An automatic examination method and device, computer equipment and storage medium

Abstract

The embodiment of the application belongs to the technical field of intelligent decision-making, and relates to an automatic examination method and device, computer equipment and a storage medium. The method comprises the following steps: reading a system database, obtaining attribute data and performance data corresponding to an examined identifier in the system database; performing feature extraction on the attribute data and the performance data according to a natural language processing technology to obtain an attribute feature vector and a performance feature vector; performing weight calculation on the attribute feature vector and the performance feature vector to obtain an attribute feature weight and a performance feature weight; and calculating a comprehensive score of the attribute feature vector, the performance feature vector, the attribute feature weight and the performance feature weight according to a weighted summation method to obtain an examination score. The application greatly improves the efficiency and accuracy of the examination. Meanwhile, by introducing the natural language processing technology and the weight calculation method, the real situation of the examined object can be more objectively reflected, and the deviation caused by human factors can be reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent decision-making technology, and in particular to an automatic assessment method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Currently, employee evaluations are based on employees' daily activities and performance.

[0003] However, the applicant found that traditional performance appraisal methods require appraisers to verify performance before conducting a comprehensive evaluation. This evaluation method is subjective and cannot provide a comprehensive and objective assessment of employees. Furthermore, the appraisers also need to verify each employee's performance, which significantly increases their time and workload in performance evaluation. Therefore, it is evident that traditional performance appraisal methods suffer from low efficiency and accuracy. Summary of the Invention

[0004] The purpose of this application is to provide an automatic assessment method, apparatus, computer equipment, and storage medium to solve the problems of low efficiency and accuracy in traditional assessment methods.

[0005] To address the aforementioned technical problems, this application provides an automatic assessment method, employing the technical solution described below:

[0006] Receive assessment requests sent by user terminals, which carry an assessment identifier.

[0007] Read the system database and obtain the attribute data and performance data corresponding to the assessed identifier from the system database;

[0008] Natural language processing techniques are used to perform feature extraction on the attribute data and performance data to obtain attribute feature vectors and performance feature vectors.

[0009] Perform weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weight and the performance feature weight;

[0010] The comprehensive score of the attribute feature vector, the performance feature vector, the attribute feature weight, and the performance feature weight is calculated using the weighted summation method to obtain the assessment score.

[0011] The assessment score is output to the user terminal.

[0012] Furthermore, the step of reading the system database and obtaining the attribute data and performance data corresponding to the assessed identifier from the system database specifically includes the following steps:

[0013] Obtain unstructured attribute data corresponding to the assessed identifier from the system database;

[0014] The unstructured attribute data is converted into text to obtain the attribute data.

[0015] Furthermore, after the step of reading the system database and obtaining the attribute data and performance data corresponding to the assessed identifier from the system database, the following steps are also included:

[0016] Based on data exploration and statistical analysis, determine whether there is any missing data in the attribute data and the performance data;

[0017] If there are missing data in the attribute data and the performance data, then the missing data is imputed using the K-nearest neighbor algorithm based on similarity.

[0018] If there is no missing data in the attribute data and the performance data, the data imputation operation will not be performed.

[0019] Furthermore, the step of performing weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weights and performance feature weights specifically includes the following steps:

[0020] The importance of the attribute feature vector and the performance feature vector is determined according to the assessment indicator system;

[0021] The importance level is calculated using the analytic hierarchy process (AHP) to obtain the attribute feature weights and performance feature weights.

[0022] Furthermore, the step of calculating the comprehensive score of the attribute feature vector, the performance feature vector, the attribute feature weights, and the performance feature weights using the weighted summation method to obtain the assessment score specifically includes the following steps:

[0023] The score interval data of the attribute feature weights and the performance feature weights are calculated using the weighted summation method.

[0024] Obtain the machine learning prediction model corresponding to the score interval data;

[0025] The attribute feature vector and the performance feature vector are input into the machine learning prediction model to perform a score prediction operation, thereby obtaining the assessment score.

[0026] Furthermore, the step of outputting the assessment score to the user terminal specifically includes the following steps:

[0027] The attribute data and the scores of the performance data are displayed using a bar chart;

[0028] The line graph shows the growth trend of the assessed person in different assessment cycles.

[0029] The radar chart illustrates the balance of the assessee's performance across different dimensions.

[0030] To address the aforementioned technical problems, this application also provides an automatic assessment device, which employs the following technical solution:

[0031] The request receiving module is used to receive assessment requests sent by user terminals, which carry an assessment identifier.

[0032] The data acquisition module is used to read the system database and obtain attribute data and performance data corresponding to the assessed identifier from the system database;

[0033] The feature extraction module is used to perform feature extraction operations on the attribute data and performance data according to natural language processing technology to obtain attribute feature vectors and performance feature vectors.

[0034] The weight calculation module is used to perform weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weight and the performance feature weight.

[0035] The scoring module is used to calculate the comprehensive score of the attribute feature vector, the performance feature vector, the attribute feature weight, and the performance feature weight according to the weighted summation method, so as to obtain the assessment score;

[0036] The scoring output module is used to output the assessment score to the user terminal.

[0037] Furthermore, the data acquisition module includes:

[0038] An unstructured attribute data acquisition submodule is used to acquire unstructured attribute data corresponding to the assessed identifier from the system database.

[0039] The text conversion submodule is used to perform text conversion operations on the unstructured attribute data to obtain the attribute data.

[0040] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0041] It includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor executes the computer-readable instructions to implement the steps of the automatic assessment method described above.

[0042] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0043] The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the automatic assessment method described above.

[0044] This application provides an automatic assessment method, comprising: receiving an assessment request carrying an assessment identifier sent by a user terminal; reading a system database and obtaining attribute data and performance data corresponding to the assessment identifier from the system database; performing feature extraction operations on the attribute data and performance data using natural language processing technology to obtain attribute feature vectors and performance feature vectors; performing weight calculation operations on the attribute feature vectors and performance feature vectors to obtain attribute feature weights and performance feature weights; calculating a comprehensive score of the attribute feature vectors, performance feature vectors, attribute feature weights, and performance feature weights using a weighted summation method to obtain an assessment score; and outputting the assessment score to the user terminal. Compared with the prior art, this application greatly improves the efficiency and accuracy of assessment; at the same time, by introducing natural language processing technology and weight calculation methods, it can more objectively reflect the true situation of the assessed object and reduce the bias caused by human factors. Attached Figure Description

[0045] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0047] Figure 2 This is a flowchart illustrating the implementation of the automatic assessment method provided in the embodiments of this application;

[0048] Figure 3 This is a schematic diagram of the structure of the automatic assessment device provided in the embodiments of this application;

[0049] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0051] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0052] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0053] like Figure 1 As shown, system architecture 100 may include terminal device 101, network 102, and server 103. Terminal device 101 may be a laptop 1011, tablet 1012, or mobile phone 1013. Network 102 is used as a medium to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0054] Users can use terminal device 101 to interact with server 103 via network 102 to receive or send messages, etc. Various communication client applications can be installed on terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0055] Terminal device 101 can be various electronic devices with a display screen and support web browsing. In addition to laptops 1011, tablets 1012, or mobile phones 1013, terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer, and a desktop computer, etc.

[0056] Server 103 can be a server that provides various services, such as a backend server that provides support for the pages displayed on terminal device 101.

[0057] It should be noted that the automatic assessment method provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the automatic assessment device is generally set in the server / terminal device.

[0058] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0059] Continue to refer to Figure 2 The diagram shows a flowchart of an embodiment of the automatic assessment method according to this application. The automatic assessment method includes steps S201, S202, S203, S204, S205, and S206.

[0060] In step S201, an assessment request carrying an assessment identifier is received from a user terminal.

[0061] In the embodiments of this application, the user terminal refers to a terminal device used to execute the image processing method for preventing document abuse provided in this application. The user terminal may be a mobile terminal such as a mobile phone, smartphone, laptop, digital broadcast receiver, PDA (personal digital assistant), PAD (tablet computer), PMP (portable multimedia player), navigation device, etc., as well as a fixed terminal such as a digital TV, desktop computer, etc. It should be understood that the examples of user terminals here are only for convenience of understanding and are not intended to limit this application.

[0062] In step S202, the system database is read, and the attribute data and performance data corresponding to the assessed identifier are obtained from the system database.

[0063] In this embodiment, upon receiving a request, the system accesses its internal database based on the provided assessment identifier. The database stores various information related to the assessment subject, including attribute data (such as static information like age, gender, position, and education) and performance data (such as dynamic performance like work performance, academic achievements, and attendance). The system retrieves the corresponding data based on the identifier for subsequent processing.

[0064] In step S203, feature extraction is performed on the attribute data and performance data using natural language processing techniques to obtain attribute feature vectors and performance feature vectors.

[0065] In this embodiment, the extracted data may be unstructured or contain a large amount of redundant information, therefore, Natural Language Processing (NLP) technology is needed to extract features from this data. NLP technology can identify and extract key information from the data, transforming it into a form that computers can understand and process, such as vectors or numerical values.

[0066] In this embodiment, for the unstructured attribute and performance data of the examinee, named entity recognition and keyword extraction algorithms in natural language processing are used to identify and extract key information that can characterize the attributes and performance of the examinee from data such as text, voice, and video. The extracted key information is then structured and represented by knowledge graph construction technology to form standardized attribute and performance feature vectors. The purpose of this step is to transform the attribute data and performance data into feature vectors that can be used for subsequent analysis and comparison.

[0067] In step S204, weight calculation operations are performed on the attribute feature vector and the performance feature vector to obtain the attribute feature weight and the performance feature weight.

[0068] In the embodiments of this application, different attributes or performances may have different importance to the assessment, so it is necessary to calculate the weight of each feature vector.

[0069] In this embodiment, after obtaining the structured attributes and performance feature vectors, a weighted summation method is used to calculate the comprehensive score. The quantified value of each feature is multiplied by its corresponding weight coefficient, and then summed to obtain the final assessment score.

[0070] In this embodiment of the application, in order to enhance the interpretability of the assessment results, the weighted summation process is decomposed step by step to form a reasoning chain for the scoring calculation.

[0071] In step S205, the comprehensive score of the attribute feature vector, performance feature vector, attribute feature weight, and performance feature weight is calculated using the weighted summation method to obtain the assessment score.

[0072] In this embodiment, after determining the feature vectors and their corresponding weights, the system uses a weighted summation method to calculate the overall score of the assessment subject. This method multiplies the value of each feature vector by its weight, and then sums all the products to obtain the final assessment score. This score reflects the overall performance of the assessment subject in terms of both attributes and results.

[0073] In step S206, the assessment score is output to the user terminal.

[0074] This application provides an automatic assessment method, comprising: receiving an assessment request carrying an assessment identifier sent by a user terminal; reading a system database to obtain attribute data and performance data corresponding to the assessment identifier; performing feature extraction on the attribute data and performance data using natural language processing technology to obtain attribute feature vectors and performance feature vectors; performing weight calculation on the attribute feature vectors and performance feature vectors to obtain attribute feature weights and performance feature weights; calculating a comprehensive score of the attribute feature vectors, performance feature vectors, attribute feature weights, and performance feature weights using a weighted summation method to obtain an assessment score; and outputting the assessment score to the user terminal. Compared with existing technologies, this application significantly improves the efficiency and accuracy of assessments; furthermore, by introducing natural language processing technology and weight calculation methods, it can more objectively reflect the true situation of the assessed object and reduce bias caused by human factors.

[0075] In some optional implementations of the embodiments of this application, the step of reading the system database and obtaining the attribute data and performance data corresponding to the assessed identifier from the system database specifically includes the following steps:

[0076] Retrieve unstructured attribute data corresponding to the assessed identifier from the system database;

[0077] Perform text conversion on unstructured attribute data to obtain attribute data.

[0078] In this embodiment of the application, unstructured attribute data associated with the identifier of the assessed object (such as employee ID, student number, etc.) is retrieved from the system database. Unstructured attribute data refers to data types that cannot be effectively retrieved and processed directly through traditional database query languages ​​(such as SQL). They may exist in the form of text, images, audio, video, etc.

[0079] In this embodiment, the data associated with the identifier of the assessed object may be stored in various forms in the database, including but not limited to text fields in tables, JSON or XML documents in document databases, and even metadata of image or video files. The system needs to be able to identify and retrieve this unstructured attribute data.

[0080] In this embodiment of the application, unstructured attribute data is diverse in form, making direct processing very difficult. Therefore, it is usually necessary to convert it into text form for text analysis, feature extraction, and other operations. Specifically:

[0081] Text extraction: For unstructured attribute data that is already in text form (such as documents, emails, etc.), this step is simply a reading and extraction operation. However, for non-text data such as images, audio, or video, specific technologies (such as optical character recognition (OCR), speech recognition, etc.) are required to convert them into text.

[0082] Data cleaning: The transformed text data contains noise, irrelevant information, or inconsistent formatting. Therefore, data cleaning is necessary to remove these interfering factors and ensure the accuracy and consistency of the data.

[0083] Structured processing: The cleaned text data still exists in an unstructured form (such as long paragraphs of text). To facilitate subsequent processing and analysis, the system needs to further structure this data, for example, by using natural language processing techniques such as word segmentation, part-of-speech tagging, and named entity recognition to extract key information and organize it into structured attribute data.

[0084] In this embodiment, the system can retrieve unstructured attribute data related to the assessed object from the system database and transform it into attribute data that can be used in subsequent assessment processes. This provides a foundation for subsequent steps such as text analysis, feature extraction, weight calculation, and comprehensive scoring.

[0085] In some optional implementations of the embodiments of this application, after the steps of reading the system database and obtaining the attribute data and performance data corresponding to the assessed identifier from the system database, the following steps are further included:

[0086] Based on data exploration and statistical analysis, determine whether there are missing data in the attribute and performance data;

[0087] If there are missing data in the attribute data and performance data, the missing data will be imputed using the K-nearest neighbor algorithm based on similarity.

[0088] If there is no missing data in the attribute data and presentation data, no data imputation operation will be performed.

[0089] In this embodiment of the application, data exploration involves preliminary visualization and descriptive statistical analysis of the data. By drawing charts such as histograms, box plots, and scatter plots, and calculating statistics such as mean, median, and standard deviation, the distribution and characteristics of the data can be intuitively understood, and the existence of outliers or missing values ​​can be preliminarily determined.

[0090] In this application embodiment, in addition to data exploration, more specific statistical analysis methods can be used to detect missing data. For example, the proportion of non-null values ​​for each attribute can be calculated; if the proportion of non-null values ​​for a certain attribute is significantly lower than that of other attributes, then missing data may exist. Furthermore, statistical tests (such as chi-square test, T-test, etc.) can be used to detect whether the data is complete.

[0091] In this embodiment of the application, when it is determined that there is missing data in the dataset, appropriate strategies need to be adopted to fill in these missing values ​​to ensure the integrity of the data and the effectiveness of subsequent analysis. Specifically:

[0092] The K-Nearest Neighbors (KNN) algorithm is based on the assumption that in the feature space, if the attribute values ​​of a sample's K nearest neighbors (i.e., the K most similar samples) are known, then the missing attribute value of the sample can be estimated using the corresponding attribute values ​​of these K neighbors. Specifically, the mean, median, or mode of the corresponding attribute values ​​of these K neighbors can be chosen as the imputation value.

[0093] Data imputation process: First, the system needs to determine the value of K (i.e., the number of neighbors), which depends on the specific data and experimental results. Then, for each sample containing missing values, the system finds its K nearest neighbors in the feature space. Finally, the system estimates and imputes the missing values ​​of the sample based on the corresponding attribute values ​​of these neighbors.

[0094] In this embodiment, to address the issues of missing data and noise interference, the distribution of missing data and the type of noisy data are first determined through data exploration and statistical analysis. For missing data, a similarity-based K-nearest neighbor algorithm is used for data imputation, estimating the missing value based on the values ​​of complete data points similar to the missing data point. For noisy data, an isolated forest algorithm is used to detect and remove outliers, and data smoothing techniques are employed to repair data affected by noise.

[0095] In this embodiment, determining data completeness through data exploration and statistical analysis, and performing data interpolation using the K-nearest neighbor algorithm as needed, are crucial steps to ensure data quality and the effectiveness of subsequent analysis. These steps provide a reliable data foundation for the subsequent evaluation process.

[0096] In some optional implementations of the embodiments of this application, the steps of performing weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weight and the performance feature weight specifically include the following steps:

[0097] The importance of attribute feature vectors and performance feature vectors is determined based on the assessment indicator system.

[0098] The importance is calculated using the analytic hierarchy process (AHP) to obtain the attribute feature weights and performance feature weights.

[0099] In this embodiment, the importance of each attribute and performance characteristic is determined according to the assessment indicator system, and the weight coefficient of each characteristic is calculated using the analytic hierarchy process (AHP). During the weight calculation process, correlation analysis is used to determine the degree of correlation between characteristics, and highly correlated characteristics are merged or removed to eliminate information redundancy. Simultaneously, fairness constraints are introduced to control the distribution range of the weight coefficients and avoid unfair assessments caused by weight imbalances.

[0100] In some optional implementations of the embodiments of this application, the step of calculating the comprehensive score of the attribute feature vector, performance feature vector, attribute feature weight, and performance feature weight according to the weighted summation method to obtain the assessment score specifically includes the following steps:

[0101] The score interval data is calculated based on the weighted summation method to determine the attribute feature weights and performance feature weights.

[0102] Obtain the machine learning prediction model corresponding to the score interval data;

[0103] The attribute feature vector and performance feature vector are input into the machine learning prediction model to perform score prediction and obtain the assessment score.

[0104] In this embodiment, to comprehensively evaluate the attributes and performance of the assessed object, we need to perform a weighted summation of each feature. The weighted summation method assigns a weight to each feature, multiplies the value of each feature by its corresponding weight, and finally sums all the products to obtain the overall score. In this process, the allocation of weights is typically based on expert experience, historical data, or statistical analysis results to reflect the importance of different features in the assessment.

[0105] In this embodiment, for attribute features and performance features, we can divide them into different score intervals based on the weighted summation result. These intervals can be determined based on actual business needs or statistical analysis. For example, the scores can be divided into several levels such as excellent, good, average, and poor, or they can be divided according to specific numerical ranges.

[0106] In this embodiment, after determining the score interval data, the next step is to select or construct a machine learning prediction model corresponding to these data. This model will be used to predict the assessment score based on the attribute feature vector and the performance feature vector, specifically:

[0107] Model selection: Depending on the characteristics of the data and the specific requirements of the assessment, we can choose different types of machine learning models. For example, if the data is linear, we can choose a linear regression model; if there are complex nonlinear relationships between the data, we can choose models such as support vector machines (SVM), random forests, or neural networks.

[0108] Model Training: After selecting a model, we need to train it using historical data or a training dataset. This involves splitting the data into training and test sets, using the training set to optimize the model's parameters, and then using the test set to evaluate the model's performance.

[0109] Model Evaluation: To ensure the accuracy and reliability of the model, we need to evaluate it. This can be done by calculating metrics such as accuracy, recall, and F1 score. If the model's performance does not meet the requirements, we need to adjust the model or choose another model.

[0110] In this embodiment, the score interval data is calculated by weighted summation, and the corresponding machine learning prediction model is obtained. The attribute feature vector and performance feature vector are then input into the model for score prediction, which can realize an automated and intelligent assessment process and improve the efficiency and accuracy of the assessment.

[0111] In some optional implementations of the embodiments of this application, the step of outputting the assessment score to the user terminal specifically includes the following steps:

[0112] The bar chart displays the attribute data and performance scores.

[0113] The line graph shows the growth trend of the assessed person in different assessment cycles.

[0114] The radar chart illustrates the balance of the assessee's performance across different dimensions.

[0115] In this embodiment, to improve the visualization of assessment results, a visualization dashboard is designed. A bar chart displays the scores for various attributes and performance, a line chart shows the growth trend of the assessed individual across different assessment periods, and a radar chart shows the balance of the assessed individual's performance across different dimensions. Simultaneously, an interactive visualization exploration function is provided, allowing users to interact with the visualization components through mouse hovering, clicking, and other operations to obtain more detailed information about the assessment results.

[0116] In some optional implementations of this application's embodiments, a rule-based decision tree algorithm is used to construct the assessment decision model to address the interpretability requirements of the assessment model. The decision tree model represents assessment rules in a tree structure, where each non-leaf node represents an assessment attribute, and each leaf node corresponds to an assessment decision result. Assessment decision paths are generated by recursively partitioning attributes and performance characteristics. The decision tree model has good interpretability and can generate decision rules in the form of "If an attribute takes the value A, and a performance score is greater than B, then the assessment result is C," making it easy for assessors and assessees to understand and accept.

[0117] In some optional implementations of this application's embodiments, considering the potential for new assessment requirements and data changes during the assessment process, incremental learning techniques are employed to continuously optimize the assessment model. When new assessment data is added, the model parameters are dynamically updated using the incremental learning algorithm, enabling the model to adapt to changes in data distribution. Simultaneously, a model performance monitoring mechanism is implemented; when model performance significantly declines, a model retraining process is triggered to ensure the accuracy and stability of the assessment results.

[0118] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0119] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0120] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0121] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0122] Further reference Figure 3 As a response to the above Figure 2 To implement the method shown, this application provides an embodiment of an automatic assessment device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0123] like Figure 3 As shown, the automatic assessment device 200 of this application embodiment includes:

[0124] The request receiving module 210 is used to receive an assessment request sent by the user terminal, which carries an assessment identifier.

[0125] Data acquisition module 220 is used to read the system database and obtain attribute data and performance data corresponding to the assessed identifier from the system database;

[0126] The feature extraction module 230 is used to perform feature extraction operations on attribute data and performance data according to natural language processing technology to obtain attribute feature vectors and performance feature vectors.

[0127] The weight calculation module 240 is used to perform weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weight and the performance feature weight.

[0128] The scoring module 250 is used to calculate the comprehensive score of attribute feature vector, performance feature vector, attribute feature weight, and performance feature weight according to the weighted summation method, so as to obtain the assessment score;

[0129] The scoring output module 260 is used to output the assessment score to the user terminal.

[0130] In this embodiment, an automatic assessment device 200 is provided, comprising: a request receiving module 210 for receiving an assessment request carrying an assessment identifier sent by a user terminal; a data acquisition module 220 for reading a system database and acquiring attribute data and performance data corresponding to the assessment identifier; a feature extraction module 230 for performing feature extraction operations on the attribute data and performance data using natural language processing technology to obtain attribute feature vectors and performance feature vectors; a weight calculation module 240 for performing weight calculation operations on the attribute feature vectors and performance feature vectors to obtain attribute feature weights and performance feature weights; a score calculation module 250 for calculating a comprehensive score of the attribute feature vectors, performance feature vectors, attribute feature weights, and performance feature weights using a weighted summation method to obtain an assessment score; and a score output module 260 for outputting the assessment score to the user terminal. Compared with the prior art, this application greatly improves the efficiency and accuracy of assessment; at the same time, by introducing natural language processing technology and weight calculation methods, it can more objectively reflect the true situation of the assessed object and reduce the bias caused by human factors.

[0131] In some optional implementations of the embodiments of this application, the above-mentioned data acquisition module includes:

[0132] The unstructured attribute data acquisition submodule is used to retrieve unstructured attribute data corresponding to the assessed identifier from the system database.

[0133] The text conversion submodule is used to perform text conversion operations on unstructured attribute data to obtain attribute data.

[0134] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of a computer device according to an embodiment of this application.

[0135] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected via a system bus. It should be noted that only the computer device 300 with components 310-330 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0136] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0137] The memory 310 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 may be an internal storage unit of the computer device 300, such as the hard disk or memory of the computer device 300. In other embodiments, the memory 310 may also be an external storage device of the computer device 300, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Of course, the memory 310 may also include both internal storage units and external storage devices of the computer device 300. In this embodiment, the memory 310 is typically used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions for automatic assessment methods. Furthermore, the memory 310 can also be used to temporarily store various types of data that have been output or will be output.

[0138] In some embodiments, the processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 320 is typically used to control the overall operation of the computer device 300. In this embodiment, the processor 320 is used to execute computer-readable instructions stored in the memory 310 or to process data, for example, to execute computer-readable instructions for the automatic assessment method.

[0139] The network interface 330 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 300 and other electronic devices.

[0140] The computer equipment provided in this application greatly improves the efficiency and accuracy of the assessment; at the same time, by introducing natural language processing technology and weight calculation methods, it can more objectively reflect the true situation of the assessed person and reduce the bias caused by human factors.

[0141] This application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the automatic assessment method described above.

[0142] The computer-readable storage medium provided in this application greatly improves the efficiency and accuracy of the assessment; at the same time, by introducing natural language processing technology and weight calculation methods, it can more objectively reflect the true situation of the assessed person and reduce the bias caused by human factors.

[0143] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0144] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. An automatic assessment method, characterized in that, Includes the following steps: Receive assessment requests sent by user terminals, which carry an assessment identifier. Read the system database and obtain the attribute data and performance data corresponding to the assessed identifier from the system database; Natural language processing techniques are used to perform feature extraction on the attribute data and performance data to obtain attribute feature vectors and performance feature vectors. Perform weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weight and the performance feature weight; The comprehensive score of the attribute feature vector, the performance feature vector, the attribute feature weight, and the performance feature weight is calculated using the weighted summation method to obtain the assessment score. The assessment score is output to the user terminal.

2. The automatic assessment method according to claim 1, characterized in that, The step of reading the system database and obtaining the attribute data and performance data corresponding to the assessed identifier from the system database specifically includes the following steps: Obtain unstructured attribute data corresponding to the assessed identifier from the system database; The unstructured attribute data is converted into text to obtain the attribute data.

3. The automatic assessment method according to claim 1, characterized in that, After the step of reading the system database and obtaining the attribute data and performance data corresponding to the assessed identifier from the system database, the following steps are also included: Based on data exploration and statistical analysis, determine whether there is any missing data in the attribute data and the performance data; If there are missing data in the attribute data and the performance data, then the missing data is imputed using the K-nearest neighbor algorithm based on similarity. If there is no missing data in the attribute data and the performance data, the data imputation operation will not be performed.

4. The automatic assessment method according to claim 1, characterized in that, The step of performing weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weights and performance feature weights specifically includes the following steps: The importance of the attribute feature vector and the performance feature vector is determined according to the assessment indicator system; The importance level is calculated using the analytic hierarchy process (AHP) to obtain the attribute feature weights and performance feature weights.

5. The automatic assessment method according to claim 1, characterized in that, The step of calculating the comprehensive score of the attribute feature vector, the performance feature vector, the attribute feature weights, and the performance feature weights using a weighted summation method to obtain the assessment score specifically includes the following steps: The score interval data of the attribute feature weights and the performance feature weights are calculated using the weighted summation method. Obtain the machine learning prediction model corresponding to the score interval data; The attribute feature vector and the performance feature vector are input into the machine learning prediction model to perform a score prediction operation, thereby obtaining the assessment score.

6. The automatic assessment method according to claim 1, characterized in that, The step of outputting the assessment score to the user terminal specifically includes the following steps: The attribute data and the scores of the performance data are displayed using a bar chart; The line graph shows the growth trend of the assessed person in different assessment cycles. The radar chart illustrates the balance of the assessee's performance across different dimensions.

7. An automatic assessment device, characterized in that, include: The request receiving module is used to receive assessment requests sent by user terminals, which carry an assessment identifier. The data acquisition module is used to read the system database and obtain attribute data and performance data corresponding to the assessed identifier from the system database; The feature extraction module is used to perform feature extraction operations on the attribute data and performance data according to natural language processing technology to obtain attribute feature vectors and performance feature vectors. The weight calculation module is used to perform weight calculation operations on the attribute feature vector and the performance feature vector to obtain the attribute feature weight and the performance feature weight. The scoring module is used to calculate the comprehensive score of the attribute feature vector, the performance feature vector, the attribute feature weight, and the performance feature weight according to the weighted summation method, so as to obtain the assessment score; The scoring output module is used to output the assessment score to the user terminal.

8. The automatic assessment device according to claim 7, characterized in that, The data acquisition module includes: An unstructured attribute data acquisition submodule is used to acquire unstructured attribute data corresponding to the assessed identifier from the system database. The text conversion submodule is used to perform text conversion operations on the unstructured attribute data to obtain the attribute data.

9. A computer device, comprising a memory and a processor, characterized in that, The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, it implements the steps of the automatic assessment method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the automatic assessment method as described in any one of claims 1 to 6.

Images