A base station congestion prediction method and related device

Abstract

The application discloses a base station congestion prediction method and related equipment, wherein the method comprises the following steps: acquiring a first base station handover record set between a target base station and a first base station around the target base station; the first base station handover record set comprises base station handover records in each time period within several days; based on the first base station handover record set, a first handover sequence between the target base station and the first base station is determined; the first handover sequence is a handover sequence with the highest handover frequency in the same time period in all base station handover records; based on the first handover sequence, a preset neural network is trained to obtain a target neural network; and based on base station handover data of the target base station in a current period and the target neural network, congestion early warning information is generated. The application can be widely applied to the technical field of network resource scheduling.

Description

Technical Field

[0001] This application relates to the field of network resource scheduling technology, and in particular to a base station congestion prediction method and related equipment. Background Technology

[0002] With the rapid development of mobile communication technology and the widespread adoption of smart terminals, data traffic in mobile networks has exploded. Base stations, as key nodes in mobile communication networks, are facing increasingly prominent congestion problems.

[0003] Traditional base station congestion detection methods primarily rely on real-time monitoring of base station load metrics, such as CPU utilization, memory usage, and bandwidth occupancy. This method is passive, only issuing warnings when congestion has already occurred or is about to occur. Consequently, traditional base station congestion prediction lacks foresight and cannot reflect the congestion situation of base stations in a timely manner. Therefore, there are still technical problems that need to be solved in related technologies. Summary of the Invention

[0004] The purpose of this application is to at least partially solve one of the technical problems existing in the prior art.

[0005] Therefore, one objective of this application is to provide a base station congestion prediction method and related equipment, which can improve the timeliness of base station congestion detection.

[0006] To achieve the above technical objectives, the technical solution adopted in this application includes: a base station congestion prediction method, comprising: acquiring a first base station handover record set between a target base station and first base stations surrounding the target base station; the first base station handover record set includes base station handover records for each time period within several days; determining a first handover sequence between the target base station and the first base station based on the first base station handover record set; the first handover sequence being the handover sequence with the highest handover frequency in the same time period among all the base station handover records; training a preset neural network based on the first handover sequence to obtain a target neural network; and generating congestion warning information based on the base station handover data of the target base station in the current period and the target neural network.

[0007] In addition, the base station congestion prediction method according to the above embodiments of the present invention may also have the following additional technical features:

[0008] Furthermore, in this embodiment of the application, the step of training a preset neural network based on the first switching sequence to obtain a target neural network specifically includes:

[0009] Extract the statistical features of the number of terminals switching from the first base station to the target base station per hour, the rate of change of the switching ratio of terminals of preset service types, the dwell time distribution of terminal devices at the first base station, and the switching time interval between base stations in the first switching sequence.

[0010] Based on the number of terminals, determine the hourly handover request growth rate of the base station;

[0011] Based on the dwell time distribution, the median dwell time of the terminal device at the previous base station is determined;

[0012] The switching request growth rate, the median dwell time, the statistical characteristics, and the switching ratio change rate are input into a preset neural network for training and the network parameters are adjusted to obtain the target neural network.

[0013] Furthermore, in this embodiment of the application, determining the hourly handover request growth rate of the base station based on the number of terminals specifically includes:

[0014] For any two adjacent time periods, the number of handover requests for the base stations in the two adjacent time periods is determined based on the number of terminals in the previous time period and the number of terminals in the current time period; wherein the duration of each time period is greater than or equal to one hour.

[0015] The hourly handover request growth rate of the base station is determined based on the increase in the number of handover requests and the duration of each time period.

[0016] Furthermore, in this embodiment of the application, the step of determining congestion warning information based on the base station handover data of the target base station in the current collection period and the target neural network specifically includes:

[0017] Extract the first time when traffic enters the target base station, the second time when traffic leaves the target base station, the coordinates of the second base station preceding the target base station, and the coordinates of the second base station following the target base station from the base station handover data;

[0018] Based on the first time, the second time, the coordinates of the first base station, and the coordinates of the second base station, the target handover sequence of the target base station in the current period is determined;

[0019] The target switching sequence is input into the target neural network to obtain the target probability of the target base station becoming congested within 1 hour after the current period.

[0020] Based on the target probability, congestion warning information is determined.

[0021] Furthermore, in this embodiment of the application, determining the first handover sequence between the target base station and the first base station based on the first base station handover record set specifically includes:

[0022] The first base station handover record set is filtered to obtain the target base station handover record set.

[0023] Based on a preset algorithm, the first handover sequence is determined from the target base station handover record set.

[0024] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium, including the method described in any of the preceding claims when executed by a processor.

[0025] To achieve the above objectives, another aspect of this application provides a base station congestion prediction device, comprising:

[0026] The acquisition unit is used to acquire a first base station handover record set between the target base station and a first base station surrounding the target base station; the first base station handover record set includes base station handover records for each time period within several days;

[0027] The first processing unit is configured to determine a first handover sequence between the target base station and the first base station based on the first base station handover record set; the first handover sequence is the handover sequence with the highest handover frequency in the same time period among all the base station handover records.

[0028] The second processing unit is used to train a preset neural network based on the first switching sequence to obtain a target neural network;

[0029] The third processing unit is used to generate congestion warning information based on the base station handover data of the target base station in the current period and the target neural network.

[0030] To achieve the above objectives, another aspect of this application provides an electronic device, comprising:

[0031] At least one processor;

[0032] At least one memory for storing at least one program;

[0033] When the at least one program is executed by the at least one processor, the at least one processor performs the method as described in any of the preceding statements.

[0034] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the methods described above.

[0035] This application provides a base station congestion prediction method, apparatus, electronic device, storage medium, and program product. The solution obtains a first set of base station handover records between a target base station and first base stations surrounding the target base station; the first set of base station handover records includes base station handover records for each time period within several days; based on the first set of base station handover records, a first handover sequence between the target base station and the first base stations is determined; the first handover sequence is the handover sequence with the highest handover frequency in the same time period among all the base station handover records; based on the first handover sequence, a preset neural network is trained to obtain a target neural network; based on the base station handover data of the target base station in the current period and the target neural network, congestion warning information is generated. This application predicts base station congestion based on a neural network and generates congestion warning information based on the base station handover data of the target base station in the current period. This application can improve the timeliness of congestion prediction. Attached Figure Description

[0036] Figure 1 This is a flowchart of a base station congestion prediction method provided in one embodiment of this application;

[0037] Figure 2 This is a flowchart of a base station congestion prediction method provided in another embodiment of this application;

[0038] Figure 3 This is a schematic diagram of signal transmission between a target base station and surrounding base stations provided in one embodiment of this application;

[0039] Figure 4 This is a schematic diagram of the structure of a base station congestion prediction device provided in one embodiment of this application;

[0040] Figure 5 This is a schematic diagram of the structure of a base station congestion prediction device provided in another embodiment of this application;

[0041] Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of this application;

[0042] Figure 7 This is a schematic diagram of the hardware structure of an electronic device provided in another embodiment of this application. Detailed Implementation

[0043] The following detailed description, in conjunction with the accompanying drawings, illustrates the principles and processes of the base station congestion prediction method, electronic device, apparatus, and storage medium in the embodiments of the present invention.

[0044] First, let me explain the terms that appear in this application:

[0045] LSTM: "Long Short Term Memory Network" is an improved recurrent neural network that selectively memorizes important content through a gating mechanism, which can solve the problem that RNNs cannot handle long-distance dependencies.

[0046] XGBoost model: An ensemble learning algorithm that builds powerful predictive models based on decision trees. It iteratively trains multiple decision tree models and continuously optimizes model performance using gradient boosting techniques.

[0047] The PrefixSpan algorithm is primarily used for sequence pattern mining, and is particularly suitable for discovering frequent subsequences from sequence databases. This algorithm avoids generating a large number of candidate sequences and improves its efficiency by progressively generating prefixes of frequent sequences and continuing to mine frequent sequences in the projected database.

[0048] GSP (Generalized Sequential Pattern) is a sequence pattern mining algorithm based on the Apriori algorithm, primarily used to discover frequent subsequence patterns in time series data. Its core feature is the efficient handling of sequential relationships in sequence data through layer-by-layer search and pruning strategies.

[0049] Spark: Apache Spark is an open-source distributed data processing framework originally developed by the AMPLab at UC Berkeley and became part of the Apache Software Foundation in 2014. Designed for fast, large-scale data processing, Spark supports multiple programming languages, including Scala, Java, Python, and R. Spark's core strengths lie in its speed and ease of use, especially in big data environments.

[0050] Secondly, refer to Figure 1 This application provides a method for predicting base station congestion. Figure 1 In this process, the base station congestion prediction method may include steps S101-S104.

[0051] S101. Obtain the first base station handover record set between the target base station and the first base stations around the target base station; the first base station handover record set includes base station handover records for each time period within several days.

[0052] S102. Based on the first base station handover record set, determine the first handover sequence between the target base station and the first base station; the first handover sequence is the handover sequence with the highest handover frequency in the same time period among all base station handover records.

[0053] S103. Based on the first switching sequence, train the preset neural network to obtain the target neural network.

[0054] S104. Based on the base station handover data of the target base station in the current period and the target neural network, generate congestion warning information.

[0055] Understandably, each base station can be assigned a different name. The first base station handover record set may include, but is not limited to, the handover time of the base station, the location of the target base station, the name of the base station, the order of base station handover, the terminal IMSI, the service type, and the terminal dwell time.

[0056] The first handover sequence may include the name of the previous base station, the name of the current base station, the name of the next base station, the handover time, the terminal dwell time, etc.

[0057] Furthermore, the step of training a preset neural network based on the first switching sequence to obtain a target neural network may include steps S201-S204.

[0058] S201. Extract the statistical characteristics of the number of terminals switching from the first base station to the target base station per hour, the switching ratio change rate of terminals of preset service types, the dwell time distribution of terminal devices at the first base station, and the switching time interval between base stations in the first handover sequence.

[0059] S202. Based on the number of terminals, determine the hourly handover request growth rate of the base station.

[0060] S203. Based on the dwell time distribution, determine the median dwell time of the terminal device at the previous base station.

[0061] S204. Input the switching request growth rate, median dwell time, statistical characteristics, and switching ratio change rate into a preset neural network for training and adjust the network parameters to obtain the target neural network.

[0062] Furthermore, the step of determining the hourly handover request growth rate of the base station based on the number of terminals may include steps S301-S302.

[0063] S301. For any two adjacent time periods, determine the number of handover requests to be increased between the two adjacent time periods based on the number of terminals in the previous time period and the number of terminals in the current time period; wherein the duration of each time period is greater than or equal to one hour.

[0064] S302. Determine the hourly handover request growth rate of the base station based on the increase in the number of handover requests and the duration of each time period.

[0065] Furthermore, based on the base station handover data of the target base station in the current collection period and the target neural network, congestion warning information is determined, specifically including steps S401-S404.

[0066] S401. Extract the first time when traffic enters the target base station, the second time when traffic leaves the target base station, the coordinates of the second base station before the traffic enters the target base station, and the coordinates of the second base station after the traffic leaves the target base station from the base station handover data.

[0067] S402. Based on the first time, the second time, the coordinates of the first base station, and the coordinates of the second base station, determine the target handover sequence of the target base station in the current period.

[0068] S403. Input the target switching sequence into the target neural network to obtain the target probability that the target base station will be congested within 1 hour after the current period.

[0069] S404. Based on the target probability, determine the congestion warning information.

[0070] Furthermore, the step of determining congestion warning information based on the target probability can specifically include steps S501-S502.

[0071] S501. Compare the target probability with the preset probability to obtain the comparison result.

[0072] S502. When the comparison result shows that the target probability is greater than the preset probability, a congestion warning message is generated.

[0073] Furthermore, the step of determining the first handover sequence between the target base station and the first base station based on the first base station handover record set specifically includes steps S601-S602.

[0074] S601. Filter the handover record set of the first base station to obtain the handover record set of the target base station.

[0075] S602. Based on a preset algorithm, determine the first handover sequence from the target base station handover record set.

[0076] The specific calculation principle of this application is explained below with reference to the accompanying drawings:

[0077] In some embodiments, such as Figure 2 As shown, the base station congestion prediction method in this embodiment includes the following specific steps:

[0078] 1. Reference Figure 3The system collects handover record data from the target base station and 5-10 surrounding base stations from the Base Station Controller (BSC) or Mobility Management Entity (MME). Specifically, the time window is the past 30 days, and the data includes fields such as handover time, source base station, target base station, terminal IMSI, and service type.

[0079] 2. Preprocess the collected switching records, including deduplication, outlier handling, and time standardization.

[0080] 3. Use the PrefixSpan algorithm to discover frequent handover sequences. For example, it was found that the handover sequence of base station A → base station B → target base station occurs with a significantly increased frequency during the morning peak hours.

[0081] 4. Extract features from the identified handover patterns, including: the number of terminals that handover to the target base station from each direction per hour, the handover ratio of terminals for specific service types (such as video streaming), the median dwell time of terminals at the previous base station, and the weekly cycle characteristics of handover requests.

[0082] 5. Train the XGBoost model using historical data, with handover features as input and the probability of congestion at the target base station in the next hour as output.

[0083] 6. Monitor current handover traffic in real time, and trigger an alert when a handover pattern similar to that before historical congestion is detected.

[0084] In some embodiments, such as Figure 4 As shown, this embodiment provides a base station congestion prediction device. (Refer to...) Figure 4 The device includes:

[0085] Data acquisition module: Collects handover event data from the network element management system via the northbound interface.

[0086] Data processing module: Uses Spark for distributed data processing, generating feature data once per hour.

[0087] Pattern analysis module: Employs an improved sequence pattern mining algorithm, taking into account time and space constraints.

[0088] Prediction Model Module: This module includes two sub-modules: offline training and online prediction. The model is automatically updated periodically.

[0089] Early warning output module: When the probability of congestion exceeds a preset threshold, a base station congestion warning is sent to terminals accessing the target base station and surrounding base stations, reminding the terminals to avoid congested periods or switch to other base stations for service processing.

[0090] In some embodiments, the handover sequence mode includes the sequence of base stations that the terminal device passes through before reaching the target base station and the time interval therebetween.

[0091] In some embodiments, the spatiotemporal characteristics include at least three of the following: switching direction distribution, switching time distribution, terminal moving speed, and service type ratio.

[0092] In summary, the base station congestion prediction method of this application has the following beneficial effects:

[0093] This application is forward-looking in its predictions. By analyzing the handover sequence patterns of terminal devices, this application can predict potential congestion risks before users actually arrive at the target base station and generate load, thus gaining valuable time for network optimization.

[0094] The prediction accuracy of this application is relatively high. This application comprehensively considers multiple dimensions such as switching direction, time distribution, and business type, making it more accurate than predictions based on a single indicator.

[0095] This application is highly interpretable. The handover sequence pattern identified by this application can intuitively reflect user movement patterns, making it easier for network operations and maintenance personnel to understand the prediction results.

[0096] This application can optimize resources. The prediction results of this application can be used to trigger load balancing measures in advance, such as adjusting antenna parameters, guiding terminals to switch to other base stations, or avoiding congested periods, thereby improving network resource utilization.

[0097] In addition, please refer to Figure 5 This application also provides another base station congestion prediction device that can implement the above-described method. The device includes an acquisition unit 1001, a first processing unit 1002, a second processing unit 1003, and a third processing unit 1004.

[0098] The acquisition unit 1001 can be used to acquire a set of first base station handover records between the target base station and a first base station in the vicinity of the target base station; the set of first base station handover records includes base station handover records for each time period within several days.

[0099] The first processing unit 1002 can be used to determine a first handover sequence between the target base station and the first base station based on the first base station handover record set; the first handover sequence is the handover sequence with the highest handover frequency in the same time period among all base station handover records.

[0100] The second processing unit 1003 can be used to train a preset neural network based on the first switching sequence to obtain a target neural network.

[0101] The third processing unit 1004 can be used to generate congestion warning information based on the base station handover data of the target base station in the current period and the target neural network.

[0102] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0103] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0104] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0105] Please see Figure 6 , Figure 6 The hardware structure of an electronic device according to one embodiment is illustrated. The electronic device includes:

[0106] The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0107] The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 using the methods described in the embodiments of this application.

[0108] The input / output interface 903 is used to implement information input and output;

[0109] The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0110] Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904);

[0111] The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0112] and Figure 1 Corresponding to the method described in this application, another electronic device is also provided, the specific structure of which can be referred to... Figure 7 ,include:

[0113] At least one processor 1011;

[0114] At least one memory 1012 is used to store at least one program;

[0115] When the at least one program is executed by the at least one processor, the at least one processor implements the base station congestion prediction method.

[0116] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0117] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0118] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0119] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0120] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0121] The base station congestion prediction method, apparatus, electronic device, storage medium, and program product provided in this application embodiment acquire a first set of user historical behavior and multi-cloud operation instructions sent by the user; the first set of historical behavior consists of several historical operations in which the user selected a multi-cloud vendor; based on the first set of historical behavior, a set of cloud resources allocated by the multi-cloud management platform is determined; in response to the user's operation of selecting a target cloud resource from the cloud resource set, based on the multi-cloud operation instructions, the service data of the multi-cloud management platform is migrated to the target cloud resource, and the service data is gridded and the data grid of the target cloud resource is adjusted to obtain target grid data. Compared with traditional methods, this application can migrate the service data of the multi-cloud management platform to the target cloud resource according to the multi-cloud operation instructions sent by the user, and perform gridding of the service data and adjustment of the data grid of the target cloud resource to obtain target grid data. This application can improve the stability and accuracy of resource scheduling.

[0122] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0123] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0124] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0125] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0126] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0127] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0129] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0131] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A base station congestion prediction method, characterized in that, Includes the following steps: Obtain the first base station handover record set between the target base station and the first base stations surrounding the target base station; the first base station handover record set includes base station handover records for each time period within several days; Based on the first base station handover record set, a first handover sequence between the target base station and the first base station is determined; the first handover sequence is the handover sequence with the highest handover frequency in the same time period among all the base station handover records, and the handover sequence includes the base station name, handover time and terminal dwell time involved in the base station handover process; Based on the first switching sequence, a preset neural network is trained to obtain a target neural network; Based on the base station handover data of the target base station in the current period and the target neural network, congestion warning information is generated; The step of training a preset neural network based on the first switching sequence to obtain a target neural network specifically includes: Extract the statistical features of the number of terminals switching from the first base station to the target base station per hour, the rate of change of the switching ratio of terminals of preset service types, the dwell time distribution of terminal devices at the first base station, and the switching time interval between base stations in the first switching sequence. Based on the number of terminals, determine the hourly handover request growth rate of the base station; Based on the dwell time distribution, the median dwell time of the terminal device at the previous base station is determined; The switching request growth rate, the median dwell time, the statistical characteristics, and the switching ratio change rate are input into a preset neural network for training and the network parameters are adjusted to obtain the target neural network.

2. The method according to claim 1, characterized in that, The step of determining the hourly handover request growth rate of the base station based on the number of terminals specifically includes: For any two adjacent time periods, the number of handover requests for the base stations in the two adjacent time periods is determined based on the number of terminals in the previous time period and the number of terminals in the current time period; wherein the duration of each time period is greater than or equal to one hour. The hourly handover request growth rate of the base station is determined based on the increase in the number of handover requests and the duration of each time period.

3. The method according to claim 1, characterized in that, The generation of congestion warning information based on the base station handover data of the target base station in the current period and the target neural network specifically includes: Extract the first time when traffic enters the target base station, the second time when traffic leaves the target base station, the coordinates of the second base station preceding the target base station, and the coordinates of the second base station following the target base station from the base station handover data; Based on the first time, the second time, the coordinates of the first base station, and the coordinates of the second base station, the target handover sequence of the target base station in the current period is determined; The target switching sequence is input into the target neural network to obtain the target probability of the target base station becoming congested within 1 hour after the current period. Based on the target probability, congestion warning information is determined.

4. The method according to claim 3, characterized in that, The determination of congestion warning information based on the target probability specifically includes: The target probability is compared with the preset probability to obtain the comparison result; When the comparison result shows that the target probability is greater than the preset probability, a congestion warning message is generated.

5. The method according to claim 4, characterized in that, The step of determining the first handover sequence between the target base station and the first base station based on the first base station handover record set specifically includes: The first base station handover record set is filtered to obtain the target base station handover record set. Based on a preset algorithm, the first handover sequence is determined from the target base station handover record set.

6. A computer-readable storage medium, characterized in that, The device contains a computer program that can be executed by a processor to implement the method of any one of claims 1 to 5.

7. A base station congestion prediction device, characterized in that, include: The acquisition unit is used to acquire a set of first base station handover records between the target base station and the first base stations surrounding the target base station; The first base station handover record set includes base station handover records for each time period within several days; The first processing unit is configured to determine a first handover sequence between the target base station and the first base station based on the first base station handover record set; the first handover sequence is the handover sequence with the highest handover frequency in the same time period among all the base station handover records, and the handover sequence includes the base station name, handover time and terminal dwell time involved in the base station handover process; The second processing unit is used to train a preset neural network based on the first switching sequence to obtain a target neural network; The third processing unit is used to generate congestion warning information based on the base station handover data of the target base station in the current period and the target neural network. The step of training a preset neural network based on the first switching sequence to obtain a target neural network specifically includes: Extract the statistical features of the number of terminals switching from the first base station to the target base station per hour, the rate of change of the switching ratio of terminals of preset service types, the dwell time distribution of terminal devices at the first base station, and the switching time interval between base stations in the first switching sequence. Based on the number of terminals, determine the hourly handover request growth rate of the base station; Based on the dwell time distribution, the median dwell time of the terminal device at the previous base station is determined; The switching request growth rate, the median dwell time, the statistical characteristics, and the switching ratio change rate are input into a preset neural network for training and the network parameters are adjusted to obtain the target neural network.

8. An electronic device, characterized in that... include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor performs the method as described in any one of claims 1-5.

9. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.

Images