Network optimization method, device, electronic device, and storage medium

Abstract

The embodiments of the present application provide a network optimization method, device, electronic device, and storage medium, which includes: sending a data analysis request message to a core network, receiving data analysis response information fed back from the core network, and determining a model processing result by an artificial intelligence learning model, and performing a network optimization operation according to the model processing result.

Description

[Technical Field]

[0001] This application is filed based on and claims priority from a Chinese patent application bearing application number 202110963030.2 and filing date August 20, 2021, the entire contents of which are hereby incorporated by reference into this application.

[0002] The present application relates to the technical field of wireless communication, and in particular to a network optimization method, device, electronic device, and storage medium. [Background technology]

[0003] With the development of wireless communication network technology, fifth-generation wireless communication networks have been adopted, and future developments beyond fifth-generation wireless communication networks are expected. Artificial intelligence (AI) technology, particularly machine learning (ML), can propose effective network optimization methods through the large amounts of data in fifth-generation wireless communication networks and beyond. Currently, core networks have Network Data Analytics Function (NWDAF) units that can provide data classification services, such as statistical information on historical network activity and forecast information on future network activity. Data analysis and forecasting functions can bring fundamental changes to communications, but they also significantly increase operational complexity. This requires carriers to optimize network deployment and operation and maintenance, improving network performance and user experience. Summary of the Invention [Problem to be solved by the invention]

[0004] The main purpose of the embodiments of the present application is to propose a network optimization method, device, electronic device, and storage medium that realizes optimization of the core network and the base station side network and improves the communication quality of the network by having the base station and the core network exchange data analysis information and perform statistics and predictions based on the data analysis information. [Means for solving the problem]

[0005] An embodiment of the present application provides a network optimization method, including: sending a data analysis request message to a core network; receiving data analysis response information fed back from the core network, and determining a model processing result through an artificial intelligence learning model; and performing a network optimization operation according to the model processing result.

[0006] An embodiment of the present application also provides a network optimization method, which includes: sending a data information request to a base station; receiving a data information response fed back from the base station; and determining a model processing result through an artificial intelligence learning model; and performing a network optimization operation according to the model processing result.

[0007] An embodiment of the present application also provides a network optimization device, including: a data analysis sending module for sending a data analysis request message to a core network; a data processing module for receiving data analysis response information fed back from the core network and determining a model processing result through an artificial intelligence learning model; and a network optimization module for performing a network optimization operation according to the model processing result.

[0008] An embodiment of the present application also provides a network optimization device, including: a data sending module for sending a data information request to a base station; a result determining module for receiving a data information response fed back from the base station and determining a model processing result through an artificial intelligence learning model; and an optimization executing module for performing a network optimization operation according to the model processing result.

[0009] An embodiment of the present application also provides an electronic device, the electronic device including one or more processors and a memory storing one or more programs, the one or more programs being executed by the one or more processors to cause the one or more processors to implement the network optimization method described in any of the embodiments of the present application.

[0010] An embodiment of the present application also provides a computer-readable storage medium storing one or more programs that, when executed by one or more processors, implement the network optimization method described in any of the embodiments of the present application. [Effects of the Invention]

[0011] In an embodiment of the present application, a data analysis request message is sent to a core network, data response information is fed back from the core network, an artificial intelligence model is used to determine a model processing result, and a corresponding network optimization operation is performed according to the model processing result. By exchanging data information with the core network and using an artificial intelligence model to determine a model processing result corresponding to the data information, data statistics and / or predictions can be realized, which can improve the accuracy of network optimization and enhance network performance and user experience. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a flowchart of a network optimization method according to an embodiment of the present application; [Figure 2]4 is a flowchart of another network optimization method according to an embodiment of the present application; [Figure 3] FIG. 1 illustrates an example of a network optimization method according to an embodiment of the present application. [Figure 4] 1 is a flowchart of a network optimization method according to an embodiment of the present application; [Figure 5] FIG. 1 illustrates an example of another network optimization method according to an embodiment of the present application. [Figure 6] FIG. 1 illustrates an example of a network optimization method according to an embodiment of the present application. [Figure 7] 1 is a structural schematic diagram of a network optimization device according to an embodiment of the present application; [Figure 8] FIG. 2 is a structural schematic diagram of another network optimization device according to an embodiment of the present application; [Figure 9] 1 is a structural schematic diagram of an electronic device according to an embodiment of the present application; DETAILED DESCRIPTION OF THE INVENTION

[0013] It should be noted that the specific examples described in this specification are merely used to interpret the present application, and are not used to limit the present application.

[0014] In the following description, the suffixes used to denote elements such as "module", "component", or "unit" are used only to facilitate the description of the present application and do not have any inherent meaning in themselves, so that "module", "component", or "unit" may be used interchangeably.

[0015] 1 is a flowchart of a network optimization method according to an embodiment of the present application. The embodiment of the present application can be applied to network intelligent optimization in a wireless communication network. The method can be performed by a network optimization device according to an embodiment of the present application, which can be implemented in the form of software and / or hardware, and can generally be integrated into a base station side node. Referring to FIG. 1, the method according to the embodiment of the present application specifically includes the following steps 110 to 130.

[0016] Step 110: Send a data analysis request message to the core network.

[0017] Here, the data analysis request message may be information for controlling data exchange between the core network and the base station side, and may include instruction information for a data analysis method, instruction information for data analysis content, etc. The data analysis request message may be transmitted to the core network by the base station side node.

[0018] Specifically, the base station side node may transmit a data analysis request message to the core network, which may include one or more pieces of instruction information that may indicate a data analysis method, data involved in the analysis, etc.

[0019] Step 120: Receive the data analysis response information fed back from the core network, and determine the model processing result through the artificial intelligence learning model.

[0020] Here, the data analysis response information may be information generated by the core network according to the received data analysis request message. The data analysis response information may include data that the core network side needs to exchange with the base station side. The data analysis response information may correspond to the data analysis request message. For example, if the data analysis request message includes data prediction instruction information, the data analysis response information may feed back data related to data prediction. The artificial intelligence learning model may be a pre-trained neural network model that can process input information and can be used for processing such as data statistics and data prediction. The model processing result may be the output result of the artificial intelligence learning model and may include data prediction results, data statistics results, etc.

[0021] In an embodiment of the present application, upon receiving the data analysis request message, the core network generates corresponding data analysis response information and feeds it back to the base station, and the base station processes the data analysis response information using an artificial intelligence learning model to generate a model processing result. Depending on the artificial intelligence learning model, the generated model processing result may be prediction information based on the data analysis response information or statistical information based on the data analysis response information.

[0022] Step 130: Perform network optimization operations according to the model processing results.

[0023] Here, the network optimization operation may be an operation for optimizing a wireless communication network, such as adjusting a cell load, adjusting the number of terminals in a cell, or adjusting a resource utilization rate of a cell.

[0024] In the embodiments of the present application, one or more different network optimization policies may be preset, a corresponding network optimization policy may be found according to the model processing result, and a corresponding network optimization operation may be performed according to the determined network optimization policy, or a network optimization policy may be generated in real time according to the model processing result.

[0025] In an embodiment of the present application, a data analysis request message is sent to a core network, data response information is fed back from the core network, an artificial intelligence model is used to determine a model processing result, and a corresponding network optimization operation is performed according to the model processing result. By exchanging data information with the core network and using an artificial intelligence model to determine a model processing result corresponding to the data information, data statistics and / or predictions can be realized, which can improve the accuracy of network optimization and enhance network performance and user experience.

[0026] Furthermore, based on the embodiment of the above application, the data analysis response information is determined when the core network performs at least one of the following processes: data collection, data statistical analysis, and data prediction according to the data analysis request message.

[0027] In an embodiment of the present application, the data analysis response information may be generated by a core network. The data analysis response information may be information generated by performing at least one of data collection, data statistical analysis, and data prediction according to the data analysis request message. An artificial intelligence learning model may be pre-configured in the core network. The artificial intelligence learning model may process the data analysis request message, and the processing result may be provided as a data analysis response message.

[0028] 2 is a flowchart of another network optimization method according to an embodiment of the present application, which is embodied based on the embodiment of the above application. Referring to FIG. 2, the method according to the embodiment of the present application specifically includes the following steps 210 to 250.

[0029] Step 210: Send a data analysis request message to the core network.

[0030] Step 220: Receive the data analysis response information fed back from the core network, and determine the model processing result through the artificial intelligence learning model.

[0031] Step 230: Perform network optimization operations according to the model processing results.

[0032] Step 240: Perform network optimization operations according to the data analysis response information.

[0033] In the embodiment of the present application, the base station side can also directly perform network optimization operations according to the data analysis response information. For example, if the data analysis response information is prediction information, the base station side can directly perform network optimization operations based on the prediction information, thereby improving network performance.

[0034] Step 250: Train or update an artificial intelligence learning model according to the data analysis response information.

[0035] Specifically, the AI learning model may be trained according to the received data analysis response information. The data analysis response information may be information transmitted from the core network during the historical process. The AI learning model may be continuously trained or updated according to the data analysis response information, thereby improving the accuracy of the model processing results. Note that the AI learning model may be updated or trained each time data analysis response information is received, or when the amount of data in the received data analysis response information is greater than a data amount threshold.

[0036] In the embodiment of the present application, a data analysis request message is sent to a core network, data response information is received from the core network, an artificial intelligence model is used to determine a model processing result, a corresponding network optimization operation is performed according to the model processing result, a network optimization operation is performed according to the data response information, and an artificial intelligence learning model is trained or updated according to the received data response information, thereby further improving the accuracy of network optimization and improving network performance and user experience.

[0037] Furthermore, based on the embodiment of the above application, the data analysis request message includes at least one of at least one data analysis type identifier, at least one data analysis format identifier, at least one terminal identifier, data analysis time information, data analysis area of interest, and expected terminal trajectory information granularity.

[0038] Here, the data analysis type identifier may indicate the type of data analysis requested and may take different values to identify different data types. The data analysis format identifier may indicate the format of data analysis and may take different values to identify different data analysis formats, which may include data statistics, data predictions, etc. The terminal identifier may identify different terminals. The data analysis time information may indicate a period during which data analysis is performed and may include a start time and an end time of the period. The data analysis interest area may represent an interest area for data analysis, such as a tracking area and a cell list. The expected terminal trajectory information granularity may represent the minimum analysis granularity of terminal trajectories for data analysis.

[0039] In an embodiment of the present application, the data analysis request message may include one or more of a data analysis type identifier, a data analysis format identifier, a terminal identifier, data analysis time information, a data analysis interest area, and an expected terminal trajectory information granularity. The number of pieces of information included in the data analysis request message is not unique and may be one or more. For example, the data analysis request message may include multiple data analysis type identifiers and multiple data analysis format identifiers.

[0040] Furthermore, based on the embodiment of the above application, the data analysis type identifier includes at least one of a terminal data type identifier, a network load data type identifier, a quality of experience data type identifier, a network slice data type identifier, and a general data type identifier.

[0041] Specifically, the data analysis type identifier may include a terminal data type identifier, a network load data type identifier, a quality of experience (QoE) data type identifier, a network slice data type identifier, a general data type identifier, etc. Each identifier has a different value, and can identify terminal data, network load data, quality of experience (QoE) data, network slice data, general data, etc.

[0042] Furthermore, based on an embodiment of the above application, the data analysis type identifier includes at least one of a data statistics identifier and a data prediction identifier.

[0043] Specifically, the data analysis format identifier may include a data statistics identifier and a data prediction identifier. The data statistics identifier allows the base station side to identify data that requires data statistics by the core network side. The data prediction identifier allows the base station side to identify data that requires data prediction by the core network side.

[0044] Furthermore, based on the embodiment of the above application, the data analysis time information includes at least one of a time granularity, a data analysis start time, and a data analysis end time.

[0045] In the present embodiment, the data analysis time information may be composed of information such as time granularity, data analysis start time, and data analysis end time, and may indicate the period during which the data analysis is performed. Among these, the time granularity may represent the length of the period during which the data analysis is performed.

[0046] Furthermore, based on the embodiment of the above application, the data analysis interest area includes at least one of a tracking area, a cell list, and a paging area.

[0047] In the embodiment of the present application, the data analysis interest area may specifically be a tracking area, a cell list, a paging area, etc.

[0048] Furthermore, based on the embodiment of the above application, the expected terminal trajectory information granularity includes at least one of a tracking area level, a cell level, and a geographical location level.

[0049] Specifically, the expected terminal trajectory information granularity may be a granularity indicating the expected terminal trajectory information, such as a tracking area level (TA level), a cell level (CellLevel), or a geographical position level (latitude and longitude).

[0050] Furthermore, based on the embodiment of the above application, the data analysis response information is: Terminal The information includes at least one of mobility statistical information, terminal mobility prediction information, network load statistical information, network load prediction information, and general data statistical information.

[0051] In the embodiment of the present application, the data analysis response information generated by the core network according to the content of the data analysis request message is: Terminal The information may include one or more of mobility statistics information, terminal mobility prediction information, network load statistics information, network load forecast information, and general data statistics information. Among them, the terminal mobility statistics information may be statistical information on the location points of one or more terminals at various times or time periods. The terminal mobility forecast information may be statistical information on the predicted locations of one or more terminals at a future time or time period. The network load statistics information may be statistical information on the network load at a time or time period. The network load forecast information may be statistical information on the network load at a future time or time period. The general data statistics information may be general data statistics such as map information of an area of interest or a terminal movement direction.

[0052] Furthermore, based on the embodiment of the above application, the terminal mobility statistical information includes at least one of the terminal geographical location coordinates, the terminal resident cell identifier, the tracking area in which the terminal is located, the connection beam identification information between the terminal and the cell, the time information when the terminal accesses the cell, the time information when the terminal accesses the tracking area, the terminal movement direction, the terminal movement speed, the map information of the local area, and the map information of the area of interest.

[0053] Furthermore, based on the embodiment of the above application, the terminal mobility prediction information includes at least one of predicted terminal geographical location coordinates, a future resident cell identifier of the terminal, a future tracking area of the terminal, time information of the terminal accessing the cell in the future, time information of the terminal accessing the tracking area in the future, and reliability.

[0054] In an embodiment of the present application, the terminal mobility prediction information may include a predicted terminal geographical location coordinate, a terminal's future residence cell identifier, a terminal's future tracking area, time information of the terminal's future access to the cell, time information of the terminal's future access to the tracking area, and corresponding reliability information. Each piece of information in the terminal mobility prediction information may have a corresponding reliability information.

[0055] Furthermore, based on the embodiment of the above application, the network load statistics information includes at least one of the following: cell load, the number of cell access terminals, cell physical resource utilization rate, and cell packet data convergence protocol data volume.

[0056] Furthermore, based on the embodiment of the above application, the network load forecast information includes at least one of a predicted cell load, a predicted number of cell access terminals, a predicted cell physical resource utilization rate, a predicted cell packet data convergence protocol data volume, and a reliability.

[0057] Furthermore, based on the embodiment of the above application, the general data statistical information includes at least one of map information of a local area, map information of a region of interest, an average moving speed of the terminal, and a moving direction of the terminal.

[0058] In one exemplary embodiment, Figure 3 illustrates an example of a network optimization method according to an embodiment of the present application. Referring to Figure 3, the process in which the RAN side obtains data analysis or prediction data of the core network to perform network optimization may include the following steps 1 to 5:

[0059] Step 1: The NG-RAN node sends a data analytics request message (DATA ANALYTICS INFORMATION REQUEST) to the core network to instruct the core network on the requested AI data analytics information. The request message includes one or more of the following: one or more data analysis type identifiers, one or more data analysis format identifiers, one or more terminal identifiers (UE IDs), a data analysis period, a data analysis area of interest, and a granularity of expected UE trajectory information. The one or more data analysis type identifiers indicate the type of data analysis requested, such as terminal (UE: User Equipment)-related type data, network load-related type data, QoE-related type data, network slice-related type data, or general data type (including map information). The one or more data analysis format identifiers indicate the data analysis format, such as a data statistics format or a prediction information format. The data analysis period includes one or more of the following: a time granularity, a start time of the data analysis report, and a cutoff time of the data analysis report. The data analysis area of interest may be, for example, a tracking area, a cell list, or a paging area. The granularity of the expected UE trajectory information includes, for example, a tracking area level (TA level), a cell level, and a geographical position level (latitude and longitude).

[0060] Step 2: The core network collects data according to the instructions in the received data analysis request message and generates a data report requested in the request message.

[0061] Step 3: The core network sends a Data Analysis Report / Response message (Data Analysis Information Report / Response) containing the message requested by the NG-RAN node to the NG-RAN node.

[0062] If the request message indicates UE-related class data in the form of data statistics, the data analysis report / response message includes UE mobility statistics, which include location statistics information of one or more UEs at a certain time or period, and may be one or more of the following: geographical location coordinates of the UE, such as latitude and longitude, a cell identifier of the UE, a tracking area (TA) in which the UE is located, connection beam identification information between the UE and the cell, the time and duration when the UE accesses the cell or tracking area TA, the UE moving direction, the UE moving speed, and map information of a local area / area of interest.

[0063] If the request message includes UE-related class data in the form of Requested Prediction Information, the Data Analysis Report / Response message includes UE mobility predictions, which include location prediction information for one or more UEs at a future time or time period, and may include one or more of the following: predicted UE geographic location coordinates, such as latitude and longitude, a predicted cell identifier where the UE will reside in the future, a predicted tracking area (TA) where the UE will be located in the future, the time and length of time the UE will access the cell or tracking area TA in the future, and a reliability or accuracy rate of the prediction information.

[0064] If the request message includes network load-related class data in the requested statistics format, the data analysis report / response message includes network load statistics information (Load statistics), which is network load statistics information at a certain point in time or for a certain period of time, and may be one or more of cell load (Traffic load), number of cell access UEs (Number of UEs), cell resource utilization rate (PRB usage), and cell packet data convergence protocol (PDCP) data volume.

[0065] If the request message includes network load-related class data in the form of requested prediction information, the data analysis report / response message includes network load prediction information (Load predictions), which is network load prediction information for one or more NG-RAN nodes or cells at a future time or period, and may be one or more of a predicted cell load (Traffic load), a predicted number of cell access UEs (Number of UEs), a predicted cell physical resource utilization rate (PRB usage), a predicted cell packet data convergence protocol (PDCP) data volume, and a reliability or accuracy rate of the prediction information.

[0066] If the request message contains requested general data type data, the data analysis report message contains one or more of map information of the local area / area of interest, the UE average moving speed, the UE moving direction, and the like.

[0067] Step 4: The NG-RAN node receives the data analysis report from the core network and performs ML model training / ML model inference.

[0068] Step 5: NG-RAN performs network optimization based on the core network data analysis report or ML model inference results.

[0069] 4 is a flowchart of a network optimization method according to an embodiment of the present application. The embodiment of the present application can be applied to network intelligent optimization in a wireless communication network. The method can be performed by a network optimization device according to an embodiment of the present application, which can be implemented in the form of software and / or hardware, and can generally be integrated into a core network node. Referring to FIG. 4, the method according to the embodiment of the present application specifically includes the following steps 310 to 330.

[0070] Step 310: Send a data information request to the base station.

[0071] Here, the data information request may be request information for the core network to acquire data on the base station side, and may include instruction information on a data analysis method, instruction information on data analysis content, etc. The data information request may be transmitted to the base station side node by the core network device.

[0072] In an embodiment of the present application, the core network may send a data information request to the base station to instruct the base station to acquire one or more pieces of data on the base station side. The core network may acquire the data on the base station side by sending the data information request to the base station.

[0073] Step 320: Receive the data information response fed back from the base station, and determine the model processing result through the artificial intelligence learning model.

[0074] Here, the data information response may be response information generated by the base station in response to the data information request, may include the requested data, and may have a correspondence relationship with the data information request. The artificial intelligence learning model may be a pre-trained neural network model that can process input information and be used for processing such as data statistics and data prediction. The model processing result may be an output result of the artificial intelligence learning model and may include a data prediction result, a data statistics result, etc.

[0075] In an embodiment of the present application, when the base station side node receives the data information request, it generates a corresponding data information response and feeds it back to the core network, and the core network responds to the data information response through an artificial intelligence learning model to generate a model processing result, which may be prediction information based on the data information response or statistical information based on the data information response, depending on the artificial intelligence learning model.

[0076] Step 330: Perform network optimization operations according to the model processing results.

[0077] In the embodiments of the present application, one or more different network optimization policies may be preset, a corresponding network optimization policy may be found according to the model processing result, and a corresponding network optimization operation may be performed according to the determined network optimization policy, or a network optimization policy may be generated in real time according to the model processing result.

[0078] In an embodiment of the present application, a data analysis request message is sent to a core network, data response information is fed back from the core network, an artificial intelligence model is used to determine a model processing result, and a corresponding network optimization operation is performed according to the model processing result. By exchanging data information with the core network and using an artificial intelligence model to determine a model processing result corresponding to the data information, data statistics and / or predictions can be realized, which can improve the accuracy of network optimization and enhance network performance and user experience.

[0079] Furthermore, based on the embodiment of the above application, the data information response is determined when the base station performs at least one of the following processes according to the data information request: data collection, data statistical analysis, and data prediction.

[0080] In an embodiment of the present application, the data information response received by the core network may be generated by a base station that performs one or more of the following processes according to the data information request: data collection, data statistical analysis, and data prediction.

[0081] 5 is a diagram showing an example of another network optimization method according to an embodiment of the present application, which is embodied based on the embodiment of the above application. Referring to FIG. 5, the method according to the embodiment of the present application specifically includes the following steps 410 to 440.

[0082] Step 410: The base station sends a data information request to the base station for training / updating the second artificial intelligence learning model.

[0083] Here, the second AI learning model may be an AI learning model set in the base station, specifically, a neural network model. The AI learning model of the core network may have a different type and structure from the second AI learning model of the base station. For example, the AI learning model of the core network can handle data that has little impact on the real-time performance of the terminal, while the second AI learning module can handle data that has a large impact on the real-time performance of the terminal, such as network load and QOE data.

[0084] In an embodiment of the present application, the core network may send a data information request to the base station, so that the base station can train or update the second artificial intelligence learning model of the base station according to the data information request, thereby improving the accuracy of the data information response fed back from the base station and further enhancing the effect of network optimization.

[0085] Step 420: Receive the data information response fed back from the base station, and determine the model processing result through the artificial intelligence learning model.

[0086] Step 430: Perform network optimization operations according to the model processing results.

[0087] Step 440: Perform a network optimization operation according to the data information response.

[0088] Specifically, the core network may perform network optimization operations according to the data information response directly fed back from the base station side.

[0089] In the embodiment of the present application, the base station sends a data analysis request message to the base station to update the second artificial intelligence learning model, receives a data information response fed back from the base station, processes the data information response using the artificial intelligence model to generate a model processing result, and performs corresponding network optimization operations using the model processing result and / or the data information response, respectively, thereby further improving the accuracy of network optimization and improving network performance and user experience.

[0090] Furthermore, based on the embodiment of the above application, the data information request includes at least one of at least one data analysis type identifier, at least one data analysis format identifier, at least one terminal identifier, data analysis time information, data analysis area of interest, and expected terminal trajectory information granularity.

[0091] Furthermore, based on the embodiment of the above application, the data analysis type identifier includes at least one of a terminal data type identifier, a network load data type identifier, a quality of experience data type identifier, a network slice data type identifier, and a general data type identifier.

[0092] Furthermore, based on an embodiment of the above application, the data analysis type identifier includes at least one of a data statistics identifier and a data prediction identifier.

[0093] Furthermore, based on the embodiment of the above application, the data analysis time information includes at least one of a time granularity, a data analysis start time, and a data analysis end time.

[0094] Furthermore, based on the embodiment of the above application, the data analysis interest area includes at least one of a tracking area, a cell list, and a paging area.

[0095] Furthermore, based on the embodiment of the above application, the expected terminal trajectory information granularity includes at least one of a tracking area level, a cell level, and a geographical location level.

[0096] Further, based on the embodiment of the above application, the data information response may include: Terminal The information includes at least one of mobility statistical information, terminal mobility prediction information, network load statistical information, network load prediction information, and general data statistical information.

[0097] Furthermore, based on the embodiment of the above application, the terminal mobility statistical information includes at least one of the terminal geographical location coordinates, the terminal resident cell identifier, the tracking area in which the terminal is located, the connection beam identification information between the terminal and the cell, the time information when the terminal accesses the cell, the time information when the terminal accesses the tracking area, the terminal movement direction, the terminal movement speed, the map information of the local area, and the map information of the area of interest.

[0098] Furthermore, based on the embodiment of the above application, the terminal mobility prediction information includes at least one of predicted terminal geographical location coordinates, a future resident cell identifier of the terminal, a future tracking area of the terminal, time information of the terminal accessing the cell in the future, time information of the terminal accessing the tracking area in the future, and reliability.

[0099] Furthermore, based on the embodiment of the above application, the network load statistics information includes at least one of the following: cell load, the number of cell access terminals, cell physical resource utilization rate, and cell packet data convergence protocol data volume.

[0100] Furthermore, based on the embodiment of the above application, the network load forecast information includes at least one of a predicted cell load, a predicted number of cell access terminals, a predicted cell physical resource utilization rate, a predicted cell packet data convergence protocol data volume, and a reliability.

[0101] Furthermore, based on the embodiment of the above application, the general data statistical information includes at least one of map information of a local area, map information of a region of interest, an average moving speed of the terminal, and a moving direction of the terminal.

[0102] In one exemplary embodiment, Figure 6 illustrates an example of a network optimization method according to an embodiment of the present application. Referring to Figure 6, taking the case where a core network obtains prediction information of NG-RAN nodes to perform network optimization as an example, the network optimization method may include the following steps 1 to 5:

[0103] Step 1: The core network sends an artificial intelligence (AI) / machine learning (ML) data information request message (AI / ML DATA INFORMATION REQUEST) to the NG-RAN node to instruct the NG-RAN on the required artificial intelligence information. The request message includes one or more of the following: one or more data analysis type identifiers, one or more data analysis format identifiers, one or more terminal identifiers (UE IDs), a data analysis period, a data analysis area of interest, and a granularity of expected UE trajectory information. The one or more data analysis type identifiers indicate the type of data analysis requested, such as UE-related type data, network load-related type data, QoE-related type data, network slice-related type data, or general data type (including map information). The one or more data analysis format identifiers indicate the data analysis format, such as a data statistics format or a prediction information format. The data analysis period includes one or more of the following: a time granularity, a start time of the data analysis report, and a cutoff time of the data analysis report. The data analysis area of interest may be, for example, a tracking area, a cell list, or a paging area. The granularity of the expected UE trajectory information includes, for example, a tracking area level (TA level), a cell level, and a geographical position level (latitude and longitude).

[0104] Step 2: The NG-RAN node performs data collection / model training / model inference according to the instructions in the received data analysis request message, and generates the data report requested in the request message.

[0105] Step 3: The NG-RAN node sends an AI / ML Data Information Report / Response to the core network, and the message includes the message requested by the core network.

[0106] If the request message indicates UE-related class data in the form of data statistics, the data analysis report / response message includes UE mobility statistics, which include location statistics information of one or more UEs at a certain time or period, and may be one or more of the following: geographical location coordinates of the UE, such as latitude and longitude, a cell identifier of the UE, a tracking area (TA) in which the UE is located, connection beam identification information between the UE and the cell, the time and duration when the UE accesses the cell or tracking area TA, the UE moving direction, the UE moving speed, and map information of a local area / area of interest.

[0107] If the request message includes UE-related class data in the form of Requested Prediction Information, the Data Analysis Report / Response message includes UE mobility predictions, which include location prediction information for one or more UEs at a future time or time period, and may include one or more of the following: predicted UE geographic location coordinates, such as latitude and longitude, a predicted cell identifier where the UE will reside in the future, a predicted tracking area (TA) where the UE will be located in the future, the time and length of time the UE will access the cell or tracking area TA in the future, and a reliability or accuracy rate of the prediction information.

[0108] If the request message includes network load-related class data in the requested statistics format, the data analysis report / response message includes network load statistics information (Load statistics), which is network load statistics information at a certain point in time or for a certain period of time, and may be one or more of cell load (Traffic load), number of cell access UEs (Number of UEs), cell resource utilization rate (PRB usage), and cell packet data convergence protocol (PDCP) data volume.

[0109] If the request message includes network load-related class data in the form of requested prediction information, the data analysis report / response message includes network load prediction information (Load predictions), which is network load prediction information for one or more NG-RAN nodes or cells at a future time or period, and may be one or more of a predicted cell load (Traffic load), a predicted number of cell access UEs (Number of UEs), a predicted cell physical resource utilization rate (PRB usage), a predicted cell packet data convergence protocol (PDCP) data volume, and a reliability or accuracy rate of the prediction information.

[0110] If the request message contains requested general data type data, the data analysis report message contains one or more of map information of the local area / area of interest, the UE average moving speed, the UE moving direction, and the like.

[0111] Step 4: The core network obtains the data analysis report of the NG-RAN node and performs data analysis, data prediction, and data statistics.

[0112] Step 5: The core network performs network optimization based on the data analysis report of the NG-RAN node or the data analysis report of the core network.

[0113] 7 is a structural schematic diagram of a network optimization device according to an embodiment of the present application, which can implement the network optimization method according to any embodiment of the present application, and includes corresponding functional modules for implementing the method and beneficial effects. The device can be implemented by software and / or hardware, and can generally be integrated into a base station. Specifically, the device includes a data analysis and transmission module 501, a data processing module 502, and a network optimization module 503.

[0114] The data analysis sending module 501 sends a data analysis request message to the core network.

[0115] The data processing module 502 receives the data analysis response information fed back from the core network, and determines the model processing result through the artificial intelligence learning model.

[0116] The network optimization module 503 performs network optimization operations according to the model processing results.

[0117] In an embodiment of the present application, a data analysis sending module sends a data analysis request message to a core network, a data processing module receives data response information fed back from the core network, an artificial intelligence model is used to determine a model processing result, and a network optimization module performs a corresponding network optimization operation according to the model processing result. By exchanging data information with the core network and using an artificial intelligence model to determine a model processing result corresponding to the data information, data statistics and / or predictions can be realized, which can improve the accuracy of network optimization and enhance network performance and user experience.

[0118] Furthermore, based on the embodiment of the above application, the device further includes a second network optimization module for performing a network optimization operation according to the data analysis response information.

[0119] Furthermore, based on the embodiment of the above application, the data analysis response information of the device is determined when the core network performs at least one of data collection, data statistical analysis, and data prediction according to the data analysis request message.

[0120] Furthermore, based on the embodiment of the above application, the data analysis request message of the device includes at least one of at least one data analysis type identifier, at least one data analysis format identifier, at least one terminal identifier, data analysis time information, data analysis area of interest, and expected terminal trajectory information granularity.

[0121] Furthermore, based on the embodiment of the above application, the data analysis type identifier of the device includes at least one of a terminal data type identifier, a network load data type identifier, a quality of experience data type identifier, a network slice data type identifier, and a general data type identifier.

[0122] Furthermore, based on an embodiment of the above application, the data analysis type identifier includes at least one of a data statistics identifier and a data prediction identifier.

[0123] Furthermore, based on the embodiment of the above application, the data analysis time information of the device includes at least one of a time granularity, a data analysis start time, and a data analysis end time.

[0124] Furthermore, based on the embodiment of the above application, the data analysis interest area of the device includes at least one of a tracking area, a cell list, and a paging area.

[0125] Furthermore, based on the embodiment of the above application, the expected terminal trajectory information granularity of the device includes at least one of a tracking area level, a cell level, and a geographical location level.

[0126] Furthermore, based on the embodiment of the above application, the data analysis response information of the device is: Terminal The information includes at least one of mobility statistical information, terminal mobility prediction information, network load statistical information, network load prediction information, and general data statistical information.

[0127] Furthermore, based on the embodiment of the above application, the terminal mobility statistical information of the device includes at least one of the terminal geographical location coordinates, the terminal resident cell identifier, the tracking area in which the terminal is located, the connection beam identification information between the terminal and the cell, the time information when the terminal accesses the cell, the time information when the terminal accesses the tracking area, the terminal movement direction, the terminal movement speed, the map information of the local area, and the map information of the area of interest.

[0128] Furthermore, based on the embodiment of the above application, the terminal mobility prediction information of the device includes at least one of predicted terminal geographical location coordinates, a future resident cell identifier of the terminal, a future tracking area of the terminal, time information of the terminal accessing the cell in the future, time information of the terminal accessing the tracking area in the future, and reliability.

[0129] Furthermore, based on the embodiment of the above application, the network load statistics information includes at least one of the following: cell load, the number of cell access terminals, cell physical resource utilization rate, and cell packet data convergence protocol data volume.

[0130] Furthermore, based on the embodiment of the above application, the network load prediction information of the device includes at least one of a predicted cell load, a predicted number of cell access terminals, a predicted cell physical resource utilization rate, a predicted cell packet data convergence protocol data volume, and a reliability.

[0131] Furthermore, based on the embodiment of the above application, the general data statistical information of the device includes at least one of map information of a local area, map information of a region of interest, an average moving speed of the terminal, and a moving direction of the terminal.

[0132] Furthermore, based on the embodiment of the above application, the device further includes a model training module for training or updating the artificial intelligence learning model according to data analysis response information.

[0133] 8 is a structural schematic diagram of another network optimization device according to an embodiment of the present application, which can implement the network optimization method according to any embodiment of the present application, and includes corresponding functional modules for implementing the method and beneficial effects. The device can be implemented by software and / or hardware, and generally integrated into core network equipment, and specifically includes: a data sending module 601, a result determining module 602, and an optimization executing module 603.

[0134] The data transmission module 601 transmits a data information request to the base station.

[0135] The result determination module 602 receives the data information response fed back from the base station, and determines the model processing result through the artificial intelligence learning model.

[0136] The optimization execution module 603 executes network optimization operations according to the model processing results. In an embodiment of the present application, a data transmission module sends a data analysis request message to a core network, a result determination module receives data response information fed back from the core network, determines a model processing result using an artificial intelligence model, and an optimization execution module performs a corresponding network optimization operation according to the model processing result. By exchanging data information with the core network and using an artificial intelligence model to determine a model processing result corresponding to the data information, data statistics and / or predictions can be realized, which can improve the accuracy of network optimization and enhance network performance and user experience.

[0137] Furthermore, based on the embodiment of the above application, the device further includes a data information optimization module that performs a network optimization operation according to the data information response.

[0138] Furthermore, based on the embodiment of the above application, the data information response of the device is determined when the base station performs at least one of the processes of data collection, data statistical analysis, and data prediction according to the data information request.

[0139] Furthermore, based on the embodiment of the above application, the data information request of the device includes at least one of at least one data analysis type identifier, at least one data analysis format identifier, at least one terminal identifier, data analysis time information, data analysis area of interest, and expected terminal trajectory information granularity.

[0140] Furthermore, based on the embodiment of the above application, the data analysis type identifier of the device includes at least one of a terminal data type identifier, a network load data type identifier, a quality of experience data type identifier, a network slice data type identifier, and a general data type identifier.

[0141] Furthermore, based on an embodiment of the above application, the data analysis type identifier includes at least one of a data statistics identifier and a data prediction identifier.

[0142] Furthermore, based on the embodiment of the above application, the data analysis time information of the device includes at least one of a time granularity, a data analysis start time, and a data analysis end time.

[0143] Furthermore, based on the embodiment of the above application, the data analysis interest area of the device includes at least one of a tracking area, a cell list, and a paging area.

[0144] Furthermore, based on the embodiment of the above application, the expected terminal trajectory information granularity of the device includes at least one of a tracking area level, a cell level, and a geographical location level.

[0145] Further, based on the embodiment of the above application, the data information response of the device is: Terminal The information includes at least one of mobility statistical information, terminal mobility prediction information, network load statistical information, network load prediction information, and general data statistical information.

[0146] Furthermore, based on the embodiment of the above application, the terminal mobility statistical information of the device includes at least one of the terminal geographical location coordinates, the terminal resident cell identifier, the tracking area in which the terminal is located, the connection beam identification information between the terminal and the cell, the time information when the terminal accesses the cell, the time information when the terminal accesses the tracking area, the terminal movement direction, the terminal movement speed, the map information of the local area, and the map information of the area of interest.

[0147] Furthermore, based on the embodiment of the above application, the terminal mobility prediction information of the device includes at least one of predicted terminal geographical location coordinates, a future resident cell identifier of the terminal, a future tracking area of the terminal, time information of the terminal accessing the cell in the future, time information of the terminal accessing the tracking area in the future, and reliability.

[0148] Furthermore, based on the embodiment of the above application, the network load statistics information includes at least one of the following: cell load, the number of cell access terminals, cell physical resource utilization rate, and cell packet data convergence protocol data volume.

[0149] Furthermore, based on the embodiment of the above application, the network load prediction information of the device includes at least one of a predicted cell load, a predicted number of cell access terminals, a predicted cell physical resource utilization rate, a predicted cell packet data convergence protocol data volume, and a reliability.

[0150] Furthermore, based on the embodiment of the above application, the general data statistical information of the device includes at least one of map information of a local area, map information of a region of interest, an average moving speed of the terminal, and a moving direction of the terminal.

[0151] Furthermore, based on the embodiment of the above application, the data transmission module 601 specifically sends the data information request to the base station for the base station to train / update the second artificial intelligence learning model.

[0152] 9 is a structural schematic diagram of an electronic device according to an embodiment of the present application. The electronic device includes a processor 70, a memory 71, an input device 72, and an output device 73. The number of processors 70 in the electronic device may be one or more, and FIG. 9 illustrates one processor 70. The processor 70, memory 71, input device 72, and output device 73 of the electronic device may be connected via a bus or other method, and FIG. 9 illustrates connection via a bus.

[0153] The memory 71 may be used as a computer-readable storage medium to store software programs, computer-executable programs, and modules such as the data analysis and transmission module 501, the data processing module 502, the network optimization module 503, or the data transmission module 601, the result determination module 602, and the optimization execution module 603 corresponding to the network optimization device in the embodiments of the present application. The processor 70 executes the software programs, instructions, and modules stored in the memory 71 to perform various functional applications and data processing of the electronic device, thereby realizing the above-mentioned network optimization method.

[0154] The memory 71 primarily includes an application storage area and a data storage area. The application storage area may store an operating system and / or application programs necessary for at least one function. The data storage area may store data generated by use of the electronic device. Furthermore, the memory 71 may include high-speed random access memory, and may further include non-volatile memory such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some examples, the memory 71 may further include memory located remotely from the processor 70 that may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, a corporate intranet, a local area network, a mobile communication network, and combinations thereof.

[0155] The input device 72 may be used to receive input numeric or textual information and to generate key signal inputs associated with user settings and function control of the electronic device. The output device 73 may include a display device such as a display screen.

[0156] An embodiment of the present application also provides a storage medium containing computer-executable instructions for performing a network optimization method, which, when executed by a computer processor, includes: sending a data analysis request message to a core network; receiving data analysis response information fed back from the core network and determining a model processing result through an artificial intelligence learning model; and performing a network optimization operation according to the model processing result. Alternatively, the method includes the steps of sending a data information request to a base station, receiving a data information response fed back from the base station, and determining a model processing result using an artificial intelligence learning model, and performing a network optimization operation according to the model processing result.

[0157] From the above description of the embodiments, it can be seen that the present application can be realized by software and necessary general-purpose hardware, and of course by hardware, but in many cases the former is a more preferred embodiment. Based on this understanding, the essential technical solution of the present application or a part that contributes to the prior art can be embodied in the form of a software product. The software product can be stored in a computer-readable storage medium such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, optical disk, etc., and includes several instructions for a computer device (which may be a personal computer, a server, a network device, etc.) to execute the methods described in various embodiments of the present application.

[0158] In the above device embodiments, the individual units and modules included are merely divided by functional logic, and are not limited to the above division as long as the corresponding functions can be realized. Furthermore, the specific names of the functional units are used only to make them easier to distinguish from one another, and are not intended to limit the scope of protection of the present application.

[0159] All or some of the steps in the methods, systems, and functional modules / units of the devices disclosed above may be implemented as software, firmware, hardware, and any suitable combination thereof.

[0160] In hardware embodiments, the division between functional modules / units set forth in the above description does not necessarily correspond to a division of physical components; for example, one physical component may have multiple functions, or multiple physical components may cooperate to perform a single function or step. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on computer-readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information (e.g., computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cartridges, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. Additionally, communication media typically include computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism and may include any information delivery media.

[0161] The above several embodiments of the present application have been described with reference to the drawings, and are not limited to the scope of protection of the present application. Any amendments, equivalent replacements and improvements made by those skilled in the art without departing from the scope and spirit of the present application shall fall within the scope of protection of the present application.

Claims

1. A network optimization method executed by a network optimization device, comprising: sending a data analysis request message to a core network; receiving data analysis response information fed back from the core network and determining a model processing result by a first artificial intelligence learning model, wherein the data analysis response information is a processing result of the core network processing the data analysis request message by a third artificial intelligence learning model; performing a network optimization operation in response to the model processing results; training or updating the first artificial intelligence learning model in response to the data analysis response information.

2. The method of claim 1 , further comprising performing a network optimization operation in response to the data analysis response information.

3. The method of claim 1 , wherein the data analysis response information is determined when the core network performs at least one of data collection, data statistical analysis, and data prediction according to the data analysis request message.

4. The data analysis request message The method of claim 1 , comprising at least one of at least one data analysis type identifier, at least one data analysis format identifier, at least one terminal identifier, data analysis time information, data analysis area of interest, and expected terminal trajectory information granularity.

5. The method of claim 4 , wherein the data analysis type identifier includes at least one of a terminal data type identifier, a network load data type identifier, a quality of experience data type identifier, a network slice data type identifier, and a general data type identifier.

6. The method of claim 4 , wherein the data analysis type identifier comprises at least one of a data statistics identifier and a data prediction identifier.

7. The method of claim 4 , wherein the data analysis time information includes at least one of a time granularity, a data analysis start time, and a data analysis end time.

8. The method of claim 4 , wherein the data analysis area of interest includes at least one of a tracking area, a cell list, and a paging area.

9. The method of claim 4 , wherein the expected terminal trajectory information granularity includes at least one of a tracking area level, a cell level, and a geographic location level.

10. the data analysis response information includes at least one of terminal mobility statistical information, terminal mobility prediction information, network load statistical information, network load prediction information, and general data statistical information; The terminal mobility statistics information includes at least one of a terminal geographical location coordinate, a terminal resident cell identifier, a tracking area where the terminal is located, connection beam identification information between the terminal and the cell, time information when the terminal accesses the cell, time information when the terminal accesses the tracking area, a terminal movement direction, a terminal movement speed, map information of a local area, and map information of a region of interest; The terminal mobility prediction information includes at least one of a predicted terminal geographical location coordinate, a future resident cell identifier of the terminal, a future tracking area of the terminal, time information of the terminal accessing the cell in the future, time information of the terminal accessing the tracking area in the future, and a reliability; The network load statistics information includes at least one of a cell load, a cell access terminal number, a cell physical resource utilization rate, and a cell packet data convergence protocol data volume; The network load forecast information includes at least one of a predicted cell load, a predicted number of cell access terminals, a predicted cell physical resource utilization rate, a predicted cell packet data convergence protocol data volume, and a reliability; The method of claim 1 , wherein the general data statistical information includes at least one of map information of a local area, map information of a region of interest, an average terminal movement speed, and a terminal movement direction.

11. one or more processors; a memory for storing one or more programs; An electronic device, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the network optimization method according to any one of claims 1 to 10.

12. A computer readable storage medium storing one or more programs which, when executed by one or more processors, implement the network optimization method of any one of claims 1 to 10.

Images