Digital twinning method for communication system, communication device, and readable storage medium

Abstract

The present application relates to the technical field of software, and in particular to a digital twinning method for a communication system, a communication device, and a storage medium. The digital twinning method comprises: on the basis of a target test scenario corresponding to a communication system, acquiring static communication data of the communication system, wherein the static communication data is historical communication data of the communication system; determining dynamic communication data; and inputting the static communication data and the dynamic communication data into an initial mirror system to obtain a twin mirror system corresponding to the communication system.

Description

Digital twin method of communication system, communication device and readable storage medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application No. 202310764719.1 filed on June 26, 2023, the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present application relates to the field of software technology, and in particular to a digital twin method, communication device, and computer-readable storage medium for a communication system. Background Art

[0004] Currently, in the software design, development, and testing process, to conserve manpower and resources, it is often necessary to build a digital twin system that simulates an existing communication system for R&D and testing. Related technologies typically use the communication system to generate simulation data based on protocols or theoretical logic, analyze the simulation data to obtain twin data, and finally construct the digital twin system based on the twin data. This protocol- or algorithm-based digital twin system is a very simplified data model, containing only data from a single theoretical logic. Therefore, in practical applications, this simulation system cannot simulate and analyze complex scenarios and is not very applicable.

[0005] Therefore, how to improve the applicability of digital twin systems has become an urgent problem that needs to be solved.

[0006] Summary of the Invention

[0007] The present application provides a digital twin method, communication device, and computer-readable storage medium for a communication system. By acquiring static communication data of the communication system based on a target test scenario corresponding to the communication system, and simulating dynamic communication data based on the static communication data, a twin mirror system is constructed based on the static communication data and the dynamic communication data. The twin mirror system can not only simulate various complex test scenarios, but also simulate feedback scenarios after data changes, thereby improving the applicability of the twin mirror system.

[0008] In the first aspect, the present application provides a digital twin method for a communication system, the method comprising: obtaining static communication data of the communication system based on a target test scenario corresponding to the communication system, the static communication data being the historical communication data of the communication system; determining dynamic communication data, the dynamic communication data being the communication data constructed based on the static communication data; and inputting the static communication data and the dynamic communication data into a preset initial mirror system to obtain a twin mirror system corresponding to the communication system.

[0009] In a second aspect, the present application also provides a communication device, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the digital twin method of the communication system as described above when executing the computer program.

[0010] In a third aspect, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor enables the processor to implement the digital twin method of the communication system as described above.

[0011] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0013] FIG1 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0014] FIG2 is a schematic flow chart of a digital twin method for a communication system provided in an embodiment of the present application;

[0015] FIG3 is a schematic flowchart of sub-steps for obtaining static communication data provided in an embodiment of the present application;

[0016] FIG4 is a schematic flow chart of sub-steps for collecting communication data provided in an embodiment of the present application;

[0017] FIG5 is a schematic flow chart of sub-steps of data cleaning provided in an embodiment of the present application;

[0018] FIG6 is a schematic flowchart of sub-steps for determining dynamic communication data provided in an embodiment of the present application;

[0019] FIG7 is a schematic scenario diagram of a digital twin method for a communication system provided in an embodiment of the present application;

[0020] Figure 8 is a schematic scenario diagram of another digital twin method for a communication system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0022] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0023] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0026] In the subsequent description, suffixes such as "module," "component," or "unit" used to represent elements are used only to facilitate the description of the present application and have no specific meaning. Therefore, "module," "component," or "unit" may be used interchangeably.

[0027] Embodiments of the present application provide a digital twin method, communication device, and computer-readable storage medium for a communication system. The digital twin method can be applied to a communication device to obtain static communication data of the communication system based on a target test scenario corresponding to the communication system, and simulate dynamic communication data based on the static communication data, thereby constructing a twin mirror system based on the static and dynamic communication data. This allows the twin mirror system to simulate not only various complex test scenarios but also feedback scenarios after data changes, thereby improving the applicability of the twin mirror system.

[0028] For example, the communication device may include a server or a terminal. The server may be a single server or a server cluster. The terminal may be an electronic device such as a smartphone, tablet computer, laptop computer, or desktop computer.

[0029] The communication system in the embodiment of the present application may be various systems, such as a 4G communication system, a 5G communication system, etc. The communication system may include multiple physical network elements.

[0030] Exemplarily, a 4G communication system may include network elements such as a network management server, a terminal, a base station, and a gateway, wherein the network management server may serve as the executor of the digital twin method of the communication system provided in the embodiment of the present application.

[0031] Please refer to Figure 1, which is a schematic diagram of the structure of a communication device 10 provided in an embodiment of the present application. The communication device 10 may include a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 may be connected via a bus, such as an Inter-Integrated Circuit (I2C) bus or any other suitable bus.

[0032] The memory 1002 may include a storage medium and an internal memory. The storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to execute the digital twin method described in any embodiment.

[0033] The processor 1001 is used to provide computing and control capabilities to support the operation of the entire communication device 10.

[0034] The processor 1001 may be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or any conventional processor.

[0035] In one embodiment, the processor 1001 is configured to run a computer program stored in the memory 1002 to implement the following steps:

[0036] Based on the target test scenario corresponding to the communication system, obtain the static communication data of the communication system, which is the historical communication data of the communication system; determine the dynamic communication data, which is the communication data constructed based on the static communication data; input the static communication data and the dynamic communication data into the preset initial mirror system to obtain the twin mirror system corresponding to the communication system.

[0037] In one embodiment, when implementing a target test scenario corresponding to the communication system and acquiring static communication data of the communication system, the processor 1001 is configured to implement:

[0038] Based on a preset collection strategy, historical communication data of the communication system is collected to obtain a first communication data set; data cleaning is performed on the first communication data set to obtain a second communication data set; based on a target test scenario, communication data matching the target test scenario is extracted from the second communication data set to obtain static communication data.

[0039] In one embodiment, when the processor 1001 collects historical communication data of the communication system based on a preset collection strategy to obtain a first communication data set, it is configured to implement:

[0040] The historical communication data is collected according to the preset target data type to obtain the initial communication data; the initial communication data is labeled according to the preset key elements and key events to obtain the target communication data with the label; and the first communication data set is determined based on the target communication data with the label.

[0041] In one embodiment, the first communication data set includes a plurality of target communication data carrying tags; when the processor 1001 performs data cleaning on the first communication data set to obtain the second communication data set, it is configured to implement:

[0042] According to the label carried by each target communication data, the abnormality type corresponding to each target communication data is determined; based on the correspondence between the preset cleaning strategy and the abnormality type, the target cleaning strategy corresponding to each target communication data is determined according to the abnormality type corresponding to each target communication data; data cleaning is performed on each corresponding target communication data according to the target cleaning strategy corresponding to each target communication data to obtain a second communication data set.

[0043] In one embodiment, when determining the abnormality type corresponding to each target communication data according to the tag carried by each target communication data, the processor 1001 is configured to implement:

[0044] The key element tags and key event tags carried by each target communication data are obtained; the target communication data whose key element tags and / or key event tags meet the preset abnormal conditions are marked to obtain the target communication data carrying the abnormal tags; the target communication data that does not carry the abnormal tags are determined as non-abnormal data; the target communication data that carries a single abnormal tag is determined as the first type of abnormal data; and the target communication data that carries at least two abnormal tags is determined as the second type of abnormal data.

[0045] In one embodiment, when the processor 1001 performs data cleaning on each target communication data according to the target cleaning strategy corresponding to each target communication data to obtain the second communication data set, it is configured to implement:

[0046] The non-abnormal data is filtered according to a preset filtering ratio to obtain a first subset data set; the first type of abnormal data and the second type of abnormal data are retained to obtain a second subset data set; and a second communication data set is determined based on the first subset data set and the second subset data set.

[0047] In one embodiment, the target test scenario includes target key elements, target key events, target occurrence time, and target noise; when the processor 1001 extracts communication data matching the target test scenario from the second communication data set based on the target test scenario to obtain static communication data, it is configured to implement:

[0048] Communication data in the second communication data set that matches the target key element, the target key event, the target occurrence time, and the target noise is determined as static communication data.

[0049] In one embodiment, when determining dynamic communication data, the processor 1001 is configured to implement:

[0050] The configuration data and the working parameter data in the static communication data are eliminated to obtain the static communication data after the data is eliminated; the occurrence time in the static communication data after the data is eliminated is updated to obtain the static communication data after the time is updated; and the dynamic communication data is determined according to the static communication data after the time is updated.

[0051] Some embodiments of the present application are described in detail below in conjunction with the accompanying drawings. The following embodiments and features in the embodiments may be combined with each other unless they conflict. Please refer to Figure 2, which is a schematic flow chart of a digital twin method for a communication system provided in an embodiment of the present application. As shown in Figure 2, the digital twin method for a communication system includes steps S101 to S103.

[0052] Step S101: Based on a target test scenario corresponding to the communication system, static communication data of the communication system is obtained, where the static communication data is historical communication data of the communication system.

[0053] In some embodiments, static communication data of the communication system may be acquired based on a target test scenario corresponding to the communication system, wherein the static communication data is historical communication data of the communication system.

[0054] For example, historical communication data of the communication system within the same time period under the target test scenario can be collected as static communication data. Test scenarios may include, but are not limited to, cell handover, cell network quality testing, communication interference, cell anomalies, or optical module failures. For example, historical communication data of the communication system within the same time period under the cell handover scenario can be collected.

[0055] In the embodiments of the present application, communication data may include configuration data, alarm data, performance data, operating parameter data, diagnostic data, and network element logs. Configuration data refers to the configuration data of network elements in a wireless network, such as base station configuration data. Alarm data refers to alarm data generated by network elements during operation. Performance data refers to data related to wireless network performance generated by network elements during operation. Operating parameter data refers to network engineering parameters. Diagnostic data refers to real-time diagnostic data of network elements. Network element logs refer to configuration changes of network elements during operation.

[0056] In the above embodiment, by obtaining static communication data of the communication system based on the target test scenario corresponding to the communication system, static communication data under various complex test scenarios can be obtained. Subsequently, a twin mirror system can be constructed based on the static communication data, so that the twin mirror system can simulate various complex test scenarios.

[0057] Step S102: Determine dynamic communication data, where the dynamic communication data is communication data constructed based on static communication data.

[0058] In an embodiment of the present application, in order to enable the twin mirror system to simulate the feedback scenario after data changes, it is necessary to construct some dynamic communication data that changes with time to build the twin mirror system.

[0059] For example, dynamic communication data can be constructed based on static communication data. Static communication data refers to communication data of a communication system at a historical moment, while dynamic communication data refers to communication data that changes over time in a simulated communication system.

[0060] For example, static communication data can be removed from the data that doesn't change over time, and dynamic communication data can be constructed from the remaining data. Configuration data and engineering parameter data in static communication data are preconfigured and remain largely unchanged during network element operation. However, alarm data, performance data, diagnostic data, and network element logs in static communication data are continuously generated or updated during network element operation. Therefore, configuration data and engineering parameter data can be removed from the static communication data, and dynamic communication data can be constructed from the alarm data, performance data, diagnostic data, and network element logs in the static communication data.

[0061] In the above embodiment, by constructing dynamic communication data based on static communication data, communication data that changes over time can be obtained. The dynamic communication data is similar to the static communication data, and both are communication data of the communication system under the target test scenario. Subsequently, a twin mirror system can be conveniently constructed based on the dynamic communication data and the static communication data to avoid inconsistent data types.

[0062] Step S103: Input the static communication data and the dynamic communication data into a preset initial mirror system to obtain a twin mirror system corresponding to the communication system.

[0063] In some embodiments, after acquiring static communication data of a communication system and determining dynamic communication data, the static communication data and the dynamic communication data may be input into a preset initial mirror system to obtain a twin mirror system corresponding to the communication system.

[0064] The preset initial mirror system refers to a simulation system that has not yet been fed with communication data. In embodiments of the present application, a blank simulation system can be pre-designed. This blank simulation system can only begin operating after communication data is fed into it. The initial mirror system can include multiple virtual network elements, each of which has the same functionality as a corresponding physical network element in the communication system.

[0065] Exemplarily, an initial mirror system may be loaded from a memory, and then static communication data and dynamic communication data may be input into the initial mirror system to obtain a twin mirror system corresponding to the communication system.

[0066] In the above embodiment, by inputting static communication data and dynamic communication data into the initial mirror system, a twin mirror system can be constructed based on the static communication data and dynamic communication data, so that the twin mirror system can not only simulate various complex test scenarios, but also simulate feedback scenarios after data changes, thereby improving the applicability of the twin mirror system.

[0067] Please refer to Figure 3, which is a schematic flowchart of the sub-steps of obtaining static communication data provided in an embodiment of the present application. In step S101, the static communication data of the communication system is obtained based on the target test scenario corresponding to the communication system, which may include the following steps S201 to S203.

[0068] Step S201: Based on a preset collection strategy, historical communication data of a communication system is collected to obtain a first communication data set.

[0069] In the embodiment of the present application, in order to collect the communication data required to build a twin mirror system, it is necessary to collect communication data based on a preset collection strategy. The collection strategy may include collecting communication data corresponding to the target data type and collecting communication data containing key elements and key events.

[0070] Target data types can include configuration data, alarm data, performance data, engineering parameter data, diagnostic data, and network element logs. Key elements refer to target network elements, target data types, and networking types. Target network elements can include 4G and 5G network elements, for example; target data types can include 700 MHz network elements, for example; and networking types can include remote radio units, for example. Key events refer to whether desired events occur during communication data collection. Examples include interference events, cell outages, and coverage issues in certain cells.

[0071] Exemplarily, when collecting historical communication data of a communication system, the historical communication data can be collected based on the target data type, key elements, and key events to obtain a first communication data set. For example, when the target data type is diagnostic data, the key element is a 4G network element, and the key event is a coverage event, diagnostic data containing 4G network elements and coverage events in the historical communication data can be collected. For another example, when the target data type is alarm data, the key element is a 700Mhz network element, and the key event is an uplink interference event, alarm data containing 700Mhz network elements and uplink interference events in the historical communication data can be collected.

[0072] In the above embodiment, by collecting historical communication data of the communication system based on a preset collection strategy, the communication data required for building a twin mirror system can be collected, and irrelevant data can be avoided.

[0073] Step S202: Clean the first communication data set to obtain a second communication data set.

[0074] In some embodiments, after collecting historical communication data of the communication system to obtain a first communication data set, data cleaning may be performed on the communication data in the first communication data set to obtain a second communication data set.

[0075] In the embodiment of the present application, data cleaning refers to cleaning useless communication data according to the abnormality type of the communication data, wherein different abnormality types correspond to different cleaning strategies.

[0076] Exemplarily, each communication data in the first communication data set may be cleansed according to a cleaning strategy corresponding to an abnormality type to which each communication data in the first communication data set belongs, to obtain a second communication data set.

[0077] In the above embodiment, relatively pure scene data can be obtained by performing data cleaning on the first communication data set.

[0078] Step S203: Based on the target test scenario, extract communication data matching the target test scenario from the second communication data set to obtain static communication data.

[0079] Illustratively, after performing data cleaning on the first communication data set to obtain the second communication data set, communication data matching the target test scenario can be extracted from the second communication data set based on the target test scenario to obtain static communication data.

[0080] In some embodiments, the target test scenario may include target key elements, target key events, target occurrence time, and target noise. Based on the target test scenario, extracting communication data matching the target test scenario from the second communication data set to obtain static communication data may include: determining communication data matching the target key elements, target key events, target occurrence time, and target noise in the second communication data set as the static communication data.

[0081] For example, when the target test scenario is a 5G network element device detection scenario, the target key elements can be the 5G network, location, time, etc., the target key events can be optical module failure, optical link failure, etc., and the target occurrence time can be set according to the actual situation. The target noise data can also be set according to the actual situation.

[0082] For example, the target test scenarios are shown in Table 1.

[0083] Table 1

[0084] For example, the communication data in which the target key element is the 5G network, the target key event is the optical module failure, and the noise data is busy white noise in the second communication data set can be determined as static communication data.

[0085] The above embodiment extracts communication data that matches the target test scenario from the second communication data set based on the target test scenario, and thus obtains static communication data that matches the target key elements, target key events, target occurrence time, and target noise required for the target test scenario. This allows the twin mirror system subsequently constructed based on the static communication data to simulate various complex test scenarios, thereby improving the applicability of the twin mirror system.

[0086] Please refer to Figure 4, which is a schematic flowchart of the sub-steps of collecting communication data provided in an embodiment of the present application. In step S201, based on a preset collection strategy, historical communication data of the communication system is collected, which may include the following steps S301 to S303.

[0087] Step S301: Collect historical communication data according to a preset target data type to obtain initial communication data.

[0088] For example, when the preset target data types are configuration data, alarm data, performance data, industrial parameter data, diagnostic data and network element logs, historical communication data of data types such as configuration data, alarm data, performance data, industrial parameter data, diagnostic data and network element logs can be collected to obtain initial communication data.

[0089] By collecting historical communication data according to a preset target data type, communication data that meets the target data type can be obtained, avoiding the collection of irrelevant communication data.

[0090] Step S302: annotate the initial communication data according to preset key elements and key events to obtain target communication data carrying the tag.

[0091] After obtaining the initial communication data, the initial communication data may be labeled according to preset key elements and key events to obtain target communication data carrying the label.

[0092] In the embodiment of the present application, the preset key elements and key events are shown in Table 2.

[0093] Table 2

[0094] Table 2 can be expanded horizontally or vertically according to actual conditions, and each item can also be expanded into branches.

[0095] For example, the initial communication data may be labeled based on the key elements and key events in Table 2 to obtain target communication data carrying labels, wherein each target communication data carries a key element label and a key event label.

[0096] In the above embodiment, by labeling the initial communication data according to preset key elements and key events, target communication data carrying the label can be obtained, and the target communication data can be conveniently cleaned according to the label carried by the target communication data.

[0097] Step S303: Determine a first communication data set according to the target communication data carrying the tag.

[0098] Exemplarily, after obtaining the target communication data carrying the tag, a first communication data set may be generated according to the target communication data carrying the tag.

[0099] Please refer to Figure 5, which is a schematic flowchart of sub-steps of data cleaning provided in an embodiment of the present application. In step S202, data cleaning is performed on the first communication data set, which may include the following steps S401 to S403.

[0100] Step S401: Determine the abnormality type corresponding to each target communication data according to the label carried by each target communication data.

[0101] Exemplarily, anomaly detection is performed based on a label carried by each target communication data to obtain an anomaly type corresponding to each target communication data.

[0102] Anomaly detection refers to detecting whether key elements in target communication data are abnormal elements and whether key events are abnormal events. Exemplarily, anomaly types may include non-abnormal data, first-category abnormal data, and second-category abnormal data. Non-abnormal data refers to communication data that does not contain abnormal key elements or abnormal key events, i.e., normal data. First-category abnormal data refers to communication data that contains a single abnormal key element or a single abnormal key event. Second-category abnormal data refers to communication data that contains multiple abnormal key elements and / or multiple abnormal key events.

[0103] For example, anomaly detection and labeling can be performed on the key element tags and key event tags carried by each target communication data to obtain target communication data carrying anomaly tags. Then, the target communication data carrying anomaly tags can be classified based on the anomaly tags to determine the anomaly type corresponding to each target communication data.

[0104] In the above embodiment, the abnormality type corresponding to each target communication data is determined according to the label carried by each target communication data. Subsequently, based on the correspondence between the cleaning strategy and the abnormality type, the target cleaning strategy corresponding to each target communication data can be determined according to the abnormality type corresponding to each target communication data.

[0105] In some embodiments, determining the abnormality type corresponding to each target communication data based on the label carried by each target communication data may include: obtaining the key element label and key event label carried by each target communication data; marking the target communication data whose key element label and / or key event label meet the preset abnormal conditions to obtain the target communication data carrying the abnormal label; determining the target communication data that does not carry the abnormal label as non-abnormal data; determining the target communication data that carries a single abnormal label as the first type of abnormal data; and determining the target communication data that carries at least two abnormal labels as the second type of abnormal data.

[0106] In the embodiment of the present application, abnormal conditions may be predefined, as shown in Table 3.

[0107] Table 3

[0108] Exemplarily, based on Table 3, the target communication data whose key element tags and / or key event tags meet the preset abnormal conditions can be marked to obtain the target communication data carrying the abnormal tag. For example, for target communication data A, if the average downlink RLC layer throughput of the cell of target communication data A is less than or equal to 10Mb / s, an abnormal tag is added to the target communication data A. If the configuration data of target communication data A does not configure a 4G cell, an abnormal tag can also be added to the target communication data A. In this case, the target communication data A carries two abnormal tags.

[0109] For example, for target communication data A, if target communication data A contains a single abnormal label, target communication data A is determined to be first-category abnormal data. For target communication data B, if target communication data B contains multiple abnormal labels, target communication data B is determined to be second-category abnormal data. For target communication data C, if target communication data C contains multiple abnormal labels, target communication data C is determined to be non-abnormal data.

[0110] In the above embodiment, by obtaining the key element tags and key event tags carried by each target communication data, the target communication data whose key element tags and / or key event tags meet the preset abnormal conditions are marked, so that the abnormal type of the target communication data can be conveniently and accurately determined according to the number of abnormal tags carried by the target communication data.

[0111] Step S402: Based on the preset correspondence between the cleaning strategy and the abnormality type, determine the target cleaning strategy corresponding to each target communication data according to the abnormality type corresponding to each target communication data.

[0112] In some embodiments, after determining the abnormality type corresponding to each target communication data, a target cleaning strategy corresponding to each target communication data may be determined according to the abnormality type corresponding to each target communication data based on a preset correspondence between cleaning strategies and abnormality types.

[0113] For example, for target communication data with an anomaly type of non-abnormal data, the corresponding target cleaning strategy may be to filter some of the data. For target communication data with an anomaly type of first-category abnormal data, the corresponding target cleaning strategy may be to retain all data. For target communication data with an anomaly type of second-category abnormal data, the corresponding target cleaning strategy may be to retain all data.

[0114] Non-abnormal data is primarily white noise data. White noise data refers to communication data generated when network elements are operating normally. White noise data containing key elements must be retained to simulate communication data generated when the communication system is operating normally. White noise data can include, but is not limited to, busy-hour white noise, off-hour white noise, nighttime white noise, urban white noise, and suburban white noise.

[0115] Step S403: performing data cleaning on each target communication data according to the target cleaning strategy corresponding to each target communication data to obtain a second communication data set.

[0116] Exemplarily, after determining the target cleaning strategy corresponding to each target communication data, data cleaning is performed on each corresponding target communication data according to the target cleaning strategy corresponding to each target communication data to obtain a second communication data set.

[0117] In some embodiments, performing data cleaning on each corresponding target communication data according to the target cleaning strategy corresponding to each target communication data to obtain a second communication data set may include: filtering non-abnormal data according to a preset filtering ratio to obtain a first sub-data set; retaining the first type of abnormal data and the second type of abnormal data to obtain a second sub-data set; and determining the second communication data set based on the first sub-data set and the second sub-data set.

[0118] The preset filtering ratio can be set according to actual conditions, and the specific value is not limited here. For example, when the preset filtering ratio is 60%, 60% of the non-abnormal data can be filtered out, and the remaining 40% of the non-abnormal data can be determined as the first sub-dataset.

[0119] Exemplarily, the first type of abnormal data and the second type of abnormal data may be retained to obtain a second subset of data. Then, the first subset of data and the second subset of data are determined as a second communication data set.

[0120] Because the first type of abnormal data is the primary data for testing and simulating key events, all of it must be retained. For example, communication data where the key element is a 5G network element and the key event is an optical module failure can subsequently serve as trigger data for software algorithms testing optical module failures. The second type of abnormal data provides feedback for testing or simulating software or algorithms in complex scenarios, so all of it must be retained.

[0121] Please refer to FIG. 6 , which is a schematic flowchart of sub-steps for determining dynamic communication data provided by an embodiment of the present application. Determining the dynamic communication data in step S102 may include the following steps S501 to S503 .

[0122] Step S501: Remove configuration data and work parameter data from static communication data to obtain static communication data after data removal.

[0123] Exemplarily, the configuration data and the working parameter data in the static communication data may be eliminated to obtain static communication data after the data is eliminated.

[0124] In the embodiment of the present application, the data types of static communication data and dynamic communication data are different. As shown in Table 4, dynamic communication data does not include configuration data and work parameter data.

[0125] Table 4

[0126] Step S502: Update the occurrence time in the static communication data after data elimination to obtain the static communication data after time update.

[0127] Exemplarily, after obtaining the static communication data after data elimination, the occurrence time in the static communication data after data elimination may be updated to obtain the time-updated static communication data.

[0128] For example, if the occurrence time in the static communication data is 9:00 on June 21, 2023, the sending time can be updated to 9:00 on June 23, 2023 according to actual needs.

[0129] By updating the occurrence time in the static communication data after data elimination, communication data that changes with time can be obtained, which can be used as real-time input communication data for the twin mirror system.

[0130] Step S503: Determine the dynamic communication data according to the static communication data after time update.

[0131] Exemplarily, after obtaining the time-updated static communication data, the time-updated static communication data may be determined as dynamic communication data.

[0132] In the above embodiment, by removing the configuration data and the working parameter data and using the static communication data at the update time as the dynamic communication data, dynamic communication data that changes with time can be obtained. Subsequently, a twin mirror system can be constructed based on the static communication data and the dynamic communication data, so that the twin mirror system can not only simulate various complex test scenarios, but also simulate feedback scenarios after data changes, thereby improving the applicability of the twin mirror system.

[0133] Please refer to Figure 7, which is a schematic scenario diagram of a digital twin method for a communication system provided in an embodiment of the present application. In scenarios such as detecting whether various types of cell switching are successful, power rates, etc., the relevant technology requires certain services to test whether various types of cell switching detections are normal in addition to testing basic functions in the laboratory after the software algorithm is developed. However, in the laboratory, only a few base stations and a few cells can be constructed, and complex scenarios cannot be simulated. In the embodiment of the present application, the above-mentioned digital twin method can be used to construct a twin mirror system, and various types of cell switching can be tested based on the twin mirror system.

[0134] As shown in Figure 7, historical communication data can be collected first, then labeled and cleaned to obtain static communication data, and the static communication data can be stored in a database or memory. Then, according to the cell switching scenario, various types of data are taken out from the database or memory to form a complete set of twin data, that is, static communication data, and replay data, that is, dynamic communication data, is constructed based on the twin data. Finally, the twin data and replay data are input into the initial mirror system to obtain a twin mirror system. At this point, the twin mirror system can be verified, for example, a cell switching test can be performed on the twin mirror system based on a preset test algorithm.

[0135] Among them, the twin data can be shown in Table 5:

[0136] Table 5

[0137] For example, communication data in a database or memory whose key element is a 5G network element, whose key event is intra-frequency switching, whose occurrence time is the hour, and whose white noise data is busy-hour white noise can be used as twin data. For another example, communication data in a database or memory whose key element is a 4G network element, whose key event is inter-frequency switching, whose occurrence time is half an hour, and whose white noise data is off-hour white noise can be used as twin data.

[0138] During the testing process, the switching events of the test algorithm's 5G network elements, 4G network elements, and cells of different operators can all be verified without the need for manual construction of simulation scenarios. Most test cases do not need to be verified in the actual on-site environment, shortening the software development process and greatly saving manpower and material resources.

[0139] Please refer to Figure 8, which is a schematic scenario diagram of another digital twin method for a communication system provided in an embodiment of the present application. In the security scenario of a venue exhibition, it is usually the wireless network optimization engineer who judges the flow of people and business models at the exhibition site based on experience, and then determines how many new equipment are needed to meet the needs of the site. However, in an actual exhibition, it is necessary to monitor various indicators of the exhibition hall network in real time. Once certain indicators are abnormal, it is necessary to adjust the parameters or add new equipment to meet the needs. In the embodiment of the present application, the above-mentioned digital twin method can be used to build a twin mirror system, and the network quality can be tested based on the twin mirror system.

[0140] The venue scenario has the following characteristics: 1. Large flow of people, requiring many user terminals to access; 2. Large data volume, high traffic volume, and high number of calls; 3. The duration is mainly during the exhibition period, mainly from 9 am to 6 pm; 4. Once too many people gather in certain small areas, the network quality of the cell in that area will drop rapidly. In this embodiment of the application, twin data can be determined based on the characteristics of the above venue scenario, as shown in Table 6.

[0141] Table 6

[0142] For example, communication data in a database or memory whose key element is a 5G network element, whose key event is a cell anomaly, whose occurrence time is any time between 9:00 and 18:00, and whose white noise data is busy-hour white noise can be used as twin data. For another example, communication data in a database or memory whose key element is a 4G network element, whose key event is a coverage issue, whose occurrence time is any time between 9:00 and 18:00, and whose white noise data is nighttime white noise can be used as twin data.

[0143] As shown in Figure 8, historical communication data can be collected first, then labeled and cleaned to obtain static communication data, which is then stored in a database or memory. Then, based on the exhibition hall network scenario, various types of data are retrieved from the database or memory to form a complete set of twin data, namely static communication data, and replay data, namely dynamic communication data, is constructed based on the twin data. Finally, the twin data and replay data are input into the initial mirror system to obtain a twin mirror system. At this point, the twin mirror system can be verified, for example, by performing exhibition hall network testing on the twin mirror system based on a preset test algorithm.

[0144] During the exhibition hall network testing process, the twin mirror system can construct various abnormal scenarios, simulating the data conditions that may be generated in the exhibition hall network environment under these abnormal scenarios. When users adjust parameters, they can also use the configuration-related data for simulation. In the data feedback closed loop, the changes in collected configuration data and corresponding performance data can be used to simulate the performance data changes caused by the relevant parameter changes through the playback data closed loop. The specific process is not detailed here.

[0145] By conducting exhibition hall network testing on the twin mirror system based on a preset test algorithm, compared with the existing road tests in actual venues and environments, which require the installation of debugging sites before data analysis and optimization can be carried out, efficiency can be improved and costs can be saved.

[0146] A computer-readable storage medium is also provided in an embodiment of the present application. The computer-readable storage medium stores a computer program, which includes program instructions. The processor executes the above program instructions to implement any digital twin method provided in the embodiment of the present application.

[0147] For example, when the program is loaded by the processor, the following steps may be performed:

[0148] Based on the target test scenario corresponding to the communication system, obtain the static communication data of the communication system, which is the historical communication data of the communication system; determine the dynamic communication data, which is the communication data constructed based on the static communication data; input the static communication data and the dynamic communication data into the preset initial mirror system to obtain the twin mirror system corresponding to the communication system.

[0149] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0150] In a hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a storable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those of ordinary skill in the art, the term storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as 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 cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0151] The above description of the optional embodiments of the present application with reference to the accompanying drawings does not limit the scope of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present application shall be within the scope of the present application.

Claims

1. A digital twin method for a communication system, wherein: The method comprises: Based on the target test scenario corresponding to the communication system, acquiring static communication data of the communication system, wherein the static communication data is historical communication data of the communication system; Determining dynamic communication data, wherein the dynamic communication data is communication data constructed based on the static communication data; The static communication data and the dynamic communication data are input into a preset initial mirror system to obtain a twin mirror system corresponding to the communication system.

2. The digital twin method of the communication system according to claim 1, wherein: The acquiring static communication data of the communication system based on the target test scenario corresponding to the communication system includes: Based on a preset collection strategy, historical communication data of the communication system is collected to obtain a first communication data set; Performing data cleaning on the first communication data set to obtain a second communication data set; Based on the target test scenario, communication data matching the target test scenario is extracted from the second communication data set to obtain the static communication data.

3. The digital twin method of the communication system according to claim 2, wherein: The collecting of historical communication data of the communication system based on a preset collection strategy to obtain a first communication data set includes: Collect the historical communication data according to a preset target data type to obtain initial communication data; The initial communication data is labeled according to preset key elements and key events to obtain target communication data carrying the label; The first communication data set is determined according to the target communication data carrying the tag.

4. The digital twin method of the communication system according to claim 2, wherein: The first communication data set includes a plurality of target communication data carrying tags; The step of performing data cleaning on the first communication data set to obtain a second communication data set includes: Determine, according to the label carried by each of the target communication data, the abnormal type corresponding to each of the target communication data; Based on the correspondence between the preset cleaning strategy and the abnormality type, determining the target cleaning strategy corresponding to each of the target communication data according to the abnormality type corresponding to each of the target communication data; Each of the target communication data is cleansed according to the target cleaning strategy corresponding to each of the target communication data to obtain the second communication data set.

5. The digital twin method of the communication system according to claim 4, wherein: The determining, according to the label carried by each of the target communication data, the abnormality type corresponding to each of the target communication data includes: Acquire key element tags and key event tags carried by each of the target communication data; Marking target communication data whose key element tags and / or key event tags meet preset abnormal conditions to obtain target communication data carrying abnormal tags; Determine the target communication data that does not carry the abnormal label as non-abnormal data; Determine a single target communication data carrying an abnormal label as the first type of abnormal data; The target communication data carrying at least two abnormal tags is determined as second-category abnormal data.

6. The digital twin method of the communication system according to claim 5, wherein: The step of performing data cleaning on each of the target communication data according to the target cleaning strategy corresponding to each of the target communication data to obtain the second communication data set includes: Filtering the non-abnormal data according to a preset filtering ratio to obtain a first sub-dataset; The first type of abnormal data and the second type of abnormal data are retained to obtain a second sub-dataset; The second communication data set is determined according to the first sub-data set and the second sub-data set.

7. The digital twin method of the communication system according to claim 2, wherein: The target test scenario includes target key elements, target key events, target occurrence time and target noise; The extracting, based on the target test scenario, communication data matching the target test scenario from the second communication data set to obtain the static communication data includes: The communication data in the second communication data set that matches the target key element, the target key event, the target occurrence time, and the target noise is determined as the static communication data.

8. The digital twin method of a communication system according to any one of claims 1 to 7, wherein: The determining of dynamic communication data comprises: Eliminating the configuration data and the work parameter data in the static communication data to obtain the static communication data after the data is eliminated; Updating the occurrence time in the static communication data after data removal to obtain the static communication data after time update; The dynamic communication data is determined according to the static communication data after time update.

9. A communication device comprising a processor and a memory; The memory is used to store programs; The processor is used to execute the program and implement the digital twin method of the communication system as described in any one of claims 1 to 8 when executing the program.

10. A computer-readable storage medium for readable storage, wherein: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the digital twin method of the communication system as described in any one of claims 1 to 8.

Images