A method, system and storage medium for adaptive recognition of multi-source heterogeneous data collection

By monitoring and analyzing the real-time status of the front-end module, generating configuration status information and adjusting parameters, the manual management problem in the existing technology is solved, automated adaptive recognition is realized, efficiency and availability is improved, and the differences in data type changes are solved. .

CN114358079BActive Publication Date: 2024-11-26硕橙(厦门)科技有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111682318.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-29
Publication Date
2024-11-26
Estimated Expiration
2041-12-29

AI Technical Summary

Technical Problem

The prior art requires manual replacement of equipment or software firmware when the data type is collected at the front end, making it difficult to achieve automated and active operation and maintenance and cannot meet management needs.

Method used

By monitoring the real-time status of the front-end module, generating configuration status information, adjusting configuration parameters, and realizing adaptive identification, including low-pass filtering, comparison, low-pass rectification filtering and high-pass rectification filtering to obtain signal components, combining analysis to generate configuration status information, and Initialize the configuration when the sensor is not connected.

Benefits of technology

It realizes automatic adaptive identification based on the different data types collected by the front-end, which improves efficiency, saves costs, enhances the availability of the system, and avoids the different problems caused by different data types.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114358079B_ABST
    Figure CN114358079B_ABST
Patent Text Reader

Abstract

The present invention relates to a method, system and storage medium for adaptive recognition of multi-source heterogeneous data collection. The method comprises: monitoring the real-time status of a front-end module; generating configuration status information according to the real-time status of the front-end module; adjusting configuration parameters according to the configuration status information; and configuring corresponding modes according to the configuration parameters. The present invention realizes adaptive recognition according to different types of front-end acquisition data, greatly improving efficiency and saving costs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of heterogeneous data recognition, and in particular to a multi-source heterogeneous data acquisition adaptive recognition method, system and storage medium. Background Art

[0002] With the advancement of information construction, the types and quantity of equipment are increasing, and the management difficulty is increasing. In the existing technology, when the data type collected by the front end changes, it is necessary to manually replace different equipment or flash different software system firmware on the front-end device. This traditional manual management mode is difficult to meet the requirements of the security task, so there is an urgent need to realize automated active operation and maintenance capabilities. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a method, system and storage medium for adaptive recognition of multi-source heterogeneous data collection, which can automatically adapt to the recognition according to the different types of data collected by the front end.

[0004] The technical solution adopted by the present invention to solve the technical problem is: to provide a multi-source heterogeneous data collection and adaptive recognition method, comprising the following steps:

[0005] Monitor the real-time status of the front-end module;

[0006] generating configuration status information according to the real-time status of the front-end module;

[0007] adjusting configuration parameters according to the configuration status information;

[0008] The corresponding mode is configured according to the configuration parameters.

[0009] The real-time status of the monitoring front-end module is specifically: obtaining the DC component signal of the output signal of the front-end module by low-pass filtering; obtaining the open circuit state signal or the short circuit state signal of the front-end module by comparison; obtaining the characteristic signal of the low-frequency signal component of the output signal of the front-end module by low-pass rectification and filtering; obtaining the characteristic signal of the high-frequency signal component of the output signal of the front-end module by high-pass rectification and filtering.

[0010] The method of generating configuration status information according to the real-time status of the front-end module is specifically as follows: combining and analyzing part or all of the DC component signal, the open circuit status signal or the short circuit status signal, the characteristic signal of the low-frequency signal component and the characteristic signal of the high-frequency signal component of the output signal of the front-end module, and generating the configuration status information based on the analysis result.

[0011] Before monitoring the real-time status of the front-end module, the method further includes: detecting whether a sensor of the front-end module is connected, and if not connected, initializing the configuration through built-in data.

[0012] The technical solution adopted by the present invention to solve the technical problem is: a multi-source heterogeneous data acquisition adaptive recognition system is also provided, comprising:

[0013] Sampling module, used to monitor the real-time status of the front-end module;

[0014] A configuration status information generating module, used to generate configuration status information according to the real-time status of the front-end module;

[0015] A calculation module, used for adjusting configuration parameters according to the configuration status information;

[0016] An input module is used to configure a corresponding mode according to the configuration parameters.

[0017] The sampling module includes: a low-pass filtering circuit, used to obtain the DC component signal of the output signal of the front-end module; a comparison circuit, used to obtain the open circuit state signal or the short circuit state signal of the front-end module; a low-pass rectifying and filtering circuit, used to obtain the characteristic signal of the low-frequency signal component of the output signal of the front-end module; and a high-pass rectifying and filtering circuit, used to obtain the characteristic signal of the high-frequency signal component of the output signal of the front-end module.

[0018] The configuration status information generation module includes: an analysis unit, which is used to combine and analyze part or all of the DC component signal, the open circuit state signal or the short circuit state signal, the characteristic signal of the low-frequency signal component and the characteristic signal of the high-frequency signal component of the output signal of the front-end module; and a generation unit, which is used to generate configuration status information based on the analysis result of the analysis unit.

[0019] The multi-source heterogeneous data acquisition and adaptive recognition system further includes: a detection module for detecting whether the sensor of the front-end module is connected; and a pre-configuration module for initializing the configuration through built-in data when the sensor is not connected.

[0020] The technical solution adopted by the present invention to solve its technical problem is: a computer-readable storage medium is also provided, on which a computer program is stored, and the program is executed by a processor to implement the above-mentioned multi-source heterogeneous data acquisition adaptive recognition method.

[0021] Beneficial Effects

[0022] Due to the adoption of the above-mentioned technical scheme, the present invention has the following advantages and positive effects compared with the prior art: the present invention monitors the status of the front-end module in real time through the sampling module, and continuously transmits the information to the calculation module. The calculation module adaptively adjusts the parameters of the input module according to the information obtained by the sampling module to meet the changes in the data type of the front-end module, thereby realizing adaptive recognition according to the different types of data collected by the front-end, greatly improving efficiency and saving costs, and enhancing the availability of the system, avoiding the difference problems caused by different data types, and can well solve the problem that traditional solutions cannot work under specific environments or requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a first embodiment of the present invention;

[0024] Figure 2 is a flow chart of an embodiment of the present invention;

[0025] Figure 3 is a block diagram of a second embodiment of the present invention;

[0026] Figure 4 is a circuit diagram of a sampling module in a second embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0028] The embodiment of the present invention relates to a multi-source heterogeneous data collection and adaptive recognition method, such as Figure 1 As shown, the following steps are included:

[0029] Step 1, monitor the real-time status of the front-end module. Specifically, in this embodiment, the DC component signal of the output signal of the front-end module is obtained by low-pass filtering; the open circuit state signal or short circuit state signal of the front-end module is obtained by comparison; the characteristic signal of the low-frequency signal component of the output signal of the front-end module is obtained by low-pass rectification and filtering; and the characteristic signal of the high-frequency signal component of the output signal of the front-end module is obtained by high-pass rectification and filtering. In the above manner, the basic status of the front-end module can be effectively obtained.

[0030] Step 2, generating configuration status information according to the real-time status of the front-end module. Specifically, this embodiment combines and analyzes part or all of the DC component signal, open circuit state signal or short circuit state signal, characteristic signal of low-frequency signal component and characteristic signal of high-frequency signal component of the output signal of the front-end module, and generates configuration status information based on the analysis result. The specific combination analysis can be implemented by a classification model, which can be based on a neural network, whose input is the DC component signal, open circuit state signal or short circuit state signal, characteristic signal of low-frequency signal component and characteristic signal of high-frequency signal component of the output signal of the front-end module, and output is the sensor type of the front-end module. The classification model can be used to identify the sensor type of the front-end module, so as to configure the status information according to the identification result.

[0031] Step 3, adjust the configuration parameters according to the configuration status information; specifically, this embodiment realizes parameter adjustment by setting a mapping table, and the mapping table stores different parameters corresponding to different status information. When the configuration status information is determined, the corresponding parameters can be found from the mapping table, so as to obtain the corresponding new parameters when the type of signal collected by the front-end module changes.

[0032] Step 4, configuring the corresponding mode according to the configuration parameters, that is, configuring the mode according to the obtained parameters, thereby completing the adaptive adjustment, avoiding the problem in the prior art that the front-end module type changes and cannot work without human intervention.

[0033] Before step 1 in this embodiment, it is also possible to detect whether the front-end module is connected. If not, initial configuration can be performed through built-in data, thereby realizing the pre-configuration function.

[0034] The present invention is further illustrated by a specific embodiment below.

[0035] like Figure 2As shown, in this embodiment, when a front-end module is connected, first detect whether the sensor of the front-end module is connected. If not, load the default circuit configuration according to the information stored in the built-in memory to complete the initialization configuration. If connected, the basic state of the front-end module is sensed and measured, and configuration status information is generated according to the measurement results; the configuration status information can be sent to the computing module through the interface. After the computing module detects the connection of the front-end module and reads the configuration status information of the front-end module, the input module is enabled and the corresponding configuration parameters are generated according to the configuration status information. The configuration parameters are sent to the input module to complete the corresponding parameter configuration. During the operation of the system, the state of the front-end module will be monitored in real time, and the configuration status information will be continuously transmitted to the computing module. When the configuration status information changes, the computing module can generate the corresponding configuration parameters according to the changed configuration status information, thereby realizing adaptive adjustment of the configuration parameters.

[0036] The embodiment of the present invention relates to a multi-source heterogeneous data acquisition adaptive recognition system, such as Figure 3 As shown, including:

[0037] Sampling module, used to monitor the real-time status of the front-end module;

[0038] A configuration status information generating module, used to generate configuration status information according to the real-time status of the front-end module;

[0039] A calculation module, used for adjusting configuration parameters according to the configuration status information;

[0040] An input module is used to configure a corresponding mode according to the configuration parameters.

[0041] like Figure 4 As shown, the sampling module includes: a low-pass filtering circuit, used to obtain the DC component signal of the output signal of the front-end module; a comparison circuit, used to obtain the open circuit state signal or the short circuit state signal of the front-end module; a low-pass rectifying and filtering circuit, used to obtain the characteristic signal of the low-frequency signal component of the output signal of the front-end module; and a high-pass rectifying and filtering circuit, used to obtain the characteristic signal of the high-frequency signal component of the output signal of the front-end module.

[0042] Among them, OP1 is a low-pass filter chip circuit, and the signal of the front-end module outputs a DC component signal after passing through OP1. OP2 is a comparator chip circuit. The signal of the front-end module is compared with several groups of voltage thresholds through the comparator formed by OP2, and outputs signals representing short circuit, open circuit and other states. OP3 and OP4 are low-pass rectifier filter chip circuits and high-pass rectifier filter chip circuits respectively. The signal of the front-end module outputs characteristic signals representing the low-frequency signal component and high-frequency signal component of the input signal after passing through OP3 and OP4.

[0043] The configuration status information generation module includes: an analysis unit, which is used to combine and analyze part or all of the DC component signal, the open circuit state signal or the short circuit state signal, the characteristic signal of the low-frequency signal component and the characteristic signal of the high-frequency signal component of the output signal of the front-end module; and a generation unit, which is used to generate configuration status information based on the analysis result of the analysis unit.

[0044] The multi-source heterogeneous data acquisition and adaptive recognition system further includes: a detection module for detecting whether the sensor of the front-end module is connected; and a pre-configuration module for initializing the configuration through built-in data when the sensor is not connected.

[0045] It should be noted that the multi-source heterogeneous data acquisition adaptive recognition system / method of the above embodiments of the present invention can be implemented by computer program instructions, for example, by a dedicated program, and these computer program instructions can be provided to a general-purpose computer, a special-purpose computer or a processor of other programmable data processing devices to constitute the multi-source heterogeneous data acquisition adaptive system of the embodiments of the present invention, and these instructions can be executed by the processor of the computer or other programmable data processing device to create units or components for implementing the functions / operations specified in these flowcharts and / or boxes and / or one or more flowcharts.

[0046] Furthermore, these computer program instructions can be stored in a computer-readable memory, which can instruct a computer or other programmable processor to implement functions in a specific manner, so that these instructions stored in the computer-readable memory constitute a manufactured product containing instruction components that implement the functions / operations specified in one or more boxes of the flowchart and / or block diagram.

[0047] It should also be noted that in some alternative implementations, the functions / operations shown in the blocks may not occur in the order shown in the flow chart. For example, two blocks shown in sequence may actually be performed substantially simultaneously or these blocks may sometimes be performed in reverse order, depending on the functions / operations involved.

[0048] It should be noted that the elements disclosed and depicted herein (including the flowcharts and block diagrams in the accompanying drawings) refer to the logical boundaries between the elements. However, according to software or hardware engineering practice, the depicted elements and their functions can be executed on a machine through a computer executable medium, and the computer executable medium has a processor capable of executing program instructions stored thereon, and the program instructions are as a single-chip software structure, as an independent software module, or as a module using external programs, codes, services, etc., or any combination of these, and all of these execution schemes may fall within the scope of the present disclosure.

[0049] Although different non-limiting embodiments have specifically described components, embodiments of the invention are not limited to these specific combinations. It is possible to use some of the components or features from any non-limiting embodiment in combination with features or components from any other non-limiting embodiment.

Claims

1. A method for adaptive recognition of multi-source heterogeneous data collection, characterized in that: The following steps are involved: Monitoring the real-time status of the front-end module, wherein the real-time status includes: a DC component signal of the front-end module output signal, an open circuit state signal or a short circuit state signal of the front-end module, a characteristic signal of a low-frequency signal component of the front-end module output signal, and a characteristic signal of a high-frequency signal component of the front-end module output signal; Generate configuration status information according to the real-time status of the front-end module, specifically: Performing combined analysis on the DC component signal, the open circuit state signal or the short circuit state signal, the characteristic signal of the low-frequency signal component, and the characteristic signal of the high-frequency signal component of the output signal of the front-end module, and generating configuration status information based on the analysis result; wherein the combined analysis is implemented by a classification model, and the classification model is based on a neural network, and its input is the DC component signal, the open circuit state signal or the short circuit state signal, the characteristic signal of the low-frequency signal component, and the characteristic signal of the high-frequency signal component of the output signal of the front-end module, and its output is the sensor type of the front-end module; adjusting configuration parameters according to the configuration status information; The corresponding mode is configured according to the configuration parameters.

2. The multi-source heterogeneous data acquisition adaptive recognition method according to claim 1 is characterized in that: The real-time status of the monitoring front-end module is specifically: obtaining the DC component signal of the output signal of the front-end module by low-pass filtering; obtaining the open circuit state signal or the short circuit state signal of the front-end module by comparison; obtaining the characteristic signal of the low-frequency signal component of the output signal of the front-end module by low-pass rectification and filtering; obtaining the characteristic signal of the high-frequency signal component of the output signal of the front-end module by high-pass rectification and filtering.

3. The multi-source heterogeneous data acquisition adaptive recognition method according to claim 1 is characterized in that: Before monitoring the real-time status of the front-end module, the method further includes: detecting whether a sensor of the front-end module is connected, and if not connected, initializing the configuration through built-in data.

4. A multi-source heterogeneous data acquisition adaptive recognition system, characterized in that: include: A sampling module, used to monitor the real-time status of the front-end module, wherein the real-time status includes: a DC component signal of the front-end module output signal, an open circuit state signal or a short circuit state signal of the front-end module, a characteristic signal of a low-frequency signal component of the front-end module output signal, and a characteristic signal of a high-frequency signal component of the front-end module output signal; A configuration status information generation module, used to generate configuration status information according to the real-time status of the front-end module; the configuration status information generation module includes: an analysis unit, used to perform combined analysis on the DC component signal, the open circuit state signal or the short circuit state signal, the characteristic signal of the low-frequency signal component and the characteristic signal of the high-frequency signal component of the output signal of the front-end module, wherein the combined analysis is implemented by a classification model, the classification model is based on a neural network, and its input is the DC component signal, the open circuit state signal or the short circuit state signal, the characteristic signal of the low-frequency signal component and the characteristic signal of the high-frequency signal component of the output signal of the front-end module, and its output is the sensor type of the front-end module; a generation unit, used to generate configuration status information based on the analysis result of the analysis unit; A calculation module, used for adjusting configuration parameters according to the configuration status information; An input module is used to configure a corresponding mode according to the configuration parameters.

5. The multi-source heterogeneous data acquisition adaptive recognition system according to claim 4 is characterized in that: The sampling module includes: a low-pass filtering circuit, used to obtain the DC component signal of the output signal of the front-end module; a comparison circuit, used to obtain the open circuit state signal or the short circuit state signal of the front-end module; a low-pass rectifying and filtering circuit, used to obtain the characteristic signal of the low-frequency signal component of the output signal of the front-end module; and a high-pass rectifying and filtering circuit, used to obtain the characteristic signal of the high-frequency signal component of the output signal of the front-end module.

6. The multi-source heterogeneous data acquisition adaptive recognition system according to claim 4 is characterized in that: Also includes: The detection module is used to detect whether the sensor of the front-end module is connected; the pre-configuration module is used to initialize the configuration through the built-in data when it is not connected.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the multi-source heterogeneous data acquisition adaptive recognition method as described in any one of claims 1-3.