Evaluation result correction method based on big data

Abstract

The invention relates to an evaluation result correction method based on big data, which can update a system by setting a new big data evaluation and correction method under the condition that an enterprise has a big data analysis and evaluation system so as to save system resources and be linked with previous data to improve the running speed. Or under the condition that an enterprise does not have a big data analysis and evaluation system, a system with a classification and evaluation template is installed to save system resources and improve the speed on the premise of ensuring the accuracy of an evaluation result.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more specifically to a method for correcting evaluation results based on big data. Background Technology

[0002] Current enterprise assessment methods for big data typically involve collecting and cleaning the data, classifying it to obtain valid data, analyzing it by category, and finally evaluating it based on the analysis results. Different algorithms are applied for classification, analysis, or evaluation in this process, or different models are used to execute these processes. However, each step of this process requires significant system resources, which can lead to resource-intensive evaluation and slow result retrieval.

[0003] To avoid the resource-intensive and slow nature of the aforementioned assessment process, companies typically simplify the classification or analysis processes, or optimize both before conducting the assessment. However, these methods require too many correction steps, or the correction process occurs too early, making it difficult to effectively correct errors in the final assessment, resulting in inaccurate results. Furthermore, during system updates, the simplifications are often overwritten, preventing integration with historical data and leaving the final assessment and correction data without reference, thus wasting system resources.

[0004] To avoid the above problems, companies now either recalibrate the entire process or only the evaluation results. Both solutions require too many calibration steps, or when calibrating the evaluation process, they cannot use a unified calibration standard for the original and current systems, nor can they reasonably divide the specific scores for different evaluation intervals, resulting in the ineffective implementation of the evaluation calibration process.

[0005] Therefore, there is an urgent need for a big data-based method for correcting evaluation results, which can ensure the accuracy of big data evaluation results without setting up new models, can be implemented with unified standards, and improve the speed of the data evaluation process. Summary of the Invention

[0006] To address the problems of the existing technologies, this invention provides a big data-based method for correcting evaluation results. This method can save system resources and improve operating speed by updating the system with a new big data evaluation and correction method when the enterprise already has a big data analysis and evaluation system. Alternatively, it can save system resources and improve speed while ensuring the accuracy of evaluation results when the enterprise does not have a big data analysis and evaluation system.

[0007] The technical solution adopted in this invention is as follows: A method for correcting evaluation results based on big data, characterized by performing the following steps: S1. The local terminal asks the user whether a big data assessment and correction system already exists; S11. If the local terminal already has a big data evaluation and correction system, then proceed to step S2; S12. If the local terminal does not have a big data evaluation and correction system, then proceed to step S3; S2. Install update package A on the local terminal; S21. The update file package A contains a system analysis module; S22. The updated file package A includes a data filtering template generation module, a data classification template generation module, and a data analysis model generation module; S23. Based on the analysis results of the system analysis module, generate a data filtering template, a data classification template, and a data analysis model for the local terminal; S24. Perform step S4; S3. Install Big Data Assessment and Correction System Installation Package B on the local terminal; S31. The installation package B contains a large data type selection module.

[0008] S32. Different types of large data have corresponding historical data and evaluation scores.

[0009] S33. Different types of large data have corresponding data filtering templates, data classification templates, and data analysis models.

[0010] S34. After the user selects a specific data type, the local terminal obtains the local terminal's data filtering template, data classification template, and data analysis model; S35. Perform step S4.

[0011] S4. After inputting the data into the various templates, the analysis results are obtained. S41. After collecting the data, input the data into the data filtering template to obtain the filtered data;

[0012] S42. Input the filtered data into the data classification template to obtain the classified grouped data.

[0013] S43. Input the classified grouped data into the data analysis model to obtain the data analysis results.

[0014] S5. Compare the analytical results with historical analytical results to obtain an evaluation result; S6. Compare the evaluation results with historical evaluation results to obtain correction data; S7. Confirm the accuracy of the correction based on the obtained correction data.

[0015] The present invention also provides a readable storage medium that stores instruction code, so that a processor can call the instruction code stored in the readable storage medium to perform the method as claimed in any one of claims 1-8.

[0016] The present invention also provides a big data-based evaluation result correction system, which includes: Memory for storing instruction codes; The processor invokes instruction codes stored in memory to execute the method as described in any one of claims 1-8.

[0017] The present invention has the following beneficial effects: This invention simplifies the process of analyzing and evaluating results by updating the existing big data analysis and evaluation system. It can also directly obtain relevant evaluation results and correction data based on historical data, enabling accurate and rapid acquisition of the required results.

[0018] By setting three thresholds, the speed of obtaining results can be improved while ensuring the accuracy of analysis and evaluation results.

[0019] Regarding the acquisition of historical data, the system takes into account whether it is the first time using the big data assessment system. If it is the first time using the system, historical data related to the big data type will be provided to the user, so that historical data cannot be obtained due to the first time using the system. If it is not the first time using the system, the system can be directly updated and applied based on the historical data of the original system, thereby improving the user experience.

[0020] Based on the original system's architecture and processes, it can automatically update each model, upgrading the system without disrupting the original processes and reducing resource waste. Attached Figure Description

[0021] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a big data-based evaluation result correction method. Detailed Implementation

[0023] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort should fall within the scope of protection of the present invention.

[0025] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0026] like Figure 1 As shown, a big data-based method for correcting evaluation results involves the following steps: S1. The local terminal asks the user whether a big data assessment and correction system already exists; S11. If the local terminal already has a big data evaluation and correction system, then proceed to step S2; S12. If the local terminal does not have a big data evaluation and correction system, then proceed to step S3; S2. Install update package A on the local terminal; S21. The update file package A contains a system analysis module; The system analysis module can analyze the historical data types collected by the local terminal's existing big data assessment and correction system, and obtain the analyzed data types. The system analysis module can obtain the evaluation results and correction data from the big data evaluation and correction system already existing on the local terminal.

[0027] S22. The updated file package A includes a data filtering template generation module, a data classification template generation module, and a data analysis model generation module; S23. Based on the analysis results of the system analysis module, generate a data filtering template, a data classification template, and a data analysis model for the local terminal; The system analysis module extracts the data filtering templates, data classification templates, and data analysis models already used by the big data assessment and correction system on the local terminal, obtains the latest versions of each template and model from the server, downloads them, and generates the local terminal's data filtering templates, data classification templates, and data analysis models. S24. Perform step S4; S3. Install Big Data Assessment and Correction System Installation Package B on the local terminal; S31. The installation package B contains a large data type selection module.

[0028] S32. Different types of large data have corresponding historical data and evaluation scores.

[0029] S33. Different types of large data have corresponding data filtering templates, data classification templates, and data analysis models.

[0030] S34. After the user selects a specific data type, the local terminal obtains the local terminal's data filtering template, data classification template, and data analysis model; The types of big data include, but are not limited to: meteorological data, operational data of specific types of machinery and equipment, road transportation data, data on goods entering and leaving warehouses, and employee mobility data.

[0031] The installation package B contains analysis results, evaluation results, and correction data corresponding to different large data types. S35. Perform step S4.

[0032] S4. After inputting the data into the various templates, the analysis results are obtained. S41. After collecting the data, input the data into the data filtering template to obtain the filtered data;

[0033] S42. Input the filtered data into the data classification template to obtain the classified grouped data.

[0034] S43. Input the classified grouped data into the data analysis model to obtain the data analysis results.

[0035] S5. Compare the analysis result data T with the average value U of historical analysis result data to obtain the evaluation result; The absolute value of the difference between the analysis result data T and the average value U of the historical analysis results is taken. If the absolute value is greater than the threshold, the evaluation result corresponding to the analysis result data is taken as the final evaluation result U2; If the absolute value is not greater than the threshold, then the data analysis result corresponding to the average value U of the historical analysis results is used as the final data.

[0036] S6. Compare the evaluation results with historical evaluation results to obtain correction data; If there exists a historical evaluation result U1 and a data analysis result T1 corresponding to the average value U of the historical analysis results, and the absolute value of the difference between the analysis result data T1 corresponding to the historical evaluation result U1 and the analysis result data T is less than the first threshold, then the historical evaluation result U1 is taken as the final analysis result data, and the correction data corresponding to the historical evaluation result U1 is taken as the final correction data.

[0037] Wherein, the first threshold is numerically smaller than the threshold.

[0038] If the absolute value is greater than the threshold, the evaluation result corresponding to the analysis result data is taken as the final evaluation result U2; the correction data corresponding to the evaluation result U2 in the historical data is taken as the final correction data.

[0039] S7. Confirm the accuracy of the correction based on the obtained correction data.

[0040] If the obtained correction data is greater than the second threshold, then the correction data is inaccurate; If the obtained correction data is not greater than the second threshold, then the correction data is accurate.

[0041] The first threshold, the second threshold, and the threshold are all set manually.

[0042] The present invention also provides a readable storage medium that stores instruction code, so that a processor can call the instruction code stored in the readable storage medium to execute a big data-based evaluation result correction method.

[0043] The present invention also provides a big data-based evaluation result correction system, which includes: Memory for storing instruction codes; The processor calls instruction codes stored in memory to execute a big data-based evaluation result correction method.

[0044] The present invention has the following beneficial effects: This invention simplifies the process of analyzing and evaluating results by updating the existing big data analysis and evaluation system. It can also directly obtain relevant evaluation results and correction data based on historical data, enabling accurate and rapid acquisition of the required results.

[0045] By setting three thresholds, the speed of obtaining results can be improved while ensuring the accuracy of analysis and evaluation results.

[0046] Regarding the acquisition of historical data, the system takes into account whether it is the first time using the big data assessment system. If it is the first time using the system, historical data related to the big data type will be provided to the user, so that historical data cannot be obtained due to the first time using the system. If it is not the first time using the system, the system can be directly updated and applied based on the historical data of the original system, thereby improving the user experience.

[0047] Based on the original system's architecture and processes, it can automatically update each model, upgrading the system without disrupting the original processes and reducing resource waste.

[0048] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

[0049] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

[0050] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for correcting evaluation results based on big data, characterized in that, Perform the following steps: S1. The local terminal asks the user whether a big data assessment and correction system already exists; S11. If the local terminal already has a big data evaluation and correction system, then proceed to step S2; S12. If the local terminal does not have a big data evaluation and correction system, then proceed to step S3; S2. Install update package A on the local terminal; S21. The update file package A contains a system analysis module; S22. The updated file package A includes a data filtering template generation module, a data classification template generation module, and a data analysis model generation module; S23. Based on the analysis results of the system analysis module, generate a data filtering template, a data classification template, and a data analysis model for the local terminal; S24. Perform step S4; S3. Install Big Data Assessment and Correction System Installation Package B on the local terminal; S4. After inputting the data into the various templates, the analysis results are obtained. S5. Compare the analysis results with historical analysis results to obtain an evaluation result; S6. Compare the evaluation results with historical evaluation results to obtain correction data; S7. Confirm the accuracy of the correction based on the obtained correction data.

2. The method for correcting evaluation results based on big data as described in claim 1, characterized in that, S41. After collecting the data, input the data into the data filtering template to obtain the filtered data; 3. The method for correcting evaluation results based on big data as described in claim 2, characterized in that, S42. Input the filtered data into the data classification template to obtain the classified grouped data.

4. The method for correcting evaluation results based on big data as described in claim 3, characterized in that, S43. Input the classified grouped data into the data analysis model to obtain the data analysis results.

5. The method for correcting evaluation results based on big data as described in claim 4, characterized in that, S31. The installation package B contains a large data type selection module.

6. The method for correcting evaluation results based on big data as described in claim 5, characterized in that, S32. Different types of large data have corresponding historical data and evaluation scores.

7. The method for correcting evaluation results based on big data as described in claim 1, characterized in that, S33. Different types of large data have corresponding data filtering templates, data classification templates, and data analysis models.

8. The method for correcting evaluation results based on big data as described in claim 7, characterized in that, S34. After the user selects a specific data type, the local terminal obtains the local terminal's data filtering template, data classification template, and data analysis model; S35. Perform step S4.

9. A readable storage medium, characterized in that, The readable storage medium stores instruction code for the processor to invoke the instruction code stored in the readable storage medium to execute the method as claimed in any one of claims 1-8.

10. A big data-based evaluation result correction system, characterized in that, The big data-based evaluation result correction system includes: Memory for storing instruction codes; The processor invokes instruction codes stored in memory to execute the method as described in any one of claims 1-8.

Images