Multi-mode broadcast signal intelligent switching method and system based on DRM

Abstract

The invention relates to the technical field of broadcast signal dynamic switching, and discloses a multi-mode broadcast signal intelligent switching method and system based on DRM, and the method comprises the steps: obtaining real-time geographic position information, real-time weather conditions and a historical switching record database; inputting the real-time geographic position information and a regional transition zone obtained by regional analysis into a geographic region division model to obtain the number of DRM broadcast signal modes; inputting a dynamic weather weighted data set constructed according to real-time weather conditions into the signal attenuation model to obtain a real-time signal intensity attenuation granularity value; extracting similar historical switching sequences according to the historical switching record database; performing matching calculation according to the similar historical switching sequence to obtain a matching result confidence coefficient; according to the similar historical switching sequence and the DRM broadcast signal mode number, multi-mode broadcast signal switching planning analysis is carried out, and a real-time optimal switching sequence is obtained. According to the method, high-precision matching of the historical switching data and the real-time scene can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of broadcast signal dynamic switching, and particularly to an intelligent switching method and system for multi-mode broadcast signals based on DRM. Background Art

[0002] Currently, in the process of dynamic frequency switching of a multi-mode broadcast signal system, it is necessary to simultaneously coordinate the complex associations of real-time scenario factors such as geographical location movement and sudden weather changes with historical switching data. Especially in the scenario where the regional transition zone is superimposed with extreme weather, it is necessary to complete signal attenuation prediction, historical data matching, and switching decision generation within milliseconds. However, sudden scenario changes often cause historical reference data to become invalid, seriously affecting the real-time performance and stability of signal switching.

[0003] In an existing technology, the DRM-based multi-mode broadcast signal switching method realizes frequency switching by presetting geographical area division rules and weather attenuation models. Specifically, a static time window is used to extract historical switching sequences, and candidate solutions are screened through a fixed similarity threshold. However, this method does not establish a dynamic weight adjustment mechanism. When the device quickly crosses the regional boundary or encounters sudden weather changes, the geographical location offset compensation parameters in the historical switching sequence accumulate errors with the spatial coordinates of the real-time scenario, and at the same time, the static weather attenuation model cannot capture the attenuation characteristics of high-frequency signals caused by instantaneous fluctuations in haze concentration, resulting in an increase in the spatio-temporal dimension matching deviation between historical data and real-time signal attenuation granularity, ultimately leading to a lag in switching decisions or signal jitter.

[0004] In summary, there is a problem in the prior art that it is difficult to achieve high-precision matching between historical switching data and real-time scenarios. Summary of the Invention

[0005] The present invention provides an intelligent switching method and system for multi-mode broadcast signals based on DRM to achieve high-precision matching between historical switching data and real-time scenarios.

[0006] In a first aspect, to solve the above technical problems, the present invention provides an intelligent switching method for multi-mode broadcast signals based on DRM, including:

[0007] Obtain the real-time geographical location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical switching record database;

[0008] Conduct regional transition analysis based on the real-time geographical location information, and input the obtained regional transition zone and the real-time geographical location information into a pre-trained geographical area division model to obtain the number of DRM broadcast signal modes in the regional transition zone;

[0009] Construct a weighted data set according to the real-time weather conditions, and input the constructed dynamic weather weighted data set into a pre-trained signal attenuation model to obtain the real-time signal strength attenuation granularity values of different DRM signal frequency bands;

[0010] According to the historical handover record database, perform similarity analysis by combining the real-time geographical location information and the real-time weather conditions, and extract the similar historical handover sequence with the highest similarity;

[0011] Perform matching calculations based on the similar historical handover sequence, the real-time signal strength attenuation granularity value, the real-time geographical location information, and the real-time weather conditions to obtain the matching result confidence level;

[0012] According to the similar historical handover sequence, the real-time signal strength attenuation granularity value, the matching result confidence level, and the number of DRM broadcast signal modes, and in combination with a preset confidence threshold, perform multi-mode broadcast signal handover planning analysis to obtain the real-time optimal handover sequence in the current scenario.

[0013] In an alternative embodiment, the obtaining of the real-time geographical location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical handover record database includes:

[0014] Obtain the original location data, original weather data, and original historical handover record database of the broadcast receiving device;

[0015] According to the original location data, perform adaptive coordinate format conversion and dynamic error correction to generate standardized real-time geographical location information;

[0016] According to the original weather data, perform unit unification and missing value filling to obtain the real-time weather conditions affecting signal propagation;

[0017] According to the original historical handover record database, perform time series alignment to obtain the historical handover record database.

[0018] In an alternative embodiment, the

[0019] According to the real-time geographical location information, perform regional transition analysis, and input the analyzed regional transition zone and the real-time geographical location information into a pre-trained geographical area division model to obtain the number of DRM broadcast signal modes in the regional transition zone, including:

[0020] According to the real-time geographical location information, in combination with a preset set of regional polygon boundary coordinates, perform distance calculation from a point to a polygon to obtain the minimum boundary distance;

[0021] Compare the minimum boundary distance with a preset transition boundary threshold. When the minimum boundary distance is less than the transition boundary threshold, determine that the location where the device is located is a regional transition zone;

[0022] Use the historical real-time geographical location information and the historical regional transition zone as inputs, and the number of historical DRM broadcast signal patterns as the output. Construct a geographical area division model and train it. When the number of training times is greater than or equal to the preset number of training times, determine that the training is completed, and obtain a trained geographical area division model;

[0023] Input the real-time geographical location information and the regional transition zone into the trained geographical area division model to obtain the number of DRM broadcast signal patterns in the regional transition zone.

[0024] In an alternative embodiment, the method of constructing a weighted data set according to the real-time weather conditions and inputting the constructed dynamic weather weighted data set into a pre-trained signal attenuation model to obtain real-time signal strength attenuation granularity values for different DRM signal frequency bands includes:

[0025] According to the real-time weather conditions, combine with preset weather type classification rules to perform dynamic weight assignment to obtain a dynamic weather weighted data set;

[0026] Use the historical dynamic weather weighted data set as the input and the historical real-time signal strength attenuation granularity value as the output. Construct a signal attenuation model and train it. When the number of training times is greater than or equal to the preset number of training times, determine that the training is completed, and obtain a trained signal attenuation model;

[0027] Input the dynamic weather weighted data set into the trained signal attenuation model to obtain real-time signal strength attenuation granularity values for different DRM signal frequency bands.

[0028] In an alternative embodiment, the method of performing similarity analysis by combining the real-time geographical location information and the real-time weather conditions according to the historical switching record database and extracting the most similar historical switching sequence includes:

[0029] According to the historical switching record database, combine with the real-time geographical location information to extract candidate historical switching records with a geographical location error less than a preset geographical location error threshold;

[0030] According to the candidate historical switching records, extract the corresponding historical weather condition parameters;

[0031] According to the historical weather condition parameters and the real-time weather conditions, perform multi-dimensional similarity calculation to obtain a weighted Euclidean distance similarity that comprehensively considers precipitation intensity, haze concentration, and visibility;

[0032] Perform time - dimension alignment based on the candidate historical handover record to generate a spatio - temporal alignment sequence;

[0033] Perform weighted fusion based on the spatio - temporal alignment sequence and the weighted Euclidean distance similarity to generate a comprehensive similarity score, and determine the historical handover sequence with the highest comprehensive similarity score in the spatio - temporal alignment sequence as the similar historical handover sequence;

[0034] The similar historical handover sequence includes historical handover background information and the corresponding handover sequence;

[0035] The historical handover background information includes historical signal strength attenuation granularity value, historical geographical location, historical weather conditions, and historical signal source interference.

[0036] In an optional implementation manner, the performing matching calculation according to the similar historical handover sequence, the real - time signal strength attenuation granularity value, the real - time geographical location information, and the real - time weather conditions to obtain the matching result confidence includes:

[0037] Perform item - by - item matching calculation on the historical signal strength attenuation granularity value, historical geographical location, and historical weather conditions in the similar historical handover sequence with the real - time signal strength attenuation granularity value, the real - time geographical location information, and the real - time weather conditions to obtain an attenuation matching degree, a geographical matching degree, and a weather matching degree;

[0038] Perform cross - interference analysis on the historical signal source interference in the similar historical handover sequence and the real - time signal strength attenuation granularity value to obtain an interference matching degree;

[0039] Perform weighted fusion according to the attenuation matching degree, the geographical matching degree, the weather matching degree, and the interference matching degree, combined with a preset fusion weight, to obtain the matching result confidence.

[0040] In an optional implementation manner, the performing multi - mode broadcast signal handover planning analysis according to the similar historical handover sequence, the real - time signal strength attenuation granularity value, the matching result confidence, and the number of DRM broadcast signal modes, combined with a preset confidence threshold, to obtain the real - time optimal handover sequence in the current scenario includes:

[0041] Compare the matching result confidence with the preset confidence threshold. When the matching result confidence is greater than the confidence threshold, determine the similar historical handover sequence as the candidate handover sequence. When the matching result confidence is less than the confidence threshold, perform matching optimization on the similar historical handover sequence to obtain the candidate handover sequence;

[0042] Construct the state space of the dynamic programming algorithm according to the number of DRM broadcast signal modes;

[0043] Map the real-time signal strength attenuation granularity value into the state space, and generate a state transition matrix in combination with a preset signal quality scoring rule;

[0044] According to the state transition matrix and the candidate handover sequence, perform multi-mode broadcast signal handover planning analysis to obtain the real-time optimal handover sequence in the current scenario.

[0045] In a second aspect, the present invention provides a DRM-based intelligent multi-mode broadcast signal switching device, including:

[0046] A data acquisition module for acquiring the real-time geographical location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical handover record database;

[0047] A region division module for performing region transition analysis according to the real-time geographical location information, inputting the obtained region transition zone and the real-time geographical location information into a pre-trained geographical region division model to obtain the number of DRM broadcast signal modes in the region transition zone;

[0048] An attenuation analysis module for constructing a weighted data set according to the real-time weather conditions, and inputting the constructed dynamic weather weighted data set into a pre-trained signal attenuation model to obtain the real-time signal strength attenuation granularity value of different DRM signal frequency bands;

[0049] A similarity analysis module for performing similarity analysis according to the historical handover record database in combination with the real-time geographical location information and the real-time weather conditions, and extracting the most similar historical handover sequence;

[0050] A matching calculation module for performing matching calculation according to the similar historical handover sequence, the real-time signal strength attenuation granularity value, the real-time geographical location information, and the real-time weather conditions to obtain the matching result confidence;

[0051] A result output module for performing multi-mode broadcast signal handover planning analysis according to the similar historical handover sequence, the real-time signal strength attenuation granularity value, the matching result confidence, and the number of DRM broadcast signal modes in combination with a preset confidence threshold to obtain the real-time optimal handover sequence in the current scenario.

[0052] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the DRM-based intelligent multi-mode broadcast signal switching method described in any one of the above.

[0053] Fourthly, the present invention also provides a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the DRM-based intelligent switching method for multi-mode broadcast signals described in any one of the above.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] (1) By obtaining the real-time geographical location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical switching record database, and performing standardized preprocessing such as coordinate format conversion, error correction, unit unification, and time series alignment on the original data, the present invention eliminates the spatio-temporal correlation deviation caused by format differences in multi-source data; through data integrity verification, it improves the accuracy of subsequent model input, reduces computational redundancy caused by data inconsistency, and provides high-reliability underlying data support for signal switching decisions in dynamic scenarios.

[0056] (2) The present invention inputs the real-time geographical location information into a pre-trained geographical area division model, determines the regional transition zone based on the dynamic point-to-polygon distance calculation, and combines the iterative optimization of the regional boundary parameters by the machine learning model to solve the problem of misjudgment of signal modes caused by blurred boundaries in traditional static division; by dynamically adjusting the number of DRM broadcast signal modes, it realizes the precise collaborative management of multi-band signals in the regional transition zone, reduces the signal switching delay caused by geographical location offset, and improves the real-time performance and adaptability of regional determination.

[0057] (3) By constructing a dynamic weather weighted data set according to the real-time weather conditions in combination with the preset weather type classification rules, and inputting the data set into a pre-trained signal attenuation model, the present invention obtains the real-time signal strength attenuation granularity values of different DRM signal bands. Using the training mapping relationship between the historical dynamic weather weighted data set and the historical real-time signal strength attenuation granularity values, compared with the overall attenuation estimation method, it can more accurately reflect the attenuation characteristics of each band signal under the current weather conditions, avoid the deviation of signal quality assessment, and improve the accuracy and reliability of switching decisions.

[0058] (4) The present invention combines the historical switching records and real-time scene parameters for similarity analysis, performs spatio-temporal alignment on the historical sequence through the dynamic time window algorithm, and uses the weighted Euclidean distance to fuse the multi-dimensional weather similarities of precipitation, haze, and visibility, improving the candidate sequence screening efficiency and reducing the spatio-temporal consistency matching error of similar historical switching sequences.

[0059] (5) By calculating the item-by-item matching of the historical signal strength attenuation granularity value, historical geographical location, and historical weather conditions in the similar historical switching sequence with the real-time data, the present invention generates an attenuation matching degree, a geographical matching degree, and a weather matching degree, and combines the cross-interference analysis of the historical signal source interference and the real-time signal strength attenuation granularity value to obtain an interference matching degree. Finally, the matching result confidence degree is generated through weighted fusion with a preset fusion weight. Compared with the single-dimensional matching method, it can comprehensively reflect the similarity between the real-time scenario and the historical data, improve the reliability of the confidence degree score, and provide a more accurate decision-making basis for the subsequent dynamic programming algorithm.

[0060] (6) By comparing the matching result confidence degree with a preset confidence degree threshold, and determining the generation method of the candidate switching sequence according to the comparison result. When the confidence degree is greater than the threshold, the similar historical switching sequence is directly used as the candidate switching sequence. When the confidence degree is less than the threshold, the similar historical switching sequence is optimized for matching to generate the candidate switching sequence. Compared with the single sequence selection method, it can make full use of the high-confidence characteristics of historical data and optimize for low-confidence scenarios to improve adaptability. At the same time, the state space of the dynamic programming algorithm is constructed according to the number of DRM broadcast signal modes, the real-time signal strength attenuation granularity value is mapped to the state space, and the state transition matrix is generated in combination with the preset signal quality scoring rule. Finally, the real-time optimal switching sequence in the current scenario is obtained through the analysis of the state transition matrix and the candidate switching sequence, ensuring that the matching accuracy and stability of the switching path and the current signal environment are improved, and providing a reliable planning basis for the multi-mode broadcast signal switching. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a schematic flowchart of a multi-mode broadcast signal intelligent switching method based on DRM provided by the first embodiment of the present invention;

[0062] Figure 2 is a schematic structural diagram of a multi-mode broadcast signal intelligent switching system based on DRM provided by the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0064] Referring to Figure 1 , the first embodiment of the present invention provides a multi-mode broadcast signal intelligent switching method based on DRM, including the following steps:

[0065] S11. Obtain the real-time geographical location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical switching record database;

[0066] S12. Conduct regional transition analysis based on the real-time geographical location information, input the obtained regional transition zone and the real-time geographical location information into a pre-trained geographical area division model, and obtain the number of DRM broadcast signal patterns in the regional transition zone;

[0067] S13. Construct a weighted data set according to the real-time weather conditions, input the constructed dynamic weather weighted data set into a pre-trained signal attenuation model, and obtain the real-time signal strength attenuation granularity values for different DRM signal frequency bands;

[0068] S14. Conduct similarity analysis based on the historical switching record database, in combination with the real-time geographical location information and the real-time weather conditions, and extract the most similar historical switching sequence;

[0069] S15. Conduct matching calculations based on the similar historical switching sequence, the real-time signal strength attenuation granularity value, the real-time geographical location information, and the real-time weather conditions, and obtain the matching result confidence level;

[0070] S16. Conduct multi-mode broadcast signal switching planning analysis based on the similar historical switching sequence, the real-time signal strength attenuation granularity value, the matching result confidence level, and the number of DRM broadcast signal patterns, in combination with a preset confidence threshold, and obtain the real-time optimal switching sequence in the current scenario.

[0071] In step S11, it is necessary to obtain the real-time geographical location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical switching record database.

[0072] In one implementation, obtaining the real-time geographical location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical switching record database includes:

[0073] Obtain the original location data, original weather data, and original historical switching record database of the broadcast receiving device; according to the original location data, conduct adaptive coordinate format conversion and dynamic error correction to generate standardized real-time geographical location information; according to the original weather data, conduct unit standardization and missing value filling to obtain the real-time weather conditions affecting signal propagation; according to the original historical switching record database, conduct time series alignment to obtain the historical switching record database.

[0074] It should be noted that the original location data of the broadcast receiving device is obtained by collecting the longitude and latitude coordinates of the device, and is dynamically updated in combination with the device's moving speed and direction to adapt to the real-time nature of location changes. The original weather data is obtained by collecting rainfall, haze particle concentration, and visibility parameters in the area where the device is located, and is preliminarily screened and supplemented according to the dynamic change trend of the real-time weather to ensure data integrity. The original historical switching record database is formed by extracting stored historical geographical locations, historical weather conditions, and historical switching sequence data, and is preliminarily sorted based on the timestamps and scenario correlations of the historical records for subsequent alignment processing. The original location data of the broadcast receiving device may contain longitude and latitude information or positioning error noise in different coordinate systems. An adaptive coordinate format conversion is performed to uniformly convert it into a standard geographic coordinate system. At the same time, dynamic error correction is carried out to eliminate positioning offsets caused by multipath effects or environmental interference, generating standardized real-time geographical location information with a unified format and controllable accuracy. The precipitation, haze concentration, and visibility parameters included in the original weather data may have problems such as mixed unit systems or missing parts of the parameters. It is necessary to convert the imperial units to international standard units through unit unification processing, for example, converting inches of precipitation to millimeters, and interpolating adjacent period data or filling in data from spatially adjacent areas for the missing visibility parameters to form complete real-time weather conditions that affect signal propagation and have consistent measurements. The original historical switching record database contains historical timestamps, geographical locations, weather parameters, and switching path records. However, there may be time zone differences or inconsistent sampling intervals in the timestamps of different records. It is necessary to unify the time bases of the historical data through a time series alignment algorithm and resample and align them according to a preset time granularity to ensure that the time correlation of historical switching events meets the analysis requirements. The real-time geographical location information is the standardized longitude and latitude data after coordinate conversion and error correction, and is used to determine the area where the device is located and the range of the transition zone. The real-time weather conditions that affect signal propagation are the complete set of meteorological parameters after unit unification and missing value filling, and are used to calculate signal attenuation characteristics. The historical switching record database is a structured data set after time alignment and is used to extract historical switching sequences that match the current scenario.

[0075] In step S12, it is necessary to perform regional transition analysis based on the real-time geographical location information, and input the obtained regional transition zone and the real-time geographical location information into a pre-trained geographical area division model to obtain the number of DRM broadcast signal patterns in the regional transition zone.

[0076] In one implementation, performing regional transition analysis based on the real-time geographical location information, and inputting the obtained regional transition zone and the real-time geographical location information into a pre-trained geographical area division model to obtain the number of DRM broadcast signal patterns in the regional transition zone includes:

[0077] Based on the real-time geographical location information, combined with the preset set of regional polygon boundary coordinates, calculate the distance from a point to a polygon to obtain the minimum boundary distance; compare the minimum boundary distance with the preset transition boundary threshold. When the minimum boundary distance is less than the transition boundary threshold, determine that the location where the device is located is the regional transition zone; use the historical real-time geographical location information and the historical regional transition zone as inputs, and the number of historical DRM broadcast signal patterns as the output, construct a geographical area division model and train it. When the number of training times is greater than or equal to the preset number of training times, determine that the training is completed, and obtain the trained geographical area division model; input the real-time geographical location information and the regional transition zone into the trained geographical area division model to obtain the number of DRM broadcast signal patterns in the regional transition zone.

[0078] It should be noted that according to the standardized longitude and latitude coordinates in the real-time geographical location information, combined with the preset multiple sets of geographical area polygon boundary coordinates, the vertical distance from the current position of the device to the boundaries of each area polygon is calculated point by point through a geometric distance calculation algorithm, and the minimum value among all the distances is selected as the minimum boundary distance. Numerically compare the calculated minimum boundary distance with the preset transition boundary threshold. If the minimum boundary distance is less than the transition boundary threshold, it is determined that the device is located in the regional transition zone. At this time, it is necessary to extract the DRM broadcast signal pattern information that overlaps and covers adjacent areas. The training of the geographical area division model is realized through a machine learning algorithm. Use the geographical location coordinates of the device in the historical record and its corresponding regional transition zone label as input features, and the number of DRM broadcast signal patterns actually supported at this location recorded in the historical database as the output label. Through iterative training, the model learns the mapping relationship between the regional boundary and the number of signal patterns. When the prediction error of the model on the validation set is lower than the preset accuracy or reaches the maximum number of training times, stop training. The trained model receives the real-time geographical location coordinates and the regional transition zone determination result as inputs, and outputs the number of available DRM broadcast signal

[0079] patterns in the current transition zone area. The number of DRM broadcast signal patterns in the regional transition zone refers to the number of different frequency band signal patterns of adjacent areas that are simultaneously supported within the range of this transition zone. For example, within the range of the transition zone, the high-frequency pattern of City A and the low-frequency pattern of City B are simultaneously supported, which is used for the definition of the state space dimension and the construction of the candidate signal source set in the subsequent dynamic programming algorithm.

[0080] In step S13, it is necessary to construct a weighted data set according to the real-time weather conditions, and input the constructed dynamic weather weighted data set into the pre-trained signal attenuation model to obtain the real-time signal strength attenuation granularity values of different DRM signal frequency bands.

[0081] In one implementation, a weighted data set is constructed according to the real-time weather conditions, and the constructed dynamic weather weighted data set is input into a pre-trained signal attenuation model to obtain real-time signal strength attenuation granularity values for different DRM signal frequency bands, including:

[0082] According to the real-time weather conditions, combined with the preset weather type classification rules, dynamic weight allocation is performed to obtain a dynamic weather weighted data set; using the historical dynamic weather weighted data set as the input and the historical real-time signal strength attenuation granularity value as the output, a signal attenuation model is constructed and trained. When the number of training times is greater than or equal to the preset number of training times, it is determined that the training is completed, and a trained signal attenuation model is obtained; the dynamic weather weighted data set is input into the trained signal attenuation model to obtain real-time signal strength attenuation granularity values for different DRM signal frequency bands.

[0083] It should be noted that according to the precipitation, haze concentration and visibility parameters in the real-time weather conditions, the dynamic weight distribution of precipitation intensity, haze level and visibility range is carried out in combination with the preset weather type classification rules. For example, in heavy rainfall weather, the weight ratio of the rain attenuation parameter is increased, while in the haze-dominated scenario, the contribution coefficient of haze attenuation is increased to generate a dynamic weather weighted dataset reflecting the weights of current weather characteristics. The preset weather type classification rules classify the weather types into multiple categories based on the precipitation, haze concentration and visibility parameters in the real-time weather conditions and assign dynamic weights to each weather characteristic. For example, when the precipitation exceeds the first precipitation threshold, it is determined as heavy rainfall weather and the weight coefficient of the impact of rainfall on signal attenuation is increased. When the haze concentration is higher than the first haze concentration threshold and the visibility is lower than the first visibility threshold, it is determined as heavy haze weather and the weight ratio of haze attenuation is increased. At the same time, the weight ratio of each weather characteristic is dynamically adjusted according to the real-time change trend of the weather parameters in the real-time weather conditions. For example, when the rainfall intensity suddenly increases, the weight of the rain attenuation factor is quickly increased to ensure that the generated dynamic weather weighted dataset can accurately reflect the differential impact of the current weather conditions on the propagation of different DRM signal frequency bands. This rule is established in advance by analyzing the correlation between historical weather data and signal attenuation and is continuously optimized in combination with the adaptive adjustment mechanism of the real-time scenario to improve the accuracy of signal attenuation model prediction and the adaptability of handover decisions. The training of the signal attenuation model is achieved through machine learning algorithms. The weight combinations of weather parameters in the historical dynamic weather weighted dataset are used as input features, and the measured signal attenuation values of different DRM frequency bands at the corresponding historical moments are used as output labels. The mapping relationship between weather parameters and signal attenuation is established through iterative training. When the model prediction error converges to the preset range or reaches the maximum number of training times, the training is completed. The trained model receives the real-time dynamic weather weighted dataset as input and outputs the real-time signal strength attenuation granularity values of each DRM signal frequency band under the current weather conditions. The real-time signal strength attenuation granularity values of different DRM signal frequency bands represent the intensity attenuation amount of each frequency band signal caused by weather factors per unit distance. For example, the high-frequency band signal is more significantly attenuated by precipitation, and the low-frequency band signal is more significantly affected by haze, which are used for signal quality evaluation in subsequent handover sequence matching calculations and scoring rules in dynamic programming algorithms to ensure that handover decisions accurately reflect the attenuation characteristics of the current signal propagation environment.

[0084] In step S14, it is necessary to perform similarity analysis according to the historical handover record database in combination with the real-time geographical location information and the real-time weather conditions, and extract the similar historical handover sequence with the highest similarity.

[0085] In one implementation, performing similarity analysis according to the historical handover record database in combination with the real-time geographical location information and the real-time weather conditions, and extracting the similar historical handover sequence with the highest similarity includes:

[0086] Extract candidate historical handover records with a geographical location error less than a preset geographical location error threshold based on the historical handover record database and in combination with the real-time geographical location information; extract corresponding historical weather condition parameters according to the candidate historical handover records; perform multi-dimensional similarity calculation based on the historical weather condition parameters and the real-time weather conditions to obtain a weighted Euclidean distance similarity that comprehensively considers precipitation intensity, haze concentration, and visibility; perform time dimension alignment on the candidate historical handover records to generate a spatio-temporal alignment sequence; perform weighted fusion based on the spatio-temporal alignment sequence and the weighted Euclidean distance similarity to generate a comprehensive similarity score, and determine the historical handover sequence with the highest comprehensive similarity score in the spatio-temporal alignment sequence as the similar historical handover sequence; the similar historical handover sequence includes historical handover background information and the corresponding handover sequence; the historical handover background information includes historical signal strength attenuation granularity values, historical geographical locations, historical weather conditions, and historical signal source interference.

[0087] It should be noted that based on the longitude and latitude differences between the historical geographical location information and the real-time geographical location information in the historical handover record database, historical records with an error less than the preset geographical location error threshold are screened out as candidate historical handover records. The corresponding historical weather parameters are extracted from the candidate records, including precipitation intensity, haze concentration, and visibility data, and multi-dimensional similarity calculation is performed with the current real-time weather conditions. The corresponding weighted Euclidean distance similarity is calculated for precipitation, haze, and visibility through preset weight allocation. For sequences with a long time span in the candidate historical handover records, the dynamic time window algorithm is used to adaptively adjust the window size, and the long sequence is segmented into several sub-segments and time dimension alignment is performed to generate a spatio-temporal alignment sequence. The time matching degree of the spatio-temporal alignment sequence and the weighted Euclidean distance similarity are fused according to a preset ratio to generate a comprehensive similarity, and the historical handover sequence with the highest similarity is selected as the similar historical handover sequence. The similar historical handover sequence contains historical signal attenuation values, geographical locations, weather conditions, and actual handover path information, which are used for multi-dimensional comparative analysis in subsequent matching calculations and provide historical interference intensity and handover path references for the dynamic programming algorithm to support high-confidence signal handover decisions.

[0088] In step S15, it is necessary to perform a matching calculation based on the similar historical handover sequence, the real-time signal strength attenuation granularity value, the real-time geographical location information, and the real-time weather conditions to obtain the confidence level of the matching result.

[0089] In one implementation, performing a matching calculation based on the similar historical handover sequence, the real-time signal strength attenuation granularity value, the real-time geographical location information, and the real-time weather conditions to obtain the confidence level of the matching result includes:

[0090] The historical signal strength attenuation granularity values, historical geographical locations and historical weather conditions in the similar historical switching sequences are matched and calculated item by item with the real-time signal strength attenuation granularity values, the real-time geographical location information and the real-time weather conditions to obtain the attenuation matching degree, geographical matching degree and weather matching degree; the historical signal source interference in the similar historical switching sequence is cross-interference analyzed with the real-time signal strength attenuation granularity value to obtain the interference matching degree; according to the attenuation matching degree, the geographical matching degree, the weather matching degree and the interference matching degree, combined with the preset fusion weights, weighted fusion is performed to obtain the matching result confidence degree.

[0091] It should be noted that the historical signal strength attenuation granularity value recorded in the similar historical switching sequence is compared with the attenuation value calculated in real time, and the degree of matching between the two in attenuation characteristics is calculated to obtain the attenuation matching degree. The longitude and latitude deviations between the historical geographic location coordinates and the real-time geographic location coordinates are converted into geographic matching degrees. The weather matching degree is obtained by calculating the weighted Euclidean distance similarity of the historical weather parameters and the real-time weather parameters through preset weights. At the same time, the signal source interference intensity recorded in the historical switching sequence is associated with the real-time signal attenuation value to evaluate the possibility of recurrence of the historical interference mode under the current signal environment and generate the interference matching degree. The above four matching degrees are weighted and summed based on the preset weight allocation rules. For example, in the regional transition zone scenario, the weight ratio of the attenuation matching degree is increased, and the weight ratio of the geographic matching degree is reduced, and finally the matching result confidence is generated by fusion. The matching result confidence indicates the matching credibility between the current scene and the historical switching sequence, which is obtained by the fusion calculation of multi-dimensional parameters and is used for the screening and optimization of candidate switching sequences in the dynamic programming algorithm.

[0092] In step S16, it is necessary to perform multi-mode broadcast signal switching planning analysis based on the similar historical switching sequence, the real-time signal strength attenuation granularity value, the matching result confidence and the number of DRM broadcast signal modes, combined with a preset confidence threshold, to obtain the real-time optimal switching sequence in the current scenario.

[0093] In one implementation, based on the similar historical switching sequence, the real-time signal strength attenuation granularity value, the matching result confidence and the number of DRM broadcast signal modes, combined with a preset confidence threshold, a multi-mode broadcast signal switching planning analysis is performed to obtain a real-time optimal switching sequence in the current scenario, including:

[0094] The confidence of the matching result is compared with a preset confidence threshold. When the confidence of the matching result is greater than the confidence threshold, the similar historical switching sequence is determined to be a candidate switching sequence. When the confidence of the matching result is less than the confidence threshold, the similar historical switching sequence is matched and optimized to obtain a candidate switching sequence. According to the number of DRM broadcast signal modes, a state space of a dynamic programming algorithm is constructed. The real-time signal strength attenuation granularity value is mapped to the state space, and a state transition matrix is ​​generated in combination with a preset signal quality scoring rule. According to the state transition matrix and the candidate switching sequence, a multi-mode broadcast signal switching planning analysis is performed to obtain a real-time optimal switching sequence in the current scenario.

[0095] It should be noted that the confidence of the matching result is numerically compared with the preset confidence threshold. If the confidence is higher than the threshold, the similar historical switching sequence is directly used as the candidate switching sequence. If it is lower than the threshold, the switching order of the signal source in the historical sequence is adjusted or the set of candidate signal sources is expanded for matching optimization to generate a candidate switching sequence that adapts to the real-time scenario. The state dimension of the dynamic programming algorithm is determined according to the number of DRM broadcast signal modes. Each state node corresponds to a signal mode or a mixed mode, and a state space covering all available signal modes is constructed. The real-time signal strength attenuation granularity value is mapped to the corresponding state node. The signal attenuation degree, switching delay and historical switching success rate are comprehensively scored in combination with the preset signal quality scoring rules to generate a state transfer matrix that reflects the cost and benefit of inter-state transfer. In the state transfer matrix, search for the switching path that meets the signal stability constraint and has the highest comprehensive score. If the device is located in the regional transition zone, the inter-regional signal coverage compensation factor is introduced to adjust the path weight, and finally the real-time optimal switching sequence in the current scenario is output. The real-time optimal switching sequence is the signal source switching order selected from the candidate paths through a dynamic programming algorithm, which comprehensively considers the signal attenuation characteristics, switching efficiency and historical success rate, and is sent to the broadcast receiving device for execution after ensuring the feasibility of the path through real-time signal quality verification, thereby ensuring the continuity and stability of signal switching.

[0096] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0097] The following describes the working process of the present invention using a common scenario as an example. Figure 2 , which is Figure 1 Schematic diagram of the working scenario of the method.

[0098] Assuming that the broadcast receiving device is in the transition zone between two geographical areas during the mobile process and encounters sudden severe weather conditions, it is necessary to dynamically switch between multiple DRM broadcast signal sources to maintain signal continuity. The present invention implements intelligent switching decision by the following steps:

[0099] First, the original geographical location information, weather parameters, and historical switching records of the broadcast receiving device are obtained in real time. There may be differences in coordinate systems or positioning errors in the original geographical location information. Standardized geographical location data is generated through coordinate format conversion and error correction. In the weather parameters, there may be inconsistencies in measurement units or data missing in precipitation, haze concentration, and visibility. After standardizing the measurement units and interpolating to fill in the missing data, a complete set of real-time weather condition data is formed. The timestamps in the historical switching records may be out of order due to inconsistent time zones. They are unified into a standardized format through a time series alignment algorithm to ensure the temporal consistency of subsequent analysis.

[0100] The standardized geographical location information is input into a pre-trained geographical area division model, which is constructed based on the mapping relationship between historical geographical locations and regional boundaries. By calculating the shortest distance between the device's current position and the preset regional polygon boundary, it is determined whether it is in the transition zone. If the distance is less than the preset threshold, it is determined as the transition zone, and the number of DRM broadcast signal modes supported by this area is extracted. For example, the transition zone may support the mixed coverage of different frequency band signals in adjacent areas. Through the dynamic optimization of historical boundary parameters by a machine learning model, the range of the transition zone can be adjusted adaptively to avoid regional division deviation caused by environmental changes.

[0101] The real-time weather conditions are input into a pre-trained signal attenuation model, which is trained through the non-linear relationship between historical weather data and measured signal attenuation values. For different DRM signal frequency bands, the model dynamically assigns weights to weather parameters such as precipitation and haze, and calculates the signal strength attenuation granularity values for each frequency band. For example, high-frequency signals are more significantly affected by precipitation, and the model calculates its attenuation contribution through the rain attenuation component rule, while low-frequency signals are more dependent on the attenuation component of haze concentration. By dynamically adjusting the weight coefficients of different weather parameters, the model can capture the instantaneous fluctuation characteristics of signal attenuation and avoid the overall estimation deviation of traditional linear models.

[0102] Combined with the historical switching record database, a similarity analysis of the real-time geographical location and weather conditions is carried out. First, the historical records with geographical location errors less than the preset threshold are screened out, and the corresponding historical weather parameters are extracted. The multi-dimensional similarity of precipitation intensity, haze concentration, and visibility is calculated through the weighted Euclidean distance, and at the same time, the dynamic time window algorithm is used to segment and align the long historical sequence. For example, the historical switching sequence is segmented into several sub-segments according to the time span. Through time dimension alignment and sub-segment weighted fusion, a spatio-temporal alignment sequence matching the current real-time data is generated. Finally, the historical switching sequence with the highest comprehensive similarity score is extracted, which contains historical signal attenuation values, geographical locations, and interference intensity information.

[0103] The extracted similar historical switching sequences are matched item by item with the real-time data to calculate the attenuation matching degree, geographical matching degree, and weather matching degree. Cross-interference analysis is performed between the historical signal source interference intensity and the current real-time attenuation value to generate the interference matching degree. According to the preset weight rules, the above matching degrees are weighted and fused to generate a comprehensive confidence score. If the confidence level exceeds the preset threshold, the historical sequence is directly adopted as the candidate solution; if it is lower than the threshold, the real-time optimization mechanism is triggered to reconstruct the candidate sequence, such as dynamically expanding the candidate signal source set based on the current attenuation value.

[0104] The state space of the dynamic programming algorithm is constructed according to the number of DRM broadcast signal patterns. The real-time signal strength attenuation granularity value is mapped to the state nodes, and a state transition matrix is generated in combination with the signal quality scoring rules. The scoring rules comprehensively consider factors such as the signal attenuation value, switching delay, and historical switching success rate. For example, an increase in the attenuation value or an extension of the switching delay will reduce the path score. When searching for the optimal path that satisfies the signal stability constraint in the state transition matrix, if the device is located in the regional transition zone, a signal coverage compensation factor is introduced to dynamically adjust the path weight to solve the problem of signal coverage differences between adjacent regions. The finally generated candidate switching sequence needs to pass the real-time signal quality verification, such as monitoring the signal strength and stability indicators after switching. If the verification fails, the path search process is re-triggered until a real-time optimal switching sequence that meets the requirements is output.

[0105] In the scenario where the broadcast receiving device moves to the regional transition zone and encounters sudden weather changes, through standardized data processing, dynamic model analysis, and multi-dimensional matching calculations, the real-time optimization of the signal switching sequence is realized, effectively avoiding the risk of signal interruption caused by data deviation, environmental mutation, or historical reference failure, and achieving high-precision matching between historical switching data and the real-time scenario.

[0106] In summary, the present invention discloses an intelligent switching method for multi-mode broadcast signals based on DRM, including obtaining the real-time geographical location information of a broadcast receiving device, the real-time weather conditions affecting signal propagation, and a historical switching record database; inputting the real-time geographical location information into a pre-trained geographical area division model to obtain the number of DRM broadcast signal modes in the regional transition zone; constructing a weighted data set according to the real-time weather conditions, and inputting the constructed dynamic weather weighted data set into a pre-trained signal attenuation model to obtain the real-time signal strength attenuation granularity values of different DRM signal frequency bands; performing similarity analysis on the historical switching record database in combination with the real-time geographical location information and the real-time weather conditions to extract the most similar historical switching sequence; performing matching calculations according to the similar historical switching sequence, the real-time signal strength attenuation granularity values, the real-time geographical location information, and the real-time weather conditions to obtain a matching result confidence level; performing multi-mode broadcast signal switching planning analysis according to the similar historical switching sequence, the real-time signal strength attenuation granularity values, the matching result confidence level, and the number of DRM broadcast signal modes, in combination with a preset confidence threshold, to obtain the real-time optimal switching sequence in the current scenario, realizing a high-precision matching between historical switching data and the real-time scenario.

[0107] Referring to Figure 2 , the second embodiment of the present invention provides an intelligent switching device for multi-mode broadcast signals based on DRM, including:

[0108] A data acquisition module, configured to obtain the real-time geographical location information of a broadcast receiving device, the real-time weather conditions affecting signal propagation, and a historical switching record database;

[0109] A regional division module, configured to perform regional transition analysis according to the real-time geographical location information, and input the obtained regional transition zone and the real-time geographical location information into a pre-trained geographical area division model to obtain the number of DRM broadcast signal modes in the regional transition zone;

[0110] An attenuation analysis module, configured to construct a weighted data set according to the real-time weather conditions, and input the constructed dynamic weather weighted data set into a pre-trained signal attenuation model to obtain the real-time signal strength attenuation granularity values of different DRM signal frequency bands;

[0111] A similarity analysis module, configured to perform similarity analysis on the historical switching record database in combination with the real-time geographical location information and the real-time weather conditions to extract the most similar historical switching sequence;

[0112] A matching calculation module, configured to perform matching calculation according to the similar historical switching sequence, the real-time signal strength attenuation granularity value, the real-time geographical location information, and the real-time weather condition, so as to obtain a matching result confidence level;

[0113] A result output module, configured to perform multi-mode broadcast signal switching planning analysis according to the similar historical switching sequence, the real-time signal strength attenuation granularity value, the matching result confidence level, and the number of DRM broadcast signal modes, in combination with a preset confidence threshold, so as to obtain a real-time optimal switching sequence in the current scenario.

[0114] It should be noted that a multi-mode broadcast signal intelligent switching device based on DRM provided in an embodiment of the present invention is used to execute all process steps of a multi-mode broadcast signal intelligent switching method based on DRM in the above embodiment. The working principles and beneficial effects of the two correspond one by one, and thus will not be elaborated here.

[0115] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a multi-mode broadcast signal intelligent switching program based on DRM. When the processor executes the computer program, the steps in the above-mentioned embodiments of various multi-mode broadcast signal intelligent switching methods are implemented, such as Figure 1 the step S11 shown. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, such as a similarity analysis module.

[0116] Exemplarily, the computer program may be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the electronic device.

[0117] The electronic device may be a computing device such as a desktop computer, a notebook, a palm computer, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device, and do not constitute a limitation to the electronic device. The electronic device may include more or fewer components than those described above, or combine certain components, or different components. For example, the electronic device may further include input / output devices, network access devices, a bus, etc.

[0118] The so-called processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), 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. The processor is the control center of the electronic device and connects all parts of the entire electronic device using various interfaces and lines.

[0119] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and by calling the data stored in the memory, the processor realizes various functions of the electronic device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.

[0120] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0121] It should be noted that the device embodiments described above are merely illustrative. The units described 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 to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative effort.

[0122] The specific embodiments described above have further elaborated on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A DRM-based multi-mode broadcast signal intelligent switching method, characterized in that: include: Obtain real-time geographic location information, real-time weather conditions and historical switching record database of broadcast receiving devices; Performing regional transition analysis according to the real-time geographic location information, inputting the regional transition zone obtained through analysis and the real-time geographic location information into a pre-trained geographic region division model, and obtaining the number of DRM broadcast signal modes in the regional transition zone; Constructing a weighted data set according to the real-time weather conditions, inputting the constructed dynamic weather weighted data set into a pre-trained signal attenuation model to obtain real-time signal strength attenuation granularity values ​​of different DRM signal frequency bands; According to the historical switching record database, similarity analysis is performed in combination with the real-time geographic location information and the real-time weather conditions to extract similar historical switching sequences with the highest similarity; Perform matching calculation according to the similar historical switching sequence, the real-time signal strength attenuation granularity value, the real-time geographic location information and the real-time weather condition to obtain a matching result confidence; According to the similar historical switching sequence, the real-time signal strength attenuation granularity value, the matching result confidence and the number of DRM broadcast signal modes, combined with a preset confidence threshold, a multi-mode broadcast signal switching planning analysis is performed to obtain the real-time optimal switching sequence in the current scenario.

2. The DRM-based multi-mode broadcast signal intelligent switching method according to claim 1, characterized in that: The method of obtaining the real-time geographic location information of the broadcast receiving device, the real-time weather conditions affecting signal propagation, and the historical switching record database includes: Obtaining original location data, original weather data and original historical switching record database of broadcast receiving equipment; According to the original location data, adaptive coordinate format conversion and dynamic error correction are performed to generate standardized real-time geographic location information; According to the original weather data, the measurement units are unified and the missing values ​​are filled to obtain the real-time weather conditions that affect the signal propagation; According to the original historical switching record database, time series alignment is performed to obtain a historical switching record database.

3. The DRM-based multi-mode broadcast signal intelligent switching method according to claim 1, characterized in that: The performing of regional transition analysis according to the real-time geographic location information, inputting the regional transition zone obtained through analysis and the real-time geographic location information into a pre-trained geographic region division model, and obtaining the number of DRM broadcast signal modes in the regional transition zone, includes: According to the real-time geographic location information, combined with a preset set of regional polygon boundary coordinates, a point-to-polygon distance calculation is performed to obtain a minimum boundary distance; According to the minimum boundary distance, a comparison is made with a preset transition boundary threshold, and when the minimum boundary distance is less than the transition boundary threshold, it is determined that the location of the device is a regional transition zone; Taking historical real-time geographic location information and historical regional transition zones as input and the number of historical DRM broadcast signal modes as output, a geographic region division model is constructed and trained. When the number of training times is greater than or equal to the preset number of training times, the training is determined to be completed, and a trained geographic region division model is obtained; The real-time geographic location information and the regional transition zone are input into the trained geographic region division model to obtain the number of DRM broadcast signal modes in the regional transition zone.

4. The DRM-based multi-mode broadcast signal intelligent switching method according to claim 1, characterized in that: The method of constructing a weighted data set according to the real-time weather conditions, inputting the constructed dynamic weather weighted data set into a pre-trained signal attenuation model, and obtaining real-time signal strength attenuation granularity values ​​of different DRM signal frequency bands includes: According to the real-time weather conditions, combined with preset weather type classification rules, dynamic weight allocation is performed to obtain a dynamic weather weighted data set; The historical dynamic weather weighted data set is used as input, and the historical real-time signal strength attenuation granularity value is used as output, a signal attenuation model is constructed and trained, and the training is determined to be completed when the number of training times is greater than or equal to the preset number of training times, and a trained signal attenuation model is obtained; The dynamic weather weighted dataset is input into The trained signal attenuation model is then used to obtain the real-time signal strength attenuation granularity values ​​of different DRM signal frequency bands.

5. The DRM-based multi-mode broadcast signal intelligent switching method according to claim 1, characterized in that: The performing similarity analysis based on the historical switching record database and combining the real-time geographic location information with the real-time weather conditions to extract similar historical switching sequences with the highest similarity includes: Extracting candidate historical switching records whose geographical location errors are less than a preset geographical location error threshold according to the historical switching record database and in combination with the real-time geographical location information; Extracting corresponding historical weather condition parameters according to the candidate historical switching records; Based on the historical weather condition parameters and the real-time weather conditions, a multi-dimensional similarity calculation is performed to obtain a weighted Euclidean distance similarity that comprehensively considers precipitation intensity, haze concentration, and visibility; Perform time dimension alignment according to the candidate historical switching records to generate a time-space alignment sequence; Perform weighted fusion according to the spatiotemporal alignment sequence and the weighted Euclidean distance similarity to generate a comprehensive similarity score, and determine the historical switching sequence with the highest comprehensive similarity score in the spatiotemporal alignment sequence as the similar historical switching sequence; The similar historical switching sequence includes historical switching background information and corresponding switching sequence; The historical switching background information includes historical signal strength attenuation granularity values, historical geographical locations, historical weather conditions, and historical signal source interference.

6. The DRM-based multi-mode broadcast signal intelligent switching method according to claim 1, characterized in that: The performing matching calculation according to the similar historical switching sequence, the real-time signal strength attenuation granularity value, the real-time geographic location information and the real-time weather condition to obtain the matching result confidence includes: Match and calculate the historical signal strength attenuation granularity value, historical geographical location and historical weather conditions in the similar historical switching sequence with the real-time signal strength attenuation granularity value, the real-time geographical location information and the real-time weather conditions item by item to obtain the attenuation matching degree, geographical matching degree and weather matching degree; Performing cross-interference analysis on the historical signal source interference in the similar historical switching sequence and the real-time signal strength attenuation granularity value to obtain an interference matching degree; According to the attenuation matching degree, the geographical matching degree, the weather matching degree and the interference matching degree, combined with the preset fusion weight, weighted fusion is performed to obtain the matching result confidence.

7. The DRM-based multi-mode broadcast signal intelligent switching method according to claim 1, characterized in that: The method of performing multi-mode broadcast signal switching planning analysis based on the similar historical switching sequence, the real-time signal strength attenuation granularity value, the matching result confidence and the number of DRM broadcast signal modes in combination with a preset confidence threshold to obtain a real-time optimal switching sequence in the current scenario includes: Comparing the matching result confidence with a preset confidence threshold, when the matching result confidence is greater than the confidence threshold, determining the similar historical switching sequence as a candidate switching sequence, and when the matching result confidence is less than the confidence threshold, performing matching optimization on the similar historical switching sequence to obtain a candidate switching sequence; Constructing a state space of a dynamic programming algorithm according to the number of DRM broadcast signal modes; Mapping the real-time signal strength attenuation granularity value to the state space, and generating a state transfer matrix in combination with a preset signal quality scoring rule; According to the state transfer matrix and the candidate switching sequence, a multi-mode broadcast signal switching planning analysis is performed to obtain a real-time optimal switching sequence in the current scenario.

8. A DRM-based multi-mode broadcast signal intelligent switching system, characterized in that: include: A data acquisition module, used to obtain real-time geographic location information of broadcast receiving equipment, real-time weather conditions affecting signal propagation, and a historical switching record database; A region division module, configured to perform a region transition analysis based on the real-time geographic location information, input the region transition zone obtained through the analysis and the real-time geographic location information into a pre-trained geographic region division model, and obtain the number of DRM broadcast signal modes in the region transition zone; An attenuation analysis module is used to construct a weighted data set according to the real-time weather conditions, input the constructed dynamic weather weighted data set into a pre-trained signal attenuation model, and obtain the real-time signal strength attenuation granularity value of different DRM signal frequency bands; A similarity analysis module, configured to perform similarity analysis based on the historical switching record database, in combination with the real-time geographic location information and the real-time weather conditions, and extract similar historical switching sequences with the highest similarity; A matching calculation module, used to perform matching calculation according to the similar historical switching sequence, the real-time signal strength attenuation granularity value, the real-time geographic location information and the real-time weather conditions, to obtain a matching result confidence; The result output module is used to perform multi-mode broadcast signal switching planning analysis based on the similar historical switching sequence, the real-time signal strength attenuation granularity value, the matching result confidence and the number of DRM broadcast signal modes, combined with a preset confidence threshold, to obtain the real-time optimal switching sequence in the current scenario.

9. An electronic device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the DRM-based multi-mode broadcast signal intelligent switching method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the DRM-based multi-mode broadcast signal intelligent switching method as described in any one of claims 1 to 7.

Images