Evaluation method based on multi-source data, electronic equipment and readable storage medium

Abstract

The invention relates to an evaluation method based on multi-source data, electronic equipment and a readable storage medium. The multi-source data comprises structured data, unstructured data and real-time Internet of Things data, and the method specifically comprises the steps that S1, the structured data, the unstructured data and the real-time Internet of Things data comprise numerical evaluation and non-numerical evaluation; s2, determining the weight of each numerical evaluation and non-numerical evaluation according to the numerical evaluation and non-numerical evaluation of the structured data, the non-structured data and the real-time Internet of Things data; s3, converting the numerical evaluation and the non-numerical evaluation into numerical scores; and S4, calculating a final score according to the numerical score and the corresponding weight. According to the method, the weights of the numerical evaluation part and the non-numerical evaluation part in the multi-source data are confirmed, the numerical evaluation part and the non-numerical evaluation part are converted into the corresponding numerical scores respectively, the final score is obtained by combining the numerical scores and the weights, the scoring standards are diversified, and the overall condition of the project can be better reflected.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an evaluation method based on multi-source data, an electronic device, and a readable storage medium. Background Art

[0002] In order to better evaluate a system, it is necessary to combine multiple dimensions and multiple data for comprehensive evaluation, including numerical and non-numerical evaluation. How to achieve efficient and reliable evaluation process based on multiple data types and improve the accuracy of evaluation results.

[0003] The invention patent with publication number CN115829405A discloses a target data processing method, device, equipment and medium based on multi-dimensionality, which relates to the field of data processing technology. The target data processing method based on multi-dimensionality includes: first, the structured data of the target to be evaluated, and the value of the structured evaluation factor of the evaluation target is calculated; then, according to the unstructured data of the target to be evaluated, the value of the unstructured evaluation factor of the evaluation target is calculated; finally, according to the value of each structured evaluation factor and the value of each unstructured evaluation factor, the influence weight information of the structured evaluation factor and the influence weight information of the unstructured evaluation factor are obtained. Thus, the device can use richer data dimensions to evaluate the target to be evaluated by obtaining the structured evaluation factor and the unstructured evaluation factor respectively, thereby realizing multi-angle evaluation of the target to be evaluated. The patent does not mention how to evaluate non-numerical data.

[0004] Therefore, providing an evaluation method that can realize multi-source data is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide an evaluation method based on multi-source data, an electronic device and a readable storage medium in order to overcome the defects of the above-mentioned prior art.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] According to a first aspect of the present invention, there is provided an evaluation method based on multi-source data, wherein the multi-source data includes structured data, unstructured data, and real-time IoT data. The method specifically comprises:

[0008] S1. The structured data, unstructured data and real-time IoT data all include numerical evaluation and non-numerical evaluation;

[0009] S2. Determine the weights of the numerical and non-numerical evaluations based on the numerical and non-numerical evaluations of the structured data, unstructured data, and real-time IoT data;

[0010] S3, converting the numerical evaluation and non-numerical evaluation into a numerical score;

[0011] S4. Calculate the final score based on the numerical score and the corresponding weight.

[0012] As a preferred technical solution, different evaluation levels are set through a fuzzy comprehensive evaluation model, the levels are divided according to the non-numerical evaluation text, and the corresponding evaluation levels are converted into numerical scores.

[0013] As a preferred technical solution, the evaluation levels include four levels: excellent, good, medium and poor.

[0014] As a preferred technical solution, the semantic features of non-numerical evaluation are extracted through the BERT model, and the emotional state of the device is obtained through sentiment analysis of the semantic features, which is then converted into a numerical score based on the emotional state.

[0015] As a preferred technical solution, the emotional state includes positive emotions and negative emotions, and the numerical score of the positive emotion is greater than the numerical score of the negative emotion.

[0016] As a preferred technical solution, multiple interval ranges are set, and the numerical evaluation is converted into a numerical score according to the interval range in which it falls.

[0017] As a preferred technical solution, the numerical scores of the different data sources are normalized to ensure that all numerical scores are on the same scale, and a Min-Max normalization or a Z-score normalization method may be used.

[0018] As a preferred technical solution, the final score uses a weighted average method or TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method or a multi-objective optimization method to fuse the numerical scores of different data sources; at the same time, the weights are dynamically adjusted according to the actual situation. According to a second aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the program, it implements the method described in any of the above items.

[0019] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method described in any one of the above items is implemented.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] 1. The present invention converts the numerical and non-numerical evaluations in multi-source data into corresponding numerical scores by confirming their weights, and then combines the numerical scores and weights to obtain the final score. The scoring criteria are diverse and can better reflect the overall situation of the project.

[0022] 2. The present invention adopts a fuzzy comprehensive evaluation model to set different evaluation levels, divides the levels according to the non-numerical evaluation text, and converts the corresponding evaluation levels into numerical scores, which can evaluate non-numerical texts.

[0023] 3. The present invention uses the BERT model to extract the semantic features of non-numerical evaluations, and derives the emotional state of the device through sentiment analysis of the semantic features. It converts the emotional state into a numerical score based on the emotional state, and can confirm the recognition of a certain indicator based on the emotional component of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0026] The goal of a multi-source data evaluation system is to integrate information from different data sources to generate a comprehensive evaluation score to support project management decisions. To achieve this goal, the evaluation system needs to be able to process structured data, unstructured data, and real-time IoT data, and convert this data into quantifiable evaluation indicators.

[0027] The present invention provides an evaluation method, electronic device and readable storage medium based on multi-source data; the present invention converts the numerical evaluation and non-numerical evaluation into corresponding numerical scores respectively by analyzing the numerical evaluation and non-numerical evaluation parts in the multi-source data and confirming the weights, and obtains the final score by combining the numerical score and the weight. The scoring criteria are diverse and can better reflect the overall situation of the project. The present invention uses a fuzzy comprehensive evaluation model to set different evaluation levels, divides the levels according to the text of the non-numerical evaluation, and converts the corresponding evaluation levels into numerical scores, which can evaluate non-numerical texts. The present invention uses the BERT model to extract the semantic features of non-numerical evaluations, and obtains the emotional state of the device through sentiment analysis of the semantic features, and converts it into a numerical score according to the emotional state, which can confirm the recognition of a certain indicator based on the emotional component of the evaluation.

[0028] Example 1

[0029] like Figure 1 As shown, an evaluation method based on multi-source data, wherein the multi-source data includes structured data, unstructured data and real-time IoT data, is characterized in that the method specifically includes:

[0030] S1. The structured data, unstructured data and real-time IoT data all include numerical evaluation and non-numerical evaluation;

[0031] S2. Determine the weights of the numerical and non-numerical evaluations based on the numerical and non-numerical evaluations of the structured data, unstructured data, and real-time IoT data;

[0032] S3, converting the numerical evaluation and non-numerical evaluation into a numerical score;

[0033] S4. Calculate the final score based on the numerical score and the corresponding weight.

[0034] Different evaluation levels are set through the fuzzy comprehensive evaluation model, the levels are divided according to the non-numerical evaluation text, and the corresponding evaluation levels are converted into numerical scores.

[0035] The evaluation grades include four grades: excellent, good, fair and poor.

[0036] The semantic features of non-numerical evaluation are extracted through the BERT model, and the emotional state of the device is obtained through sentiment analysis of the semantic features, which is then converted into a numerical score based on the emotional state.

[0037] The emotional state includes positive emotion and negative emotion, and the numerical score of the positive emotion is greater than the numerical score of the negative emotion.

[0038] Set multiple interval ranges and convert the numerical evaluation into a numerical score based on the interval range.

[0039] The numerical scores of the different data sources are normalized to ensure that all numerical scores are on the same scale. Min-Max normalization or Z-score normalization method can be used.

[0040] The final score uses a weighted average method or TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method or a multi-objective optimization method to integrate the numerical scores of different data sources; and dynamically adjusts the weights according to actual conditions.

[0041] In this embodiment,

[0042] (1) Determine the evaluation dimensions: A new power system scientific and technological research effectiveness evaluation system with multi-level indicators was constructed.

[0043] Indicator weight allocation: Use methods such as the Analytic Hierarchy Process (AHP) or the entropy method, combined with expert opinions, to determine the weight of each indicator.

[0044] The weighting should take into account the importance of different indicators to the success of the project.

[0045] (2) Quantification of non-numerical indicators

[0046] Introducing a fuzzy comprehensive evaluation model: For non-numerical indicators (such as expert review opinions and technical documentation quality), a fuzzy comprehensive evaluation model is introduced to convert qualitative evaluations into quantitative scores. The fuzzy comprehensive evaluation model converts non-numerical indicators into numerical scores by setting evaluation levels (such as excellent, good, fair, and poor) and membership functions.

[0047] Text Data Quantification: For text data (such as technical documents and expert review opinions), the BERT model is used to extract semantic features and convert them into numerical scores through sentiment analysis or topic modeling. For example, sentiment analysis can determine the positive or negative sentiment of a text and convert it into a corresponding score.

[0048] Quantification of real-time IoT data: Real-time IoT data (such as device operating status and energy conversion efficiency) is converted into scores by setting thresholds or using statistical methods (such as mean and variance). For example, device operating status can be quantified and scored based on indicators such as failure rate and operating time.

[0049] (3) Multi-source data fusion and scoring calculation

[0050] Data normalization: Normalize the scores from different data sources to ensure that all scores are on the same scale. You can use Min-Max normalization or Z-score normalization.

[0051] Multi-source data fusion: Use weighted averaging, TOPSIS (Technique for Order Preference by Similarity to Ideal Solution), or multi-objective optimization methods to combine scores from different data sources. For example, the weighted averaging method can calculate a comprehensive score based on the weights of each indicator.

[0052] Dynamic weight adjustment: Incorporating a deep learning-driven weight evolution module, the weights of various indicators are dynamically adjusted to adapt to project progress and changes in the external environment. For example, when a project enters a critical stage, the weights of technical quality and risk control can be increased.

[0053] (4) Evaluation score generation and optimization

[0054] Evaluation score generation: Based on the integrated scores, a comprehensive evaluation score for the project is generated. The evaluation score can be used for project progress monitoring, risk warning, and decision support.

[0055] Evaluation score optimization: Based on business objectives and constraints, optimization algorithms (such as gradient descent and genetic algorithms) are used to optimize evaluation scores. For example, the project progress and cost control scores can be optimized by adjusting the allocation of project resources.

[0056] (5) Visualization and application of evaluation results

[0057] Visualize evaluation results: Use visualization tools (such as Tableau and Power BI) to present evaluation results in charts and graphs to facilitate understanding and decision-making by project managers. For example, you can create radar charts, bar charts, or line charts to display the scores for each dimension and the overall score.

[0058] Application of evaluation results: Apply the evaluation results to various aspects of project management, such as project progress monitoring, risk warning, resource allocation, etc. For example, when the evaluation score falls below a certain threshold, the system can automatically trigger a risk warning, reminding project managers to take appropriate measures.

[0059] (6) Evaluation system iteration and optimization

[0060] Data feedback and model iteration: Based on actual application results, new data is collected to continuously iterate and optimize the evaluation system. For example, the parameters and structure of the evaluation model can be adjusted by collecting actual project progress data.

[0061] Evaluation system optimization: Based on the actual needs of project management, we continuously optimize the evaluation indicator system, weighting method, and data fusion strategy. For example, we can dynamically adjust the evaluation dimensions and weights according to the different stages of the project.

[0062] The multi-source data evaluation system integrates structured data, unstructured data, and real-time IoT data, introducing fuzzy comprehensive evaluation models and the BERT model. This system converts non-numerical indicators into numerical scores and generates comprehensive evaluation scores through multi-source data fusion and dynamic weighting adjustments. This system can provide comprehensive and accurate evaluation results for project management, supporting project progress monitoring, risk warning, and decision optimization.

[0063] Example 2

[0064] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the above methods when executing the program.

[0065] A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the methods described above. Those skilled in the art will clearly understand that, for ease and brevity of description, the specific working processes of the modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0066] The electronic device of the present invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0067] Multiple components in the device are connected to the I / O interface, including: input units, such as a keyboard, mouse, etc.; output units, such as various types of displays, speakers, etc.; storage units, such as magnetic disks, optical disks, etc.; and communication units, such as network cards, modems, wireless communication transceivers, etc. The communication unit allows the device to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunications networks. The processing unit performs the various methods and processes described above, such as the method of the present invention. For example, in some embodiments, the method of the present invention can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device via ROM and / or the communication unit. When the computer program is loaded into RAM and executed by the CPU, one or more steps of the method of the present invention described above can be performed. Alternatively, in other embodiments, the CPU can be configured to perform the method of the present invention by any other suitable means (e.g., by means of firmware).

[0068] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0069] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0070] In the context of the present invention, machine-readable medium can be a tangible medium that can contain or store a program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0071] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. An evaluation method based on multi-source data, wherein the multi-source data includes structured data, unstructured data and real-time IoT data, characterized in that: The method specifically includes: S1. The structured data, unstructured data and real-time IoT data all include numerical evaluation and non-numerical evaluation; S2. Determine the weights of the numerical and non-numerical evaluations based on the numerical and non-numerical evaluations of the structured data, unstructured data, and real-time IoT data; S3, converting the numerical evaluation and non-numerical evaluation into a numerical score; S4. Calculate the final score based on the numerical score and the corresponding weight.

2. The evaluation method based on multi-source data according to claim 1, characterized in that: Different evaluation levels are set through the fuzzy comprehensive evaluation model, the levels are divided according to the non-numerical evaluation text, and the corresponding evaluation levels are converted into numerical scores.

3. The evaluation method based on multi-source data according to claim 2, characterized in that: The evaluation grades include four grades: excellent, good, fair and poor.

4. The evaluation method based on multi-source data according to claim 1, characterized in that: The semantic features of non-numerical evaluation are extracted through the BERT model, and the emotional state of the device is obtained through sentiment analysis of the semantic features, which is then converted into a numerical score based on the emotional state.

5. The evaluation method based on multi-source data according to claim 4, characterized in that: The emotional state includes positive emotion and negative emotion, and the numerical score of the positive emotion is greater than the numerical score of the negative emotion.

6. The evaluation method based on multi-source data according to claim 1, characterized in that: Set multiple interval ranges and convert the numerical evaluation into a numerical score based on the interval range.

7. The evaluation method based on multi-source data according to claim 1, characterized in that: The numerical scores of the different data sources are normalized to ensure that all numerical scores are on the same scale. Min-Max normalization or Z-score normalization method can be used.

8. The evaluation method based on multi-source data according to claim 1, characterized in that: The final score uses a weighted average method or TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method or a multi-objective optimization method to fuse the numerical scores of different data sources; and dynamically adjusts the weights according to actual conditions.

9. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images