Signal coordination method and system and cloud coordination platform

Abstract

The invention relates to a signal coordination method and system and a cloud coordination platform. The method comprises the following steps: analyzing acquired detection parameters in a set area, generating distribution information of signal strength in the set area, and determining a high-interference area of signals according to the distribution information; and inputting the detection parameters of the high-interference area into a pre-trained decision model to obtain an adjustment strategy so as to adjust the power and the frequency of the high-interference area. According to the method, the high-interference area can be automatically and accurately identified according to the detection parameters, and a basis is provided for subsequent interference coordination; by adopting the pre-trained decision model, the adjustment strategy can be quickly determined, the network parameters of the high-interference area can be adjusted in real time, the problem of signal interference is effectively solved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of mobile communication technology, and in particular to a signal coordination method, system and cloud coordination platform. Background Art

[0002] With the rapid development of mobile communication technology, mobile communication networks provide users with higher transmission rates, wider coverage, and greater capacity.

[0003] In mobile communication networks, signal interference is an important factor affecting user experience and network performance. Traditional signal interference detection and processing methods mainly rely on manual troubleshooting and static configuration, which is inefficient and difficult to adapt to dynamically changing network environments.

[0004] Therefore, how to develop a signal coordination method that can quickly determine interference areas and dynamically adjust network parameters has become an urgent problem to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide a signal coordination method, system and cloud coordination platform to address the above technical issues.

[0006] In a first aspect, the present application provides a signal coordination method. The method comprises:

[0007] Acquire detection parameters within a set area; wherein the detection parameters include signal strength, geographic location, network traffic and user distribution information;

[0008] Analyzing the detection parameters to generate distribution information of the signal strength in the set area, and determining a high interference area of ​​the signal according to the distribution information;

[0009] The detection parameters of the high interference area are input into the pre-trained decision model to obtain an adjustment strategy to adjust the power and frequency of the high interference area.

[0010] In one embodiment, the analyzing the detection parameters to generate the distribution information of the signal strength in the set area, and determining the high interference area of ​​the signal according to the distribution information, includes:

[0011] Using a machine learning algorithm, the set area is divided into a plurality of clusters, and all the clusters constitute the distribution information;

[0012] Clusters with signal strength below a preset level are identified and marked as high interference areas.

[0013] In one embodiment, the detection parameter further includes time information; before parsing the detection parameter, the following is further included:

[0014] Delete abnormal data according to the preset signal strength range;

[0015] Based on the time information, a hash algorithm is used to verify the uniqueness of the detection parameters and delete duplicate records.

[0016] In one of the embodiments, the method further includes: converting the distribution information into a heat map for display.

[0017] In one embodiment, pre-training the decision model includes:

[0018] Construct training samples and compound reward functions;

[0019] Inputting the training samples into the initial deep reinforcement learning network to obtain a decision result;

[0020] Feeding back the decision result to the target base station for execution;

[0021] The execution result of the target base station is obtained, and according to the composite reward function, the initial deep reinforcement learning network is iteratively optimized to obtain a trained decision model.

[0022] In a second aspect, the present application also provides a signal coordination system. The system includes: multiple base stations and a server;

[0023] Each of the base stations is provided with at least one detection module, and the detection module includes a flow sensor and a signal sensor;

[0024] Each of the base stations is used to obtain detection parameters within a set area; wherein the detection parameters include signal strength, geographical location, network traffic and user distribution information;

[0025] The server is used to parse the detection parameters, generate distribution information of the signal strength in the set area, and determine the high interference area of ​​the signal based on the distribution information; input the detection parameters of the high interference area into a pre-trained decision model to obtain an adjustment strategy so that the base station to which the high interference area belongs adjusts the power and frequency.

[0026] In one of the embodiments, after acquiring the detection parameters, each base station compresses and packages the detection parameters and transmits them to the server through an encrypted channel according to a preset transmission strategy.

[0027] In one embodiment, the preset transmission strategy includes:

[0028] When the detection parameter is low-frequency data, a batch upload strategy is adopted;

[0029] When the detection parameter is high-frequency data or urgent data, a real-time upload strategy is adopted;

[0030] The emergency data refers to data generated when a signal mutation occurs in the set area and the mutation action satisfies a trigger condition, and the trigger condition is dynamically adjusted according to environmental changes in the set area.

[0031] In one embodiment, each of the base stations obtains the detection parameter, including:

[0032] When the preset time is met or the trigger condition is met, the detection parameter is obtained.

[0033] In a third aspect, the present application further provides a cloud collaboration platform, which includes: a plurality of signal coordination systems according to any one of the first aspects, wherein the signal coordination systems are independent of each other and share data.

[0034] The above signal coordination method, system and cloud coordination platform have at least the following advantages:

[0035] This application parses the detection parameters obtained in the set area, generates the distribution information of the signal strength in the set area, and determines the high interference area of ​​the signal based on the distribution information; then the detection parameters of the high interference area are input into the pre-trained decision model to obtain an adjustment strategy to adjust the power and frequency of the high interference area. This application can automatically and accurately identify the high interference area based on the detection parameters, providing a basis for subsequent interference coordination; using the pre-trained decision model, the adjustment strategy can be quickly determined, and the network parameters of the high interference area can be adjusted in real time, effectively solving the signal interference problem and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings constituting a part of this application are used to provide a further understanding of the present invention. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A schematic diagram of the structure of a signal coordination system in one embodiment;

[0039] Figure 2 is a flow chart of a signal coordination method in one embodiment;

[0040] Figure 3A schematic diagram of a flow chart of a step of determining a high interference area of ​​a signal in one embodiment;

[0041] Figure 4 A schematic diagram of a flow chart of a cleaning parameter detection step in an embodiment;

[0042] Figure 5 A schematic diagram of a process of pre-training a decision model in one embodiment;

[0043] Figure 6 is a structural block diagram of a signal coordination device in one embodiment;

[0044] Figure 7 A structural block diagram of a cloud coordination platform in one embodiment;

[0045] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0046] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0047] While some exemplary embodiments of the present invention have been described for the purpose of illustration, it should be understood that the present invention may be implemented in other ways not specifically shown in the drawings.

[0048] See also Figure 1 In an exemplary embodiment, the present application provides a signal coordination system, including multiple base stations 102 and a server 104.

[0049] Specifically, the base station 102 is an important component of the mobile communication network, which is used to communicate wirelessly with the mobile terminal and complete the sending and receiving of signals. The server 104 is a computing device or computer program for storing, processing or transmitting data, which is usually deployed in a data center and connected to the Internet or an intranet of an enterprise through a wired network (such as optical fiber, Ethernet, etc.). Each base station 102 is connected to the server 104 by wire or wireless means and exchanges data. Furthermore, each base station 102 in this embodiment is provided with at least one detection module, and the detection module includes a flow sensor and a signal sensor.

[0050] In the process of data interaction between each base station 102 and the server 104, the base station 102 obtains the detection parameters in the set area, wherein the detection parameters include signal strength, geographic location, network traffic and user distribution information. Further, the base station 102 transmits the obtained detection parameters to the server 104, so that the server 104 analyzes the detection parameters, generates the distribution information of the signal strength in the set area, and determines the high interference area of ​​the signal based on the distribution information; then the detection parameters of the high interference area are input into the pre-trained decision model to obtain the adjustment strategy, and the adjustment strategy is transmitted to the base station 102 to which the high interference area belongs, so that the base station 102 adjusts the power and frequency according to the adjustment strategy.

[0051] Generally speaking, base stations are divided and set according to factors such as user density, geographical location, base station type, and radiation intensity. The set area in the embodiment of the present application refers to the area where multiple base stations of the same type are located according to certain factors. In this way, the signal strength distribution of each base station in the set area is more even, and the high interference area screened out is more reasonable.

[0052] For example, the mobile terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices and portable wearable devices. IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc.

[0053] Optionally, an encrypted channel is established between each base station 102 and the server 104 to ensure the security of data transmission. Exemplarily, the embodiment of the present application uses TLS (Transport Layer Security Protocol) to build an encrypted channel. Specifically, TLS protects the confidentiality, integrity and source reliability of communication data through encryption and identity authentication.

[0054] Optionally, after obtaining the detection parameters, each base station 102 compresses and packages the detection parameters, and transmits them to the server 104 through an encrypted channel according to a preset transmission strategy. Exemplarily, the embodiment of the present application uses the LZ4 compression algorithm to compress the detection parameters. Specifically, LZ4 is an algorithm that reduces storage space by finding repeated patterns and regularities in data, and has the advantages of fast compression speed and high efficiency. Compression processing before transmission can reduce the amount of transmitted data and improve transmission efficiency.

[0055] Optionally, the preset transmission strategy includes: when the detection parameter is low-frequency data, a batch upload strategy is adopted; when the detection parameter is high-frequency data or urgent data, a real-time upload strategy is adopted. Urgent data refers to data generated when a signal mutation occurs in a set area and the mutation action meets the triggering conditions. This solution can save transmission time while taking into account immediacy.

[0056] Furthermore, the trigger condition is set based on a signal mutation in a set area, and the trigger condition is dynamically adjusted according to environmental changes in the set area. Exemplarily, the judgment method of satisfying the trigger condition includes: when the size of the signal mutation in the target area exceeds a preset signal strength threshold, it is considered that the trigger condition is satisfied, and the expression of the preset signal strength threshold is: θ(t) = θ0 + α·ΔS(t), where θ0 is the initial threshold, α is the environmental factor, and ΔS(t) is the signal strength change value.

[0057] Optionally, each base station 102 obtains detection parameters in a manner including: a combination of timed sampling and event triggering, that is, when a preset time or a trigger condition is met, the detection parameters are obtained. Exemplarily, after the sampling task is started, each sensor collects detection parameters once every one second. At the same time, when the signal strength drops by more than the preset signal strength threshold θ(t), the event recording mechanism is triggered to record the current detection parameters to form a record. It should be understood that the detection parameters also include time information. For example, if the initial threshold θ0 is set to -80dBm and the environmental factor α is set to 0.1, then at 12:35 UTC on October 1, 2023, the signal strength at latitude: 34.0522, longitude: -118.2437 drops from -78dBm to -85dBm, triggering the recording mechanism. At this time, the preset signal strength threshold θ(t) = θ(12:35) = -80 + 0.1 × (-85-(-78)) = -80.7dBm.

[0058] In the above signal coordination system, each base station 102 automatically obtains the detection parameters, compresses and packages them, and then transmits them to the server 104 through an encrypted channel, which can reduce the amount of transmitted data, improve transmission efficiency, and meet security requirements. The server 104 analyzes the detection parameters and accurately identifies the high-interference area to provide a basis for subsequent interference coordination; the pre-trained decision model can be used to quickly determine the adjustment strategy and adjust the network parameters of the high-interference area in real time, effectively solving the signal interference problem and improving the user experience.

[0059] In an exemplary embodiment, the present application provides a signal coordination method. Figure 1 The server 104 in FIG. 1 is used as an example for explanation.

[0060] See also Figure 2 , Figure 2 The following is a flow chart of a signal coordination method according to the present embodiment, which specifically includes the following steps:

[0061] Step S202, obtaining detection parameters within a set area; wherein the detection parameters include signal strength, geographic location, network traffic and user distribution information.

[0062] Step S204, analyzing the detection parameters, generating distribution information of the signal strength in the set area, and determining the high interference area of ​​the signal according to the distribution information.

[0063] Specifically, the distribution information includes signal strength, timestamp, and geographic location information. Generally speaking, high interference areas are areas where signal strength is weak and concentrated, and in these areas, the signal will experience greater interference.

[0064] Step S206: input the detection parameters of the high interference area into the pre-trained decision model to obtain an adjustment strategy to adjust the power and frequency of the high interference area.

[0065] Specifically, the decision model is trained based on historical data and simulation data. In addition to historical detection parameters, the historical data also includes historical adjustment effects. By learning the historical adjustment strategy and the effects of the strategy, the decision model can take action when the environmental state changes to obtain the optimal return.

[0066] The above signal coordination method parses the detection parameters obtained in the set area, generates the distribution information of the signal strength in the set area, and determines the high interference area of ​​the signal based on the distribution information; then the detection parameters of the high interference area are input into the pre-trained decision model to obtain an adjustment strategy to adjust the power and frequency of the high interference area. This application can automatically and accurately identify the high interference area based on the detection parameters, providing a basis for subsequent interference coordination; using the pre-trained decision model, the adjustment strategy can be quickly determined, and the network parameters of the high interference area can be adjusted in real time, effectively solving the signal interference problem and improving the user experience.

[0067] See also Figure 3 Optionally, analyzing the detection parameters, generating distribution information of the signal strength in a set area, and determining a high interference area of ​​the signal according to the distribution information, including:

[0068] Step S302: using a machine learning algorithm, the set area is divided into a plurality of clusters, and all the clusters constitute distribution information.

[0069] Step S304: identifying clusters whose signal strength is lower than a preset strength and marking them as high interference areas.

[0070] Specifically, after the server obtains the detection parameters, it classifies and stores them, and then uses a machine learning algorithm to perform in-depth statistical analysis, aiming to accurately identify areas where signal interference frequently occurs, and provide data support for subsequent interference coordination. Among them, the machine learning algorithm is a method and technology for automatically acquiring knowledge and experience from existing data, mainly including density estimation algorithms, geographically weighted regression, anomaly detection algorithms, etc. Exemplarily, the embodiment of the present application uses a K-means clustering algorithm that is suitable for large-scale data sets and has high computational efficiency for data analysis, wherein the base stations divided into the same cluster have similar geographical locations and relatively consistent signal strengths; close geographical locations refer to the base stations being located in similar environments, such as adjacent streets or areas with similar terrain features; relatively consistent signal strengths refer to the difference in signal strengths of the base stations being within the allowable range of differences.

[0071] See also Figure 4 Optionally, the detection parameter also includes time information; before parsing the detection parameter, it also includes:

[0072] Step S402: Delete abnormal data according to a preset signal strength range.

[0073] Step S404: Based on the time information, a hash algorithm is used to verify the uniqueness of the detection parameters and delete duplicate records.

[0074] Specifically, under normal circumstances, the signal strength in an area is within a reasonable strength range, and data outside this range can be considered abnormal data. For example, the signal strength value should be between -120dBm and -30dBm, and data outside this range is considered abnormal data.

[0075] Furthermore, for duplicate records, the embodiment of the present application uses a hash algorithm to perform uniqueness verification on each record, identify and delete duplicate records. The specific steps include: performing a hash calculation on the timestamp, GPS location information and signal strength value of each record to generate a unique identifier. The generated unique identifier is compared with the existing records, and if a duplicate is found, the duplicate record is deleted. The expression of the hash function is:

[0076]

[0077] Where H(r) represents the hash value of record r; Represents string concatenation operation;

[0078] timestamp represents timestamp; latitude represents latitude; longitude represents longitude; signal_strength represents signal strength value.

[0079] By adopting the above scheme, the detection parameters are pre-cleaned, abnormal data and duplicate records are eliminated, valid records are screened out, and the calculation accuracy of the clustering algorithm is improved.

[0080] Exemplarily, the step of analyzing the detection parameters using a clustering algorithm includes:

[0081] Step 1: Extract key features from the cleaned data, including signal strength, timestamp, and geographic location information.

[0082] Step 2: Initialize the K-means clustering algorithm and randomly select K data points as initial cluster centers, for example, K=10.

[0083] Step 3: Calculate the distance from each data point to each cluster center and assign it to the nearest cluster center.

[0084] Step 4: Recalculate the center point of each cluster based on the allocation results.

[0085] Repeat steps 3 and 4 above, iterate the clustering process until the cluster center no longer changes significantly, and obtain the clustering result. At this time, areas with similar signal strength and close geographical location are divided into the same cluster.

[0086] Exemplarily, the expression of the K-means clustering algorithm is:

[0087]

[0088] Among them, d(x,c) represents the Euclidean distance from the data point x to the cluster center c;

[0089] x latitude and x longitude Represent the latitude and longitude of the data point respectively;

[0090] c latitude and c longitude Represent the latitude and longitude of the cluster center respectively.

[0091] It should be understood that the above clustering algorithm is pre-trained based on historical detection parameters, and its training steps are similar to the analysis steps, which will not be repeated here.

[0092] The above signal coordination method pre-cleans the detection parameters, removes abnormal data and duplicate records, and effectively improves the analysis accuracy of the clustering algorithm. The clustering algorithm can quickly calculate a large number of detection parameters, quickly identify high-interference areas from the set area, and improve the efficiency of investigation.

[0093] Optionally, the signal coordination method of the present application further includes: converting the distribution information into a heat map for display.

[0094] Specifically, this embodiment uses a geographic information system (GIS) tool to convert the cluster analysis results into a heat map. The cluster results are imported into the GIS tool to obtain a heat map, in which the color depth represents the interference intensity, and the darker the color, the more severe the interference. Furthermore, Matplotlib and Geopandas libraries in Python are used to draw the heat map to ensure that the visualization effect is clear and easy to understand.

[0095] For example, 2000 records are obtained, and 1000 valid records are obtained after cleaning. 10 cluster centers are initialized, and the distance between each data and the center point is calculated. After 10 iterations, the cluster center is stable and the clustering result is obtained. The clustering result is imported into the GIS tool to generate a heat map. If a certain area (such as longitude -118.2437, latitude 34.0522) is found to have the darkest color, it means that the interference in this area is the most serious.

[0096] The above signal coordination method converts the clustering results into a heat map, so that users can intuitively view the clustering results and quickly identify high interference areas.

[0097] See also Figure 5 , optionally, a pre-trained decision model, including:

[0098] Step S502, constructing training samples and a composite reward function.

[0099] Step S504: input the training sample into the initial deep reinforcement learning network to obtain the decision result.

[0100] Step S506: Feedback the decision result to the target base station for execution.

[0101] Step S508, obtaining the execution result of the target base station, and iteratively optimizing the initial deep reinforcement learning network according to the composite reward function to obtain a trained decision model.

[0102] Specifically, the training samples are generated based on historical records and simulation data, where the detection parameters in the historical records include network traffic, signal strength, user distribution information, and historical adjustment effects.

[0103] Furthermore, the detection parameters are pre-cleaned to remove abnormal data and duplicate records and retain valid records. The detection parameters in the valid records are then denoised and normalized, the processed data is stored in the InfluxDB database, and a multidimensional index is established for subsequent use.

[0104] Furthermore, data is extracted from the InfluxDB database to form training samples, which are then encoded to obtain high-dimensional vectors of the training samples.

[0105] Furthermore, a composite reward function is designed. The embodiment of the present application designs a composite reward function by comprehensively considering multi-dimensional indicators such as signal quality improvement, network load balancing, and user satisfaction.

[0106] Specifically, the compound reward function expression of the embodiment of the present application is:

[0107] R(t)=α×ΔS(t)+p×ΔL(t)+γ×ΔU(t)

[0108] Among them, R(t) represents the reward value at time t;

[0109] ΔS(t) represents the improvement in signal quality, and its calculation formula is: ΔS(t)=S(t)-S(t-1), where S(t) is the signal strength at time t.

[0110] ΔL(t) represents the network load balance, and its calculation formula is: Among them, L i (t) is the load of the ith base station, is the average load, and N is the total number of base stations.

[0111] ΔU(t) represents the improvement in user satisfaction, and its calculation formula is: ΔU(t)=U(t)-U(t-1), where U(t) is the user satisfaction score at time t.

[0112] α, β, and γ are weight coefficients and can be adjusted according to actual needs.

[0113] Furthermore, the structure of the initial deep reinforcement learning network (DRL) is constructed. The embodiment of the present application is based on the DRL model of the Actor-Critic architecture, in which the Actor network is responsible for generating frequency and power adjustment strategies, and the Critic network is responsible for evaluating the pros and cons of the strategies.

[0114] Furthermore, the adjustment range and step size of frequency and power are defined, illustratively, the frequency adjustment range is 1 MHz to 100 MHz, and the power adjustment range is 0 dBm to 30 dBm, and the frequency and power adjustment actions are encoded into discrete or continuous action spaces.

[0115] Furthermore, a standard API interface is designed to realize data interaction between the DRL model and the base station control system. Specifically, according to the adjustment strategy output by the DRL model, a frequency and power adjustment instruction is generated to adjust the frequency and power of the target base station.

[0116] After completing the above steps, the high-dimensional vector of the training sample is input into the DRL model based on the Actor-Critic architecture for training.

[0117] For example, the network traffic collected by a base station in real time is 1000Mbps, the signal strength is -85dBm, and the user satisfaction score is 70. After receiving the above data, the server pre-processes it and stores it in the InfluxDB database.

[0118] The DRL model generates an adjustment strategy based on the current state of the base station: adjust the frequency to 90 MHz and the power to 20 dBm.

[0119] The server sends the adjustment strategy to the base station and obtains the adjusted detection parameters of the base station, where the adjusted network traffic is 800Mbps, the signal strength is -90dBm, and the user satisfaction score is 60.

[0120] If α, β, and γ are set to 0.5, 0.3, and 0.2 respectively, and a composite reward function is used, the calculated reward value is: R(t)=0.5×(-85-(-90))+0.3(1000-800)+0.2(70-60)=7.5.

[0121] The DRL model optimizes and updates the model hyperparameters based on the reward value.

[0122] The above-mentioned signal coordination method pre-cleans the detection parameters, eliminates abnormal data and duplicate records, and effectively improves the parsing accuracy of the clustering algorithm. The clustering algorithm can quickly calculate a large number of detection parameters, quickly identify high-interference areas from the set area, and improve the efficiency of investigation. Furthermore, the present application obtains a decision model based on training samples and composite reward functions, and inputs the detection parameters of the high-interference area into the trained decision model to obtain an adjustment strategy. Based on the adjustment strategy, the base station to which the high-interference area belongs can automatically adjust the network parameters of frequency and power to eliminate interference and improve the network environment.

[0123] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0124] Based on the same inventive concept, the embodiment of the present application also provides a signal coordination device for implementing the signal coordination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more signal coordination device embodiments provided below can refer to the limitations on the signal coordination method above, and will not be repeated here.

[0125] See also Figure 6 In an exemplary embodiment, the present application provides a signal coordination device, which is arranged in a server, and includes: an acquisition module, a data analysis module, an interference coordination algorithm module and an adjustment module, wherein:

[0126] The acquisition module is used to acquire detection parameters within a set area; wherein the detection parameters include signal strength, geographic location, network traffic and user distribution information.

[0127] The data analysis module is used to analyze the detection parameters, generate the distribution information of the signal strength in the set area, and determine the high interference area of ​​the signal based on the distribution information.

[0128] Interference coordination algorithm module, used to pre-train decision models.

[0129] The adjustment module is used to input the detection parameters of the high interference area into the pre-trained decision model to obtain an adjustment strategy to adjust the power and frequency of the base station in the high interference area.

[0130] Optionally, the data analysis module parses the detection parameters, generates distribution information of the signal strength in a set area, and determines the high interference area of ​​the signal based on the distribution information, including: using a machine learning algorithm to divide the set area into multiple clusters, and all clusters constitute the distribution information; identifying clusters with signal strength lower than a preset strength, and marking them as high interference areas.

[0131] Optionally, the signal coordination device of the embodiment of the present application further includes: a data processing module.

[0132] The data processing module is used to pre-process the detection parameters, specifically including: deleting abnormal data according to the preset signal strength range; based on time information, using a hash algorithm to verify the uniqueness of the detection parameters, deleting duplicate records, and retaining valid records.

[0133] The data processing module is also used to denoise and normalize the detection parameters in the valid records, store the processed data in the InfluxDB database, and establish a multidimensional index for subsequent use.

[0134] Optionally, the step of parsing the detection parameters by the data analysis module includes:

[0135] Step 1: Extract key features from the cleaned data, including signal strength, timestamp, and geographic location information.

[0136] Step 2: Initialize the K-means clustering algorithm and randomly select K data points as the initial cluster centers.

[0137] Step 3: Calculate the distance from each data point to each cluster center and assign it to the nearest cluster center.

[0138] Step 4: Recalculate the center point of each cluster based on the allocation results.

[0139] Repeat steps 3 and 4 above, iteratively perform the clustering process until the cluster center no longer changes significantly, and obtain the clustering result.

[0140] Optionally, the data analysis module is also used to convert the distribution information into a heat map for display.

[0141] Optionally, the interference coordination algorithm module pre-trains the decision model, including: constructing training samples and a composite reward function; inputting the training samples into the initial deep reinforcement learning network to obtain a decision result; feeding back the decision result to the target base station for execution; obtaining the execution result of the target base station, and iteratively optimizing the initial deep reinforcement learning network according to the composite reward function to obtain a trained decision model.

[0142] The above-mentioned signal coordination device pre-cleans the detection parameters, eliminates abnormal data and duplicate records, and effectively improves the parsing accuracy of the clustering algorithm. The clustering algorithm can quickly calculate a large number of detection parameters, quickly identify high-interference areas from the set area, and improve the efficiency of investigation. Furthermore, the present application obtains a decision model based on training samples and composite reward functions, and inputs the detection parameters of the high-interference area into the trained decision model to obtain an adjustment strategy. Based on the adjustment strategy, the base station to which the high-interference area belongs can automatically adjust the network parameters of frequency and power to eliminate interference and improve the network environment.

[0143] Each module in the above signal coordination device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0144] See also Figure 7 In an exemplary embodiment, the present application provides a cloud collaboration platform.

[0145] The cloud-based collaborative platform includes multiple signal coordination systems involved in the above-mentioned embodiments, wherein each signal coordination system is independent of each other and shares data. In this way, the cloud-based collaborative platform ensures efficient operation and continuous optimization of the entire system through efficient data integration, real-time collaborative processing, and a closed-loop feedback mechanism.

[0146] Optionally, the cloud-based collaborative platform of the embodiment of the present application realizes the coordination function based on data integration, coordinated processing and feedback mechanism.

[0147] Exemplarily, in terms of data integration: the embodiment of the present application adopts a microservice architecture to design a cloud collaboration platform to ensure that each system is independently deployed and expanded, while achieving dynamic collaboration between systems through a service registration and discovery mechanism.

[0148] Furthermore, the embodiments of the present application formulate a unified data format and interface standard to achieve data standardization, ensuring that signal interference data and network parameter data can be seamlessly integrated. For example, the JSON format is used as the data exchange format, and clear data models and fields are defined.

[0149] Furthermore, the embodiment of the present application selects a distributed database such as Cassandra or MongoDB to form a data storage solution to support the storage and fast query of large-scale data. The distributed database can provide high availability and horizontal scalability to meet the system's needs for data storage.

[0150] Exemplarily, in terms of coordination and processing: The embodiment of the present application designs a RESTful API interface to realize data interaction and instruction transmission between modules. The API interface should follow the REST principle and provide clear resource identification and operation methods, such as GET for data query, POST for data submission, PUT for data update, and DELETE for data deletion.

[0151] Furthermore, the embodiment of the present application introduces a message queue such as RabbitMQ system or Kafka system to process asynchronous message delivery and buffering to ensure the stability and reliability of the system under high load. The message queue can decouple the direct dependencies between modules, provide an asynchronous communication mechanism, and improve the throughput and response speed of the system.

[0152] Furthermore, the embodiments of the present application implement service governance strategies, including service monitoring, service fusing, service current limiting, etc., to ensure the system's self-recovery and self-protection capabilities under abnormal circumstances.

[0153] For example, in terms of feedback mechanism: the embodiment of the present application establishes a set of effect evaluation system to evaluate the effect of the interference coordination algorithm through real-time monitoring and statistical analysis. The evaluation indicators include signal quality improvement rate, network performance improvement, user satisfaction, etc.

[0154] Furthermore, the embodiment of the present application generates optimization suggestions for the signal interference detection module based on the effect evaluation results, for example, adjusting the signal strength threshold, improving the data collection strategy, etc.

[0155] Furthermore, the embodiment of the present application constructs a closed-loop feedback process to feed back optimization suggestions to the signal interference detection module to achieve continuous optimization of the system. The feedback process should ensure timely transmission and effective processing of information to form a virtuous cycle.

[0156] The above-mentioned cloud collaboration platform and various signal coordination systems work together to ensure the efficient operation and continuous optimization of the entire system through efficient data integration, real-time collaborative processing and closed-loop feedback mechanism.

[0157] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 8 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a signal coordination method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0158] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above signal coordination method when executing the computer program.

[0160] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned signal coordination method are implemented.

[0161] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the steps in the above signal coordination method when executed by a processor.

[0162] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0163] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0164] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A signal coordination method, characterized in that: The method comprises: Acquire detection parameters within a set area; wherein the detection parameters include signal strength, geographic location, network traffic and user distribution information; Analyzing the detection parameters to generate distribution information of the signal strength in the set area, and determining a high interference area of ​​the signal according to the distribution information; The detection parameters of the high interference area are input into the pre-trained decision model to obtain an adjustment strategy to adjust the power and frequency of the high interference area.

2. The method according to claim 1, characterized in that: The analyzing the detection parameters to generate distribution information of the signal strength in the set area, and determining the high interference area of ​​the signal according to the distribution information, includes: Using a machine learning algorithm, the set area is divided into a plurality of clusters, and all the clusters constitute the distribution information; Clusters with signal strength below a preset level are identified and marked as high interference areas.

3. The method according to claim 2, characterized in that The detection parameters also include time information; before parsing the detection parameters, the following is also included: Delete abnormal data according to the preset signal strength range; Based on the time information, a hash algorithm is used to verify the uniqueness of the detection parameters and delete duplicate records.

4. The method according to claim 3, characterized in that The method further includes: converting the distribution information into a heat map for display.

5. The method according to claim 1, characterized in that: Pre-training the decision model includes: Construct training samples and compound reward functions; Inputting the training samples into the initial deep reinforcement learning network to obtain a decision result; Feeding back the decision result to the target base station for execution; The execution result of the target base station is obtained, and according to the composite reward function, the initial deep reinforcement learning network is iteratively optimized to obtain a trained decision model.

6. A signal coordination system, characterized in that: The system comprises: a plurality of base stations and a server; Each of the base stations is provided with at least one detection module, and the detection module includes a flow sensor and a signal sensor; Each of the base stations is used to obtain detection parameters within a set area; wherein the detection parameters include signal strength, geographical location, network traffic and user distribution information; The server is used to parse the detection parameters, generate distribution information of the signal strength in the set area, and determine the high interference area of ​​the signal based on the distribution information; input the detection parameters of the high interference area into a pre-trained decision model to obtain an adjustment strategy so that the base station to which the high interference area belongs adjusts the power and frequency.

7. The system according to claim 6, characterized in that After acquiring the detection parameters, each base station compresses and packages the detection parameters and transmits them to the server through an encrypted channel according to a preset transmission strategy.

8. The system according to claim 7, characterized in that The preset transmission strategy includes: When the detection parameter is low-frequency data, a batch upload strategy is adopted; When the detection parameter is high-frequency data or urgent data, a real-time upload strategy is adopted; The emergency data refers to data generated when a signal mutation occurs in the set area and the mutation action satisfies a trigger condition, and the trigger condition is dynamically adjusted according to environmental changes in the set area.

9. The system according to claim 6, characterized in that The base stations acquiring the detection parameters include: When the preset time is met or the trigger condition is met, the detection parameter is obtained.

10. A cloud collaboration platform, characterized in that: The platform comprises a plurality of signal coordination systems according to any one of claims 6 to 9, wherein the signal coordination systems are independent of each other and share data.

Images