Data monitoring method and device based on continuous intelligence, medium and equipment

Abstract

The invention relates to a data monitoring method and device based on continuous intelligence, a medium and equipment. According to the method, the position offset of the sliding window is taken as an object, further training is carried out on the basis of the association prediction sub-model, so that lagging information of the association relationship between each index data and the specific index data is mined, a new association relationship between the index data can be found, and the accuracy of the association relationship between the index data and the specific index data is improved. And comparing a joint prediction result of the updated vector with a time sequence prediction result to help the association prediction sub-model to further learn time sequence information and improve the reliability of the second association vector, so that the potential association relationship is mined from the second association vector, and the comprehensiveness and completeness of data monitoring are improved.

Description

Technical Field

[0001] The present invention is applicable to the field of data monitoring, and in particular relates to a data monitoring method, device, medium and equipment based on continuous intelligence. Background Art

[0002] Currently, in traditional data analysis applications, enterprises regularly check and monitor various indicator data and manually browse data along predefined query paths. However, only referring to predefined technical indicators and performance indicators will limit the perspective of data monitoring, and will miss other indicators that are related to the displayed indicators but not predefined, resulting in poor comprehensiveness and completeness of data monitoring.

[0003] A method proposes to input the indicator vectors corresponding to M indicator data into the association prediction model, output M prediction vectors, determine the first training loss according to the M indicator vectors, M prediction vectors, the reference association matrix and the weight matrix corresponding to the association prediction model, and then update the weight matrix to obtain the target association matrix. According to the target association matrix, the target association data corresponding to each indicator data is determined. When the indicator data is monitored according to user instructions, the target association data of the indicator data is also monitored at the same time.

[0004] However, there may be a certain lag in the correlation between indicator data. For example, the change of a certain indicator data may not affect another indicator data until several moments later, which may result in the above method still having potential correlations between indicator data that have not been discovered, reducing the comprehensiveness and completeness of data monitoring. Therefore, how to further improve the comprehensiveness and completeness of data monitoring has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a data monitoring method, apparatus, medium and device based on continuous intelligence to solve the problem.

[0006] In a first aspect, a data monitoring method based on continuous intelligence is provided, the method comprising: Obtain monitoring data streams corresponding to M indicator data, where M is an integer greater than zero; For any indicator data, determine the indicator vectors corresponding to the M indicator data respectively according to the preset sliding window, the M monitoring data streams and the starting position offsets respectively corresponding to the M indicator data; Inputting the M indicator vectors into a trained association prediction sub-model, and outputting a prediction vector corresponding to the indicator data, wherein the trained association prediction sub-model corresponds to a first association vector of the indicator data; According to the indicator vector and the prediction vector, the starting position offsets corresponding to the M indicator data are updated to obtain the target position offsets corresponding to the M indicator data; When real-time monitoring data corresponding to the M indicator data are collected, the M monitoring data streams are updated, and update vectors corresponding to the M indicator data are determined according to the sliding window, the M updated monitoring data streams and the target position offsets corresponding to the M indicator data; Inputting M update vectors into the trained association prediction sub-model, and outputting a first prediction vector corresponding to the indicator data; Inputting the updated monitoring data stream corresponding to the indicator data into the trained time series prediction model to obtain a second prediction vector corresponding to the indicator data; updating the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model, wherein the updated association prediction sub-model corresponds to the second association vector of the indicator data; According to the second association vector, associated indicator data of the indicator data is determined, and the associated indicator data is used to simultaneously monitor the associated indicator data of the indicator data when the indicator data is monitored according to a user instruction.

[0007] In a second aspect, a data monitoring device based on continuous intelligence is provided, the device comprising: A data stream acquisition module is used to acquire monitoring data streams corresponding to M indicator data, where M is an integer greater than zero; A vector interception module, for determining, for any indicator data, the indicator vectors corresponding to the M indicator data respectively according to a preset sliding window, M monitoring data streams and the starting position offsets corresponding to the M indicator data respectively; A first vector prediction module, used for inputting the M indicator vectors into a trained association prediction sub-model, and outputting a prediction vector corresponding to the indicator data, wherein the trained association prediction sub-model corresponds to a first association vector of the indicator data; An offset updating module, used for updating the starting position offsets respectively corresponding to the M indicator data according to the indicator vector and the prediction vector, to obtain the target position offsets respectively corresponding to the M indicator data; A vector updating module, configured to update the M monitoring data streams when real-time monitoring data corresponding to the M indicator data are collected, and determine update vectors corresponding to the M indicator data according to the sliding window, the M updated monitoring data streams and the target position offsets corresponding to the M indicator data; A second vector prediction module, used for inputting M update vectors into the trained association prediction sub-model, and outputting a first prediction vector corresponding to the indicator data; A third vector prediction module, used for inputting the updated monitoring data stream corresponding to the indicator data into the trained time series prediction model to obtain a second prediction vector corresponding to the indicator data; a model updating module, configured to update the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model, wherein the updated association prediction sub-model corresponds to the second association vector of the indicator data; The data monitoring module is used to determine the associated indicator data of the indicator data according to the second association vector, and the associated indicator data is used to monitor the associated indicator data of the indicator data when the indicator data is monitored according to the user instruction.

[0008] In a third aspect, an embodiment of the present invention provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, it implements the data monitoring method of the first aspect.

[0009] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the data monitoring method of the first aspect is implemented.

[0010] Compared with the prior art, the present invention has the following beneficial effects: Taking the position offset of the sliding window as the object, further training is performed on the basis of the association prediction sub-model to mine the lagging information of the association relationship between each indicator data and the specific indicator data, which is conducive to discovering new association relationships between indicator data. Moreover, the joint prediction results of the update vector and the time series prediction results are compared to help the association prediction sub-model further learn the time series information, improve the reliability of the second association vector, and then mine the potential association relationship from the second association vector, thereby improving the comprehensiveness and completeness of data monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative labor. Figure 1This is a schematic diagram of an application environment of a data monitoring method based on continuous intelligence provided by the first embodiment of the present invention; Figure 2 1 is a flow chart of a data monitoring method based on continuous intelligence provided in Embodiment 1 of the present invention; Figure 3 is a structural diagram of a data monitoring device based on continuous intelligence provided by Embodiment 2 of the present invention; Figure 4 It is a structural diagram of a computer device corresponding to a data monitoring method based on continuous intelligence provided in Embodiment 3 of the present invention; DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0013] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0014] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0015] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0016] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0017] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0018] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0019] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0020] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0021] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.

[0022] A data monitoring method based on continuous intelligence provided by the first embodiment of the present invention can be applied in the following aspects: Figure 1In the application environment, the data input layer can provide the data monitoring method with monitoring data corresponding to each indicator data at multiple preset time points, that is, provide monitoring data streams corresponding to each indicator data. This embodiment 1 can be applied to a database to perform data analysis, determine the associated indicator data of each indicator data, and provide the association relationship between indicator data for the system monitoring service in the service platform. Then, when the user interacts with the application layer to perform the data display function, the associated indicator data with the indicator data specified by the user can be displayed at the same time, which improves the comprehensiveness of data monitoring and provides users with a better data display experience. The database can also include a trained association prediction model. The weight matrix of the trained association prediction model can be split to obtain the first association vector of the association prediction sub-model corresponding to the M indicator vectors.

[0023] See also Figure 2 , is a flow chart of a data monitoring method based on continuous intelligence provided by the first embodiment of the present invention. The above data monitoring method can be applied to Figure 1 In the database in the service platform, data analysis is performed to determine the associated indicator data of each indicator data, and the association relationship between indicator data is provided for the system monitoring service in the service platform. Then, when the user interacts with the application layer to perform the data display function, the associated indicator data with the indicator data specified by the user can be displayed at the same time, which improves the comprehensiveness of data monitoring and provides users with a better data display experience. The database can also include a trained association prediction model. By splitting the weight matrix of the trained association prediction model, the first association vector of the association prediction sub-model corresponding to each of the M indicator vectors can be obtained. Figure 2 As shown, the data monitoring method may include the following steps: Step S201, obtaining monitoring data streams corresponding to M indicator data respectively.

[0024] Wherein, M is an integer greater than zero, the indicator data may refer to the indicator to be monitored, and the monitoring data stream may be a vector formed by monitoring data obtained by monitoring the corresponding indicator data at a number of preset time points.

[0025] Step S202, for any indicator data, according to a preset sliding window, M monitoring data streams and the starting position offsets respectively corresponding to the M indicator data, determine the indicator vectors respectively corresponding to the M indicator data.

[0026] Among them, the indicator vector can be obtained from the monitoring data stream of the corresponding indicator data in the form of a sliding window. The size and step size of the sliding window are both default values ​​in this embodiment. For example, the size is a preset size and the step size is 1. The starting position of the sliding window of any indicator data is determined according to its starting position offset vector. The starting position offset can refer to the distance between the sliding window position of the corresponding indicator data and the sliding window position of the specific indicator data. In this embodiment, the sliding window position can be represented by the left border of the sliding window.

[0027] Optionally, for any indicator data, according to a preset sliding window, M monitoring data streams and starting position offsets respectively corresponding to the M indicator data, indicator vectors respectively corresponding to the M indicator data are determined, including: For any indicator data, according to the starting position offsets respectively corresponding to the M indicator data, the sliding window starting positions respectively corresponding to the M indicator data are determined, and the starting position offsets are all second preset values; According to the sliding window starting positions, sliding windows and M monitoring data streams respectively corresponding to the M indicator data, indicator vectors respectively corresponding to the M indicator data are intercepted.

[0028] The second preset value may be 0, that is, initially, the sliding window starting positions of the sliding windows are the same, which corresponds to the training result of the associated prediction model.

[0029] Step S203, inputting M indicator vectors into the trained association prediction sub-model, and outputting a prediction vector corresponding to the indicator data, wherein the trained association prediction sub-model corresponds to the first association vector of the indicator data.

[0030] The trained association prediction sub-model may be determined according to the trained association prediction model.

[0031] Specifically, the trained association prediction model can be trained based on the M indicator vectors intercepted by each sliding window at the same sliding window starting position and the preset first training loss. The trained association prediction model corresponds to a target association matrix, and the target association matrix contains target association vectors corresponding to the M indicator data respectively. The target association vector can be used to characterize the association relationship between the corresponding indicator data and other indicator data, and the target association vector is essentially a part of the weight matrix of the association prediction model.

[0032] Therefore, in this embodiment, for any indicator data, the target association vector corresponding to the indicator data in the target association matrix is ​​used as the first association vector of the indicator data, and the first association vector is used as the weight vector of the association prediction sub-model. Since the association prediction model is trained, the default association prediction sub-model is also trained. It can be known that each of the M indicator data corresponds to a trained association prediction sub-model, and the processing flow corresponding to each indicator data is the same. Therefore, this embodiment describes the processing flow with a single indicator data.

[0033] In addition, the trained association prediction model includes M first neurons and M second neurons, and correspondingly, the trained association prediction sub-model includes M first neurons and one second neuron.

[0034] Optionally, the mth element in the first association vector corresponding to the mth indicator data is a second preset value, and m is an integer in the range of [1, M].

[0035] The second preset value may be 0, and the mth element in the first association vector corresponding to the mth indicator data is the second preset value, which can ensure that the prediction of the specific indicator data will not be affected by itself.

[0036] It should be noted that when mining the correlation of indicator data, we do not want the indicator data itself to contribute to the prediction of the indicator data, but rather hope to obtain specific indicator data through the prediction of other indicator data and reflect it in the first association vector, that is, the mth element in the first association vector corresponding to the mth indicator data is the second preset value.

[0037] Step S204: updating the starting position offsets corresponding to the M indicator data respectively according to the indicator vector and the prediction vector, and obtaining the target position offsets corresponding to the M indicator data respectively.

[0038] The target position offset may refer to the updated sliding window position offset of the corresponding indicator data.

[0039] Optionally, the starting position offsets corresponding to the M indicator data are updated according to the indicator vector and the prediction vector to obtain the target position offsets corresponding to the M indicator data, including: Perform distance calculation based on the indicator vector and the prediction vector, and use the distance calculation result as the second training loss; According to the second training loss, the starting position offsets corresponding to the M indicator data are updated until the second training loss converges, and the target position offsets corresponding to the M indicator data are obtained.

[0040] The distance calculation may adopt the Euclidean distance calculation method.

[0041] Specifically, since the sliding window is a clipping operation, and the clipping operation is not differentiable, the target position offset cannot be updated according to the gradient descent method in this embodiment. In this embodiment, the simulated annealing algorithm is used to update the target position offset. The implementer can also choose genetic algorithms, random update algorithms, etc. to update the target position offset according to actual conditions.

[0042] Step S205, when real-time monitoring data corresponding to M indicator data are collected, M monitoring data streams are updated, and update vectors corresponding to the M indicator data are determined according to the sliding window, the M updated monitoring data streams and the target position offsets corresponding to the M indicator data.

[0043] For any indicator data, when the real-time monitoring data corresponding to the indicator data is collected, the monitoring data stream corresponding to the indicator data is updated, that is, the real-time monitoring data is added to the end of the monitoring data stream.

[0044] Specifically, this embodiment assumes that the monitoring data collection time points of various indicator data are consistent, so each monitoring data stream is updated synchronously, and when the real-time monitoring data corresponding to M indicator data are collected, it is necessary to update the sliding window position corresponding to the specific indicator data, specifically by adding the preset step size of the sliding window to the sliding window position to obtain the updated sliding window position.

[0045] Step S206, inputting the M update vectors into the trained association prediction sub-model, and outputting the first prediction vector corresponding to the indicator data.

[0046] The first prediction vector may refer to a joint prediction result based on M update vectors.

[0047] Step S207: input the updated monitoring data stream corresponding to the indicator data into the trained time series prediction model to obtain a second prediction vector corresponding to the indicator data.

[0048] The second prediction vector may refer to a result of performing time series prediction according to an update vector of specific indicator data.

[0049] Specifically, the time series prediction model can adopt a recurrent neural network model, a long short-term memory network model, etc.

[0050] Step S208, updating the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model, wherein the updated association prediction sub-model corresponds to the second association vector of the indicator data.

[0051] The second association vector can represent the association relationship between various indicator data, and the second association vector is essentially a weight vector of the updated association prediction sub-model.

[0052] Optionally, updating the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model includes: Performing distance calculation according to the first prediction vector and the second prediction vector, and taking the distance calculation result as the third training loss; According to the third training loss, the trained association prediction sub-model is updated until the third training loss converges to obtain an updated association prediction sub-model.

[0053] Among them, the distance calculation also adopts the Euclidean distance calculation method. In this embodiment, the weight vector of the associated prediction sub-model is updated based on the difference between the time series prediction result and the joint prediction result. The reason is that the time series information is not fully paid attention to during the training process of the associated prediction model, which may result in missed or wrong judgments in the final associated relationship. In the training process of the associated prediction sub-model, the time series prediction result construction loss is introduced to improve the perception of the associated prediction sub-model to the time series information, thereby improving the reliability and accuracy of the determination of the associated relationship, and is also conducive to discovering indicator vectors that are associated in time series, thereby improving the comprehensiveness and completeness of data monitoring.

[0054] Optionally, the trained association prediction sub-model is updated according to the third training loss until the third training loss converges to obtain an updated association prediction sub-model, including: Determining a fourth training loss based on the first association vector and the second association vector; Determine the update loss based on the third training loss and the fourth training loss; According to the update loss, the trained association prediction sub-model is updated until the update loss converges to obtain an updated association prediction sub-model.

[0055] The first associated vector and the second associated vector are multiplied point by point, the point-by-point multiplication result is subtracted from the first associated vector point by point and the absolute value is calculated, and the calculation result is element-wise summed, and the element-wise sum calculation result is used as the fourth training loss.

[0056] Specifically, the first association vector may include an element with a first preset value, which represents the prior information obtained from the target association matrix corresponding to the association prediction model. It should be noted that the target association matrix can be binarized to ensure that the elements in the first association vector only have two values, namely the first preset value and the second preset value, to facilitate subsequent processing.

[0057] The fourth training loss can supervise that the prior information in the first association vector is not lost, thereby avoiding the loss of prior information pre-introduced by the implementer or pre-learned by the association prediction model as the weight vector corresponding to the association prediction sub-model is updated during the training process, thereby ensuring that the update of the weight vector corresponding to the association prediction sub-model is better than or equal to the existing prior knowledge.

[0058] Step S209: determining associated indicator data of the indicator data according to the second associated vector, wherein the associated indicator data is used to simultaneously monitor the associated indicator data of the indicator data when the indicator data is monitored according to the user instruction.

[0059] Optionally, determining the associated indicator data of the indicator data according to the second associated vector includes: For any indicator data, the indicator data corresponding to the element in the corresponding second association vector that is not the second preset value is used as the associated indicator data of the indicator data.

[0060] Among them, the user can monitor specific indicator data through user instructions. At this time, the related indicator data of the specific indicator data is monitored at the same time. In another embodiment, all indicator data can be monitored at the same time. The user can display the monitored specific indicator data through user instructions. At this time, the monitoring data corresponding to the related indicator data of the specific indicator data is displayed at the same time, thereby improving the comprehensiveness and completeness of data monitoring and data display, and improving the user's data monitoring and data display experience.

[0061] In this embodiment, the position offset of the sliding window is taken as the object, and further training is performed on the basis of the association prediction sub-model, so as to mine the lagging information of the association relationship between each indicator data and the specific indicator data, which is conducive to discovering new association relationships between the indicator data. Moreover, the joint prediction results of the update vector and the time series prediction results are compared to help the association prediction sub-model further learn the time series information, improve the reliability of the second association vector, and then mine the potential association relationship from the second association vector, thereby improving the comprehensiveness and completeness of data monitoring.

[0062] Corresponding to the method of the above embodiment 1, Figure 3A schematic diagram of the structure of a data monitoring device based on continuous intelligence provided by the second embodiment of the present invention is shown. The above-mentioned data monitoring device is applied to a database to perform data analysis, determine the associated indicator data of each indicator data, and provide the association relationship between indicator data for the system monitoring service in the service platform. Then, when the user interacts with the application layer to perform the data display function, the associated indicator data with the indicator data specified by the user can be displayed at the same time, which improves the comprehensiveness of data monitoring and provides users with a better data display experience. The database can also include a trained association prediction model. The weight matrix of the trained association prediction model can be split to obtain the first association vector of the association prediction sub-model corresponding to M indicator vectors. For ease of explanation, only the part related to the embodiment of the present invention is shown.

[0063] See also Figure 3 , the data monitoring device comprises: The data stream acquisition module 31 is used to acquire monitoring data streams corresponding to M indicator data, where M is an integer greater than zero; The vector interception module 32 is used to determine the indicator vectors corresponding to the M indicator data respectively according to the preset sliding window, the M monitoring data streams and the starting position offsets corresponding to the M indicator data respectively for any indicator data; A first vector prediction module 33, used to input the M indicator vectors into a trained association prediction sub-model, and output a prediction vector corresponding to the indicator data, wherein the trained association prediction sub-model corresponds to a first association vector of the indicator data; An offset updating module 34 is used to update the starting position offsets corresponding to the M indicator data respectively according to the indicator vector and the prediction vector, so as to obtain the target position offsets corresponding to the M indicator data respectively; The vector updating module 35 is used to update the M monitoring data streams when the real-time monitoring data corresponding to the M indicator data are collected, and determine the update vectors corresponding to the M indicator data according to the sliding window, the M updated monitoring data streams and the target position offsets corresponding to the M indicator data; A second vector prediction module 36, used to input the M update vectors into the trained association prediction sub-model and output a first prediction vector corresponding to the indicator data; A third vector prediction module 37, used to input the updated monitoring data stream corresponding to the indicator data into the trained time series prediction model to obtain a second prediction vector corresponding to the indicator data; A model updating module 38 is used to update the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model, wherein the updated association prediction sub-model corresponds to the second association vector of the indicator data; The data monitoring module 39 is used to determine the associated indicator data of the indicator data according to the second associated vector, and the associated indicator data is used to monitor the associated indicator data of the indicator data when the indicator data is monitored according to the user instruction.

[0064] Optionally, the vector interception module 32 includes: A position determination submodule, for determining, for any indicator data, the sliding window starting positions corresponding to the M indicator data respectively according to the starting position offsets corresponding to the M indicator data respectively, wherein the starting position offsets are all second preset values; The sliding window interception submodule is used to intercept the indicator vectors corresponding to the M indicator data respectively according to the sliding window starting positions, sliding windows and M monitoring data streams corresponding to the M indicator data respectively.

[0065] Optionally, the offset updating module 34 includes: A second loss calculation submodule, used for performing distance calculation according to the indicator vector and the prediction vector, and taking the distance calculation result as the second training loss; The second loss training submodule is used to update the starting position offsets corresponding to the M indicator data respectively according to the second training loss until the second training loss converges to obtain the target position offsets corresponding to the M indicator data respectively.

[0066] Optionally, in the first association vector in the first vector prediction module 33, the mth element in the first association vector corresponding to the mth indicator data is a second preset value, and m is an integer in the range of [1, M].

[0067] Optionally, the model updating module 38 includes: A third loss calculation submodule, used for performing distance calculation according to the first prediction vector and the second prediction vector, and taking the distance calculation result as the third training loss; The third loss training submodule is used to update the trained association prediction submodel according to the third training loss until the third training loss converges to obtain an updated association prediction submodel.

[0068] Optionally, the third loss training submodule includes: a fourth loss calculation unit, configured to determine a fourth training loss according to the first association vector and the second association vector; An update loss determination unit, used to determine an update loss according to the third training loss and the fourth training loss; The update loss training unit is used to update the trained association prediction sub-model according to the update loss until the update loss converges to obtain an updated association prediction sub-model.

[0069] Optionally, the data monitoring module 39 includes: The association determination submodule is used to use, for any indicator data, the indicator data corresponding to the element in the corresponding second association vector that is not a second preset value as the associated indicator data of the indicator data.

[0070] It should be noted that the information interaction, execution process, etc. between the above-mentioned modules, sub-modules, and units are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0071] Figure 4 A schematic diagram of the structure of a computer device corresponding to a data monitoring method based on continuous intelligence provided in Embodiment 3 of the present invention. Figure 4 As shown, the computer device of this embodiment includes: at least one processor ( Figure 4 Only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor, wherein when the processor executes the computer program, the steps in any of the above-mentioned data monitoring method embodiments are implemented.

[0072] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that Figure 4 This is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than those shown in the figure, or a combination of certain components, or different components. For example, it may also include a network interface, a display screen, and an input device.

[0073] The processor may be a CPU, or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0074] The memory includes a readable storage medium, an internal memory, etc., wherein the internal memory may be the memory of a computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be a hard disk of a computer device, and in other embodiments, it may also be an external storage device of the computer device, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of a computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0075] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0076] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing.

[0077] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0079] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A data monitoring method based on continuous intelligence, characterized in that: The data monitoring method comprises: Obtain monitoring data streams corresponding to M indicator data, where M is an integer greater than zero; For any indicator data, determine the indicator vectors corresponding to the M indicator data respectively according to the preset sliding window, the M monitoring data streams and the starting position offsets respectively corresponding to the M indicator data; Inputting the M indicator vectors into a trained association prediction sub-model, and outputting a prediction vector corresponding to the indicator data, wherein the trained association prediction sub-model corresponds to a first association vector of the indicator data; According to the indicator vector and the prediction vector, the starting position offsets corresponding to the M indicator data are updated to obtain the target position offsets corresponding to the M indicator data; When real-time monitoring data corresponding to the M indicator data are collected, the M monitoring data streams are updated, and update vectors corresponding to the M indicator data are determined according to the sliding window, the M updated monitoring data streams and the target position offsets corresponding to the M indicator data; Inputting M update vectors into the trained association prediction sub-model, and outputting a first prediction vector corresponding to the indicator data; Inputting the updated monitoring data stream corresponding to the indicator data into the trained time series prediction model to obtain a second prediction vector corresponding to the indicator data; updating the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model, wherein the updated association prediction sub-model corresponds to the second association vector of the indicator data; According to the second association vector, associated indicator data of the indicator data is determined, and the associated indicator data is used to simultaneously monitor the associated indicator data of the indicator data when the indicator data is monitored according to a user instruction.

2. The data monitoring method according to claim 1, characterized in that: For any indicator data, determining the indicator vectors corresponding to the M indicator data respectively according to the preset sliding window, the M monitoring data streams and the starting position offsets respectively corresponding to the M indicator data, includes: For any indicator data, determining the sliding window starting positions corresponding to the M indicator data respectively according to the starting position offsets respectively corresponding to the M indicator data, wherein the starting position offsets are all second preset values; According to the sliding window starting positions respectively corresponding to the M indicator data, the sliding window and the M monitoring data streams, the indicator vectors respectively corresponding to the M indicator data are intercepted.

3. The data monitoring method according to claim 1, characterized in that: The updating of the starting position offsets respectively corresponding to the M indicator data according to the indicator vector and the prediction vector to obtain the target position offsets respectively corresponding to the M indicator data includes: Performing distance calculation based on the indicator vector and the prediction vector, and using the distance calculation result as the second training loss; According to the second training loss, the starting position offsets respectively corresponding to the M indicator data are updated until the second training loss converges, so as to obtain the target position offsets respectively corresponding to the M indicator data.

4. The data monitoring method according to claim 1, characterized in that: The mth element in the first association vector corresponding to the mth indicator data is a second preset value, and m is an integer in the range of [1, M].

5. The data monitoring method according to claim 1, characterized in that: The updating of the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model includes: Performing distance calculation based on the first prediction vector and the second prediction vector, and using the distance calculation result as a third training loss; According to the third training loss, the trained association prediction sub-model is updated until the third training loss converges to obtain the updated association prediction sub-model.

6. The data monitoring method according to claim 5, characterized in that: The step of updating the trained association prediction sub-model according to the third training loss until the third training loss converges to obtain the updated association prediction sub-model comprises: determining a fourth training loss according to the first association vector and the second association vector; Determine an update loss according to the third training loss and the fourth training loss; The trained association prediction sub-model is updated according to the update loss until the update loss converges to obtain the updated association prediction sub-model.

7. The data monitoring method according to claims 1 to 6, characterized in that: The determining, according to the second association vector, the associated indicator data of the indicator data comprises: For any indicator data, the indicator data corresponding to the element in the corresponding second association vector that is not the second preset value is used as the associated indicator data of the indicator data.

8. A data monitoring device based on continuous intelligence, characterized in that: The data monitoring device comprises: A data stream acquisition module is used to acquire monitoring data streams corresponding to M indicator data, where M is an integer greater than zero; A vector interception module, for determining, for any indicator data, the indicator vectors corresponding to the M indicator data respectively according to a preset sliding window, M monitoring data streams and the starting position offsets corresponding to the M indicator data respectively; A first vector prediction module, used for inputting the M indicator vectors into a trained association prediction sub-model, and outputting a prediction vector corresponding to the indicator data, wherein the trained association prediction sub-model corresponds to a first association vector of the indicator data; An offset updating module, used for updating the starting position offsets respectively corresponding to the M indicator data according to the indicator vector and the prediction vector, to obtain the target position offsets respectively corresponding to the M indicator data; A vector updating module, configured to update the M monitoring data streams when real-time monitoring data corresponding to the M indicator data are collected, and determine update vectors corresponding to the M indicator data according to the sliding window, the M updated monitoring data streams and the target position offsets corresponding to the M indicator data; A second vector prediction module, used for inputting M update vectors into the trained association prediction sub-model, and outputting a first prediction vector corresponding to the indicator data; A third vector prediction module, used for inputting the updated monitoring data stream corresponding to the indicator data into the trained time series prediction model to obtain a second prediction vector corresponding to the indicator data; a model updating module, configured to update the trained association prediction sub-model according to the first prediction vector and the second prediction vector to obtain an updated association prediction sub-model, wherein the updated association prediction sub-model corresponds to the second association vector of the indicator data; The data monitoring module is used to determine the associated indicator data of the indicator data according to the second association vector, and the associated indicator data is used to monitor the associated indicator data of the indicator data when the indicator data is monitored according to the user instruction.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the data monitoring method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the data monitoring method according to any one of claims 1 to 7 is implemented.

Images