Public institution salary management system based on artificial intelligence

Abstract

The invention relates to the technical field of artificial intelligence and digital government affairs, and provides an artificial intelligence-based public institution salary management system, which comprises a downloading center module, a storage approval file index and a preset approval table, the notification center module generates an approval notification, pushes the approval notification through a mobile terminal, WeChat or a short message, and receives signing feedback to generate a real-time state; the short message notification module is used for sending a short message in a preset format when the salary changes or the filing auditing is completed; the approval and financing summarization module is used for collecting financing data in the approval process to generate a structured table and storing the structured table; and the statistical module is used for carrying out multi-dimensional statistical analysis on the capital increase data and generating a visual report. The examination and approval efficiency and the data accuracy can be improved, multi-dimensional statistical analysis and visual reports are provided, and intelligent decision support is provided for salary management of public institutions.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence and digital government technology, and more specifically, to an artificial intelligence-based salary management system for public institutions. Background Art

[0002] In the field of payroll management for public institutions, with the continuous development of information technology, traditional payroll management methods have gradually exposed numerous shortcomings. Early payroll management relied primarily on manual operations, involving reams of paper documents and cumbersome manual processes. This approach was not only inefficient but also prone to errors and data loss. With the introduction of computer technology, some institutions began to use spreadsheets and simple database management systems to process payroll data. However, these systems generally had limited functionality and lacked intelligence and automation, failing to meet the demands of modern public institutions for efficient, accurate, and transparent payroll management.

[0003] In recent years, although some organizations have attempted to introduce more advanced information technology, such as enterprise resource planning (ERP) systems, they still face numerous challenges in practical application. These systems often require extensive customization to accommodate the specific needs of different institutions, which not only increases costs but also prolongs implementation cycles. Furthermore, existing payroll management systems still have shortcomings in data security, approval process management, notification distribution, and data analysis. For example, data storage methods are relatively simple and lack effective backup and recovery mechanisms; approval processes are not flexible enough to adapt to complex payroll adjustment scenarios; notification distribution methods are not timely and efficient enough, resulting in delayed information transmission; and data analysis capabilities are relatively weak, failing to provide in-depth decision support for management.

[0004] In the process of implementing the embodiments of the present invention, the inventors discovered that there are at least the following problems or defects in the prior art: First, existing payroll management systems have hidden dangers in data security and lack effective security verification and permission control mechanisms, which can easily lead to data leakage or tampering. Second, the approval process is not intelligent enough and cannot automatically collect and summarize approval data, resulting in low management efficiency. Third, the notification release methods are not diverse enough and lack real-time monitoring and feedback mechanisms, making it difficult to ensure the effective transmission of notifications. Finally, the data analysis function is relatively limited, and it is impossible to conduct in-depth mining and visual display of payroll data, which cannot provide strong decision-making support for management. Summary of the Invention

[0005] The present invention provides an artificial intelligence-based salary management system for public institutions, comprising:

[0006] Download center module, used to store multiple approval document indexes and multiple preset approval forms;

[0007] The notification center module is used to generate approval notification data and publish it through mobile terminals, push it to the WeChat server or SMS server simultaneously, receive the receipt feedback data returned by the handler terminal and generate real-time receipt status;

[0008] The SMS notification module is used to trigger SMS generation instructions when a salary change event or file review completion event is detected, and send a preset format SMS containing change details or review results to the target teacher terminal;

[0009] The capital increase approval summary module is used to collect the capital increase data generated in each approval process, generate a structured capital increase approval form and store it in the preset database;

[0010] The statistical module is used to perform multi-dimensional statistical analysis on the data in the approval capital increase form and generate a visual report.

[0011] Furthermore, the download center module includes:

[0012] The approval document index module is used to classify and store multiple approval documents and generate searchable document index tags;

[0013] The approval form storage module is used to store multiple preset electronic form templates associated with the salary approval process of public institutions.

[0014] Furthermore, the notification center module includes:

[0015] Notification issuing unit, used to receive approval notification input data through the mobile terminal interface and generate standard notification message;

[0016] A cross-platform synchronization unit, used to synchronously send the standard notification message to the WeChat server and the SMS server interface;

[0017] The receipt feedback unit is used to receive the receipt confirmation signal returned by the handler terminal through the WeChat server or the SMS server, and update the unit receipt count and receipt timestamp in the real-time receipt status.

[0018] Furthermore, the SMS notification module includes:

[0019] The event trigger unit is used to monitor job adjustment data or job title change data in salary change events, as well as review status change data in the file review process;

[0020] The content generation unit is used to call the preset SMS template according to the event type and inject the corresponding variable parameters to generate the target SMS content;

[0021] The multi-channel distribution unit is used to send the target SMS content to the bound mobile phone number of the target teacher terminal through the SMS server interface, and receive a successful sending confirmation signal returned by the SMS server.

[0022] Furthermore, the capital increase approval summary module includes:

[0023] The data collection unit is used to extract the capital increase amount, effective time and adjustment basis fields from multiple approval process nodes;

[0024] A form generation unit, configured to fill the capital increase amount, effective time, and adjustment basis fields into a preset form structure in chronological order, and generate a capital increase approval form with a version identifier;

[0025] The version management unit is used to add a digital signature to the approval capital increase form and store it in the blockchain evidence node.

[0026] Furthermore, the statistics module includes:

[0027] The indicator configuration unit is used to receive statistical dimension parameters input by the user and generate data filtering conditions;

[0028] an analysis engine unit, configured to perform trend analysis, difference comparison, and outlier detection on the historical data in the approved capital increase form based on the data screening conditions;

[0029] The visualization rendering unit is used to convert the analysis results into at least one form of a bar chart, a line chart or a heat map and embed the result into the visualization report.

[0030] Furthermore, the approval document index module also includes:

[0031] A security verification unit is used to calculate a hash value for the approval file when generating a file index tag, and to bind the hash value to the index tag for storage;

[0032] The permission control unit is used to dynamically control the access rights and download permissions to the approval documents according to the user role identification.

[0033] Furthermore, the receipt feedback unit further includes:

[0034] A timeout warning unit, configured to generate a warning notification with a unit identifier and resend it to the WeChat server and SMS server when no receipt confirmation signal is received within a preset time;

[0035] The receipt statistics unit is used to generate unit receipt rate data and receipt delay time data according to the real-time receipt status.

[0036] Furthermore, the version management unit also includes:

[0037] The difference comparison unit is used to compare the newly generated capital increase approval form with the historical version at the field level and generate a change log;

[0038] The backtracking unit is used to retrieve the specified historical version of the capital increase approval form according to the version identifier stored in the blockchain evidence node.

[0039] Furthermore, the analysis engine unit further includes:

[0040] The prediction unit is used to build a time series model based on historical capital increase data, predict capital increase trends in future cycles, and generate prediction confidence indicators;

[0041] The association analysis unit is used to identify implicit patterns associated with job categories and professional title levels in the capital increase data through clustering algorithms.

[0042] The above-described embodiments of the present invention have at least the following beneficial effects: The AI-based public institution salary management system of the present invention can improve the efficiency and accuracy of salary management. The download center module enables efficient storage and retrieval of approval documents and pre-set approval forms, ensuring orderly and convenient file management. The notification center module enables the immediate release and simultaneous push of approval notifications across platforms, while also tracking receipt status in real time, improving the efficiency of notification delivery and the timeliness of management. The SMS notification module automatically triggers SMS notifications upon salary changes or file review completion, ensuring that relevant information is promptly and accurately communicated to targeted teachers, improving the timeliness and accuracy of information transmission. The capital increase approval summary module automatically collects capital increase data and generates a structured capital increase approval form. Furthermore, it uses blockchain evidence storage nodes for storage and version management, ensuring data security and traceability, and effectively reducing the risk of data loss or tampering. The statistics module performs multi-dimensional statistical analysis on the data in the capital increase approval form and generates intuitive visual reports, providing powerful decision support for management and enhancing the scientific nature and transparency of salary management.

[0043] In addition, the present invention can also enhance the security and flexibility of the salary management system. The security verification unit and the authority control unit in the approval document index module can ensure the safe storage and access control of the approval documents, and prevent unauthorized access and data leakage. The timeout warning unit and the receipt statistics unit in the receipt feedback unit can effectively monitor the receipt of notifications, promptly discover and deal with problems such as receipt delays, and improve the level of refined management. The difference comparison unit and the backtracking unit in the version management unit can conveniently perform version management and historical data tracing on the approval capital increase form, facilitate the discovery and correction of data errors, and ensure the accuracy and consistency of the data. The prediction unit and the correlation analysis unit in the analysis engine unit can perform capital increase trend prediction and correlation pattern recognition based on historical data, provide a scientific basis for salary adjustment and human resource planning, and further enhance the intelligence level of salary management. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily apparent by reading the following detailed description with reference to the accompanying drawings, in which several embodiments of the present invention are shown by way of example and not limitation, in which:

[0045] Figure 1 A schematic diagram of the structure of an artificial intelligence-based salary management system for public institutions provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0046] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided solely to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. Rather, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0047] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present invention may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0048] It should be noted that any number of elements in the drawings is for illustration only and not for limitation, and any naming is only for distinction and does not have any limiting meaning.

[0049] Reference below Figure 1 , Figure 1 This is a schematic diagram of the structure of an artificial intelligence-based salary management system for public institutions provided by one embodiment of the present invention. Figure 1As shown, an artificial intelligence-based salary management system for public institutions includes:

[0050] Download center module 101, used to store multiple approval document indexes and multiple preset approval forms;

[0051] Notification center module 102 is used to generate approval notification data and publish it through mobile terminals, synchronously push it to WeChat server or SMS server, receive the receipt feedback data returned by the handler terminal and generate real-time receipt status;

[0052] The SMS notification module 103 is used to trigger an SMS generation instruction when a salary change event or a file review completion event is detected, and send a preset format SMS containing change details or review results to the target teacher terminal;

[0053] The capital increase approval summary module 104 is used to collect the capital increase data generated in each approval process, generate a structured capital increase approval form and store it in a preset database;

[0054] The statistics module 105 is used to perform multi-dimensional statistical analysis on the data in the approval capital increase form and generate a visual report.

[0055] It should be noted that the download center module mentioned in the public institution salary management system of the present invention is used to store multiple approval document indexes and multiple preset approval forms. The approval document index here refers to a data structure that classifies and marks approval documents in order to quickly retrieve and locate the required documents, similar to the book catalog system in a library, where the corresponding files can be quickly found through specific tags or keywords. The preset approval form refers to an electronic form template that is pre-designed according to the public institution salary approval process. These templates contain various information fields that need to be filled in during the approval process, such as employee name, position, amount of capital increase, etc., which are used to standardize the approval process and improve approval efficiency. Through this modular design, the efficiency and accuracy of file management can be effectively improved, ensuring the orderly storage and convenient retrieval of approval documents.

[0056] Specifically, the notification center module is used to generate approval notification data and publish it through the mobile terminal, push it to the WeChat server or SMS server synchronously, receive the receipt feedback data returned by the agent's terminal and generate a real-time receipt status. Among them, the approval notification data refers to a data packet containing approval-related information, such as the start of the approval process, approval progress update, etc. These data are input through the mobile terminal interface and generate a standard notification message. The cross-platform synchronization unit ensures that notifications can be pushed on the WeChat server and the SMS server at the same time, covering the receiving preferences of different users. The receipt feedback data refers to the confirmation signal returned by the agent through WeChat or SMS after receiving the notification. The system receives these signals through the receipt feedback unit and updates the real-time receipt status, including the unit receipt count and receipt timestamp, thereby realizing real-time monitoring and management of the notification communication effect.

[0057] Preferably, the capital increase approval summary module collects the capital increase data generated in each approval process, generates a structured capital increase approval form and stores it in a preset database. In actual operation, the data collection unit can extract key information from multiple approval process nodes, such as the amount of capital increase, effective time and adjustment basis and other fields. The collection of these fields can be achieved through preset data interfaces and rules to ensure the accuracy and completeness of the data. The table generation unit fills the collected data into the preset table structure in chronological order, and adds a version identifier to each table for version management and historical data tracing. The version management unit further stores the capital increase approval form in the blockchain evidence node, using the tamper-proof nature of the blockchain to ensure the security and traceability of the data. In this way, the system can not only efficiently summarize and store capital increase data, but also provide reliable data support for subsequent data analysis and auditing.

[0058] In some embodiments, the download center module includes:

[0059] The approval document index module is used to classify and store multiple approval documents and generate searchable document index tags;

[0060] The approval form storage module is used to store multiple preset electronic form templates associated with the salary approval process of public institutions.

[0061] It should be noted that the download center module in the public institution salary management system of the present invention includes an approval file index module and an approval form storage module. The function of the approval file index module is to classify and store multiple approval files and generate searchable file index tags so that users can quickly locate the required files. The approval form storage module is used to store multiple preset electronic form templates associated with the public institution salary approval process. These templates provide a standardized format for the approval process, ensuring the standardization and consistency of the approval process. Through the collaborative work of these two modules, the download center module can effectively improve the efficiency and convenience of file management, and provide basic support for the efficient operation of the salary management system.

[0062] Specifically, when the approval document index module categorizes and stores approval documents, it will generate index tags based on the file's attributes or content. These attributes can include the file's type, department, approval level, etc. Through these tags, users can quickly find the required files through keyword search or category filtering. The preset spreadsheet templates stored in the approval form storage module cover various information fields involved in the salary approval process, such as employee basic information, job changes, increased funding amounts, and effective time. These templates can be customized according to different approval scenarios, such as new employee onboarding approval, job adjustment approval, or annual salary adjustment approval, to ensure that each approval process has corresponding standardized forms available. In this way, the approval document index module and the approval form storage module provide a clear logic and structure for file storage and retrieval of the salary management system.

[0063] Preferably, the approval document index module can use an automated classification algorithm when generating file index tags. For example, by performing text analysis on the title, content or keywords of the approval document, key information can be extracted and index tags can be generated. At the same time, when storing preset electronic form templates, the approval form storage module can set the fields and formats of the template according to different approval processes. For example, for the new employee entry approval form, fields such as employee name, entry date, and initial salary can be set; and for the position adjustment approval form, fields such as the reason for the position change and the comparison of the new and old position salaries can be set. In addition, the system can also set a unique identifier for each approval document and form template so that it can be quickly located and traced when needed. Through these detailed operating steps, the download center module can more efficiently manage and utilize approval documents and form templates, further improving the intelligence level of the salary management system.

[0064] In some embodiments, the notification center module includes:

[0065] Notification issuing unit, used to receive approval notification input data through the mobile terminal interface and generate standard notification message;

[0066] A cross-platform synchronization unit, used to synchronously send the standard notification message to the WeChat server and the SMS server interface;

[0067] The receipt feedback unit is used to receive the receipt confirmation signal returned by the handler terminal through the WeChat server or the SMS server, and update the unit receipt count and receipt timestamp in the real-time receipt status.

[0068] It should be noted that the Notification Center module is a key component of the public institution payroll management system for processing approval notifications. It receives approval notification input data via mobile terminals and generates standard notification messages. These messages are then synchronously sent to the WeChat and SMS server interfaces via a cross-platform synchronization unit. Furthermore, the Receipt Feedback Unit receives receipt confirmation signals from the handler's terminal via the WeChat or SMS server, and updates the unit's receipt count and receipt timestamp in the real-time receipt status. This module is designed to ensure efficient notification delivery and real-time monitoring of receipt status, thereby improving management efficiency and transparency.

[0069] Specifically, the notification publishing unit is one of the core components of the notification center module. It receives approval notification input data through the mobile terminal interface. This data usually includes information such as the start, progress update or completion of the approval process. Standard notification messages are generated according to a preset format to ensure the standardization and consistency of the notification content. The cross-platform synchronization unit is responsible for synchronously sending notification messages to the interfaces of the WeChat server and the SMS server. This means that notifications can be sent to relevant personnel in the form of WeChat messages or SMS messages, covering different user receiving preferences. The receipt feedback unit receives the receipt confirmation signal returned by the handler terminal. These signals can be read receipts of WeChat messages or confirmation replies of SMS messages. The unit receipt count refers to the number of units that successfully signed for the notification within a specific time, and the receipt timestamp records the specific time of each receipt action. This information is crucial for monitoring the communication effect of the notification and the progress of the management process.

[0070] Preferably, the notification publishing unit can generate standard notification messages through preset templates, and these templates can be customized according to different approval processes and notification types. For example, for the new employee entry approval notification, the template can contain information such as the employee's name, entry date, approval process number, etc. When sending notifications, the cross-platform synchronization unit can set the priority according to the user's preferences. For example, it can give priority to sending via WeChat, and if it fails, it can send it via SMS. The receipt feedback unit can set a timeout warning mechanism. If the receipt confirmation signal is not received within the preset time, the system will automatically trigger a warning notification to remind relevant personnel to deal with it in time.

[0071] Furthermore, the receipt statistics unit can generate unit receipt rate data and receipt delay data based on real-time receipt status. This data can be used to evaluate the efficiency and timeliness of notification delivery and provide decision support for management. Through these detailed operational steps, the notification center module can more efficiently process approval notifications, ensuring timely information delivery and refined management.

[0072] In some embodiments, the SMS notification module includes:

[0073] The event trigger unit is used to monitor job adjustment data or job title change data in salary change events, as well as review status change data in the file review process;

[0074] The content generation unit is used to call the preset SMS template according to the event type and inject the corresponding variable parameters to generate the target SMS content;

[0075] The multi-channel distribution unit is used to send the target SMS content to the bound mobile phone number of the target teacher terminal through the SMS server interface, and receive a successful sending confirmation signal returned by the SMS server.

[0076] It should be noted that the SMS notification module is a key component in the salary management system of public institutions that is used to send notifications to target teacher terminals when specific events occur. This module can trigger SMS generation instructions when a salary change event or a file review completion event is detected, and send a preset format SMS containing change details or review results to the target teacher terminal. A salary change event refers to a situation where an employee's salary changes due to job adjustments, job title changes, etc., and a file review completion event refers to a situation where the employee file review process is completed and the review results are obtained. Through the SMS notification module, the system can promptly send this important information to relevant personnel in the form of SMS, ensuring the timeliness and accuracy of information transmission.

[0077] Specifically, the SMS notification module includes an event triggering unit, a content generation unit, and a multi-channel distribution unit. The event triggering unit is responsible for monitoring job adjustment data or professional title change data in salary change events, as well as audit status change data in the file creation and review process. This data is typically stored in the system's database. The event triggering unit determines whether an event requiring notification has occurred by querying the relevant fields in the database in real time. The content generation unit then calls a preset SMS template based on the event type and injects the corresponding change parameters to generate the target SMS content. The preset SMS template is a pre-designed SMS format that contains necessary information fields, such as employee name, change type, and post-change salary. The multi-channel distribution unit sends the target SMS content to the bound mobile phone number of the target teacher's terminal through the SMS server interface and receives a successful delivery confirmation signal from the SMS server. This process ensures that the SMS is accurately delivered to the designated recipient.

[0078] Preferably, the event triggering unit can monitor changes in salary and file review status in real time by setting up scheduled tasks or database triggers. For example, it can be set to check the update status of relevant fields in the database every 10 minutes. When generating SMS content, the content generation unit can select the corresponding template according to different event types and dynamically fill in specific change parameters. For example, for a position adjustment event, the SMS template can be "Dear employee's name, your position has been adjusted from the original position to the new position, the salary has been adjusted accordingly to the new salary, and the effective date is the effective date." When sending SMS messages, the multi-channel distribution unit can record detailed information for each transmission, including the sending time, the receiving mobile phone number, the SMS content, etc., for subsequent query and statistics. In addition, the system can also set a retry mechanism for failed SMS sending to ensure that the SMS can be successfully delivered. Through these detailed operation steps, the SMS notification module can handle notification events more efficiently and ensure the timeliness and reliability of information transmission.

[0079] In some embodiments, the capital increase approval summary module includes:

[0080] The data collection unit is used to extract the capital increase amount, effective time and adjustment basis fields from multiple approval process nodes;

[0081] A form generation unit, configured to fill the capital increase amount, effective time, and adjustment basis fields into a preset form structure in chronological order, and generate a capital increase approval form with a version identifier;

[0082] The version management unit is used to add a digital signature to the approval capital increase form and store it in the blockchain evidence node.

[0083] It should be noted that the capital increase approval summary module is an important component of the salary management system of public institutions for collecting capital increase data generated in the approval process and generating structured capital increase approval forms. This module extracts key fields such as capital increase amount, effective time and adjustment basis from multiple approval process nodes through the data collection unit, and the form generation unit fills these fields into the preset table structure in chronological order to generate a capital increase approval form with a version identification. The version management unit is responsible for adding a digital signature to the capital increase approval form and storing it in the blockchain notarization node to ensure the security and traceability of the data. This module is designed to improve the efficiency and accuracy of capital increase data management, while enhancing the credibility and transparency of the data through blockchain technology.

[0084] Specifically, the capital increase approval summary module consists of three main units: a data collection unit, a table generation unit, and a version management unit. The data collection unit is responsible for extracting key information from each node in the approval process, such as the capital increase amount, effective date, and adjustment basis. These fields are typically stored in the system's database, and the data collection unit reads this data from the database using pre-set interfaces and rules. The table generation unit populates the collected data chronologically into a pre-set table structure to generate a structured capital increase approval form. The table structure consists of a header and a body. The header lists the field names, while the body contains the specific field values. The version management unit adds a digital signature to the generated capital increase approval form. A digital signature is a cryptographic verification method used to ensure the integrity and authenticity of the form content. The blockchain evidence storage node is used to store the capital increase approval form. The distributed ledger nature of the blockchain makes the data tamper-proof once stored, thereby enhancing the data's credibility and traceability.

[0085] Preferably, the data collection unit can collect data in the approval process in real time by setting a scheduled task or trigger. For example, whenever a node in the approval process is completed, the trigger automatically triggers the data collection operation. When generating the approval capital increase form, the form generation unit can set different form templates according to different approval processes. For example, for the annual salary adjustment approval process, the form template can contain fields such as employee name, position, capital increase amount, effective date, etc. When the version management unit adds a digital signature to the approval capital increase form, it can use an asymmetric encryption algorithm, such as the RSA algorithm, to generate a digital signature. When storing in the blockchain evidence node, the hash value of the form can be stored on the blockchain for subsequent verification of the integrity and authenticity of the form. Through these detailed operating steps, the approval capital increase summary module can more efficiently collect, generate and manage capital increase data to ensure the security and traceability of the data.

[0086] In some embodiments, the statistics module includes:

[0087] The indicator configuration unit is used to receive statistical dimension parameters input by the user and generate data filtering conditions;

[0088] an analysis engine unit, configured to perform trend analysis, difference comparison, and outlier detection on the historical data in the approved capital increase form based on the data screening conditions;

[0089] The visualization rendering unit is used to convert the analysis results into at least one form of a bar chart, a line chart or a heat map and embed the result into the visualization report.

[0090] It's important to note that the statistics module is a key component of the public institution payroll management system, used to perform multi-dimensional statistical analysis on the data in the approved capital increase forms and generate visual reports. This module receives user-entered statistical dimension parameters through the indicator configuration unit and generates data filtering conditions. The analysis engine unit then performs trend analysis, difference comparison, and outlier detection on historical data based on these conditions. Finally, the visual rendering unit converts the analysis results into bar charts, line graphs, or heat maps, and embeds them into visual reports. This module is designed to provide management with intuitive data analysis results to support better decision-making.

[0091] Specifically, the statistics module consists of three main units: the indicator configuration unit, the analysis engine unit, and the visualization rendering unit. The indicator configuration unit is responsible for receiving user-entered statistical dimension parameters, which can include time range, job category, and professional title level, and is used to generate data filtering criteria. For example, users can choose to perform statistical analysis by year, department, or position. The analysis engine unit processes historical data in the capital increase approval form based on these filtering criteria. Its functions include trend analysis, difference comparison, and outlier detection. Trend analysis is used to observe data trends over time, difference comparison is used to compare data differences between different categories, and outlier detection is used to identify data points that do not conform to the norm. The visualization rendering unit displays the analysis results in intuitive charts, such as bar charts for comparing numerical values ​​between different categories, line charts for displaying data trends over time, and heat maps for displaying data distribution density. These chart formats make complex data analysis results easier to understand and use.

[0092] Preferably, the indicator configuration unit can provide a user-friendly interface, allowing users to select statistical dimension parameters through a drop-down menu or input box. For example, the user can select a specific time range, such as January 2024 to December 2024, or select a specific job category, such as teachers or administrative staff. When performing trend analysis, the analysis engine unit can use time series analysis methods to smooth data fluctuations by calculating moving averages, thereby more clearly displaying the trend of the data. In difference comparison, statistical methods such as variance analysis or t-test can be used to evaluate the significant differences between different categories. Outlier detection can identify data points that are out of the normal range by calculating the standard deviation and mean of the data. When generating charts, the visual rendering unit can select different colors and styles according to the user's preferences, for example, using red to represent outliers and blue to represent normal values. Through these detailed operation steps, the statistical module can more efficiently process and display data analysis results, providing strong decision support for management.

[0093] In some embodiments, the approval file index module further includes:

[0094] A security verification unit is used to calculate a hash value for the approval file when generating a file index tag, and to bind the hash value to the index tag for storage;

[0095] The permission control unit is used to dynamically control the access rights and download permissions to the approval documents according to the user role identification.

[0096] It should be noted that the security verification unit and permission control unit in the approval document index module are key components used to ensure the security and access rights of approval documents in the public institution payroll management system. The security verification unit calculates a hash value for the approval document when generating the file index tag and stores the hash value bound to the index tag to ensure the integrity and consistency of the file. The permission control unit dynamically controls access and download permissions for approval documents based on user role identification to prevent unauthorized access and data leakage. Through the collaborative work of these two units, the system can effectively protect the security and confidentiality of approval documents and ensure the standardization and transparency of the payroll management process.

[0097] Specifically, the security verification unit calculates the hash value of the approval file through a hash algorithm. The hash value is a digital fingerprint of fixed length that can uniquely identify the content of the file. When the file content changes, the hash value will also change accordingly. Binding the hash value to the index tag for storage can ensure the integrity and consistency of the file during storage and retrieval. The permission control unit dynamically assigns access rights and download permissions based on the user's role identification. User role identification can include different levels such as administrators, ordinary users, and reviewers, and each role corresponds to different permission settings. For example, administrators can have full access and management permissions to all files, while ordinary users can only view files related to them. Through this role-based access control mechanism, the system can flexibly manage the permissions of different users to ensure the security and confidentiality of approval documents.

[0098] Preferably, the security verification unit can use a common hash algorithm, such as SHA-256, when calculating the hash value. When a file is uploaded or updated, the system automatically calculates the hash value of the file and stores it in the database together with the index tag of the file. When the file is retrieved or downloaded, the system calculates the hash value of the file again and compares it with the stored hash value. If the two are consistent, it means that the file has not been tampered with. When assigning permissions, the permission control unit can set different access levels based on the user's role identification. For example, the permission rules for each role are defined through configuration files or database tables, such as read, write, delete and other operation permissions. When a user requests to access a file, the system queries the corresponding permission rules based on the user's role identification to decide whether to allow the operation. Through these detailed operating steps, the approval file index module can more effectively protect the security and access control of approval files and ensure the stable operation of the salary management system.

[0099] In some embodiments, the receipt feedback unit further includes:

[0100] A timeout warning unit, configured to generate a warning notification with a unit identifier and resend it to the WeChat server and SMS server when no receipt confirmation signal is received within a preset time;

[0101] The receipt statistics unit is used to generate unit receipt rate data and receipt delay time data according to the real-time receipt status.

[0102] It should be noted that the Timeout Warning Unit and the Receipt Statistics Unit within the Receipt Feedback Unit are key components of the public institution payroll management system for monitoring notification receipts and generating receipt statistics. If the Timeout Warning Unit fails to receive a receipt confirmation signal within the preset time, it generates a warning notification with the unit's identification and resends it to the WeChat and SMS servers to ensure the timeliness and effectiveness of the notification. The Receipt Statistics Unit generates unit receipt rate data and receipt delay data based on real-time receipt status, providing management with quantitative analysis of receipt status, helping to optimize notification processes and improve management efficiency.

[0103] Specifically, the core function of the timeout warning unit is to monitor the receipt of receipt confirmation signals. The preset time refers to a reasonable waiting period set by the system after sending a notification, for example, it can be set to 24 hours. If no receipt confirmation signal is received from the handler's terminal within this time, the timeout warning unit triggers the warning mechanism. The unit identifier refers to the specific unit or department involved in the notification. It is used to clearly indicate the unit that has not signed in the warning notification, facilitating timely follow-up by management. The receipt statistics unit is responsible for collecting and analyzing real-time receipt status data, including unit receipt counts and receipt timestamps. The unit receipt rate refers to the ratio of the number of units that successfully signed for the notification within the specified time to the total number of units that should have signed, while the receipt delay refers to the time difference between the notification being sent and the actual receipt. This data provides management with an intuitive analysis of the receipt status, helping to evaluate the efficiency and timeliness of the notification process.

[0104] Preferably, the timeout warning unit can flexibly adjust the preset time according to the urgency and importance of the notification. For example, a shorter preset time, such as 12 hours, can be set for emergency notifications, and a longer preset time, such as 48 hours, can be set for routine notifications. When generating a warning notification, detailed information such as the specific name of the unit that did not sign for it, the type of notification, and the time the notification was sent can be included, so that relevant personnel can quickly understand the situation and take measures. When generating the receipt rate data, the receipt statistics unit can classify and count it by time period, department, or notification type, and generate a detailed receipt report. For example, the receipt rate of each department can be counted on a monthly basis, or the average receipt delay time can be counted by notification type. Through these detailed operating steps, the receipt feedback unit can more effectively monitor the receipt of notifications and provide comprehensive receipt data support to management, thereby optimizing the notification process and improving management efficiency.

[0105] In some embodiments, the version management unit further includes:

[0106] The difference comparison unit is used to compare the newly generated capital increase approval form with the historical version at the field level and generate a change log;

[0107] The backtracking unit is used to retrieve the specified historical version of the capital increase approval form according to the version identifier stored in the blockchain evidence node.

[0108] It should be noted that the difference comparison unit and backtracking unit within the version management unit are key components of the public institution salary management system for ensuring version management and data traceability of the approval and capital increase form. The difference comparison unit compares the newly generated approval and capital increase form with the historical version at the field level and generates a change log. This helps record the specific content of each version update, facilitating tracking and auditing. The backtracking unit retrieves a specified historical version of the approval and capital increase form based on the version identifier stored in the blockchain evidence node, ensuring that historical data can be quickly restored or reviewed when needed, enhancing system reliability and transparency.

[0109] Specifically, the core function of the difference comparison unit is to perform a detailed field-level comparison of different versions of the capital increase approval form. Field-level difference comparison refers to checking each field in the form one by one, such as the capital increase amount, effective time, adjustment basis, etc., and comparing the differences between the old and new versions. The change log is a document that records these differences. It describes in detail which fields have changed, the specific content of the changes, and the timestamp of the changes. The retrospective unit relies on the version identifier stored in the blockchain evidence node to locate and retrieve historical versions of the form. The version identifier is a unique identifier used to distinguish different versions of a form. It usually contains information such as the version number and timestamp to ensure that each version can be accurately identified and retrieved.

[0110] Preferably, the difference comparison unit can use automated scripts or tools to implement field-level comparisons. For example, after a new version of a form is generated, the system can automatically call the comparison tool to compare the data of the old and new versions field by field. For each difference found, the system will record the field name, old value, new value, and change time to generate a detailed change log. When retrieving historical versions, the backtracking unit can provide a version selection function through the user interface, allowing the user to enter or select a specific version identifier. Based on the input version identifier, the system retrieves the corresponding form from the blockchain evidence node and displays it to the user. In order to improve efficiency, the system can cache commonly used historical versions locally to reduce the frequency of access to the blockchain evidence node. Through these detailed operating steps, the version management unit can more efficiently manage the versions of the approval capital increase form, ensuring the traceability of the data and the reliability of the system.

[0111] In some embodiments, the analysis engine unit further comprises:

[0112] The prediction unit is used to build a time series model based on historical capital increase data, predict capital increase trends in future cycles, and generate prediction confidence indicators;

[0113] The association analysis unit is used to identify implicit patterns associated with job categories and professional title levels in the capital increase data through clustering algorithms.

[0114] It's important to note that the Forecasting Unit and the Correlation Analysis Unit within the Analytical Engine are key components of the public institution salary management system for data analysis and decision support. The Forecasting Unit constructs a time series model based on historical salary increase data to predict salary increase trends in future cycles and generate a prediction confidence indicator. The Correlation Analysis Unit uses a clustering algorithm to identify implicit patterns in salary increase data related to job categories and professional title levels. This helps management better understand the factors influencing salary adjustments and formulate more appropriate salary policies.

[0115] Specifically, the core function of the prediction unit is to construct a time series model using historical salary increase data. A time series model is a statistical model used to analyze and predict time series data—data points arranged in chronological order. In this system, historical salary increase data refers to records of employee salary adjustments over a period of time, including information such as the salary increase amount and effective date. The prediction unit analyzes the time series characteristics of this data to construct a model to predict salary increase trends in future cycles. The prediction confidence index quantitatively assesses the reliability of the prediction results, typically calculated based on the model's goodness of fit and margin of error. The association analysis unit uses clustering algorithms to identify hidden patterns in the salary increase data. Clustering algorithms are data mining techniques that divide data points into clusters, ensuring high similarity among data points within the same cluster and low similarity among data points in different clusters. In this system, the association analysis unit uses clustering algorithms to analyze the relationship between salary increase data and job categories and professional titles, thereby discovering potential correlation patterns.

[0116] Preferably, the prediction unit can employ common statistical methods, such as the ARIMA autoregressive integrated moving average model, when constructing the time series model. This model predicts future data points by analyzing the autocorrelation and moving average characteristics of the data. In practical applications, the system can automatically select appropriate model parameters, such as the order of the autoregressive term, the number of differencing operations, and the order of the moving average term, based on the time series characteristics of historical capital increase data. The association analysis unit can employ the K-means algorithm when performing cluster analysis. This algorithm discovers structure in the data by partitioning data points into K clusters. In this system, capital increase data can be combined with features such as job category and professional title level as input parameters for cluster analysis. For example, an employee's job category, professional title level, and capital increase amount can be used as feature vectors and partitioned into clusters using the K-means algorithm to identify capital increase patterns across job categories and professional title levels. Through these refined steps, the analysis engine unit can provide management with more accurate capital increase trend forecasts and more in-depth association analysis results, thereby supporting more informed salary decisions.

[0117] The aforementioned embodiments of the present invention have the following beneficial effects: the system can improve the efficiency of payroll management in public institutions. The download center module enables intelligent classification, storage, and rapid retrieval of approval documents. The notification center module ensures real-time synchronization of approval information across platforms and tracks receipt status. The SMS notification module automatically triggers salary change reminders, improving the timeliness of information dissemination. The approval and capital increase summary module enables structured storage of approval data and supports blockchain-based evidence storage, ensuring data security and traceability. The statistics module analyzes salary change trends in multiple dimensions and generates visual reports, providing data support for decision-making.

[0118] The system also optimizes management processes. Security verification and permission control prevent file leaks or unauthorized access. Timeout warnings automatically resend unsigned notifications to ensure information is delivered. Version management records each approval change and supports historical review. Difference comparison automatically generates a change log. Predictive models analyze salary increase patterns and predict future trends. Correlation analysis uncovers potential connections between salary and positions and titles, helping managers develop more informed salary policies. This comprehensive solution enables digital and intelligent management of the entire salary approval process, reducing manual intervention and error rates.

[0119] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, or a tablet.

[0120] The above descriptions are merely some preferred embodiments of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also encompass other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by mutually replacing the above-mentioned features with (but not limited to) technical features having similar functions disclosed in the embodiments of the present invention.

Claims

1. An artificial intelligence-based salary management system for public institutions, characterized in that: include: Download center module, used to store multiple approval document indexes and multiple preset approval forms; The notification center module is used to generate approval notification data and publish it through mobile terminals, synchronously push it to the WeChat server or SMS server, receive the receipt feedback data returned by the handler terminal and generate real-time receipt status; The SMS notification module is used to trigger SMS generation instructions when a salary change event or file review completion event is detected, and send a preset format SMS containing change details or review results to the target teacher terminal; The capital increase approval summary module is used to collect the capital increase data generated in each approval process, generate a structured capital increase approval form and store it in the preset database; The statistical module is used to perform multi-dimensional statistical analysis on the data in the approval capital increase form and generate a visual report.

2. The artificial intelligence-based salary management system for public institutions according to claim 1 is characterized in that: The download center module includes: The approval document index module is used to classify and store multiple approval documents and generate searchable document index tags; The approval form storage module is used to store multiple preset electronic form templates associated with the salary approval process of public institutions.

3. The artificial intelligence-based salary management system for public institutions according to claim 1 is characterized in that: The notification center module includes: Notification issuing unit, used to receive approval notification input data through the mobile terminal interface and generate standard notification message; A cross-platform synchronization unit, used to synchronously send the standard notification message to the WeChat server and the SMS server interface; The receipt feedback unit is used to receive the receipt confirmation signal returned by the handler terminal through the WeChat server or the SMS server, and update the unit receipt count and receipt timestamp in the real-time receipt status.

4. The artificial intelligence-based salary management system for public institutions according to claim 1 is characterized in that: The SMS notification module includes: The event trigger unit is used to monitor job adjustment data or job title change data in salary change events, as well as review status change data in the file review process; The content generation unit is used to call the preset SMS template according to the event type and inject the corresponding variable parameters to generate the target SMS content; The multi-channel distribution unit is used to send the target SMS content to the bound mobile phone number of the target teacher terminal through the SMS service interface, and receive a successful sending confirmation signal returned by the SMS service.

5. The artificial intelligence-based salary management system for public institutions according to claim 1 is characterized in that: The capital increase approval summary module includes: The data collection unit is used to extract the capital increase amount, effective time and adjustment basis fields from multiple approval process nodes; A form generation unit, configured to fill the capital increase amount, effective time, and adjustment basis fields into a preset form structure in chronological order, and generate a capital increase approval form with a version identifier; The version management unit is used to add a digital signature to the approval capital increase form and store it in the blockchain evidence node.

6. The artificial intelligence-based salary management system for public institutions according to claim 1 is characterized in that: The statistics module includes: The indicator configuration unit is used to receive statistical dimension parameters input by the user and generate data filtering conditions; an analysis engine unit, configured to perform trend analysis, difference comparison, and outlier detection on the historical data in the approved capital increase form based on the data screening conditions; The visualization rendering unit is used to convert the analysis results into at least one form of a bar chart, a line chart or a heat map and embed the result into the visualization report.

7. The artificial intelligence-based salary management system for public institutions according to claim 2 is characterized in that: The approval document index module also includes: A security verification unit is used to calculate a hash value for the approval file when generating a file index tag, and to bind the hash value to the index tag for storage; The permission control unit is used to dynamically control the access rights and download permissions to the approval documents according to the user role identification.

8. The artificial intelligence-based salary management system for public institutions according to claim 3 is characterized in that: The receipt feedback unit further includes: A timeout warning unit, configured to generate a warning notification with a unit identifier and resend it to the WeChat server and SMS server when no receipt confirmation signal is received within a preset time; The receipt statistics unit is used to generate unit receipt rate data and receipt delay time data according to the real-time receipt status.

9. The artificial intelligence-based salary management system for public institutions according to claim 5 is characterized in that: The version management unit also includes: The difference comparison unit is used to compare the newly generated capital increase approval form with the historical version at the field level and generate a change log; The backtracking unit is used to retrieve the specified historical version of the capital increase approval form according to the version identifier stored in the blockchain evidence node.

10. The artificial intelligence-based salary management system for public institutions according to claim 6 is characterized in that: The analysis engine unit further includes: The prediction unit is used to build a time series model based on historical capital increase data, predict capital increase trends in future cycles, and generate prediction confidence indicators; The association analysis unit is used to identify implicit patterns associated with job categories and professional title levels in the capital increase data through clustering algorithms.

Images