Intelligent base station decision-making method and system, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of mobile communication, and relates to an intelligent base station decision-making method, which comprises the following steps: acquiring communication service data and moving track information of a user; inputting the communication service data and the moving track information into a preset behavior prediction model, and outputting a behavior prediction result of the user through the behavior prediction model; selecting a current base station corresponding to the user and each adjacent base station as a to-be-switched base station, and acquiring a slice resource state and signal environment data of the to-be-switched base station; sorting the base stations to be switched according to the behavior prediction result, the slice resource state and the signal environment data, and generating a base station priority sequence; and determining a target base station in the base stations to be switched according to the base station priority sequence, and executing a switching operation corresponding to the target base station. According to the base station switching method and device, the hysteresis caused by base station switching on the base station side is avoided, and the accuracy and intelligence of base station switching are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mobile communication, and in particular to an intelligent base station decision method and system, a computer device and a storage medium. BACKGROUND

[0002] Currently, mobile communication technology is in a rapid development stage, and the process of evolution from 5G to 6G is accelerating, and the intelligent level of the network continues to improve to better cope with increasingly rich application scenarios.

[0003] Currently, the decision of mobile communication network switching mainly depends on the radio resource management (RRM) algorithm on the base station side, and the switching process is triggered based on static indicators such as signal strength and neighbor load. For example, the A3 event triggering mechanism widely used in 4G / 5G networks uses signal strength difference as the switching criterion.

[0004] However, this traditional way of deciding whether to perform base station switching by the base station side through a single indicator not only cannot dynamically adapt to the differentiated needs of user services, but also requires the base station side to obtain terminal measurement reports through signaling interaction, and the decision delay is usually in the order of hundreds of milliseconds, which is strongly lagging and difficult to meet the microsecond-level switching response needs with the development of the times.

[0005] In view of this, the present application is proposed. SUMMARY

[0006] The purpose of the embodiments of the present application is to propose an intelligent base station decision method and system, a computer device and a storage medium to solve the technical problem of strong lag when the base station side performs base station switching.

[0007] In order to solve the above technical problems, the embodiments of the present application provide an intelligent base station decision method, which adopts the following technical solutions: An intelligent base station decision method, comprising the following steps: Obtaining communication service data and mobile trajectory information of a user; Inputting the communication service data and the mobile trajectory information into a preset behavior prediction model, and outputting a behavior prediction result of the user through the behavior prediction model; Selecting a current base station and each neighbor base station corresponding to the user as a to-be-switched base station, and obtaining slice resource status and signal environment data of the to-be-switched base station; According to the behavior prediction result, the slice resource status and the signal environment data, sorting the to-be-switched base station to generate a base station priority sequence; According to the base station priority sequence, determining a target base station in the to-be-switched base station, and performing a switching operation corresponding to the target base station.

[0008] Further, the behavior prediction result includes a predicted service type and a predicted moving track, and the step of ranking the to-be-switched base stations according to the behavior prediction result, the slice resource state and the signal environment data to generate a base station priority sequence specifically includes: mapping the predicted service type according to a preset slice attribute library to obtain a target slice parameter corresponding to the predicted service type; screening the to-be-switched base stations according to the target slice parameter and the slice resource state to obtain candidate base stations; determining a signal priority score corresponding to the candidate base stations according to the signal environment data and the predicted moving track; ranking the candidate base stations according to the signal priority score to generate the base station priority sequence.

[0009] Further, the step of determining a target base station from the to-be-switched base stations according to the base station priority sequence and performing a handover operation corresponding to the target base station specifically includes: determining a candidate base station with the highest signal priority score as the target base station; judging whether the target base station is the current base station; if the target base station is the current base station, maintaining a current communication state; if the target base station is not the current base station, sending a target base station handover request carrying the target slice parameter to the current base station, and establishing a connection channel corresponding to the target base station through the target base station handover request.

[0010] Further, before the step of ranking the to-be-switched base stations according to the behavior prediction result, the slice resource state and the signal environment data to generate a base station priority sequence, the method further includes: obtaining historical service data of the user; analyzing the historical service data to determine slice parameters corresponding to each service type; constructing the slice attribute library according to the slice parameters.

[0011] Further, before the step of inputting the communication service data and the moving track information into a preset behavior prediction model and outputting a behavior prediction result of the user through the behavior prediction model, the method further includes: obtaining initial access information, historical service data and historical track information of the user; performing feature extraction on the initial access information, the historical service data and the historical track information to obtain a feature data set; dividing the feature data set into a training set and a test set; establish an initial model according to a preset deep learning algorithm; train the initial model according to the training set to obtain a trained prediction model; optimize the prediction model according to the test set to obtain the behavior prediction model.

[0012] Further, after the step of determining a target base station from the to-be-switched base stations according to the base station priority sequence and performing a switching operation corresponding to the target base station, the method further comprises: detecting a communication state corresponding to the target base station every preset period; when the communication state appears an abnormal situation, returning to perform the steps of acquiring the communication service data and the movement trajectory information of the user.

[0013] Further, the step of acquiring the communication service data and the movement trajectory information of the user comprises: acquiring a service type, a data transmission rate, a data transmission delay and a data transmission packet loss rate of a service performed in a preset time period as the communication service data; recording position coordinate information of the user in the preset time period through a global positioning system, and generating the movement trajectory information according to the position coordinate information.

[0014] To solve the above technical problems, the embodiments of the present application also provide an intelligent base station decision system, which adopts the technical scheme as follows: An intelligent base station decision system comprises: a first acquisition module configured to acquire communication service data and movement trajectory information of a user; a model prediction module configured to input the communication service data and the movement trajectory information into a preset behavior prediction model, and output a behavior prediction result of the user through the behavior prediction model; a second acquisition module configured to select a current base station corresponding to the user and each neighbor base station as a to-be-switched base station, and acquire slice resource states and signal environment data of the to-be-switched base station; an analysis module configured to sort the to-be-switched base stations according to the behavior prediction result, the slice resource states and the signal environment data, and generate a base station priority sequence; a determination module configured to determine a target base station from the to-be-switched base stations according to the base station priority sequence, and perform a switching operation corresponding to the target base station.

[0015] To solve the above technical problems, the embodiments of the present application also provide a computer device, which adopts the technical scheme as follows: A computer device comprises a memory and a processor, the memory stores computer readable instructions, and the processor implements the steps of the intelligent base station decision method as described above when executing the computer readable instructions.

[0016] To solve the above technical problems, the embodiment of the application further provides a computer readable storage medium, which adopts the technical scheme as described below. A computer readable storage medium stores computer readable instructions, and the computer readable instructions are executed by a processor to implement the steps of the intelligent base station decision method as described above.

[0017] Compared with the prior art, the embodiment of the application has the following beneficial effects: The intelligent base station decision method disclosed in the application obtains the communication service data and the mobile trajectory information of a user, inputs the communication service data and the mobile trajectory information into a preset behavior prediction model, outputs the behavior prediction result of the user through the behavior prediction model, selects the current base station and the adjacent base station corresponding to the user as the to-be-switched base station, obtains the slice resource state and the signal environment data of the to-be-switched base station, sorts the to-be-switched base station according to the behavior prediction result, the slice resource state and the signal environment data, generates a base station priority sequence, determines a target base station in the to-be-switched base station according to the base station priority sequence, and switches the current base station corresponding to the user to the target base station. The application combines the service demand of the user with the slice resource and the signal environment of the base station, selects the relatively optimal base station for switching from the mobile terminal side, realizes efficient intelligent base station decision, avoids the hysteresis caused by base station switching from the base station side, improves the accuracy and intelligence of base station switching, and improves the communication experience of the user. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the schemes in the application, the drawings needed in the description of the embodiments of the application will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is an exemplary system architecture diagram to which the application can be applied; Figure 2 is a flowchart of one embodiment of the intelligent base station decision method according to the application; Figure 3 is a structural schematic diagram of one embodiment of the intelligent base station decision system according to the application; Figure 4 is a structural schematic diagram of one embodiment of the computer device according to the present application. DETAILED DESCRIPTION

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application; the use herein of terms such as "comprise" and "have" and any variations thereof are intended to cover a non-exclusive inclusion; the use herein of terms such as "first", "second" and the like are intended to distinguish between similar objects unless the context indicates otherwise.

[0021] Reference herein to "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase that the phrase in the specification appear in various places means that the specification does not necessarily refer to the same embodiment, or that it is not mutually exclusive or alternative embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] In order to make the technical personnel in the art better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings.

[0023] As shown in Figure 1 The system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a communication link medium between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0024] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0025] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like.

[0026] The server 105 can be a server providing various services, such as a background server providing support for a page displayed on the terminal devices 101, 102, and 103.

[0027] It should be noted that the intelligent base station decision method provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the intelligent base station decision system is generally arranged in a server / terminal device.

[0028] It should be understood that Figure 1 The number of terminal devices, networks, and servers in

[0029] With reference to Figure 2 , a flowchart of one embodiment of the intelligent base station decision method according to the present application is shown. The intelligent base station decision method includes the following steps: Step S201: Obtain communication service data and mobile trajectory information of a user.

[0030] In the present embodiment, the electronic device (e.g., the server / terminal device shown in Figure 1 The server / terminal device can send or receive data through wired connection or wireless connection. It should be noted that the wireless connection can include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other now known or future developed wireless connection.

[0031] The terminal device includes, but is not limited to, a smart phone, a tablet computer, a notebook computer, an electronic book reader, and the like mobile terminal. The communication service data of the user includes real-time service indicators of the mobile terminal, such as an application type, a data transmission rate, a service delay, a packet loss rate, and the like, and signal quality parameters between the mobile terminal and a current base station, such as a signal strength, a signal-to-noise ratio, and an interference condition. The mobile trajectory information of the user includes mobile trajectory update information of the mobile terminal, that is, position information in a period of time.

[0032] In step S202, the communication service data and the mobile trajectory information are input into a preset behavior prediction model, and a behavior prediction result of the user is output by the behavior prediction model.

[0033] The behavior prediction model is a deep learning neural network model constructed by a long short-term memory (LSTM) algorithm. The long short-term memory (LSTM) algorithm is a special recurrent neural network (RNN), which is proposed to solve the problems of gradient disappearance and gradient explosion of the traditional RNN when processing long sequence data.

[0034] Optionally, after obtaining the communication service data and the mobile trajectory information of the user, the communication service data and the mobile trajectory information can be preprocessed and feature extracted to obtain communication service feature data and mobile trajectory feature data, and stored in a specific feature database. The preprocessing operation can remove obviously erroneous or abnormal data points (such as unreasonable data volume mutation, negative transmission delay, and the like) in the communication service data and the mobile trajectory information, and interpolate or fill in missing data to ensure the integrity and consistency of the data. The communication service feature data includes an average data transmission rate of the mobile terminal under different service types, a duration of each service, a periodicity of the service (such as using a video service at a specific time period every day), and the like. The mobile trajectory feature data includes a switching frequency between different base station coverage areas, a resident base station area (such as a user equipment staying in a coverage range of a base station for a longer time), a distribution rule of a moving direction and a speed, and the like.

[0035] In an embodiment, the behavior prediction model is preset and deployed on the mobile terminal of the user, and every certain time (for example, every 5 seconds), the mobile terminal extracts the communication service feature data and the mobile trajectory feature data in the time period from the feature database, and inputs the behavior prediction model, so as to call the behavior prediction model to perform inference calculation, and obtain the behavior prediction result of the user. Specifically, the behavior prediction model includes an encoder and a decoder, wherein the encoder is a "service-mobile" joint feature encoder, and the decoder is a "service-mobile" double task predictor; the behavior prediction result includes a predicted service type and a predicted mobile trajectory, wherein the predicted service type is the future change trend of the service type of the user, and the predicted mobile trajectory is the future change trend of the mobile trajectory of the user; and the loss function of the behavior prediction model is: L = a CrossEntropy + b CrossEntropy + g MSE Wherein, a = 0.5, b = 0.3, g = 0.2, CrossEntropy represents service, CrossEntropy represents direction, and MSE represents speed.

[0036] Step S203, selecting the current base station and each neighbor base station corresponding to the user as the to-be-switched base station, and obtaining the slice resource state and signal environment data of the to-be-switched base station.

[0037] Wherein, the current base station corresponding to the user is the base station currently connected by the mobile terminal for communication, the neighbor is a functional concept, that is, a set of target cells set by the current base station for the terminal to smoothly switch, and the neighbor base station refers to the base station of each target cell in the set.

[0038] In an embodiment, the mobile terminal selects the current base station and each neighbor base station as the to-be-switched base station through the communication connection of the current base station, and obtains the slice resource state and signal environment data of the to-be-switched base station in real time through the terminal side measurement report, wherein the slice resource state of the base station includes the slice type supported by the base station (static attribute, such as whether the base station supports slice A / B / C), the dynamic state of the slice resource (updated every 100 ms), the current available bandwidth and the bandwidth proportion of the target slice, the number of users in the slice and the average delay, and the core network tunnel resource state corresponding to the slice; the signal environment data of the base station includes signal strength (such as RSRP =-75dBm), signal quality (such as RSRQ =-10dB), interference level (such as-85dB), etc.

[0039] Step S204, according to the behavior prediction result, the slice resource state and the signal environment data, sorting the to-be-switched base station to generate a base station priority sequence.

[0040] The ranking of the to-be-switched base stations can be achieved by multi-dimensional scoring, for example, determining slice requirements according to the predicted service type of the user, and preferentially meeting the slice requirements, and then combining signal strength and user movement trend to comprehensively score, and finally generating a base station priority sequence according to the comprehensive score.

[0041] For example, the to-be-switched base stations include: Base0, Base1, Base2, Base3, Base4, and Base5. Base0 is the current base station, and the remaining are the neighboring base stations of Base0. When the predicted service type is high-definition video, the slice resource state of the required base station includes eMBB slice. Among the to-be-switched base stations, the available bandwidth of the eMBB of Base3 is 250Mbps (satisfying the requirement), the signal strength is -70dBm (better than -75dBm of Base1), and the user will enter the coverage area of Base3 after 3 seconds, and the comprehensive score is 88; the score of Base1 is 82; and the score of Base0 is 75. The base station priority sequence can be ranked from high to low according to the comprehensive score, such as [Base3, Base1, Base0, Base2, Base4, Base5].

[0042] In step S205, a target base station is determined from the to-be-switched base stations according to the base station priority sequence, and a handover operation corresponding to the target base station is performed.

[0043] The target base station is the base station ranked first in the base station priority sequence. If the target base station is the current base station (Base0), the current communication state is maintained. If the target base station is a new base station (such as Base3), the mobile terminal sends a handover request (including the identifier of Base3 and the slice requirement) to Base0. After Base0 and Base3 negotiate resources through the Xn interface, the mobile terminal establishes a new communication connection with Base3 and releases the link with Base0. The handover time is ≤20ms, which ensures that the video playback is not stuck.

[0044] The application combines the service requirement of the user with the slice resource and signal environment of the base station, selects the relatively optimal base station for handover from the mobile terminal side, realizes efficient intelligent base station decision, avoids the hysteresis caused by base station handover from the base station side, improves the accuracy and intelligence of base station handover, and improves the communication experience of the user.

[0045] In some optional implementations of the embodiment, the behavior prediction result includes a predicted service type and a predicted movement trajectory, and the step of ranking the to-be-switched base stations according to the behavior prediction result, the slice resource state, and the signal environment data to generate a base station priority sequence includes: mapping the predicted service type according to a preset slice attribute library to obtain a target slice parameter corresponding to the predicted service type; screening the base stations to be switched according to the target slice parameter and the slice resource state to obtain candidate base stations; determining a signal priority score corresponding to the candidate base stations according to the signal environment data and the predicted moving trajectory; sorting the candidate base stations according to the signal priority score to generate the base station priority sequence.

[0046] The mapping relationship between the service type and the slice parameter is pre-stored in the preset slice attribute library, as shown in Table 1 below. The slice parameter includes a slice type, a bandwidth requirement, and a latency requirement. According to the slice attribute library, the predicted service type is mapped to obtain the target slice parameter.

[0047] For example, when the predicted service type is “high-definition video”, the mapped slice type, bandwidth requirement, and latency requirement are “eMBB, ≥20Mbps, and ≤50ms”, respectively. When the predicted service type is “real-time game”, the mapped slice type, bandwidth requirement, and latency requirement are “URLLC, ≥10Mbps, and ≤20ms”, respectively. Then, the candidate base stations are screened according to the target slice parameter and the slice resource state. The slice resource state of the candidate base stations needs to support the target slice parameter. For example, Base5 that does not support eMBB and Base4 that has an eMBB bandwidth of only 15Mbps are excluded, and Base0, Base1, and Base3 are retained. Then, the signal priority score of the candidate base stations is determined according to the signal environment data and the predicted moving trajectory. The scoring formula can be Score = signal strength (40%) + predicted coverage duration (30%) + interference level (30%). For example, the signal strength of Base3 is -70dBm (90 points), the predicted coverage duration is 10 minutes (100 points), and the interference level is -90dB (100 points). Therefore, the signal priority score of Base3 is 96 points. The signal priority score of Base1 is 85 points, and the signal priority score of Base0 is 78 points. Finally, the base station priority sequence is generated according to the signal priority score, and the candidate base stations are sorted according to the score: [Base3 (96 points), Base1 (85 points), Base0 (78 points)].

[0048] The application combines the service demand of the user with the slice resource and the signal environment of the base station, comprehensively analyzes from the mobile terminal side, determines the base station priority sequence, and selects the relatively optimal base station for subsequent base station switching, thereby improving the accuracy and intelligence of the base station switching and improving the communication experience of the user.

[0049] In some optional implementations of the embodiment, the step of determining a target base station from the base stations to be switched according to the base station priority sequence and performing a handover operation corresponding to the target base station comprises: determining the candidate base station with the highest signal priority score as the target base station; judging whether the target base station is the current base station; if the target base station is the current base station, maintaining the current communication state; if the target base station is not the current base station, sending a target base station handover request carrying the target slice parameter to the current base station, and establishing a connection channel corresponding to the target base station through the target base station handover request.

[0050] The target base station is the candidate base station with the highest signal priority score (e.g. Base3), and the ID of the target base station is compared with the ID of the current base station. If they are different (Base3≠Base0), a base station handover process is performed.

[0051] In an embodiment, the target base station handover request includes the target slice parameter and the ID of the target base station. After the current base station Base0 and the target base station Base3 complete resource reservation through an Xn interface, the mobile terminal synchronizes with Base3 through a random access channel (RACH), establishes a physical layer connection, and releases the Base0 resource after the handover is completed.

[0052] The application combines the service demand of the user with the slice resource and signal environment of the base station, and realizes efficient intelligent base station decision-making from the mobile terminal side, thereby avoiding the hysteresis caused by base station handover from the base station side, improving the accuracy and intelligence of base station handover, and improving the communication experience of the user.

[0053] In some optional implementations of the embodiment, before the step of sorting the base stations to be switched according to the behavior prediction result, the slice resource state and the signal environment data, and generating a base station priority sequence, the method further comprises: obtaining historical service data of the user; analyzing the historical service data to determine slice parameters corresponding to each service type; constructing the slice attribute library according to the slice parameters.

[0054] The historical service data includes historical service records of the user, for example, service records of the user in the last 30 days, including: "watching high-definition video from 19:00 to 21:00 every day, with an average bandwidth of 18 Mbps", "playing games from 15:00 to 17:00 every Saturday, with an average latency of 15 ms", and the like.

[0055] In an embodiment, the slice parameters corresponding to each service type are determined by analyzing the historical service data, for example, it is determined that "high-definition video requires eMBB slice (bandwidth > 18 Mbps)", "game requires URLLC slice (latency < 15 ms)". Then, the analysis result is stored in the local database, and a mapping table between the predicted service type and the slice parameter is formed as shown in Table 1, and a slice attribute library is constructed.

[0056] The slice attribute library containing the mapping relationship between the slice parameter and the service type is constructed by the historical service data of the user, so that the mobile terminal side can select a relatively optimal base station for switching by using the slice attribute library subsequently, the accuracy and intelligence of base station switching are improved, and the communication experience of the user is improved.

[0057] In some optional implementation manners of the embodiment, before the step of inputting the communication service data and the mobile trajectory information into the preset behavior prediction model and outputting the behavior prediction result of the user by the behavior prediction model, the method further includes: obtaining initial access information, historical service data and historical trajectory information of the user; performing feature extraction on the initial access information, the historical service data and the historical trajectory information to obtain a feature data set; dividing the feature data set into a training set and a test set; establishing an initial model according to a preset deep learning algorithm; training the initial model according to the training set to obtain a trained prediction model; optimizing the prediction model according to the test set to obtain the behavior prediction model.

[0058] The initial access information includes a mobile terminal model, an operator, and the like, the historical service data includes historical service records of the user, and the historical trajectory information includes a GPS coordinate time sequence of the user in a preset time. The preset deep learning algorithm includes an LSTM (long short-term memory) algorithm.

[0059] In an embodiment, feature extraction is performed on the above data, i.e., service type proportion, average moving speed, peak period service preference, etc. are obtained to form a feature vector. Then, the feature vector is divided into a training set (80%) and a test set (20%) according to a ratio of 8:2. An initial model is established. Then, an initial model is established using LSTM, the input layer dimension is set to 32 (the number of features), the hidden layer is set to 2 layers (64 neurons per layer), and the output layer predicts the service type and the moving track. The initial model is trained according to the training set to obtain a trained prediction model. The prediction model is optimized according to the test set, and a behavior prediction model is obtained.

[0060] Optionally, the training and optimization process can be as follows: using the Adam optimizer (learning rate 0.001) to train for 50 rounds, verifying through the test set, adjusting the model parameters until the prediction accuracy is greater than or equal to 90%, and finally deploying on the mobile terminal.

[0061] The application constructs a behavior prediction model that can predict the service type and moving track of a user through a preset deep learning algorithm, and outputs the behavior prediction result of the user using the model, so that the mobile terminal determines the relatively optimal base station according to the behavior prediction result, and finally realizes efficient intelligent base station decision-making, avoiding the hysteresis caused by base station switching from the base station side, and improving the accuracy and intelligence of base station switching.

[0062] In some optional implementations of the embodiment, after the step of determining a target base station from the to-be-switched base stations according to the base station priority sequence and performing a switching operation corresponding to the target base station, the method further includes: detecting a communication state corresponding to the target base station every preset period; when the communication state appears an abnormal situation, returning to perform the steps of obtaining the communication service data and the moving track information of the user.

[0063] For example, the preset period is 500 ms, so the communication state of the target base station is detected every 500 ms after switching to the target base station. Under normal circumstances, the indicators can include signal strength ≥-100 dBm, video delay ≤50 ms, and packet loss rate ≤1%. If "signal strength < -105 dBm" or "delay > 80 ms" or "packet loss rate > 1%" is detected for three consecutive times, it is determined that the communication state appears an abnormal situation. At this time, the steps of obtaining the communication service data and the moving track information of the user are returned to perform, and the base station switching process is re-entered.

[0064] The application periodically detects the communication state of the base station after switching to ensure the stability of intelligent base station decision-making, improve the robustness of intelligent base station decision-making, and improve the communication experience of the user.

[0065] In some optional implementations of the embodiment, the step of obtaining the communication service data and the mobile trajectory information of the user comprises: collecting the service type, the data transmission rate, the data transmission delay and the data transmission packet loss rate of the service performed in the preset time period as the communication service data; recording the position coordinate information of the user in the preset time period through a global positioning system, and generating the mobile trajectory information according to the position coordinate information.

[0066] For example, in the process of collecting the communication service data, the preset time period can be set to 10s, the mobile terminal obtains the service type corresponding to the current application through the API interface, and calculates the data transmission rate (such as 200MB transmitted in 10s, representing 160Mbps), the data transmission delay (the average TCP RTT is 30ms) and the data transmission packet loss rate (such as 5 out of 1000 data packets are lost, representing 0.5%). In the process of obtaining the mobile trajectory information, the coordinates can be recorded once per second through GPS (such as (116.3°E, 39.9°N)), and the GPS coordinate time sequence in 10s is generated, the moving speed (such as 50m / 10s=5m / s) and the direction (such as northeast) are calculated.

[0067] The application obtains the communication service data and the mobile trajectory information of the user, predicts the behavior prediction result of the user, and uses the result as the data basis for subsequent selection of the base station, thereby realizing efficient intelligent base station decision, avoiding the hysteresis caused by base station switching on the base station side, and improving the accuracy and intelligence of base station switching.

[0068] The embodiment of the application can obtain and process related data based on artificial intelligence technology. The artificial intelligence (AI) is the use of digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.

[0069] The basic technology of artificial intelligence generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0070] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing relevant hardware through computer readable instructions, and the computer readable instructions can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiment methods. Among them, the storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0071] It should be understood that although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or other steps. Sub-steps or stages.

[0072] Further referring to Figure 3 , as an implementation of the method shown in Figure 2 , the present application provides an embodiment of an intelligent base station decision system, which corresponds to the method embodiment shown in Figure 2 , and the system can be applied to various electronic devices.

[0073] As shown in Figure 3 , the intelligent base station decision system 300 described in the embodiment includes a first acquisition module 301, a model prediction module 302, a second acquisition module 303, an analysis module 304, and a determination module 305. Among them: The first acquisition module 301 is configured to acquire communication service data and mobile trajectory information of a user. The model prediction module 302 is configured to input the communication service data and the mobile trajectory information into a preset behavior prediction model, and output a behavior prediction result of the user through the behavior prediction model. The second acquisition module 303 is configured to select a current base station and each neighbor base station corresponding to the user as a to-be-switched base station, and acquire slice resource status and signal environment data of the to-be-switched base station. The analysis module 304 is configured to sort the to-be-switched base station according to the behavior prediction result, the slice resource status, and the signal environment data, and generate a base station priority sequence. The determining module 305 is configured to determine a target base station from the base stations to be switched according to the base station priority sequence, and perform a handover operation corresponding to the target base station.

[0074] The intelligent base station decision system provided in the application selects a relatively optimal base station for handover from the mobile terminal side by combining the service demand of a user with the slice resource and signal environment of a base station, realizes efficient intelligent base station decision, thereby avoiding the hysteresis caused by base station handover from the base station side, and improves the accuracy and intelligence of base station handover and the communication experience of the user.

[0075] In some optional implementations of the embodiment, the behavior prediction result includes a predicted service type and a predicted moving track, and the analyzing module 304 is further configured to: map the predicted service type according to a preset slice attribute library to obtain a target slice parameter corresponding to the predicted service type; filter the base stations to be switched according to the target slice parameter and the slice resource state to obtain candidate base stations; determine a signal priority score corresponding to the candidate base stations according to the signal environment data and the predicted moving track; sort the candidate base stations according to the signal priority score to generate the base station priority sequence.

[0076] The intelligent base station decision system provided in the application determines a base station priority sequence by comprehensively analyzing the service demand of a user and the slice resource and signal environment of a base station from the mobile terminal side, thereby selecting a relatively optimal base station for subsequent base station handover, improving the accuracy and intelligence of base station handover, and improving the communication experience of the user.

[0077] In some optional implementations of the embodiment, the determining module 305 is further configured to: determine a candidate base station with the highest signal priority score as the target base station; determine whether the target base station is the current base station; if the target base station is the current base station, maintain the current communication state; if the target base station is not the current base station, send a target base station handover request carrying the target slice parameter to the current base station, and establish a connection channel corresponding to the target base station through the target base station handover request.

[0078] The intelligent base station decision system provided in the application can realize efficient intelligent base station decision by the mobile terminal side by combining the service demand of the user with the slice resource and signal environment of the base station, thereby avoiding the hysteresis caused by base station switching from the base station side and improving the accuracy and intelligence of base station switching and the communication experience of the user.

[0079] In some optional implementation manners of the embodiment, the intelligent base station decision system 300 is further used for: obtaining historical service data of the user; analyzing the historical service data to determine slice parameters corresponding to each service type; constructing the slice attribute library according to the slice parameters.

[0080] The intelligent base station decision system provided in the application can construct a slice attribute library containing the mapping relationship between slice parameters and service types by the historical service data of the user, so that the relatively optimal base station for switching can be selected by the mobile terminal side using the slice attribute library subsequently, the accuracy and intelligence of base station switching are improved, and the communication experience of the user is improved.

[0081] In some optional implementation manners of the embodiment, the intelligent base station decision system 300 is further used for: obtaining initial access information, historical service data and historical trajectory information of the user; performing feature extraction on the initial access information, the historical service data and the historical trajectory information to obtain a feature data set; dividing the feature data set into a training set and a test set; establishing an initial model according to a preset deep learning algorithm; training the initial model according to the training set to obtain a trained prediction model; optimizing the prediction model according to the test set to obtain the behavior prediction model.

[0082] The intelligent base station decision system provided in the application can construct a behavior prediction model that can predict the service type and moving trajectory of the user by a preset deep learning algorithm, and output the behavior prediction result of the user by using the model, so that the mobile terminal can determine the relatively optimal base station according to the behavior prediction result, and finally realize efficient intelligent base station decision, avoid the hysteresis caused by base station switching from the base station side, and improve the accuracy and intelligence of base station switching.

[0083] In some optional implementation manners of the embodiment, the intelligent base station decision system 300 is further used for: detecting the communication state corresponding to the target base station every preset period; When an abnormal situation occurs in the communication status, return to the step of obtaining the user's communication service data and movement trajectory information.

[0084] The intelligent base station decision-making system provided in this application ensures the stability of intelligent base station decision-making, improves the robustness of intelligent base station decision-making, and enhances the user's communication experience by periodically detecting anomalies in the communication status of the base station after handover.

[0085] In some optional implementations of this embodiment, the first acquisition module 301 is further configured to: Collect the service type, data transmission rate, data transmission latency, and data transmission packet loss rate of the services performed within a preset time period, and use them as the communication service data; The location coordinates of the user are recorded using the Global Positioning System (GPS) within the preset time period, and the movement trajectory information is generated based on the location coordinates.

[0086] The intelligent base station decision-making system provided in this application obtains user communication service data and mobile trajectory information to predict user behavior prediction results, which serve as the data basis for subsequent base station selection. This achieves efficient intelligent base station decision-making, avoids the lag caused by base station handover from the base station side, and improves the accuracy and intelligence of base station handover.

[0087] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0088] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0089] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The computer device can interact with a user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device, or the like.

[0090] The memory 41 includes at least one type of readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, or the like), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, or the like. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, or the like. Of course, the memory 41 can also include both an internal storage unit and an external storage device of the computer device 4. In this embodiment, the memory 41 is generally used to store an operating system and various application software installed in the computer device 4, such as computer readable instructions of the intelligent base station decision method, or the like. In addition, the memory 41 can also be used to temporarily store various data that has been output or will be output.

[0091] The processor 42 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer readable instructions or process data stored in the memory 41, such as computer readable instructions of the intelligent base station decision method.

[0092] The network interface 43 can include a wireless network interface or a wired network interface, and is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0093] The computer device provided in the application selects a relatively optimal base station for switching from the mobile terminal side by combining the service requirement of the user with the slice resource and signal environment of the base station, realizes efficient intelligent base station decision, thereby avoiding the hysteresis caused by base station switching from the base station side, and improves the accuracy and intelligence of base station switching and the communication experience of the user.

[0094] The application further provides another implementation, namely providing a computer readable storage medium, the computer readable storage medium stores computer readable instructions, the computer readable instructions can be executed by at least one processor, so that the at least one processor executes the steps of the intelligent base station decision method as described above.

[0095] The computer readable storage medium provided in the application selects a relatively optimal base station for switching from the mobile terminal side by combining the service requirement of the user with the slice resource and signal environment of the base station, realizes efficient intelligent base station decision, thereby avoiding the hysteresis caused by base station switching from the base station side, and improves the accuracy and intelligence of base station switching and the communication experience of the user.

[0096] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better implementation. Based on such understanding, the technical solutions of the application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions for making a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the method described in each embodiment of the application.

[0097] Obviously, the above-described embodiments are only some of the embodiments of the application, not all the embodiments, and the preferred embodiments of the application are given in the drawings, but do not limit the patent scope of the application. The application can be realized in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the application more thorough and comprehensive. Although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art can modify the technical solutions recorded in the foregoing specific embodiments, or make equivalent replacements to some technical features. Any equivalent structure made by using the contents of the specification and drawings, directly or indirectly applied to other related technical fields, is also within the patent protection scope of the application.

Claims

1. A smart base station decision-making method, characterized in that, Includes the following steps: To obtain users' communication service data and movement trajectory information; The communication service data and the movement trajectory information are input into a preset behavior prediction model, and the behavior prediction model outputs the user's behavior prediction result. Select the current base station corresponding to the user and each neighboring cell base station as the base station to be switched, and obtain the slice resource status and signal environment data of the base station to be switched; Based on the behavior prediction results, the slice resource status, and the signal environment data, the base stations to be switched are sorted to generate a base station priority sequence; Based on the base station priority sequence, a target base station is determined among the base stations to be switched, and a switching operation corresponding to the target base station is performed.

2. The intelligent base station decision-making method according to claim 1, characterized in that, The behavior prediction result includes predicted service type and predicted movement trajectory. The step of sorting the base stations to be handed over based on the behavior prediction result, the slice resource status, and the signal environment data to generate a base station priority sequence specifically includes: The predicted service type is mapped according to a preset slice attribute library to obtain the target slice parameters corresponding to the predicted service type; The base stations to be switched are filtered according to the target slice parameters and the slice resource status to obtain candidate base stations; Based on the signal environment data and the predicted movement trajectory, the signal priority score corresponding to the candidate base station is determined; Based on the signal priority score, the candidate base stations are sorted to generate the base station priority sequence.

3. The intelligent base station decision-making method according to claim 2, characterized in that, The step of determining the target base station among the base stations to be handed over according to the base station priority sequence and performing the handover operation corresponding to the target base station specifically includes: The candidate base station with the highest signal priority score is determined as the target base station; Determine whether the target base station is the current base station; If the target base station is the current base station, then the current communication state is maintained; If the target base station is not the current base station, a target base station handover request carrying the target slice parameters is sent to the current base station, and a connection channel corresponding to the target base station is established through the target base station handover request.

4. The intelligent base station decision-making method according to claim 2, characterized in that, Before the step of sorting the base stations to be handed over based on the behavior prediction results, the slice resource status, and the signal environment data to generate a base station priority sequence, the method further includes: Obtain the user's historical business data; The historical business data is parsed to determine the slice parameters corresponding to each business type; Based on the slice parameters, construct the slice attribute library.

5. The intelligent base station decision-making method according to claim 1, characterized in that, Before the step of inputting the communication service data and the movement trajectory information into a preset behavior prediction model, and outputting the user's behavior prediction result through the behavior prediction model, the method further includes: Obtain the user's initial access information, historical business data, and historical trajectory information; Feature extraction is performed on the initial access information, the historical service data, and the historical trajectory information to obtain a feature dataset; The feature dataset is divided into a training set and a test set; An initial model is built based on a pre-defined deep learning algorithm; The initial model is trained based on the training set to obtain a trained prediction model; The prediction model is optimized based on the test set to obtain the behavior prediction model.

6. The intelligent base station decision-making method according to claim 1, characterized in that, After the step of determining the target base station among the base stations to be handed over according to the base station priority sequence and performing the handover operation corresponding to the target base station, the method further includes: The communication status corresponding to the target base station is detected at preset intervals; When an abnormal situation occurs in the communication status, return to the step of obtaining the user's communication service data and movement trajectory information.

7. The intelligent base station decision-making method according to any one of claims 1 to 6, characterized in that, The steps for obtaining the user's communication service data and movement trajectory information include: Collect the service type, data transmission rate, data transmission latency, and data transmission packet loss rate of the services performed within a preset time period, and use these as the communication service data. The location coordinates of the user are recorded using the Global Positioning System (GPS) within the preset time period, and the movement trajectory information is generated based on the location coordinates.

8. A smart base station decision-making system, characterized in that, include: The first acquisition module is used to acquire the user's communication service data and movement trajectory information; The model prediction module is used to input the communication service data and the movement trajectory information into a preset behavior prediction model, and output the user's behavior prediction result through the behavior prediction model; The second acquisition module is used to select the current base station corresponding to the user and each neighboring cell base station as the base station to be switched, and to acquire the slice resource status and signal environment data of the base station to be switched. The analysis module is used to sort the base stations to be switched based on the behavior prediction results, the slice resource status and the signal environment data, and generate a base station priority sequence. The determination module is used to determine the target base station among the base stations to be switched based on the base station priority sequence, and to perform the switching operation corresponding to the target base station.

9. A computer device, characterized in that, The system includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the smart base station decision method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the smart base station decision method as described in any one of claims 1 to 7.

Images