A data processing method and system applicable to the business assessment system for organizational construction

Abstract

The present invention discloses a data processing method and system applicable to an organizational construction business evaluation system. The method includes obtaining organizational construction data corresponding to the organizational construction business to be evaluated; sequentially processing the organizational construction data to obtain data to be processed; processing the data to be processed based on a constructed multi-dimensional evaluation model to obtain assessment score information. The multi-dimensional evaluation model is designed to dynamically adjust the weights of each target dimension corresponding to the organizational construction business to be evaluated according to an adaptive weight allocation mechanism, and calculate the assessment score information with the adjusted weights; generating a corresponding visualization result log; and sending the visualization result log to corresponding terminals respectively. The data processing method and system applicable to the organizational construction business evaluation system of the present invention promote the digital and intelligent process of organizational construction business evaluation by designing a complete data processing method flow, and thus achieve a more comprehensive, objective and efficient comprehensive evaluation.

Description

Technical Field

[0001] The present invention relates to the field of computer processing technologies, and in particular, to a data processing method and system applicable to an organizational construction business evaluation system. Background Art

[0002] In the prior art, the evaluation of organizational construction business not only requires manual offline operations by personnel, such as filling out paper forms and manually summarizing data, resulting in low efficiency and easy errors, but also relies on the subjective experience of evaluators, leading to inaccurate evaluation results and making it difficult to achieve intelligent management and monitoring of data in the organizational construction business evaluation system.

[0003] Therefore, how to design a data processing method applicable to an organizational construction business evaluation system to promote the digitalization and intelligentization process of organizational construction business evaluation has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0004] The present invention provides a data processing method and system applicable to an organizational construction business evaluation system, which abandons the drawbacks of relying on offline and subjective experience in the prior art. By designing a perfect process of a data processing method applicable to an organizational construction business evaluation system, the digitalization and intelligentization process of organizational construction business evaluation is promoted, and thus a more comprehensive, objective, and efficient comprehensive evaluation is achieved.

[0005] To solve the above technical problems, an embodiment of the present invention provides a data processing method applicable to an organizational construction business evaluation system, including:

[0006] Obtaining organizational construction data corresponding to the organizational construction business to be evaluated;

[0007] Successively performing data cleaning, data formatting, data standardization, and data filling on the organizational construction data to obtain data to be processed;

[0008] Processing the data to be processed based on a constructed multi-dimensional evaluation model to obtain assessment score information corresponding to the organizational construction business to be evaluated, wherein the multi-dimensional evaluation model is designed to dynamically adjust the weights of each target dimension corresponding to the organizational construction business to be evaluated according to an adaptive weight allocation mechanism, and calculate the assessment score information with the adjusted weights;

[0009] Intelligently analyzing the assessment score information to generate a corresponding visualization result log;

[0010] Sending the visualization result log to at least one of the following terminals: a platform terminal, an evaluator's mobile terminal, or a data storage cloud.

[0011] As one of the preferred solutions, the obtaining of the organizational construction data corresponding to the organizational construction business to be evaluated includes:

[0012] Obtain the first organizational construction sub-data corresponding to the organizational construction business to be evaluated through data crawler technology;

[0013] Import the second organization construction sub-data corresponding to the organization construction business to be evaluated through a preset automation interface;

[0014] Perform content recognition and analysis on the data in the local database to obtain the third-party organization construction sub-data corresponding to the organization construction business to be evaluated;

[0015] The first organization construction sub-data, the second organization construction sub-data and the third organization construction sub-data are integrated and analyzed to obtain the organization construction data.

[0016] As one of the preferred solutions, the organization construction data is sequentially cleaned, formatted, standardized and supplemented to obtain the data to be processed, including:

[0017] Acquire the first data to be processed after the data standardization processing;

[0018] If it is detected that the missing value of the first data to be processed does not reach the preset threshold, the first data to be processed is filled in based on the mean gap filling algorithm;

[0019] If it is detected that the first data to be processed meets a preset skewed distribution condition, the first data to be processed is filled in based on a median filling algorithm;

[0020] If it is detected that the data volume of the first data to be processed is within a preset range, the first data to be processed is supplemented based on a prediction algorithm.

[0021] As one of the preferred solutions, the construction of the multi-dimensional evaluation model includes:

[0022] Determine organizational construction business target data and scoring dimensions corresponding to the organizational construction business target data;

[0023] Based on the hierarchical analysis method, the business target data of the organization construction is quantified to obtain each target level;

[0024] Converting the weights of each target level into the weights of the corresponding scoring dimensions according to a weighting matrix;

[0025] Based on an adaptive weight allocation mechanism, dynamically adjust each of the weights;

[0026] Construct the multi-dimensional evaluation model with each of the dynamically adjusted weights.

[0027] As one of the preferred solutions, the dynamically adjusting each of the weights based on the adaptive weight allocation mechanism includes:

[0028] Adjust each of the weights based on a linear regression model;

[0029] Feedback and correct the effects of each of the adjusted weights according to the Q-learning model.

[0030] As one of the preferred solutions, the dynamically adjusting each of the weights based on the adaptive weight allocation mechanism includes:

[0031] Repeatedly correct each of the weights in the time series based on the Holt-Winters exponential smoothing method;

[0032] Conduct a difference analysis on the corrected errors until the difference analysis result meets the preset.

[0033] As one of the preferred solutions, the organizational construction data includes historical organizational construction data and real-time organizational construction data;

[0034] After obtaining the assessment score information corresponding to the organizational construction business to be evaluated, the method further includes:

[0035] Conduct big data analysis and processing on the real-time organizational construction data;

[0036] Predict the trend prediction information corresponding to the organizational construction business to be evaluated according to the big data analysis and processing results, the historical organizational construction data, and the assessment score information;

[0037] Based on the trend prediction information, strengthen and correct the weights in the multi-dimensional evaluation model.

[0038] As one of the preferred solutions, the format of the visualization result log includes at least documents, bar charts, pie charts, and radar charts.

[0039] As one of the preferred solutions, the intelligent analysis of the assessment score information to generate the corresponding visualization result log includes:

[0040] Conduct accuracy verification and integrity verification on the assessment score information in sequence to obtain the data to be processed;

[0041] Create each chart data corresponding to the data to be processed;

[0042] Based on the large language model technology, generate the to-be-corrected natural language text data matching each of the chart data;

[0043] Performing correction processing on the natural language text data to be corrected to obtain natural language text data;

[0044] Generate a corresponding visualization result log using the natural language text data and the chart data.

[0045] Another embodiment of the present invention provides a data processing system suitable for an organization construction business evaluation system, including:

[0046] An acquisition module is used to acquire the organizational construction data corresponding to the organizational construction business to be evaluated;

[0047] A processing module, used to sequentially perform data cleaning, data formatting, data standardization and data filling processing on the organization construction data to obtain data to be processed;

[0048] An evaluation module is used to process the data to be processed based on the constructed multi-dimensional evaluation model to obtain the evaluation score information corresponding to the organization construction business to be evaluated, wherein the multi-dimensional evaluation model is designed to dynamically adjust the weights of each target dimension corresponding to the organization construction business to be evaluated according to an adaptive weight allocation mechanism, and calculate the evaluation score information with the adjusted weights;

[0049] An analysis module, used to perform intelligent analysis on the assessment score information and generate a corresponding visual result log;

[0050] The sending module is used to send the visualization result log to at least one of the following terminals: a platform terminal, an assessor's mobile terminal or a data storage cloud.

[0051] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0052] Abandoning the drawbacks of the existing technology that relies on offline and subjective experience, a complete data processing method process suitable for the organization construction business evaluation system is designed. Specifically, the organization construction data corresponding to the organization construction business to be evaluated is first obtained to provide accurate data support for subsequent data processing; then, in order to ensure the data quality, targeted data cleaning, data formatting, data standardization and data gap filling are carried out in sequence; then a multidimensional evaluation model is constructed. The multidimensional evaluation model in the present invention is no longer a simple fixed weight calculation, but dynamically adjusts the weight according to an adaptive weight allocation mechanism, thereby effectively improving the generalization ability of the multidimensional evaluation model and the accuracy of the output results; then the relevant result log is generated and finally sent to different data terminals. The whole process integrates data collection, processing and analysis, no longer relies on the subjective experience of the evaluator, realizes a comprehensive digital process, and provides scientific decision-making support for organization construction and human resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a flowchart of a data processing method applicable to an organization construction business evaluation system in one embodiment of the present invention;

[0054] Figure 2 It is a logic block diagram of a data processing method applicable to an organization construction business evaluation system in one embodiment of the present invention;

[0055] Figure 3 It is a structural block diagram of a data processing system applicable to an organization construction business evaluation system in one embodiment of the present invention;

[0056] Reference numerals:

[0057] Among them, 11, acquisition module; 12, processing module; 13, evaluation module; 14, analysis module; 15, sending module. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0060] In the description of the present application, it should be noted that, unless otherwise clearly defined and limited, the terms "installed", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for the purpose of illustration and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0061] In the description of the present application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0062] It should be noted in advance that although the existing general evaluation and management system is applicable to various business scenarios, the evaluation method mainly relies on the subjective evaluation of the evaluators, making it difficult to comprehensively reflect the complex actual situation. And there are generally problems such as a single evaluation dimension, insufficient optimization for the specific needs of organizational construction evaluation, lack of in-depth understanding of organizational construction business, inability to effectively support collaborative evaluation at multiple levels and multiple departments, and inability to flexibly meet the needs of different organizations for comprehensive evaluation of organizational construction business. In view of this, the present invention designs a data processing method applicable to the evaluation system for organizational construction business, to solve the problems of insufficient data integration, subjective evaluation deviation, poor dynamic adaptability, high computational complexity, etc. in the prior art, so as to achieve a more comprehensive, objective and efficient comprehensive evaluation.

[0063] Specifically, an embodiment of the present invention provides a data processing method applicable to the evaluation system for organizational construction business. Please refer toFigure 1 , Figure 1 It shows a schematic flowchart of a data processing method applicable to an organizational construction business evaluation system in one embodiment of the present invention, including steps S1 to S5, which are specifically as follows:

[0064] S1. Obtain the organizational construction data corresponding to the organizational construction business to be evaluated;

[0065] S2. Perform data cleaning, data formatting, data standardization, and data filling processing on the organizational construction data in sequence to obtain the data to be processed;

[0066] S3. Process the data to be processed based on the constructed multi-dimensional evaluation model to obtain the assessment score information corresponding to the organizational construction business to be evaluated. Among them, the multi-dimensional evaluation model is designed to dynamically adjust the weights of each target dimension corresponding to the organizational construction business to be evaluated according to the adaptive weight allocation mechanism, and calculate the assessment score information with the adjusted weights;

[0067] S4. Perform intelligent analysis on the assessment score information to generate a corresponding visual result log;

[0068] S5. Send the visual result log to at least one of the following terminals: the platform terminal, the evaluator's mobile terminal, or the data storage cloud.

[0069] The embodiments of the present invention mainly achieve efficient, statistical, and fair organizational construction evaluation by automatically integrating multi-dimensional data, dynamically adjusting the evaluation model, and reducing the computational complexity. For ease of understanding, the following is described in conjunction with the organizational construction business evaluation system.

[0070] Optionally, the organizational construction business evaluation system may include the following modules:

[0071] (1) Data processing module: Integrate the middle platform data in the organizational construction domain and the human resources domain, such as data on personnel certificates, personnel titles, and responsibility fulfillment information, and perform data cleaning and preprocessing on the data.

[0072] (2) Evaluation model module: Based on the integrated data and in combination with the actual situation of the organization, construct a dynamically adjusted evaluation model to provide multi-dimensional evaluation results.

[0073] (3) Dynamic prediction module: Based on historical data and real-time data, use machine learning algorithms to predict the future trend of organizational construction work and dynamically adjust the evaluation criteria.

[0074] (4) User feedback module: By combining the assessment scores and dynamic performance of personnel and using natural language generation (NLG) technology, the system can automatically generate personalized feedback reports for each person, helping them identify strengths, discover problems, and improve themselves.

[0075] For details, see Figure 2 , Figure 2 The following is a logical block diagram of a data processing method for an organization construction business evaluation system in one embodiment of the present invention. The first is the data acquisition (collection) stage, which mainly acquires various types of data related to organization construction through the automation interface and data import function. The data sources include but are not limited to: organization construction work data: work reports, activity records, task completion status, etc.

[0076] In the above embodiment, the method of data acquisition can be carried out through data crawler technology, automatic interface or local database import. It only needs to be integrated and analyzed after obtaining the sub-data of each organization construction, which will not be described in detail here.

[0077] After obtaining the above data, in order to ensure data quality and consistency, a series of processing is required, including but not limited to data cleaning, data formatting, data standardization and data filling. Data cleaning is used to clean the collected data, remove invalid data, fill missing values, correct format inconsistencies, delete duplicate data, complete missing data, and handle outliers. Data formatting is used to convert data from different data sources into a unified format, such as date format, number format, etc. Data standardization is used to normalize data according to required standardized indicators to ensure that data of different dimensions can be effectively compared. Data filling is used to fill key data by filling in the mean, filling in the median, or using a prediction algorithm. Among them, if the data is evenly distributed and there are few missing values, mean filling is a simple and effective choice. If the data has extreme values ​​or skewed distribution, it is more appropriate to use the median to fill in the gaps. In the case of high data quality and large data volume, using a prediction algorithm to fill in the gaps can achieve better results.

[0078] The multi-dimensional assessment model in the embodiment of the present invention is to score and evaluate the organization construction work. The main contents include: Dimension setting: The system will set corresponding evaluation indicators according to the various dimensions of the organization construction work. Each dimension may contain multiple detailed indicators. Weighted evaluation: The weights of different dimensions and detailed indicators can be configured according to the actual needs of the organization. The system dynamically adjusts the weight of each dimension and finally calculates the comprehensive assessment score of the personnel. Finally, the different dimensions are scored by comprehensively using mathematical models and algorithms to ensure the detectability and scientificity of the scoring process. This will be explained in detail later.

[0079] Furthermore, after the multi-dimensional evaluation model is executed, the embodiments of the present invention will also perform trend prediction. By analyzing historical data and real-time data, machine learning algorithms are used to predict the future trend of organizational construction work, and the evaluation criteria are dynamically adjusted according to the prediction results to ensure that the evaluation is more accurate, real-time, and forward-looking. In addition, if the prediction shows that a certain work may have major problems, the system automatically increases the weight of the relevant dimension and strengthens the evaluation of that dimension. That is, based on the trend prediction information, the weights in the multi-dimensional evaluation model are strengthened and corrected, so that the multi-dimensional evaluation model can be adjusted according to the current working state of the organization to ensure the timeliness of the model.

[0080] According to the multi-dimensional evaluation model and the dynamic scores after system adjustment, the comprehensive score of each organization is calculated, and a detailed evaluation report is generated. The report content includes at least: Comprehensive score: Displays the comprehensive score of the organizational construction work and the scores of each dimension. Analysis of advantages and disadvantages: The system analyzes the outstanding and areas for improvement in the organizational construction work based on the scoring results and puts forward improvement suggestions. Visualization results: Using data visualization techniques such as bar charts, pie charts, radar charts, etc., to quickly display the evaluation results and help users understand. The above results will be presented through the user interface or the report generation system and sent to the relevant terminals.

[0081] In the embodiments of the present invention, the dimension scores include the regular scoring data of each dimension. The historical scores and trends include the scoring trend data of each dimension of personnel in the historical cycle, which is convenient for analyzing the change patterns of dimension performance. External factors such as organizational level changes may affect the weight adjustment. The deviation between the target value and the actual value is used to discover potential scoring deviations by analyzing the difference between the historical scores of personnel and the expected goals, which serves as the basis for weight optimization.

[0082] The goal of dynamic weight optimization is to enable the model to flexibly adjust the weights of each dimension according to the performance changes of personnel, its own feedback, and environmental factors through continuous learning and adjustment, so as to achieve the accuracy, personalization, and fairness of the scoring system. The "dynamic weight optimization method" will be elaborated in detail below, covering the application of time series analysis, machine learning models, reinforcement learning, and other optimization techniques.

[0083] Definition of organizational goals (i.e., organizational construction business goal data) and modeling:

[0084] Organizational goals usually include annual goals, long-term task goals, and short-term task goals. In order to interface with the evaluation system, these goals need to be quantified and transformed into specific measurable indicators. These goals can be divided into several levels:

[0085] Annual goals: Such as personnel activity participation, etc.

[0086] Long-term task objectives: such as strengthening the ideological construction of personnel, enhancing leadership capabilities, etc.

[0087] Task objectives: Tasks in a specific period, such as improving the effectiveness of organizational construction work.

[0088] Then, it is necessary to accurately model the organization's objectives and quantify these objectives into evaluation dimensions. The technical implementation methods include:

[0089] Hierarchical modeling of objectives (Analytic Hierarchy Process - AHP):

[0090] Objective stratification: According to the overall task objectives of the organization, break down the objectives into different sub-objectives and construct an objective tree. For example, the annual objectives can be broken down into "ideological construction of personnel", "work performance", etc.

[0091] Application of AHP method: Quantitatively evaluate the priorities between objectives through expert review or historical data. By calculating the weights of each objective level, ensure that the system can identify which objectives are more important for the long-term development of the organization.

[0092] Quantitative indicators of objectives:

[0093] For each sub-objective, define clear scoring dimensions.

[0094] Use the objective weight matrix: Convert the weights of each objective level into the weights of scoring dimensions through a weighted matrix. In this process, AHP provides a relatively clear quantitative framework to ensure that the scoring of each dimension is consistent with the organizational objectives.

[0095] For the adaptive weight allocation mechanism in the embodiments of the present invention, it includes the following contents:

[0096] (1) Generation of the training data set:

[0097] Matching of objectives and scoring dimensions: First, determine how each evaluation dimension maps to the organization's objectives.

[0098] Label generation: Generate labels according to the priorities of organizational objectives. The label of each sample will represent the relative importance of the organizational objective (e.g., 0.8 indicates a higher priority of the objective, and 0.2 indicates a lower priority).

[0099] (2) Optimize weights using a regression model:

[0100] Linear regression: Use a linear regression model, input the historical scores and objective weights of each dimension, output a comprehensive score, and finally optimize the dimension weights through a loss function (such as Mean Squared Error - MSE). By training historical data, the model will learn how to adjust the weights according to the performance of the scoring dimensions.

[0101] Gradient Boosting Decision Tree (GBDT): By using tree models such as GBDT, the complex relationships between features can be automatically processed, and the contribution of different dimensions to the score can be evaluated. Each tree makes "split" decisions based on historical data of different dimensions and finally outputs the weights of each dimension.

[0102] (3) Weight Optimization and Adaptive Adjustment:

[0103] L1 / L2 Regularization: To prevent the weights from over-relying on a certain feature, L1 or L2 regularization methods can be used to ensure the smoothness of the weights. L1 regularization can produce sparse solutions, forcing the weights of some unimportant features to be zero; L2 regularization balances the weights of each feature to avoid overfitting.

[0104] Self-adaptability of the Objective Function: In each optimization process, according to the changes in the organizational objectives, the structure of the objective function is adjusted. Specifically, the weight terms of the objective function can change dynamically according to the priorities of the organizational objectives, thus promoting the weight adjustment process to be consistent with the objective changes.

[0105] (4) Reinforcement Learning and Real-time Weight Update

[0106] Reinforcement learning can be used to automate the process of optimizing weight allocation, ensuring that the system can adaptively adjust the weights according to real-time feedback.

[0107] Optionally, the effects of the adjusted weights are feedback-corrected according to the Q-learning model.

[0108] State Space of the Q-learning Model: The scores of each evaluation dimension serve as the states of the system (e.g., the work performance scores of personnel, etc.), constituting the state space. The degree of match between the performance of each dimension and the organizational objectives determines the current state.

[0109] Action Space of the Q-learning Model: Weight adjustment is the "action" of reinforcement learning, that is, the system decides whether to increase or decrease the weight of a dimension according to the current state (i.e., the match between the score dimension performance and the organizational objectives).

[0110] Reward Function of the Q-learning Model: The reward is calculated based on the similarity between the performance of the dimension and the organizational objectives.

[0111] The Q-learning algorithm includes the following:

[0112] State: The dimension scores and weight status after each scoring period. Action: Adjust the weights of each dimension. Reward: The degree of match between the score after each adjustment and the actual performance, or the scoring accuracy. Q-value: Represents the value of taking a certain action in the current state, and the update formula is:

[0113]

[0114] where is the learning rate, is the discount factor, is the immediate reward, is the maximum Q-value of all actions in the next state.

[0115] The application of Q-learning is that each time according to the new evaluation data, the system calculates the weight change of each dimension based on the historical Q-value table (i.e., the weight value table of the dimension matching the target). If the weight adjustment of a certain dimension can better reflect the organizational goal, the system will increase the weight of that dimension. The system continuously adjusts the strategy between the existing historical data and the new data through exploration and exploitation to achieve the optimal weight allocation.

[0116] Optionally, after each evaluation period, the system will perform incremental training on the reinforcement learning model through the new evaluation data, update the Q-value table, so as to adjust the dimension weights in real time. Through incremental learning, the system can dynamically update the weight allocation strategy according to the changes of organizational goals in different periods, avoiding the impact of the retraining process on real-time performance.

[0117] Optionally, based on the Holt-Winters exponential smoothing method, dynamic weight adjustment based on time series analysis can also be performed as follows:

[0118] Time series analysis can identify the trends, seasonal fluctuations and abnormal behaviors in the scoring data over time, thus providing a basis for dynamic weight adjustment. By predicting the performance of each dimension in the future for a period of time, the system can adjust the weights according to the trends.

[0119] The Holt-Winters exponential smoothing method is a commonly used time series prediction method, suitable for dealing with situations where there are trends and seasonal fluctuations in the data. In the organizational construction scoring system, dimensions such as work performance may change over time. Using this method can capture these change trends and adjust the weights of the scores accordingly.

[0120] The Holt-Winters model includes additive and multiplicative types. Among them, the additive model is suitable for time series data with relatively stable fluctuation amplitudes and is suitable for dealing with relatively stable score data such as personnel scoring.

[0121] The model consists of three main components:

[0122] Level: Represents the basic level position of time series data.

[0123] Trend: Represents the rate of change of the data (i.e., the speed of increase or decrease).

[0124] Seasonality: Represents the pattern of periodic fluctuations in the data.

[0125] Currently, the system adopts an additive model, and the update formula for the time series is as follows:

[0126] Level ( ):

[0127]

[0128] Trend ( ):

[0129]

[0130] Seasonality ( ):

[0131]

[0132] Forecast ( )

[0133]

[0134] Wherein, is the observed value (i.e., the score value of the current period), is the level, is the trend, is the seasonality, , , are smoothing parameters, and m is the seasonal period.

[0135] The specific application is as follows:

[0136] In the evaluation of organizational construction, the trend of historical scores is crucial for dynamic weight adjustment. The system can apply the Holt-Winters model to predict each evaluation dimension (such as work performance, etc.) and dynamically adjust the weights based on the prediction results. The following are the specific steps of the application process:

[0137] Data preparation: First, the system collects the score data of each evaluation dimension over a past period (such as the past 12 months). Assume that the score data for the work performance dimension is , where t is the time point.

[0138] Model training: Input historical score data into the Holt-Winters model. The model will output three key parameters: (smoothing coefficient), (trend smoothing coefficient), (seasonal smoothing coefficient). These parameters will be used to calculate the trend values for each dimension.

[0139] Smoothing process: The model calculates the long-term trend and seasonal fluctuations of the current dimension score through weighted averaging.

[0140] Trend prediction: Using the obtained trend parameters, the system can predict the future trend of the dimension score. For example, if the score of work performance shows an upward trend, the system will predict that the future score will continue to rise.

[0141] Predicted score and trend adjustment: Based on the predicted score trend, the system will automatically determine the weight of the current dimension. Assuming that the score of work performance continues to rise, the system can increase the weight of this dimension to make its impact on the scoring result more prominent.

[0142] Weight increase: If the score trend of a certain dimension is predicted to rise, the system will emphasize its importance in the evaluation by increasing the weight of this dimension. For example, increase the weight of "work performance" from the initial value of 10% to 15% to reflect its importance at the current stage.

[0143] After each scoring, the system will obtain the actual scoring result. By comparing the predicted score with the actual score, the system can calculate the error and make feedback adjustments based on the error, thereby improving the prediction accuracy and real-time adaptability of the model.

[0144] Error calculation: The system calculates the error by comparing the difference between the predicted score and the actual score. Specifically, the error is:

[0145] Error = actual score - predicted score

[0146] For example, if the predicted score of the work performance dimension is 80 and the actual score is 75, then the error is -5.

[0147] The system uses the error to fine-tune the model. This process is mainly achieved through two ways:

[0148] Parameter update: According to the error magnitude, fine-tune the three smoothing parameters (α, β, γ) of the Holt-Winters model. By adjusting these parameters, the model can better adapt to the actual data, thereby improving the prediction accuracy.

[0149] Dynamic weight adjustment: If the error is large, it indicates that the current prediction may be inaccurate. The system will fine-tune the dimension weights according to the error value. For example, when the error is large, the system may temporarily reduce the weight of this dimension to avoid over-relying on the score of a certain dimension.

[0150] After each scoring, the system will adjust the weights according to the error feedback, enabling the prediction model to continuously optimize itself and improve the accuracy of prediction and scoring. The feedback process of the system includes the following steps:

[0151] Evaluate the size of the error:

[0152] If the error is small, the system considers the current weight allocation to be reasonable and continues to maintain the existing dimension weights.

[0153] If the error is large, the system will re-evaluate whether the current weights are reasonable. Especially for the dimensions with deviations in trend prediction, the system will dynamically adjust the weights.

[0154] Weight fine-tuning:

[0155] Positive fine-tuning: When the prediction deviation is small and the performance of the trend dimension is good, the system can slightly increase the weight of this dimension to further highlight its role in scoring.

[0156] Negative fine-tuning: When the prediction error of a certain dimension is large, the system will reduce the weight of this dimension to reduce its impact on the scoring result until the system converges to a suitable weight allocation through the feedback mechanism.

[0157] Real-time adjustment:

[0158] Since the evaluation of organizational construction involves comprehensive scoring of multiple dimensions, the real-time feedback mechanism ensures that the system can dynamically adjust the weights of each dimension according to the current actual situation. In this way, the weights of dimensions such as work performance will be continuously optimized based on historical score trends and real-time feedback data.

[0159] After each scoring, by comparing the difference (error) between the predicted score and the actual score, the system will fine-tune the parameters to ensure the real-time adaptability of the model.

[0160] In the embodiments of the present invention, by combining the assessment scores and dynamic performance of personnel, the system can provide detailed and specific feedback for each person to help them identify strengths, discover problems, and improve themselves. The system uses natural language generation (NLG) or large language model technology to enable the comprehensive assessment system of organizational construction to automatically generate personalized feedback reports, combined with chart data, which not only improves the efficiency of feedback but also enhances the readability and incentive effect of the feedback content.

[0161] In another embodiment of the present invention, first, the system needs to obtain structured data from various dimensions of organizational construction evaluation (such as learning, work, activities, etc.), including: Dimension scores: The score values for each dimension (such as 0 - 100 points, or classification scores "excellent", "qualified", "unqualified"). Dimension performance: Data such as course grades, activity participation, task completion rate, etc. Historical performance data: The past assessment records of personnel, providing comparison and trend analysis. Personalized characteristics: Such as the nature of the work of personnel, the growth stage of personnel (new personnel, old personnel), etc. After these data are processed through data cleaning and standardization, they are formed into a unified format for the NLG system to call.

[0162] The logical part for generating personalized feedback mainly includes:

[0163] 1. Template selection based on scores: According to the scores or evaluations of personnel in each dimension (such as excellent learning performance, less activity participation), the system selects a suitable feedback template.

[0164] 2. Dynamic template construction: For each dimension, the system can generate targeted feedback based on the specific scores. For example, when the score in the learning dimension is relatively high, the feedback content can be biased towards motivation and praise; while when the score in the activity dimension is relatively low, improvement suggestions are generated.

[0165] Based on the statistical participation times, the system calculates the participation ratio of each person in each dimension and dynamically adjusts the weight values in the evaluation model according to the ratio. The specific steps are as follows:

[0166] Ratio calculation: For each person, calculate their participation ratio in each dimension. For example:

[0167] The course learning ratio of person A is: 5 times / 10 times = 50%.

[0168] The theme day ratio of person A is: 3 times / 10 times = 30%.

[0169] The volunteer service ratio of person A is: 2 times / 10 times = 20%.

[0170] Weight value determination: According to the participation ratio, the system dynamically adjusts the weight values of each dimension in the evaluation model. For example: If a person has a relatively high participation ratio in the course learning dimension, the system can appropriately increase the weight of this dimension to reflect their outstanding performance in this aspect. If a person has a relatively low participation ratio in the volunteer service dimension, the system can appropriately reduce the weight of this dimension to avoid having too much impact on their overall score.

[0171] In this embodiment, to ensure that the tone of the feedback content is appropriate (neither losing fairness nor motivation), the NLG system evaluates the tone of the feedback through the sentiment analysis module. Sentiment analysis adjusts the tone of the feedback according to the scores of the personnel, ensuring that the feedback content is both constructive and encouraging. For example, based on the comprehensive score and the scores of each dimension of the personnel to be analyzed, the system generates personalized feedback logs to help the personnel identify their strengths, discover problems, and improve themselves. The specific steps are as follows:

[0172] Feedback content generation:

[0173] Strength identification: The system generates praise feedback based on the high scores of the personnel in each dimension. For example: "You have performed outstandingly in course learning, with 5 participation times. It is recommended to continue to maintain and study in depth."

[0174] Problem discovery: The system generates improvement suggestions based on the low scores of the personnel in each dimension. For example: "Your participation in volunteer services is relatively low. It is recommended to increase participation in group activities to enhance organizational cohesion."

[0175] Feedback strategy suggestions:

[0176] Organizational construction business rotation strategy: Based on the performance of the personnel in each dimension, the system recommends that they participate in different types of organizational construction businesses to achieve all-round development. For example: "You have participated more in theme days. It is recommended to appropriately increase participation in volunteer service activities to improve comprehensive capabilities."

[0177] Organizational construction business configuration strategy: The system recommends that the personnel invest more energy in certain dimensions according to their performance.

[0178] The core of NLG is to convert structured data (scores, performances, etc.) into natural language text. Two main methods can be used to build the NLG model:

[0179] 1. Template-based NLG: Fixed template + filled data: Combine the preset template with the actual data to generate feedback content. The template usually includes a general feedback framework, which contains preset phrases or sentence patterns. For example:

[0180] "Your learning score is **[learning score], and the performance is [excellent / good / qualified / to be improved]**. It is recommended to continue to maintain and study in depth [course content]."

[0181] "Your activity participation rate is relatively low, and the current score is **[activity score]**. It is recommended to increase participation in group activities to improve organizational cohesion."

[0182] 2. NLG Based on Deep Learning (such as GPT-like models): Data-driven Text Generation: Utilize deep learning models (such as pre-trained generation models like GPT series, T5, etc.) to generate more natural and personalized feedback by learning a large amount of personnel feedback data. The model generates natural language text based on various performance data and historical feedback data of personnel.

[0183] In the organizational construction evaluation system, feedback is not limited to text but can also be multimodal. As needed, in addition to text feedback, the system can also combine charts (such as bar charts, radar charts, etc.) to display the scores of personnel in each dimension.

[0184] The generated feedback report (log) will be output in a customizable format to ensure that the needs of different personnel or organizations are met. Feedback can be output in the following ways:

[0185] Display on the online platform terminal: Display the personalized feedback through the personnel evaluation management system, and personnel can view it at any time.

[0186] Notify the mobile terminal of personnel by email or text message: The system sends emails or text messages according to the preferences of personnel to provide feedback content.

[0187] It should be noted that for the case of requiring a paper report, the system supports generating personalized reports in PDF format for the organization to use. In addition, relevant logs also need to be uploaded to the data storage cloud for storage.

[0188] As can be seen from the above, the embodiments of the present invention mainly perform dynamic correction on weights. The following will be compared and described in combination with the static weights of a single dimension.

[0189] Limitations of Static Weights in a Single Dimension:

[0190] ① Fixed weight value: In the single-dimension static weight model, the weight values of each dimension are fixed and cannot be adjusted according to actual performance. For example, the weight value of course learning is fixed at 0.5, and no matter how the performance of personnel in this dimension changes, the weight value remains unchanged.

[0191] ② Lack of real-time nature: The static weight model cannot respond to changes in personnel performance in real time. For example, if a certain person's performance in course learning significantly improves in a certain stage, the static weight model cannot adjust the weight value in time, resulting in a lag in the evaluation result.

[0192] ③ Lack of foresight: The static weight model cannot predict future performance trends and can only evaluate based on historical data. For example, if a certain person's performance in volunteer service shows an upward trend, the static weight model cannot adjust the weight value in advance, resulting in a lack of foresight in the evaluation result.

[0193] Advantages of Dynamically Adjusting Weights:

[0194] ① Dynamically adjust weight values: The dynamic prediction module can dynamically adjust the weight values of each dimension based on historical data and real-time data. For example, if a person's performance in course learning shows an upward trend, the system can appropriately increase the weight value of this dimension to reflect their outstanding performance in this aspect.

[0195] ② Respond to changes in real time: The dynamic prediction module can respond to changes in a person's performance in real time. For example, if a person's performance in volunteer service significantly improves during a certain period, the system can immediately adjust the weight value of this dimension to ensure the real-time nature of the evaluation results.

[0196] ③ Forward-looking prediction: The dynamic prediction module can predict future performance trends and adjust the weight values according to the prediction results.

[0197] Example: Dynamic weight adjustment for the course learning dimension.

[0198] Background: Person A's participation in course learning has gradually increased in the past 6 months, and their performance shows an upward trend.

[0199] Static weight model: The weight value for course learning is fixed at 0.5, and regardless of how Person A's performance changes, the weight value remains unchanged.

[0200] Dynamic prediction module: The system predicts through time series analysis that Person A's performance in course learning will continue to improve. The system dynamically adjusts the weight value for course learning from 0.5 to 0.6.

[0201] Result: Person A's score in course learning has increased significantly, and the evaluation results more accurately reflect their actual performance.

[0202] Another embodiment of the present invention provides a data processing system applicable to the organizational construction business evaluation system. Specifically, please refer to Figure 3 , Figure 3 which is shown as the structural block diagram of the data processing system applicable to the organizational construction business evaluation system in one of the embodiments of the present invention, and it includes:

[0203] An acquisition module 11, configured to acquire organizational construction data corresponding to the organizational construction business to be evaluated;

[0204] A processing module 12, configured to sequentially perform data cleaning, data formatting, data standardization, and data filling on the organizational construction data to obtain data to be processed;

[0205] The evaluation module 13 is used to process the data to be processed based on the constructed multi-dimensional evaluation model to obtain the evaluation score information corresponding to the organization construction business to be evaluated, wherein the multi-dimensional evaluation model is designed to dynamically adjust the weights of each target dimension corresponding to the organization construction business to be evaluated according to an adaptive weight allocation mechanism, and calculate the evaluation score information with the adjusted weights;

[0206] The analysis module 14 is used to perform intelligent analysis on the assessment score information and generate a corresponding visual result log;

[0207] The sending module 15 is used to send the visualization result log to at least one of the following terminals: a platform terminal, an assessor's mobile terminal or a data storage cloud.

[0208] The data processing method and system applicable to the organization construction business evaluation system according to the embodiment of the present invention have the following beneficial effects:

[0209] (1) By building a multi-source data integration mechanism, we have achieved deep integration of data from multiple fields such as organizational construction and human resources. By introducing an improved fuzzy comprehensive evaluation algorithm and combining it with machine learning technology, we have optimized the subjective evaluation data. Specific technical means include fuzzy matrix optimization: clustering analysis of subjective evaluation data through machine learning algorithms, identifying and eliminating abnormal evaluations, and reducing the impact of personal bias; dynamic weight adjustment: combining historical data and real-time data to dynamically adjust the weights of each factor to ensure the objectivity and scientificity of the evaluation results.

[0210] (2) The problems of insufficient data integration, subjective evaluation bias, poor dynamic adaptability and high computational complexity in the prior art are effectively solved. The drawbacks of the prior art that relies on offline and subjective experience are abandoned, and a complete data processing method suitable for the organization construction business evaluation system is designed. Specifically, the organization construction data corresponding to the organization construction business to be evaluated is first obtained to provide accurate data support for subsequent data processing; then, in order to ensure data quality, targeted data cleaning, data formatting, data standardization and data gap filling are carried out in sequence; then a multi-dimensional evaluation model is constructed. The multi-dimensional evaluation model in the present invention is no longer a simple fixed weight calculation, but dynamically adjusts the weight according to the adaptive weight allocation mechanism, thereby effectively improving the generalization ability of the multi-dimensional evaluation model and the accuracy of the output results; then the relevant result log is generated and finally sent to different data terminals. The whole process integrates data collection, processing and analysis, no longer relies on the subjective experience of the evaluator, realizes a comprehensive digital process, and provides scientific decision-making support for organization construction and human resource management.

[0211] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

Claims

1. A data processing method suitable for an organization construction business evaluation system, characterized in that: include: Obtain the organizational construction data corresponding to the organizational construction business to be evaluated; The organization construction data is sequentially cleaned, formatted, standardized and supplemented to obtain data to be processed; The data to be processed is processed based on the constructed multi-dimensional evaluation model to obtain the evaluation score information corresponding to the organization construction business to be evaluated, wherein the multi-dimensional evaluation model is designed to dynamically adjust the weights of each target dimension corresponding to the organization construction business to be evaluated according to an adaptive weight allocation mechanism, and calculate the evaluation score information with the adjusted weights; Perform intelligent analysis on the assessment score information and generate a corresponding visual result log; Send the visualization result log to at least one of the following terminals: a platform terminal, an examiner's mobile terminal, or a data storage cloud; The construction of the multi-dimensional evaluation model includes: Determine organizational construction business target data and scoring dimensions corresponding to the organizational construction business target data; Based on the hierarchical analysis method, the business target data of the organization construction is quantified to obtain each target level; Converting the weights of each target level into the weights of the corresponding scoring dimensions according to a weighting matrix; Based on an adaptive weight allocation mechanism, dynamically adjust each of the weights; Constructing the multi-dimensional evaluation model with the dynamically adjusted weights; The method of dynamically adjusting each weight based on the adaptive weight allocation mechanism includes: Adjusting each of the weights based on a linear regression model; Performing feedback correction on the effects of the adjusted weights according to the Q-learning model; The organization construction data includes historical organization construction data and real-time organization construction data; After obtaining the assessment score information corresponding to the organization construction business to be assessed, the method further includes: Performing big data analysis and processing on the real-time organization construction data; Predicting trend prediction information corresponding to the organization construction business to be evaluated based on the big data analysis and processing results, the historical organization construction data and the assessment score information; Based on the trend prediction information, the weights in the multi-dimensional evaluation model are enhanced and revised.

2. The data processing method applicable to the organization construction business evaluation system according to claim 1, characterized in that: The obtaining of the organizational construction data corresponding to the organizational construction business to be evaluated includes: Obtain the first organizational construction sub-data corresponding to the organizational construction business to be evaluated through data crawler technology; Import the second organization construction sub-data corresponding to the organization construction business to be evaluated through a preset automation interface; Perform content recognition and analysis on the data in the local database to obtain the third-party organization construction sub-data corresponding to the organization construction business to be evaluated; The first organization construction sub-data, the second organization construction sub-data and the third organization construction sub-data are integrated and analyzed to obtain the organization construction data.

3. The data processing method applicable to the organization construction business evaluation system according to claim 1, characterized in that: The data cleaning, data formatting, data standardization and data supplementation processing are performed on the organization construction data in sequence to obtain the data to be processed, including: Acquire the first data to be processed after the data standardization processing; If it is detected that the missing value of the first data to be processed does not reach the preset threshold, the first data to be processed is filled in based on the mean gap filling algorithm; If it is detected that the first data to be processed meets a preset skewed distribution condition, the first data to be processed is filled in based on a median filling algorithm; If it is detected that the data volume of the first data to be processed is within a preset range, the first data to be processed is supplemented based on a prediction algorithm.

4. The data processing method applicable to the organization construction business evaluation system according to claim 1, characterized in that: The method of dynamically adjusting each weight based on the adaptive weight allocation mechanism includes: Repeatedly modifying each of the weights in time series based on the Holt-Winters exponential smoothing method; Perform difference analysis on the corrected errors until the difference analysis results meet the preset requirements.

5. The data processing method applicable to the organization construction business evaluation system according to claim 1, characterized in that: The format of the visualization result log includes at least a document, a bar chart, a pie chart and a radar chart.

6. The data processing method applicable to the organization construction business evaluation system as claimed in claim 5, characterized in that: The intelligent analysis of the assessment score information to generate a corresponding visual result log includes: The accuracy and integrity of the assessment score information are sequentially checked to obtain data to be processed; Creating various chart data corresponding to the data to be processed; Based on the large language model technology, generating natural language text data to be corrected that matches each of the chart data; Performing correction processing on the natural language text data to be corrected to obtain natural language text data; Generate a corresponding visualization result log using the natural language text data and the chart data.

7. A data processing system suitable for an organization construction business evaluation system, characterized in that: include: An acquisition module is used to acquire the organizational construction data corresponding to the organizational construction business to be evaluated; A processing module, used to sequentially perform data cleaning, data formatting, data standardization and data filling processing on the organization construction data to obtain data to be processed; An evaluation module is used to process the data to be processed based on the constructed multi-dimensional evaluation model to obtain the evaluation score information corresponding to the organization construction business to be evaluated, wherein the multi-dimensional evaluation model is designed to dynamically adjust the weights of each target dimension corresponding to the organization construction business to be evaluated according to an adaptive weight allocation mechanism, and calculate the evaluation score information with the adjusted weights; An analysis module, used to perform intelligent analysis on the assessment score information and generate a corresponding visual result log; A sending module, used to send the visualization result log to at least one of the following terminals: a platform terminal, an examiner's mobile terminal or a data storage cloud; The construction of the multi-dimensional evaluation model includes: Determine organizational construction business target data and scoring dimensions corresponding to the organizational construction business target data; Based on the hierarchical analysis method, the business target data of the organization construction is quantified to obtain each target level; Converting the weights of each target level into the weights of the corresponding scoring dimensions according to a weighting matrix; Based on an adaptive weight allocation mechanism, dynamically adjust each of the weights; Constructing the multi-dimensional evaluation model with the dynamically adjusted weights; The method of dynamically adjusting each weight based on the adaptive weight allocation mechanism includes: Adjusting each of the weights based on a linear regression model; Performing feedback correction on the effects of the adjusted weights according to the Q-learning model; The organization construction data includes historical organization construction data and real-time organization construction data; After obtaining the assessment score information corresponding to the organization construction business to be assessed, the method further includes: Performing big data analysis and processing on the real-time organization construction data; Predicting trend prediction information corresponding to the organization construction business to be evaluated based on the big data analysis and processing results, the historical organization construction data and the assessment score information; Based on the trend prediction information, the weights in the multi-dimensional evaluation model are enhanced and revised.

Images