An Optimization Method for Profit Distribution and Settlement of Mobile Terminals

Abstract

The present application provides an optimized method for split settlement of mobile terminals, including: obtaining the geographical location information, signal strength data, and mobile trajectory records of multiple mobile terminals, using the data as input parameters, and grouping the mobile terminals by using a clustering algorithm to obtain several mobile terminal groups; for each mobile terminal group, using a priority scoring model to determine the master mobile terminal within the group, the priority scoring model comprehensively considers the signal strength, geographical location, and similarity of the mobile trajectories of the mobile terminals, calculates the priority scores of each mobile terminal, and selects the mobile terminal with the highest score as the master mobile terminal; when a paging request needs to be initiated by a certain mobile terminal group, first, the master mobile terminal of the group initiates the paging on behalf of the group. If the paging fails, according to the sorting result of the priority scores of other mobile terminals within the group, other mobile terminals are sequentially tried to initiate the paging until the paging is successful or all mobile terminals are traversed.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular, to an optimized method for split - account settlement for mobile terminals. Background Art

[0002] In the scenario of split - account settlement for mobile terminals, how to optimize the paging strategy to improve communication efficiency and resource utilization when multiple devices settle accounts simultaneously is a key technical issue. Currently, the common practice is that each device independently initiates a paging request, which may lead to repeated paging and resource waste. If all devices' paging requests are simply merged, the overall paging failure rate may increase due to differences in device locations and signal strengths. The core contradiction in paging optimization lies in how to balance the resource waste caused by repeated paging and the paging failure rate caused by excessive merging. An ideal optimization scheme needs to comprehensively consider multiple factors such as the geographical location, signal strength, and movement trajectory of the devices, and dynamically adjust the paging strategy. However, the location and signal quality of the devices change at any time, and the optimization algorithm must be able to perceive these changes in real - time and respond quickly. In addition, the movement trajectories of different devices may be correlated, and paging optimization needs to explore this correlation, coordinate the paging order and time of different devices, and avoid mutual interference. The problem of multi - device cooperative paging optimization can be formally described as an optimal control problem of a stochastic process. Its state variables include the locations, signal strengths, etc. of each device, the control variable is the paging strategy of each device, and the goal is to minimize a cost function that comprehensively considers repeated paging and paging failure. Solving this optimization problem requires real - time tracking of state variables, predicting their future change trends, and solving a stochastic dynamic programming problem. This poses high requirements on the computing and storage resources of mobile terminals, and also requires real - time information interaction and synchronization between mobile terminals, presenting new challenges to the design of wireless communication networks. Summary of the Invention

[0003] The present invention provides an optimized method for split - account settlement for mobile terminals, mainly including:

[0004] Obtain the basic information of multiple mobile terminals, where the basic information includes geographical location information, signal strength data, and movement trajectory records; use the basic information as input parameters, and group the multiple mobile terminals by using a clustering algorithm to obtain several groups of mobile terminals;

[0005] For each group of mobile terminals, construct a priority scoring model by using a multi - layer perceptron, and use the priority scoring model to determine the master mobile terminal within each group of mobile terminals;

[0006] When a paging request needs to be initiated for a certain mobile terminal group, first, the master mobile terminal of the group initiates paging on behalf of the group. If the paging fails, according to the sorting result of the priority scores of other mobile terminals in the group, other mobile terminals are sequentially tried to initiate paging until the paging is successful or all mobile terminals are traversed;

[0007] When determining the paging order of each mobile terminal group, a graph-based scheduling algorithm is adopted. Each mobile terminal group is abstracted as a node of the graph, and the potential interference relationship between mobile terminal groups is abstracted as a directed edge between nodes. The graph is partitioned by the minimum cut algorithm to obtain several non-interfering subgraphs. The mobile terminal groups within the subgraph are paged in parallel, and the subgraphs are paged serially;

[0008] Real-time track the location change and dynamic change of the signal strength of the mobile terminal. When it is detected that the location change of a certain mobile terminal exceeds the preset location change threshold or the signal strength change exceeds the preset signal strength change threshold, an incremental update is triggered, and only the affected mobile terminal groups are adjusted to avoid global regrouping;

[0009] During the paging process, a reinforcement learning framework is adopted to continuously optimize the priority scoring model and grouping strategy of each mobile terminal. The success rate of each paging is used as the feedback reward, and the model parameters are updated through the policy gradient algorithm to adjust the weight parameters in the priority scoring model, so that the system can adaptively adjust the paging strategy according to historical experience.

[0010] The technical solution provided by the embodiment of the present invention may include the following beneficial effects:

[0011] The present invention discloses an optimization method for split settlement of mobile terminals. The method obtains the geographical location, signal strength, and mobile trajectory data of multiple mobile terminals, groups the mobile terminals by using a clustering algorithm, and determines the master mobile terminal of each group by using a priority scoring model. When paging, the master mobile terminal initiates first, and after failure, other mobile terminals are sequentially tried according to the priority. The present invention also adopts a graph-based scheduling algorithm to determine the paging order between groups, realizing an optimized combination of parallel and serial paging. In addition, the present invention can real-time track the state change of the mobile terminal and perform incremental updates to avoid frequent global reorganization. By introducing a reinforcement learning framework, the present invention can continuously optimize the scoring model and grouping strategy to improve the paging success rate. The method significantly improves the efficiency and reliability of mobile terminal group paging and is applicable to large-scale mobile communication scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flowchart of an optimization method for split settlement of mobile terminals according to the present invention.

[0013] Figure 2Schematic diagram of an optimization method for split - account settlement for a mobile terminal according to the present invention.

[0014] Figure 3 Another schematic diagram of an optimization method for split - account settlement for a mobile terminal according to the present invention. Detailed implementation manners

[0015] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all the embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this specification.

[0016] As Figures 1-3 , an optimization method for split - account settlement for a mobile terminal in this embodiment may specifically include:

[0017] S101. Obtain the basic information of multiple mobile terminals, where the basic information includes geographical location information, signal strength data, and mobile trajectory records; use the basic information as input parameters, and group the multiple mobile terminals by using a clustering algorithm to obtain several mobile terminal groups.

[0018] Obtain the geographical location information, signal strength data, and mobile trajectory records of at least two mobile terminals; pre - process the geographical location information, and use the Kalman filtering algorithm to remove outliers and noise data to obtain the cleaned location data; perform normalization processing on the signal strength data, and use the maximum - minimum normalization method to uniformly map the signal strength data of different mobile terminals into the interval [0, 1] to obtain the normalized strength data; compress the mobile trajectory records, and use the Douglas - Peucker algorithm to extract key location points including stop points and inflection points to obtain the compressed trajectory data; construct a feature vector from the cleaned location data, normalized strength data, and compressed trajectory data; measure their similarity by distance to obtain the grouping result of the mobile terminals; for each mobile terminal group, perform density clustering on the location data within the mobile terminal group to obtain the typical location distribution of the mobile terminal group; for each mobile terminal group, perform statistical analysis on the signal strength data within the mobile terminal group to obtain the signal strength distribution of the mobile terminal group; for each mobile terminal group, perform frequent sequence mining on the trajectory data within the mobile terminal group to obtain the typical mobile trajectory pattern of the mobile terminal group; integrate the location distribution, signal strength distribution, and mobile trajectory pattern feature attributes of each mobile terminal group to construct a mobile terminal group portrait.

[0019] Specifically, first, obtain the geographical location information, signal strength data, and movement trajectory records of multiple mobile terminals. For example, obtain the longitude and latitude coordinates through GPS positioning, obtain the signal strength value through the signal strength detection module, and obtain the movement trajectory points through the trajectory recording module. Then, preprocess the geographical location information, and use the Kalman filtering algorithm to remove outliers and noise data. For example, consider longitude and latitude coordinates outside a reasonable range as outliers to be removed, and consider randomly fluctuating coordinate points as noise to be removed, to obtain the cleaned position data. Next, perform normalization processing on the signal strength data, and use the maximum-minimum normalization method to uniformly map the signal strength data of different mobile terminals to the interval from 0 to 1. For example, map the signal strength values from -90 dBm to -60 dBm to the interval from 0 to 1 to obtain the normalized strength data. Compress the movement trajectory records, and use the Douglas-Peucker algorithm to extract key position points such as staying points and inflection points. For example, consider position points with a movement speed lower than 1 m / s and a duration exceeding 10 minutes as staying points, and consider position points with a movement direction change exceeding 45 degrees as inflection points, to obtain the compressed trajectory data. Construct a feature vector from the cleaned position data, the normalized strength data, and the compressed trajectory data. For example, use a two-dimensional longitude and latitude vector to represent the position feature, use a one-dimensional signal strength vector to represent the strength feature, and use a sequence of staying points and inflection points to represent the trajectory feature. Input the feature vector into the K-means clustering algorithm, and measure the similarity by calculating the Euclidean distance between mobile terminals. For example, calculate the sum of the Euclidean distances of the position vectors, strength vectors, and trajectory vectors of two mobile terminals as the similarity metric, set the number of clusters K to 3, and iteratively optimize the cluster centers until convergence to obtain the grouping result of the mobile terminals. For each group, perform DBSCAN density clustering on the position data within the group to obtain the typical position distribution of the group. For example, set the density radius to 100 meters and the density threshold to 5, and extract the position area with a density exceeding the threshold as the typical position distribution. For each group, perform statistical analysis on the signal strength data within the group to obtain the signal strength distribution of the group. For example, calculate statistical quantities such as the mean, variance, and quantiles of the signal strength, and plot the probability density curve and cumulative distribution curve of the signal strength. For each group, perform PrefixSpan frequent sequence mining on the trajectory data within the group to obtain the typical movement trajectory pattern of the group. For example, set the frequency threshold to 20%, and mine the staying point sequences and inflection point sequences with a frequency exceeding the threshold as the typical trajectory pattern. Finally, integrate the characteristic attributes such as the position distribution, signal strength distribution, and movement trajectory pattern of each group to construct a portrait of the mobile terminal groups, which is convenient for intuitively displaying the characteristic differences of each group and providing a reference basis for subsequent personalized services.

[0020] S102: for each mobile terminal group, a multi-layer perceptron is used to construct a priority scoring model, and the priority scoring model is used to determine a master mobile terminal in each mobile terminal group.

[0021] The signal strength, geographic location and movement trajectory information of multiple mobile terminals are obtained; for each movement trajectory of the mobile terminal, two trajectories are sampled to obtain a sampling point sequence of equal length; the Euclidean distance matrix between the two sampling point sequences is calculated; the path with the minimum cost is found in the distance matrix, and the path with the minimum cost is used as the optimal match of the two trajectories; the similarity of the two trajectories is calculated according to the optimal match; for each mobile terminal, a weighted average model is used to calculate the comprehensive priority score of each mobile terminal according to the signal strength, geographic location and movement trajectory similarity, and the weight in the weighted average model is preset according to actual needs; the mobile terminal with the highest comprehensive priority score in each mobile terminal group is determined as the candidate master mobile terminal of the group; if there are multiple candidate master mobile terminals with the same comprehensive priority score, the signal strengths of the multiple candidate master mobile terminals are compared, and the candidate master mobile terminal with the highest signal strength is determined as the master mobile terminal of the group; the master mobile terminal information of each mobile terminal group is output, and the master mobile terminal information includes a mobile terminal identifier, a signal strength, a geographic location coordinate and a mobile terminal group to which it belongs.

[0022] Specifically, first, a multi-layer perceptron network with 3 hidden layers is constructed. The number of nodes in the hidden layers is 16, 8, and 4 respectively, and there is 1 node in the output layer. The ReLU activation function is used. The mean squared error is used as the loss function, and the Adam optimizer with a learning rate of 0.1 is used to train the model until convergence. The model outputs a priority score ranging from 0 to 100. Signal strength data of multiple mobile terminals are obtained through the wireless communication module, such as obtaining the RSSI value of each mobile terminal, with the unit of dBm. At the same time, the geographical location coordinates of each mobile terminal are obtained through the GPS positioning module, such as obtaining the longitude and latitude, with the unit of degree. Then, the historical movement trajectory data of each mobile terminal are obtained through the trajectory recording module, such as obtaining a sequence of position points within a certain period of time. For the movement trajectory of each mobile terminal, the linear interpolation algorithm is used to resample the two trajectories to obtain an equally long sequence of sampled points, such as resampling the trajectory into 100 equally spaced position points. Then, the Euclidean distance matrix between the two sequences of sampled points is calculated, such as calculating the value of each element in the matrix using the straight-line distance formula between two points. Next, the path with the minimum cost is found in the distance matrix, such as using the dynamic programming algorithm to find the diagonal path with the minimum cumulative distance, and this path is used as the optimal match between the two trajectories. The similarity between the two trajectories is calculated based on the optimal match, such as using the average distance value of the optimal match to measure the similarity, and the smaller the distance, the higher the similarity. For each mobile terminal, a weighted average algorithm is used to construct a priority score model to calculate the comprehensive priority score. For example, the signal strength weight is set to 5, the geographical location weight is set to 3, and the trajectory similarity weight is set to 2, and the three indicators are weighted and summed to obtain the comprehensive score. The mobile terminal with the highest comprehensive score in each group is determined as the candidate master mobile terminal. If there are multiple candidate mobile terminals with the same score, their signal strengths are compared, and the mobile terminal with the highest signal strength is determined as the master mobile terminal of the group. Finally, the information of the master mobile terminal of each group is output, including the mobile terminal ID, RSSI, longitude and latitude, and group ID, etc., for subsequent communication control and resource scheduling.

[0023] S103. When a paging request needs to be initiated for a certain mobile terminal group, first, the master mobile terminal of the group initiates the paging on behalf of the group. If the paging fails, according to the sorting result of the priority scores of other mobile terminals within the group, other mobile terminals are sequentially tried to initiate the paging until the paging is successful or all mobile terminals are traversed.

[0024] A1. Obtain the pre-configured mobile terminal grouping information, and determine the master mobile terminal and the standby mobile terminal in each group; A2. When a certain mobile terminal group needs to initiate a paging request, determine whether the master mobile terminal in the group is available; if the master mobile terminal is available, the master mobile terminal represents the group to initiate a paging request; if the master mobile terminal is unavailable, obtain the preset priority information of the standby mobile terminals in the group; A3. Sort the standby mobile terminals in descending order according to the priority to obtain a sorting result; A4. According to the sorting result, sequentially attempt to initiate a paging request by the standby mobile terminals whose priority is higher than the preset threshold, and wait for a response; if the response from the target mobile terminal is received within the preset time threshold, determine that the paging request is successful and end the paging process; if the response from the target mobile terminal is not received within the preset time threshold, determine that the paging request fails; A5. If there are still standby mobile terminals that have not been attempted to page, select the next standby mobile terminal whose priority is higher than the preset threshold, and repeat steps A1 - A4; A6. If the paging is still not successful after traversing all the standby mobile terminals in the group, determine that the paging request of this mobile terminal group fails and end the paging process.

[0025] Specifically, first read the mobile terminal grouping information from the pre-configured database. For example, there are 10 groups, and each group contains 5 - 10 mobile terminals. For each group, use the above-mentioned priority scoring model to calculate the comprehensive priority score of each mobile terminal, determine the mobile terminal with the highest score as the master mobile terminal, and the mobile terminal with the second highest score as the first standby mobile terminal, and so on. When group 1 needs to initiate a paging to the target mobile terminal, first check the status flag bit of the master mobile terminal A. If it is 1, it means it is available, and directly initiate a paging request by A. If the status flag bit of A is 0, then read the priority array of the standby mobile terminals, such as {B:8, C:7, D:6, E:5}, and set the priority threshold to 6. Sort the standby mobile terminals in descending order according to the priority to obtain the sequence {B, C, D}. First, B sends a paging request to the target mobile terminal, and at the same time starts a 2 - second timer. If the response from the target mobile terminal is received within 2 seconds, mark B as the new master mobile terminal, update the priority array, and end the paging process. If no response is received after 2 seconds of timeout, traverse the next standby mobile terminal C and repeat the above process. If no response is received after traversing {B, C, D}, mark the entire group 1 as paging failed, report it to the network management system, and trigger the exception handling mechanism. Finally, write the paging result into the database, update the status information of the relevant mobile terminals, complete a paging task, and wait for the next paging request to come.

[0026] S104. When determining the paging order of each mobile terminal group, a graph-based scheduling algorithm is adopted. Each mobile terminal group is abstracted as a node of the graph, and the potential interference relationship between mobile terminal groups is abstracted as a directed edge between nodes. The graph is partitioned by the minimum cut algorithm to obtain several non-interfering subgraphs. The mobile terminal groups within a subgraph are paged in parallel, and the subgraphs are paged serially.

[0027] According to the mobile terminal group information, an initial interference graph is constructed. Each node in the initial interference graph represents a mobile terminal group, and the directed edge between nodes represents the potential interference relationship between groups. The maximum flow minimum cut algorithm is used to partition the initial interference graph into several non-interfering subgraphs. The minimum cut means the minimum interference between subgraphs, ensuring that the parallel paging within the subgraphs will not interfere with each other. For each subgraph obtained by partitioning, all the mobile terminal groups within it are added to the same parallel paging queue. The groups in the parallel paging queue can perform paging operations simultaneously without interference. Through the depth-first search algorithm, the topological order of the subgraph is obtained. The topological order represents the dependency relationship between subgraphs, with the subgraphs that complete paging first ranked in the front and those that complete later ranked in the back. According to the topological order, the serial paging scheme between subgraphs is determined to ensure that the paging between subgraphs will not affect each other. Within the parallel paging queue of each subgraph, the round-robin scheduling algorithm is used to perform paging operations on each mobile terminal group in turn. The round-robin scheduling adopts a cyclic method to allocate paging time slices to each group in turn until the queue is empty. During the serial paging process, if all the groups in the current subgraph have completed paging, then according to the topological order relationship, it jumps to the next subgraph and starts its parallel paging queue. Through a recursive method, the parallel paging and serial paging are continuously executed until the paging queues of all subgraphs are empty, completing the entire paging scheduling process.

[0028] Specifically, first, an initial interference graph is constructed based on the mobile terminal grouping information. For example, if there are 10 groups, each group is regarded as a node in the graph. According to the interference relationship between groups, directed edges are added between nodes, and the weight of the edge represents the interference intensity. Then, the maximum flow minimum cut algorithm is used to partition the interference graph. For example, the Edmonds-Karp algorithm is used to repeatedly find an augmenting path on the residual graph and calculate the maximum flow between nodes until no augmenting path can be found. Finally, the graph is partitioned into several non-interfering subgraphs according to the minimum cut, and paging can be performed in parallel within the subgraphs. Next, for each subgraph, all the groups inside it are added to a parallel paging queue. Then, the topological order of the subgraph is obtained through depth-first search. First, the nodes with an in-degree of 0 are visited, and then their adjacent nodes are recursively visited until all nodes are visited. The topological order represents the dependency relationship between subgraphs, and the subgraphs that complete paging first are ranked in the front. According to the topological order, a serial paging scheme between subgraphs is determined to ensure that the subgraphs paged first will not affect the subgraphs paged later. Inside the parallel paging queue of each subgraph, a round-robin scheduling algorithm, such as time slice rotation, is used to allocate a 10-millisecond time slice for each group and perform paging in sequence until the queue is empty. During serial paging, if all the current subgraphs have completed paging, then according to the topological order, the next subgraph is jumped to and the parallel paging queue of it is started. Through recursive execution and serial paging, until the queues of all subgraphs are empty, the entire paging scheduling process is completed. This scheme cleverly uses graph algorithms to achieve automatic decomposition and scheduling of paging tasks, maximizing the paging efficiency and avoiding interference, and is an efficient and feasible technical solution.

[0029] S105. Real-time track the position change and dynamic change of the signal strength of the mobile terminal. When it is detected that the position change of a certain mobile terminal exceeds the preset position change threshold or the signal strength change exceeds the preset signal strength change threshold, trigger incremental update, and only adjust the affected groups to avoid global regrouping.

[0030] Obtain the real-time location information and signal strength information of the mobile terminal; compare the real-time location information of the mobile terminal with a preset location threshold, and compare the signal strength information with a preset signal strength threshold; if the change in the real-time location information of the mobile terminal exceeds the preset location threshold or the change in the signal strength information exceeds the preset signal strength threshold, trigger incremental update; determine the affected groups according to the current location and signal strength of the mobile terminal by using a pre-established location-signal strength-group mapping table; adopt the K-means clustering algorithm, with the location and signal strength of the mobile terminal as features, re-cluster the affected groups to obtain a new grouping result; compare the new grouping result with the original global grouping result one by one, if the number of mobile terminals in the group or the location center changes significantly, it is determined as a group that needs to be adjusted; according to the groups that need to be adjusted, update the mapping relationship between the mobile terminal and the base station, map each group to the base station with the optimal signal strength, and obtain an updated global grouping scheme; package the updated global grouping scheme into an incremental update instruction and send it to the corresponding mobile terminal and base station through the mobile network to notify them to update the local group cache to complete the incremental update.

[0031] Specifically, the mobile terminal collects the GPS location and the signal strength RSSI every 5 seconds and reports them to the location management server. A trigger with a location change threshold of 10 meters and a signal strength change threshold of 3 dB is maintained in the server memory. Once the location change of the mobile terminal exceeds 10 meters or the signal strength change exceeds 3 dB, the trigger generates an incremental update event. The event carries the new location and new signal strength of the mobile terminal, and quickly locates the affected group by searching the location-signal strength-group mapping table through the hash algorithm. Then, the K-means clustering algorithm is adopted, with the clustering center K = 5, and the longitude and latitude of the mobile terminal location and the signal strength RSSI are used as feature vectors to re-cluster the affected group to obtain several new clusters. The new clusters are compared with the original groups one by one, and the change rate of the number of mobile terminals in the cluster and the drift distance of the cluster center are calculated. If the change rate exceeds 20% or the center drift distance exceeds 15 meters, it is determined that the corresponding original group needs to be adjusted. During the adjustment, the drifted mobile terminals are first removed, and then the newly added mobile terminals are inserted into the cluster. For the groups that need to be adjusted, update their mapping relationship with the base station, traverse each mobile terminal, select the base station with the maximum signal strength RSSI as the serving base station, and establish a new group-base station mapping table. Finally, the updated grouping scheme is packaged into an incremental update instruction, compressed by Protobuf, and distributed to the corresponding mobile terminals and base stations through the message queue to notify them to update the local grouping cache. The incremental update instruction is in JSON format and contains fields such as group ID, mobile terminal list, base station ID, etc. Through this incremental update mechanism, the changes in the location and signal strength of the mobile terminal can be quickly responded to, the grouping scheme can be dynamically optimized, and thus the paging efficiency and success rate can be improved.

[0032] S106. During the paging process, adopt a reinforcement learning framework to continuously optimize the priority scoring model and grouping strategy of each mobile terminal. Use the success rate of each paging as the feedback reward, and update the model parameters through the policy gradient algorithm to adjust the weight parameters in the priority scoring model, so that the system can adaptively adjust the paging strategy according to historical experience.

[0033] Relevant data in the paging process are obtained, including the location information, moving speed and power attributes of the mobile terminal, and the historical paging success rate; the relevant data are cleaned and normalized preprocessed, and key features are extracted as the input of the model; the mobile terminal priority scoring model is trained to predict its priority score according to the mobile terminal attributes; the mobile terminals are grouped according to the priority scores of the mobile terminals using the K-means clustering algorithm, and mobile terminals with similar priority scores are divided into the same group; in each paging process, a specific mobile terminal group is selected for paging according to a preset strategy, and the preset strategy includes randomly selecting a mobile terminal group with a preset probability and selecting a mobile terminal group with the highest priority score with a preset probability; the success rate of each paging is recorded as a reward feedback for reinforcement learning, and the policy gradient algorithm is used to update the parameters of the mobile terminal priority scoring model; through continuous data collection and reinforcement learning, the mobile terminal priority scoring model and paging strategy are continuously optimized to adapt to changes in actual paging scenarios and improve the overall paging success rate.

[0034] Specifically, during the paging process, the data is cleaned and normalized through attribute data such as GPS location, moving speed, and power reported by the mobile terminal, as well as related data such as historical paging success rate. When cleaning, outliers with GPS location beyond the reasonable range (such as latitude and longitude beyond -90~90 degrees), moving speed less than 0 or greater than 100m / s, and power less than 0 or greater than 100% are eliminated. When normalizing, the maximum and minimum values ​​are normalized for continuous variables, and unique hot encoding is used for discrete variables. Four key features of mobile terminal location, moving speed, power, and historical paging success rate are extracted as model inputs. Based on priority scores, the K-means clustering algorithm is used to divide mobile terminals into 5 groups, and the Euclidean distance is used to measure similarity during clustering. When paging, a group is randomly selected with a probability of 20%, and the group with the highest average priority score is selected with a probability of 80%. Assuming that the second group is selected for a certain paging, which contains 100 mobile terminals, and 90 of them are successfully awakened, the paging success rate is 90%. The success rate is used as reward feedback and substituted into the policy gradient algorithm to update the model parameters and group selection probability. The policy gradient uses the Monte Carlo method to estimate the gradient and is weighted by the reward value with a learning rate of 0.01. Through continuous iterative optimization, the model can accurately predict the priority based on the attributes of the mobile terminal, and the group selection strategy can adapt to different scenarios, thereby improving the overall paging success rate.

[0035] The description of the above embodiments is only used to help understand the technical solutions and core ideas of the present application. Ordinary technical personnel in this field should understand that they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents. However, these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An optimization method for split settlement of a mobile terminal, characterized in that, The method includes: Obtain the basic information of multiple mobile terminals, where the basic information includes geographical location information, signal strength data, and mobile trajectory records; use the basic information as input parameters, and use a clustering algorithm to group the multiple mobile terminals to obtain several mobile terminal groups; For each mobile terminal group, use a multi-layer perceptron to construct a priority scoring model, and use the priority scoring model to determine the master mobile terminal within each mobile terminal group; When a certain mobile terminal group needs to initiate a paging request, first the master mobile terminal of the group initiates paging on behalf of the group. If the paging fails, then according to the sorting result of the priority scores of other mobile terminals within the group, other mobile terminals are successively tried to initiate paging until the paging is successful or all mobile terminals are traversed; When determining the paging order of each mobile terminal group, use a graph-based scheduling algorithm. Abstract each mobile terminal group as a node of the graph, and abstract the potential interference relationship between mobile terminal groups as a directed edge between nodes. Divide the graph through the minimum cut algorithm to obtain several non-interfering subgraphs. The mobile terminal groups within the subgraph are paged in parallel, and the subgraphs are paged serially; Real-time track the position change and dynamic change of signal strength of the mobile terminal. When it is detected that the position change of a certain mobile terminal exceeds the preset position change threshold or the signal strength change exceeds the preset signal strength change threshold, trigger incremental update, and only adjust the affected mobile terminal groups to avoid global regrouping; During the paging process, use a reinforcement learning framework to continuously optimize the priority scoring model and grouping strategy of each mobile terminal. Use the success rate of each paging as feedback reward, and update the model parameters through the policy gradient algorithm to adjust the weight parameters in the priority scoring model, so that the system can adaptively adjust the paging strategy according to historical experience.

2. The method according to claim 1, wherein Obtain the basic information of multiple mobile terminals, where the basic information includes geographical location information, signal strength data, and mobile trajectory records; use the basic information as input parameters, and use a clustering algorithm to group the multiple mobile terminals to obtain several mobile terminal groups, including: Obtain the geographical location information, signal strength data, and mobile trajectory records of at least two mobile terminals; Preprocess the geographical location information, and use the Kalman filtering algorithm to remove outliers and noise data to obtain the cleaned position data; Normalize the signal strength data, and use the maximum-minimum normalization method to uniformly map the signal strength data of different mobile terminals into the interval [0, 1] to obtain the normalized strength data; Compress the mobile trajectory record, and use the Douglas-Peucker algorithm to extract the key position points including stop points and inflection points to obtain the compressed trajectory data; Construct a feature vector from the cleaned position data, the normalized strength data, and the compressed trajectory data; Input the feature vector into the K-means clustering algorithm, and measure its similarity by calculating the Euclidean distance between mobile terminals to obtain the grouping result of mobile terminals; For each mobile terminal group, perform density clustering on the location data within the mobile terminal group to obtain the typical location distribution of the mobile terminal group; For each mobile terminal group, perform statistical analysis on the signal strength data within the mobile terminal group to obtain the signal strength distribution of the mobile terminal group; For each mobile terminal group, perform frequent sequence mining on the trajectory data within the mobile terminal group to obtain the typical mobile trajectory pattern of the mobile terminal group; Integrate the location distribution, signal strength distribution, and mobile trajectory pattern feature attributes of each mobile terminal group to construct a mobile terminal group profile.

3. The method according to claim 1, wherein For each mobile terminal group, construct a priority scoring model using a multi-layer perceptron; use the priority scoring model to determine the master mobile terminal within each mobile terminal group, including: Obtain the signal strength, geographical location, and mobile trajectory information of multiple mobile terminals; For the mobile trajectory of each mobile terminal, sample two trajectories to obtain equidistant sampling point sequences; Calculate the Euclidean distance matrix between the two sampling point sequences; Find the path with the minimum cost in the distance matrix and use the path with the minimum cost as the optimal match for the two trajectories; Calculate the similarity between the two trajectories based on the optimal match; For each mobile terminal, calculate the comprehensive priority score of each mobile terminal using the priority scoring model based on the signal strength, geographical location, and mobile trajectory similarity. The weights in the priority scoring model are preset according to actual requirements; Determine the mobile terminal with the highest comprehensive priority score within each mobile terminal group as the candidate master mobile terminal of the group; If there are multiple candidate master mobile terminals with the same comprehensive priority score, compare the signal strengths of the multiple candidate master mobile terminals and determine the candidate master mobile terminal with the highest signal strength as the master mobile terminal of the group; Output the master mobile terminal information of each mobile terminal group. The master mobile terminal information includes the mobile terminal identifier, signal strength, geographical location coordinates, and the mobile terminal group to which it belongs.

4. The method according to claim 1, characterized in that When a certain mobile terminal group needs to initiate a paging request, first, the master mobile terminal of the group initiates the paging on behalf of the group. If the paging fails, then according to the sorting result of the priority scores of other mobile terminals within the group, other mobile terminals are successively tried to initiate the paging until the paging is successful or all mobile terminals are traversed, including: A1. Obtain the pre-configured mobile terminal group information and determine the master mobile terminal and standby mobile terminals within each group; A2. When a certain mobile terminal group needs to initiate a paging request, determine whether the master mobile terminal within the group is available; If the master mobile terminal is available, the master mobile terminal initiates a paging request on behalf of the group; If the master mobile terminal is unavailable, obtain the preset priority information of the standby mobile terminals within the group; A3. Sort the standby mobile terminals in descending order according to the priority to obtain the sorting result; A4. According to the sorting result, successively try the standby mobile terminals with priorities higher than the preset threshold to initiate paging requests and wait for responses; If a response from the target mobile terminal is received within the preset time threshold, it is determined that the paging request is successful and the paging process ends; If a response from the target mobile terminal is not received within the preset time threshold, it is determined that the paging request fails; A5. If there are still standby mobile terminals that have not been paged, select the next standby mobile terminal with a priority higher than the preset threshold, and repeat steps A1 - A4; A6. If the paging is still not successful after traversing all standby mobile terminals in the group, it is determined that the paging request for this mobile terminal group fails and the paging process ends.

5. The method according to claim 1, wherein When determining the paging order of each mobile terminal group, a graph - based scheduling algorithm is used. Each mobile terminal group is abstracted as a node of the graph, and the potential interference relationship between mobile terminal groups is abstracted as a directed edge between nodes. The graph is partitioned by the minimum cut algorithm to obtain several non - interfering sub - graphs. The mobile terminal groups within the sub - graphs are paged in parallel, and the sub - graphs are paged serially, including: According to the mobile terminal group information, construct an initial interference graph, where each node in the initial interference graph represents a mobile terminal group, and the directed edge between nodes represents the potential interference relationship between groups; Use the maximum - flow minimum - cut algorithm to partition the initial interference graph into several non - interfering sub - graphs. The minimum cut means the minimum interference between sub - graphs, ensuring that the parallel paging within the sub - graphs will not interfere with each other; For each sub - graph obtained by partitioning, add all the mobile terminal groups inside it to the same parallel paging queue. The groups in the parallel paging queue can perform paging operations simultaneously without interference; Through the depth - first search algorithm, obtain the topological order of the sub - graph. The topological order represents the dependency relationship between sub - graphs. The sub - graphs that complete paging first are ranked in front, and those that complete later are ranked behind; According to the topological order, determine the serial paging scheme between sub - graphs to ensure that the paging between sub - graphs will not affect each other; Within the parallel paging queue of each sub - graph, use the round - robin scheduling algorithm to perform paging operations on each mobile terminal group in turn. The round - robin scheduling uses a cyclic method to allocate paging time slices to each group in turn until the queue is empty; During the serial paging process, if all the groups in the current sub - graph have completed paging, according to the topological order relationship, jump to the next sub - graph and start its parallel paging queue; Through a recursive method, continuously perform parallel paging and serial paging until the paging queues of all sub - graphs are empty, completing the entire paging scheduling process.

6. The method according to claim 1, characterized in that, Real - time track the position change and dynamic change of the signal strength of the mobile terminal. When it is detected that the position change of a certain mobile terminal exceeds the preset position change threshold or the signal strength change exceeds the preset signal strength change threshold, trigger an incremental update and only adjust the affected groups to avoid global re - grouping, including: Obtain the real - time position information and signal strength information of the mobile terminal; Compare the real - time position information of the mobile terminal with the preset position threshold, and compare the signal strength information with the preset signal strength threshold; If the change in the real-time location information of the mobile terminal exceeds a preset location threshold or the change in the signal strength information exceeds a preset signal strength threshold, an incremental update is triggered; According to the current location and signal strength of the mobile terminal, using the pre-established location-signal strength-group mapping table, determine the affected groups; Adopt the K-means clustering algorithm, with the location and signal strength of the mobile terminal as features, re-cluster the affected groups to obtain a new grouping result; Compare the new grouping result with the original global grouping result one by one. If the number of mobile terminals in the group or the location center changes significantly, it is determined as the group that needs to be adjusted; According to the groups that need to be adjusted, update the mapping relationship between the mobile terminal and the base station, map each group to the base station with the optimal signal strength, and obtain the updated global grouping scheme; Package the updated global grouping scheme into an incremental update instruction, and send it to the corresponding mobile terminal and base station through the mobile network, notifying them to update the local group cache to complete the incremental update.

7. The method according to claim 3, characterized in that, During the paging process, adopt a reinforcement learning framework to continuously optimize the priority scoring model and grouping strategy of each mobile terminal. Use the success rate of each paging as the feedback reward, and update the model parameters through the policy gradient algorithm to adjust the weight parameters in the priority scoring model, so that the system can adaptively adjust the paging strategy according to historical experience, including: Obtain the relevant data during the paging process. The relevant data includes the location information, moving speed and power attributes of the mobile terminal, as well as the historical paging success rate; Perform cleaning and normalization preprocessing operations on the relevant data, and extract key features as the input of the model; Through training, enable the mobile terminal priority scoring model to predict its priority score according to the mobile terminal attributes; According to the priority scores of the mobile terminals, use the K-means clustering algorithm to group the mobile terminals, and divide the mobile terminals with similar priority scores into the same group; During each paging process, select a specific mobile terminal group for paging according to the preset strategy. The preset strategy includes randomly selecting a mobile terminal group with a preset probability and selecting the mobile terminal group with the highest priority score with a preset probability; Record the success rate of each paging as the reward feedback of reinforcement learning, and use the policy gradient algorithm to update the parameters of the mobile terminal priority scoring model; Through continuous data collection and reinforcement learning, continuously optimize the mobile terminal priority scoring model and paging strategy, adapt to the changes in the actual paging scenario, and improve the overall paging success rate.

Images