Performance form creation method and system of human resource system

Abstract

The invention discloses a performance form creation method and system of a human resource system, belongs to the technical field of artificial intelligence, and can conveniently generate performance forms suitable for assessment requirements of different departments. Comprising the following steps: acquiring historical multi-version performance form data of a first department and actual assessment scene information corresponding to each version; performing text analysis on the historical multi-version performance form data, extracting text fragments with the occurrence frequency reaching a set threshold value, converting the text fragments into structured data, and recording the structured data as a historical key data set; acquiring real-time business demand data; performing comparative analysis on the historical key data set and the real-time business demand data, and judging the matching degree of the historical key data set and the real-time business demand data; if the matching degree is lower than a set threshold value, optimizing and adjusting the historical key data set; and dynamically generating a performance form adapted to the new business scene of the first department according to the optimized and adjusted data in combination with a preset form layout rule.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a performance form creation method and system for a human resources system. Background Art

[0002] With the rapid development of modern enterprises and the increasingly complex competitive environment, performance management has become one of the core contents of enterprise human resource management. Performance management can help enterprises effectively improve employee work efficiency, optimize resource allocation, and enhance the overall competitiveness of the organization. In the performance management system, performance forms, as an important tool, have the important functions of recording assessment content, quantifying employee performance, and providing feedback on assessment results.

[0003] However, with the continuous development of the performance management concept, the requirements of enterprises for performance appraisal in practical applications are becoming increasingly diversified. Different enterprises often have different performance appraisal processes and rules due to their differences in industry background, organizational structure, and development strategy. Even in the same enterprise, the performance appraisal methods of different departments, positions, and employee groups may vary significantly. For example, the sales department may need quantitative appraisal based on performance data, while the R&D department may pay more attention to the qualitative evaluation of project quality and innovation capabilities. Therefore, how to flexibly design and generate performance forms that adapt to diverse appraisal needs has become an important challenge in enterprise human resource management.

[0004] The disclosure of the above background technology content is only used to assist in understanding the concept and technical solution of the present invention. It does not necessarily belong to the prior art of this patent application. In the absence of clear evidence that the above content has been disclosed on the filing date of this patent application, the above background technology should not be used to evaluate the novelty and creativity of the present application. Summary of the invention

[0005] The present application provides a method for creating a performance form for a human resources system, which can facilitate the generation of performance forms suitable for the assessment needs of different departments.

[0006] To achieve the above objectives, the present application discloses the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for creating a performance form in a human resources system, comprising the following steps:

[0008] Obtain the historical multi-version performance form data of the first department and the actual assessment scenario information corresponding to each version;

[0009] Perform text analysis on historical multi-version performance form data to extract key indicator text segments, process node text segments, and association relationship text segments whose occurrence frequency reaches the set threshold;

[0010] Use natural language processing technology to convert key indicator text fragments, process node text fragments, and association relationship text fragments into structured data and record them as historical key data sets;

[0011] Obtain real-time business demand data;

[0012] Compare and analyze historical key data sets with real-time business demand data, and determine the degree of match between the two based on a predefined similarity algorithm;

[0013] If the matching degree is lower than the set threshold, the preset machine learning model is used to optimize and adjust the historical key data set;

[0014] Based on the optimized and adjusted data and combined with the preset form layout rules, a performance form that adapts to the new business scenarios of the first department is dynamically generated.

[0015] In the embodiment of this application, we first obtain historical multi-version performance form data and the actual assessment scenario information corresponding to each version. These historical data contain the rich experience accumulated by the department in the past when conducting performance assessments for different business objects at different business stages, covering a variety of assessment methods, indicator settings, etc., laying the foundation for the subsequent construction of adaptive forms.

[0016] Then, we perform text analysis on the historical multi-version performance form data to extract key indicator text fragments, process node text fragments, and associated relationship text fragments whose frequency reaches the set threshold. For example, key indicators such as the performance completion rate that frequently appears in past assessments of the sales department, and related indicators such as the on-time delivery rate of projects in the R&D department can all be extracted. By extracting these core elements, we can capture the performance assessment characteristics of each department and position and extract a representative assessment model.

[0017] Then, we use natural language processing technology to further transform them into structured data and record them as a collection of historical key data. We can organize the originally messy and unstructured historical form data into a standardized form that is convenient for subsequent analysis, comparison and use, and dig out the common assessment mode and key elements hidden in the historical data. Acquiring real-time business demand data can keenly capture the changes in the current business of the department and provide a realistic basis for timely adjustment of performance forms.

[0018] Compare and analyze the organized historical key data set with the real-time business demand data, and determine the degree of match between the two based on the predefined similarity algorithm. You can consider the fit between historical data and real-time needs from multiple dimensions, and accurately determine whether the current historical data can meet real-time business needs. If the match is lower than the set threshold, it means that historical experience is not enough to be directly applied to the current business scenario. At this time, based on the existing historical data and real-time business demand data, the preset machine learning model is used to optimize and adjust the historical key data set. Then, based on the optimized and adjusted data and the established layout rules, the optimized key indicators, process nodes and other elements are reasonably presented on the form, and a performance form that adapts to the new business scenario is dynamically generated to ensure that the generated performance form can reflect new needs while retaining the applicability of historical experience.

[0019] If the matching degree is high, it means that the historical data is already well adapted to the current needs and no further adjustment is needed. Through this real-time monitoring mechanism, the assessment form can timely adapt to new needs caused by business adjustments or organizational changes.

[0020] In this way, it is easy to generate performance forms for the assessment needs of different departments, ensuring that the generated forms are in line with the department's habits of display and use, and closely fit the actual assessment needs of the current business, and realize flexible design and generation of adaptive performance forms according to different business scenarios, effectively solving the problem of large differences in performance assessment methods among different companies and different departments, positions and employee groups in the same company.

[0021] In some possible implementations of the first aspect, the historical multi-version performance form data includes performance forms from multiple different periods and different business lines, and the actual assessment scenario information includes the organizational structure, business objectives, and the category of assessors.

[0022] In some possible implementations of the first aspect, the step of acquiring the real-time business demand data includes:

[0023] Use database connection technology and pre-developed API interfaces to establish connections with the databases of various business systems within the enterprise, including project management systems, ERP systems, CRM systems, and human resource management systems;

[0024] By analyzing the data of each business system, determine the key data sources that reflect real-time business needs and the unique identifiers of the data in each data source;

[0025] Periodically monitor data changes in key data sources through database triggers or scheduled tasks;

[0026] When data update is detected, the updated data is extracted through the API interface according to the pre-set data collection rules;

[0027] Clean the collected data, remove duplicate, erroneous and incomplete data, and integrate data from different data sources according to preset data association rules;

[0028] Update the cleaned and integrated data to the preset business demand database;

[0029] Retrieve business demand data from the business demand database as real-time business demand data. In this way, the latest business demand data can be obtained in a timely manner, ensuring the real-time and accuracy of the data, and providing a reliable data basis for the dynamic generation of performance forms. In addition, cleaning and integrating the collected data can remove invalid data, improve data quality, and reduce form generation errors or inaccuracies caused by data problems. In addition, integrating data from different business systems breaks down data silos, enabling a more comprehensive understanding of the company's business status, thereby generating performance forms that better meet actual business needs.

[0030] In some possible implementations of the first aspect, the specific formula of the predefined similarity algorithm is as follows:

[0031]

[0032] in:

[0033] h i : represents the i-th keyword in the historical keyword set;

[0034] r j : represents the jth keyword in the real-time business requirement set;

[0035] S: indicates the comprehensive matching degree between the keywords in the two sets. The larger the value, the higher the matching degree between the two sets.

[0036] n: represents the total number of historical keywords in the set;

[0037] m: indicates the total number of real-time demand keywords in the set;

[0038] w ij : Weight, indicating historical keywords h i Keywords related to real-time business needs j The strength of the association between them, the larger the weight value, the closer the relationship between them;

[0039] f(h i ,r j ): matching function, used to determine the keyword h i With keyword r j Whether it matches or not is defined as follows:

[0040]

[0041] In some possible implementations of the first aspect, the preset machine learning model is a classification model based on a decision tree algorithm. When constructing the preset machine learning model, key indicator text fragments, process node text fragments, and association relationship text fragments in the historical key data set are used as feature vectors, and the adaptation effects of performance forms in past actual business scenarios are used as label data for training. Among them, the model based on the decision tree algorithm can automatically learn the rules and patterns in historical data, classify the performance form requirements in different business scenarios, and provide intelligent decision support for subsequent optimization and adjustment. In addition, training with the adaptation effects in past actual business scenarios as label data enables the model to make full use of the company's historical experience, improves the accuracy and reliability of the model, and thereby improves the adaptability of the performance form.

[0042] In some possible implementations of the first aspect, the specific training process of the preset machine learning model includes:

[0043] Preprocess the historical data, convert text features into numerical features using one-hot encoding, use the information gain algorithm to screen out features that have a significant impact on performance form adaptation, and construct node branches of the decision tree;

[0044] By recursively partitioning the training data set, the structure of the decision tree is continuously optimized so that it can accurately classify the performance form demand patterns in different business scenarios;

[0045] When the similarity score is lower than the set threshold, the current real-time business demand data is also converted into the feature vector form required by the decision tree model and input into the trained model. The model makes judgments step by step from the root node according to the path of the feature value in the decision tree, and finally classifies the current business scenario into the corresponding performance form demand category. Based on this category information, optimization and adjustment strategies are extracted from past well-adapted performance form cases to optimize the historical key data set. The optimization and adjustment strategies include weight adjustment of key indicators, increase or decrease of process nodes, and reconfiguration of association relationships.

[0046] In a second aspect, an embodiment of the present application provides a performance form creation system for a human resources system, including:

[0047] The first acquisition module is used to obtain the historical multi-version performance form data of the first department and the actual assessment scenario information corresponding to each version;

[0048] The first parsing module is used to perform text parsing on the historical multi-version performance form data to extract key indicator text segments, process node text segments, and association relationship text segments whose occurrence frequencies reach a set threshold;

[0049] A first conversion module converts the key indicator text fragment, the process node text fragment, and the association relationship text fragment into structured data using natural language processing technology, and records them as a historical key data set;

[0050] The second acquisition module is used to acquire real-time business demand data;

[0051] A first comparison module is used to compare and analyze the historical key data set with the real-time business demand data, and determine the matching degree between the two according to a predefined similarity algorithm;

[0052] A first adjustment module is used to optimize and adjust the historical key data set using a preset machine learning model if the matching degree is lower than a set threshold;

[0053] The form generation module is used to dynamically generate performance forms that adapt to the new business scenarios of the first department based on the optimized and adjusted data and combined with preset form layout rules.

[0054] In some possible implementations of the second aspect, the historical multi-version performance form data includes performance forms from multiple different periods and different business lines, and the actual assessment scenario information includes the organizational structure, business objectives, and the category of assessors.

[0055] In some possible implementations of the second aspect, the second acquisition module is specifically used to: establish a connection with the databases of various business systems within the enterprise using database connection technology and a pre-developed API interface, the business systems including a project management system, an ERP system, a CRM system, and a human resources management system; determine the key data sources that reflect real-time business needs and the unique identifier of the data in each data source through data analysis of each business system; periodically monitor data changes in key data sources through database triggers or scheduled tasks; when data updates are detected, extract the updated data through the API interface according to pre-set data collection rules; clean the collected data to remove duplicate, erroneous and incomplete data, and integrate data from different data sources according to preset data association rules; update the cleaned and integrated data to a preset business needs database; and retrieve business needs data from the business needs database as real-time business needs data.

[0056] In some possible implementations of the second aspect, the specific formula of the predefined similarity algorithm is as follows:

[0057]

[0058] in:

[0059] h i: represents the i-th keyword in the historical keyword set;

[0060] r j : represents the jth keyword in the real-time business requirement set;

[0061] S: indicates the comprehensive matching degree between the keywords in the two sets. The larger the value, the higher the matching degree between the two sets.

[0062] n: represents the total number of historical keywords in the set;

[0063] m: indicates the total number of real-time demand keywords in the set;

[0064] w ij : Weight, indicating historical keywords h i Keywords related to real-time business needs j The strength of the association between them, the larger the weight value, the closer the relationship between them;

[0065] f(h i ,r j ): matching function, used to determine the keyword h i With keyword r j Whether it matches or not is defined as follows:

[0066]

[0067] In some possible implementations of the second aspect, the preset machine learning model is a classification model based on a decision tree algorithm. When constructing the preset machine learning model, key indicator text fragments, process node text fragments, and association relationship text fragments in the historical key data set are used as feature vectors, and the adaptation effects of performance forms in past actual business scenarios are used as label data for training.

[0068] In some possible implementations of the second aspect, the specific training process of the preset machine learning model includes:

[0069] Preprocess the historical data, convert text features into numerical features using one-hot encoding, use the information gain algorithm to screen out features that have a significant impact on performance form adaptation, and construct node branches of the decision tree;

[0070] By recursively partitioning the training data set, the structure of the decision tree is continuously optimized so that it can accurately classify the performance form demand patterns in different business scenarios;

[0071] When the similarity score is lower than the set threshold, the current real-time business demand data is also converted into the feature vector form required by the decision tree model and input into the trained model. The model makes judgments step by step from the root node according to the path of the feature value in the decision tree, and finally classifies the current business scenario into the corresponding performance form demand category. Based on this category information, optimization and adjustment strategies are extracted from past well-adapted performance form cases to optimize the historical key data set. The optimization and adjustment strategies include weight adjustment of key indicators, increase or decrease of process nodes, and reconfiguration of association relationships.

[0072] In a third aspect, an embodiment of the present application provides an electronic device, comprising one or more processors; a storage device on which one or more programs are stored; when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any technical solution of the first aspect.

[0073] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any technical solution of the first aspect is implemented.

[0074] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in any technical solution of the first aspect.

[0075] Among them, the technical effects brought about by any design method in the second to fifth aspects can refer to the technical effects brought about by different design methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0077] Figure 1 A flowchart of a method for creating a performance form in a human resources system provided in some embodiments of the present application;

[0078] Figure 2 A schematic diagram of the structure of a performance form creation system for a human resources system provided in some embodiments of the present application;

[0079] Figure 3It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0080] Specific embodiments of the present invention will now be mentioned in detail. Although the present invention is described in conjunction with these specific embodiments, it should be appreciated that it is not intended to limit the present invention to these specific embodiments. On the contrary, these embodiments are intended to cover substitutions, changes or equivalent embodiments that may be included in the spirit and scope of the invention defined by the claims. In the following description, a large number of specific details are set forth in order to provide a comprehensive understanding of the present invention. The present invention may be implemented without some or all of these specific details.

[0081] When used in conjunction with "including," "methods comprising," or similar language in this specification and the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Unless defined otherwise, 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 invention belongs.

[0082] Application Overview: With the rapid development of modern enterprises and the increasingly complex competitive environment, performance management has become one of the core contents of enterprise human resource management. Performance management can help enterprises effectively improve employee work efficiency, optimize resource allocation, and enhance the overall competitiveness of the organization. In the performance management system, performance forms, as an important tool, bear the important functions of recording assessment content, quantifying employee performance and providing feedback on assessment results.

[0083] However, with the continuous development of the performance management concept, the requirements of enterprises for performance appraisal in practical applications are becoming increasingly diversified. Different enterprises often have different performance appraisal processes and rules due to their differences in industry background, organizational structure, and development strategy. Even in the same enterprise, the performance appraisal methods of different departments, positions, and employee groups may vary significantly. For example, the sales department may need quantitative appraisal based on performance data, while the R&D department may pay more attention to the qualitative evaluation of project quality and innovation capabilities. Therefore, how to flexibly design and generate performance forms that adapt to diverse appraisal needs has become an important challenge in enterprise human resource management.

[0084] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows: a performance form creation method for a human resources system is provided, comprising the following steps: obtaining historical multi-version performance form data of the first department and the actual assessment scenario information corresponding to each version; performing text parsing on the historical multi-version performance form data, and extracting key indicator text fragments, process node text fragments, and association relationship text fragments whose occurrence frequency reaches a set threshold; using natural language processing technology to convert key indicator text fragments, process node text fragments, and association relationship text fragments into structured data, recorded as a historical key data set; obtaining real-time business demand data; comparing and analyzing the historical key data set with the real-time business demand data, and judging the degree of match between the two based on a predefined similarity algorithm; if the degree of match is lower than the set threshold, using a preset machine learning model to optimize and adjust the historical key data set; based on the optimized and adjusted data, combined with preset form layout rules, dynamically generating a performance form that adapts to the new business scenario of the first department.

[0085] This method first obtains historical multi-version performance form data and the actual assessment scenario information corresponding to each version. These historical data contain the rich experience accumulated by the department in conducting performance assessments for different business objects at different business stages in the past, covering a variety of assessment methods, indicator settings, etc., laying the foundation for the subsequent construction of adaptive forms.

[0086] Then, the text of the historical multi-version performance form data is parsed to extract the key indicator text fragments, process node text fragments, and association relationship text fragments whose occurrence frequency reaches the set threshold.

[0087] For example, key indicators such as performance completion rate that frequently appeared in past assessments of the sales department and relevant indicators such as the on-time delivery rate of projects in the R&D department can be extracted. By extracting these core elements, the performance assessment characteristics of each department and position can be captured, and a representative assessment model can be extracted.

[0088] Then, we use natural language processing technology to further transform them into structured data and record them as a collection of historical key data. We can organize the originally messy and unstructured historical form data into a standardized form that is convenient for subsequent analysis, comparison and use, and dig out the common assessment mode and key elements hidden in the historical data. Acquiring real-time business demand data can keenly capture the changes in the current business of the department and provide a realistic basis for timely adjustment of performance forms.

[0089] Compare and analyze the organized historical key data set with the real-time business demand data, and determine the degree of match between the two based on the predefined similarity algorithm. You can consider the fit between historical data and real-time needs from multiple dimensions, and accurately determine whether the current historical data can meet real-time business needs. If the match is lower than the set threshold, it means that historical experience is not enough to be directly applied to the current business scenario. At this time, based on the existing historical data and real-time business demand data, the preset machine learning model is used to optimize and adjust the historical key data set. Then, based on the optimized and adjusted data and the established layout rules, the optimized key indicators, process nodes and other elements are reasonably presented on the form, and a performance form that adapts to the new business scenario is dynamically generated to ensure that the generated performance form can reflect new needs while retaining the applicability of historical experience.

[0090] If the match is high, it means that the historical data is already well adapted to current needs and no further adjustment is needed. Through this real-time monitoring mechanism, the assessment form can promptly adapt to new needs caused by business adjustments or organizational changes. For example, based on the higher requirements of real-time business for innovation capabilities, the weights of innovation-related indicators in the R&D department's performance form can be adjusted through machine learning models.

[0091] In this way, it is easy to generate performance forms for the assessment needs of different departments, ensuring that the generated forms are in line with the department's habits of display and use, and closely fit the actual assessment needs of the current business, and realize flexible design and generation of adaptive performance forms according to different business scenarios, effectively solving the problem of large differences in performance assessment methods among different companies and different departments, positions and employee groups in the same company.

[0092] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced in conjunction with the accompanying drawings. Figure 1 The present application embodiment provides a method for creating a performance form in a human resources system, comprising the following steps:

[0093] S101: Obtaining historical multi-version performance form data of the first department and actual assessment scenario information corresponding to each version;

[0094] Specifically, in some embodiments, the historical multi-version performance form data includes performance forms of multiple different periods and different business lines, and the actual assessment scenario information includes the organizational structure, business objectives, and the categories of assessors. Exemplarily, in some embodiments, the historical multi-version performance form data and the actual assessment scenario information corresponding to each version can be actively obtained by the execution subject of the performance form creation method of the human resources system from a preset database, and can be manually uploaded to the execution subject by the human resources department.

[0095] S102: Perform text parsing on historical multi-version performance form data to extract key indicator text segments, process node text segments, and association relationship text segments whose occurrence frequencies reach a set threshold;

[0096] S103: using natural language processing technology to convert key indicator text fragments, process node text fragments, and association relationship text fragments into structured data, which are recorded as a historical key data set;

[0097] S104: Acquire real-time business demand data;

[0098] Real-time business demand data includes but is not limited to: current business objectives, employee position distribution, and assessment cycle requirements.

[0099] Specifically, in some embodiments, real-time business demand data may be obtained by following the steps below:

[0100] The first step is to use database connection technology and pre-developed API interfaces to establish connections with the databases of various business systems within the enterprise, including project management systems, ERP systems, CRM systems, and human resource management systems;

[0101] The second step is to determine the key data sources that reflect real-time business needs and the unique identifiers of the data in each data source through data analysis of each business system;

[0102] The third step is to periodically monitor data changes in key data sources through database triggers or scheduled tasks;

[0103] Step 4: When data update is detected, the updated data is extracted through the API interface according to the pre-set data collection rules;

[0104] The fifth step is to clean the collected data, remove duplicate, erroneous and incomplete data, and integrate the data from different data sources according to the preset data association rules;

[0105] Step 6: Update the cleaned and integrated data to the preset business demand database;

[0106] The seventh step is to retrieve the business demand data from the business demand database as real-time business demand data. In this way, the latest business demand data can be obtained in a timely manner, ensuring the real-time and accuracy of the data, and providing a reliable data basis for the dynamic generation of performance forms. In addition, the collected data is cleaned and integrated to remove invalid data, improve the quality of the data, and reduce the errors or inaccuracies in form generation caused by data problems. In addition, the integration of data from different business systems breaks the data silos, and can more comprehensively understand the business status of the enterprise, thereby generating performance forms that are more in line with actual business needs. Of course, the present application is not limited to this. In other embodiments, the human resources department can also manually upload at fixed time intervals.

[0107] S105: Compare and analyze the historical key data set with the real-time business demand data, and determine the matching degree between the two according to a predefined similarity algorithm;

[0108] Specifically, in some embodiments, the specific formula of the predefined similarity algorithm is as follows:

[0109]

[0110] in:

[0111] h i : represents the i-th keyword in the historical keyword set;

[0112] r j : represents the jth keyword in the real-time business requirement set;

[0113] S: indicates the comprehensive matching degree between the keywords in the two sets. The larger the value, the higher the matching degree between the two sets.

[0114] n: represents the total number of historical keywords in the set;

[0115] m: indicates the total number of real-time demand keywords in the set;

[0116] w ij : Weight, indicating historical keywords h i Keywords related to real-time business needs j The strength of the association between them, the larger the weight value, the closer the relationship between them;

[0117] f(h i ,r j ): matching function, used to determine the keyword h i With keyword r j Whether it matches or not is defined as follows:

[0118]

[0119] S106: If the matching degree is lower than the set threshold, the preset machine learning model is used to optimize and adjust the historical key data set;

[0120] Specifically, in some embodiments, the preset machine learning model is a classification model based on a decision tree algorithm. When constructing the preset machine learning model, key indicator text fragments, process node text fragments, and association relationship text fragments in the historical key data set are used as feature vectors, and the adaptation effects of performance forms in past actual business scenarios are used as label data for training. Among them, the model based on the decision tree algorithm can automatically learn the rules and patterns in historical data, classify the performance form requirements in different business scenarios, and provide intelligent decision support for subsequent optimization and adjustment. In addition, using the adaptation effects in past actual business scenarios as label data for training enables the model to make full use of the company's historical experience, improve the accuracy and reliability of the model, and thereby improve the adaptability of the performance form.

[0121] Based on the above embodiment, the specific training process of the preset machine learning model includes:

[0122] The first step is to pre-process the historical data, convert text features into numerical features using one-hot encoding, use the information gain algorithm to screen out features that have a significant impact on performance form adaptation, and construct node branches of the decision tree;

[0123] The second step is to continuously optimize the structure of the decision tree by recursively partitioning the training data set, so that it can accurately classify the performance form demand patterns in different business scenarios;

[0124] In the third step, when the similarity score is lower than the set threshold, the current real-time business demand data is also converted into the feature vector form required by the decision tree model and input into the trained model. The model gradually judges from the root node according to the path of the feature value in the decision tree, and finally classifies the current business scenario into the corresponding performance form demand category. Based on this category information, the optimization adjustment strategy is extracted from the past well-adapted performance form cases to optimize the historical key data set. The optimization adjustment strategy includes the weight adjustment of key indicators, the increase or decrease of process nodes, and the reconfiguration of association relationships.

[0125] S107: Based on the optimized and adjusted data and in combination with the preset form layout rules, a performance form adapted to the new business scenario of the first department is dynamically generated.

[0126] The specific cases are as follows:

[0127] The HR department of a company needs to develop a new performance form for its marketing department (referred to as the "first department") to evaluate the work performance of employees. The main responsibility of the marketing department is to increase the company's market share through advertising, customer development and brand promotion. Since the company has just launched a marketing plan for a new product, the existing performance form does not fully meet the new needs, so it is necessary to dynamically generate a performance form that meets the current new business scenario.

[0128] The following is the specific process of completing the creation of a performance form according to the steps in the claim:

[0129] 1. Obtain historical performance form data

[0130] Extract historical data on performance forms used by the marketing department in the past 12 months from the department’s database, including the following:

[0131] Indicator data for different versions of the form, for example:

[0132] Indicator 1: Advertising ROI (Return on Investment)

[0133] Metric 2: Customer Conversion Rate

[0134] Metric 3: Brand awareness increase percentage

[0135] Metric 4: Social Media Interactions

[0136] Process node data, such as:

[0137] Node 1: Self-evaluation of frontline employees

[0138] Node 2: Department Manager Evaluation

[0139] Node 3: Human Resources Department Assessment

[0140] Relationship data, such as:

[0141] There is a “direct positive correlation” between advertising ROI and customer conversion rate, with weights of 40% and 35% respectively.

[0142] At the same time, the actual assessment scenario information corresponding to these forms is also obtained, for example:

[0143] The main tasks of the department: regular marketing, quarterly promotional activities, etc.

[0144] Department organizational structure: including marketing manager, advertising specialist, account manager, etc.

[0145] 2. Text parsing and key information extraction

[0146] Parse and analyze the text content of historical forms through natural language processing (NLP) algorithms:

[0147] Use word segmentation technology and frequency statistics to extract key indicator text fragments from the form, such as:

[0148] Indicators that appear more frequently: “Advertising ROI” (appears more than 10 times) and “Customer conversion rate” (appears more than 8 times).

[0149] Extract process node text fragments, such as:

[0150] Department Manager Evaluation appears in all versions of the form.

[0151] Extract key relationship text fragments, such as:

[0152] "Advertising ROI" is positively correlated with "customer conversion rate".

[0153] Key indicators, process nodes, and text snippets that have a frequency of occurrence that reaches a set threshold (such as 30%) are organized into a historical key data set, including:

[0154] Indicator set: advertising ROI, customer conversion rate, brand awareness improvement, etc.

[0155] Process node collection: employee self-evaluation, manager evaluation, and personnel assessment.

[0156] Correlation: Advertising ROI → Customer conversion rate (positive correlation).

[0157] 3. Obtain real-time business demand data

[0158] In the current business environment, real-time business demand data is collected through the following channels:

[0159] Get it from Marketing's Task Management System:

[0160] Current business goal: Launch and promote new products, with an expected target customer base of 500,000 people.

[0161] Mission focus: Increase brand awareness through social media advertising and short video promotion.

[0162] Get data from department head input:

[0163] New assessment indicators added: “Short video click-through rate” and “New customer acquisition”.

[0164] Current assessment period: 1 month (for short-term performance of promotional activities).

[0165] Obtained from historical business data analysis:

[0166] Completed advertising volume: 500,000 impressions.

[0167] Current customer conversion rate: 5%.

[0168] Real-time business demand data is determined as:

[0169] Business goal: new product promotion.

[0170] New indicators: short video click-through rate (expected to increase by 30%) and new customer acquisition (target 1,000 people).

[0171] Assessment period: 1 month.

[0172] 4. Matching analysis

[0173] Compare and analyze real-time business demand data with historical key data sets:

[0174] Similarity calculation:

[0175] Indicators such as "advertising ROI" and "customer conversion rate" in the historical key data set are highly correlated with current business goals, with a similarity score of 85%.

[0176] The "short video click-through rate" indicator does not appear in the historical form, which is partially inconsistent with current needs.

[0177] Matching results:

[0178] Matching score: 70%, which is lower than the set threshold (75%), and the historical key data set needs to be optimized and adjusted.

[0179] 5. Data optimization and adjustment

[0180] Use preset machine learning models (such as random forest algorithms) and rule engines to optimize historical key data sets:

[0181] New indicators: Introducing the "short video click-through rate" and "new customer acquisition" indicators, with weights of 25% and 15% respectively.

[0182] Adjust weights: Reduce the weight of “advertising ROI” (from 40% to 20%) to highlight the focus of current short-term promotion activities.

[0183] Update process nodes: Add a new "Social Media Operation Specialist Evaluation" link in the assessment node, which is responsible for evaluating the effectiveness of short video delivery.

[0184] Verification results: Through business rationality verification, ensure that the new indicators and weight allocation meet actual needs.

[0185] Optimized and adjusted data:

[0186] Indicator set: advertising ROI (20%), customer conversion rate (30%), short video click-through rate (25%), and new customer acquisition (15%).

[0187] Process nodes: employee self-evaluation, social media operations specialist evaluation, manager evaluation, and personnel assessment.

[0188] 6. Dynamically generate performance forms

[0189] Based on the optimized data and combined with the form layout rules, a new performance form is dynamically generated:

[0190] Form content:

[0191] Indicator weight distribution:

[0192] Advertising ROI (20%)

[0193] Customer conversion rate (30%)

[0194] Short video click-through rate (25%)

[0195] New customer acquisition (15%)

[0196] Assessment process:

[0197] Step 1: Employee Self-Evaluation

[0198] Step 2: Social Media Operations Specialist Evaluation

[0199] Step 3: Department Manager Evaluation

[0200] Step 4: Final evaluation by HR

[0201] Form Format:

[0202] Dynamically generated HTML pages support online filling and submission.

[0203] Can be exported to PDF format for archiving.

[0204] See also Figure 2 Based on the same inventive concept as the method for creating a performance form for a human resources system in the aforementioned embodiment, the embodiment of the present application provides a system for creating a performance form for a human resources system, including:

[0205] The first acquisition module 201 is used to acquire the historical multi-version performance form data of the first department and the actual assessment scenario information corresponding to each version;

[0206] The first parsing module 202 is used to perform text parsing on the historical multi-version performance form data to extract key indicator text segments, process node text segments, and association relationship text segments whose occurrence frequencies reach a set threshold;

[0207] The first conversion module 203 converts the key indicator text segment, the process node text segment and the association relationship text segment into structured data using natural language processing technology, and records them as a historical key data set;

[0208] The second acquisition module 204 is used to acquire real-time business demand data;

[0209] A first comparison module 205 is used to compare and analyze the historical key data set with the real-time business demand data, and determine the matching degree between the two according to a predefined similarity algorithm;

[0210] A first adjustment module 206, configured to optimize and adjust the historical key data set using a preset machine learning model if the matching degree is lower than a set threshold;

[0211] The form generation module 207 is used to dynamically generate a performance form adapted to the new business scenario of the first department based on the optimized and adjusted data in combination with preset form layout rules.

[0212] In some embodiments, historical multi-version performance form data includes performance forms from multiple different periods and different business lines, and actual assessment scenario information includes organizational structure, business objectives, and categories of assessors.

[0213] In some embodiments, the second acquisition module 204 is specifically used to: establish a connection with the databases of various business systems within the enterprise using database connection technology and a pre-developed API interface, the business systems including a project management system, an ERP system, a CRM system, and a human resources management system; determine the key data sources that reflect real-time business needs and the unique identifiers of the data in each data source through data analysis of each business system; periodically monitor data changes in key data sources through database triggers or scheduled tasks; when data updates are detected, extract updated data through an API interface based on pre-set data collection rules; clean the collected data to remove duplicate, erroneous, and incomplete data, and integrate data from different data sources according to pre-set data association rules; update the cleaned and integrated data to a pre-set business needs database; and retrieve business needs data from the business needs database as real-time business needs data.

[0214] In some embodiments, the specific formula of the predefined similarity algorithm is as follows:

[0215]

[0216] in:

[0217] h i : represents the i-th keyword in the historical keyword set;

[0218] r j : represents the jth keyword in the real-time business requirement set;

[0219] S: indicates the comprehensive matching degree between the keywords in the two sets. The larger the value, the higher the matching degree between the two sets.

[0220] n: represents the total number of historical keywords in the set;

[0221] m: indicates the total number of real-time demand keywords in the set;

[0222] w ij : Weight, indicating historical keywords h i Keywords related to real-time business needs j The strength of the association between them, the larger the weight value, the closer the relationship between them;

[0223] f(h i ,r j ): matching function, used to determine the keyword h i With keyword r j Whether it matches or not is defined as follows:

[0224]

[0225] In some embodiments, the preset machine learning model is a classification model based on a decision tree algorithm. When constructing the preset machine learning model, key indicator text fragments, process node text fragments, and association relationship text fragments in the historical key data set are used as feature vectors, and the adaptation effects of performance forms in past actual business scenarios are used as label data for training.

[0226] In some embodiments, the specific training process of the preset machine learning model includes:

[0227] Preprocess the historical data, convert text features into numerical features using one-hot encoding, use the information gain algorithm to screen out features that have a significant impact on performance form adaptation, and construct node branches of the decision tree;

[0228] By recursively partitioning the training data set, the structure of the decision tree is continuously optimized so that it can accurately classify the performance form demand patterns in different business scenarios;

[0229] When the similarity score is lower than the set threshold, the current real-time business demand data is also converted into the feature vector form required by the decision tree model and input into the trained model. The model makes judgments step by step from the root node according to the path of the feature value in the decision tree, and finally classifies the current business scenario into the corresponding performance form demand category. Based on this category information, optimization and adjustment strategies are extracted from past well-adapted performance form cases to optimize the historical key data set. The optimization and adjustment strategies include weight adjustment of key indicators, increase or decrease of process nodes, and reconfiguration of association relationships.

[0230] It is understandable that the performance form creation system of the human resources system records the modules and references Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the performance form creation system of the human resources system and the modules contained therein, and will not be repeated here.

[0231] See also Figure 3 Based on the inventive concept of a method for creating a performance form of a human resources system in the aforementioned embodiment, an embodiment of the present application provides an electronic device. The electronic device may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device includes a processing device 301 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a ROM 302 (read-only memory) or a program loaded from a storage device 308 into a RAM 303 (random access memory). In RAM 303, various programs and data required for the operation of the electronic device are also stored. The processing device 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An input / output interface (i.e., an I / O interface 305) is also connected to the bus 304.

[0232] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data.

[0233] In particular, according to some embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present application are executed.

[0234] It should be noted that the computer-readable medium recorded in some embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0235] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an adhoc peer-to-peer network), as well as any currently known or future developed network.

[0236] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains the historical multi-version performance form data of the first department and the actual assessment scenario information corresponding to each version; performs text analysis on the historical multi-version performance form data, extracts key indicator text fragments, process node text fragments, and association text fragments whose occurrence frequency reaches a set threshold; uses natural language processing technology to convert key indicator text fragments, process node text fragments, and association text fragments into structured data, recorded as a historical key data set; obtains real-time business demand data; compares and analyzes the historical key data set with the real-time business demand data, and determines the degree of match between the two based on a predefined similarity algorithm; if the degree of match is lower than the set threshold, uses a preset machine learning model to optimize and adjust the historical key data set; and dynamically generates a performance form adapted to the new business scenario of the first department based on the optimized and adjusted data and in combination with the preset form layout rules.

[0237] The computer program code for performing the operation of some embodiments of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer, partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0238] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0239] The modules described in some embodiments of the present application may be implemented by software or by hardware. The modules described may also be provided in a processor: for example, they may be described as: a first acquisition module, a first parsing module, a first conversion module, a second acquisition module, a first comparison module, a first adjustment module, and a table generation module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the first acquisition module may also be described as a "historical performance form receiving module."

[0240] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0241] Some embodiments of the present application also provide a computer program product, including a computer program, which implements any of the above-mentioned performance form creation methods for the human resources system when executed by a processor.

[0242] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for creating a performance form in a human resources system, characterized in that: The following steps are involved: Obtain the historical multi-version performance form data of the first department and the actual assessment scenario information corresponding to each version; Performing text parsing on the historical multi-version performance form data to extract key indicator text segments, process node text segments, and association relationship text segments whose occurrence frequencies reach a set threshold; Using natural language processing technology, the key indicator text fragment, the process node text fragment, and the association relationship text fragment are converted into structured data, which are recorded as a historical key data set; Obtain real-time business demand data; Comparing and analyzing the historical key data set with the real-time business demand data, and determining the degree of matching between the two according to a predefined similarity algorithm; If the matching degree is lower than the set threshold, the preset machine learning model is used to optimize and adjust the historical key data set; Based on the optimized and adjusted data and combined with the preset form layout rules, a performance form that adapts to the new business scenarios of the first department is dynamically generated.

2. The method for creating a performance form for a human resources system according to claim 1, characterized in that: The historical multi-version performance form data includes performance forms from multiple different periods and different business lines, and the actual assessment scenario information includes organizational structure, business objectives, and assessment personnel categories.

3. The method for creating a performance form for a human resources system according to claim 2, characterized in that: The steps for obtaining real-time business demand data include: Use database connection technology and pre-developed API interfaces to establish connections with the databases of various business systems within the enterprise, including project management systems, ERP systems, CRM systems, and human resource management systems; By analyzing the data of each business system, determine the key data sources that reflect real-time business needs and the unique identifiers of the data in each data source; Periodically monitor data changes in key data sources through database triggers or scheduled tasks; When data update is detected, the updated data is extracted through the API interface according to the pre-set data collection rules; Clean the collected data, remove duplicate, erroneous and incomplete data, and integrate data from different data sources according to preset data association rules; Update the cleaned and integrated data to the preset business demand database; The business requirement data is retrieved from the business requirement database as the real-time business requirement data.

4. The method for creating a performance form for a human resources system according to claim 3, characterized in that: The specific formula of the predefined similarity algorithm is as follows: in: h i : represents the i-th keyword in the historical keyword set; r j : represents the jth keyword in the real-time business requirement set; S: indicates the comprehensive matching degree between the keywords in the two sets. The larger the value, the higher the matching degree between the two sets. n: represents the total number of historical keywords in the set; m: indicates the total number of real-time demand keywords in the set; w ij : Weight, indicating historical keywords h i Keywords related to real-time business needs j The strength of the association between them, the larger the weight value, the closer the relationship between them; f(h i ,r j ): matching function, used to determine the keyword h i With keyword r j Whether it matches or not is defined as follows:

5. The method for creating a performance form for a human resources system according to claim 4, characterized in that: The preset machine learning model is a classification model based on the decision tree algorithm. When constructing the preset machine learning model, key indicator text fragments, process node text fragments, and association relationship text fragments in the historical key data set are used as feature vectors, and the adaptation effects of performance forms in past actual business scenarios are used as label data for training.

6. The method for creating a performance form in a human resources system according to claim 5, characterized in that: The specific training process of the preset machine learning model includes: Preprocess the historical data, convert text features into numerical features using one-hot encoding, use the information gain algorithm to screen out features that have a significant impact on performance form adaptation, and construct node branches of the decision tree; By recursively partitioning the training data set, the structure of the decision tree is continuously optimized so that it can accurately classify the performance form demand patterns in different business scenarios; When the similarity score is lower than the set threshold, the current real-time business demand data is also converted into the feature vector form required by the decision tree model and input into the trained model. The model makes judgments step by step from the root node according to the path of the feature value in the decision tree, and finally classifies the current business scenario into the corresponding performance form demand category. Based on this category information, optimization and adjustment strategies are extracted from past well-adapted performance form cases to optimize the historical key data set. The optimization and adjustment strategies include weight adjustment of key indicators, increase or decrease of process nodes, and reconfiguration of association relationships.

7. A performance form creation system for a human resources system, characterized in that: include: The first acquisition module is used to obtain the historical multi-version performance form data of the first department and the actual assessment scenario information corresponding to each version; The first parsing module is used to perform text parsing on the historical multi-version performance form data to extract key indicator text segments, process node text segments, and association relationship text segments whose occurrence frequencies reach a set threshold; A first conversion module converts the key indicator text fragment, the process node text fragment, and the association relationship text fragment into structured data using natural language processing technology, and records them as a historical key data set; The second acquisition module is used to acquire real-time business demand data; A first comparison module is used to compare and analyze the historical key data set with the real-time business demand data, and determine the matching degree between the two according to a predefined similarity algorithm; A first adjustment module is used to optimize and adjust the historical key data set using a preset machine learning model if the matching degree is lower than a set threshold; The form generation module is used to dynamically generate performance forms that adapt to the new business scenarios of the first department based on the optimized and adjusted data and combined with preset form layout rules.

8. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processing device, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processing device, the method according to any one of claims 1 to 6 is implemented.

Images