A data collection method, device, medium, and product

Abstract

The present disclosure relates to a data collection method, device, medium and product, the method comprising: obtaining first observation parameters of each type of monitoring data of a monitoring device for a preset time monitoring window; wherein the first observation parameters comprise: a first window observation value of each type of monitoring data and a first observation fluctuation threshold of the first window observation value; determining first prediction parameters of each type of monitoring data for the first time monitoring window; the first prediction parameters at least comprise: a prediction value, an upper limit of the prediction value, and a lower limit of the prediction value; determining whether the first time monitoring window satisfies a collection condition based on the first observation parameters and the first prediction parameters; in the case of determining that the collection condition is satisfied, collecting data of the monitoring device to obtain a target observation value. The present disclosure can avoid a large amount of redundant data in the data collection process, reduce the storage and calculation cost of hardware for data, and improve the efficiency of data collection.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of mobile communication machine room dynamic environment monitoring, and in particular to a data acquisition method, device, medium and product. BACKGROUND

[0002] The dynamic environment monitoring system is an operations and maintenance center (OMC) for remotely monitoring the operation of the machine room, base station communication power supply, air conditioning system equipment and comprehensive environment, and is a basic information acquisition platform for power operation and maintenance professional operation and maintenance management support capability construction. The dynamic environment monitoring system is composed of a supervision center (SC), a field supervision unit (FSU) and a monitoring device.

[0003] In the related art, the FSU acquires performance data of different monitoring devices, and needs to return full performance data to the SC each time. However, the SC does not classify and acquire the returned full performance data according to the monitoring scene requirements, thereby generating a large amount of redundant data and further leading to low transmission efficiency. In the related art, the SC simultaneously accesses multiple FSUs, and the SC needs to perform full comparison processing on the performance data returned by each FSU. The excessive data of the comparison processing leads to high storage and calculation costs, and the data processing takes a long time, thereby failing to meet the requirement of real-time monitoring of the monitoring device. SUMMARY

[0004] The present disclosure provides a data acquisition method, device, medium and product.

[0005] According to a first aspect of the present disclosure, a data acquisition method is provided, the method comprising:

[0006] obtaining a first observation parameter of each type of monitoring data of a monitoring device for a preset time monitoring window; wherein the first observation parameter comprises a first window observation value of the each type of monitoring data and a first observation fluctuation threshold value of the first window observation value;

[0007] determining a first prediction parameter of the each type of monitoring data for a first time monitoring window; the first prediction parameter at least comprises a predicted value, an upper limit of the predicted value, and a lower limit of the predicted value;

[0008] determining whether the first time monitoring window meets an acquisition condition based on the first observation parameter and the first prediction parameter;

[0009] in a case where it is determined that the acquisition condition is met, performing data acquisition on the monitoring device to obtain a target observation value.

[0010] Further, the determining the first prediction parameter of the each type of monitoring data for the first time monitoring window comprises:

[0011] The first prediction parameter of the each type of monitoring data for the first time monitoring window is obtained by processing the first historical window observation value in the historical database through the deep learning prediction model.

[0012] Further, the determining whether the first time monitoring window meets the collection condition based on the first observation parameter and the first prediction parameter comprises:

[0013] In a case where it is determined that the first preset condition is met between the first window observation value and the first prediction parameter, or it is determined that the second preset condition is met between the first window observation value and the first prediction parameter, it is determined that the first time monitoring window meets the collection condition.

[0014] The first preset condition is that an absolute value of a difference between the window observation value and the prediction value is greater than the observation fluctuation threshold, and the second preset condition is that the window observation value is greater than an upper limit of the prediction value or the window observation value is less than a lower limit of the prediction value.

[0015] Further, in a case where it is determined that the collection condition is met, after the data collection of the monitoring device is performed to obtain the target observation value, the method further comprises:

[0016] In a case where it is determined that the second preset condition is met between the first window observation value and the first prediction parameter, a second observation fluctuation threshold under a second time monitoring window is determined based on the target observation value, the first observation fluctuation threshold and the first window observation value, wherein the second time monitoring window is a next time monitoring window after the first time monitoring window.

[0017] Further, the determining the second observation fluctuation threshold under the second time monitoring window based on the target observation value, the first observation fluctuation threshold and the first window observation value comprises:

[0018] calculating an absolute value of a difference between the target observation value and the window observation value;

[0019] determining a minimum value between the absolute value and the first observation fluctuation threshold;

[0020] determining the minimum value as the second fluctuation threshold.

[0021] Further, the method further comprises:

[0022] In a case where it is determined that the observation parameter and the first prediction parameter do not satisfy the first preset condition and the second preset condition, it is determined that the first time monitoring window does not satisfy the collection condition, and it is determined whether a second time monitoring window satisfies the collection condition based on a second observation parameter of the second time monitoring window and the first prediction parameter; the second time monitoring window is a next time monitoring window after the first time monitoring window.

[0023] Further, in a case where it is determined that the collection condition is satisfied, after the target observation value is obtained by performing data collection on the monitoring device, the method further comprises:

[0024] extracting a second historical window observation value in the historical database according to a preset period; the second historical window observation value is a window observation value obtained by performing data collection on the monitoring device in a time monitoring window before a second time monitoring window; the second time monitoring window is a next time monitoring window after the first time monitoring window;

[0025] sending the second historical window observation value to the deep learning prediction model to determine a second prediction parameter of each type of monitoring data for the second time monitoring window;

[0026] determining whether the second time monitoring window satisfies the collection condition based on the second observation parameter of the second time monitoring window and the second prediction parameter.

[0027] According to a second aspect of the present disclosure, a data collection device is provided, and the device comprises:

[0028] an acquisition module configured to acquire a first observation parameter of each type of monitoring data of a monitoring device for a preset time monitoring window; the first observation parameter comprises a first window observation value of the each type of monitoring data and a first observation fluctuation threshold of the window observation value;

[0029] a first determination module configured to determine a first prediction parameter of each type of monitoring data for a first time monitoring window; the first prediction parameter at least comprises a predicted value, an upper limit of the predicted value, and a lower limit of the predicted value;

[0030] a second determination module configured to determine whether the first time monitoring window satisfies a collection condition based on the first observation parameter and the first prediction parameter;

[0031] a data collection module configured to perform data collection on the monitoring device to obtain a target observation value in a case where it is determined that the collection condition is satisfied.

[0032] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device comprises a memory and a processor, the memory having stored thereon a computer program, the processor implementing the method as described above when executing the program.

[0033] According to a fourth aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, the program being executed by a processor to implement the method as described above.

[0034] According to a fifth aspect of the present disclosure, a computer program product is provided. The computer program product comprises a computer program, the computer program being executed by a processor to implement the method as described above.

[0035] The data acquisition method, device, medium and product provided by the embodiments of the present disclosure, in the embodiments of the present application, first, the first observation parameter of each type of monitoring data of the monitoring device for the preset time monitoring window is obtained; wherein the first observation parameter includes: the first window observation value of each type of monitoring data and the first observation fluctuation threshold of the window observation value; then, the first prediction parameter of each type of monitoring data for the first time monitoring window is determined; the first prediction parameter at least includes: the prediction value, the upper limit of the prediction value, and the lower limit of the prediction value; thereafter, based on the first observation parameter and the first prediction parameter, it is determined whether the first time monitoring window satisfies the acquisition condition; finally, in the case of determining that the acquisition condition is satisfied, the monitoring device is subjected to data acquisition to obtain the target observation value.

[0036] Through the above processing mode, data acquisition can be performed on the monitoring device in the case of determining that the acquisition condition is satisfied, thereby avoiding the generation of a large amount of redundant data and improving the efficiency of data acquisition; at the same time, the number of request times and the response time of data acquisition can be reduced, and the storage and calculation cost of hardware for data can be reduced, thereby further improving the efficiency of data acquisition. BRIEF DESCRIPTION OF DRAWINGS

[0037] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which like reference characters refer to like parts throughout the figures. The accompanying drawings provide illustration of the embodiments of the present disclosure and constitute a part of the specification, which together with the detailed description serve to explain the present disclosure. The accompanying drawings do not limit the present disclosure, and are used to explain the present disclosure together with the embodiments of the present disclosure. In the drawings, the same reference numerals generally refer to the same components or steps throughout the figures.

[0038] Figure 1 A flowchart of a data acquisition method provided for an exemplary embodiment of the present disclosure;

[0039] Figure 2 A structural schematic diagram of a dynamic ring monitoring system provided for an exemplary embodiment of the present disclosure;

[0040] Figure 3 Workflow diagram of the server provided for an exemplary embodiment of the present disclosure;

[0041] Figure 4 Workflow diagram of the server provided for another exemplary embodiment of the present disclosure;

[0042] Figure 5 Workflow diagram of the server provided for another exemplary embodiment of the present disclosure;

[0043] Figure 6 Flowchart of the data collection method provided for another exemplary embodiment of the present disclosure;

[0044] Figure 7 Workflow diagram of the server provided for another exemplary embodiment of the present disclosure;

[0045] Figure 8 Flowchart of the data collection method provided for another exemplary embodiment of the present disclosure;

[0046] Figure 9 Workflow diagram of the server provided for another exemplary embodiment of the present disclosure;

[0047] Figure 10 Workflow diagram of the server provided for another exemplary embodiment of the present disclosure;

[0048] Figure 11 Functional module schematic block diagram of the data collection device provided for an exemplary embodiment of the present disclosure;

[0049] Figure 12 Structural block diagram of the electronic device provided for an exemplary embodiment of the present disclosure;

[0050] Figure 13 Structural block diagram of the computer system provided for an exemplary embodiment of the present disclosure;

[0051] Figure 14 Structural block diagram of the computer program product provided for an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0052] Embodiments of the present disclosure will be described in more detail by referring to the drawings. Although certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein, but rather the embodiments are provided so as to more thoroughly and completely understand the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0053] It should be understood that each of the steps recited in the method embodiments of the present disclosure can be performed in different orders and / or in parallel. In addition, the method embodiments can include additional steps and / or omit performing the steps shown. The scope of the present disclosure is not limited in this regard.

[0054] The term "comprises" and variations thereof used in the present disclosure are open-ended, that is, "comprising but not limited to". The term "based on" is "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Related definitions will be given in the following description. It should be noted that the "first", "second", etc. concepts mentioned in the present disclosure are only used to distinguish different modules or units, and are not used to limit the order or interdependence of the functions performed by these modules or units.

[0055] It should be noted that the modification of "one" or "multiple" mentioned in the present disclosure is illustrative and not limiting, and those skilled in the art should understand that unless the context clearly indicates otherwise, it should be understood as "one or more".

[0056] The names of the messages or information exchanged between the devices in the embodiments of the present disclosure are only for illustrative purposes, and are not used to limit the scope of the messages or information.

[0057] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type, scope of use, use scenario, etc. of the personal information involved in the present disclosure should be notified to the user and the authorization of the user should be obtained in a proper manner according to relevant laws and regulations.

[0058] For example, in response to receiving the active request of the user, the user is sent prompt information to explicitly prompt the user that the operation requested to be performed will require obtaining and using the personal information of the user. Thus, the user can voluntarily choose whether to provide personal information to the software or hardware such as electronic device, application program, server or storage medium, etc. that performs the operation of the technical solutions of the present disclosure according to the prompt information.

[0059] As an optional but not limited implementation manner, in response to receiving the active request of the user, the manner of sending prompt information to the user may, for example, be a pop-up window manner, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide personal information to the electronic device. It can be understood that the above notification and obtaining of user authorization process is only illustrative, and does not limit the implementation manner of the present disclosure, and other manners that meet the relevant laws and regulations can also be applied to the implementation manner of the present disclosure.

[0060] In one embodiment, Figure 1 As shown, a data collection method is provided, comprising the following steps:

[0061] Step 101: Obtain first observation parameters of various types of monitoring data of a monitoring device for a preset time monitoring window.

[0062] Here, when data collection is required for the monitoring device, the first observation parameters of each type of monitoring data of the monitoring device for a preset time monitoring window (Time observation window, TOW) can be obtained through the server, wherein the first observation parameters include: the first window observation value (Window observations, WO) of each type of monitoring data and the first observation fluctuation threshold (Fluctuation Threshold, FT) of the first window observation value.

[0063] In one possible embodiment, Figure 2 As shown, Figure 2 The schematic diagram of the structure of the dynamic environment monitoring system is shown as an example. The server is located in the monitoring center, which interacts with multiple dynamic environment monitoring units 1, 2, and N via the traditional B interface. The multiple dynamic environment monitoring units detect various types of monitoring data from monitoring devices 1 to N in real time via the A interface. After the dynamic environment monitoring units send the monitoring data to the monitoring center, the server can obtain the first observation parameters of each type of monitoring data from the monitoring devices for a preset time monitoring window from the monitoring center. The first observation parameters include: the first window observation value of each type of monitoring data and the first observation fluctuation threshold of the first window observation value. The first window observation value is the data value obtained by monitoring the monitoring data within the preset time monitoring window. The first observation fluctuation threshold is the trigger threshold for incremental data collection. When the first window observation value meets the first observation fluctuation threshold, the server triggers the dynamic environment monitoring unit to collect data from the monitoring devices. The time monitoring window is the observation period of the monitoring data.

[0064] It should be noted that the monitoring data includes state quantities and analog quantities. Since different types of monitoring data have different frequencies of change and data fluctuation amplitudes, it is possible to obtain the first window observation value and the first observation fluctuation threshold of each type of monitoring data of the monitoring device for the preset time monitoring window according to business needs, thereby obtaining the first observation parameter.

[0065] In the embodiments of the present disclosure, the preset time monitoring window can be the latest time monitoring window, and can also be a time monitoring window before the current time. Here, the preset time monitoring window is not limited to be accurate. For example, the first window observation value can be a data value in the latest time monitoring window, or a data value in another time monitoring window. The first observation fluctuation threshold can be set according to the data value in the latest time monitoring window. The setting method of the first window observation value and the first observation fluctuation threshold is not limited here.

[0066] In step 102, a first prediction parameter of each type of monitoring data for the first time monitoring window is determined.

[0067] Here, after obtaining the first observation parameter of each type of monitoring data of the monitoring device for the preset time monitoring window, the server can determine the first prediction parameter of each type of monitoring data for the first time monitoring window, wherein the first prediction parameter at least includes: predicted value (Predicted Value, PV), upper limit of predicted value (The Upper limit of the Predicted Value, PV_U), and lower limit of predicted value (The Lower limit of the Predicted Value, PV_L).

[0068] In one possible embodiment, determining the first prediction parameter of each type of monitoring data for the first time monitoring window includes the following steps:

[0069] The first historical window observation value in the historical database is processed by the deep learning prediction model to obtain the first prediction parameter of each type of monitoring data for the first time monitoring window.

[0070] In the embodiments of the present disclosure, after the server obtains the first observation parameter of each type of monitoring data of the monitoring device for the preset time monitoring window, the server can process the first historical window observation value in the historical database by using the pre-trained deep learning prediction model to obtain the first prediction parameter of each type of monitoring data for the first time monitoring window, wherein the first prediction parameter at least includes: predicted value, upper limit of predicted value, and lower limit of predicted value.

[0071] For example, a neural network time series prediction model (NeuralProphet) can be used to model, train and predict the historical window observation value of one year to obtain the first prediction parameter of each type of monitoring data for the first time monitoring window. It should be noted that other deep learning prediction models can also be used to obtain the first prediction parameter, and the method for obtaining the first prediction parameter is not limited here, as long as it can be realized accurately.

[0072] As Figure 3 shown, Figure 3 An exemplary server workflow diagram is shown, the server determines the first observation parameter WO and the first observation fluctuation threshold FT of each type of monitoring data for the first time monitoring window TOW, and then starts the first time monitoring window in multi-thread. After the end of the first time monitoring window, the first prediction parameter of each type of monitoring data for the first time monitoring window can be determined by a deep learning prediction model. If the first time monitoring window has not ended, the server continues to detect each type of monitoring data in the first time monitoring window.

[0073] Step 103, based on the first observation parameter and the first prediction parameter, determine whether the first time monitoring window meets the collection condition.

[0074] Here, after the server determines the first prediction parameter of each type of monitoring data for the first time monitoring window, the server can determine whether the first time monitoring window meets the collection condition based on the first observation parameter and the first prediction parameter.

[0075] In one possible implementation, based on the first observation parameter and the first prediction parameter, determining whether the first time monitoring window meets the collection condition includes the following steps:

[0076] In a case where it is determined that the first preset condition is met between the first window observation value and the first prediction parameter, or it is determined that the second preset condition is met between the first window observation value and the first prediction parameter, it is determined that the first time monitoring window meets the collection condition.

[0077] In a case where it is determined that the observation parameter and the first prediction parameter do not meet the first preset condition and the second preset condition, it is determined that the first time monitoring window does not meet the collection condition, and based on the second observation parameter and the first prediction parameter of the second time monitoring window, it is determined whether the second time monitoring window meets the collection condition.

[0078] Specifically, after the server determines the first prediction parameter of each type of monitoring data for the first time monitoring window, the server determines whether the first time monitoring window meets the collection condition based on the first observation parameter and the first prediction parameter, wherein the first preset condition is that the absolute value of the difference between the window observation value and the prediction value is greater than the observation fluctuation threshold, i.e. |WO-PV|>FT, and the second preset condition is that the window observation value is greater than the upper limit of the prediction value, or the window observation value is less than the lower limit of the prediction value, i.e. WO>PV_U or WO<PV_L.

[0079] Exemplarily, as Figure 4 shown, Figure 4Another workflow diagram of the server is shown as an example. After the server determines the first observation parameter WO and the first observation fluctuation threshold FT for each type of monitoring data for the first time monitoring window, the multi-threaded server opens the first time monitoring window. When the first time monitoring window ends, the first prediction parameter for each type of monitoring data for the first time monitoring window is determined, and then based on the first observation parameter and the first prediction parameter, it is determined whether the first time monitoring window meets the acquisition condition. There are three scenarios here. Scenario one corresponds to the first preset condition, and scenario two corresponds to the second preset condition. When it is determined that the first preset condition is met between the observation value of the first window and the first prediction parameter, or when it is determined that the second preset condition is met between the observation value of the first window and the first prediction parameter, that is, when the first scenario or the second scenario is met, it is determined that the first time monitoring window meets the acquisition condition.

[0080] In another possible embodiment, when it is determined that the observation parameters and the first prediction parameters do not meet the first preset conditions and the second preset conditions, that is, when the first scenario and the second scenario are not met, it is determined to be the third scenario, then it is determined that the first time monitoring window does not meet the acquisition conditions, and based on the second observation parameters and the first prediction parameters of the second time monitoring window, it is determined whether the second time monitoring window meets the acquisition conditions, wherein the second time monitoring window is the next time monitoring window after the first time monitoring window.

[0081] Step 104: When it is determined that the collection conditions are met, data is collected from the monitoring equipment to obtain target observation values.

[0082] Here, based on the first observation parameter and the first prediction parameter, the server collects data from the monitoring device and obtains the target observation value when it determines that the collection conditions are met.

[0083] In one possible embodiment, Figure 5 As shown, Figure 5 Another workflow diagram of the server is shown as an example. The server determines whether the first time monitoring window meets the collection conditions based on the first observation parameter and the first prediction parameter. When it is determined that the collection conditions are met, that is, when scenario one or scenario two is met, the server triggers the dynamic environment monitoring unit to collect data from the monitoring equipment to obtain the target observation value.

[0084] The data acquisition method, device, medium and product provided by the embodiments of the present disclosure, in the embodiments of the present application, first, the first observation parameter of each type of monitoring data of the monitoring device for the preset time monitoring window is obtained; wherein the first observation parameter includes: the first window observation value of each type of monitoring data and the first observation fluctuation threshold value of the first window observation value; then, the first prediction parameter of each type of monitoring data for the first time monitoring window is determined; the first prediction parameter at least includes: the predicted value, the upper limit of the predicted value, and the lower limit of the predicted value; thereafter, based on the first observation parameter and the first prediction parameter, it is determined whether the first time monitoring window meets the acquisition condition; finally, in the case of determining that the acquisition condition is met, data acquisition is performed on the monitoring device to obtain the target observation value.

[0085] Through the above processing mode, data acquisition can be performed on the monitoring device in the case of determining that the acquisition condition is met, avoiding the generation of a large amount of redundant data, improving the efficiency of data acquisition; at the same time, the request number and response time of data acquisition can be reduced, and the storage and calculation cost of hardware for data can be reduced, further improving the efficiency of data acquisition.

[0086] In one embodiment, as shown in Figure 6 After step 104, in the case of determining that the acquisition condition is met, data acquisition is performed on the monitoring device to obtain the target observation value, a data acquisition method is further provided, including the following steps:

[0087] Step 601, in the case of determining that the first window observation value and the first prediction parameter meet the second preset condition, the second observation fluctuation threshold value under the second time monitoring window is determined based on the target observation value, the first observation fluctuation threshold value and the first window observation value.

[0088] In one possible embodiment, the second observation fluctuation threshold value under the second time monitoring window is determined based on the target observation value, the first observation fluctuation threshold value and the first window observation value, including the following steps:

[0089] Calculate the absolute value of the difference between the target observation value and the window observation value;

[0090] Determine the minimum value of the absolute value and the first observation fluctuation threshold value;

[0091] The minimum value is determined as the second fluctuation threshold value.

[0092] Specifically, the server can determine the second observation fluctuation threshold value under the second time monitoring window based on the target observation value, the first observation fluctuation threshold value and the first window observation value in the case of determining that the first window observation value and the first prediction parameter meet the second preset condition, wherein the second time monitoring window is the next time monitoring window after the first time monitoring window.

[0093] Exemplarily, as Figure 7 shown, Figure 7 Exemplarily, another workflow schematic diagram of the server is shown, when the server determines that the second preset condition between the first window observation value and the first prediction parameter is met, i.e., scenario two is met, the server calculates the absolute value of the difference between the target observation value and the window observation value, after the absolute value of the difference between the target observation value and the window observation value is calculated, the minimum value of the absolute value and the first observation fluctuation threshold is determined, and the minimum value is determined as the second fluctuation threshold. For example, when the absolute value of the difference between the target observation value and the window observation value is 20, and the first observation fluctuation threshold is 30, the second fluctuation threshold can be determined as 20 by the formula: second fluctuation threshold = min(FT, |AC-WO|), wherein AC is the target observation value.

[0094] In this embodiment, the server determines the second observation fluctuation threshold under the second time monitoring window based on the target observation value, the first observation fluctuation threshold, and the first window observation value when the first window observation value and the first prediction parameter meet the second preset condition. As described above, the server dynamically updates the observation fluctuation threshold under the second time monitoring window by the target observation value, the first observation fluctuation threshold, and the first window observation value, continuously optimizes the observation parameter, and triggers the collection of various data by the updated observation parameter, so that the collected monitoring data is more in line with the collection demand, avoids a large amount of redundant data, and improves the efficiency and reliability of the data collection method.

[0095] In one embodiment, as Figure 8 shown, step 104, after determining that the collection condition is met and collecting the target observation value from the monitoring device, further provides a data collection method, comprising the following steps:

[0096] Step 801, extracting a second historical window observation value from the historical database according to a preset period.

[0097] Here, after the server collects the target observation value from the monitoring device, the second historical window observation value is extracted from the historical database according to a preset period, wherein the second historical window observation value is the window observation value obtained by collecting data from the monitoring device in the time monitoring window before the second time monitoring window, and the second time monitoring window is the next time monitoring window after the first time monitoring window.

[0098] In a possible embodiment, as Figure 9 shown, Figure 9Another workflow schematic diagram of the server is exemplarily shown. After the server collects the target observation value from the monitoring device, the server caches the target observation value into the cache database, and periodically synchronizes the window observation value in the storage database to the historical database. Exemplarily, the user can customize to synchronize the window observation value in the storage database to the historical database every week, and the server extracts the second historical window observation value from the historical database according to the preset period, wherein the second historical window observation value is the window observation value obtained by collecting data from the monitoring device in the time monitoring window before the second time monitoring window.

[0099] In step 802, the second historical window observation value is sent to the deep learning prediction model to determine the second prediction parameter of each type of monitoring data for the second time monitoring window.

[0100] After the server extracts the second historical window observation value from the historical database according to the preset period, the server can send the second historical window observation value to the deep learning prediction model to determine the second prediction parameter of each type of monitoring data for the second time monitoring window.

[0101] In a possible embodiment, as shown in Figure 9 After the server extracts the second historical window observation value from the historical database according to the preset period, the server sends the second historical window observation value to the deep learning prediction model for incremental learning to determine the second prediction parameter of each type of monitoring data for the second time monitoring window. Exemplarily, the neural network time series can be used for incremental learning to determine the second prediction parameter of each type of monitoring data for the second time monitoring window. It should be noted that other deep learning prediction models can also be used to determine the second prediction parameter, and the method of obtaining the second prediction parameter is not limited herein, as long as it can be achieved accurately.

[0102] In step 803, whether the second time monitoring window meets the collection condition is determined based on the second observation parameter and the second prediction parameter of the second time monitoring window.

[0103] After the server sends the second historical window observation value to the deep learning prediction model and determines the second prediction parameter of each type of monitoring data for the second time monitoring window, whether the second time monitoring window meets the collection condition is determined based on the second observation parameter and the second prediction parameter of the second time monitoring window.

[0104] In a possible embodiment, as shown in Figure 10 Figure 10 ​Another workflow schematic diagram of the server is exemplarily shown. After the server determines the second prediction parameters of the various types of monitoring data for the second time monitoring window, the server determines whether the second time monitoring window satisfies the collection condition based on the second observation parameters and the second prediction parameters of the second time monitoring window. The specific steps of determining whether the second time monitoring window satisfies the collection condition can be referred to the steps of determining whether the first time monitoring window satisfies the collection condition in step 103, which will not be described herein again. After determining whether the second time monitoring window satisfies the collection condition, if the second time monitoring window satisfies the collection condition, data collection is performed on the monitoring device to obtain the target observation value, and if the second time monitoring window does not satisfy the collection condition, whether a next time monitoring window of the second time monitoring window satisfies the collection condition is determined.

[0105] In this embodiment, first, the server extracts the second historical window observation value in the historical database according to a preset period, then the server sends the second historical window observation value to the deep learning prediction model to determine the second prediction parameters of the various types of monitoring data for the second time monitoring window, and finally, the server determines whether the second time monitoring window satisfies the collection condition based on the second observation parameters and the second prediction parameters of the second time monitoring window. As can be known from the above description, the second prediction parameters are determined by the server through the deep learning prediction model, the server performs real-time dynamic analysis on the prediction parameters and triggers the collection of various types of data, and the prediction parameters are continuously optimized through the post-analysis and incremental learning of the collected monitoring data, thereby improving the data collection performance. In addition, the server collects data according to the optimized prediction parameters, improves the value density of the collected monitoring data, and further improves the reliability of the data collection method.

[0106] In the case of dividing various functional modules corresponding to various functions, the data collection device provided by an exemplary embodiment of the present disclosure can be a server or a chip applied to a server. Figure 11 A functional module schematic diagram of the data collection device provided by an exemplary embodiment of the present disclosure is shown in FIG. 11. As shown in FIG. 11, the data collection device includes: Figure 11

[0107] The acquisition module 1101 is configured to acquire first observation parameters of various types of monitoring data of a monitoring device for a preset time monitoring window. The first observation parameters include first window observation values of the various types of monitoring data and first observation fluctuation thresholds of the first window observation values.

[0108] The first determination module 1102 is configured to determine first prediction parameters of the various types of monitoring data for a first time monitoring window. The first prediction parameters at least include a predicted value, an upper limit of the predicted value, and a lower limit of the predicted value. ​

[0109] The second determination module 1103 is configured to determine whether the first time monitoring window satisfies a collection condition based on the first observation parameter and the first prediction parameter.

[0110] The data collection module 1104 is configured to collect data of the monitoring device to obtain a target observation value when it is determined that the collection condition is satisfied.

[0111] In an embodiment, the first determination module 1102 includes:

[0112] The acquisition unit is configured to process the first historical window observation value in the historical database by a deep learning prediction model to obtain the first prediction parameter of the first time monitoring window for each type of monitoring data.

[0113] In an embodiment, the second determination module 1103 includes:

[0114] The first determination unit is configured to determine that the first time monitoring window satisfies the collection condition when it is determined that a first preset condition between the first window observation value and the first prediction parameter is satisfied, or a second preset condition between the first window observation value and the first prediction parameter is satisfied.

[0115] The first preset condition is that an absolute value of a difference between the window observation value and the prediction value is greater than the observation fluctuation threshold, and the second preset condition is that the window observation value is greater than an upper limit of the prediction value or the window observation value is less than a lower limit of the prediction value.

[0116] In an embodiment, the apparatus further includes:

[0117] The third determination module is configured to determine a second observation fluctuation threshold of a second time monitoring window based on the target observation value, the first observation fluctuation threshold, and the first window observation value when it is determined that the second preset condition between the first window observation value and the first prediction parameter is satisfied, wherein the second time monitoring window is a next time monitoring window after the first time monitoring window.

[0118] In an embodiment, the third determination module includes:

[0119] The calculation unit is configured to calculate an absolute value of a difference between the target observation value and the window observation value.

[0120] The second determination unit is configured to determine a minimum value between the absolute value and the first observation fluctuation threshold.

[0121] The third determination unit is configured to determine the minimum value as the second fluctuation threshold.

[0122] In an embodiment, the apparatus further comprises:

[0123] The fourth determining module is configured to, in a case where the observation parameter and the first prediction parameter do not satisfy the first preset condition and the second preset condition, determine that the first time monitoring window does not satisfy the collection condition, and determine whether a second time monitoring window satisfies the collection condition based on a second observation parameter of the second time monitoring window and the first prediction parameter; the second time monitoring window is a next time monitoring window after the first time monitoring window.

[0124] In an embodiment, the apparatus further comprises:

[0125] The extracting module is configured to extract a second historical window observation value in the historical database according to a preset period; the second historical window observation value is a window observation value obtained by data collection of the monitoring device on a time monitoring window before a second time monitoring window; the second time monitoring window is a next time monitoring window after the first time monitoring window.

[0126] The fifth determining module is configured to send the second historical window observation value to a deep learning prediction model, and determine a second prediction parameter of each type of monitoring data for the second time monitoring window.

[0127] The sixth determining module is configured to determine whether the second time monitoring window satisfies the collection condition based on a second observation parameter of the second time monitoring window and the second prediction parameter.

[0128] The embodiments of the present disclosure further provide an electronic device, which comprises at least one processor, a memory for storing instructions executable by the at least one processor, and wherein the at least one processor is configured to execute the instructions to implement the above method disclosed by the embodiments of the present disclosure.

[0129] Figure 12 The structure schematic diagram of the electronic device provided by an exemplary embodiment of the present disclosure is shown in FIG. 12. As shown in FIG. 12, the electronic device 1200 comprises at least one processor 1201 and a memory 1202 coupled to the processor 1201, and the processor 1201 can execute corresponding steps in the above method disclosed by the embodiments of the present disclosure. Figure 12

[0130] ​The processor 1201 can also be referred to as a central processing unit (CPU), which can be an integrated circuit chip that has the processing capability of signals. Each step in the above method disclosed by the embodiments of the present disclosure can be completed by the integrated logic circuit of hardware or the instructions in the form of software in the processor 1201. The processor 1201 can be a general-purpose processor, a digital signal processor (DSP), an ASIC, a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as hardware code processing for execution, or executed by a combination of hardware and software modules in the code processing. The software module can be located in the memory 1202, such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register or other mature storage medium in the art. The processor 1201 reads the information in the memory 1202 and completes the steps of the above method in combination with the hardware thereof.

[0131] In addition, various operations / processes according to the present disclosure, when implemented by software and / or firmware, can be loaded from a storage medium or a network to a computer system with a dedicated hardware structure, such as Figure 13 The computer system 1300 shown is installed with programs constituting the software, and when various programs are installed, the computer system can perform various functions, including functions such as those described above. Figure 13 A structural block diagram of a computer system provided for an exemplary embodiment of the present disclosure.

[0132] The computer system 1300 is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown in the figures, their connections and relationships, and their functions, are merely examples, and are not intended to limit the implementations described and / or claimed in this document.

[0133] As Figure 13As shown, computer system 1300 includes a computing unit 1301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1302 or a computer program loaded from a storage unit 1308 into a random access memory (RAM) 1303. Various programs and data required for the operation of computer system 1300 may also be stored in RAM 1303. Computing unit 1301, ROM 1302, and RAM 1303 are connected to each other via a bus 1304. An input / output (I / O) interface 1305 is also connected to bus 1304.

[0134] Multiple components within computer system 1300 are connected to I / O interface 1305, including an input unit 1306, an output unit 1307, a storage unit 1308, and a communication unit 1309. Input unit 1306 can be any type of device capable of inputting information into computer system 1300. Input unit 1306 can receive input numeric or character information and generate key input signals related to user settings and / or function control of an electronic device. Output unit 1307 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 1308 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 1309 allows computer system 1300 to exchange information / data with other devices over a network, such as the Internet, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0135] The computing unit 1301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1301 performs the various methods and processes described above. For example, in some embodiments, the above-mentioned methods disclosed in the embodiments of the present disclosure may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1200 via the ROM 1302 and / or the communication unit 1309. In some embodiments, the computing unit 1301 may be configured to perform the above-mentioned methods disclosed in the embodiments of the present disclosure by any other appropriate means (e.g., by means of firmware).

[0136] The embodiment of the present disclosure further provides a computer readable storage medium, wherein when instructions in the computer readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the above method disclosed by the embodiment of the present disclosure.

[0137] The computer readable storage medium in the embodiment of the present disclosure can be a tangible medium, which can contain or store programs for use by or in connection with an instruction execution system, apparatus or device. The above computer readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination of the above. More specifically, the above computer readable storage medium can include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0138] The above computer readable medium can be included in the above electronic device; or can exist separately without being assembled into the electronic device.

[0139] Figure 14 A computer program product 1400 is provided for an exemplary embodiment of the present disclosure, which includes a computer program 1401, wherein the computer program 1401 is executed by a processor to implement the above method disclosed by the embodiment of the present disclosure.

[0140] In the embodiments of the present disclosure, computer program code for carrying out operations of the present disclosure can be written in one or more programming languages or combinations of the same, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" programming language or similar programming languages. Program code can be executed entirely on a user computer, partially on a user computer, as an independent software package, partially on a user computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer.

[0141] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0142] The modules, components, or units described in the embodiments of the present disclosure may be implemented in software or hardware. The names of the modules, components, or units do not necessarily limit the modules, components, or units themselves.

[0143] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, and without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0144] The above descriptions are merely some embodiments of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present disclosure.

[0145] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art will appreciate that the above examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Those skilled in the art will appreciate that modifications may be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A data acquisition method, characterized by, The method comprises: Obtaining first observation parameters of each type of monitoring data of a monitoring device for a preset time monitoring window; wherein the first observation parameters include: a first window observation value of each type of monitoring data and a first observation fluctuation threshold of the first window observation value; Determining first prediction parameters for each type of monitoring data for a first time monitoring window; the first prediction parameters include at least: a predicted value, an upper limit of the predicted value, and a lower limit of the predicted value; determining, based on the first observation parameter and the first prediction parameter, whether the first time monitoring window satisfies an acquisition condition; When it is determined that the acquisition conditions are met, data is collected from the monitoring device to obtain a target observation value; When it is determined that the first window observation value and the first prediction parameter meet the second preset condition, calculate the absolute value of the difference between the target observation value and the first window observation value; determine the minimum value between the absolute value and the first observation fluctuation threshold; and determine the minimum value as the second fluctuation threshold of the second time monitoring window, wherein the second preset condition is that the first window observation value is greater than the upper limit of the prediction value, or that the first window observation value is less than the lower limit of the prediction value, and the second time monitoring window is the next time monitoring window after the first time monitoring window.

2. The method of claim 1, wherein, The determining of the first prediction parameter of each type of monitoring data for the first time monitoring window includes: The observation values ​​of the first historical window in the historical database are processed through a deep learning prediction model to obtain the first prediction parameters of each type of monitoring data for the first time monitoring window.

3. The method of claim 1, wherein, The determining, based on the first observation parameter and the first prediction parameter, whether the first time monitoring window meets the acquisition condition includes: Determining that the first time monitoring window satisfies the acquisition condition when it is determined that the first window observation value and the first prediction parameter satisfy a first preset condition, or when it is determined that the first window observation value and the first prediction parameter satisfy a second preset condition; Among them, the first preset condition is that the absolute value of the difference between the first window observation value and the predicted value is greater than the observation fluctuation threshold, and the second preset condition is that the first window observation value is greater than the upper limit of the predicted value, or the first window observation value is less than the lower limit of the predicted value.

4. The method of claim 3, wherein, The method further comprises: When it is determined that the observation parameter and the first prediction parameter do not meet the first preset condition and the second preset condition, it is determined that the first time monitoring window does not meet the acquisition condition, and based on the second observation parameter and the first prediction parameter of the second time monitoring window, it is determined whether the second time monitoring window meets the acquisition condition; wherein, the second time monitoring window is the next time monitoring window after the first time monitoring window.

5. The method of claim 1, wherein, When it is determined that the collection condition is met, data is collected from the monitoring device to obtain the target observation value, and the method further includes: extracting second historical window observation values in the historical database according to a preset period; wherein the second historical window observation values are window observation values obtained by data collection on the monitoring device in a time monitoring window before a second time monitoring window, and the second time monitoring window is a next time monitoring window after the first time monitoring window; sending the second historical window observation values to the deep learning prediction model to determine second prediction parameters of each type of monitoring data for the second time monitoring window; determining whether the second time monitoring window meets the collection condition based on the second observation parameters of the second time monitoring window and the second prediction parameters.

6. An electronic device, comprising: comprise: at least one processor; a memory for storing instructions executable by the at least one processor; wherein the at least one processor is configured to execute the instructions to implement the method of any one of claims 1-5.

7. A computer readable storage medium characterized in that, When the instructions in the computer readable storage medium are executed by the processor of the electronic device, the electronic device can perform the method of any one of claims 1-5.

8. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-5.

Images