Data acquisition method and apparatus, device, medium, and program product

Abstract

The present application relates to a data acquisition method and apparatus, a device, a medium, and a program product. The method comprises: receiving first network data sent by a data acquisition device, wherein the first network data is network data of a current period, which is acquired from a network element device by the data acquisition device sending a first data acquisition request for the current period to the network element device at a first time point; on the basis of the first network data, performing acquisition time analysis to obtain a second time point for the next data acquisition; on the basis of a data missing rate in the first network data, performing acquisition period analysis to obtain a target period for the next data acquisition; and sending the second time point and the target period to the data acquisition device, so as to instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point and acquire second network data of the target period from the network element device. By using the present method, the timeliness and completeness of traffic statistics data can be improved.

Description

Data acquisition methods, devices, equipment, media and software products

[0001] This application claims priority to Chinese Patent Application No. 2024104937248, filed on April 23, 2024, entitled “Data Acquisition Method, Apparatus, Device, Media and Program Product”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a data acquisition method, apparatus, device, medium, and program product. Background Technology

[0003] In communication networks, network elements periodically output call statistics data, such as call volume statistics and traffic statistics. Technicians frequently need to collect this data using data acquisition devices. Currently, data acquisition devices typically collect call statistics data from network elements based on scheduled tasks. Because the periodic output of call statistics data by network elements introduces a delay, the data acquisition device needs to delay its collection task for each data collection period. If a uniform delay time is applied to all network elements in the communication network, the data timeliness is poor. If the delay time is determined based on the device model, then when a new network element needs to be added, the corresponding delay time needs to be manually set.

[0004] Due to factors such as network congestion and limited equipment resources, the time when network element devices output call statistics data may fluctuate. Scheduled data collection tasks may occasionally result in missing or distorted data. Meanwhile, conventional data supplementation methods are somewhat delayed, thus failing to guarantee the timeliness and integrity of call statistics data collection.

[0005] Summary of the Invention

[0006] Therefore, it is necessary to provide a data acquisition method, device, equipment, medium, and program product that can improve the timeliness and integrity of call statistics data acquisition in response to the above-mentioned technical problems.

[0007] In a first aspect, this application provides a data acquisition method, the method comprising:

[0008] The system receives first network data sent by a data acquisition device. The first network data is network data for the current period that the data acquisition device collects from the network element device at a first time point by sending a first data acquisition request for the current period to the network element device.

[0009] Based on the first network data, the collection time analysis is performed to obtain the second time point of the next data collection;

[0010] Based on the data missing rate in the first network data, the collection cycle is analyzed to obtain the target cycle for the next data collection, wherein the target cycle is the current cycle or the cycle following the current cycle.

[0011] The second time point and the target period are sent to the data acquisition device. The second time point and the target period are used to instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data of the target period from the network element device.

[0012] Secondly, this application provides a data acquisition device, the device comprising:

[0013] The receiving module is used to receive first network data sent by the data acquisition device. The first network data is the network data of the current period that the data acquisition device acquires from the network element device at a first time point by sending a first data acquisition request for the current period to the network element device at a first time point.

[0014] The analysis module is used to perform collection time analysis based on the first network data to obtain the second time point of the next data collection; and to perform collection cycle analysis based on the data missing rate in the first network data to obtain the target cycle of the next data collection, wherein the target cycle is the current cycle or the cycle after the current cycle.

[0015] The first sending module is used to send the second time point and the target period to the data acquisition device. The second time point and the target period are used to instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data of the target period from the network element device.

[0016] Thirdly, this application provides a data acquisition method, the method comprising:

[0017] Send a first data collection request for the current period to the network element device at the first time point, so as to collect the first network data of the current period from the network element device;

[0018] The first network data is sent to the data analysis device. The first network data is used to instruct the data analysis device to perform collection time analysis based on the first network data to obtain the second time point of the next data collection, and to perform collection cycle analysis based on the data missing rate in the first network data to obtain the target cycle of the next data collection. The target cycle is the current cycle or the next cycle of the current cycle.

[0019] At the second time point, a second data acquisition request for the target period is sent to the network element device to acquire second network data for the target period from the network element device.

[0020] Fourthly, this application provides a data acquisition device, the device comprising:

[0021] The acquisition module is used to send a first data acquisition request for the current period to the network element device at a first time point, so as to acquire the first network data of the current period from the network element device;

[0022] The second sending module is used to send the first network data to the data analysis device. The first network data is used to instruct the data analysis device to perform collection time analysis based on the first network data to obtain the second time point of the next data collection, and to perform collection cycle analysis based on the data missing rate in the first network data to obtain the target cycle of the next data collection. The target cycle is the current cycle or the next cycle of the current cycle.

[0023] The acquisition module is used to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data for the target period from the network element device.

[0024] Fifthly, this application provides a data analysis device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the various method embodiments of this application.

[0025] In a sixth aspect, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the various method embodiments of this application.

[0026] In a seventh aspect, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps in the various method embodiments of this application.

[0027] The aforementioned data acquisition method, apparatus, device, medium, and program product receive first network data sent by a data acquisition device. This first network data is the network data for the current period acquired by the data acquisition device from the network element device at a first time point after sending a first data acquisition request for the current period. Based on the first network data, the acquisition time is analyzed to obtain a second time point for the next data acquisition. Based on the data missing rate in the first network data, the acquisition period is analyzed to obtain a target period for the next data acquisition, where the target period is the current period or the period following the current period. The second time point and the target period are sent to the data acquisition device, instructing the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data for the target period from the network element device. Compared to the timed data acquisition methods of related technologies, this application predicts the time point for the next data acquisition by analyzing the acquisition time of the network data for the current period, thus achieving successful triggering of the data acquisition task without setting a timed task. Furthermore, by analyzing the data missing rate in the network data of the current period, it is possible to determine whether the next data collection period is the current period or the period after the current period. That is, to determine whether to continue collecting data for the next period or to re-collect data for the current period, so as to avoid data missing and data distortion, thereby improving the timeliness and integrity of network data collection. Attached Figure Description

[0028] Figure 1 is an application environment diagram of a data acquisition method in one embodiment;

[0029] Figure 2 is a flowchart illustrating a data acquisition method in one embodiment;

[0030] Figure 3 is a flowchart illustrating the data acquisition method in another embodiment;

[0031] Figure 4 is a schematic diagram of the process of collecting network data for the second period after collecting network data for the first period in one embodiment.

[0032] Figure 5 is a schematic diagram of the process for supplementing network data collection in the first cycle in one embodiment;

[0033] Figure 6 is a model architecture diagram of the acquisition time prediction model in one embodiment;

[0034] Figure 7 is a structural block diagram of a data acquisition device in one embodiment;

[0035] Figure 8 is a structural block diagram of the data acquisition device in another embodiment;

[0036] Figure 9 is an internal structure diagram of a data analysis device in one embodiment. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0038] The data acquisition method provided in this application can be applied to the application environment shown in Figure 1. In this method, network element device 102 communicates with data acquisition device 104 via a network, and data acquisition device 104 communicates with data analysis device 106 via a network. In some embodiments, data analysis device 106 can receive first network data sent by data acquisition device 104. This first network data is network data for the current period acquired by data acquisition device 104 from network element device 102 at a first time point, based on a first data acquisition request for the current period sent by data acquisition device 104 to network element device 102. Data analysis device 106 can perform acquisition time analysis based on the first network data to obtain a second time point for the next data acquisition, and perform acquisition period analysis based on the data missing rate in the first network data to obtain a target period for the next data acquisition, where the target period is the current period or the period following the current period. The data analysis device 106 can send a second time point and a target period to the data acquisition device 104. The second time point and target period are used to instruct the data acquisition device 104 to send a second data acquisition request for the target period to the network element device 102 at the second time point, so as to acquire second network data for the target period from the network element device 102. It is understood that this embodiment is not limited in this respect, and the application scenario in Figure 1 is merely illustrative and not limited thereto.

[0039] In one embodiment, as shown in FIG2, a data acquisition method is provided. Taking the data analysis device 106 in FIG1 as an example, this embodiment includes the following steps:

[0040] Step 202: Receive the first network data sent by the data acquisition device. The first network data is the network data of the current period that the data acquisition device obtains from the network element device at the first time point by sending the first data acquisition request for the current period to the network element device.

[0041] In some embodiments, network elements may periodically output call statistics data, such as call volume statistics and traffic statistics. The call statistics data is included in the network data for the network element; additionally, the network data also includes collection details related to the collection of the call statistics data. A data acquisition device may send a first data acquisition request for the current period to the network element at a first point in time to collect first network data for the current period from the network element. The data acquisition device may send the first network data to a data analysis device, and the data analysis device may receive the first network data sent by the data acquisition device.

[0042] Step 204: Analyze the acquisition time based on the first network data to obtain the second time point for the next data acquisition.

[0043] In some embodiments, since network elements periodically output call statistics data, data acquisition devices need to collect call statistics data output by network elements in different periods. It can be understood that the data acquisition device will collect network data containing call statistics data multiple times to collect call statistics data for different periods. The data analysis device can perform collection time analysis on the first network data of the current period to obtain the second time point for the next data collection, thereby notifying the data acquisition device to perform the next data collection at the second time point. This allows for network data collection for the next period of the current period, or for re-collecting data for the current period, i.e., supplementary collection, to avoid data loss or distortion. This also eliminates the need to set a scheduled task to trigger the data collection task.

[0044] In one embodiment, the data analysis device can extract features from the first network data of the current period to obtain the network data features of the first network data. Then, based on the network data features, the data analysis device can predict the collection time to obtain a second time point for the next data collection, thereby notifying the data collection device to perform the next data collection at the second time point, without needing to set a scheduled task to trigger the data collection task.

[0045] Step 206: Based on the data missing rate in the first network data, perform a data collection cycle analysis to obtain the target cycle for the next data collection. The target cycle is the current cycle or the cycle following the current cycle.

[0046] The missing data rate can be used to characterize the completeness of the network data collected in the current period during this data collection. It can be understood that the missing data rate is negatively correlated with the completeness of the network data collected in the current period during this data collection; that is, the higher the completeness of the network data collected in the current period during this data collection, the lower the missing data rate, and vice versa.

[0047] In some embodiments, the data analysis device may perform collection cycle analysis based on the data missing rate in the first network data to determine whether the target cycle for the next data collection is the current cycle or the cycle after the current cycle, that is, to determine whether the network data of the current cycle needs to be re-collected.

[0048] In one embodiment, when the data missing rate in the first network data is 0, the data analysis device can determine the next period of the current period as the target period for the next data collection. When the data missing rate in the first network data is not 0, the data analysis device can determine the current period as the target period for the next data collection, so as to re-collect the network data of the current period, thereby avoiding the loss or distortion of network data in the current period.

[0049] Step 208: Send a second time point and target period to the data acquisition device. The second time point and target period are used to instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire the second network data of the target period from the network element device.

[0050] In some embodiments, the data analysis device may send a second time point and a target period to the data acquisition device. The data acquisition device may receive the second time point and the target period, and send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data for the target period from the network element device. It can be understood that if the target period is the current period, the second network data is consistent with the first network data of the current period, and it can be understood that the data acquisition unit has re-acquired the network data of the current period. When the target period is the next period after the current period, the second network data is the network data of the next period after the current period.

[0051] In the aforementioned data acquisition method, the following steps are taken: First network data is received from a data acquisition device. This first network data is the network data for the current period collected from the network element device by the data acquisition device sending a first data acquisition request for the current period at a first time point. Based on the first network data, acquisition time analysis is performed to obtain a second time point for the next data acquisition. Based on the data missing rate in the first network data, acquisition period analysis is performed to obtain a target period for the next data acquisition, which is either the current period or the period following the current period. The second time point and target period are then sent to the data acquisition device. These two points instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to collect second network data for the target period from the network element device. Compared to the timed data acquisition methods of related technologies, this application predicts the time point for the next data acquisition by analyzing the acquisition time of the network data for the current period, thus achieving successful triggering of the data acquisition task without setting a scheduled task. Furthermore, by analyzing the data missing rate in the network data of the current period, it is possible to determine whether the next data collection period is the current period or the period after the current period. That is, to determine whether to continue collecting data for the next period or to re-collect data for the current period, so as to avoid data missing and data distortion, thereby improving the timeliness and integrity of network data collection.

[0052] In one embodiment, performing acquisition time analysis based on first network data to obtain a second time point for the next data acquisition includes: inputting the first network data into a trained acquisition time prediction model to extract network data features of the first network data through the trained acquisition time prediction model; and performing acquisition time prediction based on the network data features to obtain a second time point for the next data acquisition.

[0053] In some embodiments, the data analysis device can input first network data into a trained acquisition time prediction model to extract features from the first network data using the trained acquisition time prediction model, thereby obtaining network data features of the first network data. Furthermore, the data analysis device can use the trained acquisition time prediction model to predict the acquisition time based on the network data features, thus obtaining a second time point for the next data acquisition.

[0054] In the above embodiments, the network data features of the first network data are extracted by the trained acquisition time prediction model, and the acquisition time is predicted based on the network data features to obtain the second time point of the next data acquisition. This can improve the prediction accuracy of the second time point of the next data acquisition, thereby further improving the timeliness and integrity of network data acquisition.

[0055] In one embodiment, the method further includes a model training step, which includes: acquiring a historical network data sequence containing historical network data from multiple historical periods collected from network element devices; inputting the historical network data sequence into a collection time prediction model to be trained, so as to predict the predicted collection time points corresponding to the historical network data contained in the historical network data sequence based on the historical network data sequence; acquiring reference collection time points corresponding to the historical network data contained in the historical network data sequence; and training the collection time prediction model to be trained based on the differences between the predicted collection time points corresponding to the historical network data contained in the historical network data sequence and the corresponding reference collection time points, thereby obtaining a trained collection time prediction model.

[0056] In some embodiments, the data analysis device can acquire historical network data sequences corresponding to network elements. These historical network data sequences contain historical network data from multiple historical periods collected from the network elements. The data analysis device can input these historical network data sequences into a data acquisition time prediction model to be trained, so that the model can predict the predicted acquisition time points corresponding to each historical network data point within the historical network data sequence. The data analysis device can also acquire reference acquisition time points corresponding to each historical network data point within the historical network data sequence. Each historical network data point contains a reference acquisition time point recorded when it was acquired by the data acquisition device, and the data analysis device can directly extract the corresponding reference acquisition time points from the historical network data. Based on the difference between the predicted acquisition time points and the corresponding reference acquisition time points for each historical network data point within the historical network data sequence, the data analysis device can determine the loss value for model training and iteratively train the data acquisition time prediction model to be trained in the direction that reduces the loss value, thereby obtaining a trained data acquisition time prediction model.

[0057] In the above embodiments, the acquisition time prediction model to be trained predicts the predicted acquisition time points corresponding to the historical network data contained in the historical network data sequence based on the historical network data sequence. The acquisition time prediction model to be trained is trained according to the difference between the predicted acquisition time points corresponding to the historical network data contained in the historical network data sequence and the corresponding reference acquisition time points, thereby obtaining a trained acquisition time prediction model. This can improve the accuracy of the trained acquisition time prediction model, thereby further improving the timeliness and integrity of network data acquisition.

[0058] In one embodiment, the collection cycle analysis is performed based on the data missing rate in the first network data to obtain the target cycle for the next data collection, including: when the data missing rate in the first network data is less than or equal to a preset missing rate, the next cycle of the current cycle is determined as the target cycle for the next data collection; when the data missing rate in the first network data is greater than the preset missing rate, the current cycle is determined as the target cycle for the next data collection.

[0059] In some embodiments, the data analysis device can compare the data missing rate in the first network data with a preset missing rate. When the data missing rate in the first network data is less than or equal to the preset missing rate, it indicates that there is little or no missing data. In this case, the data analysis device can determine the next period as the target period for the next data collection, and continue to collect network data for the next period. When the data missing rate in the first network data is greater than the preset missing rate, it indicates that there is a lot of missing data. In this case, the data analysis device can determine the current period as the target period for the next data collection, and re-collect the network data for the current period, i.e., data supplementation, to avoid missing network data for the current period.

[0060] In the above embodiments, when the data missing rate in the first network data is less than or equal to the preset missing rate, it indicates that there is little or no missing data. In this case, by determining the next period of the current period as the target period for the next data collection, and continuing to collect network data for the next period, the timeliness of network data collection can be improved, further enhancing the timeliness of network data collection. When the data missing rate in the first network data is greater than the preset missing rate, it indicates that there is a lot of missing data. In this case, by determining the current period as the target period for the next data collection, and re-collecting the network data for the current period, network data missing or distortion can be avoided, further improving the data integrity of the network data.

[0061] In one embodiment, the network data of the network element device includes call statistics data and collection details data. The collection details data includes at least one of the following: data missing rate, data collection time, device model of the data collection device, resource usage data of the data collection device, device model of the network element device, resource usage data of the network element device, or network status data.

[0062] In one embodiment, the network data of the network element device includes call statistics data and collection details data. The collection details data includes data missing rate, data collection time, device model of the data collection device, resource usage data of the data collection device, device model of the network element device, resource usage data of the network element device, and network status data, etc.

[0063] In some embodiments, the data acquisition device sends a first data acquisition request for the current period to the network element device at a first time point. The first network data for the current period acquired from the network element device can be understood as including call statistics data and acquisition details data for the current period. The data acquisition device can send the first network data to a data analysis device, which can receive the first network data sent by the data acquisition device. The data analysis device can perform acquisition time analysis based on the first network data to obtain a second time point for the next data acquisition, and perform acquisition period analysis based on the data missing rate in the first network data to obtain a target period for the next data acquisition, wherein the target period is the current period or the period following the current period. Furthermore, the data analysis device can send the second time point and the target period to the data acquisition device. The data acquisition device can send a second data acquisition request for the target period to the network element device at the second time point to acquire second network data for the target period from the network element device. It can be understood that the second network data includes call statistics data and acquisition details data for the target period.

[0064] In the above embodiments, by limiting the collection details data in the network data to include at least one of the following: data missing rate, data collection time, device model of data collection device, resource usage data of data collection device, device model of network element device, resource usage data of network element device, or network status data, the prediction accuracy of the second time point and target period of the next data collection can be improved, thereby further improving the timeliness and integrity of network data collection.

[0065] In one embodiment, as shown in FIG3, a data acquisition method is provided. This embodiment uses the data acquisition device 104 in FIG1 as an example for illustration, including the following steps:

[0066] Step 302: Send a first data collection request for the current period to the network element device at the first time point to collect the first network data of the current period from the network element device.

[0067] Step 304: Send first network data to the data analysis device. The first network data is used to instruct the data analysis device to perform collection time analysis based on the first network data to obtain the second time point of the next data collection, and to perform collection cycle analysis based on the data missing rate in the first network data to obtain the target cycle of the next data collection. The target cycle is the current cycle or the next cycle after the current cycle.

[0068] Step 306: At the second time point, send a second data acquisition request for the target period to the network element device to acquire the second network data of the target period from the network element device.

[0069] In some embodiments, network elements may periodically output call statistics data, such as call volume statistics and traffic statistics. The call statistics data is included in the network data for the network element; additionally, the network data also includes collection details related to the collection of the call statistics data. A data acquisition device may send a first data acquisition request for the current period to the network element at a first point in time to collect the first network data for the current period from the network element. The data acquisition device may send the first network data to a data analysis device, which may receive the first network data sent by the data acquisition device. Because the network element periodically outputs call statistics data, the data acquisition device needs to collect the call statistics data output by the network element in different periods. It is understandable that data acquisition equipment will collect network data, including call statistics data, multiple times to collect call statistics data for different periods. Data analysis equipment can analyze the collection time of the first network data of the current period to obtain the second time point for the next data collection. This allows the data acquisition equipment to be notified to perform the next data collection at the second time point, thus enabling network data collection for the next period of the current cycle, or to re-collect data for the current cycle, i.e., supplementary collection, to avoid data loss or distortion. This also eliminates the need to set a scheduled task to trigger the data collection task. Data analysis equipment can analyze the collection cycle based on the data loss rate in the first network data to determine whether the target period for the next data collection is the current period or the period following the current period, i.e., whether to re-collect network data for the current period. Data analysis equipment can send the second time point and the target period to the data acquisition equipment. The data acquisition equipment can receive the second time point and the target period, and at the second time point, send a second data collection request for the target period to the network element equipment to collect the second network data for the target period from the network element equipment. It is understandable that if the target period is the current period, then the second network data is consistent with the first network data of the current period, meaning the data acquisition unit has re-acquired the network data for the current period. When the target period is the next period after the current period, then the second network data is the network data for the next period after the current period.

[0070] In the above embodiments, a first data acquisition request for the current period is sent to the network element device at a first time point to collect first network data for the current period from the network element device. The first network data is then sent to a data analysis device. This first network data instructs the data analysis device to perform acquisition time analysis based on the first network data to obtain a second time point for the next data acquisition, and to perform acquisition period analysis based on the data missing rate in the first network data to obtain a target period for the next data acquisition. The target period is the current period or the period following the current period. At the second time point, a second data acquisition request for the target period is sent to the network element device to collect second network data for the target period from the network element device. Compared to the timed data acquisition methods of related technologies, this application predicts the time point for the next data acquisition by performing acquisition time analysis on the network data of the current period, thus achieving successful triggering of the data acquisition task without setting a timed task. Furthermore, by analyzing the data missing rate in the network data of the current period, it is possible to determine whether the next data collection period is the current period or the period after the current period. That is, to determine whether to continue collecting data for the next period or to re-collect data for the current period, so as to avoid data missing and data distortion, thereby improving the timeliness and integrity of network data collection.

[0071] In one embodiment, as shown in Figure 4, the data analysis device includes a data storage unit, a model training unit, and a data analysis unit. The data storage unit stores historical network data sequences. The model training unit can obtain the historical network data sequences from the data storage unit and input them into a data acquisition time prediction model to be trained. Based on the historical network data sequences, the model predicts the predicted acquisition time points corresponding to the historical network data contained in the historical network data sequences, obtains the reference acquisition time points corresponding to the historical network data contained in the historical network data sequences, and trains the data acquisition time prediction model to be trained based on the differences between the predicted acquisition time points and the corresponding reference acquisition time points. The model training unit can then deploy the trained data acquisition time prediction model to the data analysis unit. The data acquisition device sends a first data acquisition request for the first period to the network element device at a first time point, acquires the first network data for the first period from the network element device, and stores the first network data in the data storage unit. The data analysis unit can obtain first network data from the data storage unit and input it into a trained acquisition time prediction model. The model extracts network data features from the first network data and predicts the acquisition time based on these features to obtain the second time point for the next data acquisition. When the data missing rate in the first network data is less than or equal to a preset missing rate, the data analysis unit can determine the next period after the first period, i.e., the second period, as the target period for the next data acquisition. The data analysis unit can send an analysis report containing the second time point and the second period to the data acquisition device. Based on the analysis report, the data acquisition device sends a second data acquisition request for the second period to the network element device at the second time point to acquire the second network data for the second period from the network element device.

[0072] In one embodiment, as shown in Figure 5, the data analysis device includes a data storage unit, a model training unit, and a data analysis unit. The data storage unit stores historical network data sequences. The model training unit can obtain the historical network data sequences from the data storage unit and input them into a data acquisition time prediction model to be trained. Based on the historical network data sequences, the model predicts the predicted acquisition time points corresponding to the historical network data contained in the historical network data sequences, obtains the reference acquisition time points corresponding to the historical network data contained in the historical network data sequences, and trains the data acquisition time prediction model to be trained based on the differences between the predicted acquisition time points and the corresponding reference acquisition time points. The model training unit can then deploy the trained data acquisition time prediction model to the data analysis unit. The data acquisition device sends a first data acquisition request for the first period to the network element device at a first time point, acquires the first network data for the first period from the network element device, and stores the first network data in the data storage unit. The data analysis unit can obtain first network data from the data storage unit and input it into a trained acquisition time prediction model. The model extracts network data features from the first network data and predicts the acquisition time based on these features to obtain the second time point for the next data acquisition. If the data missing rate in the first network data exceeds a preset missing rate, the data analysis unit can determine the first period as the target period for the next data acquisition. The data analysis unit can send an analysis report containing the second time point and the first period to the data acquisition device. Based on the analysis report, the data acquisition device sends a second data acquisition request for the first period to the network element device at the second time point to acquire the second network data for the first period from the network element device, effectively re-acquiring the network data for the first period.

[0073] In one embodiment, as shown in Figure 6, the acquisition time prediction model includes a gated residual network, a static covariate encoder, a multi-head attention network, a temporal fusion decoder, and a long short-term memory network. The temporal fusion decoder includes a position-by-variable feedforward layer, a temporal attention layer, and a static enrichment layer. It can be understood that during the training phase of the acquisition time prediction model, the input to the model to be trained is a historical network data sequence. The model can predict the predicted acquisition time points corresponding to the historical network data contained in the historical network data sequence based on this sequence. Furthermore, reference acquisition time points corresponding to the historical network data contained in the historical network data sequence are obtained. Based on the differences between the predicted acquisition time points corresponding to the historical network data contained in the historical network data sequence and the corresponding reference acquisition time points, the model to be trained is trained to obtain the trained acquisition time prediction model.

[0074] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially, these steps are not necessarily executed in that order. Unless otherwise expressly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the above embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0075] In one embodiment, as shown in FIG7, a data acquisition device 700 is provided, which specifically includes:

[0076] The receiving module 702 is used to receive the first network data sent by the data acquisition device. The first network data is the network data of the current period that the data acquisition device obtains from the network element device at the first time point by sending the first data acquisition request for the current period to the network element device.

[0077] Analysis module 704 is used to perform acquisition time analysis based on the first network data to obtain the second time point of the next data acquisition; and to perform acquisition cycle analysis based on the data missing rate in the first network data to obtain the target cycle of the next data acquisition, wherein the target cycle is the current cycle or the cycle after the current cycle.

[0078] The first sending module 706 is used to send a second time point and a target period to the data acquisition device. The second time point and the target period are used to instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data of the target period from the network element device.

[0079] In one embodiment, the analysis module 704 is further configured to input the first network data into a trained acquisition time prediction model to extract network data features of the first network data through the trained acquisition time prediction model; and to perform acquisition time prediction based on the network data features to obtain the second time point of the next data acquisition.

[0080] In one embodiment, the data acquisition device 700 further includes:

[0081] The training module is used to acquire historical network data sequences, which contain historical network data from multiple historical periods collected from network elements. These historical network data sequences are then input into a data acquisition time prediction model to be trained. Based on the historical network data sequences, the model predicts the predicted acquisition time points corresponding to each historical network data point within the sequences. Reference acquisition time points corresponding to each historical network data point within the sequences are then obtained. Finally, the model is trained based on the differences between the predicted acquisition time points and the corresponding reference acquisition time points, resulting in a trained data acquisition time prediction model.

[0082] In one embodiment, the analysis module 704 is further configured to determine the next period of the current period as the target period for the next data collection when the data missing rate in the first network data is less than or equal to a preset missing rate; and to determine the current period as the target period for the next data collection when the data missing rate in the first network data is greater than the preset missing rate.

[0083] In one embodiment, the network data of the network element device includes call statistics data and collection details data. The collection details data includes at least one of the following: data missing rate, data collection time, device model of the data collection device, resource usage data of the data collection device, device model of the network element device, resource usage data of the network element device, or network status data.

[0084] The aforementioned data acquisition device receives first network data sent by a data acquisition device. This first network data is the network data for the current period acquired by the data acquisition device from the network element device at a first time point after sending a first data acquisition request for the current period. Based on the first network data, it performs acquisition time analysis to obtain a second time point for the next data acquisition. Based on the data missing rate in the first network data, it performs acquisition period analysis to obtain a target period for the next data acquisition, where the target period is the current period or the period following the current period. It then sends the second time point and the target period to the data acquisition device. These two information instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, thereby acquiring second network data for the target period from the network element device. Compared to traditional timed data acquisition methods, this application predicts the time point for the next data acquisition by analyzing the acquisition time of the network data for the current period, thus achieving successful triggering of the data acquisition task without the need for setting a scheduled task. Furthermore, by analyzing the data missing rate in the network data of the current period, it is possible to determine whether the next data collection period is the current period or the period after the current period. That is, to determine whether to continue collecting data for the next period or to re-collect data for the current period, so as to avoid data missing and data distortion, thereby improving the timeliness and integrity of network data collection.

[0085] In one embodiment, as shown in FIG8, a data acquisition device 800 is provided, which specifically includes:

[0086] The acquisition module 802 is used to send a first data acquisition request for the current period to the network element device at the first time point, so as to acquire the first network data of the current period from the network element device;

[0087] The second sending module 804 is used to send first network data to the data analysis device. The first network data is used to instruct the data analysis device to perform collection time analysis based on the first network data to obtain the second time point of the next data collection, and to perform collection cycle analysis based on the data missing rate in the first network data to obtain the target cycle of the next data collection. The target cycle is the current cycle or the next cycle of the current cycle.

[0088] The acquisition module 806 is used to send a second data acquisition request for a target period to the network element device at a second time point, so as to acquire second network data for the target period from the network element device.

[0089] The aforementioned data acquisition device sends a first data acquisition request for the current period to the network element device at a first time point to acquire first network data for the current period from the network element device. It then sends the first network data to a data analysis device, which instructs the data analysis device to perform acquisition time analysis based on the first network data to obtain a second time point for the next data acquisition, and to perform acquisition period analysis based on the data missing rate in the first network data to obtain a target period for the next data acquisition, where the target period is the current period or the period following the current period. At the second time point, it sends a second data acquisition request for the target period to the network element device to acquire second network data for the target period from the network element device. Compared to traditional timed data acquisition methods, this application predicts the time point for the next data acquisition by performing acquisition time analysis on the network data of the current period, thus achieving successful triggering of the data acquisition task without setting a scheduled task. Furthermore, by analyzing the data missing rate in the network data of the current period, it is possible to determine whether the next data collection period is the current period or the period after the current period. That is, to determine whether to continue collecting data for the next period or to re-collect data for the current period, so as to avoid data missing and data distortion, thereby improving the timeliness and integrity of network data collection.

[0090] Each module in the aforementioned data acquisition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the data analysis device in hardware form or independent of it, or stored in the memory of the data analysis device in software form, so that the processor can call and execute the operations corresponding to each module.

[0091] In one embodiment, a data analysis device is provided, which may be a server, and its internal structure can be as shown in Figure 9. The data analysis device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the data analysis device provides computing and control capabilities. The memory of the data analysis device includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The I / O interfaces of the data analysis device are used for exchanging information between the processor and external devices. The communication interface of the data analysis device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a data acquisition method.

[0092] Those skilled in the art will understand that the structure shown in Figure 9 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the data analysis device to which the present application is applied. The specific data analysis device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0093] In one embodiment, a data analysis device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0094] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0095] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0096] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0097] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0098] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A data acquisition method, comprising: The system receives first network data sent by a data acquisition device. The first network data is network data for the current period that the data acquisition device collects from the network element device at a first time point by sending a first data acquisition request for the current period to the network element device. Based on the first network data, the collection time analysis is performed to obtain the second time point of the next data collection; Based on the data missing rate in the first network data, the collection cycle is analyzed to obtain the target cycle for the next data collection, wherein the target cycle is the current cycle or the cycle following the current cycle. The second time point and the target period are sent to the data acquisition device. The second time point and the target period are used to instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data of the target period from the network element device.

2. The method according to claim 1, wherein, The step of analyzing the collection time based on the first network data to obtain the second time point for the next data collection includes: The first network data is input into a trained acquisition time prediction model to extract network data features of the first network data through the trained acquisition time prediction model. Based on the network data characteristics, the collection time is predicted to obtain the second time point for the next data collection.

3. The method according to claim 2, further comprising a model training step, the model training step comprising: Obtain historical network data sequences, which contain historical network data from multiple historical periods collected from the network element device; The historical network data sequence is input into the acquisition time prediction model to be trained, so that the acquisition time prediction model to be trained can predict the predicted acquisition time points corresponding to the historical network data contained in the historical network data sequence based on the historical network data sequence. Obtain the reference collection time points corresponding to the historical network data contained in the historical network data sequence; Based on the differences between the predicted collection time points and the corresponding reference collection time points corresponding to the historical network data contained in the historical network data sequence, the collection time prediction model to be trained is trained to obtain the trained collection time prediction model.

4. The method according to claim 1, wherein, The step of analyzing the data collection cycle based on the data missing rate in the first network data to obtain the target cycle for the next data collection includes: When the data missing rate in the first network data is less than or equal to the preset missing rate, the next period of the current period is determined as the target period for the next data collection. When the data missing rate in the first network data is greater than the preset missing rate, the current period is determined as the target period for the next data collection.

5. The method according to claim 1, wherein, The network data of the network element device includes call statistics data and collection details data. The collection details data includes at least one of the following: data missing rate, data collection time, device model of the data collection device, resource usage data of the data collection device, device model of the network element device, resource usage data of the network element device, or network status data.

6. The method according to claim 1, wherein, The step of analyzing the collection time based on the first network data to obtain the second time point for the next data collection includes: The first network data is collected multiple times at different periods, and the first network data in the current period is collected. By analyzing the time frame, the second time point of the next data collection can be obtained; The data acquisition device is notified to perform the next data acquisition at the second time point, so as to carry out the network data acquisition for the next cycle of the current cycle, or to re-acquire data for the current cycle.

7. The method according to claim 1, wherein, The step of analyzing the collection time based on the first network data to obtain the second time point for the next data collection includes: Feature extraction is performed on the first network data of the current period to obtain the network data features of the first network data; Based on the network data characteristics, the collection time is predicted to obtain the second time point for the next data collection.

8. The method according to claim 1, wherein, The step of analyzing the data collection cycle based on the data missing rate in the first network data to obtain the target cycle for the next data collection includes: When the data missing rate in the first network data is 0, the next period of the current period is determined as the target period for the next data collection. When the data missing rate in the first network data is not 0, the current period is determined as the target period for the next data collection, so that the network data of the current period can be collected again.

9. A data acquisition method, comprising: Send a first data collection request for the current period to the network element device at the first time point, so as to collect the first network data of the current period from the network element device; The first network data is sent to the data analysis device. The first network data is used to instruct the data analysis device to perform collection time analysis based on the first network data to obtain the second time point of the next data collection, and to perform collection cycle analysis based on the data missing rate in the first network data to obtain the target cycle of the next data collection. The target cycle is the current cycle or the next cycle of the current cycle. At the second time point, a second data acquisition request for the target period is sent to the network element device to acquire second network data for the target period from the network element device.

10. A data acquisition device, comprising: The receiving module is used to receive first network data sent by the data acquisition device. The first network data is the network data of the current period that the data acquisition device acquires from the network element device at a first time point by sending a first data acquisition request for the current period to the network element device at a first time point. The analysis module is used to perform time analysis based on the first network data to obtain the second time point of the next data collection. Based on the data missing rate in the first network data, the collection cycle is analyzed to obtain the target cycle for the next data collection, wherein the target cycle is the current cycle or the cycle following the current cycle. The first sending module is used to send the second time point and the target period to the data acquisition device. The second time point and the target period are used to instruct the data acquisition device to send a second data acquisition request for the target period to the network element device at the second time point, so as to acquire second network data of the target period from the network element device.

11. A data analysis device, comprising a memory and a processor, wherein the memory stores a computer program, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

13. A computer program product comprising a computer program, wherein, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images