Intelligent human resource data processing method and system

Abstract

The application provides a kind of based on intelligent human resource data processing method and system, it is related to data processing technology, the present application can obtain various human resource data such as employee salary, recruitment, training from multiple data sources (such as financial system, personnel management system, project management system etc.), chain of employee exclusive cost statistics is integrated and generated, ensure the integrity and accuracy of data.Secondly, by establishing a prediction model, the system can predict the cost of human resources according to historical data, help enterprises make budget and resource allocation.System supports multi-terminal intercommunication, management can view prediction results and reports in real time through web or mobile terminal, convenient decision and management.And the system has flexible customization function, can be adjusted and optimized according to the specific needs of enterprises.

Description

Technical Field

[0001] This invention relates to data processing technology, and more particularly to an intelligent human resources data processing method and system. Background Technology

[0002] In the process of enterprise digital transformation, human resource management, as a core part of enterprise operation, faces increasingly complex challenges.

[0003] Currently, human resources-related data is scattered across multiple heterogeneous data sources, such as financial systems, human resource management systems, and project management systems. The data in each system is independent and lacks a unified integration mechanism, resulting in a state of "information silos." For example, employee salary data exists only in the financial system, recruitment information is stored in the human resource management system, and training records are kept in the training system. Data between these systems cannot be automatically linked or shared. Managers need to spend a significant amount of time and effort manually collecting and organizing data from different systems, which is not only inefficient but also prone to data omissions and duplicate entries, seriously affecting the accuracy and completeness of the data.

[0004] Therefore, how to quickly integrate human resource data from different systems and improve the efficiency and accuracy of data management has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides an intelligent human resources data processing method and system that can integrate human resources data from different systems, thereby improving the efficiency and accuracy of data management.

[0006] A first aspect of the present invention provides a method for intelligent human resource data processing, comprising:

[0007] Based on the human resources data corresponding to each user in each data source, a data chain corresponding to each user is generated, and the data chain includes multiple cost nodes;

[0008] Input the historical data corresponding to the data chain into the prediction model, and obtain the resource prediction data output by the prediction model; generate display data based on the resource prediction data corresponding to each user, and the display data is associated with multiple interactive terminals;

[0009] Based on the customized instructions, the data parameters of the displayed data are adjusted to obtain customized data that meets the requirements.

[0010] Optionally, in one possible implementation of the first aspect, a data chain corresponding to each user is generated based on the human resource data corresponding to each user in each data source. The data chain includes multiple cost nodes, including:

[0011] Construct cost nodes corresponding to each cost type, map human resource data of each user to the corresponding cost nodes, generate data chains by associating the corresponding cost nodes with the unique identifier of each user, and add timestamps to each cost node.

[0012] Optionally, in one possible implementation of the first aspect, inputting historical data corresponding to the data chain into the prediction model and obtaining resource prediction data output by the prediction model includes:

[0013] When the cost node corresponding to the historical data is a work element type, image data of the target area is obtained according to the prediction model;

[0014] The cost quantification data of each operation element is analyzed based on the image data. The operation elements include equipment elements and area elements. Resource prediction data corresponding to the corresponding cost node is obtained based on the sum of the cost quantification data of each operation element. Each cost quantification data is configured with an abnormal threshold. When the cost quantification data is greater than or equal to the abnormal threshold, an abnormal reminder message is generated.

[0015] Optionally, in one possible implementation of the first aspect, analyzing cost quantification data for each operational element based on the image data includes:

[0016] The image data is divided into multiple work areas, and the target area corresponding to each user in the multiple work areas is determined; the cost quantification data corresponding to the area elements is calculated based on the area proportion of the target area.

[0017] Obtain the equipment operating parameters in the target area, and calculate the cost quantification data corresponding to the equipment element based on the equipment operating parameters.

[0018] Optionally, in one possible implementation of the first aspect, determining the target region corresponding to the corresponding user in multiple job regions includes:

[0019] By comparing the user's workstation number with the area number of each work area, the work area corresponding to the area number that matches the workstation number is determined as the target area.

[0020] Optionally, in one possible implementation of the first aspect, calculating the cost quantification data corresponding to the regional elements based on the regional proportion of the target region includes:

[0021] The first quantitative data is obtained by multiplying the target area's proportion of the total area by the total site cost;

[0022] The cost of public space is obtained, and a second quantitative data is obtained based on the ratio of the cost of public space to the number of users. The cost quantitative data is obtained based on the first and second quantitative data.

[0023] Optionally, in one possible implementation of the first aspect, obtaining equipment operating parameters in the target area and calculating cost quantification data corresponding to the equipment element based on the equipment operating parameters includes:

[0024] The device runtime and device damage value are obtained based on the image data, and the device operating parameters include the device runtime and device damage value;

[0025] Based on the correspondence between preset duration and depreciation rate, the current depreciation rate corresponding to the device's operating duration is determined;

[0026] Based on the adjustment factor corresponding to the equipment damage value, the current depreciation rate is updated to obtain the adjusted depreciation rate.

[0027] Based on the adjusted depreciation rate, the initial cost of the equipment is depreciated to obtain the cost quantification data corresponding to the equipment element.

[0028] Optionally, in one possible implementation of the first aspect, obtaining the device runtime based on the image data includes:

[0029] Extract the device outline from the image data, count the number of pixels in the device outline that are located in the preset pixel interval corresponding to the black screen, and obtain the black screen percentage based on the ratio of the number of pixels to the total number of pixels.

[0030] When the percentage of black screen is less than the black screen pixel threshold, it is determined to be a device running state, and the total device runtime in the device running state is recorded.

[0031] Optionally, in one possible implementation of the first aspect, obtaining the device damage value based on the image data includes:

[0032] Extract the device outline from the image data, and compare the stored initial device outline with the current device outline to obtain the outline similarity;

[0033] When the contour similarity is less than the similarity threshold, the initial device contour and the pixels with the same coordinates in the device contour are compared; the difference region composed of pixels with inconsistent pixel values ​​is obtained, the damage characteristics of the difference region are identified, the preset damage value of the damage characteristics under the area corresponding to the device contour is retrieved, and the device damage value is obtained by multiplying the area ratio of the difference region and the device contour with the preset damage value.

[0034] A second aspect of the present invention provides an intelligent human resources data processing system, comprising:

[0035] The statistical analysis module is used to generate a data chain for each user based on the human resources data of each user in each data source. The data chain includes multiple cost nodes.

[0036] The data prediction module is used to input the historical data corresponding to the data chain into the prediction model and obtain the resource prediction data output by the prediction model.

[0037] The data display module is used to generate display data based on the resource prediction data corresponding to each user, and the display data is associated with multiple interactive terminals;

[0038] The data customization module is used to adjust the data parameters of the displayed data based on customization instructions to obtain customized data that meets the requirements.

[0039] The beneficial effects of this invention are as follows:

[0040] 1. This invention can generate data chains corresponding to each user, systematically integrating various costs generated throughout an employee's lifecycle to form a unified and complete cost record, providing a more comprehensive and accurate data foundation. It achieves automated and comprehensive collection and integration of employee cost data.

[0041] 2. This invention can predict user cost data through data in the data chain, enabling rapid and accurate real-time monitoring of cost data. This allows users to combine the prediction results with timely and targeted actions.

[0042] 3. This invention can combine image data to quantitatively predict the cost of operational elements, which can more accurately grasp the cost situation related to the use of physical resources, provide a data foundation for cost quantification, prediction and anomaly monitoring, and improve the accuracy of data prediction.

[0043] 4. This invention can generate and display data and associate it with multiple interactive terminals, thereby presenting the data to users in an intuitive and visual way, improving data utilization and promoting information sharing within the enterprise.

[0044] 5. This invention can flexibly filter, combine, and present data according to the specific needs of users, providing users with personalized data services and improving the flexibility of data display. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of an application scenario provided by an embodiment of the present invention;

[0046] Figure 2 This is a flowchart illustrating an intelligent human resources data processing method provided in an embodiment of the present invention;

[0047] Figure 3This is a schematic diagram of a structure of an intelligent human resources data processing system provided in an embodiment of the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] See Figure 1 This is a schematic diagram illustrating an application scenario provided by an embodiment of the present invention. The present invention can acquire various human resource data, such as employee salaries, recruitment, and training, from multiple data sources (e.g., financial systems, human resource management systems, project management systems, etc.), and integrate them to generate a chain of employee-specific cost statistics, ensuring data integrity and accuracy. Secondly, by establishing a predictive model, the system can predict human resource costs based on historical data, helping enterprises to make better budgets and resource allocations. The system supports multi-terminal interoperability; management can view prediction results and reports in real time via web or mobile devices, facilitating decision-making and management. Furthermore, the system has flexible customization capabilities, allowing adjustments and optimizations based on the specific needs of the enterprise.

[0050] See Figure 2 This is a flowchart illustrating an intelligent human resource data processing method provided in an embodiment of the present invention. Figure 2 The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S4 are detailed as follows:

[0051] S1. Based on the human resources data corresponding to each user in each data source, generate a data chain corresponding to each user, wherein the data chain includes multiple cost nodes.

[0052] Understandably, employee costs are complex and dispersed across different business segments during a company's operations. Generating a data chain can systematically integrate all costs generated throughout an employee's lifecycle, forming a unified and complete cost record. This provides a more comprehensive and accurate data foundation, avoiding management blind spots and decision-making errors caused by fragmented data.

[0053] The data sources are the channels from which human resources data originates, including but not limited to the HR department's recruitment management system (which records recruitment-related data), financial system (which stores data on salaries, benefits, expense reimbursements, etc.), HR training system (which records information on training courses, instructors, etc.), and asset management system (which manages asset data such as electronic devices and office supplies). These systems each store data generated by employees in different business scenarios.

[0054] Human resources data encompasses all human-related data related to an employee's employment from onboarding to departure. In the recruitment phase, this includes data on recruitment channel costs; in terms of salary and benefits, it includes data on employee salaries, bonuses, various insurances, and welfare payments; in the training phase, it includes training course fees and trainer costs; in the departure phase, it includes data on severance pay; and it also includes cost data related to employee use, such as electronic devices and office supplies.

[0055] A data chain is a cost record chain formed by linking the cost nodes generated by each employee in various business processes in chronological order. A cost node refers to a specific cost item in the data chain, corresponding to the cost incurred by an employee in a particular business process. For example, the recruitment cost node records various expenses incurred during the recruitment process; the salary and benefits cost node stores monthly salary and bonus disbursement data; and the training cost node stores training-related expenses.

[0056] By generating a data chain, the automated and comprehensive collection and integration of employee cost data has been achieved. Enterprises can clearly and intuitively see the cost input of each employee at each stage, which facilitates refined cost management.

[0057] Based on the above embodiments, step S1 can be implemented in the following ways:

[0058] Construct cost nodes corresponding to each cost type, map human resource data of each user to the corresponding cost nodes, generate data chains by associating the corresponding cost nodes with the unique identifier of each user, and add timestamps to each cost node.

[0059] A unique identifier is a user's identification code, typically an employee ID number, but can also be a national ID number or other unique identifier. A timestamp is a time record added to each cost node, accurate to the specific date and time.

[0060] For example, the system can automatically create recruitment cost nodes, salary and benefits cost nodes, training cost nodes, turnover cost nodes, and workstation cost nodes based on preset cost types. When mapping human resource data, the system will accurately connect with the data source according to the characteristics of different cost nodes. For example, for the recruitment cost node, the system can connect with the HR department's recruitment management system to obtain data such as the expenses incurred by the user on the recruitment platform during the recruitment process and the work costs invested by recruiters, and automatically populate the data; the salary and benefits cost node records data such as the user's basic salary, performance bonus, and various insurance and benefits payments synchronized from the financial system at the end of each month; when the user participates in new employee training and job skills training, the system connects with the HR training system to collect training course fees and training venue usage fees to form training cost node data; and for the workstation cost node, the system can record the corresponding cost data based on the user's workstation usage. When generating the data chain, the system can connect each cost node in chronological order according to the user's unique identifier to form a user-specific data chain, completely recording various cost information from recruitment to onboarding. When data is entered or updated at each cost node, the system can automatically add a timestamp to record the operation time, ensuring that each cost data has a clear time record, which facilitates subsequent time-based analysis and traceability.

[0061] S2, input the historical data corresponding to the data chain into the prediction model, and obtain the resource prediction data output by the prediction model.

[0062] Understandably, a company's operating environment is constantly changing. To improve the real-time nature of data, historical data can be used to predict resource cost data, thereby improving the company's resource management efficiency.

[0063] Historical data refers to cost data recorded within a predetermined timeframe in the data chain, including cost data from traditional business processes and workstation usage data derived from the analysis of images taken at workstations. The predictive model is a data analysis tool built to predict costs. Resource prediction data consists of estimated resource costs output by the predictive model based on the input historical data, after calculation and analysis; this includes predicted workstation costs.

[0064] By inputting historical data into predictive models to obtain cost forecasts, businesses can quickly and accurately grasp the real-time status of cost data. Based on the forecast results, businesses can adjust their cost budgets in a timely manner. If current cost data exceeds expectations, they can immediately analyze whether it is due to rising rent, equipment depreciation, or other factors, and then take targeted measures, such as negotiating rent with the property management or optimizing equipment procurement plans.

[0065] Based on the above embodiments, step S2 can be implemented in the following ways:

[0066] S21, when the cost node corresponding to the historical data is a work element type, obtain the image data of the target area according to the prediction model.

[0067] Understandably, in the course of business operations, the costs of operational elements involving the use of physical resources such as equipment and premises, including equipment depreciation and site rental, are difficult to calculate and manage due to a lack of intuitive and real-time data support. Obtaining image data of the target area through predictive models aims to provide raw data support for operational element cost analysis, enabling a more accurate understanding of costs related to the use of physical resources. This provides a data foundation for cost quantification, prediction, and anomaly monitoring, thereby achieving refined management of these costs.

[0068] Cost nodes for activity element types are used to record data directly related to the use of physical resources, including costs incurred by equipment elements and area elements. The target area is the office area.

[0069] S22, Analyze the cost quantification data of each operation element based on the image data, wherein the operation elements include equipment elements and area elements.

[0070] Analyzing image data and calculating the cost quantification data of each operational element is to quantify the physical information contained in the image, such as the equipment operating status and area usage, so as to predict the cost data of each operational element and improve the accuracy of data prediction.

[0071] Operational elements are the core physical resource units constituting the target area, mainly divided into equipment elements and area elements. Equipment elements refer to various hardware devices within the target area, such as office equipment; area elements refer to the spatial resources within the target area, including workstations and office spaces. Cost quantification data are cost values ​​obtained through analysis of image data.

[0072] In some embodiments, the cost quantification data of each operation element can be analyzed based on the image data through the following steps:

[0073] S221, divide the image data into multiple work areas and determine the target area corresponding to the user in the multiple work areas.

[0074] By clearly defining the target area actually used by the user, ambiguity in cost data calculation can be avoided, ensuring that the cost data accurately reflects the user's actual occupation of physical resources, and laying the foundation for subsequent accurate calculation of cost quantification data for area elements and equipment elements.

[0075] The work area is the physical space encompassed by image data divided into different sub-areas based on factors such as function, purpose, or user. In practical applications, this division can be combined with the area layout. For example, in an office environment, it can be divided into individual workstation areas, public meeting areas, etc. The target area is the specific area determined from multiple work areas for a particular user, either for their actual use or related to cost accounting. For example, the target area for a certain employee might be their individual workstation and the public area.

[0076] In some embodiments, the target area corresponding to the user can be determined through the following steps:

[0077] By comparing the user's workstation number with the area number of each work area, the work area corresponding to the area number that matches the workstation number is determined as the target area.

[0078] The workstation number is a unique identifier assigned to each workstation, used to distinguish different workstations and including the location of the workstation. The area number is a unique identifier assigned to each work area, used to distinguish different work areas and including the location of the area.

[0079] By comparing workstation numbers and area numbers to determine the target area, precise matching between users and work areas can be achieved, improving the accuracy of data processing.

[0080] S222, calculate the cost quantification data corresponding to the regional elements based on the regional proportion of the target region.

[0081] By calculating cost quantification data based on the regional proportion of the target area, these overall costs can be reasonably allocated to the specific target areas corresponding to each user, making the accounting of regional element costs more equitable and accurate. In this way, enterprises can clearly understand the corresponding expenditures in terms of regional element costs for each target area, providing specific data references for cost control and resource allocation.

[0082] The area proportion refers to the percentage of the target area within the entire operational scenario, which can be determined by its area. The cost quantification data corresponding to the area element includes cost forecast data for both the target area and the common area.

[0083] Quantifying regional element costs based on regional proportions can achieve reasonable allocation of regional element costs and improve the accuracy of data prediction.

[0084] In some embodiments, the cost quantification data corresponding to the regional elements can be calculated based on the regional proportion of the target region through the following steps:

[0085] The first quantitative data is obtained by multiplying the target area's proportion of the total area by the total site cost; the public site cost is obtained, and the second quantitative data is obtained based on the ratio of the public site cost to the number of users; the cost quantitative data is obtained based on the first and second quantitative data.

[0086] Understandably, the first quantitative data, derived by multiplying the target area's proportion of the total area by the total site cost, is used to allocate the total site cost according to the target area's proportion within the entire site, thus determining the direct site cost share that the target area should bear. For example, if the target area accounts for 30% of the total area and the total site cost is 10,000 yuan, then the first quantitative data would be 3,000 yuan.

[0087] Obtaining the cost of public space, and then using the ratio of public space cost to the number of users to derive a second quantitative data point, is to distribute the public space cost evenly among each user, thus obtaining each user's share of the public space cost. For example, if the public space cost is 5000 yuan and there are 50 users, then the second quantitative data point would be 100 yuan.

[0088] The first quantitative data is the site cost predicted based on the proportion of the target area, and the second quantitative data is the predicted public site cost to be shared by a single user.

[0089] S223, Obtain the equipment operating parameters in the target area, and calculate the cost quantification data corresponding to the equipment element based on the equipment operating parameters.

[0090] Equipment incurs various costs during use, including depreciation and energy consumption. Equipment operating parameters directly reflect its usage status and intensity. Obtaining equipment operating parameters within a target area and calculating quantifiable cost data allows for accurate measurement of the costs generated during actual use. This approach enables businesses to clearly understand the cost consumption of each piece of equipment, providing data-driven support for decisions regarding equipment procurement, maintenance, and upgrades. It also allows for refined management of equipment element costs, preventing waste of equipment resources and unreasonable cost expenditures.

[0091] Among them, equipment operating parameters are data indicators reflecting the operating status and usage of equipment, including equipment operating time, damage status, etc. The cost quantification data corresponding to the equipment elements are the cost prediction data for the equipment.

[0092] By acquiring equipment operating parameters and calculating quantitative data on equipment element costs, the cost consumption of each piece of equipment can be accurately grasped. This allows for the identification of equipment with excessive energy consumption and equipment with abnormal maintenance costs, enabling targeted measures such as energy-saving retrofits for high-energy-consuming equipment and adjustments to maintenance plans or replacement considerations for equipment with high maintenance costs.

[0093] In some embodiments, cost quantification data corresponding to a device element can be obtained through the following steps:

[0094] The device runtime and device damage value are obtained based on the image data. The device operating parameters include the device runtime and device damage value. Based on the correspondence between preset runtime and depreciation rate, the current depreciation rate corresponding to the device runtime is determined. Based on the adjustment multiple corresponding to the device damage value, the current depreciation rate is updated to obtain an adjusted depreciation rate. Based on the adjusted depreciation rate, the initial cost of the device is depreciated to obtain the cost quantification data corresponding to the device element.

[0095] Understandably, by acquiring operating parameters such as equipment runtime and equipment damage value, and combining them with preset rules to calculate the depreciation rate and deduct the initial cost of the equipment, the cost consumption during the use of the equipment can be accurately measured, thus improving the accuracy of data prediction.

[0096] The device runtime is the cumulative working time of the device. In some embodiments, the device runtime can be recorded through the following steps:

[0097] Extract the device outline from the image data, count the number of pixels in the device outline that are located in the preset pixel interval corresponding to the black screen, and obtain the black screen percentage based on the ratio of the number of pixels to the total number of pixels; when the black screen percentage is less than the black screen pixel threshold, it is determined to be a device running state, and the total device running time in the device running state is recorded.

[0098] The device outline refers to the boundary range of the device in the image data. It can be extracted using image recognition technology and used to locate the device's position and shape in the image. The preset pixel range corresponding to the black screen can be a range of black pixels. The black screen percentage is the ratio of the number of pixels in the device outline located within the preset black screen pixel range to the total number of pixels, reflecting the proportion of the black screen portion of the device within the overall device. The black screen pixel threshold is a limit value set based on the black screen situation during normal device operation, used to determine the black screen percentage to judge the device's operating status. When the black screen percentage is less than this threshold, the device is determined to be in an operating state; when it is greater than or equal to this threshold, it may indicate that the device is in an abnormal black screen or shutdown state.

[0099] For example, image recognition algorithms can be used to process the acquired computer device image data, accurately extracting the device's outline in the image. Image analysis techniques can then be used to count the number of pixels within the device outline that fall within a preset black screen pixel range. Assume the total number of pixels within the computer device outline is 1000, and 50 pixels fall within the preset black screen pixel range. Based on the counted pixels, the black screen percentage is calculated, which is 5%. Given that the black screen pixel threshold for this computer device is 10%, since the calculated black screen percentage of 5% is less than the black screen pixel threshold of 10%, the system determines that the computer device is in a running state. At this point, the system begins recording the total device runtime while the computer is in a running state.

[0100] By following the steps above, the operating status of the device can be accurately determined based on image data, and the device's operating time can be recorded in real time.

[0101] The equipment damage value is an estimate derived from an assessment of the extent of physical damage to the equipment. In some embodiments, the equipment damage value can be determined through the following steps:

[0102] Extract the device outline from the image data, compare the stored initial device outline with the current device outline to obtain the outline similarity; when the outline similarity is less than the similarity threshold, compare the pixels with the same coordinates in the initial device outline and the current device outline; obtain the difference region formed by pixels with inconsistent pixel values, identify the damage features of the difference region, retrieve the preset damage value of the damage feature under the area corresponding to the device outline, and obtain the device damage value according to the product of the ratio of the area of ​​the difference region and the device outline and the preset damage value.

[0103] Understandably, accurately assessing equipment damage is crucial for maintenance, replacement decisions, and cost accounting. By extracting the equipment outline from image data, comparing the initial and current outlines, identifying areas of difference, and calculating the equipment damage value, the extent of equipment damage can be quantified, providing accurate information about the equipment's condition.

[0104] The initial device outline is the outline data in its initial state, used as a comparison benchmark and stored in the system. The similarity threshold is a pre-set boundary value used to judge the similarity of device outlines. When the outline similarity is less than this threshold, it indicates that the device may have been damaged and requires further analysis. The difference region is the area formed by pixels with inconsistent pixel values ​​when comparing the initial and current device outlines. These areas may indicate wear, damage, or other issues with the device. Damage features are the specific manifestations of device damage presented in the difference regions, such as scratches on the device surface, deformation of components, and wear marks, used to assess the degree of damage. The preset damage value is a pre-set quantitative value related to the area of ​​the device outline, based on factors such as the device type, material, and usage environment, stored in the system as the basis for calculating the device damage value.

[0105] For example, the system can use image recognition algorithms to process the acquired device image data and extract the current device outline. Simultaneously, it retrieves the initial device outline data from system storage. The similarity between the initial and current device outlines is calculated using an algorithm; assuming a similarity of 70%, and a pre-set similarity threshold of 80%, the system further compares pixels with the same coordinates in the initial and current device outlines. Through image analysis techniques, it identifies discrepancy regions formed by pixels with inconsistent pixel values. For example, in a certain component area of ​​the device, there might be a significant difference in pixel values ​​between the initial and current outlines, forming a discrepancy region. The system identifies damage characteristics of these discrepancy regions, such as scratches on the device surface or wear marks on components. Based on the device type and damage characteristics, a pre-set damage value related to the device outline area is retrieved, assuming a cost of 0.8 yuan per square centimeter. Assuming the discrepancy region is 130 square centimeters and the overall device area is 1200 square centimeters, the area ratio is approximately 10.83%. Based on the calculation formula, the equipment damage value is 1040 yuan.

[0106] The preset relationship between operating time and depreciation rate is based on factors such as equipment type, performance, and service life. It is a pre-set rule that corresponds the equipment operating time to the corresponding depreciation rate. For example, if the equipment operating time is less than 1,000 hours, the depreciation rate is 10% per year; if the operating time is between 1,000 and 2,000 hours, the depreciation rate is 15% per year, etc.

[0107] The adjustment factor is a coefficient set based on the correspondence between the equipment damage value and the preset damage standard, used to adjust the current depreciation rate. For example, if the equipment damage value reaches a certain level, the adjustment factor is 1.2, meaning the depreciation rate will increase by 20% from the current level.

[0108] The adjusted depreciation rate is the updated depreciation rate after combining the current depreciation rate corresponding to the equipment's operating time and the adjustment multiple corresponding to the equipment's damage value. The initial cost of the equipment is the original investment made by the company when purchasing the equipment.

[0109] For example, assuming the equipment has accumulated 1500 hours of operation, image analysis reveals that the wear and tear on key components has reached a certain percentage, and the assessed damage value is 10% of the initial cost. Based on the preset correlation between operating time and depreciation rate, the current depreciation rate for 1500 hours of operation is 15% per annum. Since the damage value is 10%, according to the preset adjustment rule, assuming an adjustment multiple of 1.3 (equipment damage increases the depreciation rate), combined with the current depreciation rate of 15%, the adjusted depreciation rate is 19.5%. Given that the initial cost of the equipment is 10,000 yuan, the depreciation cost calculated at the adjusted depreciation rate of 19.5% is 1950 yuan. This 1950 yuan is the quantified cost data corresponding to this equipment element.

[0110] By calculating the quantitative data of equipment element costs through the above steps, we can more accurately grasp the cost consumption of equipment under different operating conditions and improve the accuracy of data prediction.

[0111] S23, resource prediction data corresponding to the corresponding cost node is obtained based on the sum of the cost quantification data of each of the operation elements. Each of the cost quantification data is configured with an abnormal threshold. When the cost quantification data is greater than or equal to the abnormal threshold, an abnormal reminder message is generated.

[0112] By aggregating the quantified cost data of each operational element, resource forecast data is obtained, which comprehensively and accurately reflects the overall cost situation of cost nodes for each operational element type, providing an important reference for enterprises to formulate budgets and evaluate cost-effectiveness. Simultaneously, setting anomaly thresholds for each quantified cost data point and monitoring it allows for timely generation of alerts when cost data anomalies occur. This helps enterprises promptly identify problems in cost management, such as equipment failures leading to cost spikes or regional resource waste, enabling rapid adjustments and optimizations.

[0113] The anomaly threshold is a pre-defined upper limit for a reasonable range for each quantified cost data point. When the actual calculated quantified cost data exceeds this threshold, the system will determine that the cost data is abnormal. Anomaly alerts are automatically generated warning notifications when the quantified cost data is greater than or equal to the anomaly threshold. These notifications can be sent to relevant personnel via email, SMS, system pop-ups, and other methods.

[0114] By calculating resource forecast data and setting anomaly thresholds, comprehensive monitoring and dynamic management of operational element costs can be achieved.

[0115] S3, generate display data based on the resource prediction data corresponding to each user, and the display data is associated with multiple interactive terminals.

[0116] Understandably, generating and displaying resource forecast data and linking it to multiple interactive terminals is intended to present it to users in an intuitive and visual way. This allows different roles, such as senior managers, middle managers, and frontline employees, to access the information they need anytime and anywhere on their commonly used devices (such as computers, mobile phones, and tablets), thereby improving data utilization, promoting information sharing within the enterprise, and enabling personnel at all levels to conduct effective analysis and decision-making based on data.

[0117] The displayed data is the result of organizing, processing, and visualizing resource forecast data. Interactive terminals are devices that allow users to interact with the system and view the displayed data, including personal computers, smartphones, tablets, and large internal information screens within enterprises.

[0118] In practical applications, the displayed data can be a list of resource prediction data for each user. Users can view the displayed data according to their corresponding permissions; different permissions correspond to different lists of data, with higher permissions allowing access to more data.

[0119] S4. Adjust the data parameters of the displayed data based on the customized instructions to obtain customized data that meets the requirements.

[0120] By adjusting the data parameters of the displayed data based on customized instructions, data can be flexibly filtered, combined, and presented according to the user's specific needs, providing users with personalized data services and improving the flexibility of data display.

[0121] Customization instructions are specific requests from users to the system regarding adjustments to displayed data parameters based on their own needs. Users can select a specific time range, specify a department or job category, and set filtering conditions for cost data. Data parameters are various conditions and variables used to define the scope, content, and presentation of displayed data, including parameters such as time, department, job, and cost. Customized data is data generated by the system after reprocessing the displayed data according to the user's input customization instructions to meet the user's specific needs. Requirement conditions are the conditions corresponding to the user's input instructions.

[0122] For example, when a user sets the time range to "the last six months", selects "all departments" as the department parameter, and focuses on filtering "recruitment costs" as the cost parameter, a list of data that meets the user's needs can be generated and displayed by combining these parameters, thus improving the flexibility of data display.

[0123] See Figure 3This is a schematic diagram of a structure based on an intelligent human resources data processing system provided in an embodiment of the present invention. The intelligent human resources data processing system includes:

[0124] The statistical analysis module is used to generate a data chain for each user based on the human resources data of each user in each data source. The data chain includes multiple cost nodes.

[0125] The data prediction module is used to input the historical data corresponding to the data chain into the prediction model and obtain the resource prediction data output by the prediction model.

[0126] The data display module is used to generate display data based on the resource prediction data corresponding to each user, and the display data is associated with multiple interactive terminals;

[0127] The data customization module is used to adjust the data parameters of the displayed data based on customization instructions to obtain customized data that meets the requirements.

[0128] Figure 3 The apparatus of the illustrated embodiment can be used to perform corresponding actions. Figure 2 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent human resource data processing, characterized in that, include: Based on the human resources data corresponding to each user in each data source, a data chain corresponding to each user is generated, and the data chain includes multiple cost nodes; Input the historical data corresponding to the data chain into the prediction model, and obtain the resource prediction data output by the prediction model, including: When the cost node corresponding to the historical data is a work element type, image data of the target area is obtained according to the prediction model; Based on the image data analysis, cost quantification data for each operational element is analyzed. These operational elements include equipment elements and area elements, including: Divide the image data into multiple work areas and determine the target area corresponding to the user in each of the multiple work areas; Calculate the cost quantification data corresponding to the regional elements based on the regional proportion of the target region; Obtain the equipment operating parameters in the target area, and calculate the cost quantification data corresponding to the equipment element based on the equipment operating parameters; Resource prediction data corresponding to the corresponding cost node is obtained based on the sum of the cost quantification data of each of the aforementioned work elements. Each of the cost quantification data is configured with an abnormal threshold. When the cost quantification data is greater than or equal to the abnormal threshold, an abnormal reminder message is generated. Display data is generated based on the resource prediction data corresponding to each user, and the display data is associated with multiple interactive terminals; Based on the customized instructions, the data parameters of the displayed data are adjusted to obtain customized data that meets the requirements.

2. The method according to claim 1, characterized in that, Based on the human resources data corresponding to each user from various data sources, a data chain is generated for each user. This data chain includes multiple cost nodes, including: Construct cost nodes corresponding to each cost type, map human resource data of each user to the corresponding cost nodes, generate data chains by associating the corresponding cost nodes with the unique identifier of each user, and add timestamps to each cost node.

3. The method according to claim 1, characterized in that, Determine the target region corresponding to the relevant user in multiple job regions, including: By comparing the user's workstation number with the area number of each work area, the work area corresponding to the area number that matches the workstation number is determined as the target area.

4. The method according to claim 3, characterized in that, The cost quantification data corresponding to the regional elements is calculated based on the regional proportion of the target region, including: The first quantitative data is obtained by multiplying the target area's proportion of the total area by the total site cost; The cost of public space is obtained, and a second quantitative data is obtained based on the ratio of the cost of public space to the number of users. The cost quantitative data is obtained based on the first and second quantitative data.

5. The method according to claim 1, characterized in that, Obtain the equipment operating parameters in the target area, and calculate the cost quantification data corresponding to the equipment element based on the equipment operating parameters, including: The device runtime and device damage value are obtained based on the image data, and the device operating parameters include the device runtime and device damage value; Based on the correspondence between preset duration and depreciation rate, the current depreciation rate corresponding to the device's operating duration is determined; Based on the adjustment factor corresponding to the equipment damage value, the current depreciation rate is updated to obtain the adjusted depreciation rate. Based on the adjusted depreciation rate, the initial cost of the equipment is depreciated to obtain the cost quantification data corresponding to the equipment element.

6. The method according to claim 5, characterized in that, The device runtime is obtained based on the image data, including: Extract the device outline from the image data, count the number of pixels in the device outline that are located in the preset pixel interval corresponding to the black screen, and obtain the black screen percentage based on the ratio of the number of pixels to the total number of pixels. When the percentage of black screen is less than the black screen pixel threshold, it is determined to be a device running state, and the total device runtime in the device running state is recorded.

7. The method according to claim 6, characterized in that, The device damage value is obtained based on the image data, including: Extract the device outline from the image data, and compare the stored initial device outline with the current device outline to obtain the outline similarity; When the contour similarity is less than the similarity threshold, the pixels with the same coordinates in the initial device contour and the device contour are compared. Obtain the difference region formed by pixels with inconsistent pixel values, identify the damage characteristics of the difference region, retrieve the preset damage value of the damage characteristics under the area corresponding to the device outline, and obtain the device damage value by multiplying the area ratio of the difference region and the device outline by the preset damage value.

8. A human resource data processing system, characterized in that, include: The statistical analysis module is used to generate a data chain for each user based on the human resources data of each user in each data source. The data chain includes multiple cost nodes. The data prediction module is used to input historical data corresponding to the data chain into the prediction model and obtain resource prediction data output by the prediction model, including: When the cost node corresponding to the historical data is a work element type, image data of the target area is obtained according to the prediction model; Based on the image data analysis, cost quantification data for each operational element is analyzed. These operational elements include equipment elements and area elements, including: Divide the image data into multiple work areas and determine the target area corresponding to the user in each of the multiple work areas; Calculate the cost quantification data corresponding to the regional elements based on the regional proportion of the target region; Obtain the equipment operating parameters in the target area, and calculate the cost quantification data corresponding to the equipment element based on the equipment operating parameters; Resource prediction data corresponding to the corresponding cost node is obtained based on the sum of the cost quantification data of each of the aforementioned work elements. Each of the cost quantification data is configured with an abnormal threshold. When the cost quantification data is greater than or equal to the abnormal threshold, an abnormal reminder message is generated. The data display module is used to generate display data based on the resource prediction data corresponding to each user, and the display data is associated with multiple interactive terminals; The data customization module is used to adjust the data parameters of the displayed data based on customization instructions to obtain customized data that meets the requirements.

Images