Multi-protocol data processing method and device, electronic equipment and storage medium
By loading protocol plugins, preprocessing, and identifying anomalies in the recognition model, and adjusting rule configuration information, the problem of poor adaptability of multi-protocol data processing methods is solved, enabling flexible data processing and intelligent operation and maintenance.
Patent Information
- Application Number
- CN202511699146.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-19
- Publication Date
- 2026-04-10
AI Technical Summary
Existing multi-protocol data processing methods are poorly adaptable, unable to meet the needs of dynamically changing and complex application scenarios, and have high development costs, complex maintenance, and poor scalability.
By loading multiple protocol plugins, the original management information of heterogeneous devices is obtained, preprocessed, and then input into the recognition model for anomaly identification. The rule configuration information is adjusted, the rule configuration information is generated, and the information is encapsulated based on the communication protocol of the target device.
It achieves high flexibility and adaptability, is suitable for complex application scenarios with dynamic changes, and supports unified processing and intelligent operation and maintenance of multi-protocol data.
Smart Images
Figure CN121842300A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of data processing, and in particular to a multi-protocol data processing method and device, electronic equipment and storage medium. BACKGROUND
[0002] With the rapid development of technologies such as the Internet of Things, the Industrial Internet and the Internet of Vehicles, the number and types of terminal devices accessing the network are growing explosively. These devices often come from different manufacturers and use diversified and heterogeneous communication protocols for data exchange. This fragmentation of protocols leads to a serious data island problem, making it extremely difficult to gather, analyze and process data in a unified platform or upper-layer application. Currently, existing multi-protocol data processing methods usually require adaptation and customized development for each type of protocol. This approach not only has high development costs and complex maintenance, but also requires repeated development when new devices are added, which has poor scalability and is difficult to meet the complex application scenarios that change dynamically. SUMMARY
[0003] The present application provides a multi-protocol data processing method, device, electronic equipment and storage medium to solve the defects of poor adaptability of existing multi-protocol data processing methods and difficulty in meeting complex application scenarios that change dynamically.
[0004] The present application provides a multi-protocol data processing method, comprising: loading a plurality of protocol plug-ins based on protocol configuration information, and obtaining original management information from heterogeneous devices based on the plurality of protocol plug-ins; preprocessing the original management information to obtain management information, inputting the management information into a pre-constructed identification model to obtain an abnormality identification result of the management information output by the identification model, and the identification model being obtained by training based on sample management information of sample heterogeneous devices and abnormality identification result labels of the sample management information; adjusting initial rule configuration information based on the abnormality identification result to generate rule configuration information, and processing the management information based on the rule configuration information to obtain processed management information; based on a communication protocol corresponding to a target device, encapsulating the processed management information, and sending the encapsulated management information to the target device.
[0005] In some embodiments, the adjusting of the initial rule configuration information comprises at least one of: adjusting related threshold parameters in the initial rule configuration information in the case of identifying a new device normal operation baseline; In a case where a new abnormal pattern is identified, one or more rules matching the new abnormal pattern are added in the initial rule configuration information; In a case where a target initial rule frequently triggers false positives, the target initial rule is disabled or the priority of the target initial rule is reduced.
[0006] In some embodiments, the management information includes alarm information and performance information, the identification model includes a feature extraction layer, a feature fusion layer, and an identification layer; the feature extraction layer is configured to perform feature extraction on the management information to obtain an alarm feature vector and a performance feature vector; the feature fusion layer is configured to fuse the alarm feature vector and the performance feature vector to obtain a fused feature vector; and the identification layer is configured to perform abnormal identification on the fused feature vector to output the abnormal identification result.
[0007] In some embodiments, the processing of the management information to obtain processed management information includes: filtering the management information to obtain filtered management information; aggregating the filtered management information to obtain aggregated management information; performing correlation analysis on the aggregated management information to obtain the processed management information.
[0008] In some embodiments, the preprocessing of the original management information to obtain management information includes: parsing the original management information to obtain parsed original management information; performing data cleaning, standardization, and alignment processing on the parsed original management information to obtain the management information.
[0009] In some embodiments, the loading of the plurality of protocol plug-ins based on the protocol configuration information includes: obtaining user input in real time; updating initial protocol configuration information based on the user input to obtain the protocol configuration information; updating a plurality of initial protocol plug-ins based on the protocol configuration information to obtain a plurality of protocol plug-ins, and loading the plurality of protocol plug-ins.
[0010] In some embodiments, the training process of the identification model includes: obtaining original sample management information of a sample heterogeneous device, and preprocessing the original sample management information to obtain sample management information; determining an abnormal identification result label of the sample management information; input the sample management information to an initial identification model to obtain an abnormality identification prediction result of the sample management information output by the initial identification model; Based on the abnormality identification prediction result and the abnormality identification result label of the sample management information, a loss function value is calculated, and based on the loss function value, the parameters of the initial identification model are iteratively optimized to obtain the identification model.
[0011] The application also provides a multi-protocol data processing device, comprising: An acquisition unit is configured to load a plurality of protocol plug-ins based on protocol configuration information, and acquire original management information from a heterogeneous device based on the plurality of protocol plug-ins. An abnormality identification unit is configured to preprocess the original management information to obtain management information, and input the management information to a pre-constructed identification model to obtain an abnormality identification result of the management information output by the identification model, wherein the identification model is obtained by training based on sample management information of a sample heterogeneous device and an abnormality identification result label of the sample management information. A rule adjustment unit is configured to adjust initial rule configuration information based on the abnormality identification result to generate rule configuration information, and process the management information based on the rule configuration information to obtain processed management information. A sending unit is configured to encapsulate the processed management information based on a communication protocol corresponding to a target device, and send the encapsulated management information to the target device.
[0012] The application also provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the multi-protocol data processing method according to any one of the above embodiments when executing the program.
[0013] The application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable on a processor to implement the multi-protocol data processing method according to any one of the above embodiments.
[0014] The application provides a multi-protocol data processing method and device, electronic equipment and a storage medium. BRIEF DESCRIPTION OF DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the application or prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.
[0016] Figure 1 is a flowchart of the multi-protocol data processing method provided by the embodiment of the application.
[0017] Figure 2 is a flowchart of the training process of the identification model provided by the embodiment of the application.
[0018] Figure 3 is a structural schematic diagram of the multi-protocol data processing device provided by the embodiment of the application.
[0019] Figure 4 is a structural schematic diagram of the electronic equipment provided by the embodiment of the application. DETAILED DESCRIPTION
[0020] In order to make the purpose, technical solutions and advantages of the application clearer, the technical solutions in the application will be described clearly and completely in combination with the drawings in the application. Obviously, the described embodiments are some embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor belong to the protection scope of the application.
[0021] Figure 1 is a flowchart of the multi-protocol data processing method provided by the embodiment of the application. As Figure 1As shown, a multi-protocol data processing method is provided, comprising the following steps: steps 110-140. The method flow steps are only as a possible implementation of the present application.
[0022] Step 110, based on the protocol configuration information, loading a plurality of protocol plug-ins, based on the plurality of protocol plug-ins, obtaining raw management information from a heterogeneous device; The protocol configuration information is a set of pre-set data used to describe and define the communication protocols and their operating parameters that the system needs to support. The protocol configuration information includes but is not limited to: protocol identifier, plug-in association information, listening / connection parameters, and other information.
[0023] The protocol plug-in is an independent, dynamically loadable software module, each protocol plug-in is responsible for processing a specific communication protocol. Each plug-in encapsulates all technical details such as encoding, decoding, connection management, and session maintenance of the communication protocol. The plug-in follows the unified interface specification defined by the main framework. The main framework can manage all different types of plug-ins in a unified way, realizing the decoupling of the main framework and the specific protocol. The protocol plug-in can be a listening-type plug-in or a polling-type plug-in.
[0024] The heterogeneous device refers to a terminal device that has differences in hardware platform, operating system, communication method, and data format, and the heterogeneous device supports different communication protocols.
[0025] The raw management information is the raw data obtained directly from the heterogeneous device through the protocol plug-in without business logic analysis and standardization processing, and the raw management information at least includes raw alarm information and raw performance information.
[0026] Optionally, the protocol configuration information is parsed to obtain parsed protocol configuration information, and based on the parsed protocol configuration information, a plurality of protocol plug-ins are loaded.
[0027] In some embodiments, based on the protocol configuration information, a plurality of protocol plug-ins are loaded, comprising: Real-time acquisition of user input; Based on the user input, updating the initial protocol configuration information to obtain the protocol configuration information; Based on the protocol configuration information, updating a plurality of initial protocol plug-ins to obtain a plurality of protocol plug-ins, and loading the plurality of protocol plug-ins.
[0028] Optionally, a new protocol plug-in is added, an initial protocol plug-in is updated or removed.
[0029] Step 120, preprocessing the original management information to obtain management information, inputting the management information into a pre-constructed identification model to obtain an abnormality identification result of the management information output by the identification model, the identification model being trained based on sample management information of a sample heterogeneous device and an abnormality identification result label of the sample management information; Optionally, the abnormality identification result includes information such as an abnormality mode, a false alarm frequency, and an abnormality score.
[0030] In some embodiments, preprocessing the original management information to obtain the management information includes: parsing the original management information to obtain parsed original management information; performing data cleaning, standardization, and alignment processing on the parsed original management information to obtain the management information.
[0031] Optionally, information from different data sources but describing the same event or entity is associated.
[0032] In some embodiments, the management information includes alarm information and performance information, and the identification model includes a feature extraction layer, a feature fusion layer, and an identification layer; the feature extraction layer is configured to perform feature extraction on the management information to obtain an alarm feature vector and a performance feature vector; the feature fusion layer is configured to fuse the alarm feature vector and the performance feature vector to obtain a fusion feature vector; and the identification layer is configured to perform abnormality identification on the fusion feature vector to output the abnormality identification result.
[0033] The alarm information is discrete events generated by a system, such as error reports, warnings, and the like. The performance information is continuous system index data, such as CPU usage, memory occupation, network delay, and the like.
[0034] Optionally, the feature fusion layer is configured to associate the alarm feature vector and the performance feature vector to determine an association relationship of the alarm feature vector and the performance feature vector; and fuse the alarm feature vector and the performance feature vector based on the association relationship of the alarm feature vector and the performance feature vector to obtain the fusion feature vector.
[0035] Step 130, adjusting initial rule configuration information based on the abnormality identification result to generate rule configuration information, and processing the management information based on the rule configuration information to obtain processed management information; Optionally, the initial rule configuration information includes but is not limited to data flow conversion rules, data sampling rules, alarm rules, and data labeling rules.
[0036] Optionally, the abnormality identification result is analyzed to determine a new device normal operation baseline and / or a new abnormality mode, and a target initial rule frequently causing false alarms is determined.
[0037] In some embodiments, the initial rule configuration information is adjusted, including at least one of the following: In the case of identifying a new device normal operation baseline, the relevant threshold parameters in the initial rule configuration information are adjusted; In the case of identifying a new abnormal mode, one or more rules matching the new abnormal mode are added to the initial rule configuration information; In the case of identifying that the target initial rule frequently triggers false positives, the target initial rule is disabled or the priority of the target initial rule is reduced.
[0038] Optionally, the initial rule configuration information includes but is not limited to threshold rules, state machine rules, and fluctuation rules, for example, when the temperature of device A exceeds 80℃ for 5 consecutive minutes, a high temperature alarm is triggered.
[0039] Wherein, the device normal operation baseline refers to the normal data pattern or value range exhibited by the device under certain working conditions or in certain environment. The device normal operation baseline is not fixed and may drift due to factors such as seasonal changes, device aging, process adjustments, etc.
[0040] Wherein, the new abnormal mode refers to a new data behavior pattern that has never occurred in the history of the device and can indicate a potential fault. For example, small amplitude periodic fluctuation of voltage is a new precursor of imminent damage to a certain component.
[0041] Wherein, the processed management information is a structured data object, for example, a JSON object, which clearly defines the operations to be performed inside.
[0042] In some embodiments, the management information is processed to obtain processed management information, including: The management information is filtered to obtain filtered management information; The filtered management information is aggregated to obtain aggregated management information; The aggregated management information is analyzed to obtain processed management information.
[0043] Optionally, the aggregated management information is analyzed to identify hidden linkage relationships between different devices or different indicators. Multiple simple aggregated information is combined to define a complex event with clear business meaning.
[0044] Step 140, based on the communication protocol corresponding to the target device, the processed management information is encapsulated, and the encapsulated management information is sent to the target device.
[0045] Optionally, the target device is an actuator, a controller, or a configurable device.
[0046] The embodiment of the application constructs a complete closed loop from data acquisition, intelligent analysis to automatic control, so that the system can dynamically and accurately adjust the running state of the field device according to the real-time analysis result, and realize truly intelligent operation and management.
[0047] In the embodiment of the application, based on the protocol configuration information, a plurality of protocol plug-ins are loaded, and based on the plurality of protocol plug-ins, original management information from a heterogeneous device is acquired; the original management information is preprocessed to obtain management information, the management information is input into a pre-constructed identification model to obtain an abnormal identification result of the management information output by the identification model; based on the abnormal identification result, initial rule configuration information is adjusted to generate rule configuration information, and based on the rule configuration information, the management information is processed to obtain processed management information; based on a communication protocol corresponding to a target device, the processed management information is encapsulated, and the encapsulated management information is sent to the target device, which is flexible and adaptable and suitable for complex application scenarios that dynamically change.
[0048] Figure 2 A flowchart of a training process of an identification model is provided in the embodiment of the application. In some embodiments, the training process of the identification model includes: Step 210, original sample management information of a sample heterogeneous device is acquired, and the original sample management information is preprocessed to obtain sample management information; Step 220, an abnormal identification result label of the sample management information is determined; Step 230, the sample management information is input into an initial identification model to obtain an abnormal identification prediction result of the sample management information output by the initial identification model; Step 240, based on the abnormal identification prediction result and the abnormal identification result label of the sample management information, a loss function value is calculated, and based on the loss function value, parameters of the initial identification model are iteratively optimized to obtain an identification model.
[0049] Optionally, the original sample management information is preprocessed to obtain the sample management information, including: The original sample management information is parsed to obtain parsed original sample management information; The parsed original sample management information is subjected to data cleaning, standardization and alignment processing to obtain sample management information.
[0050] In some embodiments, the sample management information comprises sample alarm information and sample performance information, the initial identification model comprises an initial feature extraction layer, an initial feature fusion layer and an initial identification layer; the initial feature extraction layer is configured to extract features of the sample management information to obtain a sample alarm feature vector and a sample performance feature vector; the sample feature fusion layer is configured to fuse the sample alarm feature vector and the sample performance feature vector to obtain a sample fusion feature vector; and the sample identification layer is configured to perform abnormal identification on the sample fusion feature vector to output an abnormal identification prediction result.
[0051] The multi-protocol data processing device provided by the embodiments of the present application is described below. The multi-protocol data processing device described below can be referred to in conjunction with the multi-protocol data processing method described above.
[0052] Figure 3 A structural schematic diagram of the multi-protocol data processing device provided by the embodiments of the present application is shown in FIG. 3. The multi-protocol data processing device 300 comprises: Figure 3 An acquisition unit 310 is configured to load a plurality of protocol plug-ins based on protocol configuration information, and acquire original management information from a heterogeneous device based on the plurality of protocol plug-ins. An abnormal identification unit 320 is configured to preprocess the original management information to obtain management information, input the management information into a pre-constructed identification model, and obtain an abnormal identification result of the management information output by the identification model. The identification model is obtained by training based on sample management information of a sample heterogeneous device and an abnormal identification result label of the sample management information. A rule adjustment unit 330 is configured to adjust initial rule configuration information based on the abnormal identification result, generate rule configuration information, and process the management information based on the rule configuration information to obtain processed management information. A sending unit 340 is configured to encapsulate the processed management information based on a communication protocol corresponding to a target device, and send the encapsulated management information to the target device.
[0053] Optionally, the adjustment of the initial rule configuration information comprises at least one of the following: In a case where a new device normal operation baseline is identified, a related threshold parameter in the initial rule configuration information is adjusted. In a case where a new abnormal mode is identified, one or more rules matching the new abnormal mode are added in the initial rule configuration information. In a case where a target initial rule frequently causes false positives, the target initial rule is disabled or the priority of the target initial rule is reduced.
[0054] Optionally, the management information comprises alarm information and performance information, and the identification model comprises a feature extraction layer, a feature fusion layer, and an identification layer; the feature extraction layer is configured to perform feature extraction on the management information to obtain an alarm feature vector and a performance feature vector; the feature fusion layer is configured to fuse the alarm feature vector and the performance feature vector to obtain a fused feature vector; and the identification layer is configured to perform abnormality identification on the fused feature vector to output an abnormality identification result.
[0055] Optionally, the processing of the management information to obtain the processed management information comprises: filtering the management information to obtain filtered management information; aggregating the filtered management information to obtain aggregated management information; performing correlation analysis on the aggregated management information to obtain the processed management information.
[0056] Optionally, the management information is obtained by preprocessing the original management information, and the preprocessing of the original management information comprises: parsing the original management information to obtain parsed original management information; performing data cleaning, standardization, and alignment processing on the parsed original management information to obtain the management information.
[0057] Optionally, the multiple protocol plug-ins are loaded based on the protocol configuration information, and the loading of the multiple protocol plug-ins comprises: acquiring user input in real time; updating the initial protocol configuration information based on the user input to obtain the protocol configuration information; updating the multiple initial protocol plug-ins based on the protocol configuration information to obtain the multiple protocol plug-ins, and loading the multiple protocol plug-ins.
[0058] Optionally, the training process of the identification model comprises: obtaining original sample management information of a sample heterogeneous device, and preprocessing the original sample management information to obtain sample management information; determining an abnormality identification result label of the sample management information; inputting the sample management information into an initial identification model to obtain an abnormality identification prediction result of the sample management information output by the initial identification model; calculating a loss function value based on the abnormality identification prediction result of the sample management information and the abnormality identification result label, and iteratively optimizing parameters of the initial identification model based on the loss function value to obtain the identification model.
[0059] It should be noted that the multi-protocol data processing apparatus provided in this embodiment of the invention can implement all the method steps implemented in the above-described multi-protocol data processing method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.
[0060] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 4 As shown, the electronic device may include: a processor 410, a communications interface 420, a memory 430, and a communication bus 440. The processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a multi-protocol data processing method. This method includes: loading multiple protocol plugins based on protocol configuration information; acquiring raw management information from heterogeneous devices based on the multiple protocol plugins; preprocessing the raw management information to obtain management information; inputting the management information into a pre-built recognition model to obtain anomaly recognition results of the management information output by the recognition model. The recognition model is trained based on sample management information from sample heterogeneous devices and anomaly recognition result labels of the sample management information; adjusting the initial rule configuration information based on the anomaly recognition results to generate rule configuration information; processing the management information based on the rule configuration information to obtain processed management information; encapsulating the processed management information based on the communication protocol corresponding to the target device; and sending the encapsulated management information to the target device.
[0061] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0062] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements a multi-protocol data processing method provided by any of the above methods, the method comprising: loading a plurality of protocol plug-ins based on protocol configuration information, obtaining original management information from a heterogeneous device based on the plurality of protocol plug-ins; preprocessing the original management information to obtain management information, inputting the management information into a pre-constructed identification model to obtain an abnormality identification result of the management information output by the identification model, the identification model being obtained by training based on sample management information of a sample heterogeneous device and an abnormality identification result label of the sample management information; adjusting initial rule configuration information based on the abnormality identification result to generate rule configuration information, processing the management information based on the rule configuration information to obtain processed management information; and encapsulating the processed management information based on a communication protocol corresponding to a target device, and sending the encapsulated management information to the target device.
[0063] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.
[0064] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary universal hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.
[0065] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A multi-protocol data processing method, characterized in that, include: Based on the protocol configuration information, multiple protocol plugins are loaded, and based on the multiple protocol plugins, raw management information from heterogeneous devices is obtained; The original management information is preprocessed to obtain management information. The management information is then input into a pre-built recognition model to obtain the anomaly recognition result of the management information output by the recognition model. The recognition model is trained based on the sample management information of heterogeneous sample devices and the anomaly recognition result label of the sample management information. Based on the anomaly identification results, the initial rule configuration information is adjusted to generate rule configuration information. Based on the rule configuration information, the management information is processed to obtain the processed management information. Based on the communication protocol corresponding to the target device, the processed management information is encapsulated and then sent to the target device.
2. The multi-protocol data processing method according to claim 1, characterized in that, The adjustment of the initial rule configuration information includes at least one of the following: Upon identifying a new baseline for normal device operation, adjust the relevant threshold parameters in the initial rule configuration information; If a new anomaly pattern is identified, one or more rules matching the new anomaly pattern are added to the initial rule configuration information; If the target initial rule is found to frequently cause false alarms, the target initial rule is disabled or its priority is reduced.
3. The multi-protocol data processing method according to claim 1, characterized in that, The management information includes alarm information and performance information. The identification model includes a feature extraction layer, a feature fusion layer, and an identification layer. The feature extraction layer is used to extract features from the management information to obtain alarm feature vectors and performance feature vectors. The feature fusion layer is used to fuse the alarm feature vectors and performance feature vectors to obtain a fused feature vector. The identification layer is used to identify anomalies in the fused feature vector and output the anomaly identification result.
4. The multi-protocol data processing method according to claim 1, characterized in that, The process of processing the management information to obtain processed management information includes: The management information is filtered to obtain filtered management information; The filtered management information is aggregated to obtain aggregated management information; The aggregated management information is subjected to correlation analysis to obtain processed management information.
5. The multi-protocol data processing method according to claim 1, characterized in that, The preprocessing of the original management information to obtain management information includes: The original management information is parsed to obtain the parsed original management information; The parsed original management information is then cleaned, standardized, and aligned to obtain the management information.
6. The multi-protocol data processing method according to claim 1, characterized in that, The loading of multiple protocol plugins based on protocol configuration information includes: Real-time acquisition of user input; Based on the user input, the initial protocol configuration information is updated to obtain the protocol configuration information; Based on the protocol configuration information, multiple initial protocol plugins are updated to obtain multiple protocol plugins, and the multiple protocol plugins are loaded.
7. The multi-protocol data processing method according to claim 1, characterized in that, The training process of the recognition model includes: Obtain the original sample management information of the heterogeneous sample device, and preprocess the original sample management information to obtain sample management information; Determine the anomaly identification result label of the sample management information; The sample management information is input into the initial identification model to obtain the anomaly identification prediction result of the sample management information output by the initial identification model; Based on the anomaly detection prediction results and anomaly detection result labels of the sample management information, a loss function value is calculated. Based on the loss function value, the parameters of the initial detection model are iteratively optimized to obtain the detection model.
8. A multi-protocol data processing apparatus, characterized in that, include: The acquisition unit is used to load multiple protocol plugins based on protocol configuration information, and acquire raw management information from heterogeneous devices based on the multiple protocol plugins; An anomaly identification unit is used to preprocess the original management information to obtain management information, input the management information into a pre-built identification model, and obtain the anomaly identification result of the management information output by the identification model. The identification model is trained based on the sample management information of sample heterogeneous devices and the anomaly identification result label of the sample management information. The rule adjustment unit is used to adjust the initial rule configuration information based on the anomaly identification result, generate rule configuration information, and process the management information based on the rule configuration information to obtain the processed management information. The sending unit is used to encapsulate the processed management information based on the communication protocol corresponding to the target device, and send the encapsulated management information to the target device.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the multi-protocol data processing method as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the multi-protocol data processing method as described in any one of claims 1 to 7.