A 5g message sending failure retransmission optimization method and system

Abstract

The application provides a 5G message sending failure retransmission optimization method and system, comprising: constructing a multi-dimensional failure cause label for a message with sending failure, the label comprising a network state dimension, a user state dimension and a base station load dimension; calculating a dynamic weight based on the multi-dimensional failure cause label to obtain a failure feature vector for the message; adaptively selecting a retransmission strategy according to the failure feature vector, comprising delayed retransmission, fragmented retransmission, path switching retransmission and cross-protocol degradation retransmission; using a failure heat index (FHI) in the retransmission process, the index being calculated from failure frequency, failure concentration and network area failure density; performing priority scheduling on the message according to the failure heat index to determine whether to immediately retransmit or delay queuing; splitting the 5G message and using a progressive retransmission mechanism to preferentially transmit a message digest and key metadata, and then gradually supplementing the complete content after the network condition is improved.

Description

Technical Field

[0001] This invention relates to the field of 5G communication technology, and in particular to a method and system for optimizing 5G message transmission failure retransmission. Background Technology

[0002] With the popularization of 5G networks and the development of rich media messaging services, communication between user terminals has expanded from traditional short text SMS to multimodal information transmission including text, voice, and video. Compared with traditional SMS, 5G messaging relies on the collaboration of multiple protocol stacks at the transport layer, including HTTP / 2, SIP, and RCSSession, and has the characteristics of high bandwidth, high latency sensitivity, and dynamic link dependency. However, in complex wireless environments, message sending failures are still common, especially when there are network fluctuations, base station overloads, or abnormal user status, including weak signals and mobile handover, messages may fail to be retransmitted multiple times or be delayed in delivery.

[0003] Traditional message retransmission mechanisms mostly employ fixed retransmission intervals or simple acknowledgment / reply (ACK / NACK) mechanisms, lacking multi-dimensional identification and dynamic adaptive capabilities for failure causes. When network conditions are complex and failure modes are diverse, these mechanisms often lead to repeated retransmissions, wasted bandwidth, and message congestion, thereby reducing the overall delivery rate and user experience. Although some systems have introduced delayed retransmission or backup path sending mechanisms, it is still difficult to achieve global optimization of message content, network characteristics, and protocol channels.

[0004] This invention proposes a 5G message transmission failure retransmission optimization method. This method constructs a failure reason labeling system, quantifies and generates failure feature vectors, and combines the Failure Heat Index (FHI) to achieve message priority scheduling. This allows for adaptive selection of the optimal retransmission strategy under different network conditions. Furthermore, this invention introduces a progressive fragmentation retransmission mechanism and a cross-protocol dynamic degradation mechanism. Message content is transmitted in layers according to importance, prioritizing the transmission of digests and key metadata in weak network environments to ensure core information is delivered first. Simultaneously, based on real-time network evaluation results, intelligent switching is performed between protocols such as RCS, IMS, and SMS to ensure stable delivery of messages through degradation paths even when protocol link parts fail. This invention significantly improves the delivery rate and retransmission success rate of 5G rich media messages without increasing additional signaling burden, realizing an evolution from "single-dimensional retransmission" to "adaptive intelligent retransmission," providing a reliable, flexible, and intelligent transmission guarantee solution for 5G message distribution systems. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for optimizing 5G message sending failure retransmission.

[0006] This invention aims to solve the following technical problems existing in the current 5G message sending process: First, the failure cause identification dimension is too single and there is a lack of targeted retransmission strategies. Existing message sending systems mostly rely on simple ACK / NACK. First, existing mechanisms for determining whether to retransmit messages based on timeouts cannot identify specific failure types, such as network fluctuations, excessive base station load, or abnormal user status. Retransmission strategies struggle to accurately match these different failure scenarios, leading to repeated retransmissions or wasted resources. Second, retransmission mechanisms are static and rigid, lacking dynamic adaptability. Traditional systems typically use fixed-interval retransmissions or preset paths, failing to dynamically adjust retransmission windows, fragmentation strategies, or delay strategies based on real-time network characteristics and historical failure patterns. This results in messages potentially failing multiple times in weak or congested environments, reducing overall delivery rates. Third, message content transmission lacks hierarchical design, causing delays in the delivery of important information. In unstable network scenarios, the transmission of complete rich media messages (including images, videos, and files) is highly prone to failure. Existing mechanisms do not differentiate the importance of message content, failing to prioritize the transmission of key information such as summaries and metadata, causing user experience delays or information loss. Therefore, this invention utilizes multi-dimensional failure feature identification and adaptive retransmission algorithms to achieve intelligent retransmission and cross-protocol dynamic degradation of 5G messages, significantly improving message delivery rates and transmission efficiency.

[0007] A method for optimizing 5G message transmission failure retransmission includes:

[0008] S1: Construct multi-dimensional failure reason labels for 5G messages that fail to be sent, including network status dimension, user status dimension, and base station load dimension;

[0009] S2: Calculate dynamic weights based on the multi-dimensional failure reason labels to obtain the failure feature vector for the 5G message;

[0010] S3: Based on the failure feature vector, adaptively select a retransmission strategy, including delayed retransmission, fragmented retransmission, path switching retransmission, and cross-protocol degradation retransmission;

[0011] S4: The Failure Heat Index (FHI) is used during the retransmission process. The index is calculated from the failure frequency, failure concentration, and network area failure density.

[0012] S5: Prioritize messages based on the failure heat index to determine whether to resend them immediately or delay queuing.

[0013] S6: 5G messages are split and a progressive retransmission mechanism is adopted, prioritizing the transmission of message summaries and key metadata, and then gradually retransmitting the complete content as network conditions improve.

[0014] A 5G message transmission failure retransmission optimization system, implemented based on a 5G message transmission failure retransmission optimization method, includes:

[0015] Failure Analysis and Multidimensional Labeling Module: Receives messages and sends feedback information, including success and failure, network logs, extracts and generates multidimensional failure reason labels, including signal strength, packet loss rate, and network type in the network status dimension, user online status and device type in the user status dimension, and current load and congestion status in the base station load dimension, providing the raw data foundation for subsequent strategy selection;

[0016] Failure Feature Vector Generation Module: Quantizes and weights multi-dimensional failure labels, uses dynamic weight formula to generate failure feature vectors, reflects the failure characteristics of each message in different dimensions, and transforms the original labels into numerical vectors that can be used for algorithm decision-making.

[0017] Retransmission strategy selection module: Adaptively selects the optimal retransmission strategy based on the failure feature vector. The strategies include fragmented retransmission PFRT, delayed retransmission, path switching retransmission, and cross-protocol dynamic degradation retransmission CPADR, forming a specific retransmission plan for each message.

[0018] Failure Heat Index Module: Calculates the failure heat index based on failure frequency, failure concentration, and network area failure density. It is used to measure network congestion and areas of concentrated failure, and provides indicators for message prioritization and retransmission rhythm.

[0019] Priority scheduling module: Determines the message retransmission order based on FHI and user historical behavior prediction, decides whether to retransmit immediately or delay queuing, and reasonably allocates the retransmission order in resource-limited and high-failure environments to improve the delivery rate of core content;

[0020] The progressive retransmission module splits messages into digests, key metadata, and the complete content. It prioritizes sending digests or key fragments and gradually retransmits the complete content as network conditions improve. It combines the fragmentation strategy and protocol selection output by the retransmission strategy selection module.

[0021] Furthermore, in step S2, based on the failure reason label, a failure feature vector for the 5G message is obtained, including:

[0022] S21: Network state dimension construction, collecting real-time network state information from the message sending path, including packet loss rate. Average delay Bandwidth usage and network slicing availability After normalizing each indicator, the network state score is calculated: ,in , , , This is an adjustable coefficient, optimized based on historical failure logs;

[0023] S22: User status dimension construction: Collect user online status, terminal type and reliability, user activity, and historical message reception success rate; quantify each indicator and calculate the user status score. ,in Indicates the probability of a user being online. This indicates the terminal reliability score. Indicates the user's recent activity level. This indicates the user's historical reception success rate. , , , These are adjustable weighting coefficients;

[0024] S23: Base station load dimension construction, obtain the current number of connections of the base station where the message was sent. Base station failure rate and regional failure density Information: The specific calculation method for base station load score is as follows: ,in This represents the maximum number of connections a base station can support. These are adjustable weighting coefficients;

[0025] S24: Multidimensional Tag Vector Generation and Fusion, integrating three-dimensional scores into a multidimensional failure reason tag vector for the message: Add dynamic weights to each dimension This forms the final failure feature vector: ;

[0026] S25: Update the corresponding metrics for each failed 5G message, including network packet loss rate, user online probability, and base station load status. Periodically analyze failure logs and adjust weights by minimizing prediction error and using reinforcement learning. ;

[0027] S26: The failure feature vector It serves directly as input to the retransmission strategy selection module, providing a basis for subsequent priority scheduling and progressive retransmission.

[0028] The multidimensional failure reason labels are not only composed of numerical features, but also employ a hierarchical semantic mapping structure:

[0029] Base Tag: Physical metrics extracted directly from raw data, such as packet loss rate, latency, online rate, load value, etc.

[0030] Fusion Tag: The base layer tags are transformed into semantic tags, such as "high latency", "regional congestion", and "high terminal risk", through clustering or rule engine.

[0031] Behavior Tag: Dynamic tags generated by combining historical behavior data, such as "periodic failure user", "instantaneous overload base station", and "short-term high failure area".

[0032] The system uses a sliding time window when generating failure labels. The system aggregates and analyzes message sending failure data over a continuous time period. When a certain dimension indicator exhibits abnormal fluctuations within a window, the system automatically increases the weight of that dimension label. When the dimension's performance stabilizes, a weight decay mechanism is triggered, mathematically expressed as follows: ,in The weights for the i-th dimension include network, user, and base station. The rate of change of this dimension indicator within the current window. For the change threshold, As a weight adjustment factor, this dynamic migration mechanism enables the labeling system to continuously reflect the real changes in the current network environment, rather than static feature descriptions.

[0033] To prevent the formation of "failure hotspots" in the same geographical area or from the same base station within a short period of time, the system further introduces a spatial clustering algorithm. This algorithm models the geographical location attributes of failure labels to identify potential "failure clusters." , This indicates the geographical distance between two failed records. The spatial distance threshold, The system uses a similarity threshold for labels. If the number of failed labels in a cluster exceeds the threshold, the system will generate a new “Regional Failure Tag” and dynamically adjust the weight of the base station load dimension in that region. This mechanism enables the label system to have spatial awareness and prevents concentrated retransmission avalanche at the macro level.

[0034] Furthermore, by employing a label evolution mechanism, the label feature vectors are retrained and optimized periodically (e.g., hourly) based on failed samples and retransmitted successful samples:

[0035] If a certain type of label is associated with a high failure rate for a long period of time, the risk weight of that type of label will be automatically increased.

[0036] If a certain tag is associated with successful resubmission for a long period of time, its risk weight should be reduced.

[0037] For newly emerging unknown labels (such as new terminal models or temporary regional interference), the system will first assign a low-confidence label and then gradually correct it during subsequent learning.

[0038] Furthermore, in step S4, the failure popularity index is used during the retransmission process, including:

[0039] S31: Multi-dimensional failure data collection. After a message transmission failure, multi-dimensional data related to the failure event is automatically collected. This data includes: network layer parameters, specifically signal strength, latency, and packet loss rate; user layer status, specifically terminal online rate, network handover frequency, and mobile speed; base station layer parameters, specifically base station load, congestion level, and handover frequency; message layer characteristics, specifically message type, message length, retransmission count, and real-time requirements; and geographic layer information, specifically the coordinates of the failure location, area identifier, and failure concentration. The data is then processed in a fixed time window. Sampling is performed to form a time-series multidimensional sample set. ;

[0040] S32: Failure density matrix construction. The spatial coordinate region is divided into fixed grids, and the number of failure events in each grid is counted within each time window. A Gaussian kernel function is used to smooth the local region to eliminate data discreteness, resulting in the failure density matrix. Its definition is, Where x and y are the horizontal and vertical coordinates of the geographical location, and t is the time. Let be the geographical coordinates at the time the i-th failure event occurs. For the current time window A set of failure event indexes within the specified time range. Let i be the timestamp of the i-th failure event. It is a spatial distance function, representing a point. With assessment points The distance between them for Geographical location The specific representation is as follows , This is a kernel function used to convert spatial distance into weights;

[0041] S33: Dynamic calculation of dimension weights; the system calculates the information entropy value for each dimension. This reflects the contribution of each dimension to the overall failure trend, and a weight vector is generated accordingly. ,in For the network state dimension, For the user status dimension, From the perspective of base station load, As a message characteristic dimension, For the geographical distribution dimension, the dimension calculation method is as follows: , Let be the real-time information entropy value of the i-th dimension. The sum of information entropy of all dimensions. The higher the information entropy, the greater the volatility and uncertainty of that dimension, and the stronger its explanatory power for system failure modes. Therefore, its weight is also higher. The system dynamically adjusts the weights according to real-time data to ensure that the model adapts to changes in the environment.

[0042] S34: Generation of local failure feature vectors. After obtaining the weight vector, the system extracts the local failure features under the current time window to form a vector. Each component represents the failure rate and statistical indicators of the corresponding dimension, including base station failure rate, message timeout rate, and area density. This vector is the "failure feature fingerprint" under the current network state.

[0043] S35: Calculation of the time decay factor. The impact of historical failure events weakens over time, so a time decay factor α(t) is used. The specific calculation method for α(t) is as follows: , where λ is the attenuation coefficient, used to control the contribution of past data to the current FHI. By introducing α(t), we can avoid the old data from causing excessive interference to the current decision.

[0044] S36: Geographic clustering correction, assessing the clustering of failure events using spatial statistical methods, and calculating the clustering coefficient using Ripley's K function. ,in The specific calculation method is as follows: Where K(d) is the spatial distribution function of actual failure events, representing the average number of other failure event points around any failure event point within an observation radius of d. It is a spatial aggregation function obtained after region area normalization, and its specific calculation method is as follows: A is the area of ​​the observation region, and N is the total number of failure events. Let be the distance between the i-th and j-th failure event points. For indicator functions, when The value is 1 if the condition is met, and 0 otherwise. Let be a reference function for the theoretical random distribution, representing the expected average number of events within a radius d under a completely random distribution. It serves as a baseline to help the system determine if there are anomalous clusters in the current failure distribution. Its calculation method is as follows: ,when A value >0 indicates that failure events show a clear clustering trend in a certain area, and the system will increase the priority retransmission level of messages in that area;

[0045] S37: The system integrates weights across various dimensions, local features, time decay, and geographical clustering to calculate the Failure Heat Index (FHI). κ is the aggregation amplification factor, used to adjust the impact of geographic aggregation effect. The calculated FHI is normalized, and its range is [0,1]. It is divided into five levels: 0 to 0.2 is normal, 0.2 to 0.4 is slight failure, 0.4 to 0.6 is moderate failure, 0.6 to 0.8 is high-risk failure, and above 0.8 is severe failure. The scheduling module automatically determines the retransmission strategy according to the FHI level. If the FHI is low, the queue is merged and the retransmission is delayed; if the FHI is medium, the retransmission is carried out through the normal path; if the FHI is high, path switching is enabled and cross-protocol retransmission is carried out; if the FHI is extremely high, batch message sending is suspended and network diagnosis is triggered. The value of FHI reflects the comprehensive risk level of failure events. When the FHI value is high, it indicates that the failure probability of the current region or user group is on the rise, and network resources should be allocated or the retransmission path should be adjusted first.

[0046] S38: Finally, the final priority score for a single message m. The FHI and the message's own failure feature vector Joint decision: , Let m be the region to which message m belongs, and w be the linear weight vector from message features to score. This is the number of seconds the message has been waiting to be retransmitted. For normalization function, , , These are the coefficients for each item.

[0047] The specific calculation method for the information entropy value of each dimension is as follows:

[0048] Dimensional feature discretization and probability distribution construction: Based on the collected failure-related parameters, the indicators of this dimension are segmented and clustered to form a discretized state set. Then, the frequency of failure events in each state is counted to form a probability distribution: ;

[0049] Noise smoothing calculation, the specific calculation method is as follows: , The minimum noise smoothing coefficient is automatically calculated based on the data volatility of the most recent time window. , The standard deviation of this dimension of features. The adjustment coefficient set for the system ranges from 0.01 to 0.05;

[0050] Dimensional information entropy calculation When the state distribution of a certain dimension is extremely simple, it indicates low entropy, meaning that this dimension contributes weakly to failure. When the state distribution of a certain dimension is very scattered and unpredictable, it indicates high entropy, meaning that this dimension is the main failure factor.

[0051] Multi-window fusion , The current window entropy, The entropy of the previous window, For the entropy of the first two windows, Window weight;

[0052] Entropy normalization, Normalized entropy can be directly used to calculate weights: .

[0053] Time complexity: The calculation of FHI mainly involves summing the failure events within the window and time decay. Sliding windows and incremental updates can be used (incremental updates can reduce the processing of each new event to O(1)), which is suitable for high-concurrency scenarios.

[0054] Space: It is necessary to maintain an event summary (count, time statistics, weighted sum) for each region, rather than storing all raw events, thus saving storage space;

[0055] Robustness: Design backoff values ​​and confidence levels for missing indicators (such as the state of no slice at a certain time) so that FHI can still work stably under incomplete information.

[0056] If a base station FHI exceeds The system uniformly places messages within the base station area with a Priority(m) below a certain threshold into a delay queue and releases them slowly from low to high according to a multi-scale FHI (Fear of Hierarchy Indicator) to avoid a large number of instantaneous retransmissions. For messages with a low FHI but a high Priority(m) for a single message (such as OTP), immediate cross-protocol parallel retransmission is allowed to ensure real-time performance. The system also handles messages with a significantly decreased FHI (below a certain threshold). After that, the delayed digest and remaining fragments are quickly resent using a priority queue (progressive resending).

[0057] When an abnormally sharp increase in FHI is detected within a short period of time (e.g., the growth rate exceeds the threshold in a short window), The system will trigger an "abnormal alarm mode":

[0058] Temporarily freeze all uncompleted retransmission requests in the area and request network-side intervention (such as switching the loopback or notifying the operator).

[0059] Increase FHI monitoring in adjacent areas to determine if it is lateral spread.

[0060] The failure heat index dynamically assesses the risk of message sending failure by integrating multi-dimensional features of time, space, network, users, and messages.

[0061] Implement dynamic retransmission priority decision-making: avoid unnecessary retransmissions, reduce network congestion, and improve overall bandwidth utilization;

[0062] Regional-level predictive capabilities: Identify potential "network failure hotspots" in advance to avoid cascading transmission failures;

[0063] Integrating time decay and historical weighting mechanisms enhances the model's real-time responsiveness, enabling the system to "respond instantly and converge quickly," thus improving its adaptive capabilities.

[0064] Cross-dimensional cause diagnosis: "Failure source tracing" within the system facilitates intelligent operation and maintenance or strategy optimization, forming a causal and explainable failure model.

[0065] The FHI value, as a unified risk indicator for the system, directly drives the transmission scheduling module.

[0066] When FHI is low, the system delays retransmission or merges queues;

[0067] When FHI is high, the system prioritizes retransmission or switching paths;

[0068] When FHI is extremely high, the system automatically pauses batch tasks and triggers network diagnostics.

[0069] Furthermore, step S6 employs a progressive retransmission mechanism, including:

[0070] S41: Fragment the message M to be retransmitted, forming a fragment set. And calculate semantic importance values ​​for each piece. High-importance fragments include message digest, title, main image, and structural metadata;

[0071] S42: Calculate the retransmission priority score for each fragment. This involves comprehensively considering the importance of fragmentation, network conditions, and regional popularity. ,in, This is a standardized value for network failure rate. , As a failure popularity index, the higher the priority of the fragment, the more likely it will be scheduled in the resend window;

[0072] S43: Based on the current available network bandwidth and average fragment size Calculate the progressive send window size, which is the number of fragments currently allowed to be sent simultaneously: ,in This is the window compression factor. As FHI increases, the window automatically compresses to avoid secondary congestion in high-failure-rate areas of the network. The minimum number of slices allowed for a window. The maximum number of slices allowed for a window, determined by... Theoretically, the number of fragments that can be sent can be calculated, and clipping can be used to trim them to [...]. , Range, then multiply by When the failure rate is high, the window is further narrowed to achieve adaptive progressive sending;

[0073] S44: After sorting by priority score, select the set of fragments within the window from high to low. And calculate the adaptive redundancy ratio. ,in For redundant growth rate, Based on the basic redundancy ratio, To assess the semantic importance of fragmentation, redundancy ratio It changes in tandem with the popularity of failures and the importance of fragmentation;

[0074] S45: Perform redundant coding on the fragments within the window to generate additional check fragments, forming an error-correctable progressive transmission group;

[0075] S46: Execute the initial transmission. After receiving some high-priority fragments, the receiving end can display the message summary and some visual content to achieve a gradual experience of "usable first, then complete".

[0076] S47: Monitor the ACK / NACK messages fed back by the receiver and calculate the local loss rate and latency indicators;

[0077] S48: Based on feedback and changes in FHI, execute a tiered retransmission decision when... Immediately retransmit all NACK fragments; when Only the top k priority fragments are retransmitted, among which ,when It delays the retransmission of low-priority fragments and only performs cross-protocol concurrent transmission on high-importance fragments.

[0078] The metadata for each shard includes:

[0079] frag_id: an integer;

[0080] importance: Abstract ≈ 1

[0081] size: byte;

[0082] state ;

[0083] send_count: Number of times the message has been sent;

[0084] last_send_ts: timestamp;

[0085] hash: Integrity verification;

[0086] p_score: Priority score, calculated in real time.

[0087] Suppose the system retransmits a 20KB 5G rich media message:

[0088] The message was split into 10 fragments with importance values ​​of [1.0, 0.9, 0.8, …, 0.1], respectively.

[0089] Current network bandwidth estimate =8KB, average fragment size =2KB, FHI=0.6;

[0090] Then window size ;

[0091] The system selects only the three highest priority fragments (abstract, title, and thumbnail) and adds 20% redundancy;

[0092] After being sent, the receiving end can immediately display the core content;

[0093] The remaining fragments will be automatically resent after the FHI drops.

[0094] Complexity: Most operations are sorting and window selection (O(k log k)), feedback processing can be batched, FHI and MDFRL are incremental updates (constant time / event), making it suitable for high-concurrency scenarios;

[0095] Robustness: For missing data (without FHI or network estimation), a conservative default is adopted (FHI is set to 0.5, loss_est is set to the historical median), and the missing data is compensated for by the Learning Module;

[0096] Security: Each shard contains a verification hash, and important shards can be signed to prevent tampering.

[0097] In this embodiment, before performing the fragmentation operation, the system first performs content structure analysis on the original 5G message, dividing the message into "core content fragments" and "auxiliary content fragments". The core fragments include the title, event summary, first image or key information fields, while the auxiliary fragments include secondary images, long text or multimedia additional content. When the network quality is poor or the failure rate index is high, the system prioritizes retransmitting only the core fragments, so that the receiving end can recover the main semantic content of the message in a short time. When the network condition returns to normal, the auxiliary fragments are gradually retransmitted, realizing a progressive message reconstruction of "information usability first, content completeness later".

[0098] FHI also serves as a feedback update factor, participating in the dynamic scheduling of the retransmission phase. When a fragment fails consecutively during retransmission, the system reports the failure event corresponding to that fragment to the FHI module, correcting the failure heat value of the corresponding region in real time. Conversely, when a fragment retransmits successfully, the FHI value will decay according to the weight factor. Through this two-way linkage, the system can achieve "instant correction" of FHI at the fragment level, making the failure heat distribution closer to the real-time network state and avoiding window control imbalance caused by global lag.

[0099] Furthermore, step S3 uses cross-protocol downgrade retransmission, including:

[0100] S51: Obtain failure information and evaluation conditions; receive the list of fragments that failed to be transmitted by the progressive fragmentation retransmission module. Obtain the failure heat index FHI value H and the multi-dimensional failure feature vector F to determine whether the cross-protocol degradation conditions are met. and Any one of the conditions in, where, For fragment weights, Based on historical success rate, Set a threshold for the system;

[0101] S52: Protocol Availability and Weight Calculation, defining the set of currently available protocols. Includes RCS, IP, SMS, and MMS for each fragment. In each protocol Calculate the weights above. , Given the importance of fragmentation, For fragmentation In the agreement The historical success rate, where H is the failure popularity index. For the protocol delay normalized value, These are the adjustable weighting coefficients of the system.

[0102] S53: Dynamic protocol selection for each fragment. Select the protocol with the highest weight. For high-priority fragments, which contain digests and key metadata, protocols with high weight and low latency are prioritized for transmission.

[0103] S54: Probability-driven redundancy scheduling calculates the redundancy transmission probability for critical fragments. With probability Key fragments are repeatedly sent on the selected protocol to enhance reliability in high failure hot environments, while non-critical fragments are sent with low redundancy or delayed according to the system policy.

[0104] S55: Iterate through sending and receiving feedback, select the result to send messages according to fragmentation priority and protocol, receive feedback ACK and NACK, and update the fragmentation status. For failed fragments, update the protocol's historical success rate. Recalculate the weights Then, select the next backup protocol and form a loop iteration until the fragmentation is successful and the retransmission limit is reached.

[0105] The system first receives input from the Progressive Fragmented Retransmission (PFRT) module, which includes the set of fragments to be retransmitted and their transmission status information. At the same time, the system extracts the feedback results of the most recent transmission from the failure analysis module, including multi-dimensional feature parameters such as network latency, packet loss rate, signal strength, base station load, and user online status. The system generates a failure feature vector based on these features and calls the FHI (Failure Heat Index) module to calculate the current failure heat index. If the heat index exceeds a preset threshold or multiple consecutive failures are detected, a cross-protocol dynamic degradation process is triggered.

[0106] The system evaluates the suitability of each protocol for each fragment in the current environment, referencing metrics including:

[0107] Historical transmission success rate (learned from logs);

[0108] Current network latency and bandwidth utilization;

[0109] Protocol load capacity and compatibility;

[0110] User terminal support status.

[0111] Based on the protocol priority results obtained in the previous stage, the system selects the optimal protocol for each message fragment. During the selection process, the importance of the fragment is comprehensively considered, including:

[0112] If the fragment contains critical information (such as message digest, title, warning content, etc.), then a protocol with low latency and high stability should be selected first.

[0113] If the fragments are non-critical content (such as images, attachments, or supplementary descriptions), a protocol with higher throughput but relatively lower reliability can be selected for transmission.

[0114] In addition, to avoid the extra overhead caused by frequent switching, the cost of protocol switching, such as signaling reconstruction time and encoding conversion cost, will be assessed, and cross-protocol degradation will only be performed when necessary.

[0115] The system dynamically calculates the probability of redundant transmission based on the importance of the fragment and its historical success rate. For fragments with high importance, the system may send them simultaneously on two different protocols to prevent information loss due to the failure of a single channel. The core idea of ​​redundancy scheduling is "limited redundancy and precise redundancy": the system will not blindly repeat transmission, but will dynamically judge whether redundancy is necessary based on the real-time network status. When the network is congested or resources are limited, the system can automatically reduce the redundancy intensity to prevent the formation of new transmission pressure.

[0116] The sending end listens for acknowledgment messages (ACK) or failure receipts (NACK) from each protocol channel and dynamically updates its internal status table based on the results. For successful fragmentation, the system marks it as completed; for failed fragmentation, the system records the reason for the failure of the current protocol (such as network timeout, terminal non-response, format incompatibility, etc.) and adjusts the historical success rate parameter of the protocol. Subsequently, the system re-evaluates the protocol weights, selects the next alternative protocol for retransmission, and if multiple attempts still fail, the system delays the fragmentation until the network recovers before attempting it again, based on priority.

[0117] This invention constructs multidimensional failure reason labels, quantifies and generates failure feature vectors, and combines them with the Failure Heat Index (FHI) to achieve message priority scheduling. Building upon traditional 5G message retransmission mechanisms, it introduces a progressive fragmentation retransmission mechanism and a cross-protocol dynamic degradation retransmission strategy, thus forming a complete, adaptive, and intelligent message retransmission optimization system. This system can effectively identify multidimensional causes of message transmission failures in complex and ever-changing wireless network environments, including network status fluctuations, abnormal user online status, and excessive base station load. It quantifies this multidimensional information into failure feature vectors that can be used for algorithmic decision-making through a dynamic weighting formula, enabling the system to fully consider various influencing factors when selecting retransmission strategies, achieving precise and personalized results. Retransmission decision-making: By introducing a failure heat index, this invention can quantify the frequency, concentration, and density of failures within a network area. This allows message retransmission to not only rely on the failure status of individual messages but also prioritize messages based on the overall network conditions, thereby rationally arranging message sending order in congested environments and improving resource utilization efficiency. Furthermore, this invention innovatively designs a progressive fragmentation retransmission mechanism, splitting complete messages into digests, key metadata, and non-key content for layered transmission. When network conditions are poor or congested, the system prioritizes sending digests and key metadata to ensure users receive core information as quickly as possible; as network conditions improve, the remaining fragments are then gradually retransmitted. By retransmitting complete content, the high latency and low success rate problems caused by traditional single full retransmission are effectively alleviated. This fragmentation mechanism not only improves the timeliness of core information delivery but also significantly reduces the network bandwidth consumption of redundant data, achieving optimized utilization of network resources. Simultaneously, this invention proposes a cross-protocol dynamic degradation retransmission strategy. For various transmission protocols that 5G messages may rely on, including RCS, IMS, SMS, MMS, or low-speed data channels, the system can dynamically calculate the weight of each fragment under different protocols based on the failure feature vector and FHI, and select the optimal protocol for transmission. In high failure heat environments, for critical... In the fragmentation process, the system uses a probability-driven redundancy strategy to send messages using multiple protocols, improving message delivery reliability under complex network conditions. For non-critical fragments, low-redundancy or delayed sending is selected based on priority and network conditions, thus balancing resource consumption and transmission reliability. Through an iterative feedback mechanism, the system can update the historical success rate of each protocol in real time, recalculate weights, and adjust protocol selection, achieving an adaptive, multi-round optimized dynamic degradation and retransmission process. This strategy overcomes the limitation of traditional retransmission mechanisms that cannot guarantee message reliability in the event of a single point of failure in the protocol, enabling the system to ensure the successful delivery of critical messages even when part of the protocol link fails.This invention significantly improves the overall delivery rate of 5G messages in complex network environments, especially the success rate of core information transmission, providing users with a stable and reliable communication experience. It supports various types of rich media messages, including text, images, and audio / video files, and has broad application value in enterprise communication, financial transaction notifications, public information push, and emergency message service scenarios. Through the method of this invention, even in environments with frequent network fluctuations, peak base station loads, or frequent user mobile handovers, reliable and timely message delivery can be guaranteed, improving user experience and system service quality. This invention achieves a technological upgrade from the traditional single-dimensional, static message retransmission mechanism to a multi-dimensional, dynamically adaptive, and intelligent retransmission system, solving the problems of low efficiency and insufficient reliability caused by network fluctuations, single-point protocol failures, and full message duplication in existing technologies. It has significant value for the performance optimization and application promotion of 5G messaging systems. Attached Figure Description

[0118] Figure 1 Flowchart of an optimization method for retransmitting failed 5G messages;

[0119] Figure 2 This is a module diagram of a 5G message sending failure retransmission optimization system. Detailed Implementation

[0120] The present invention will be further described clearly and completely below, but the scope of protection of the present invention is not limited thereto.

[0121] like Figure 1 The diagram shown is a flowchart of an optimization method for retransmission of failed 5G messages.

[0122] A method for optimizing 5G message transmission failure retransmission includes:

[0123] S1: Construct multi-dimensional failure reason labels for 5G messages that fail to be sent, including network status dimension, user status dimension, and base station load dimension;

[0124] S2: Calculate dynamic weights based on the multi-dimensional failure reason labels to obtain the failure feature vector for the 5G message;

[0125] S3: Based on the failure feature vector, adaptively select a retransmission strategy, including delayed retransmission, fragmented retransmission, path switching retransmission, and cross-protocol degradation retransmission;

[0126] S4: The Failure Heat Index (FHI) is used during the retransmission process. The index is calculated from the failure frequency, failure concentration, and network area failure density.

[0127] S5: Prioritize messages based on the failure heat index to determine whether to resend them immediately or delay queuing.

[0128] S6: 5G messages are split and a progressive retransmission mechanism is adopted, prioritizing the transmission of message summaries and key metadata, and then gradually retransmitting the complete content as network conditions improve.

[0129] like Figure 2 The diagram shown is a module diagram of a 5G message sending failure retransmission optimization system.

[0130] A 5G message transmission failure retransmission optimization system, implemented based on a 5G message transmission failure retransmission optimization method, includes:

[0131] Failure Analysis and Multidimensional Labeling Module: Receives messages and sends feedback information, including success and failure, network logs, extracts and generates multidimensional failure reason labels, including signal strength, packet loss rate, and network type in the network status dimension, user online status and device type in the user status dimension, and current load and congestion status in the base station load dimension, providing the raw data foundation for subsequent strategy selection;

[0132] Failure Feature Vector Generation Module: Quantizes and weights multi-dimensional failure labels, uses dynamic weight formula to generate failure feature vectors, reflects the failure characteristics of each message in different dimensions, and transforms the original labels into numerical vectors that can be used for algorithm decision-making.

[0133] Retransmission strategy selection module: Adaptively selects the optimal retransmission strategy based on the failure feature vector. The strategies include fragmented retransmission PFRT, delayed retransmission, path switching retransmission, and cross-protocol dynamic degradation retransmission CPADR, forming a specific retransmission plan for each message.

[0134] Failure Heat Index Module: Calculates the failure heat index based on failure frequency, failure concentration, and network area failure density. It is used to measure network congestion and areas of concentrated failure, and provides indicators for message prioritization and retransmission rhythm.

[0135] Priority scheduling module: Determines the message retransmission order based on FHI and user historical behavior prediction, decides whether to retransmit immediately or delay queuing, and reasonably allocates the retransmission order in resource-limited and high-failure environments to improve the delivery rate of core content;

[0136] The progressive retransmission module splits messages into digests, key metadata, and the complete content. It prioritizes sending digests or key fragments and gradually retransmits the complete content as network conditions improve. It combines the fragmentation strategy and protocol selection output by the retransmission strategy selection module.

[0137] Furthermore, in step S2, based on the failure reason label, a failure feature vector for the 5G message is obtained, including:

[0138] S21: Network state dimension construction, collecting real-time network state information from the message sending path, including packet loss rate. Average delay Bandwidth usage and network slicing availability After normalizing each indicator, the network state score is calculated: ,in , , , This is an adjustable coefficient, optimized based on historical failure logs;

[0139] S22: User status dimension construction: Collect user online status, terminal type and reliability, user activity, and historical message reception success rate; quantify each indicator and calculate the user status score. ,in Indicates the probability of a user being online. This indicates the terminal reliability score. Indicates the user's recent activity level. This indicates the user's historical reception success rate. , , , These are adjustable weighting coefficients;

[0140] S23: Base station load dimension construction, obtain the current number of connections of the base station where the message was sent. Base station failure rate and regional failure density Information: The specific calculation method for base station load score is as follows: ,in This represents the maximum number of connections a base station can support. These are adjustable weighting coefficients;

[0141] S24: Multidimensional Tag Vector Generation and Fusion, integrating three-dimensional scores into a multidimensional failure reason tag vector for the message: Add dynamic weights to each dimension This forms the final failure feature vector: ;

[0142] S25: Update the corresponding metrics for each failed 5G message, including network packet loss rate, user online probability, and base station load status. Periodically analyze failure logs and adjust weights by minimizing prediction error and using reinforcement learning. ;

[0143] S26: The failure feature vector It serves directly as input to the retransmission strategy selection module, providing a basis for subsequent priority scheduling and progressive retransmission.

[0144] The multidimensional failure reason labels are not only composed of numerical features, but also employ a hierarchical semantic mapping structure:

[0145] Base Tag: Physical metrics extracted directly from raw data, such as packet loss rate, latency, online rate, load value, etc.

[0146] Fusion Tag: The base layer tags are transformed into semantic tags, such as "high latency", "regional congestion", and "high terminal risk", through clustering or rule engine.

[0147] Behavior Tag: Dynamic tags generated by combining historical behavior data, such as "periodic failure user", "instantaneous overload base station", and "short-term high failure area".

[0148] The system uses a sliding time window when generating failure labels. The system aggregates and analyzes message sending failure data over a continuous time period. When a certain dimension indicator exhibits abnormal fluctuations within a window, the system automatically increases the weight of that dimension label. When the dimension's performance stabilizes, a weight decay mechanism is triggered, mathematically expressed as follows: ,in The weights for the i-th dimension include network, user, and base station. The rate of change of this dimension indicator within the current window. For the change threshold, As a weight adjustment factor, this dynamic migration mechanism enables the labeling system to continuously reflect the real changes in the current network environment, rather than static feature descriptions.

[0149] To prevent the formation of "failure hotspots" in the same geographical area or from the same base station within a short period of time, the system further introduces a spatial clustering algorithm. This algorithm models the geographical location attributes of failure labels to identify potential "failure clusters." , This indicates the geographical distance between two failed records. The spatial distance threshold, The system uses a similarity threshold for labels. If the number of failed labels in a cluster exceeds the threshold, the system will generate a new “Regional Failure Tag” and dynamically adjust the weight of the base station load dimension in that region. This mechanism enables the label system to have spatial awareness and prevents concentrated retransmission avalanche at the macro level.

[0150] Furthermore, by employing a label evolution mechanism, the label feature vectors are retrained and optimized periodically (e.g., hourly) based on failed samples and retransmitted successful samples:

[0151] If a certain type of label is associated with a high failure rate for a long period of time, the risk weight of that type of label will be automatically increased.

[0152] If a certain tag is associated with successful resubmission for a long period of time, its risk weight should be reduced.

[0153] For newly emerging unknown labels (such as new terminal models or temporary regional interference), the system will first assign a low-confidence label and then gradually correct it during subsequent learning.

[0154] Furthermore, in step S4, the failure popularity index is used during the retransmission process, including:

[0155] S31: Multi-dimensional failure data collection. After a message transmission failure, multi-dimensional data related to the failure event is automatically collected. This data includes: network layer parameters, specifically signal strength, latency, and packet loss rate; user layer status, specifically terminal online rate, network handover frequency, and mobile speed; base station layer parameters, specifically base station load, congestion level, and handover frequency; message layer characteristics, specifically message type, message length, retransmission count, and real-time requirements; and geographic layer information, specifically the coordinates of the failure location, area identifier, and failure concentration. The data is then processed in a fixed time window. Sampling is performed to form a time-series multidimensional sample set. ;

[0156] S32: Failure density matrix construction. The spatial coordinate region is divided into fixed grids, and the number of failure events in each grid is counted within each time window. A Gaussian kernel function is used to smooth the local region to eliminate data discreteness, resulting in the failure density matrix. Its definition is, Where x and y are the horizontal and vertical coordinates of the geographical location, and t is the time. Let be the geographical coordinates at the time the i-th failure event occurs. For the current time window A set of failure event indexes within the specified time range. Let i be the timestamp of the i-th failure event. It is a spatial distance function, representing a point. With assessment points The distance between them for Geographical location The specific representation is as follows , This is a kernel function used to convert spatial distance into weights;

[0157] S33: Dynamic calculation of dimension weights; the system calculates the information entropy value for each dimension. This reflects the contribution of each dimension to the overall failure trend, and a weight vector is generated accordingly. ,in For the network state dimension, For the user status dimension, From the perspective of base station load, As a message characteristic dimension, For the geographical distribution dimension, the dimension calculation method is as follows: , Let be the real-time information entropy value of the i-th dimension. The sum of information entropy of all dimensions. The higher the information entropy, the greater the volatility and uncertainty of that dimension, and the stronger its explanatory power for system failure modes. Therefore, its weight is also higher. The system dynamically adjusts the weights according to real-time data to ensure that the model adapts to changes in the environment.

[0158] S34: Generation of local failure feature vectors. After obtaining the weight vector, the system extracts the local failure features under the current time window to form a vector. Each component represents the failure rate and statistical indicators of the corresponding dimension, including base station failure rate, message timeout rate, and area density. This vector is the "failure feature fingerprint" under the current network state.

[0159] S35: Calculation of the time decay factor. The impact of historical failure events weakens over time, so a time decay factor α(t) is used. The specific calculation method for α(t) is as follows: , where λ is the attenuation coefficient, used to control the contribution of past data to the current FHI. By introducing α(t), we can avoid the old data from causing excessive interference to the current decision.

[0160] S36: Geographic clustering correction, assessing the clustering of failure events using spatial statistical methods, and calculating the clustering coefficient using Ripley's K function. ,in The specific calculation method is as follows: Where K(d) is the spatial distribution function of actual failure events, representing the average number of other failure event points around any failure event point within an observation radius of d. It is a spatial aggregation function obtained after region area normalization, and its specific calculation method is as follows: A is the area of ​​the observation region, and N is the total number of failure events. Let be the distance between the i-th and j-th failure event points. For indicator functions, when The value is 1 if the condition is met, and 0 otherwise. Let be a reference function for the theoretical random distribution, representing the expected average number of events within a radius d under a completely random distribution. It serves as a baseline to help the system determine if there are anomalous clusters in the current failure distribution. Its calculation method is as follows: ,when A value >0 indicates that failure events show a clear clustering trend in a certain area, and the system will increase the priority retransmission level of messages in that area;

[0161] S37: The system integrates weights across various dimensions, local features, time decay, and geographical clustering to calculate the Failure Heat Index (FHI). κ is the aggregation amplification factor, used to adjust the impact of geographic aggregation effect. The calculated FHI is normalized, and its range is [0,1]. It is divided into five levels: 0 to 0.2 is normal, 0.2 to 0.4 is slight failure, 0.4 to 0.6 is moderate failure, 0.6 to 0.8 is high-risk failure, and above 0.8 is severe failure. The scheduling module automatically determines the retransmission strategy according to the FHI level. If the FHI is low, the queue is merged and the retransmission is delayed; if the FHI is medium, the retransmission is carried out through the normal path; if the FHI is high, path switching is enabled and cross-protocol retransmission is carried out; if the FHI is extremely high, batch message sending is suspended and network diagnosis is triggered. The value of FHI reflects the comprehensive risk level of failure events. When the FHI value is high, it indicates that the failure probability of the current region or user group is on the rise, and network resources should be allocated or the retransmission path should be adjusted first.

[0162] S38: Finally, the final priority score for a single message m. The FHI and the message's own failure feature vector Joint decision: , Let m be the region to which message m belongs, and w be the linear weight vector from message features to score. This is the number of seconds the message has been waiting to be retransmitted. For normalization function, , , These are the coefficients for each item.

[0163] The specific calculation method for the information entropy value of each dimension is as follows:

[0164] Dimensional feature discretization and probability distribution construction: Based on the collected failure-related parameters, the indicators of this dimension are segmented and clustered to form a discretized state set. Then, the frequency of failure events in each state is counted to form a probability distribution: ;

[0165] Noise smoothing calculation, the specific calculation method is as follows: , The minimum noise smoothing coefficient is automatically calculated based on the data volatility of the most recent time window. , The standard deviation of this dimension of features. The adjustment coefficient set for the system ranges from 0.01 to 0.05;

[0166] Dimensional information entropy calculation When the state distribution of a certain dimension is extremely simple, it indicates low entropy, meaning that this dimension contributes weakly to failure. When the state distribution of a certain dimension is very scattered and unpredictable, it indicates high entropy, meaning that this dimension is the main failure factor.

[0167] Multi-window fusion , The current window entropy, The entropy of the previous window, For the entropy of the first two windows, Window weight;

[0168] Entropy normalization, Normalized entropy can be directly used to calculate weights: .

[0169] Time complexity: The calculation of FHI mainly involves summing the failure events within the window and time decay. Sliding windows and incremental updates can be used (incremental updates can reduce the processing of each new event to O(1)), which is suitable for high-concurrency scenarios.

[0170] Space: It is necessary to maintain an event summary (count, time statistics, weighted sum) for each region, rather than storing all raw events, thus saving storage space;

[0171] Robustness: Design backoff values ​​and confidence levels for missing indicators (such as the state of no slice at a certain time) so that FHI can still work stably under incomplete information.

[0172] If a base station FHI exceeds The system uniformly places messages within the base station area with a Priority(m) below a certain threshold into a delay queue and releases them slowly from low to high according to a multi-scale FHI (Fear of Hierarchy Indicator) to avoid a large number of instantaneous retransmissions. For messages with a low FHI but a high Priority(m) for a single message (such as OTP), immediate cross-protocol parallel retransmission is allowed to ensure real-time performance. The system also handles messages with a significantly decreased FHI (below a certain threshold). After that, the delayed digest and remaining fragments are quickly resent using a priority queue (progressive resending).

[0173] When an abnormally sharp increase in FHI is detected within a short period of time (e.g., the growth rate exceeds the threshold in a short window), The system will trigger an "abnormal alarm mode":

[0174] Temporarily freeze all uncompleted retransmission requests in the area and request network-side intervention (such as switching the loopback or notifying the operator).

[0175] Increase FHI monitoring in adjacent areas to determine if it is lateral spread.

[0176] The failure heat index dynamically assesses the risk of message sending failure by integrating multi-dimensional features of time, space, network, users, and messages.

[0177] Implement dynamic retransmission priority decision-making: avoid unnecessary retransmissions, reduce network congestion, and improve overall bandwidth utilization;

[0178] Regional-level predictive capabilities: Identify potential "network failure hotspots" in advance to avoid cascading transmission failures;

[0179] Integrating time decay and historical weighting mechanisms enhances the model's real-time responsiveness, enabling the system to "respond instantly and converge quickly," thus improving its adaptive capabilities.

[0180] Cross-dimensional cause diagnosis: "Failure source tracing" within the system facilitates intelligent operation and maintenance or strategy optimization, forming a causal and explainable failure model.

[0181] The FHI value, as a unified risk indicator for the system, directly drives the transmission scheduling module.

[0182] When FHI is low, the system delays retransmission or merges queues;

[0183] When FHI is high, the system prioritizes retransmission or switching paths;

[0184] When FHI is extremely high, the system automatically pauses batch tasks and triggers network diagnostics.

[0185] Furthermore, step S6 employs a progressive retransmission mechanism, including:

[0186] S41: Fragment the message M to be retransmitted, forming a fragment set. And calculate semantic importance values ​​for each piece. High-importance fragments include message digest, title, main image, and structural metadata;

[0187] S42: Calculate the retransmission priority score for each fragment. This involves comprehensively considering the importance of fragmentation, network conditions, and regional popularity. ,in, This is a standardized value for network failure rate. , As a failure popularity index, the higher the priority of the fragment, the more likely it will be scheduled in the resend window;

[0188] S43: Based on the current available network bandwidth and average fragment size Calculate the progressive send window size, which is the number of fragments currently allowed to be sent simultaneously: ,in This is the window compression factor. As FHI increases, the window automatically compresses to avoid secondary congestion in high-failure-rate areas of the network. The minimum number of slices allowed for a window. The maximum number of slices allowed for a window, determined by... Theoretically, the number of fragments that can be sent can be calculated, and clipping can be used to trim them to [...]. , Range, then multiply by When the failure rate is high, the window is further narrowed to achieve adaptive progressive sending;

[0189] S44: After sorting by priority score, select the set of fragments within the window from high to low. And calculate the adaptive redundancy ratio. ,in For redundant growth rate, Based on the basic redundancy ratio, To assess the semantic importance of fragmentation, redundancy ratio It changes in tandem with the popularity of failures and the importance of fragmentation;

[0190] S45: Perform redundant coding on the fragments within the window to generate additional check fragments, forming an error-correctable progressive transmission group;

[0191] S46: Execute the initial transmission. After receiving some high-priority fragments, the receiving end can display the message summary and some visual content to achieve a gradual experience of "usable first, then complete".

[0192] S47: Monitor the ACK / NACK messages fed back by the receiver and calculate the local loss rate and latency indicators;

[0193] S48: Based on feedback and changes in FHI, execute a tiered retransmission decision when... Immediately retransmit all NACK fragments; when Only the top k priority fragments are retransmitted, among which ,when It delays the retransmission of low-priority fragments and only performs cross-protocol concurrent transmission on high-importance fragments.

[0194] The metadata for each shard includes:

[0195] frag_id: an integer;

[0196] importance: Abstract ≈ 1

[0197] size: byte;

[0198] state ;

[0199] send_count: Number of times the message has been sent;

[0200] last_send_ts: timestamp;

[0201] hash: Integrity verification;

[0202] p_score: Priority score, calculated in real time.

[0203] Suppose the system retransmits a 20KB 5G rich media message:

[0204] The message was split into 10 fragments with importance values ​​of [1.0, 0.9, 0.8, …, 0.1], respectively.

[0205] Current network bandwidth estimate =8KB, average fragment size =2KB, FHI=0.6;

[0206] Then window size ;

[0207] The system selects only the three highest priority fragments (abstract, title, and thumbnail) and adds 20% redundancy;

[0208] After being sent, the receiving end can immediately display the core content;

[0209] The remaining fragments will be automatically resent after the FHI drops.

[0210] Complexity: Most operations are sorting and window selection (O(k log k)), feedback processing can be batched, FHI and MDFRL are incremental updates (constant time / event), making it suitable for high-concurrency scenarios;

[0211] Robustness: For missing data (without FHI or network estimation), a conservative default is adopted (FHI is set to 0.5, loss_est is set to the historical median), and the missing data is compensated for by the Learning Module;

[0212] Security: Each shard contains a verification hash, and important shards can be signed to prevent tampering.

[0213] In this embodiment, before performing the fragmentation operation, the system first performs content structure analysis on the original 5G message, dividing the message into "core content fragments" and "auxiliary content fragments". The core fragments include the title, event summary, first image or key information fields, while the auxiliary fragments include secondary images, long text or multimedia additional content. When the network quality is poor or the failure rate index is high, the system prioritizes retransmitting only the core fragments, so that the receiving end can recover the main semantic content of the message in a short time. When the network condition returns to normal, the auxiliary fragments are gradually retransmitted, realizing a progressive message reconstruction of "information usability first, content completeness later".

[0214] FHI also serves as a feedback update factor, participating in the dynamic scheduling of the retransmission phase. When a fragment fails consecutively during retransmission, the system reports the failure event corresponding to that fragment to the FHI module, correcting the failure heat value of the corresponding region in real time. Conversely, when a fragment retransmits successfully, the FHI value will decay according to the weight factor. Through this two-way linkage, the system can achieve "instant correction" of FHI at the fragment level, making the failure heat distribution closer to the real-time network state and avoiding window control imbalance caused by global lag.

[0215] Furthermore, step S3 uses cross-protocol downgrade retransmission, including:

[0216] S51: Obtain failure information and evaluation conditions; receive the list of fragments that failed to be transmitted by the progressive fragmentation retransmission module. Obtain the failure heat index FHI value H and the multi-dimensional failure feature vector F to determine whether the cross-protocol degradation conditions are met. and Any one of the conditions in, where, For fragment weights, Based on historical success rate, Set a threshold for the system;

[0217] S52: Protocol Availability and Weight Calculation, defining the set of currently available protocols. Includes RCS, IP, SMS, and MMS for each fragment. In each protocol Calculate the weights above. , Given the importance of fragmentation, For fragmentation In the agreement The historical success rate, where H is the failure popularity index. For the protocol delay normalized value, These are the adjustable weighting coefficients of the system.

[0218] S53: Dynamic protocol selection for each fragment. Select the protocol with the highest weight. For high-priority fragments, which contain digests and key metadata, protocols with high weight and low latency are prioritized for transmission.

[0219] S54: Probability-driven redundancy scheduling calculates the redundancy transmission probability for critical fragments. With probability Key fragments are repeatedly sent on the selected protocol to enhance reliability in high failure hot environments, while non-critical fragments are sent with low redundancy or delayed according to the system policy.

[0220] S55: Iterate through sending and receiving feedback, select the result to send messages according to fragmentation priority and protocol, receive feedback ACK and NACK, and update the fragmentation status. For failed fragments, update the protocol's historical success rate. Recalculate the weights Then, select the next backup protocol and form a loop iteration until the fragmentation is successful and the retransmission limit is reached.

[0221] The system first receives input from the Progressive Fragmented Retransmission (PFRT) module, which includes the set of fragments to be retransmitted and their transmission status information. At the same time, the system extracts the feedback results of the most recent transmission from the failure analysis module, including multi-dimensional feature parameters such as network latency, packet loss rate, signal strength, base station load, and user online status. The system generates a failure feature vector based on these features and calls the FHI (Failure Heat Index) module to calculate the current failure heat index. If the heat index exceeds a preset threshold or multiple consecutive failures are detected, a cross-protocol dynamic degradation process is triggered.

[0222] The system evaluates the suitability of each protocol for each fragment in the current environment, referencing metrics including:

[0223] Historical transmission success rate (learned from logs);

[0224] Current network latency and bandwidth utilization;

[0225] Protocol load capacity and compatibility;

[0226] User terminal support status.

[0227] Based on the protocol priority results obtained in the previous stage, the system selects the optimal protocol for each message fragment. During the selection process, the importance of the fragment is comprehensively considered, including:

[0228] If the fragment contains critical information (such as message digest, title, warning content, etc.), then a protocol with low latency and high stability should be selected first.

[0229] If the fragments are non-critical content (such as images, attachments, or supplementary descriptions), a protocol with higher throughput but relatively lower reliability can be selected for transmission.

[0230] In addition, to avoid the extra overhead caused by frequent switching, the cost of protocol switching, such as signaling reconstruction time and encoding conversion cost, will be assessed, and cross-protocol degradation will only be performed when necessary.

[0231] The system dynamically calculates the probability of redundant transmission based on the importance of the fragment and its historical success rate. For fragments with high importance, the system may send them simultaneously on two different protocols to prevent information loss due to the failure of a single channel. The core idea of ​​redundancy scheduling is "limited redundancy and precise redundancy": the system will not blindly repeat transmission, but will dynamically judge whether redundancy is necessary based on the real-time network status. When the network is congested or resources are limited, the system can automatically reduce the redundancy intensity to prevent the formation of new transmission pressure.

[0232] The sending end listens for acknowledgment messages (ACK) or failure receipts (NACK) from each protocol channel and dynamically updates its internal status table based on the results. For successful fragmentation, the system marks it as completed; for failed fragmentation, the system records the reason for the failure of the current protocol (such as network timeout, terminal non-response, format incompatibility, etc.) and adjusts the historical success rate parameter of the protocol. Subsequently, the system re-evaluates the protocol weights, selects the next alternative protocol for retransmission, and if multiple attempts still fail, the system delays the fragmentation until the network recovers before attempting it again, based on priority.

[0233] The embodiments disclosed herein are preferred embodiments, but are not limited thereto. Those skilled in the art can readily grasp the spirit of the present invention based on the above embodiments and make different extensions and variations, but as long as they do not depart from the spirit of the present invention, they are all within the protection scope of the present invention.

[0234] This invention constructs multidimensional failure reason labels, quantifies and generates failure feature vectors, and combines them with the Failure Heat Index (FHI) to achieve message priority scheduling. Building upon traditional 5G message retransmission mechanisms, it introduces a progressive fragmentation retransmission mechanism and a cross-protocol dynamic degradation retransmission strategy, thus forming a complete, adaptive, and intelligent message retransmission optimization system. This system can effectively identify multidimensional causes of message transmission failures in complex and ever-changing wireless network environments, including network status fluctuations, abnormal user online status, and excessive base station load. It quantifies this multidimensional information into failure feature vectors that can be used for algorithmic decision-making through a dynamic weighting formula, enabling the system to fully consider various influencing factors when selecting retransmission strategies, achieving precise and personalized results. Retransmission decision-making: By introducing a failure heat index, this invention can quantify the frequency, concentration, and density of failures within a network area. This allows message retransmission to not only rely on the failure status of individual messages but also prioritize messages based on the overall network conditions, thereby rationally arranging message sending order in congested environments and improving resource utilization efficiency. Furthermore, this invention innovatively designs a progressive fragmentation retransmission mechanism, splitting complete messages into digests, key metadata, and non-key content for layered transmission. When network conditions are poor or congested, the system prioritizes sending digests and key metadata to ensure users receive core information as quickly as possible; as network conditions improve, the remaining fragments are then gradually retransmitted. By retransmitting complete content, the high latency and low success rate problems caused by traditional single full retransmission are effectively alleviated. This fragmentation mechanism not only improves the timeliness of core information delivery but also significantly reduces the network bandwidth consumption of redundant data, achieving optimized utilization of network resources. Simultaneously, this invention proposes a cross-protocol dynamic degradation retransmission strategy. For various transmission protocols that 5G messages may rely on, including RCS, IMS, SMS, MMS, or low-speed data channels, the system can dynamically calculate the weight of each fragment under different protocols based on the failure feature vector and FHI, and select the optimal protocol for transmission. In high failure heat environments, for critical... In the fragmentation process, the system uses a probability-driven redundancy strategy to send messages using multiple protocols, improving message delivery reliability under complex network conditions. For non-critical fragments, low-redundancy or delayed sending is selected based on priority and network conditions, thus balancing resource consumption and transmission reliability. Through an iterative feedback mechanism, the system can update the historical success rate of each protocol in real time, recalculate weights, and adjust protocol selection, achieving an adaptive, multi-round optimized dynamic degradation and retransmission process. This strategy overcomes the limitation of traditional retransmission mechanisms that cannot guarantee message reliability in the event of a single point of failure in the protocol, enabling the system to ensure the successful delivery of critical messages even when part of the protocol link fails.This invention significantly improves the overall delivery rate of 5G messages in complex network environments, especially the success rate of core information transmission, providing users with a stable and reliable communication experience. It supports various types of rich media messages, including text, images, and audio / video files, and has broad application value in enterprise communication, financial transaction notifications, public information push, and emergency message service scenarios. Through the method of this invention, even in environments with frequent network fluctuations, peak base station loads, or frequent user mobile handovers, reliable and timely message delivery can be guaranteed, improving user experience and system service quality. This invention achieves a technological upgrade from the traditional single-dimensional, static message retransmission mechanism to a multi-dimensional, dynamically adaptive, and intelligent retransmission system, solving the problems of low efficiency and insufficient reliability caused by network fluctuations, single-point protocol failures, and full message duplication in existing technologies. It has significant value for the performance optimization and application promotion of 5G messaging systems.

Claims

1. A method for optimizing 5G message transmission failure retransmission, characterized in that, include: S1: Construct multi-dimensional failure reason labels for 5G messages that fail to be sent, including network status dimension, user status dimension, and base station load dimension; S2: Calculate dynamic weights based on the multi-dimensional failure reason labels to obtain the failure feature vector for the 5G message; S3: Based on the failure feature vector, adaptively select a retransmission strategy, including delayed retransmission, fragmented retransmission, path switching retransmission, and cross-protocol degradation retransmission; S4: During the retransmission process, the Failure Heat Index (FHI) is used. The retransmission strategy is automatically determined based on the FHI level. A Gaussian kernel function is used to smooth local regions to eliminate data discreteness, resulting in a failure density matrix and generating local failure feature vectors. After obtaining the weight vector, the system extracts local failure features within the current time window to form a vector. Geographic clustering correction: The clustering of failure events is assessed using spatial statistical methods, and the geographic clustering is calculated using Ripley's K function. ,when A value >0 indicates that failure events show a clear clustering trend in a certain area. The system will increase the priority retransmission level of messages in that area. The system calculates the Failure Heat Index (FHI) by comprehensively considering the weights of various dimensions, local failure feature vectors, time decay, and geographical clustering. S5: Prioritize messages based on the failure heat index to determine whether to resend them immediately or delay queuing. S6: 5G messages are split and a progressive retransmission mechanism is adopted. Message digests and key metadata are sent first, and then the complete content is gradually retransmitted as network conditions improve, including based on the current available network bandwidth. and average fragment size Calculate the progressive sending window size, which is the number of fragments that can be sent simultaneously at the current time.

2. The 5G message transmission failure retransmission optimization method according to claim 1, characterized in that, In step S2, based on the failure reason label, a failure feature vector for the 5G message is obtained, including: S21: Network state dimension construction, collecting real-time network state information from the message sending path, including packet loss rate. Average delay Bandwidth usage and network slicing availability After normalizing each indicator, the network state score is calculated: ,in , , , This is an adjustable coefficient, optimized based on historical failure logs; S22: User status dimension construction: Collect user online status, terminal type and reliability, user activity, and historical message reception success rate; quantify each indicator and calculate the user status score. ,in Indicates the probability of a user being online. This indicates the terminal reliability score. Indicates the user's recent activity level. This indicates the user's historical reception success rate. , , , These are adjustable weighting coefficients; S23: Base station load dimension construction, obtain the current number of connections of the base station where the message was sent. Base station failure rate and regional failure density Information: The specific calculation method for base station load score is as follows: ,in This represents the maximum number of connections a base station can support. These are adjustable weighting coefficients; S24: Multidimensional Tag Vector Generation and Fusion, integrating three-dimensional scores into a multidimensional failure reason tag vector for the message: Add dynamic weights to each dimension This forms a failure feature vector: ; S25: Update the corresponding metrics for each failed 5G message, including network packet loss rate, user online probability, and base station load status. Periodically analyze failure logs and adjust weights by minimizing prediction error and using reinforcement learning. ; S26: The failure feature vector It serves directly as input to the retransmission strategy selection module, providing a basis for subsequent priority scheduling and progressive retransmission.

3. The 5G message transmission failure retransmission optimization method according to claim 1, characterized in that, The failure popularity index used in step S4 during the retransmission process includes: S41: Multi-dimensional failure data collection. After a message transmission failure event, multi-dimensional data related to the failure event is automatically collected. This data includes: network layer parameters, specifically signal strength, latency, and packet loss rate; user layer status, specifically terminal online rate, network handover frequency, and mobile speed; base station layer parameters, specifically base station load, congestion level, and handover frequency; message layer characteristics, specifically message type, message length, retransmission count, and real-time requirements; and geographic layer information, specifically the coordinates of the failure location, area identifier, and failure concentration. The data is then processed in a fixed time window. Sampling is performed to form a time-series multidimensional sample set. ; S42: Failure density matrix construction involves dividing the spatial coordinate region into fixed grids and counting the number of failure events in each grid within each time window. The failure density matrix is ​​defined as follows: Where x and y are the horizontal and vertical coordinates of the geographical location, and t is the time. Let be the geographical coordinates at the time the i-th failure event occurs. For the current time window A set of failure event indexes within the specified time range. Let i be the timestamp of the i-th failure event. It is a spatial distance function, representing a point. With assessment points The distance between them for Geographical location The specific representation is as follows , This is a kernel function used to convert spatial distance into weights; S43: Dynamic calculation of dimension weights; the system calculates the information entropy value for each dimension. This reflects the contribution of each dimension to the overall failure trend, and a weight vector is generated accordingly. ,in For the network state dimension, For the user status dimension, From the perspective of base station load, As a message characteristic dimension, For the geographical distribution dimension, the general calculation method for each dimension is as follows: Where i represents the information dimension, and its value ranges from network status dimension, user status dimension, base station load dimension, message characteristic dimension, and geographical distribution dimension. Let be the real-time information entropy value of the i-th dimension. The sum of information entropy of all dimensions. The higher the information entropy, the greater the volatility and uncertainty of that dimension, and the stronger its explanatory power for system failure modes. Therefore, its weight is also higher. The system dynamically adjusts the weights according to real-time data to ensure that the model adapts to changes in the environment. S44: The general calculation method for each dimension is as follows , This represents the comprehensive representation of the risk of message sending failure at the current moment for a certain dimension. This represents the message sending failure rate corresponding to the i-th dimension within the current statistical time window, and its specific calculation method is as follows: , This indicates the number of failures in this dimension. This represents the total number of transmissions, and Di is the state deviation factor. The specific calculation method for Di is as follows: , This indicates the average failure level of this dimension over a historical statistical period. The deviation represents the degree of difference between the current state and the normal state. Making Di a dimensionless value facilitates unified calculations across different dimensions. This is a preset minimum value used to prevent... When =0, a division by zero occurs; the current state is normal. but Without amplifying the risks, the current failure rate has suddenly increased. but As the risk increases, the potential danger is amplified. S45: Calculation of the time decay factor. The impact of historical failure events weakens over time. A time decay factor α(t) is used, where α(t) is calculated as follows: ,in α(t) is the attenuation coefficient used to control the contribution of past data to the current FHI. By introducing α(t), we can avoid the old data from causing excessive interference to the current decision. S46: Geographical Clustering The specific calculation method is as follows: Where K(d) is the spatial distribution function of actual failure events, representing the average number of other failure event points around any failure event point within an observation radius of d. It is a spatial aggregation function obtained after region area normalization, and its specific calculation method is as follows: A represents the area of ​​the observation region, and N represents the total number of failure events. Let be the distance between the i-th and j-th failure event points. For indicator functions, when The value is 1 if the condition is met, and 0 otherwise. Let be a reference function for the theoretical random distribution, representing the expected average number of events within a radius d under a completely random distribution. It serves as a baseline to help the system determine if there are anomalous clusters in the current failure distribution. Its calculation method is as follows: ; S47: Calculate the failure popularity index κ is the aggregation amplification factor, used to adjust the impact of geographic aggregation effect. The calculated FHI is normalized, and its range is [0,1], divided into five levels: 0 to 0.2 is normal, 0.2 to 0.4 is slight failure, 0.4 to 0.6 is moderate failure, 0.6 to 0.8 is high-risk failure, and above 0.8 is severe failure. The scheduling module automatically determines the retransmission strategy according to the FHI level. If the FHI is low, the queue is merged and the retransmission is delayed; if the FHI is medium, the retransmission is performed on the normal path; if the FHI is high, path switching is enabled and cross-protocol retransmission is performed; if the FHI is extremely high, batch message sending is suspended and network diagnostics are triggered. The value of FHI reflects the comprehensive risk level of the failure event. When the FHI value is high, it indicates that the failure probability of the user group in the current area is on the rise, and network resources should be allocated or the retransmission path should be adjusted.

4. The 5G message transmission failure retransmission optimization method according to claim 1, characterized in that, Step S6 employs a progressive retransmission mechanism, including: S61: Fragment the message M to be retransmitted, forming a fragment set. And calculate semantic importance values ​​for each piece. High-importance fragments include message digest, title, main image, and structural metadata; S62: Calculate the retransmission priority score for each fragment. This involves comprehensively considering the importance of fragmentation, network conditions, and regional popularity. ,in, This is a standardized value for network failure rate. , As a failure popularity index, the higher the priority of the fragment, the more likely it will be scheduled in the resend window; S63: Calculate the number of fragments that are currently allowed to be sent simultaneously. ,in This is the window compression factor. The window automatically compresses as FHI increases, preventing secondary congestion in high-failure-rate areas of the network. The minimum number of slices allowed for a window. The maximum number of slices allowed for a window, determined by... Theoretically, the number of fragments that can be sent can be calculated, and clipping can be used to trim them to [...]. , Range, then multiply by When the failure rate is high, the window is further narrowed to achieve adaptive progressive sending; S64: After sorting by priority score, select the set of fragments within the window from high to low. And calculate the adaptive redundancy ratio. ,in For redundant growth rate, Based on the basic redundancy ratio, To assess the semantic importance of fragmentation, redundancy ratio It changes in tandem with the popularity of failures and the importance of fragmentation; S65: Perform redundant coding on the fragments within the window to generate additional check fragments, forming an error-correctable progressive transmission group; S66: Upon initial transmission, the receiving end can display the message summary and some visual content after receiving some high-priority fragments, thus achieving a gradual experience of "available first, then complete". S67: Monitor the ACK / NACK messages fed back by the receiver and calculate the local loss rate and latency indicators; S68: Based on feedback and changes in FHI, execute a tiered retransmission decision when... Immediately retransmit all NACK fragments; when Only the top k priority fragments are retransmitted, among which ,when It delays the retransmission of low-priority fragments and only performs cross-protocol concurrent transmission on high-importance fragments.

5. The 5G message transmission failure retransmission optimization method according to claim 1, characterized in that, The use of cross-protocol downgrade retransmission in step S3 includes: S31: Obtain failure information and evaluation conditions; receive the list of fragments that failed to be transmitted by the progressive fragment retransmission module. Obtain the Failure Heat Index (FHI) value H and the Failure Feature Vector to determine whether the cross-protocol degradation conditions are met. and Any one of the conditions in; S32: Protocol availability and weight calculation, defining the set of currently available protocols. Includes RCS, IP, SMS, and MMS for each fragment. In each protocol Calculate the weights above. , Given the importance of fragmentation, For fragmentation In the agreement The historical success rate, where H is the failure popularity index. For the protocol delay normalized value, These are the adjustable weighting coefficients of the system. S33: Dynamic protocol selection, for each fragment Select the protocol with the highest weight. For high-priority fragments, which contain digests and key metadata, protocols with high weight and low latency are prioritized for transmission. S34: Probability-driven redundancy scheduling calculates the redundancy transmission probability for critical fragments. With probability Key fragments are repeatedly sent on the selected protocol to enhance reliability in high failure hot environments, while non-critical fragments are sent with low redundancy or delayed according to the system policy. S35: Iterate through sending and receiving feedback, select the result to send messages according to fragmentation priority and protocol, receive feedback ACK and NACK, and update the fragmentation status. For failed fragments, update the protocol's historical success rate. Recalculate the weights Then, select the next backup protocol and form a loop iteration until the fragmentation is successful and the retransmission limit is reached.

6. A system for optimizing 5G message transmission failure retransmission based on the method of claim 1, characterized in that, include: Failure Analysis and Multidimensional Labeling Module: Receives messages and sends feedback information, including success and failure, network logs, extracts and generates multidimensional failure reason labels, including signal strength, packet loss rate, and network type in the network status dimension, user online status and device type in the user status dimension, and current load and congestion status in the base station load dimension, providing the raw data foundation for subsequent strategy selection; Failure Feature Vector Generation Module: Quantizes and weights multi-dimensional failure labels, uses dynamic weight formula to generate failure feature vectors, reflects the failure characteristics of each message in different dimensions, and transforms the original labels into numerical vectors that can be used for algorithm decision-making. Retransmission strategy selection module: Adaptively selects the optimal retransmission strategy based on the failure feature vector. The strategies include fragmented retransmission PFRT, delayed retransmission, path switching retransmission, and cross-protocol dynamic degradation retransmission CPADR, forming a specific retransmission plan for each message. Failure Heat Index Module: Calculates the failure heat index based on failure frequency, failure concentration, and network area failure density. It is used to measure network congestion and areas of concentrated failure, and provides indicators for message prioritization and retransmission rhythm. Priority scheduling module: Determines the message retransmission order based on FHI and user historical behavior prediction, decides whether to retransmit immediately or delay queuing, and reasonably allocates the retransmission order in resource-limited and high-failure environments to improve the delivery rate of core content; The progressive retransmission module splits messages into digests, key metadata, and the complete content. It prioritizes sending digests or key fragments and gradually retransmits the complete content as network conditions improve. It combines the fragmentation strategy and protocol selection output by the retransmission strategy selection module.

Images