Business data classification optimization method, device and non-volatile storage medium

Abstract

The present application discloses a method, device and non-volatile storage medium for optimizing the classification of business data. The method includes: determining the business type of the business data in the target business data set, and determining the first weight value of the business field in the business data corresponding to the business type; analyzing the business data based on the optical reserve pool to obtain the second weight value of the business field in the target business data set; calculating the first fitting value and the second fitting value of the target business data set based on the first weight value, the second weight value and the business data; adjusting the business type division of the business data in the target business data set when the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold. The present application solves the technical problem that the data classification accuracy is not high in the related technology when classifying and predicting business data due to the huge amount of business data of each business type.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and non-volatile storage medium for optimizing business data classification. Background Art

[0002] With the development of science and technology and the Internet, the era of big data is coming. All walks of life are generating huge amounts of data fragments every day. For business processing systems, due to the huge amount of business data of various business types, in the process of analyzing and processing business data, they are limited by computing power and the accuracy of artificial intelligence models. When classifying and predicting business data in distributed clusters, there are technical problems such as low data classification accuracy.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a business data classification optimization method, device and non-volatile storage medium to at least solve the technical problem of low data classification accuracy when classifying and predicting business data in related technologies due to the huge amount of business data of various business types.

[0005] According to one aspect of an embodiment of the present application, a business data classification optimization method is provided, including: determining the business type of business data in a target business data set, and determining a first weight value of a business field in the business data corresponding to the business type, wherein the business data in the same target business data set are of the same business type, and each business data includes at least one business field; analyzing the business data based on an optical reserve pool to obtain a second weight value of the business field in the target business data set, wherein the optical reserve pool is a data analysis model that uses optical signals to perform calculations on data; calculating a first fitting value and a second fitting value of the target business data set based on the first weight value, the second weight value and the business data, wherein the first fitting value is used to characterize the proportion of the business data used in determining the first weight value to all the business data in the target business data set, and the second fitting value is used to characterize the proportion of the business data used in determining the second weight value to all the business data in the target business data set; when the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold, adjusting the business type division of the business data in the target business data set.

[0006] Optionally, calculating the first fitting value and the second fitting value of the target business data set based on the first weight value, the second weight value and the business data includes: determining a target regression function, wherein the target regression function is used to characterize the quantity of business data used in the process of determining the weight value of the business field based on the business data; inputting the first weight value and the business data into the target regression function for calculation to obtain the first fitting value; inputting the second weight value and the business data into the target regression function for calculation to obtain the second fitting value.

[0007] Optionally, adjusting the business type classification of business data in the target business data set includes: determining the target business data in the target business data set, wherein the target business data is the business data used in the process of determining the first weight value and the second weight value; determining the overfitted business data based on the target business data, wherein the overfitted business data is the remaining business data in all the business data of the target business data set excluding the target business data; and adjusting the overfitted business data to the remaining target business data set.

[0008] Optionally, adjusting the overfitted business data to the remaining target business data sets includes: adding the overfitted business data to the first business data set, wherein the first business data set is a target business data set other than the target business data set where the overfitted business data is located; recalculating the first fitting value and the second fitting value of the first business data set based on the first business data set after adding the overfitted business data; when the difference between the recalculated first fitting value and the second fitting value of the first business data set is greater than a preset fitting threshold, re-adding the overfitted business data to the remaining target business data sets, and repeating the above steps until the difference between the recalculated first fitting value and the second fitting value is not greater than the preset fitting threshold.

[0009] Optionally, after recalculating the first fitting value and the second fitting value of the first business data set, it also includes: when the difference between the recalculated first fitting value and the second fitting value of the first business data set is not greater than a preset fitting threshold, determining that the business type of the overfitted data is the business type corresponding to the first business data set, and storing the first business data set after adding the overfitted business data into the system.

[0010] Optionally, the method also includes: when all target business data sets have been added with overfitted business data to recalculate the first fitting value and the second fitting value and both do not meet the preset conditions, determining that the overfitted business data is miscellaneous data, wherein the preset condition is that the difference between the recalculated first fitting value and the second fitting value is not greater than a preset fitting threshold.

[0011] Optionally, before determining the first weight value of the business field in the business data corresponding to the business type, it also includes: establishing a target scheduling cluster; establishing multiple target clusters through the target scheduling cluster, wherein the target cluster is used to run each application module within the business system; according to the target classification function, dividing the business data generated in the target cluster to obtain multiple target business data sets, wherein the target classification function is used to indicate the correlation between the business data and the business type.

[0012] According to another aspect of an embodiment of the present application, a service data classification optimization device is further provided, comprising: a first calculation module, configured to determine a service type of service data in a target service data set, and determine a first weight value of a service field in the service data corresponding to the service type, wherein the service data in the same target service data set are of the same service type, and each service data includes at least one service field; a second calculation module, configured to analyze the service data based on an optical reserve pool to obtain a second weight value of the service field in the target service data set, wherein the optical reserve pool is a data analysis model that uses optical signals to perform calculations on data; a fitting judgment module, configured to calculate a first fitting value and a second fitting value of the target service data set based on the first weight value, the second weight value, and the service data, wherein the first fitting value is used to represent the proportion of the service data used in determining the first weight value to the total service data in the target service data set, and the second fitting value is used to represent the proportion of the service data used in determining the second weight value to the total service data in the target service data set; and a classification optimization module, configured to adjust the service type classification of the service data in the target service data set when the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold.

[0013] According to another aspect of an embodiment of the present application, an electronic device is provided. The electronic device includes a processor, and the processor is used to run a program, wherein the business data classification optimization method is executed when the program is running.

[0014] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the business data classification optimization method by running the computer program.

[0015] In an embodiment of the present application, a method is adopted to determine the business type of business data in a target business data set, and to determine a first weight value of a business field in the business data corresponding to the business type, wherein the business data in the same target business data set are of the same business type, and each piece of business data includes at least one business field; the business data is analyzed based on an optical reserve pool to obtain a second weight value of the business field in the target business data set, wherein the optical reserve pool is a data analysis model that uses optical signals to perform calculations on data; based on the first weight value, the second weight value and the business data, a first fitting value and a second fitting value of the target business data set are calculated, wherein the first fitting value is used to characterize the proportion of the business data used in determining the first weight value. The second fitting value is used to characterize the proportion of all business data in the target business data set in the process of determining the second weight value; when the difference between the first fitting value and the second fitting value is greater than the preset fitting threshold, the business type division of the business data in the target business data set is adjusted, and the overfitting calculation is performed through the data regression model, and the target business data set of each business type is adjusted according to the calculated fitting value and the preset conditions, thereby achieving the purpose of improving the accuracy of business data classification, and thus solving the technical problem of low data classification accuracy when classifying and predicting business data in related technologies due to the huge amount of business data of each business type. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 This is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a method for optimizing business data classification according to an embodiment of the present application.

[0018] Figure 2 This is a schematic diagram of a method flow for optimizing business data classification according to an embodiment of the present application;

[0019] Figure 3 1 is a schematic diagram of a method flow for determining a business type of business data and a weight value of a business field in business data of each business type provided in an embodiment of the present application;

[0020] Figure 4 This is a schematic diagram of the composition structure of a light storage tank provided according to an embodiment of the present application;

[0021] Figure 5It is a structural diagram of a business data classification optimization device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] To facilitate those skilled in the art to better understand the embodiments of the present application, some technical terms or nouns involved in the embodiments of the present application are explained as follows:

[0025] Kubernetes: An open-source Linux container automation platform that eliminates many of the manual steps involved in deploying and scaling containerized applications. In other words, you can combine multiple hosts into clusters to run Linux containers, and Kubernetes helps you manage those clusters simply and efficiently. These clusters can also span public, private, and hybrid clouds.

[0026] Master: The machine that controls the Kubernetes nodes and where jobs are created.

[0027] Node: Each node machine performs assigned tasks under the control of the Kubernetes master node.

[0028] Pod: A collection of one or more containers deployed as a whole to a single node. Containers within a pod share IP addresses, inter-process communication (IPC), hostnames, and other resources. Pods abstract the underlying container's networking and storage, making it easier to migrate containers within the cluster.

[0029] In related technologies, due to limitations in computing power and the accuracy of artificial intelligence models, there is a problem of low data classification accuracy when classifying and predicting business data. To address this problem, the present application provides a related solution in the following embodiments, which is described in detail below.

[0030] According to an embodiment of the present application, an embodiment of a method for optimizing business data classification is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The following is a hardware block diagram of a computer terminal (or electronic device) for implementing a method for optimizing business data classification. Figure 1 As shown, the computer terminal 10 (or electronic device 10) may include one or more (illustrated as 102a, 102b, ..., 102n) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0032] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or electronic device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0033] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the business data classification optimization method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned business data classification optimization method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0034] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0035] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or electronic device).

[0036] In the above operating environment, the embodiment of the present application provides a business data classification optimization method, Figure 2 FIG. 1 is a schematic diagram of a method flow for optimizing business data classification according to an embodiment of the present application. Figure 2 As shown, the method includes the following steps:

[0037] Step S202: determining the business type of the business data in the target business data set, and determining a first weight value of a business field in the business data corresponding to the business type, wherein the business data in the same target business data set are of the same business type, and each piece of business data includes at least one business field;

[0038] In some embodiments of the present application, before determining the first weight value of the business field in the business data corresponding to the business type, the following steps are also included: establishing a target scheduling cluster; establishing multiple target clusters through the target scheduling cluster, wherein the target cluster is used to run each application module within the business system; dividing the business data generated in the target cluster according to the target classification function to obtain multiple target business data sets, wherein the target classification function is used to indicate the correlation between the business data and the business type.

[0039] First, create a Kubernetes-based scheduling cluster (the target scheduling cluster) on a cluster management server within the network. Simultaneously, establish multiple Kubernetes-based clusters (the target clusters) within the network. The network node where the cluster management server resides is referred to as the cluster management node. Next, use the target classification function to calculate each service classification (service type).

[0040] Specifically, all Pod data (i.e., the above-mentioned business data) in the cluster are analyzed through the target classification function, and the Pod data (i.e., the above-mentioned business data) are divided into multiple business types according to the business type.

[0041] The above target classification function can adopt the Pareto classification model formula, which is shown as follows:

[0042] minf(x)=(f1(x),…f p (x)) T

[0043] Where x is a feasible point, f(x) is the target problem, P represents the number of feasible solutions, the variable feasible region is S, and the corresponding target feasible region is Z = f(S). Given a feasible point x*∈S, we have If f(x*) < f(x), then x* is called the absolutely optimal solution to the multi-objective programming problem. If there is no x∈S such that f(x) < f(x*), then x* is called an efficient solution for the business type, also known as a Pareto optimal solution.

[0044] As an optional implementation method, the Pareto classification model can be used in combination with business data of the same business type to obtain fields with higher weights in the business type and mark the weights (i.e., the first weight value mentioned above). That is, the Pareto classification method is used to perform secondary operations to obtain the first weight value of the business fields in each business type and the business data of each business type.

[0045] Figure 3 is a schematic diagram of a method flow for determining the business type of business data and the weight value of the business field in the business data of each business type provided in an embodiment of the present application, such as Figure 3 As shown, in some embodiments of the present application, the Pod business types of the cluster include but are not limited to: application business, collection and monitoring business, tripartite cooperation business, etc. As an optional implementation method, the weight value can use different numbers to represent different weight levels, for example, 1 represents a high weight level, 2 represents a medium weight level, and 3 represents a low weight level. Figure 3 As shown in , the first weight value of the business field in the business data of each business type calculated by the Pareto classification model is as follows:

[0046] Application business (10): Name = 1, IP = 1, Source = 1, Occurrence time = 2, End time = 2, Work order number = 2, SN = 1, Department = 1, Cluster = 3, Pod = 3

[0047] Collection and monitoring services (12): Device name = 1, Collection cycle = 3, Threshold = 1, Monitoring status = 1, IP = 1, Fault occurrence time = 1, Fault recovery time = 2, Fault duration = 2, Fault level = 2, Fault cause = 1, Cluster = 3, Pod = 3

[0048] Tripartite cooperation business (7): Source manufacturer = 1, Data format = 2, Index data, Application department = 2, Cluster = 3, Pod = 3, IP = 1

[0049] Step S204: Analyze the service data based on the optical reserve pool to obtain a second weight value of the service field in the target service data set, wherein the optical reserve pool is a data analysis model that uses optical signals to perform computational processing on data;

[0050] Figure 4 Schematic diagram of the composition structure of a light storage pool provided in an embodiment of the present application, such as Figure 4As shown, the input layer (optical filter) and reservoir processing in the optical reservoir are fixed and can be implemented using an optical path. By arranging information in wavelength, phase, and polarization direction, large-scale parallel computing can be performed in the same optical path. In addition, since there is no resistance in the optical path, the power consumption is theoretically zero, and all calculations are performed through optical interference, so computing can be performed with ultra-low power. By applying optical device technology for communication, they can be deployed and installed on a large scale in a very small size.

[0051] The reservoir is embodied as a ring-shaped optical path, with a semiconductor optical amplifier placed inside. With a simple structure, it realizes the function of generating nonlinear interactions between circulating optical signals and generating various complex signals required by the reservoir.

[0052] Reservoir Computing significantly simplifies the data training process for artificial intelligence (AI) analysis of big data in ultra-large Kubernetes distributed clusters. This provides an efficient, low-cost, and feasible approach for integrating AI with Kubernetes and Pod services. This significantly improves the accuracy of GNN model training for various service types in cluster big data, optimizing operational efficiency and reducing implementation costs. This application leverages the powerful learning, modeling, and fast processing capabilities of Optical Reservoir Computing to enhance the stability and speed of AI computing in distributed clusters.

[0053] Step S206: Calculate a first fitting value and a second fitting value of the target business data set based on the first weight value, the second weight value, and the business data, wherein the first fitting value is used to represent the proportion of the business data used in determining the first weight value to the total business data in the target business data set, and the second fitting value is used to represent the proportion of the business data used in determining the second weight value to the total business data in the target business data set;

[0054] In some embodiments of the present application, calculating the first fitting value and the second fitting value of the target business data set based on the first weight value, the second weight value and the business data includes the following steps: determining a target regression function, wherein the target regression function is used to characterize the quantity of business data used in the process of determining the weight value of the business field based on the business data; inputting the first weight value and the business data into the target regression function for calculation to obtain the first fitting value; inputting the second weight value and the business data into the target regression function for calculation to obtain the second fitting value.

[0055] As an optional implementation, the above target regression function may adopt a ridge regression method model formula, which is shown in the following formula:

[0056] ||Xθ-y|| 2 +||Γθ|| 2

[0057] Where X is the input, y is the output (prediction result), || represents the regularization operation, and Γ = aI (objective training result = fitting value).

[0058] Specifically, the operation process to prevent overfitting is θ(a)=(X T X+aI) -1 X T y, where I is the identity matrix, θ is the fitting hyperparameter, a is the weight of the identity matrix, and θ(a) is calculated when a is determined. The result of the operation is the above fitting value.

[0059] Step S208 : When the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold, the business type classification of the business data in the target business data set is adjusted.

[0060] In some embodiments of the present application, adjusting the business type classification of business data in a target business data set includes the following steps: determining target business data in the target business data set, wherein the target business data is the business data used in the process of determining the first weight value and the second weight value; determining overfitted business data based on the target business data, wherein the overfitted business data is the remaining business data in all business data of the target business data set excluding the target business data; and adjusting the overfitted business data to the remaining target business data set.

[0061] In some embodiments of the present application, adjusting the overfitted business data to the remaining target business data sets includes the following steps: adding the overfitted business data to the first business data set, wherein the first business data set is a target business data set other than the target business data set where the overfitted business data is located; recalculating the first fitting value and the second fitting value of the first business data set based on the first business data set after adding the overfitted business data; when the difference between the recalculated first fitting value and the second fitting value of the first business data set is greater than a preset fitting threshold, re-adding the overfitted business data to the remaining target business data sets, and repeating the above steps until the difference between the recalculated first fitting value and the second fitting value is not greater than the preset fitting threshold.

[0062] Specifically, the overfitted data (i.e., the overfitted business data) is fitted with other Pod business data (i.e., business data in the target business data set of other business types), and the first fitting value and the second fitting value are recalculated. If the difference between the first fitting value and the second fitting value is within 10% (i.e., the preset fitting threshold), the data is used as incremental data for the target business data set of other business types to supplement the business model calculation. If the difference between the first fitting value and the second fitting value is greater than 10%, the data is then calculated with the Pod business of other business types.

[0063] The above preset fitting threshold can be adjusted according to actual needs.

[0064] As an optional implementation method, the data in the overfitting data where the difference between the first fitting value and the second fitting value is within 10%-20% (the numerical range can be adjusted according to actual conditions) can be retained as redundant data of the current cluster Pod business type data. This step can significantly improve the accuracy of the training of this type of cluster Pod business model.

[0065] In some embodiments of the present application, after recalculating the first fitting value and the second fitting value of the first business data set, the following steps are also included: when the difference between the recalculated first fitting value and the second fitting value of the first business data set is not greater than a preset fitting threshold, determining that the business type of the overfitted data is the business type corresponding to the first business data set, and storing the first business data set after adding the overfitted business data into the system.

[0066] In some embodiments of the present application, the method also includes the following steps: when all target business data sets have been added with overfitted business data to recalculate the first fitting value and the second fitting value and both do not meet the preset conditions, determining that the overfitted business data is miscellaneous data, wherein the preset condition is that the difference between the recalculated first fitting value and the second fitting value is not greater than the preset fitting threshold.

[0067] Specifically, when the overfitting status data (i.e., the above-mentioned overfitting business data) and other Pod business data (i.e., business data in the target business data set of other business types) are fitted and still do not meet the condition that the difference between the first fitting value and the second fitting value is within 10% (i.e., the above-mentioned preset fitting threshold), the overfitting status data (i.e., the above-mentioned overfitting business data) is stored in the miscellaneous database.

[0068] Through the above steps, overfitting calculations are performed through the data regression model, and based on the calculated fitting values ​​and preset conditions, the target business data set of each business type is adjusted, thereby achieving the purpose of improving the accuracy of business data classification, and thus solving the technical problem of low data classification accuracy in related technologies when classifying and predicting business data due to the huge amount of business data of each business type.

[0069] According to an embodiment of the present application, an embodiment of a business data classification optimization device is also provided. Figure 5 This is a schematic diagram of the structure of a business data classification optimization device provided according to an embodiment of the present application. Figure 5 As shown, the device includes:

[0070] A first calculation module 50 is configured to determine a business type of business data in a target business data set, and determine a first weight value of a business field in the business data corresponding to the business type, wherein the business data in the same target business data set are of the same business type, and each piece of business data includes at least one business field;

[0071] A second calculation module 52 is configured to analyze the service data based on the optical reserve pool to obtain a second weight value of the service field in the target service data set, wherein the optical reserve pool is a data analysis model that calculates and processes data using optical signals;

[0072] The fitting judgment module 54 is configured to calculate a first fitting value and a second fitting value of the target business data set based on the first weight value, the second weight value, and the business data, wherein the first fitting value is used to represent the proportion of the business data used in determining the first weight value to the total business data in the target business data set, and the second fitting value is used to represent the proportion of the business data used in determining the second weight value to the total business data in the target business data set;

[0073] The classification optimization module 56 is configured to adjust the business type classification of the business data in the target business data set when the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold.

[0074] It should be noted that the various modules in the above-mentioned business data classification optimization device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0075] It should be noted that the service data classification optimization device provided in this embodiment can be used to perform Figure 1The business data classification optimization method shown, therefore, the relevant explanations and descriptions of the above-mentioned business data classification optimization method are also applicable to the embodiments of this application and will not be repeated here.

[0076] The embodiment of the present application also provides a non-volatile storage medium, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following service data classification optimization method by running the computer program: determining the service type of service data in the target service data set, and determining the first weight value of the service field in the service data corresponding to the service type, wherein the service data in the same target service data set are of the same service type, and each service data includes at least one service field; analyzing the service data according to the optical reserve pool to obtain the second weight value of the service field in the target service data set, wherein the optical reserve pool is a kind of optical reserve pool. A data analysis model that uses optical signals to perform computational processing on data; based on a first weight value, a second weight value and business data, a first fitting value and a second fitting value of a target business data set are calculated, wherein the first fitting value is used to characterize the proportion of the business data used in determining the first weight value to all business data in the target business data set, and the second fitting value is used to characterize the proportion of the business data used in determining the second weight value to all business data in the target business data set; when the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold, the business type classification of the business data in the target business data set is adjusted.

[0077] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0078] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0079] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, 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 units or modules, which can be electrical or other forms.

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

[0081] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0082] 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 this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0083] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A business data classification optimization method, characterized in that: include: Determining a business type of business data in a target business data set, and determining a first weight value of a business field in the business data corresponding to the business type, wherein the business data in the same target business data set are of the same business type, and each piece of the business data includes at least one of the business fields; Analyzing the service data according to an optical reserve pool to obtain a second weight value of the service field in the target service data set, wherein the optical reserve pool is a data analysis model that uses optical signals to perform computational processing on data; Calculating a first fitting value and a second fitting value of the target business data set based on the first weight value, the second weight value, and the business data, wherein the first fitting value is used to represent the proportion of the business data used in determining the first weight value to all business data in the target business data set, and the second fitting value is used to represent the proportion of the business data used in determining the second weight value to all business data in the target business data set; When the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold, the business type division of the business data in the target business data set is adjusted.

2. The business data classification optimization method according to claim 1, characterized in that: Calculating a first fitting value and a second fitting value of the target business data set based on the first weight value, the second weight value, and the business data includes: Determining a target regression function, wherein the target regression function is used to characterize the quantity of the business data used in the process of determining the weight value of the business field based on the business data; Inputting the first weight value and the business data into the target regression function for calculation to obtain the first fitting value; The second weight value and the business data are input into the target regression function for calculation to obtain the second fitting value.

3. The business data classification optimization method according to claim 1, characterized in that: Adjusting the business type classification of the business data in the target business data set includes: Determining target business data in the target business data set, wherein the target business data is the business data used in the process of determining the first weight value and the second weight value; Determining overfitted business data based on the target business data, wherein the overfitted business data is the remaining business data in all the business data of the target business data set excluding the target business data; Adjust the overfitted business data to the remaining target business data sets.

4. The business data classification optimization method according to claim 3, characterized in that: Adjusting the overfitted service data to the remaining target service data sets includes: Adding the overfitting business data to a first business data set, wherein the first business data set is a target business data set other than the target business data set where the overfitting business data is located; recalculating a first fitting value and a second fitting value of the first business data set according to the first business data set after the overfitting business data is added; When the difference between the recalculated first fitting value and the second fitting value of the first business data set is greater than the preset fitting threshold, the overfitted business data is re-added to the remaining target business data sets, and the above steps are repeated until the difference between the recalculated first fitting value and the second fitting value is no greater than the preset fitting threshold.

5. The business data classification optimization method according to claim 4, characterized in that: After recalculating the first fitting value and the second fitting value of the first business data set, the method further includes: When the difference between the first fitting value and the second fitting value of the recalculated first business data set is not greater than the preset fitting threshold, the business type of the overfitted business data is determined to be the business type corresponding to the first business data set, and the first business data set after adding the overfitted business data is stored in the system.

6. The business data classification optimization method according to claim 4, characterized in that: The method further comprises: When all target business data sets have been added with the overfitted business data to recalculate the first fitting value and the second fitting value and both do not meet the preset conditions, the overfitted business data is determined to be miscellaneous data, wherein the preset condition is that the difference between the recalculated first fitting value and the second fitting value is not greater than the preset fitting threshold.

7. The business data classification optimization method according to claim 1, characterized in that: Before determining the first weight value of the service field in the service data corresponding to the service type, the method further includes: Establish a target scheduling cluster; Establishing multiple target clusters through the target scheduling cluster, wherein the target clusters are used to run various application modules in the business system; The business data generated in the target cluster is divided according to a target classification function to obtain a plurality of target business data sets, wherein the target classification function is used to indicate a correlation between the business data and the business type.

8. A business data classification detection device, characterized in that: include: a first calculation module, configured to determine a business type of business data in a target business data set, and determine a first weight value of a business field in the business data corresponding to the business type, wherein the business data in the same target business data set are of the same business type, and each piece of the business data includes at least one of the business fields; a second calculation module, configured to analyze the service data based on an optical reserve pool to obtain a second weight value of the service field in the target service data set, wherein the optical reserve pool is a data analysis model that performs calculations on data using optical signals; a fitting judgment module, configured to calculate a first fitting value and a second fitting value of the target business data set based on the first weight value, the second weight value, and the business data, wherein the first fitting value is used to represent the proportion of the business data used in determining the first weight value to all business data in the target business data set, and the second fitting value is used to represent the proportion of the business data used in determining the second weight value to all business data in the target business data set; A classification optimization module is used to adjust the business type classification of the business data in the target business data set when the difference between the first fitting value and the second fitting value is greater than a preset fitting threshold.

9. An electronic device comprising a processor, characterized in that: The processor is used to run a program, wherein the program executes the business data classification optimization method according to any one of claims 1 to 7 when running.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the business data classification optimization method according to any one of claims 1 to 7 by running the computer program.

Images