Text data and picture data fusion method and system based on power production
By classifying response levels and setting fault tolerance for text and image data from power production, and optimizing data fusion, the problem of excessive data fusion resource consumption in power production was solved, enabling efficient and accurate emergency response and fault prediction, and improving power production efficiency.
Patent Information
- Application Number
- CN202510940847.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-08
- Publication Date
- 2025-11-21
AI Technical Summary
In current technologies, single text or image data is insufficient to accurately reflect problems in power production. This leads to excessive resource consumption in improving the accuracy of data fusion in the power production process, affecting real-time power production data fusion for emergency response and reducing production efficiency.
By employing feature extraction and deep learning models, text and image data related to power production are categorized into critical, emergency, and general response data according to their response levels. Fault tolerance is set and the data is fused to optimize the data fusion method, reduce the error rate, and improve the accuracy of emergency response.
In resource-constrained power systems, ensuring timely processing of emergency response data reduces data fusion error rates, improves power production efficiency, predicts potential faults, and enhances system safety and stability.
Smart Images
Figure CN120995373A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of power production data fusion, and particularly relates to a text data and picture data fusion method and system based on power production. BACKGROUND
[0002] Since single power production text data or picture data is sometimes difficult to accurately reflect problems in the power production process, power production text data and picture data are usually fused. The higher the accuracy of the fusion of power production text data and picture data, the more accurately the problems in the power production process can be reflected, so as to make a corresponding response to the problems in the power production process in a timely manner. In the prior art, the accuracy of the fusion of all power production text data and picture data is generally improved. However, the data volume of power production text data and picture data is huge. If the accuracy of the fusion of all power production text data and picture data is comprehensively improved, too much power system resources will be occupied, thereby negatively affecting the accuracy of real-time power production data fusion that needs to be urgently responded, and it is difficult to respond to real-time power production data that needs to be urgently responded, and the efficiency of power production is reduced. SUMMARY
[0003] The present application provides a text data and picture data fusion method and system based on power production, which optimizes the prior art.
[0004] In a first aspect, an embodiment of the present application provides a text data and picture data fusion method and system based on power production, which can include the following steps:
[0005] A feature extraction model is used to extract data features of real-time power production text data and data features of power production picture data;
[0006] According to the extracted data features of real-time power production text data and data features of power production picture data, a deep learning model is used to divide real-time power production text data and power production picture data into critical response data, emergency response data and general response data in order from high to low according to response levels;
[0007] The fault tolerance of the fusion of real-time power production text data and power production picture data is set according to the high and low of the response levels of real-time power production text data and power production picture data;
[0008] According to the fault tolerance of the fusion of the real-time power generation text data and the power generation picture data, a real-time fusion mode between the real-time power generation text data and the power generation picture data is set, and the real-time power generation text data and the power generation picture data are fused according to the real-time fusion mode.
[0009] In the above technical solution, since the power generation data has the characteristics of large data volume, high data rate and strong real-time data, the data fusion of the power generation data is prone to errors, and the response requirement of the power generation data is very high, and the tolerance of the data fusion error is very low, so that the higher the response level of the real-time power generation text data and the power generation picture data, the lower the fusion fault tolerance of the real-time data, and the fusion of the real-time power generation data cannot be error-free. The real-time fusion of the real-time power generation text data and the power generation picture data effectively reduces the occupation of the power system resources by the real-time power generation text data and the power generation picture data, ensures the high accuracy of the real-time power generation data fusion for emergency response, improves the efficiency of power generation, especially in the application scenario of limited power system resources, so that the real-time power generation text data and the power generation picture data can be responded in time, and the production efficiency of power generation will not be adversely affected.
[0010] In a preferred example, the first aspect of the application can be further configured as:
[0011] The power generation text data and picture data fusion method can further include the following steps:
[0012] The data characteristics of the real-time power generation text data and the power generation picture data are used to predict potential faults of power equipment.
[0013] Through the above technical solution, the level of safe and stable operation of the power system is improved, and the production efficiency of the power system is further improved.
[0014] In a preferred example, the first aspect of the application can be further configured as:
[0015] The step of predicting potential faults of power equipment by using the data characteristics of the real-time power generation text data and the power generation picture data can include the following steps:
[0016] The data characteristics of the real-time power generation text data and the power generation picture data of each power generation equipment are collected into the same data characteristic set, and a number is set for each data characteristic set of the power generation equipment;
[0017] presetting device text fault data features of data features of real-time text data of real-time power generation of the power generation device and device picture fault data features of data features of power generation picture data;
[0018] when the data features of the real-time text data of real-time power generation of the power generation device are similar to the features of the device text fault data features with a similarity greater than a preset data feature similarity, or the data features of the picture data of the real-time power generation of the power generation device are greater than a preset picture feature similarity, obtaining the number of a data feature set to which the data features of the real-time text data or the data features of the picture data belong, and predicting the power device corresponding to the data feature set of the number as having a potential fault.
[0019] Through the above technical solution, the potential fault of the power device can be efficiently and accurately predicted.
[0020] The first aspect of the application can be further configured in a preferred example as follows:
[0021] In the step of setting the real-time fusion mode between the real-time text data of real-time power generation and the picture data of power generation according to the fault tolerance of the real-time text data of real-time power generation and the picture data of power generation, the setting method of the real-time fusion mode between the real-time text data of real-time power generation and the picture data of power generation includes the following expression:
[0022]
[0023] wherein D represents the real-time fusion data between the real-time text data of real-time power generation and the picture data of power generation, W n represents the data features of the nth real-time power generation text data, 1≤n≤N, n is a positive integer, N represents the total number of data features of real-time power generation text data, P m represents the data features of the mth real-time power generation picture data, m is a positive integer, 1≤m≤M, M represents the total number of data features of real-time power generation picture data, R represents the fault tolerance of the fusion of the nth real-time power generation text data and the picture data of power generation.
[0024] Through the above technical solution, the setting efficiency of the real-time fusion mode between the real-time text data of real-time power generation and the picture data of power generation is improved.
[0025] The first aspect of the application can be further configured in a preferred example as follows:
[0026] The power production-based text data and picture data fusion method can further include the following steps:
[0027] The real-time fusion data obtained by fusing the real-time power production text data and the power production picture data in real time is used to train the deep learning model.
[0028] In the above technical solution, the deep learning model is trained by the real-time fusion data, which effectively improves the accuracy of the deep learning model in dividing the response level.
[0029] The first aspect of the application can be further configured in a preferred example as follows:
[0030] The power production-based text data and picture data fusion method can further include:
[0031] When the feature matching degree between the data features of the real-time power production text data and the data features of the power production picture data exceeds the preset matching degree, the real-time fusion of the real-time power production text data and the power production picture data is performed.
[0032] In the above technical solution, the real-time fusion of the real-time power production text data and the power production picture data is only performed when the feature matching degree between the data features of the real-time power production text data and the data features of the power production picture data exceeds the preset matching degree, thereby further reducing the error rate of the real-time fusion of the real-time power production text data and the power production picture data.
[0033] Secondly, an embodiment of the application provides a power production-based text data and picture data fusion system, which can include:
[0034] The data feature extraction module is configured to extract the data features of the real-time power production text data and the data features of the power production picture data using a feature extraction model.
[0035] The response level division module is configured to divide the real-time power production text data and the power production picture data into critical response data, emergency response data, and general response data according to the extracted data features of the real-time power production text data and the data features of the power production picture data using a deep learning model.
[0036] The fault tolerance degree setting module is configured to set the fault tolerance degree of the fusion of the real-time power production text data and the power production picture data according to the high and low of the response level of the real-time power production text data and the power production picture data.
[0037] The data fusion module is configured to set a real-time fusion mode between the real-time power generation text data and the power generation picture data according to a fault tolerance of fusion of the real-time power generation text data and the power generation picture data, and fuse the real-time power generation text data and the power generation picture data according to the real-time fusion mode.
[0038] The second aspect of the application can be further configured as follows in a preferred example:
[0039] The power generation text data and picture data fusion system can further include:
[0040] The potential fault prediction module is configured to predict a potential fault of the power equipment by using data features of the real-time power generation text data and data features of the power generation picture data.
[0041] The second aspect of the application can be further configured as follows in a preferred example:
[0042] The power generation text data and picture data fusion system can further include:
[0043] The deep learning model module is configured to train the deep learning model by using real-time fusion data obtained by real-time fusion of the real-time power generation text data and the power generation picture data.
[0044] The second aspect of the application can be further configured as follows in a preferred example:
[0045] The power generation text data and picture data fusion system can further include:
[0046] The feature matching module is configured to fuse the real-time power generation text data and the power generation picture data in real time when a feature matching degree between data features of the real-time power generation text data and data features of the power generation picture data exceeds a preset matching degree.
[0047] On the basis of the above-mentioned method embodiment, the application correspondingly provides a terminal embodiment;
[0048] The application provides a terminal, which comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor executes the computer program to implement the power generation text data and picture data fusion method according to any one of the embodiments of the application.
[0049] On the basis of the above-mentioned method embodiment, the application correspondingly provides a storage medium embodiment;
[0050] The application provides a storage medium, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the method for fusing text data and picture data based on power production according to any one of the embodiments of the application.
[0051] The application has at least the following beneficial effects:
[0052] The method for fusing text data and picture data based on power production provided by the application effectively reduces the error rate of data fusion between real-time power production text data and power production picture data, and the accuracy of power production data is very high. In an application scenario where the resources of the power system are limited, the real-time power production text data and the power production picture data can be responded in time, and the generation efficiency of the power system is effectively improved. BRIEF DESCRIPTION OF DRAWINGS
[0053] Figure 1 is a fusion method flowchart of text data and picture data based on power production according to an embodiment of the application.
[0054] Figure 2 is a structural block diagram of a fusion system of text data and picture data based on power production according to an embodiment of the application. DETAILED DESCRIPTION
[0055] The technical solutions in the application will be described in detail below with reference to the drawings in the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the protection scope of the application.
[0056] As shown in Figure 1 An embodiment of the application provides a method for fusing text data and picture data based on power production, which can specifically include the following steps:
[0057] Step S1, a feature extraction model is used to extract data features of real-time power production text data and data features of power production picture data;
[0058] Step S2, according to the extracted data features of real-time power production text data and data features of power production picture data, a deep learning model is used to divide real-time power production text data and power production picture data into critical response data, emergency response data and general response data in order from high to low according to response levels;
[0059] Step S3, set the fault tolerance degree of the real-time power production text data and the power production picture data according to the response level of the real-time power production text data and the power production picture data;
[0060] Step S4, set the real-time fusion mode between the real-time power production text data and the power production picture data according to the fault tolerance degree of the real-time power production text data and the power production picture data, and the real-time power production text data and the power production picture data are fused according to the real-time fusion mode.
[0061] In the fusion method of the power production text data and the picture data in the embodiment, since the power production data has the characteristics of large data volume, high data rate and strong real-time data, the data fusion of the power production data is prone to error, and the power production data with high response requirement has very low tolerance to data fusion error, so that the higher the response level of the real-time power production text data and the power production picture data, the lower the real-time data fusion fault tolerance, and the more the real-time power production data fusion cannot be error; the above technical solution fuses the real-time power production text data and the power production picture data in real time, effectively reduces the occupation of the power system resources by the real-time power production text data and the power production picture data, ensures the high accuracy of the real-time power production data fusion for emergency response, improves the efficiency of power generation, especially in the application scene of limited power system resources, so that the real-time power production text data and the power production picture data can be responded in time, and the production efficiency of power production will not be affected.
[0062] In a preferred embodiment, in order to improve the level of safe and stable operation of the power system and further improve the production efficiency of the power system, the fusion method of the power production text data and the picture data can further include the following steps:
[0063] Predict potential faults of power equipment through the data characteristics of the real-time power production text data and the data characteristics of the power production picture data.
[0064] In a preferred embodiment, in order to efficiently and accurately predict potential faults of power equipment, the step of predicting potential faults of power equipment through the data characteristics of the real-time power production text data and the data characteristics of the power production picture data can include the following steps:
[0065] The data features of the real-time text data of the real-time power production of each power production device and the data features of the picture data of the power production are classified into the same data feature set, and a number is set for each data feature set of the power production device;
[0066] The device text fault data features of the data features of the real-time text data of the real-time power production of the power production device and the device picture fault data features of the data features of the picture data of the power production are preset;
[0067] When the data features of the real-time text data of the real-time power production of the power production device are similar to the features of the device text fault data features with a similarity greater than a preset data feature similarity, or the data features of the picture data of the real-time power production of the power production device are greater than a preset picture feature similarity, the number of the data feature set to which the data features of the real-time text data or the data features of the picture data belong is obtained, and the power device corresponding to the data feature set with the number is predicted to have a potential fault.
[0068] In a preferred embodiment, in order to improve the setting efficiency of the real-time fusion mode between the text data of the real-time power production and the picture data of the power production, in the step of fusing the text data of the real-time power production and the picture data of the power production according to the fault tolerance, the setting method of the real-time fusion mode between the text data of the real-time power production and the picture data of the power production includes the following expression:
[0069]
[0070] Wherein, D represents the real-time fusion data between the text data of the real-time power production and the picture data of the power production, W n represents the data features of the n-th real-time power production text data, 1≤n≤N, n is a positive integer, N represents the total number of data features of the real-time power production text data, P m represents the data features of the m-th real-time power production picture data, m is a positive integer, 1≤m≤M, M represents the total number of data features of the real-time power production picture data, R represents the fault tolerance of the n-th real-time power production text data and the picture data of the power production.
[0071] In a preferred embodiment, in order to train the deep learning model by real-time fusion data, effectively improve the accuracy of the deep learning model in dividing the response level, the power production based text data and picture data fusion method can further include the following steps:
[0072] The real-time fusion data obtained by real-time fusion of the real-time power production text data and the power production picture data is used to train the deep learning model.
[0073] In a preferred embodiment, in order to realize real-time fusion of real-time power production text data and power production picture data only when the feature matching degree between the data features of the real-time power production text data and the data features of the power production picture data exceeds the preset matching degree, thereby further reducing the error rate of real-time fusion of real-time power production text data and power production picture data, the power production based text data and picture data fusion method can further include:
[0074] When the feature matching degree between the data features of the real-time power production text data and the data features of the power production picture data exceeds the preset matching degree, the real-time power production text data and the power production picture data are fused.
[0075] As shown in Figure 2 An embodiment of the present application provides a power production based text data and picture data fusion system, which can specifically include:
[0076] A data feature extraction module is configured to extract data features of real-time power production text data and data features of power production picture data by using a feature extraction model.
[0077] A response level division module is configured to divide real-time power production text data and power production picture data into critical response data, emergency response data and general response data in order from high to low according to the extracted data features of the real-time power production text data and the data features of the power production picture data by using a deep learning model.
[0078] A fault tolerance degree setting module is configured to set a fault tolerance degree of fusion of real-time power production text data and power production picture data according to the high and low of the response level of the real-time power production text data and the power production picture data.
[0079] The data fusion module is configured to set a real-time fusion mode between the real-time power generation text data and the power generation picture data according to a fault tolerance of fusion of the real-time power generation text data and the power generation picture data, and fuse the real-time power generation text data and the power generation picture data according to the real-time fusion mode.
[0080] In a preferred embodiment, the power generation text data and picture data fusion system further comprises:
[0081] The potential fault prediction module is configured to predict a potential fault of the power equipment by using data features of the real-time power generation text data and data features of the power generation picture data.
[0082] In a preferred embodiment, the power generation text data and picture data fusion system further comprises:
[0083] The deep learning model module is configured to train the deep learning model by using real-time fusion data obtained by real-time fusion of the real-time power generation text data and the power generation picture data.
[0084] In a preferred embodiment, the power generation text data and picture data fusion system further comprises:
[0085] The feature matching module is configured to fuse the real-time power generation text data and the power generation picture data when a feature matching degree between data features of the real-time power generation text data and data features of the power generation picture data exceeds a preset matching degree.
[0086] It should be noted that the above-described system embodiments are only illustrative, and the modules described above as separate components can or can not be physically separated, and the components shown as modules can or can not be physical modules, 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 according to actual needs. In addition, the connection relationship between the modules in the system embodiments provided in the present application indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor. The above schematic diagram is only an example of a power generation text data and picture data fusion system and does not constitute a limitation on a power generation text data and picture data fusion system, which can include more or fewer components than the diagram, or combine certain components, or different components.
[0087] Based on the above method embodiment, the application provides a terminal embodiment.
[0088] Another embodiment of the application provides a terminal, which comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor executes the computer program to implement the power production-based text data and picture data fusion method according to any one of the embodiments of the application.
[0089] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the device.
[0090] The terminal can be a desktop computer, a notebook computer, a palm computer, a cloud server, and other computing devices. The device can include, but is not limited to, a processor and a memory.
[0091] The processor can be a central processing module (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the device, which connects all parts of the device through various interfaces and lines.
[0092] The memory can be used to store the computer program and / or the modules, and the processor can realize various functions of the device by running or executing the computer program and / or the modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function, and the like; in addition, the memory can include a high-speed random access memory, and can also include a nonvolatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.
[0093] On the basis of the method embodiment, the application provides a storage medium embodiment.
[0094] Another embodiment of the application provides a storage medium, which comprises a stored computer program, wherein the computer program controls a device where the storage medium is located to perform the power production-based text data and picture data fusion method according to any one of the embodiments of the application when the computer program is running.
[0095] In this embodiment, the storage medium is a computer-readable storage medium, the computer program comprises computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, a software distribution medium, and the like.
[0096] The above is the preferred embodiment of the application, and it should be pointed out that, for those skilled in the art, without departing from the principle of the application, some improvements and refinements can be made, which are also regarded as the protection scope of the application.
Claims
1. A method for fusing text data and image data based on electricity production, characterized in that, The steps include the following: A feature extraction model is used to extract data features from text data and image data of real-time power production. Based on the data characteristics of the extracted text data and image data of real-time power production, a deep learning model is used to classify the text data and image data of real-time power production into critical response data, emergency response data and general response data in descending order of response level. The fault tolerance for fusing real-time power generation text data and power generation image data is set based on the response level of the text data and power generation image data. Based on the fault tolerance of fusing the text data and image data of real-time power production, a real-time fusion method is set between the text data and image data of real-time power production, and the text data and image data of real-time power production are fused according to the real-time fusion method.
2. The method for fusing text data and image data based on power production according to claim 1, characterized in that, It also includes the following steps: By utilizing the data characteristics of the textual data and the image data of real-time power production, potential faults in power equipment can be predicted.
3. The method for fusing text data and image data based on power production according to claim 2, characterized in that, The step of predicting potential faults in power equipment using the data features of the text data and image data of real-time power generation includes the following steps: The data features of real-time text data and image data of power production from each power production device are aggregated into the same data feature set, and a number is assigned to the data feature set of each power production device. The preset data features of real-time power production text data of the power production equipment include equipment text fault data features, and the data features of power production image data include equipment image fault data features. When the similarity between the data features of the real-time text data of the power production equipment and the features of the equipment text fault data is greater than a preset data feature similarity, or when the similarity between the data features of the image data of the power production equipment and the features of the equipment image fault data is greater than a preset image feature similarity, the number of the data feature set to which the data features of the real-time text data or the data features of the image data belong is obtained, and the power equipment corresponding to the data feature set with the number is predicted to have a potential fault.
4. The method for fusing text data and image data based on power production according to claim 1, characterized in that, In the step of fusing the text data and image data of real-time power production based on the fault tolerance, setting the real-time fusion method between the text data and image data of real-time power production, and fusing the text data and image data of real-time power production according to the real-time fusion method, the method for setting the real-time fusion method between the text data and image data of real-time power production includes the following expression: Where D represents the real-time fusion data between text data and image data of real-time power production, and W... n P represents the data feature of the nth real-time power production text data, 1≤n≤N, where n is a positive integer and N represents the total number of data features of the real-time power production text data. m Let m represent the data feature of the m-th real-time power production image data, where m is a positive integer, 1≤m≤M, and M represents the total number of data features of the real-time power production image data. R is the fault tolerance for fusing the text data and image data of the n-th real-time power production.
5. The method for fusing text data and image data based on power production according to claim 1, characterized in that, It also includes the following steps: The deep learning model is trained using the real-time fused data obtained by fusing the text data and image data of real-time power production.
6. The method for fusing text data and image data based on power production according to claim 1, characterized in that, It also includes the following steps: When the feature matching degree between the data features of the text data of real-time power production and the data features of the image data of power production exceeds a preset matching degree, the text data of real-time power production and the image data of power production are fused in real time.
7. A system for fusing text and image data based on electricity production, characterized in that, include: The data feature extraction module is used to extract data features from text data and image data of real-time power production using a feature extraction model. The response level classification module is used to classify the extracted real-time power production text data and power production image data into critical response data, emergency response data and general response data in descending order of response level based on the data characteristics of the extracted text data and image data of power production using a deep learning model. The fault tolerance setting module is used to set the fault tolerance for fusing the text data and image data of real-time power generation, based on the response level of the text data and image data of real-time power generation. The data fusion module is used to set the real-time fusion method between the text data and image data of real-time power production based on the fault tolerance of the fusion, and the text data and image data of real-time power production are fused according to the real-time fusion method.
8. A system for fusing text and image data based on power production according to claim 7, characterized in that, Also includes: The potential fault prediction module is used to predict potential faults in power equipment based on the data characteristics of the text data and the image data of the real-time power production.
9. A system for fusing text and image data based on power production according to claim 7, characterized in that, Also includes: The deep learning model module is used to train the deep learning model using the real-time fused data obtained by fusing the text data and image data of the real-time power production.
10. A system for fusing text and image data based on power production according to claim 7, characterized in that, Also includes: The feature matching module is used to fuse the text data and image data of real-time power production in real time when the feature matching degree between the data features of the text data and the data features of the image data of power production exceeds a preset matching degree.