unit, used to execute a genetic operation on the initial population to obtain a next generation population, and use the next generation population as the initial population;

[0139] An iterative unit, used for repeatedly executing the step of performing genetic operations on the initial population to obtain a next generation population, until an optimal solution of the fitness function is obtained;

[0140] An output unit, used for obtaining the individual corresponding to the optimal solution as the adjusted frequency range of each sub-frequency band;

[0141] The fitness function is determined based on minimizing interference and / or maximizing communication quality.

[0142] In an optional embodiment, the adjustment module 503 dynamically adjusts the frequency range corresponding to each of the sub-frequency bands based on a reinforcement learning model, and the reinforcement learning model is constructed based on the following steps: defining a state space, wherein the state in the state space includes at least one of the following: current frequency band allocation, signal strength, and interference level; defining an action space, wherein the actions in the action space include strategies for adjusting frequency band allocation; defining a reward function, wherein the reward function is used to evaluate the pros and cons of each of the actions; and constructing the reinforcement learning model using a reinforcement learning algorithm.

[0143] In an optional embodiment, the reward function R(s,a) can be expressed as the following formula:

[0144] R(s,a)=γ×(L0–L1)+δ×(B1–B0);

[0145] Among them, γ and δ are weight coefficients, L0 is the current interference level, L1 is the adjusted interference level, B1 is the adjusted communication quality score, and B0 is the current communication quality score.

[0146] In an optional embodiment, the frequency range corresponding to each of the sub-frequency bands is dynamically adjusted based on at least one of the following principles: preferentially adjusting the sub-frequency bands with interference levels higher than a threshold; ensuring that the bandwidth requirements of each of the sub-frequency bands are met; and using a smooth transition strategy for dynamic adjustment.

[0147] In an optional embodiment, the interference assessment model obtains the degree of interference between different sub-frequency bands according to a target feature, and the target feature includes at least one of the following: average signal strength, interference frequency, and signal fluctuation range.

[0148] For more information about the working principle and working mode of the signal optimization device 50, please refer to the relevant description of the signal optimization method, which will not be repeated here.

[0149] The present application also provides a storage medium, which can be a computer-readable storage medium for storing a computer program, wherein the program is executed by a computer or a processor in any of the steps of the above-mentioned signal optimization method. The computer-readable storage medium may include a non-volatile memory or a non-transitory memory, and may also include an optical disk, a mechanical hard disk, a solid-state hard disk, etc.

[0150] An embodiment of the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the program is executed by the processor, the steps of any one of the above-mentioned signal optimization methods can be implemented.

[0151] In the embodiments of the present application, the processor may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application may be directly embodied as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0152] In the embodiment of the present application, the memory may be a non-volatile memory, such as a hard disk drive (HDD) or a solid-state drive (SSD), etc., or a volatile memory (volatile memory), such as a random-access memory (RAM). The memory is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiment of the present application may also be a circuit or any other device that can realize a storage function, for storing computer programs and / or data.

[0153] In the signal optimization method provided in the embodiment of the present application, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device or other programmable device. The computer program may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instruction may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, an SSD).

[0154] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0155] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0156] In the above embodiments, the description of each embodiment has its own emphasis, and any multiple embodiments can be used in combination. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0157] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software units in a processor for execution. The software unit can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor executes the instructions in the memory, and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.

[0158] In the embodiment of the present application, the processor of the above-mentioned device may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0159] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the above method embodiment. The computer program product may be a software installation package.

[0160] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0161] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0162] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0163] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or TRP, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0164] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article indicates that the associated objects before and after are in an "or" relationship.

[0165] The "plurality" appearing in the embodiments of the present application refers to two or more.

[0166] The first, second, etc. descriptions appearing in the embodiments of the present application are only used for illustration and distinction of the description objects. There is no order, nor do they indicate any special limitation on the number of devices in the embodiments of the present application, and cannot constitute any limitation on the embodiments of the present application.

[0167] The "connection" that appears in the embodiments of the present application refers to various connection methods such as direct connection or indirect connection to achieve communication between devices, and the embodiments of the present application do not impose any limitations on this.

[0168] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A signal optimization method, characterized in that: The method comprises: Acquire an initial signal, and divide an available frequency band of the initial signal into a plurality of sub-frequency bands; Obtaining the interference degree between the different sub-frequency bands according to the interference assessment model to obtain an interference assessment result; dynamically adjusting the frequency range corresponding to each sub-frequency band according to the interference assessment result; Wherein, the interference assessment model is constructed based on support vector machine and / or random forest.

2. The method according to claim 1, characterized in that The dynamically adjusting the frequency range corresponding to each of the sub-frequency bands according to the interference evaluation result includes: Calculating the total interference level of the plurality of sub-frequency bands; Dynamically adjust the frequency range corresponding to each sub-band to minimize the value corresponding to the total interference level; the total interference level A is obtained based on the following formula: Where M is the number of sub-bands, I ij is the degree of interference between the i-th sub-band and the j-th sub-band.

3. The method according to claim 1, characterized in that The dynamically adjusting the frequency range corresponding to each of the sub-frequency bands includes: generating an initial population, wherein each individual in the initial population represents a frequency band allocation scheme; Obtaining a fitness function, and evaluating each of the individuals according to the fitness function; Performing genetic operations on the initial population to obtain a next-generation population, and using the next-generation population as the initial population; Repeating the step of performing genetic operations on the initial population to obtain a next generation population until an optimal solution to the fitness function is obtained; Obtaining the individual corresponding to the optimal solution as the adjusted frequency range of each sub-frequency band; The fitness function is determined based on minimizing interference and / or maximizing communication quality.

4. The method according to claim 1, characterized in that Dynamically adjust the frequency range corresponding to each of the sub-frequency bands based on a reinforcement learning model, wherein the reinforcement learning model is constructed based on the following steps: Define a state space, where the state in the state space includes at least one of the following: current frequency band allocation, signal strength, and interference level; defining an action space, wherein actions in the action space include strategies for adjusting frequency band allocation; Defining a reward function, wherein the reward function is used to evaluate the quality of each of the actions; The reinforcement learning model is constructed using a reinforcement learning algorithm.

5. The method according to claim 4, characterized in that The reward function R(s,a) can be expressed as the following formula: R(s,a)=γ×(L0–L1)+δ×(B1–B0); Among them, γ and δ are weight coefficients, L0 is the current interference level, L1 is the adjusted interference level, B1 is the adjusted communication quality score, and B0 is the current communication quality score.

6. The method according to any one of claims 1 to 5, characterized in that: The frequency range corresponding to each of the sub-frequency bands is dynamically adjusted based on at least one of the following principles: preferentially adjusting the sub-frequency bands with interference levels higher than a threshold; ensuring that the bandwidth requirements of each of the sub-frequency bands are met; and adopting a smooth transition strategy for dynamic adjustment.

7. The method according to any one of claims 1 to 5, characterized in that: The interference assessment model obtains the interference degree between different sub-frequency bands according to target characteristics, and the target characteristics include at least one of the following: average signal strength, interference frequency, and signal fluctuation range.

8. A signal optimization device, characterized in that: The device comprises: A signal division module, used to obtain an initial signal and divide an available frequency band of the initial signal into a plurality of sub-frequency bands; An interference assessment module, used to obtain the interference degree between the different sub-frequency bands according to the interference assessment model, and obtain an interference assessment result; An adjustment module, configured to dynamically adjust the frequency range corresponding to each of the sub-frequency bands according to the interference evaluation result; Wherein, the interference assessment model is constructed based on support vector machine and / or random forest.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, which, when executed by the processor, can implement the steps of the method according to any one of claims 1 to 7.

10. A storage medium for storing a computer program, characterized in that: When the program is executed by a computer or a processor, the program implements the steps of the method according to any one of claims 1 to 7.

Images