Method, apparatus, device and medium for generating data reference set of intelligent slicing system

Abstract

The present application discloses a method, device, electronic device, readable storage medium and access network system for generating a slice data reference set of an access network wireless intelligent slice system, which is applied to the field of wireless communication technologies. The method includes that a base station receives a self-traversal instruction and switches to a slice traversal mode; in the slice traversal mode, the base station automatically sets multiple different resource configuration conditions for each slice to be configured based on slice configuration information, drives the base station to operate under each set of resource configuration conditions of each slice to be configured, and simultaneously obtains the base station status information and slice parameter information of each slice to be configured under different resource configuration conditions. The base station sends all the obtained base station status information and slice parameter information to the intelligent learning database of the wireless intelligent slice system, so that a slice data reference set required for the access network wireless intelligent slice system can be established quickly and completely.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technologies, and particularly to a method, apparatus, electronic device, readable storage medium, and access network system for generating a slice data reference set of an access network wireless intelligent slice system. Background Art

[0002] Network slicing technology is a way of networking on demand. According to the SLA (Service Level Agreement), the required virtual machines and physical resources are selected for specific communication service types to achieve the reorganization of resources. It allows operators to separate multiple virtual end-to-end networks on a unified infrastructure. Each network slice is logically isolated from the radio access network to the bearer network and then to the core network to adapt to various types of applications.

[0003] Currently, related technologies can sink network slicing technology to the access network through artificial intelligence technology and machine learning methods, so as to provide intelligent slice services for operators and users. As is well known, the implementation of both artificial intelligence technology and machine learning methods relies on a knowledge base or a data reference set. However, related technologies cannot quickly and completely establish a data reference set.

[0004] In view of this, how to quickly and completely generate the slice data reference set required for the access network wireless intelligent slice system is a technical problem that those skilled in the art need to solve. Summary of the Invention

[0005] The present application provides a method, apparatus, electronic device, readable storage medium, and access network system for generating a slice data reference set of an access network wireless intelligent slice system, which can quickly and completely establish the slice data reference set required for the access network wireless intelligent slice system.

[0006] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions:

[0007] On the one hand, an embodiment of the present invention provides a method for generating a slice data reference set of an access network wireless intelligent slice system, which is applied to a base station and includes:

[0008] When receiving a self-traversal instruction, switch to the slice traversal mode;

[0009] In the slice traversal mode, based on the slice configuration information, automatically set multiple different resource configuration conditions for each slice to be configured, and drive the base station to run under each set of resource configuration conditions of each slice to be configured, and simultaneously obtain the base station status information and slice parameter information of all slices to be configured under different resource configuration conditions;

[0010] Send the base station status information and the slice parameter information to the intelligent learning database of the wireless intelligent slice system.

[0011] Optionally, automatically set multiple different resource configuration conditions for each slice to be configured based on the slice configuration information, including:

[0012] Obtain slice configuration information; the slice configuration information includes a traversal period, the total number of slices to be configured, the total number of resource blocks, the resource block configuration range of each slice to be configured, and an initial configuration value;

[0013] In each traversal period, determine all resource block allocation schemes for each slice to be configured based on the slice configuration information.

[0014] Optionally, automatically set multiple different resource configuration conditions for each slice to be configured based on the slice configuration information, including:

[0015] A1: Divide each slice to be configured into multiple first slices to be configured, multiple second slices to be configured, and multiple candidate slices to be configured;

[0016] A2: Fix the resource block configuration value of each first slice to be configured to the corresponding initial configuration value, select one second slice to be configured from each second slice to be configured as the current second slice to be configured, set the resource block configuration value of the current second slice to be configured to increase by a first target number of resource blocks in each statistical period, and cycle through to determine all resource block allocation schemes for the remaining second slices to be configured and each candidate slice to be configured in each statistical period based on the slice configuration information;

[0017] A3: When the resource block configuration value of the current second slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each first slice to be configured as the current first slice to be configured, set the resource block configuration value of the current first slice to be configured to increase by a second target number of resource blocks in each statistical period, restore the resource block configuration values of each candidate slice to be configured, each second slice to be configured, and the remaining first slices to be configured to the corresponding initial configuration values, and repeat steps A2 and A3 until the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value;

[0018] A4: When the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value, select another first slice to be configured from each first slice to be configured as the current first slice to be configured and jump to execute A3 until the resource block configuration values of each first slice to be configured all reach the corresponding maximum configuration values;

[0019] A5: Select a second slice to be configured again from each of the second slices to be configured as the current second slice to be configured, and jump to execute A2 until the resource block configuration values of each second slice to be configured reach the corresponding maximum configuration values.

[0020] Optionally, the automatically setting multiple different resource configuration conditions for each slice to be configured based on the slice configuration information further includes:

[0021] Determine whether there is slice traversal interruption information; the slice traversal interruption information is the slice resource configuration situation stored when the base station interrupts the previous slice traversal mode.

[0022] If there is the slice traversal interruption information, continue to set corresponding resource configuration conditions for the slices to be configured that have not been traversed in the current cycle based on the slice traversal interruption information.

[0023] Optionally, it further includes:

[0024] When receiving the slice deduction configuration information sent by the wireless intelligent slice system, send the slice deduction configuration information to the intelligent learning database.

[0025] Another aspect of the embodiments of the present invention provides a generating device for a slice data reference set of an access network wireless intelligent slice system, which is applied to a base station and includes:

[0026] A mode switching module, configured to switch to the slice traversal mode when receiving a self-traversal instruction.

[0027] A slice automatic configuration module, configured to, in the slice traversal mode, automatically set multiple different resource configuration conditions for each slice to be configured based on the slice configuration information, and drive the base station to run under each set of resource configuration conditions of each slice to be configured, and simultaneously obtain the base station status information and slice parameter information of all slices to be configured under different resource configuration conditions.

[0028] A data generating module, configured to send the base station status information and the slice parameter information to the intelligent learning database of the wireless intelligent slice system.

[0029] The embodiments of the present invention further provide an electronic device, which is applied to a base station and includes a processor, and the processor is configured to implement the steps of the method for generating a slice data reference set of the access network wireless intelligent slice system as described in any one of the previous items when executing a computer program stored in a memory.

[0030] The embodiments of the present invention further provide a readable storage medium, which is applied to a base station, and a computer program is stored on the readable storage medium, and the computer program is configured to implement the steps of the method for generating a slice data reference set of the access network wireless intelligent slice system as described in any one of the previous items when being executed by a processor.

[0031] An embodiment of the present invention finally also provides an access network system, including a base station and a wireless intelligent slicing system;

[0032] Data and instructions are transmitted between the base station and the wireless intelligent slicing system through a communication interface;

[0033] The base station is configured to implement the steps of the method for generating a slice data reference set of the access network wireless intelligent slicing system as described in any one of the previous items;

[0034] The wireless intelligent slicing system is configured to use all the base station status information and all the slice parameter information sent by the base station as a slice data reference set to train a slice configuration model based on an artificial intelligence algorithm.

[0035] Optionally, the wireless intelligent slicing system includes an intelligent learning database, a slice training module, a slice deduction module, a data processing module, and an instruction management module;

[0036] The base station is further configured to send real-time slice statistical data and FAPI interface data to the data processing module through the communication interface;

[0037] The data processing module is configured to process the real-time slice statistical data and the FAPI interface data, and send the data processing result to the slice deduction module;

[0038] The slice training module is configured to train the slice configuration model based on the intelligent learning database;

[0039] The slice deduction module is configured to call the slice configuration model to calculate the data processing result to obtain slice deduction configuration information, and send the slice deduction configuration information to the instruction management module;

[0040] The instruction management module is configured to generate slice configuration instructions based on the slice deduction configuration information, and send them to the base station through the communication interface.

[0041] The advantages of the technical solution provided by this application are that the base station periodically sets different resource configuration conditions for each slice by itself, and traverses each slice to count the base station status information and slice parameter information in each cycle of slice changes. The slice traversal in one cycle can reach the second level, and only one-tenth or even one-hundredth of the original time is required to loop multiple cycles to generate a larger number of slice data, quickly and completely expanding the intelligent learning database of the artificial intelligence algorithm.

[0042] In addition, as the data volume of the intelligent learning database continues to improve and grow, the more data samples are supplied to the slice training module of the wireless intelligent slicing system, the more accurate the parameter configuration results output by the slice configuration model will be. The slice deduction module can also continuously optimize based on the data feedback of the base station behavior configured with parameters according to its own algorithm, autonomously learn, continuously optimize the optimal solution, allocate slice resources more reasonably, and effectively improve the slice configuration performance of the base station.

[0043] In addition, the present application also provides corresponding implementation devices, electronic devices, readable storage media, and access network systems for the method of generating a slice data reference set of the access network wireless intelligent slicing system, further making the method more practical, and the devices, electronic devices, readable storage media, and access network systems have corresponding advantages.

[0044] It should be understood that the above general description and the following detailed description are only exemplary and do not limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0046] Figure 1 Schematic flow chart of a method for generating a slice data reference set of an access network wireless intelligent slicing system provided by an embodiment of the present invention;

[0047] Figure 2 Structural diagram of a specific implementation manner of a device for generating a slice data reference set of an access network wireless intelligent slicing system provided by an embodiment of the present invention;

[0048] Figure 3 Structural diagram of a specific implementation manner of an electronic device provided by an embodiment of the present invention;

[0049] Figure 4 Structural diagram of a specific implementation manner of an access network system provided by an embodiment of the present invention;

[0050] Figure 5 Frame schematic diagram of an exemplary application scenario provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0052] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may include steps or units not listed. The various non-limiting embodiments of this application will be described in detail below.

[0053] First, refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for generating a slice data reference set of a slice in an access network wireless intelligent slice system provided by an embodiment of the present invention. The wireless intelligent slice system analyzes and processes the real-time slice data reported by the base station by using a slice configuration model trained based on an artificial intelligence algorithm to obtain the configuration information of the corresponding slice resources. For the sake of easy description and without causing ambiguity, the configuration information of the slice resources sent by the wireless intelligent slice system to the base station is called slice deduction configuration information. The base station allocates corresponding resource blocks to each slice based on the received slice deduction configuration information. It can be understood that the training of the slice configuration model requires a large amount of sample data, and the sample data is the data in the intelligent learning database. In the related art, the data in the intelligent learning library includes slice deduction configuration information and the data generated by the base station when operating under the slice deduction configuration information; since all the data in the intelligent learning library comes from the data generated by the base station in the normal working state, it takes a lot of time to achieve good results in both data expansion and data completeness of the intelligent learning database. In order to quickly and completely generate the slice data reference set, the base station of this application actively traverses and runs according to the slice type within the resource range of the resource block, records and reports the relevant data of the base station and the slice index parameters in response, that is, most of the data in the intelligent learning database of the wireless intelligent slice system comes from the data collected during the self-traversal operation of the base station, and may include the following content:

[0054] S101: When receiving the self-traversal instruction, switch to the slice traversal mode.

[0055] It can be understood that the base station is usually in a normal working state, that is, reporting slice real-time data to the wireless intelligent slice system and allocating corresponding resources for each slice based on the resource configuration information of the slice fed back by the wireless intelligent slice system. In this embodiment, the base station can be triggered to switch from the normal working state to the slice traversal mode through a self-traversal instruction. The slice traversal mode is that the base station periodically traverses the configurations of the slices by itself and records the base station status information and slice parameter information under each slice configuration. The self-traversal instruction can be flexibly selected according to the actual application scenario. For example, it can be an instruction input by the user through the human-computer interaction module, an instruction issued by setting a button or a key on the base station, or a built-in automatic trigger instruction, such as triggering once every three days at a certain time period at night. This does not affect the implementation of this application.

[0056] S102: In the slice traversal mode, automatically set multiple different resource configuration conditions for each slice to be configured based on the slice configuration information, and drive the base station to run under each set of resource configuration conditions of each slice to be configured, and obtain the base station status information and slice parameter information of all slices to be configured under different resource configuration conditions.

[0057] When the base station is triggered to switch to the slice traversal mode, it will obtain slice configuration information, which is the basic information for self-configuring resources for each slice to be configured. For example, it includes but is not limited to the traversal period, the total number of slices to be configured, the total number of resource blocks, the resource block configuration range for each slice to be configured, and the initial configuration value. Among them, the traversal period is the number of cycles for the base station to set resource configuration conditions for each slice to be configured in the current slice traversal mode. The total number of resource blocks is determined based on the actual network situation. For example, when the 5G NR has 30M subcarriers and 100M bandwidth, the total number of resource blocks is 273. The resource block configuration range refers to the range of resource blocks allocated to each slice to be configured, including the maximum configuration value and the minimum configuration value for each slice to be configured. The initial configuration value is the number of resource blocks configured for each slice to be configured in the initial state. Read the traversal period from the slice configuration information. In each traversal period, based on the slice configuration information, determine all resource block allocation schemes for each slice to be configured. After sequentially traversing all slices to be configured in this period, enter the next traversal period. The resource block allocation scheme is also the situation of the resource blocks that each slice to be configured may be allocated within the total number of resource blocks. After determining each resource allocation scheme, drive the base station to operate according to various possible resource configuration conditions, that is, the resource allocation scheme, and obtain and record the base station status information and slice parameter information under each resource allocation scheme. In this way, all slice configuration situations that meet the constraint conditions can be completely traversed, which is conducive to generating a complete slice data reference set. The so-called constraint conditions mean that the slice configuration conditions are subject to the slice configuration information. For example, the resource blocks allocated to all slices to be configured shall not exceed the total number of resource blocks, and the number of resource blocks allocated to each slice to be configured shall not be less than the minimum configuration value and shall not exceed the maximum configuration value. Among them, the base station status information includes nFAFI (Next generation Femtocell Application Programming Interface) messages. nFAFI is a new version of FAFI. FAFI defines the message channel between the small cell MAC (Media Access Control) and PHY (Physical), which is mainly used to implement the configuration management of PHY by MAC, the synchronization between MAC and PHY, and the time-slot-based scheduling function, corresponding to a set / group of standard message interaction processes. nFAFI defines a set of control messages and data exchange messages. Correspondingly, the base station status information may include various scheduling information transmitted between the MAC layer and the physical layer. The slice parameter information includes the time stamp, the number of slices, the slice ID, the uplink and downlink SINR corresponding to each slice ID, the actual average transmission rate (unit: kbps / s) of the uplink and downlink of each slice, the air interface delay, the rate satisfaction rate, the satisfaction rate of the air interface delay, and the resource block information of each slice configured last time.The so-called slice resource block information includes, but is not limited to, the number of resource blocks configured for each slice.

[0058] S103: Send the base station status information and slice parameter information to the intelligent learning database of the wireless intelligent slice system.

[0059] After obtaining the base station status information and slice parameter information of all slices to be configured under different resource configuration conditions in the previous step, send this data to the intelligent learning database of the wireless intelligent slice system as a slice data reference set for the artificial intelligence algorithm, that is, a training sample set for training the slice configuration model. Further, in order to make the intelligent learning database more complete, when the base station receives the slice deduction configuration information sent by the wireless intelligent slice system during normal operation, it can also send the slice deduction configuration information to the intelligent learning database.

[0060] In the technical solution provided in the embodiment of the present invention, by the base station periodically setting different resource configuration conditions for each slice by itself, and by traversing each slice to count the base station status information and slice parameter information in each cycle of slice change, the slice traversal of one cycle can reach the second level, and only one-tenth or even one-hundredth of the original time is required to loop through multiple cycles to generate a larger number of slice data, quickly and completely expanding the intelligent learning database of the artificial intelligence algorithm. In addition, as the data volume of the intelligent learning database continues to improve and grow, the more data samples are supplied to the slice training module of the wireless intelligent slice system, the more accurate the parameter configuration results output by the slice configuration model, and the slice deduction module can also continuously optimize according to the data feedback of the base station behavior configured by its own algorithm, autonomously learn, continuously optimize the optimal solution, more reasonably allocate slice resources, and effectively improve the slice configuration performance of the base station.

[0061] It should be noted that there is no strict order of execution between the steps in this application. As long as it conforms to the logical order, these steps can be executed simultaneously or in a certain preset order. Figure 1 It is only a schematic way and does not mean that it can only be in this order of execution.

[0062] In the above embodiment, there is no limitation on how to execute step S102. In this embodiment, an optional implementation manner of automatically setting multiple different resource configuration conditions for each slice to be configured based on the slice configuration information is given. For the sake of easy implementation, the slices to be configured can be divided into multiple first slices to be configured, multiple second slices to be configured, and multiple candidate slices to be configured based on the slice type. The following steps can be included in one traversal cycle:

[0063] A1: Divide the slices to be configured into multiple first slices to be configured, multiple second slices to be configured, and multiple candidate slices to be configured;

[0064] A2: Fix the resource block configuration values of each first slice to be configured to their respective initial configuration values, select one second slice to be configured from each of the second slices to be configured as the current second slice to be configured, set the resource block configuration value of the current second slice to be configured to increase by a first target number of resource blocks in each statistical period, and cycle through the slice configuration information to determine all resource block allocation schemes for the remaining second slices to be configured and each candidate slice to be configured in each statistical period;

[0065] A3: When the resource block configuration value of the current second slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each of the first slices to be configured as the current first slice to be configured, set the resource block configuration value of the current first slice to be configured to increase by a second target number of resource blocks in each statistical period, restore the resource block configuration values of each candidate slice to be configured, each second slice to be configured, and the remaining first slices to be configured to their respective initial configuration values, and repeat steps A2 and A3 until the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value;

[0066] A4: When the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value, select another first slice to be configured from each of the first slices to be configured as the current first slice to be configured and jump to execute A3 until the resource block configuration values of each first slice to be configured reach their corresponding maximum configuration values;

[0067] A5: Select another second slice to be configured from each of the second slices to be configured as the current second slice to be configured and jump to execute A2 until the resource block configuration values of each second slice to be configured reach their corresponding maximum configuration values.

[0068] In this embodiment, a traversal period includes five steps from A1 to A5. After each traversal period is completed, all slices to be configured can be reset to the initial state, and the number of slices to be configured and / or the initial configuration value of each slice to be configured and / or the minimum configuration value and maximum configuration value of each slice to be configured can be adjusted, and A1 - A5 are repeatedly executed for the next traversal. The statistical period in this embodiment refers to determining all resource allocation schemes for each slice to be configured under a fixed configuration condition, that is, executing step A2 once or executing step A3 once. For example, a statistical period is: when the resource block configuration values of each first slice to be configured are fixed to the corresponding initial configuration values, and the resource block configuration value of the current second slice to be configured is at the initial configuration value, all resource block allocation schemes for the remaining second slices to be configured and each candidate slice to be configured are determined based on the slice configuration information. The next statistical period is: when the resource block configuration values of each first slice to be configured are fixed to the corresponding initial configuration values, and the resource block configuration value of the current second slice to be configured is the initial configuration value + the number of resource blocks of the first target, all resource block allocation schemes for the remaining second slices to be configured and each candidate slice to be configured are determined based on the slice configuration information. When making an increase adjustment to each slice to be configured, it can be increased by a fixed value, such as increasing by one resource block each time, or it can be increased in an arithmetic progression, or randomly increased. The number of resource blocks of the first target and the number of resource blocks of the second target can be set to the same value or different values, which does not affect the implementation of this application.

[0069] To make those skilled in the art more clearly understand the technical solution of this embodiment, this embodiment also provides a schematic example. In this embodiment, the number of slices to be configured is n, and each slice to be configured is called N1, N2,... Nn. For the convenience of description, the number of resource blocks configured for each slice to be configured can be replaced by a number accordingly. That is, the number of resource blocks currently configured for slice to be configured N1 can be directly represented by N1. The upper and lower limits of the number of resource blocks of each slice to be configured are Nnl and Nnh respectively, and the total number of resource blocks of the base station is Nsum. For the application scenario of 5G NR 30M subcarriers and 100M bandwidth (the total number of resource blocks is 273, that is, Nsum = 273), it is necessary to simultaneously satisfy:

[0070] N1 + N2 + … + Nn <= Nsum = 273

[0071] N1l < N1 < N1h

[0072] N2l < N2 < N2h

[0073] …

[0074] Nnl < Nn < Nnh

[0075] N1h = Nsum - N2l - N3l … - Nnl

[0076] N2h = Nsum - N1l - N3l… - Nnl

[0077] …

[0078] Nnh = Nsum - N1l - N2l… - Nn - 1l

[0079] Among them, Nsum, N1l...Nnl, N1h..Nnh are all constants. In this embodiment, the implementation process of the above technical solution is described by taking the number of slices to be configured N = 4 as an example. In this embodiment, according to the slice type, the 4 slices to be configured are divided into: the first slice to be configured is N1 and N2, the second slice to be configured is N3, and the candidate slice to be configured is N4; for the convenience of description, the initial configuration values of the resource blocks of each slice to be configured are set as: N1 = N1l, N2 = N2l, N3 = N3l, N4 = Nsum - N1 - N2 - N3. Both the first target number of resource blocks and the second target number of resource blocks are set to 1. The process of automatically setting multiple different resource configuration conditions for each slice to be configured based on the slice configuration information may include:

[0080] Stage 1: The resource block resources of N1 and N2 are configured without change, that is, the configuration values of the resource blocks of N1 and N2 are set to the values in the initial state. N3 increases by 1 resource block in each statistical cycle, that is, N1 = N1l, N2 = N2l, N3 = N3 + 1, N4 = Nsum - N1 - N2 - N3. At this time, traverse all possible values of the resource blocks allocated to N3 and N4 when N1 and N2 are fixed (that is, N1 = N1l, N2 = N2l).

[0081] Stage 2: As the configuration value of the N3 resource block in Stage 1 is continuously incremented by 1, when the current resource block of N3 is configured to the maximum configuration value and the corresponding N4 is the minimum configuration value N4l, at this time when N3 = Nsum - N1 - N2 - N4l, adjust the configuration value of the resource block of N2 + 1, and at the same time restore N3 and N4 to the initial configuration values. Return to Stage 1, and at this time the initial values in Stage 1 are updated correspondingly to N1 = N1l, N2 = N2 + 1, N3 = N3l, N4 = Nsum - N1 - N2 - N3. Repeat the process of Stage 1 and Stage 2, that is, Stage 1 traverses all configurations of the N3 and N4 slices under the condition of N1 = N1l, N2 = N2l + 1. That is, it can realize traversing all possible values of the resource blocks allocated to N2, N3, and N4 when N1 is fixed (that is, N1 = N1l).

[0082] Phase 3: As the configuration value of the N2 resource block in Phase 2 is incremented by 1 continuously, when the current N2 resource block is configured to the maximum configuration value, that is, when the currently configurable resources reach the maximum value, at this time N2 = Nsum - N1 - N3l - N4l, modify the N1 configuration value +1, and at the same time restore N2, N3, and N4 to their initial configuration values. Return to Phase 1. At this time, the initial values in Phase 1 are updated correspondingly to N1 = N1 + 1, N2 = N2l, N3 = N3l, N4 = Nsum - N1 - N2 - N3. Traverse in the manner of Phase 1, then enter Phase 2, and then enter Phase 3. That is, repeat Phase 3, Phase 2, and Phase 1 until N1 increases to the maximum value and all feasible allocated resource block values of N1, N2, N3, and N4 are traversed.

[0083] Phase 4: When the value of N1 reaches the maximum configurable value, that is, N1 = N1h = Nsum - N2l - N3l - N4l, all possible resource block allocation values of the four slices have been traversed, and the slice configuration can be reset to the initial state to perform the next round of repeated traversal.

[0084] Record the base station status information and slice parameter information under each set of resource configuration conditions for each slice to be configured, and a complete slice data parameter set can be obtained.

[0085] In the actual implementation process, the implementation process of this embodiment can generate a corresponding computer program, embed this computer program into the processor of the base station, and the processor executes the corresponding content of this embodiment by calling this section of the computer program. The Slice1_num variable is defined as the number of resource blocks configured for the first slice, the Slice2_num variable is defined as the number of resource blocks configured for the second slice, the Slice3_num variable is defined as the number of resource blocks configured for the third slice, the Slice4_num variable is defined as the number of resource blocks configured for the fourth slice, and the Nsum variable represents the total number of resource blocks of the base station. The following is the computer program corresponding to quickly completing one cycle of traversal of 4 slices to be configured:

[0086]

[0087]

[0088] Among them, the bottom else branch corresponds to Phase 1, the penultimate else branch corresponds to Phase 2, the third-to-last else branch corresponds to Phase 3, and the first if corresponds to Phase 4.

[0089] This embodiment can achieve second-level traversal of slice configuration in a certain scenario, and then store and output the obtained data to the intelligent learning database of the wireless intelligent slice system, and a complete data set required by the slice training module in this scenario can be quickly and completely generated.

[0090] To further improve the generation efficiency of the slice data reference set, based on the above embodiments, it may further include:

[0091] Determine whether there is slice traversal interruption information; the slice traversal interruption information is the slice resource configuration stored when the base station interrupts the previous slice traversal mode;

[0092] If there is slice traversal interruption information, based on the slice traversal interruption information, continue to set corresponding resource configuration conditions for the slices to be configured that have not been traversed in the current cycle from the interruption position.

[0093] In this embodiment, the base station can record the traversal of each slice data to be configured into a file by text means, that is, the slice traversal interruption information can be stored in a specified file. Even if the base station is interrupted due to other factors (such as power failure and crash), after the base station is restarted and powered on next time, it can still obtain the data traversed last time by reading the file and then complete the traversal process, with strong stability and higher efficiency.

[0094] The embodiments of the present invention also provide corresponding devices for the method of generating the slice data reference set of the access network wireless intelligent slice system, all of which are applied to the base station, further making the method more practical. Among them, the device can be described from the perspective of functional modules and the perspective of hardware. The following introduces the device for generating the slice data reference set of the access network wireless intelligent slice system provided by the embodiments of the present invention. The device for generating the slice data reference set of the access network wireless intelligent slice system described below can be correspondingly referred to the method of generating the slice data reference set of the access network wireless intelligent slice system described above.

[0095] From the perspective of functional modules, see Figure 2 , Figure 2 which is the structural diagram of the device for generating the slice data reference set of the access network wireless intelligent slice system provided by the embodiments of the present invention in a specific implementation manner. The device may include:

[0096] A mode switching module 201, configured to switch to the slice traversal mode when receiving a self-traversal instruction;

[0097] A slice automatic configuration module 202, configured to automatically set multiple different resource configuration conditions for each slice to be configured based on the slice configuration information in the slice traversal mode, drive the base station to run under each set of resource configuration conditions of each slice to be configured respectively, and simultaneously obtain the base station status information and slice parameter information of all slices to be configured under different resource configuration conditions;

[0098] A data generation module 203, configured to send the base station status information and slice parameter information to the intelligent learning database of the wireless intelligent slice system.

[0099] Optionally, in some embodiments of this embodiment, the above slice automatic configuration module 202 can be used to: obtain slice configuration information; the slice configuration information includes a traversal period, the total number of slices to be configured, the total number of resource blocks, the resource block configuration range of each slice to be configured, and an initial configuration value; in each traversal period, based on the slice configuration information, determine all resource block allocation schemes for each slice to be configured.

[0100] As an optional implementation manner of the above embodiment, the above slice automatic configuration module 202 can be further used to:

[0101] A1: Divide each slice to be configured into multiple first slices to be configured, multiple second slices to be configured, and multiple candidate slices to be configured;

[0102] A2: Fix the resource block configuration value of each first slice to be configured to the corresponding initial configuration value, select one second slice to be configured from each second slice to be configured as the current second slice to be configured, set the resource block configuration value of the current second slice to be configured to increase by a first target number of resource blocks in each statistical period, and based on the slice configuration information, circularly determine all resource block allocation schemes of the remaining second slices to be configured and each candidate slice to be configured in each statistical period;

[0103] A3: When the resource block configuration value of the current second slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each first slice to be configured as the current first slice to be configured, set the resource block configuration value of the current first slice to be configured to increase by a second target number of resource blocks in each statistical period, restore the resource block configuration values of each candidate slice to be configured, each second slice to be configured, and the remaining first slices to be configured to the corresponding initial configuration values, and repeat steps A2 and A3 until the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value;

[0104] A4: When the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each first slice to be configured again as the current first slice to be configured and jump to execute A3 until the resource block configuration values of each first slice to be configured all reach the corresponding maximum configuration values;

[0105] A5: Select one second slice to be configured from each second slice to be configured again as the current second slice to be configured and jump to execute A2 until the resource block configuration values of each second slice to be configured all reach the corresponding maximum configuration values.

[0106] Optionally, in some other embodiments of this embodiment, the above slice automatic configuration module 202 can also be used to: determine whether there is slice traversal interruption information; the slice traversal interruption information is the slice resource configuration situation stored when the base station interrupts the previous slice traversal mode; if there is slice traversal interruption information, based on the slice traversal interruption information, continue to set corresponding resource configuration conditions for the slices to be configured that have not been traversed in the current cycle from the interruption position.

[0107] Optionally, in some other embodiments of this embodiment, the above device includes, for example, a deduced data sending module, configured to send the slice deduced configuration information to the intelligent learning database when receiving the slice deduced configuration information sent by the wireless intelligent slice system.

[0108] The functions of the functional modules of the slice data reference set generation device of the access network wireless intelligent slice system in the embodiments of the present invention can be specifically implemented according to the methods in the above method embodiments, and the specific implementation process can refer to the relevant descriptions in the above method embodiments, which will not be elaborated here.

[0109] As can be seen from the above, the embodiments of the present invention can quickly and completely establish the slice data reference set required for the access network wireless intelligent slice system.

[0110] The slice data reference set generation device of the access network wireless intelligent slice system mentioned above is described from the perspective of functional modules. Further, the present application also provides an electronic device, which is described from the perspective of hardware. Figure 3 It is a schematic structural diagram of the electronic device provided in an embodiment of the present application. As Figure 3 shown, the electronic device includes a memory 30 for storing a computer program; a processor 31 for implementing the steps of the method for generating the slice data reference set of the access network wireless intelligent slice system as mentioned in any of the above embodiments when executing the computer program.

[0111] Among them, the processor 31 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 31 may also be a controller, a microcontroller, a microprocessor, or other data processing chips, etc. The processor 31 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 31 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 31 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 31 may also include an AI (Artificial Intelligence) processor, and the AI processor is used to process computational operations related to machine learning.

[0112] The memory 30 may include one or more computer-readable storage media, which may be non-transitory. The memory 30 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. The memory 30 may be an internal storage unit of an electronic device in some embodiments, such as the hard disk of a server. The memory 30 may also be an external storage device of an electronic device in other embodiments, such as a plug-in hard disk equipped on a server, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 30 may include both an internal storage unit and an external storage device of the electronic device. The memory 30 can be used not only to store application software installed on the electronic device and various types of data, such as the code of a program during the execution of the method for generating the slice data reference set of the access network wireless intelligent slicing system, but also to temporarily store data that has been output or will be output. In this embodiment, the memory 30 is at least used to store the following computer program 301. After the computer program is loaded and executed by the processor 31, it can implement the relevant steps of the method for generating the slice data reference set of the access network wireless intelligent slicing system disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 30 may also include an operating system 302 and data 303, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 302 may include Windows, Unix, Linux, etc. The data 303 may include, but is not limited to, data corresponding to the generation result of the slice data reference set of the access network wireless intelligent slicing system, etc.

[0113] In some embodiments, the above-mentioned electronic device may further include a display screen 32, an input / output interface 33, a communication interface 34 or a network interface, a power supply 35, and a communication bus 36. Among them, the display screen 32 and the input / output interface 33, such as a keyboard, belong to user interfaces. Optional user interfaces may also include standard wired interfaces, wireless interfaces, etc. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. The display may also be appropriately referred to as a display screen or a display unit, and is used to display the information processed in the electronic device and to display a visual user interface. The communication interface 34 may optionally include a wired interface and / or a wireless interface, such as a WI-FI interface, a Bluetooth interface, etc., and is generally used to establish a communication connection between the electronic device and other electronic devices. The communication bus 36 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus may be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 3 it is only represented by a thick line in the figure, but it does not mean that there is only one bus or one type of bus.

[0114] Those skilled in the art can understand that Figure 3 the structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than those shown in the figure. For example, it may further include sensors 37 for implementing various functions.

[0115] The functions of the functional modules of the electronic device according to the embodiments of the present invention can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can refer to the relevant descriptions in the above method embodiments, and will not be elaborated here.

[0116] As can be seen from the above, the embodiments of the present invention can quickly and completely establish a slice data reference set required for an access network wireless intelligent slice system.

[0117] It can be understood that if the method for generating the slice data reference set of the access network wireless intelligent slice system in the above embodiments is implemented in the form of software functional units and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods in the various embodiments of the present application. The foregoing storage medium includes: USB flash drive, mobile hard disk, read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM, register, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, removable disk, CD-ROM, magnetic disk or optical disk, etc., which can store program codes of various kinds.

[0118] Based on this, the embodiment of the present invention further provides a readable storage medium, storing a computer program, and when the computer program is executed by a processor, it performs the steps of the method for generating the slice data reference set of the access network wireless intelligent slice system in any one of the above embodiments.

[0119] The embodiment of the present invention further provides an access network system. Please refer to Figure 4 , and it may include:

[0120] The access network system may include a base station 401 and a wireless intelligent slice system 402. The base station 401 and the wireless intelligent slice system 402 transmit data and instructions through a communication interface such as E2AP (E2 Application Protocol, base station application program interface).

[0121] The base station 401 in this embodiment is used to implement the steps of the method for generating the slice data reference set of the access network wireless intelligent slice system recorded in any one of the above embodiments; the wireless intelligent slice system 402 is used to use all the base station status information and all the slice parameter information sent by the base station as a slice data reference set, and train a slice configuration model based on artificial intelligence algorithms such as artificial neural network algorithms, convolutional neural network algorithms, deep neural network algorithms, etc. The generation of the slice data reference set only requires the participation of the intelligent learning database of the base station and the wireless intelligent slice system, and does not require other functional modules of the wireless intelligent slice system to be started.

[0122] For the wireless intelligent slice system 402, such as Figure 5As shown, it may include an intelligent learning database, a slice training module, a slice deduction module, a data processing module, and an instruction management module. The intelligent learning database and the slice training module and the slice deduction module can be deployed in a combined manner or in a distributed cluster, and then provide data communication support through a high-speed network or an optical port, which does not affect the implementation of this application.

[0123] The base station 401 is further configured to send real-time slice statistical data and FAPI interface data to the data processing module through a communication interface. The data processing module, for example, can be a UEDM (User Data Management) module, and can be used to process the real-time slice statistical data and FAPI (a standard defined by the small cell alliance) interface data, such as performing operations such as extraction, management, encapsulation, and unpacking on the received data to obtain a data processing result, and then sending the data processing result to the slice deduction module. The slice training module is used to train a slice configuration model based on the intelligent learning database; the slice deduction module is used to call the slice configuration model to calculate the data processing result to obtain slice deduction configuration information, and send the slice deduction configuration information to the instruction management module; the instruction management module, for example, can be a UERM (User Resource Manager) module, and is used to generate slice configuration instructions based on the slice deduction configuration information and send them to the base station through a communication interface. The intelligent learning database can be, for example, a Redis database, or other high-efficiency read-write databases can also be used. The intelligent learning database needs to meet a certain timeliness, and it is required that the replacement database read-write efficiency reaches 8000 records / second at best.

[0124] Figure 5Among them, the gNB is a 5G NR base station, representing the object of the wireless intelligent slice service. The E2AP interface is the communication interface between the wireless intelligent slice system and the base station. The UEDM module extracts, manages, encapsulates, and unpacks data; the UERM module is responsible for the management of control instructions; the slice deduction module receives the slice-related data information uploaded by the base station in real time and deduces the real-time slice configuration information; the slice training module trains the slice configuration model according to the big data of the base station stored in the database and continuously updates and improves the training model according to the changes in the Redis database data. The base station reports the real-time slice statistical data and FAPI interface data to the E2AP and Redis databases. The FAPI interface is located inside the gNB-DU and is the interface standard between the MAC layer and the physical layer. The data type of the real-time slice statistical data of the base station can be the custom SLICEINFO and uses the TLV format (TLV format data refers to the data composed of Tag, Length, and Value). The corresponding message body includes the timestamp, the number of slices, the slice ID, and the uplink and downlink SINR, slice rate, slice rate satisfaction rate, slice air interface delay, slice delay satisfaction rate, and the number of RBs configured last time corresponding to the slice ID. The slice configuration information sent to the base station through the UERM can also use the TLV format, and the message body can include the number of configured slices, the slice ID, and the number of RBs corresponding to the slice ID.

[0125] The accuracy of the configuration result of slice deduction is determined by the rationality of the slice training model parameters, which is trained by the artificial intelligence learning framework according to the data in the Redis database. Therefore, it is crucial to have a complete and sound large database. Running the gNB for a long time to enrich the database can achieve certain effects, but it is difficult to guarantee both the timeliness of data collection and the completeness of the data set. In this implementation, by the method of the base station periodically changing the slice allocation and traversing the slice configuration by itself, the base station information and SLICEINFO statistical parameters in each cycle of slice change are counted and stored in the Redis database as the slice data reference set. At the same time, considering the shutdown problem of the base station system, the currently traversed configuration will be saved to a file, and the base station will continue to traverse based on the previous configuration when it is restarted next time.

[0126] The functions of the functional modules of the access network system in the embodiments of the present invention can be specifically implemented according to the methods in the above method embodiments. The specific implementation process can refer to the relevant descriptions of the above method embodiments and will not be elaborated here.

[0127] As can be seen from the above, this embodiment can quickly, completely, and stably obtain a large amount of learning data required for the training of the slice training module, optimize the slice management of the base station, and the wireless intelligent slice system can learn autonomously and continuously evolve to continuously update and approach the optimal solution for slice allocation in different times and occasions.

[0128] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the hardware, including devices and electronic equipment, disclosed in the embodiments, since it corresponds to the methods disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description in the method section.

[0129] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0130] The above has introduced in detail a method, apparatus, electronic device, readable storage medium, and access network system for generating a slice data reference set of an access network wireless intelligent slice system provided in this application. Specific examples are used herein to elaborate on the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements and modifications can still be made to this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for generating a slice data reference set of an access network wireless intelligent slice system, characterized in that, Applied to a base station, including: When receiving a self-traversing instruction, switch to the slice traversing mode; In the slice traversing mode, automatically set multiple different resource configuration conditions for each slice to be configured based on the slice configuration information, and drive the base station to operate under each set of resource configuration conditions of each slice to be configured respectively, and simultaneously obtain the base station status information and slice parameter information of all slices to be configured under different resource configuration conditions; Send the base station status information and the slice parameter information to the intelligent learning database of the wireless intelligent slice system; Among them, the automatically setting multiple different resource configuration conditions for each slice to be configured based on the slice configuration information includes: A1: Divide each slice to be configured into multiple first slices to be configured, multiple second slices to be configured, and multiple candidate slices to be configured; A2: Fix the resource block configuration value of each first slice to be configured to the corresponding initial configuration value, select one second slice to be configured from each second slice to be configured as the current second slice to be configured, set the resource block configuration value of the current second slice to be configured to increase by the first target number of resource blocks in each statistical period, and based on the slice configuration information, cycle through to determine all resource block allocation schemes of the remaining second slices to be configured and each candidate slice to be configured in each statistical period; A3: When the resource block configuration value of the current second slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each first slice to be configured as the current first slice to be configured, set the resource block configuration value of the current first slice to be configured to increase by the second target number of resource blocks in each statistical period, restore the resource block configuration values of each candidate slice to be configured, each second slice to be configured, and the remaining first slices to be configured to the corresponding initial configuration values, and repeat steps A2 and A3 until the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value; A4: When the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each first slice to be configured again as the current first slice to be configured and jump to execute A3 until the resource block configuration values of each first slice to be configured all reach the corresponding maximum configuration values; A5: Select one second slice to be configured from each second slice to be configured again as the current second slice to be configured and jump to execute A2 until the resource block configuration values of each second slice to be configured all reach the corresponding maximum configuration values.

2. The method for generating a slice data reference set of an access network wireless intelligent slice system according to claim 1, characterized in that, The automatically setting multiple different resource configuration conditions for each slice to be configured based on the slice configuration information includes: Obtain the slice configuration information; the slice configuration information includes the traversing period, the total number of slices to be configured, the total number of resource blocks, the resource block configuration range and the initial configuration value of each slice to be configured; In each traversing period, determine all resource block allocation schemes for each slice to be configured based on the slice configuration information.

3. The method for generating a slice data reference set of an access network wireless intelligent slice system according to claim 1 or 2, characterized in that, The automatically setting multiple different resource configuration conditions for each slice to be configured based on the slice configuration information further includes: Determine whether there is slice traversal interruption information; the slice traversal interruption information is the slice resource configuration stored when the base station interrupts the previous slice traversal mode. If there is the slice traversal interruption information, based on the slice traversal interruption information, continue to set corresponding resource configuration conditions for the un-traversed slices to be configured in the current cycle from the interruption position.

4. The method for generating a slice data reference set of an access network wireless intelligent slice system according to claim 3, characterized in that, It further includes: When receiving the slice deduction configuration information sent by the wireless intelligent slice system, send the slice deduction configuration information to the intelligent learning database.

5. A device for generating a slice data reference set of an access network wireless intelligent slice system, characterized in that, Applied to the base station, it includes: A mode switching module, used to switch to the slice traversal mode when receiving the self-traversal instruction. A slice automatic configuration module, used to automatically set multiple different resource configuration conditions for each slice to be configured based on the slice configuration information in the slice traversal mode, and drive the base station to run under each set of resource configuration conditions of each slice to be configured respectively, and simultaneously obtain the base station status information and slice parameter information of all slices to be configured under different resource configuration conditions. A data generation module, used to send the base station status information and the slice parameter information to the intelligent learning database of the wireless intelligent slice system. Among them, the slice automatic configuration module is further used for: A1: Divide each slice to be configured into multiple first slices to be configured, multiple second slices to be configured, and multiple candidate slices to be configured. A2: Fix the resource block configuration value of each first slice to be configured to the corresponding initial configuration value, select one second slice to be configured from each second slice to be configured as the current second slice to be configured, set the resource block configuration value of the current second slice to be configured to increase the first target number of resource blocks in each statistical cycle, and based on the slice configuration information, circularly determine all resource block allocation schemes of the remaining second slices to be configured and each candidate slice to be configured in each statistical cycle. A3: When the resource block configuration value of the current second slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each first slice to be configured as the current first slice to be configured, set the resource block configuration value of the current first slice to be configured to increase the second target number of resource blocks in each statistical cycle, restore the resource block configuration values of each candidate slice to be configured, each second slice to be configured, and the remaining first slices to be configured to the corresponding initial configuration values, and repeat steps A2 and A3 until the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value. A4: When the resource block configuration value of the current first slice to be configured reaches the corresponding maximum configuration value, select one first slice to be configured from each first slice to be configured again as the current first slice to be configured and jump to execute A3 until the resource block configuration values of each first slice to be configured reach the corresponding maximum configuration values. A5: Select one second slice to be configured from each second slice to be configured again as the current second slice to be configured and jump to execute A2 until the resource block configuration values of each second slice to be configured reach the corresponding maximum configuration values.

6. An electronic device, characterized in that, Applied to a base station, including a processor and a memory, the processor is configured to implement the steps of the method for generating a slice data reference set of the access network wireless intelligent slice system according to any one of claims 1 to 4 when executing a computer program stored in the memory.

7. A readable storage medium, characterized in that, Applied to a base station, a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the steps of the method for generating a slice data reference set of the access network wireless intelligent slice system according to any one of claims 1 to 4 are implemented.

8. An access network system, characterized in that, Including a base station and a wireless intelligent slice system; The base station and the wireless intelligent slice system transmit data and instructions through a communication interface; The base station is configured to implement the steps of the method for generating a slice data reference set of the access network wireless intelligent slice system according to any one of claims 1 to 4; The wireless intelligent slice system is configured to use all base station status information and all slice parameter information sent by the base station as a slice data reference set to train a slice configuration model based on an artificial intelligence algorithm.

9. The access network system according to claim 8, characterized in that, The wireless intelligent slice system includes an intelligent learning database, a slice training module, a slice deduction module, a data processing module, and an instruction management module; The base station is further configured to send real-time slice statistical data and FAPI interface data to the data processing module through the communication interface; The data processing module is configured to process the real-time slice statistical data and the FAPI interface data, and send the data processing result to the slice deduction module; The slice training module is configured to train the slice configuration model based on the intelligent learning database; The slice deduction module is configured to call the slice configuration model to calculate the data processing result, obtain slice deduction configuration information, and send the slice deduction configuration information to the instruction management module; The instruction management module is configured to generate a slice configuration instruction based on the slice deduction configuration information and send it to the base station through the communication interface.

Images