A network measurement data repairing method, device and equipment

Abstract

This invention relates to a method, apparatus, and device for repairing network measurement data, belonging to the field of network data processing technology. The method includes: acquiring multi-source heterogeneous data; wherein the multi-source heterogeneous data includes at least core network user signaling data and network-side multi-dimensional measurement reports; based on the multi-source heterogeneous data, performing a dynamic integrity assessment of the network measurement data to determine a target matching rate; wherein the target matching rate is the matching rate between the core network user signaling data and the network-side multi-dimensional measurement reports; if the target matching rate is less than a matching rate threshold, determining a root cause localization result based on the multi-source heterogeneous data; wherein the root cause localization result indicates the cause of the missing network measurement data; based on the root cause localization result, determining a repair strategy corresponding to the root cause localization result, and performing network measurement data repair based on the repair strategy. This invention can accurately identify whether network measurement data is abnormal.

Description

Technical Field

[0001] This invention relates to the field of network data processing technology, and specifically to a method, apparatus, and equipment for repairing network measurement data. Background Technology

[0002] During the operation of mobile communication networks, network measurement data is the core foundation for network planning, performance optimization, fault diagnosis, and user experience improvement. However, during the collection, transmission, and processing of network measurement data, problems such as data loss and reporting anomalies can easily occur, which in turn affect the integrity of the network measurement data.

[0003] In related technologies, the integrity of network-side data is determined by statistically analyzing the number of missing core network user signaling data (XDR) or by simply comparing the difference between the number of XDRs and the number of network-side multidimensional measurement reports (MR). In this way, when the network-side data is incomplete, it can be repaired.

[0004] However, judging the integrity of network-side data solely by comparing the difference between XDR and MR can easily lead to misjudgments of integrity anomalies.

[0005] Therefore, there is an urgent need for a method that can accurately identify whether network measurement data is abnormal. Summary of the Invention

[0006] The technical problem to be solved by this invention is that the method of judging the integrity of network-side data by comparing the difference between XDR and MR in related technologies is prone to misjudgment of integrity abnormalities.

[0007] The technical solution of this invention to solve the above-mentioned technical problems is as follows: a method for repairing network measurement data, the method comprising: acquiring multi-source heterogeneous data; wherein, the multi-source heterogeneous data includes at least core network user signaling data and network-side multi-dimensional measurement reports; based on the multi-source heterogeneous data, performing a dynamic integrity assessment of the network measurement data to determine a target matching rate; wherein, the target matching rate is the matching rate between core network user signaling data and network-side multi-dimensional measurement reports; if the target matching rate is less than a matching rate threshold, determining a root cause localization result based on the multi-source heterogeneous data; wherein, the root cause localization result indicates the cause of the missing network measurement data; based on the root cause localization result, determining a repair strategy corresponding to the root cause localization result, and performing network measurement data repair based on the repair strategy.

[0008] The beneficial effects of this invention are as follows: By acquiring multi-source heterogeneous data, including core network user signaling data and multi-dimensional measurement reports from the network side, the judgment bias caused by simply counting the quantity difference is avoided; then, by dynamically evaluating the integrity of network measurement data to determine the target matching rate, rather than simply counting the number of missing data, the true situation of missing data can be accurately identified; finally, when the target matching rate is lower than the threshold, the root cause localization result is determined by combining multi-source data, and the corresponding repair strategy is executed according to the root cause matching. At the same time, the integrity is further confirmed through the verification step after repair, which solves the problem that judging integrity by simply counting the quantity difference is prone to misjudgment and cannot accurately locate the problem.

[0009] Based on the above technical solution, the present invention can be further improved as follows.

[0010] Furthermore, based on multi-source heterogeneous data, the integrity of network measurement data is dynamically evaluated to determine the target matching rate. This includes: constructing a unified index key for associating core network user signaling data with network-side multi-dimensional measurement reports; based on the unified index key, counting the target number of network-side multi-dimensional measurement reports successfully associated with core network user signaling data within a preset time granularity; and determining the target matching rate based on the ratio of the target number to the total number of core network user signaling data.

[0011] The beneficial effect of adopting the above-mentioned further solution is that by constructing a unified index key for associating core network user signaling data and network-side multi-dimensional measurement reports, a precise correlation benchmark between the two types of data can be established, effectively solving the problem of the lack of a unified standard and chaotic correlation between the two types of data.

[0012] Furthermore, based on this unified index key, the number of target multi-dimensional measurement reports on the network side that are successfully associated with core network user signaling data is counted within a preset time granularity. Then, the target matching rate is determined based on the ratio of this target number to the total number of core network user signaling data. This can accurately reflect the matching degree of the two types of data. Compared with the method of simply comparing the difference in the number of data, it can effectively improve the accuracy of network measurement data integrity assessment.

[0013] Furthermore, the multi-source heterogeneous data also includes network configuration and operating parameters. Based on the multi-source heterogeneous data, the root cause localization results are determined, including: based on the network configuration and operating parameters, detecting whether the data collection subscription status of the network unit meets the preset subscription status to obtain a first detection result; detecting whether the full user reporting setting status of the network element meets the preset reporting status to obtain a second detection result; detecting whether the call history reporting switch status meets the preset switch status to obtain a third detection result; performing complementary analysis on the core network user signaling data and the network-side multi-dimensional measurement reports to obtain complementary analysis results; and determining the root cause localization results based on the first detection result, the second detection result, the third detection result, and the complementary analysis results.

[0014] The beneficial effect of adopting the above-mentioned further scheme is that, based on the network configuration and operation parameters in multi-source heterogeneous data, the data acquisition subscription status of network units, the full user reporting status of network elements, and the call history reporting switch status are detected to obtain the first detection result, the second detection result, and the third detection result, respectively. Based on the core network user signaling data and network-side multi-dimensional measurement reports in multi-source heterogeneous data, complementary analysis is carried out to obtain complementary analysis results. Finally, based on the first detection result, the second detection result, the third detection result, and the complementary analysis results, the root cause localization result is integrated to clarify the specific reasons, scope of impact, and severity of the missing network measurement data, thereby accurately determining the cause of the missing network measurement data.

[0015] Furthermore, the network-side multi-dimensional measurement report includes at least periodically triggered measurement reports and event-triggered measurement reports. Complementary analysis is performed on the core network user signaling data and the network-side multi-dimensional measurement reports to obtain complementary analysis results, including: determining the user session duration based on the core network user signaling data; determining the reporting period based on the periodically triggered measurement reports; detecting whether the user session duration is less than the reporting period; if no periodically triggered measurement report is matched to the core network user signaling data, searching for event-triggered measurement reports within the same session period; if the user session duration is less than the reporting period and no event-triggered measurement report exists within the same session period, the complementary analysis result is determined to be a reasonable missing result; if the user session duration is not less than the reporting period and no event-triggered measurement report exists within the same session period, the complementary analysis result is determined to be a configuration anomaly result.

[0016] The beneficial effect of adopting the above-mentioned further solution is that by combining the user session duration determined by the core network user signaling data, the reporting cycle of periodic trigger measurement reports, and the existence status of event trigger measurement reports within the same session period, complementary analysis can be performed to accurately distinguish the data missing types. When the user session duration is less than the reporting cycle of periodic trigger measurement reports and there are no event trigger measurement reports, it is judged as a reasonable missing data. When the user session duration is not less than the reporting cycle of periodic trigger measurement reports and there are no event trigger measurement reports, it is judged as a configuration anomaly. This effectively improves the accuracy and pertinence of the determination of the root cause of missing network measurement reports.

[0017] Furthermore, the core network user signaling data includes the inactivity timer parameters of user terminals. Complementary analysis is performed on the core network user signaling data and the network-side multi-dimensional measurement reports to obtain complementary analysis results, including: determining the reporting period based on periodically triggered measurement reports; detecting whether the inactivity timer parameters of user terminals are less than the reporting period; if the inactivity timer parameters of user terminals are not less than the reporting period, then the complementary analysis result is determined to be an abnormal parameter setting result.

[0018] The beneficial effect of adopting the above-mentioned further solution is that by determining the reporting period based on periodically triggered measurement reports, it can detect whether the user equipment inactivity timer parameter is less than the reporting period. When the user equipment inactivity timer parameter is not less than the reporting period, it can directly determine the complementarity analysis result as an abnormal parameter setting result. This can quickly and accurately locate network measurement report anomalies caused by improper inactivity timer parameter configuration, and improve the efficiency and accuracy of root cause diagnosis of missing measurement report data.

[0019] Furthermore, the multi-source heterogeneous data also includes network performance and status data; complementary analysis is performed on core network user signaling data and network-side multi-dimensional measurement reports to obtain complementary analysis results, including: identifying target core network user signaling data from the core network user signaling data that does not match periodically triggered measurement reports; determining the serving cell where the user corresponding to the target core network user signaling data is located based on the target core network user signaling data; detecting whether the signal strength of the serving cell is less than a strength threshold based on the network performance of the serving cell; detecting whether the signal-to-noise ratio of the serving cell is less than a signal-to-noise ratio threshold based on the status data of the serving cell; if the signal strength and signal-to-noise ratio of the serving cell are both less than the strength threshold, the complementary analysis result is determined to be a weak coverage result.

[0020] The beneficial effect of adopting the above-mentioned further solution is to locate the corresponding serving cell by using core network user signaling data that has never matched a periodically triggered measurement report, and to detect whether the signal strength is lower than the strength threshold by combining the network performance data of the serving cell and whether the signal-to-noise ratio is lower than the signal-to-noise ratio threshold by combining the status data. When both the signal strength and the signal-to-noise ratio are lower than the corresponding thresholds, it is directly determined as a weak coverage result. This can quickly and accurately identify the problem of missing periodically triggered measurement reports caused by weak coverage environment, and improve the efficiency and accuracy of locating the root cause of network measurement data anomalies.

[0021] Furthermore, complementary analysis is performed on the core network user signaling data and the network-side multi-dimensional measurement reports to obtain complementary analysis results, including: determining the user session duration based on the core network user signaling data; determining the reporting period based on the periodically triggered measurement reports; detecting whether the user session duration is less than the reporting period; if the user session duration is not less than the reporting period, and the core network user signaling data does not match the network-side multi-dimensional measurement reports, then the complementary analysis result is determined to be a time anomaly result.

[0022] The beneficial effect of adopting the above-mentioned further solution is that by determining the user session duration based on core network user signaling data and determining the reporting period based on periodically triggered measurement reports, it can detect whether the user session duration is less than the reporting period. When the user session duration is not less than the reporting period and the core network user signaling data does not match the network-side multi-dimensional measurement report, the complementarity analysis result is directly determined to be a time anomaly result. This can accurately determine the measurement report missing caused by time issues related to user session duration, and improve the accuracy and reliability of the root cause location of measurement data anomalies.

[0023] Furthermore, based on the root cause localization results, the corresponding remediation strategy is determined, including: based on the root cause localization results and the preset mapping relationship, the remediation strategy corresponding to the root cause localization results is determined.

[0024] The beneficial effect of adopting the above-mentioned further solution is that by directly determining the corresponding repair strategy through the root cause localization results and the preset mapping relationship, it is possible to achieve accurate matching between the abnormal root cause and the handling solution, quickly output the appropriate repair measures, and improve the automation level and handling efficiency of network measurement data integrity assurance.

[0025] Furthermore, the present invention provides a network measurement data repair device, the device comprising: an acquisition module for acquiring multi-source heterogeneous data; wherein the multi-source heterogeneous data includes at least core network user signaling data and network-side multi-dimensional measurement reports; a first determination module for performing a dynamic integrity assessment of the network measurement data based on the multi-source heterogeneous data to determine a target matching rate; wherein the target matching rate is the matching rate between the core network user signaling data and the network-side multi-dimensional measurement reports; a second determination module for determining a root cause localization result based on the multi-source heterogeneous data if the target matching rate is less than a matching rate threshold; wherein the root cause localization result indicates the cause of the missing network measurement data; and a repair determination module for determining a repair strategy corresponding to the root cause localization result based on the root cause localization result, and performing network measurement data repair based on the repair strategy.

[0026] Furthermore, the present invention provides a computer device, including: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the network measurement data repair method described in the first aspect or any corresponding embodiment.

[0027] Furthermore, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the network measurement data repair method described in the first aspect or any corresponding embodiment thereof.

[0028] Furthermore, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for repairing network measurement data described in the first aspect or any corresponding embodiment. Attached Figure Description

[0029] Figure 1 A flowchart illustrating the method for repairing network measurement data provided by the present invention; Figure 2 A flowchart illustrating another method for repairing network measurement data provided by the present invention; Figure 3 A flowchart illustrating another method for repairing network measurement data provided by the present invention; Figure 4 This is a flowchart illustrating another method for repairing network measurement data provided by the present invention.

[0030] Figure 5 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0031] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0032] During the operation of mobile communication networks, network measurement data is the core foundation for network planning, performance optimization, fault diagnosis, and user experience improvement. However, during the collection, transmission, and processing of network measurement data, problems such as data loss and reporting anomalies can easily occur, which in turn affect the integrity of the network measurement data.

[0033] In related technologies, the integrity of network-side data is determined by statistically analyzing the number of missing core network user signaling data (XDR) or by simply comparing the difference between the number of XDRs and the number of network-side multidimensional measurement reports (MR). In this way, when the network-side data is incomplete, it can be repaired.

[0034] However, judging the integrity of network-side data solely by comparing the difference between XDR and MR can easily lead to misjudgments of integrity anomalies.

[0035] Based on this, the present invention provides a method for repairing network measurement data. By acquiring multi-source heterogeneous data, including core network user signaling data and multi-dimensional measurement reports from the network side, it avoids the judgment bias caused by simply counting the quantity difference. Then, by dynamically evaluating the integrity of the network measurement data to determine the target matching rate, rather than simply counting the number of missing data, it can accurately identify the true situation of data missing. Finally, when the target matching rate is lower than a threshold, the root cause location result is determined by combining multi-source data, and the corresponding repair strategy is matched according to the root cause and the repair is performed. At the same time, the integrity is further confirmed through the verification step after repair, which solves the problem that judging integrity by only counting the quantity difference is prone to misjudgment and cannot accurately locate the root cause.

[0036] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the structure of the network measurement data repair system provided by the present invention.

[0037] Combination Figure 1 As shown, the network measurement data repair system includes a data acquisition and processing layer, an intelligent analysis and decision-making layer, and a strategy execution and feedback layer.

[0038] The data acquisition and processing layer collects multi-source heterogeneous data and preprocesses it to obtain standardized correlated data. The multi-source heterogeneous data includes at least core network user signaling data, network-side multi-dimensional measurement reports, network configuration and operation parameters, and network performance and status data. During the preprocessing process, a unified index key is constructed to correlate signaling data and measurement data to achieve time synchronization and normalization of multi-source data. The intelligent analysis and decision-making layer dynamically evaluates the integrity of network measurement data based on standardized correlation data and calculates the matching rate. When the matching rate is consistently lower than the matching rate threshold, the root cause diagnosis process is triggered. The intelligent analysis and decision-making layer, based on standardized correlated data and combined with the results of XDR-MR matching rate anomalies, performs intelligent root cause diagnosis through multi-source data cross-verification, and simultaneously conducts configuration and parameter compliance analysis, XDR and multi-dimensional measurement data complementarity analysis, accurately locates the root cause of missing measurement data, and obtains root cause location results; Based on the root cause localization results, the intelligent analysis and decision-making layer generates targeted remediation strategies, which are then executed by the strategy execution and feedback layer. After the strategy execution and feedback layer executes the repair strategy, it collects multi-source data again and obtains new standardized correlation data through preprocessing. Based on the new data, it recalculates the matching rate, monitors the change in the matching rate within a preset period after the repair, verifies the repair effect, and forms a closed-loop governance process of perception, diagnosis, execution and verification.

[0039] According to an embodiment of the present invention, a method for repairing network measurement data is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0040] This embodiment provides a method for repairing network measurement data, which can be used in the aforementioned network measurement data repair system. Figure 2 This is a flowchart of a method for repairing network measurement data according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain multi-source heterogeneous data; wherein, the multi-source heterogeneous data includes at least core network user signaling data and network-side multi-dimensional measurement reports.

[0041] Multi-source heterogeneous data can be understood as a collection of data from different domains, structures, and formats in mobile communication networks. It includes at least core network user signaling data and multi-dimensional measurement reports from the network side, and may also include network configuration parameters, network performance and status data.

[0042] Core network user signaling data can be understood as user control plane and user plane signaling data collected by the core network, which may include user identifier, process type, timestamp, serving cell, signaling process identifier, etc.

[0043] A network-side multi-dimensional measurement report can be understood as measurement data generated by the wireless side, and can include at least periodically triggered measurement reports and event-triggered measurement reports.

[0044] Specifically, multi-source heterogeneous data is collected from the core network, wireless network, and network management system.

[0045] In one possible implementation, after cleaning, parsing, and time-synchronizing multi-source heterogeneous data, a unified association key can be constructed for serving cell identifier, precise time window, and signaling process identifier.

[0046] Step S202: Based on multi-source heterogeneous data, perform a dynamic integrity assessment of the network measurement data to determine the target matching rate; wherein, the target matching rate is the matching rate between core network user signaling data and network-side multi-dimensional measurement reports.

[0047] The target matching rate can be understood as the percentage of samples in which core network user signaling data is successfully correlated with network-side multi-dimensional measurement reports.

[0048] Specifically, after identifying multi-source heterogeneous data, the target matching rate is determined by dynamically evaluating the integrity of network measurement data.

[0049] As an example, after collecting and processing multi-source heterogeneous data at a fixed granularity (e.g., 15 minutes), the calculation window is set at the hour level. The total amount of effective core network user signaling data and the number of samples successfully matched with the network-side multi-dimensional measurement reports are counted according to dimensions such as cell, base station, base station cluster, city / region, and service type. The ratio of the two is then calculated to obtain the target matching rate, thus completing the dynamic evaluation of integrity.

[0050] As an example, 10 base stations in the same area are divided into a base station cluster. The matching results of all core network user signaling data within the base station cluster with the measurement reports are statistically analyzed, and the cluster-level target matching rate is calculated.

[0051] Step S203: If the target matching rate is less than the matching rate threshold, determine the root cause localization result based on multi-source heterogeneous data; wherein, the root cause localization result indicates the reason for the missing network measurement data.

[0052] The matching rate threshold can be understood as a pre-configured standard value for the integrity and health of measurement data.

[0053] Root cause analysis results indicate the reasons for missing network measurement data. These can include legitimate missing data, configuration errors, parameter setting errors, weak coverage, timing issues, network element failures, and data acquisition link interruptions.

[0054] Specifically, if the target matching rate is less than the matching rate threshold, root cause localization can be initiated to determine the root cause localization result based on multi-source heterogeneous data.

[0055] As an example, a user session duration shorter than the reporting period for periodically triggered measurement reports, and no event-triggered measurement reports are reported within the same session period, is considered a reasonable missing report. When both periodically triggered and event-triggered measurement reports are missing, and the measurement subscription switch is off, it is considered a configuration anomaly. When the user equipment inactivity timer is less than N seconds, it is considered a parameter setting anomaly. When the signal strength of the serving cell is less than the strength threshold, and the signal-to-noise ratio is less than the signal-to-noise ratio threshold, it is considered weak coverage.

[0056] As an example, the target matching rate suddenly drops to 0. The core network user signaling data collection is normal, but no measurement report data is obtained. At the same time, the base station status data shows that the network element is offline. At this time, the root cause location result is a base station network element failure.

[0057] As an example, the core network user signaling data collection is normal, and the base station equipment can generate measurement reports normally locally. However, the data platform cannot receive the measurement report data, and the collection link status detection result is interrupted. At this time, the root cause location result is that the measurement data collection link is interrupted.

[0058] Step S204: Based on the root cause localization results, determine the corresponding repair strategy and perform network measurement data repair based on the repair strategy.

[0059] The repair strategy can be understood as a solution for repairing and handling network measurement data. Specifically, it may include automatic configuration repair, parameter calibration, measurement subscription distribution, weak coverage optimization work orders, network element restart commands, and data acquisition link repair.

[0060] Specifically, after determining the root cause, the corresponding remediation strategy can be further determined.

[0061] As an example, based on the root cause localization results, a preset mapping relationship is matched to automatically generate the corresponding repair strategy. The repair operation is executed through the network management interface and the automated operation and maintenance platform. After execution, the target matching rate is continuously monitored to verify the repair effect and form a closed-loop governance.

[0062] In one possible implementation scenario, multi-source heterogeneous data from 23 base stations in the cutover area can be collected in batches through a cloud-native data platform. This includes core network user signaling data, periodically triggered measurement reports, event-triggered measurement reports, cell signal strength, signal-to-noise ratio, base station configuration parameters, and UE inactivity timer values. After cleaning, a unified association key is constructed to complete data alignment.

[0063] Data was collected at 15-minute intervals, and the target matching rate of this base station cluster was found to be only 38%, far below the preset matching rate threshold of 85%, indicating a serious abnormality in data integrity.

[0064] Initiating multi-source data cross-verification diagnosis: excluding weak coverage (cell signal strength and signal-to-noise ratio both exceed thresholds); excluding abnormal parameters (inactive timer configured to 10 seconds, exceeding the MRO reporting cycle); excluding network element faults (base station online and operating normally); detection revealed that user session durations were not less than the measurement reporting cycle, and core network user signaling data did not match any network-side multi-dimensional measurement reports; ultimately, the root cause was determined to be time anomaly, caused by system time offset and loss of measurement cycle configuration after base station cutover.

[0065] Based on the preset mapping relationship, a repair strategy is automatically generated, as follows: Synchronize the base station system time to the core network standard time; reissue the periodic measurement and event measurement subscription configurations; reset the base station measurement reporting period parameters. Fifteen minutes after the policy execution, the target matching rate of the base station cluster is recalculated and rises to 94%. After remaining stable for three hours, the repair is deemed successful, and this operation is stored in the experience database, completing the closed-loop governance process.

[0066] The network measurement data repair method provided by this invention avoids judgment bias caused by simply counting quantity differences by acquiring multi-source heterogeneous data, including core network user signaling data and multi-dimensional measurement reports from the network side. Then, it determines the target matching rate by dynamically evaluating the integrity of the network measurement data, rather than simply counting the number of missing data, which can accurately identify the true situation of data missing data. Finally, when the target matching rate is lower than a threshold, the root cause location result is determined by combining multi-source data, and the corresponding repair strategy is matched according to the root cause and the repair is performed. At the same time, the integrity is further confirmed by the verification step after repair, which solves the problem that judging integrity by quantity difference alone is prone to misjudgment and cannot accurately locate the root cause.

[0067] Based on step S202 of this embodiment, which involves dynamically evaluating the integrity of network measurement data using multi-source heterogeneous data, the target matching rate is determined by methods such as... Figure 3 The implementation of steps S3021 to S3023 is as follows: Step S3021: Construct a unified index key for linking core network user signaling data with network-side multi-dimensional measurement reports.

[0068] A unified index key can be understood as a composite unique identifier constructed by accurately aligning core network user signaling data with multi-dimensional measurement reports from the network side. Specifically, it can be composed of fields such as network location, time window, and signaling flow identifier.

[0069] Specifically, key fields are extracted from three dimensions: network location, time, and unique signaling identifier. These fields are combined to generate a unified index key, which binds the core network user signaling data and the network-side multi-dimensional measurement reports to the same session, the same cell, and the same time, thereby achieving accurate cross-domain data association.

[0070] Step S3022: Based on the unified index key, count the target number of network-side multi-dimensional measurement reports that are successfully associated with core network user signaling data within a preset time granularity.

[0071] The preset time granularity can be understood as the set statistical time unit, usually 5 minutes, 10 minutes, or 15 minutes, used to calculate data matching in different time periods.

[0072] The target number can be understood as the number of network-side multi-dimensional measurement reports that are successfully associated and matched with core network user signaling data through a unified index key within a preset time granularity.

[0073] Specifically, the data is divided into windows according to a preset time granularity. Using a unified index key as the matching basis, the core network user signaling data and the network-side multi-dimensional measurement reports are compared one by one. Data with completely identical key values ​​are considered successfully associated, and the number of measurement reports that are successfully matched within the time window is counted to obtain the target quantity. For example, with a preset time granularity of 15 minutes, the total number of successfully associated MRO and MRE reports within the time window is counted based on the unified index key, and this number is used as the target quantity.

[0074] Step S3023: Determine the target matching rate based on the ratio of the target number to the total number of core network user signaling data.

[0075] Specifically, within the same preset time granularity, the target number of successfully associated network-side multi-dimensional measurement reports is divided by the total number of core network user signaling data collected within that time window to calculate the ratio, which is the target matching rate used to evaluate data integrity.

[0076] In one possible implementation scenario, to achieve accurate correlation between core network user signaling data and multi-dimensional measurement reports from the network side, a unified index key is constructed using a combination of cell global identifiers, second-level time slices, and RRC session identifiers to prepare for cross-domain data alignment. A preset time granularity of 15 minutes is set, and data within this time period is matched one by one based on the unified index key. A total of 2860 periodically triggered and event-triggered measurement reports are successfully correlated; this number is the target number. The total number of valid core network user signaling data collected within this 15-minute window is 3200. Dividing the target number of 2860 by the total number of 3200 yields a ratio of 0.8937, indicating a target matching rate of 89.37%.

[0077] The network measurement data repair method provided by this invention establishes a precise correlation benchmark between the two types of data by constructing a unified index key for associating core network user signaling data and network-side multi-dimensional measurement reports. This effectively solves the problems of lack of a unified standard and chaotic correlation between the two types of data. Furthermore, based on this unified index key, the target number of network-side multi-dimensional measurement reports successfully associated with core network user signaling data is counted within a preset time granularity. Then, the target matching rate is determined based on the ratio of this target number to the total number of core network user signaling data. This accurately reflects the degree of matching between the two types of data, and compared to simply comparing the difference in the number of data items, it effectively improves the accuracy of network measurement data integrity assessment.

[0078] Multi-source heterogeneous data also includes network configuration and operating parameters. Based on the multi-source heterogeneous data determined in step S203 of this embodiment, the root cause localization result is determined using the following method: Figure 4 The implementation of steps S4031 to S4035 is as follows: Step S4031: Based on network configuration and operating parameters, detect whether the data acquisition subscription status of the network unit meets the preset subscription status, and obtain the first detection result.

[0079] Network configuration can be understood as the functional configuration information of network elements such as base stations and core networks obtained from the network management system. Specifically, it may include measurement data acquisition subscription, measurement type switch, measurement control parameters, etc.

[0080] Operating parameters can be understood as the key parameters for the real-time operation of network elements, which may include inactivity timers of user terminals, measurement cycles, reporting modes, and service-related parameters.

[0081] A network unit can be understood as the smallest logical unit in a network that can be managed independently and has data acquisition capabilities. Specifically, it can include a single cell, a single base station, a base station cluster, or a collection of network devices in a region.

[0082] The data acquisition subscription status can be understood as the configuration status of whether the network unit has enabled acquisition tasks such as periodic measurement reports and event measurement reports, and is divided into subscribed, unsubscribed, and abnormal subscription.

[0083] The default subscription status can be understood as the standard subscription status defined by network specifications or operation and maintenance policies to ensure the normal collection of measurement reports.

[0084] The first detection result can be understood as a judgment result indicating whether the data collection subscription status meets the preset requirements, which can specifically include two situations: compliant and non-compliant.

[0085] Specifically, the network configuration and operating parameters of the specified network unit are read from the network management system, and the subscription configuration information of collection tasks such as periodic measurement reports and event measurement reports is extracted. The current subscription status is compared with the preset subscription status to determine whether they are consistent, thereby obtaining the first detection result.

[0086] As an example, the system reads the network configuration and operating parameters of the base station, checks the collection and subscription status of periodically triggered measurement reports and event-triggered measurement reports. The preset subscription status requires that both types of measurements have been subscribed. If both are currently subscribed, the first detection result is compliant; if either is not subscribed, it is non-compliant.

[0087] Step S4032: Check whether the reporting status of all users of the network element meets the preset reporting status, and obtain the second detection result.

[0088] The preset reporting status can be understood as the network element reporting mode that ensures data integrity.

[0089] The second detection result can be understood as whether the reported settings status of all users of the network element conforms to the preset reporting status. Specifically, the second detection result can include whether the reported settings status of all users of the network element conforms to the preset reporting status or not.

[0090] Specifically, the network element configuration information of the network unit is read, the current user measurement report reporting mode is checked, it is determined whether it is the preset reporting state, and the second detection result is obtained.

[0091] As an example, check the user reporting mode of the base station network element. The default reporting state is full user reporting. If the network element is configured to report all users, the second detection result is compliant. If it is configured to sample proportionally, report some users, or turn off reporting, it is non-compliant.

[0092] Step S4033: Detect whether the switch status reported in the call history records conforms to the preset switch status, and obtain the third detection result.

[0093] The call history reporting switch status can be understood as a functional switch in the network element that controls the output of call history record (CHR), and is a supporting switch for normal reporting of measurement reports.

[0094] The preset switch state can be understood as the switch state that ensures the normal output of measurement data.

[0095] Specifically, the call history record (CHR) configuration of the network element is read, the current status of the call history record reporting switch is checked, and it is determined whether it is the preset switch status (on) to obtain the third detection result.

[0096] As an example, check the reported switch status in the CHR output control information of the network element. The default switch status is open. If the switch is in the open state, the third detection result is compliant; if it is in the closed state, it is non-compliant.

[0097] Step S4034: Perform complementary analysis on the core network user signaling data and the network-side multi-dimensional measurement report to obtain the complementary analysis results.

[0098] The results of complementarity analysis can be understood as the specific conclusions obtained after the complementarity analysis, which may include reasonable missing values, configuration anomalies, parameter anomalies, weak coverage, time anomalies, etc.

[0099] Specifically, after obtaining the core network user signaling data and the network-side multi-dimensional measurement report, complementary analysis can be performed on the core network user signaling data and the network-side multi-dimensional measurement report to obtain complementary analysis results.

[0100] As an example, the signaling data of core network users is cross-compared with the multi-dimensional measurement reports of the network side. The complementary verification is carried out by combining information such as user session duration, measurement reporting cycle, signal strength, signal-to-noise ratio, and inactivity timer, and the complementary analysis results are obtained.

[0101] As an example, the user session duration is determined based on the core network user signaling data, and the reporting period is determined based on the periodic trigger measurement report. If the user session duration is less than the reporting period and there is no event measurement report for the same session, the complementarity analysis result is a reasonable missing result; if the session duration is not less than the reporting period and there is no measurement report, it is a time anomaly; if the inactive timer is too small, it is a parameter anomaly; if there is weak coverage, it is a weak coverage result.

[0102] Step S4035: Based on the first detection result, the second detection result, the third detection result, and the complementarity analysis result, determine the root cause localization result.

[0103] After obtaining the first, second, and third detection results, as well as the complementarity analysis results, the root cause localization result can be obtained. For example, if the first, second, and third detection results are inconsistent, and the complementarity analysis result indicates a configuration anomaly, the comprehensive determination of the root cause localization result is that the configuration anomaly is caused by missing measurement acquisition subscription, full reporting not being enabled, or the CHR switch being turned off.

[0104] The network measurement data repair method provided by this invention, based on network configuration and operating parameters in multi-source heterogeneous data, detects the data acquisition subscription status of network units, the full user reporting status of network elements, and the call history reporting switch status, respectively obtaining a first detection result, a second detection result, and a third detection result. Based on the core network user signaling data and multi-dimensional measurement reports from the network side in the multi-source heterogeneous data, a complementary analysis is carried out to obtain a complementary analysis result. Finally, based on the first detection result, the second detection result, the third detection result, and the complementary analysis result, the root cause localization result is integrated to clarify the specific cause, scope of impact, and severity of the missing network measurement data, thereby accurately determining the cause of the missing network measurement data.

[0105] The network-side multi-dimensional measurement report includes at least periodically triggered measurement reports and event-triggered measurement reports. Based on the complementary analysis of core network user signaling data and network-side multi-dimensional measurement reports in step S4034 of this embodiment, the complementary analysis results can include the following steps: Step a1: Determine the user session duration based on core network user signaling data.

[0106] User session duration can be understood as the duration from when a user device accesses the network to when it disconnects, calculated from the session start time and end time in the core network user signaling data.

[0107] Specifically, the start and end timestamps of the user session are extracted from the collected core network user signaling data. The duration of the user session is calculated by subtracting the start time from the end time.

[0108] Step a2: Determine the reporting cycle based on the periodically triggered measurement report.

[0109] The reporting cycle can be understood as the preset periodic reporting time interval for periodically triggered measurement reports.

[0110] Specifically, the periodic measurement reporting interval configured on the base station side is read from the network configuration corresponding to the periodically triggered measurement report to determine the reporting period for that cell.

[0111] Step a3: Detect whether the user session duration is less than the reporting period.

[0112] The user session duration is compared with the reporting period to determine whether the user session duration is less than the reporting period.

[0113] Step a4: If no periodically triggered measurement report is found in the core network user signaling data, search for whether an event-triggered measurement report exists within the same session period.

[0114] When no corresponding periodically triggered measurement report is found for the core network user signaling data, an event-triggered measurement report is searched for within the same session period to cross-verify whether the measurement function is working properly. For example, within the same session period, a search is conducted to determine whether measurement reports triggered by various events such as A3, A2, and A5 events exist.

[0115] Step a5: If the user session duration is less than the reporting period and there are no event-triggered measurement reports within the same session period, then the complementarity analysis result is determined to be a reasonable missing result.

[0116] Specifically, if the user session duration is less than the reporting period and there are no event-triggered measurement reports within the same session period, the complementarity analysis result is considered a reasonably missing result. For example, if the user session duration is 6 seconds, the reporting period is 10 seconds, and there are no MREs within the same session, it is considered a reasonably missing result.

[0117] Step a6: If the user session duration is not less than the reporting period and there is no event-triggered measurement report within the same session period, then the complementarity analysis result is determined to be a configuration anomaly result.

[0118] If the user session duration is greater than or equal to the reporting period, and there are no event-triggered measurement reports within the same session period, the complementarity analysis result is determined to be a configuration anomaly. For example, if the user session duration is 20 seconds, the reporting period is 10 seconds, and there are no MREs within the same session, it is determined to be a configuration anomaly.

[0119] The network measurement data repair method provided by this invention, by combining the user session duration determined by core network user signaling data, the reporting cycle of periodically triggered measurement reports, and the existence status of event-triggered measurement reports within the same session period for complementary analysis, can accurately distinguish the data missing type. When the user session duration is less than the reporting cycle of periodically triggered measurement reports and there are no event-triggered measurement reports, it is determined to be a reasonable missing data. When the user session duration is not less than the reporting cycle of periodically triggered measurement reports and there are no event-triggered measurement reports, it is determined to be a configuration anomaly. This effectively improves the accuracy and pertinence of determining the root cause of missing network measurement reports.

[0120] The core network user signaling data includes the inactivity timer parameters of the user terminal. Based on the complementary analysis of the core network user signaling data and the network-side multi-dimensional measurement report in step S4034 of this embodiment, the complementary analysis results can include the following steps: Step b1: Determine the reporting cycle based on the periodically triggered measurement report.

[0121] By reading and parsing the network configuration parameters corresponding to the periodically triggered measurement reports from the network management configuration or the measurement data itself, the fixed reporting period of measurement data under the current cell or network element can be determined. For example, by reading the configuration parameters of the periodically triggered measurement report MRO in the cell measurement configuration, the measurement reporting period of the current cell can be determined to be 10 seconds.

[0122] Step b2: Check whether the inactivity timer parameter of the user terminal is less than the reporting period.

[0123] The user equipment inactivity timer parameter can be understood as the UE inactivity timer configured on the base station side, which specifically indicates the waiting time for the network to maintain the user connection when the user equipment has no data transmission.

[0124] Specifically, the inactivity timer parameter of the user equipment in the network element configuration is read, its value is compared with the reporting period, and it is determined whether the inactivity timer is less than the reporting period.

[0125] Step b3: If the inactivity timer parameter of the user terminal is not less than the reporting period, then the complementarity analysis result is determined to be an abnormal parameter setting result.

[0126] If the inactivity timer parameter of the user terminal is not less than the reporting period, it means that the user connection duration is sufficient to complete the measurement reporting. If the measurement report is still missing at this time, the complementarity analysis result can be directly determined to be an abnormal parameter setting result.

[0127] In a feasible scenario, the periodic measurement report configuration for the cell is read, and the reporting period is determined to be 10 seconds. The inactivity timer parameter of the user equipment in the cell is read, and it is found that the configuration is 3 seconds. After testing, it is determined that the inactivity timer parameter is less than the reporting period.

[0128] Record the result and continue analyzing other user samples. Analysis process for another sector within the same cell: The reporting period is confirmed to be 10 seconds. The inactivity timer parameter of the user equipment is read as 12 seconds, and it is determined that the inactivity timer parameter is not less than the reporting period. If the determination condition is met, the complementarity analysis result is directly identified as an abnormal parameter setting result. Based on this result, an automatic repair strategy is executed, uniformly correcting the inactivity timer to 10 seconds or more. Within 15 minutes after the repair, the XDR-MR matching rate of this cell recovers to 92%, data integrity returns to normal, and closed-loop governance is completed.

[0129] The network measurement data repair method provided by this invention determines the reporting period based on periodically triggered measurement reports, detects whether the user equipment inactivity timer parameter is less than the reporting period, and directly determines the complementarity analysis result as an abnormal parameter setting result when the user equipment inactivity timer parameter is not less than the reporting period. This method can quickly and accurately locate network measurement report anomalies caused by improper inactivity timer parameter configuration, and improves the efficiency and accuracy of root cause diagnosis of missing measurement report data.

[0130] Multi-source heterogeneous data also includes network performance and status data. Based on the complementary analysis of core network user signaling data and network-side multi-dimensional measurement reports in step S4034 of this embodiment, the complementary analysis results can be obtained through the following steps: Step c1: Identify the target core network user signaling data from the core network user signaling data that does not match the periodically triggered measurement report.

[0131] The target core network user signaling data can be understood as core network user signaling data that has corresponding signaling records during the association matching process, but which has not been matched with the periodically triggered measurement report.

[0132] Specifically, the collected core network user signaling data is fully correlated and matched with periodically triggered measurement reports to filter out records that have valid signaling records but cannot be matched with the corresponding periodic measurement data, and these records are identified as target core network user signaling data.

[0133] Step c2: Based on the target core network user signaling data, determine the serving cell where the user corresponding to the target core network user signaling data is located.

[0134] A serving cell can be understood as the cell where a user device is currently accessing and conducting services; it is the smallest statistical unit for network performance and status data.

[0135] Specifically, location fields such as cell identifier, base station identifier, and tracking area code are extracted from the target core network user signaling data. Based on the location information carried in the signaling, the serving cell accessed by the user during the measurement missing period is located.

[0136] Step c3: Based on the network performance of the serving cell, detect whether the signal strength of the serving cell is less than the strength threshold.

[0137] The strength threshold can be understood as a pre-set threshold for acceptable signal strength.

[0138] Specifically, the network performance data corresponding to the identified serving cell is read, the signal strength index of the cell in the missing time period is extracted, and it is compared with the preset strength threshold to determine whether the signal strength is lower than the qualified standard.

[0139] Step c4: Based on the status data of the serving cell, detect whether the signal-to-noise ratio of the serving cell is less than the signal-to-noise ratio threshold.

[0140] Status data can be understood as a set of data on the operating status of the serving cell, link quality, and interference, which may include signal-to-noise ratio, data rate, bit error rate, connection success rate, etc.

[0141] The signal-to-noise ratio threshold can be understood as a pre-set acceptable signal-to-noise ratio threshold.

[0142] Specifically, the status data corresponding to the serving cell is read, the signal-to-noise ratio (SNR) index of the cell during the measurement missing period is extracted, and it is compared with the preset SNR threshold.

[0143] Step c5: If the signal strength of the serving cell is less than the strength threshold and the signal-to-noise ratio is less than the signal-to-noise ratio threshold, the complementarity analysis result is determined to be a weak coverage result.

[0144] When a serving cell simultaneously meets two conditions—signal strength less than the strength threshold and signal-to-noise ratio (SNR) less than the SNR threshold—it indicates a poor wireless environment that prevents measurement reporting. The system ultimately determines the complementarity analysis result as weak coverage. For example, if the serving cell has a signal strength of -118 dBm (less than the -110 dBm threshold) and an SINR of -3 dB (less than the 3 dB threshold), the complementarity analysis result is determined to be weak coverage.

[0145] In one possible implementation scenario, the signaling data of all core network users is correlated and matched with periodically triggered measurement reports to filter out a large number of records with signaling records but no MRO (Maintenance, Repair, and Overhaul) information, which are identified as the target core network user signaling data. Cell identifiers are extracted from the target signaling data, and the user is located in a roadside cell (CI=56982), which is identified as the serving cell. Network performance data of this serving cell is read; the average signal strength (RSRP) during the time period is -119dBm, while the preset strength threshold is -110dBm, indicating the signal strength is below the threshold. Cell status data is read; the average signal-to-noise ratio (SINR) during the time period is -2dB, while the preset SINR threshold is 3dB, indicating the SINR is below the threshold. Since both indicators are below the preset thresholds, the complementarity analysis result is ultimately determined to be weak coverage.

[0146] The network measurement data repair method provided by this invention locates the corresponding serving cell by using core network user signaling data that has never matched a periodically triggered measurement report. It then combines the network performance data of the serving cell to detect whether the signal strength is lower than the strength threshold and the status data to detect whether the signal-to-noise ratio is lower than the signal-to-noise ratio threshold. When both the signal strength and the signal-to-noise ratio are lower than the corresponding thresholds, it is directly determined to be a weak coverage result. This method can quickly and accurately identify the problem of missing periodically triggered measurement reports caused by weak coverage environment, and improve the efficiency and accuracy of locating the root cause of network measurement data anomalies.

[0147] Based on the complementary analysis of core network user signaling data and network-side multi-dimensional measurement reports in step S4034 of this embodiment, the complementary analysis results can be obtained through the following steps: Step d1: Determine the user session duration based on core network user signaling data. Please refer to step a1 above for details, which will not be elaborated upon here.

[0148] Step d2: Based on the periodically triggered measurement report, determine the reporting cycle. Please refer to step a2 above for details, which will not be elaborated further here.

[0149] Step d3 involves checking if the user session duration is less than the reporting period. Please refer to step a3 above for details; further explanation is omitted here.

[0150] Step d4: If the user session duration is not less than the reporting period, and the core network user signaling data does not match the network-side multi-dimensional measurement report, then the complementarity analysis result is determined to be a time anomaly result.

[0151] When two conditions are met simultaneously: the user session duration is not less than the reporting period, and the core network user signaling data does not match any network-side multi-dimensional measurement report, it indicates that the user connection duration is sufficient to complete the measurement reporting, but no measurement data is generated. The complementarity analysis result is determined to be a time anomaly.

[0152] In one possible implementation scenario, the access and release times of multiple users are extracted from the core network user signaling data. The calculated user session durations are 20 seconds, 30 seconds, and 40 seconds, all of which are relatively long sessions. The periodically triggered measurement report configuration for this cell is read, and the reporting period is determined to be 10 seconds. The user session durations are compared with the reporting period, and it is determined that the user session durations of all users are not less than the reporting period. Further detection reveals that the core network user signaling data of the above users does not match any network-side multi-dimensional measurement reports, such as periodically triggered measurement reports or event triggered measurement reports, which meets the time anomaly judgment conditions. Therefore, the complementarity analysis result is determined to be a time anomaly result.

[0153] The network measurement data repair method provided by this invention determines the user session duration based on core network user signaling data, determines the reporting period based on periodically triggered measurement reports, and detects whether the user session duration is less than the reporting period. When the user session duration is not less than the reporting period and the core network user signaling data does not match the network-side multi-dimensional measurement report, the complementarity analysis result is directly determined to be a time anomaly result. This method can accurately determine the measurement report missing caused by time issues related to user session duration, thereby improving the accuracy and reliability of root cause localization of measurement data anomalies.

[0154] Based on the root cause localization results, determining the remediation strategy corresponding to the root cause localization results in step S204 of this embodiment may include the following steps: Step e1: Based on the root cause localization results and the preset mapping relationship, determine the repair strategy corresponding to the root cause localization results.

[0155] The preset mapping relationship can be understood as the correspondence rules between the root cause localization results and the repair strategies that are predefined and stored in the strategy library.

[0156] Specifically, the system reads the generated root cause localization results, retrieves pre-configured mapping relationships from the policy library, accurately matches the root cause type with standard handling actions, and automatically queries and determines the remediation strategy to be executed for the current root cause. For example, when the root cause localization result is missing measurement subscription or full user reporting not enabled, based on the rules for configuring anomalies, automatically issuing measurement subscriptions, and enabling full reporting in the pre-configured mapping relationships, the remediation strategy is determined to be automatically sending measurement subscription configuration instructions to the network management platform, enabling periodic measurement report and event measurement report subscriptions, and setting the network element reporting mode to full user reporting.

[0157] The network measurement data repair method provided by this invention directly determines the corresponding repair strategy by matching the root cause location result with the preset mapping relationship. This enables precise matching of abnormal root causes and handling solutions, and quickly outputs suitable repair measures, thereby improving the automation level and processing efficiency of network measurement data integrity assurance.

[0158] In some embodiments, the network measurement data repair device of the present invention can be implemented in a combination of hardware and software. As an example, the network measurement data repair device of the present invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the network measurement data repair method of the present invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0159] The modules described in the embodiments of this invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0160] An electronic device according to an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-mentioned network measurement data repair methods. That is, an electronic device according to an embodiment of the present invention may include, but is not limited to: a processor and a memory; the memory is used to store the computer program; the processor is used to execute the network measurement data repair method shown in any embodiment of the present invention by calling the computer program.

[0161] In one alternative embodiment, an electronic device is provided, such as Figure 5 As shown, Figure 5 The illustrated electronic device 5000 includes a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are connected, for example, via a bus 5002. Optionally, the electronic device 5000 may further include a transceiver 5004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 5004 is not limited to one type, and the structure of the electronic device 5000 does not constitute a limitation on the embodiments of the present invention.

[0162] Processor 5001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 5001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0163] Bus 5002 may include a path for transmitting information between the aforementioned components. Bus 5002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 5002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5The bus 5002 is represented by only one thick line, but this does not mean that there is only one bus or one type of bus.

[0164] The memory 5003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0165] The memory 5003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 5001. The processor 5001 executes the application code stored in the memory 5003 to implement the content shown in the foregoing method embodiments.

[0166] Among them, electronic devices can also be terminal devices, which can be any device that can install applications, including at least one of smartphones, tablets, laptops, desktop computers, smart speakers, smartwatches, smart TVs, and smart in-vehicle devices.

[0167] It should be noted that, Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0168] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-described methods for repairing network measurement data.

[0169] Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CD-ROM), magnetic tape, a floppy disk, and an optical data storage device, etc.

[0170] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the aforementioned method for repairing network measurement data.

[0171] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0172] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0173] The computer-readable storage medium provided in this invention can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EEPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0174] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0175] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0176] It should be noted that the terms "first," "second," etc., used in the specification and claims of this invention are used to distinguish similar objects and do not imply a specific order or sequence. Where appropriate, the order of use for similar objects can be interchanged so that the embodiments of the invention described herein can be implemented in an order other than that shown or described.

[0177] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this invention can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0178] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for repairing network measurement data, characterized in that, The method includes: Acquire multi-source heterogeneous data; wherein, the multi-source heterogeneous data includes at least core network user signaling data and network-side multi-dimensional measurement reports; Based on the aforementioned multi-source heterogeneous data, the integrity of network measurement data is dynamically evaluated to determine the target matching rate; wherein, the target matching rate is the matching rate between core network user signaling data and network-side multi-dimensional measurement reports. If the target matching rate is less than the matching rate threshold, the root cause localization result is determined based on the multi-source heterogeneous data; wherein, the root cause localization result indicates the reason for the missing network measurement data; Based on the root cause localization results, a corresponding repair strategy is determined, and the network measurement data is repaired based on the repair strategy.

2. The method for repairing network measurement data according to claim 1, characterized in that, Based on the aforementioned multi-source heterogeneous data, a dynamic integrity assessment of the network measurement data is performed to determine the target matching rate, including: Construct a unified index key for linking core network user signaling data with multi-dimensional measurement reports from the network side; Based on the unified index key, the target number of network-side multi-dimensional measurement reports successfully associated with core network user signaling data is counted within a preset time granularity. The target matching rate is determined based on the ratio of the target number to the total number of core network user signaling data.

3. The method for repairing network measurement data according to claim 1, characterized in that, The multi-source heterogeneous data also includes network configuration and operating parameters. The determination of root cause localization results based on the multi-source heterogeneous data includes: Based on the network configuration and the operating parameters, the data acquisition subscription status of the network unit is detected to see if it conforms to the preset subscription status, and a first detection result is obtained. The second detection result is obtained by detecting whether the reporting status of all users of the network element meets the preset reporting status. The system checks whether the switch status reported in the call history matches the preset switch status, and obtains a third detection result. Complementary analysis was performed on core network user signaling data and network-side multi-dimensional measurement reports to obtain complementary analysis results; Based on the first detection result, the second detection result, the third detection result, and the complementarity analysis result, the root cause localization result is determined.

4. The method for repairing network measurement data according to claim 3, characterized in that, The network-side multi-dimensional measurement report includes at least periodically triggered measurement reports and event-triggered measurement reports. The complementary analysis processing of core network user signaling data and network-side multi-dimensional measurement reports to obtain complementary analysis results includes: Based on the core network user signaling data, the user session duration is determined; Based on the periodically triggered measurement report, the reporting cycle is determined; Detect whether the user session duration is less than the reporting period; If no periodically triggered measurement report is found in the core network user signaling data, search for whether an event-triggered measurement report exists within the same session period; If the user session duration is less than the reporting period, and there is no event-triggered measurement report within the same session period, then the complementarity analysis result is determined to be a reasonable missing result. If the duration of the user session is not less than the reporting period, and there is no event-triggered measurement report within the same session period, then the complementarity analysis result is determined to be a configuration anomaly result.

5. The method for repairing network measurement data according to claim 3, characterized in that, The core network user signaling data includes inactivity timer parameters for user terminals. The complementary analysis processing of the core network user signaling data and the network-side multi-dimensional measurement reports yields complementary analysis results, including: Based on the periodically triggered measurement report, the reporting cycle is determined; Detect whether the inactivity timer parameter of the user terminal is less than the reporting period; If the inactivity timer parameter of the user terminal is not less than the reporting period, then the complementarity analysis result is determined to be an abnormal parameter setting result.

6. The method for repairing network measurement data according to claim 3, characterized in that, The multi-source heterogeneous data also includes network performance and status data; The complementary analysis of core network user signaling data and network-side multi-dimensional measurement reports yields complementary analysis results, including: Identify target core network user signaling data from core network user signaling data that do not match periodically triggered measurement reports; Based on the target core network user signaling data, determine the serving cell where the user corresponding to the target core network user signaling data is located; Based on the network performance of the serving cell, detect whether the signal strength of the serving cell is less than a strength threshold. Based on the status data of the serving cell, detect whether the signal-to-noise ratio of the serving cell is less than the signal-to-noise ratio threshold; If the signal strength of the serving cell is less than the strength threshold and the signal-to-noise ratio is less than the signal-to-noise ratio threshold, the complementarity analysis result is determined to be a weak coverage result.

7. The method for repairing network measurement data according to claim 3, characterized in that, The complementary analysis of core network user signaling data and network-side multi-dimensional measurement reports yields complementary analysis results, including: Based on the core network user signaling data, the user session duration is determined; Based on the periodically triggered measurement report, the reporting cycle is determined; Detect whether the user session duration is less than the reporting period; If the user session duration is not less than the reporting period, and the core network user signaling data does not match the network-side multi-dimensional measurement report, then the complementarity analysis result is determined to be a time anomaly result.

8. The method for repairing network measurement data according to claim 1, characterized in that, Based on the root cause localization results, the corresponding remediation strategy is determined, including: Based on the root cause localization results and the preset mapping relationship, the repair strategy corresponding to the root cause localization results is determined.

9. A device for repairing network measurement data, characterized in that, The device includes: The acquisition module is used to acquire multi-source heterogeneous data; wherein, the multi-source heterogeneous data includes at least core network user signaling data and network-side multi-dimensional measurement reports; The first determining module is used to perform a dynamic integrity assessment of network measurement data based on the multi-source heterogeneous data, and determine the target matching rate; wherein, the target matching rate is the matching rate between core network user signaling data and network-side multi-dimensional measurement reports; The second determining module is used to determine the root cause localization result based on the multi-source heterogeneous data if the target matching rate is less than the matching rate threshold; wherein the root cause localization result indicates the reason for the missing network measurement data. The repair module is used to determine the repair strategy corresponding to the root cause localization result based on the root cause localization result, and to perform repair of network measurement data based on the repair strategy.

10. An electronic device, characterized in that, include: A processor and a memory connected to the processor; wherein the memory stores instructions executable by the processor, the instructions being executed by the processor to cause the processor to perform a method for repairing network measurement data as described in any one of claims 1-8.

Images