Employee subsidy issuing configuration system, method, equipment and product based on large model

Abstract

The invention discloses an employee subsidy issuing configuration system, method, equipment and product based on a large model, and the system comprises an analysis and extraction module which is used for analyzing a subsidy declaration form template through calling a first large model, and extracting a calculation rule of a plurality of fields and a target field; the display editing module is used for supporting constraint conditions of the user input fields and editing the multiple fields and the calculation rules; the compliance verification unit is used for calling legal regulations and internal regulations of an enterprise through a second large model and carrying out compliance verification on calculation rules and constraint conditions; the back-end configuration unit is used for converting a plurality of fields, calculation rules and constraint conditions confirmed by the user into parameter templates through a second large model, and constructing an application programming interface for accessing a back end; and the front-end configuration unit is used for creating a subsidy issuing declaration page according to the parameter template. Configuration of the subsidy issuing tool is realized based on the natural language, the development difficulty can be reduced, and the configuration efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a system, method, electronic device, computer-readable storage medium, and computer program product for distributing employee subsidies based on a large model. Background Art

[0002] As companies expand and their employee benefits systems improve, employee subsidy distribution requirements become increasingly diverse and compliant. Traditional subsidy distribution systems typically use fixed form templates, with human resources departments manually configuring fields and calculation rules. However, this approach has the following drawbacks:

[0003] 1) Low configuration efficiency: Every time the subsidy type or rules are adjusted, technical personnel are required to modify the back-end code and front-end pages, which results in a long development cycle and an inability to quickly respond to policy changes or corporate needs.

[0004] 2) High compliance risk: Subsidy distribution must comply with labor laws, tax regulations, and internal corporate systems. Manual verification is prone to omissions or errors, leading to legal disputes or financial losses.

[0005] 3) Lack of flexibility: Field constraints (such as type, range, and association) and calculation rules (such as subsidy amount formula) need to be hard-coded and difficult to support dynamic adjustment.

[0006] In existing technologies, some systems attempt to simplify configuration through rule engines or low-code platforms, but the following issues still exist: While rule engines support logical configuration, they require professional syntax development and cannot automatically link legal clauses with corporate systems. Low-code tools provide a visual interface, but field mapping and front-end and back-end linkage still need to be completed manually, and they lack intelligent compliance verification capabilities. As enterprises accelerate their digital transformation, small and medium-sized enterprises and non-technical users, in particular, urgently need a more user-friendly employee subsidy distribution configuration system to configure personalized subsidy distribution tools to enable their respective subsidy application and distribution. Summary of the Invention

[0007] In view of this, embodiments of the present application provide a large-scale model-based employee subsidy payment configuration system, method, electronic device, computer-readable storage medium and computer program product for solving at least one of the above technical problems.

[0008] In a first aspect, an embodiment of the present application provides an employee subsidy distribution configuration system based on a large model, comprising:

[0009] An analysis and extraction module is used to analyze the subsidy application form template uploaded by the user by calling the first model, extract multiple fields that need to be filled in or confirmed by the employee, and calculation rules for the target field, where the target field includes at least the subsidy amount field;

[0010] A display and editing module is used to display the calculation rules of the extracted multiple fields and target fields through a configuration interface. The configuration interface is provided with input controls, which are used to support users to modify and confirm the calculation rules of the multiple fields and target fields, as well as input field constraints;

[0011] The second largest model processing module includes a compliance verification unit, a backend configuration unit, and a frontend configuration unit, wherein:

[0012] The compliance verification unit is used to retrieve the legal regulations related to subsidy issuance and the internal regulations of the enterprise to which the template belongs through the second largest model, and to perform compliance verification on the calculation rules and constraints based on the legal regulations and internal regulations;

[0013] After compliance verification is successful, the backend configuration unit is used to convert the multiple fields confirmed by the user, the calculation rules and constraints of the target field into a parameter template that can be executed by the system through the second largest model. Based on the parameter template, an application programming interface for accessing the backend is built. The parameter template includes the field name, constraints, the calculation rules of the target field, and the mapping relationship between each field and the corresponding field in the database.

[0014] The front-end configuration unit is used to create a subsidy payment declaration page based on the parameter template, and to establish an association between the subsidy payment declaration page and the back-end based on the application programming interface; the subsidy payment declaration page is used to interact with employees to complete the filling and display of the subsidy declaration form.

[0015] According to some embodiments of the present application, optionally, the constraint conditions include field type, field length, field filling range, and association relationship between fields, and the backend configuration unit is specifically used to set the field type, field length, field filling range, and association relationship between fields of multiple fields in the parameter template according to the constraint conditions; and map each field to a corresponding field in the database, and set a mapping relationship between each field and the corresponding field in the database in the parameter template;

[0016] The front-end configuration unit is specifically used to match the corresponding user interface components according to the field type of each field, and automatically arrange the user interface components according to the preset field priority; convert the constraints in the parameter template into front-end verification logic, and synchronize the front-end verification logic to the back-end; and establish the submission logic for the information filled in by employees.

[0017] According to some embodiments of the present application, optionally, the configuration interface is further provided with a query control, which is used to support users in querying the laws and regulations related to subsidy issuance and the internal regulations of the enterprise to which the template belongs, and parse the target laws and regulations and / or target internal regulations selected by the user through the first large model to obtain the key fields and constraints associated with the target laws and regulations and / or target internal regulations, and automatically configure the constraints of the key fields according to the parsing results.

[0018] According to some embodiments of the present application, optionally, the configuration interface is further provided with a sensitive field marking switch, forcing the user to mark the fields that need to be desensitized.

[0019] According to some embodiments of the present application, optionally, the compliance verification unit is also used to output a compliance report, which includes calculation rules or constraints that failed the verification, referenced laws and regulations or internal regulations, and correction suggestions, and supports one-click adoption of correction suggestions, automatically replacing the calculation rules or constraints that failed the verification based on the correction suggestions.

[0020] According to some embodiments of the present application, optionally, a chat portal is provided on the subsidy payment application page, which supports employees to initiate consultations or make complaints when they have questions about the meaning of form fields, calculation rules or filling requirements.

[0021] According to some embodiments of the present application, optionally, the system also includes a consultation response module, which is used to automatically respond to employee consultation questions through the second largest model; and when an employee applies for a manual response, the second largest model is used to perform keyword recognition on the employee consultation questions, and questions involving calculation rules and constraints are automatically assigned to legal personnel for processing, and questions involving employee personal information are automatically assigned to human resources management personnel for processing.

[0022] In a second aspect, an embodiment of the present application provides a method for allocating employee subsidies based on a large model, including:

[0023] By calling the first model to analyze the subsidy application form template uploaded by the user, multiple fields that need to be filled in or confirmed by the employee and the calculation rules of the target field are extracted. The target field includes at least the subsidy amount field;

[0024] The calculation rules of multiple fields and target fields are displayed through the configuration interface, and the user is allowed to modify and confirm the calculation rules of multiple fields and target fields, as well as the constraints of the fields;

[0025] The second model retrieves the legal regulations related to subsidy disbursement and the internal regulations of the enterprise to which the template belongs, and performs compliance verification on the calculation rules and constraints based on the legal regulations and internal regulations;

[0026] After the compliance check is successful, the second model converts the multiple fields confirmed by the user, the calculation rules and constraints of the target field into a parameter template that the system can execute. Based on the parameter template, an application programming interface for accessing the backend is built. The parameter template contains the field name, constraints, the calculation rules of the target field, and the mapping relationship between each field and the corresponding field in the database.

[0027] Based on the parameter template, a subsidy payment declaration page is created, and based on the application programming interface, an association is established between the subsidy payment declaration page and the backend; among them, the subsidy payment declaration page is used to interact with employees to complete the filling and display of the subsidy declaration form.

[0028] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, the steps of the method described above are implemented.

[0029] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions, when executed by a processor, implement the steps of the method described above.

[0030] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes computer program instructions, and when the computer program instructions are executed by a processor, the steps of the method described above are implemented.

[0031] The employee subsidy payment configuration system, method, electronic device, computer-readable storage medium and computer program product based on the big model provided by the embodiments of the present application can automatically parse the subsidy application form template uploaded by the user and complete the configuration of the back-end and front-end subsidy payment application pages through the natural language understanding ability of the big model, thereby reducing manual intervention and improving configuration efficiency. Moreover, it can be developed directly by non-technical personnel (such as legal personnel or human resources management personnel) through natural language, and the configuration of the back-end and front-end pages can be achieved without professional programmers, which reduces communication costs and reduces the difficulty of enterprise (especially small and medium-sized enterprises) development tools. In addition, the automatic conversion of parameter templates and the automatic construction of application programming interfaces also avoid manual coding, allowing the system to quickly adapt to changes in different subsidy policies.

[0032] Furthermore, this application uses a large-scale model to search and compare legal provisions and internal corporate regulations in real time, ensuring that subsidy rules meet the latest compliance requirements. This automated compliance verification reduces human error and avoids legal disputes or financial losses caused by non-compliant grants. Furthermore, through a visual configuration interface and parameterized configuration, this application allows non-technical personnel to quickly adjust subsidy rules, improving system maintainability. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings in the embodiments of the present application.

[0034] Figure 1 A structural block diagram of the employee subsidy distribution configuration system based on a large model provided in an embodiment of the present application.

[0035] Figure 2 A working diagram of the analysis and extraction module.

[0036] Figure 3 The subsidy payment application page is schematically shown.

[0037] Figure 4 A flowchart of a method for configuring employee subsidy distribution based on a large model provided in an embodiment of the present application.

[0038] Figure 5 A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0039] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present application by illustrating the examples of the present application.

[0040] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0041] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0042] It will be apparent to those skilled in the art that various modifications and variations can be made in this application without departing from the spirit or scope of this application. Therefore, this application is intended to cover modifications and variations of this application that fall within the scope of the corresponding claims (technical solutions claimed for protection) and their equivalents. It should be noted that the embodiments provided in the examples of this application can be combined with each other without contradiction.

[0043] Before describing the technical solutions provided by the embodiments of the present application, in order to facilitate understanding of the embodiments of the present application, the present application first specifically describes the problems existing in the prior art:

[0044] As companies expand and their employee benefits systems improve, employee subsidy distribution requirements become increasingly diverse and compliant. Traditional subsidy distribution systems typically use fixed form templates, with human resources departments manually configuring fields and calculation rules. However, this approach has the following drawbacks:

[0045] 1) Low configuration efficiency: Every time the subsidy type or rules are adjusted, technical personnel are required to modify the back-end code and front-end pages, which results in a long development cycle and an inability to quickly respond to policy changes or corporate needs.

[0046] 2) High compliance risk: Subsidy distribution must comply with labor laws, tax regulations, and internal corporate systems. Manual verification is prone to omissions or errors, leading to legal disputes or financial losses.

[0047] 3) Lack of flexibility: Field constraints (such as type, range, and association) and calculation rules (such as subsidy amount formula) need to be hard-coded and difficult to support dynamic adjustment.

[0048] In existing technologies, some systems attempt to simplify configuration through rule engines or low-code platforms, but the following issues still exist: While rule engines support logical configuration, they require professional syntax development and cannot automatically link legal clauses with corporate systems. Low-code tools provide a visual interface, but field mapping and front-end and back-end linkage still need to be completed manually, and they lack intelligent compliance verification capabilities. As enterprises accelerate their digital transformation, small and medium-sized enterprises and non-technical users, in particular, urgently need a more user-friendly employee subsidy distribution configuration system to configure personalized subsidy distribution tools to enable their respective subsidy application and distribution.

[0049] The development of big model technology in natural language processing offers new solutions to these problems. For example, big models can automatically parse policy texts, generate configuration logic, or answer employee questions through interactive conversations. However, currently, no system fully integrates big model capabilities into the entire subsidy disbursement process, providing an integrated solution from template parsing and compliance verification to automated front-end and back-end configuration.

[0050] In view of this, the embodiments of the present application provide a large-model-based employee subsidy payment configuration system, method, electronic device, computer-readable storage medium and computer program product, which can solve at least one of the above-mentioned technical problems existing in the prior art.

[0051] The following first introduces the employee subsidy distribution configuration system based on the large model provided in the embodiment of the present application.

[0052] The Big Model-Based Employee Subsidy Disbursement Configuration System provided in this application embodiment utilizes Big Model (AI) technology to automatically parse subsidy application form templates, perform compliance verification, configure front-end and back-end configuration, and implement employee interaction. This system can significantly improve subsidy disbursement configuration efficiency, ensure compliance, and optimize the employee filling experience.

[0053] Figure 1 This is a structural diagram of the employee subsidy distribution configuration system based on a large model provided in the embodiment of this application. Figure 1 As shown, the employee subsidy payment configuration system 10 based on the large model provided in the embodiment of the present application may include an analysis and extraction module 110, a display and editing module 120, and a second large model processing module 130. The second large model processing module 130 may include a compliance verification unit 131, a back-end configuration unit 132, and a front-end configuration unit 133.

[0054] The analysis and extraction module 110 can be used to analyze the subsidy application form template uploaded by the user by calling the first large model, and extract multiple fields that need to be filled in or confirmed by the employee and the calculation rules of the target field. Among them, the target field can at least include the subsidy amount field.

[0055] In the employee subsidy payment configuration system based on the large model, the first and second models respectively undertake different AI processing tasks. The first model focuses on natural language understanding (NLP), and is mainly used to parse subsidy form templates, extract fields and calculation rules. For example, the first model can be used to input subsidy application form templates uploaded by users (such as Excel / Word), and through semantic analysis, understand which fields in the template need to be filled in by employees and which are automatically calculated by the system, and output structured field lists and calculation rules. The second model focuses on rule reasoning and code generation, and is mainly used for compliance verification and front-end and back-end automated configuration. For example, the second model can be used to input fields, calculation rules and constraints confirmed by users, and generate compliance reports, executable parameter templates, back-end application programming interfaces (APIs) and front-end pages.

[0056] Figure 2 This is a working diagram of the analysis and extraction module. Figure 2 As shown, the subsidy application form template may include multiple fields that employees need to fill in or confirm and calculation rules for target fields. For example, in some embodiments, the subsidy application form template may include the following fields: employee name, ID number, age, length of service, gender, department, position / rank, date of employment, bank card number, subsidy project name, subsidy amount, pre-tax / post-tax identification, whether included in the social security base, attachment upload, approver / approval opinion and / or employee confirmation signature, etc. In addition, the subsidy application form template may also include calculation rules for target fields, such as subsidy amount = daily standard × actual working days. It should be noted that the various fields and calculation rules in the subsidy application form template can be flexibly adjusted according to actual conditions, and different enterprises can personalize the various fields and calculation rules in the subsidy application form template to meet the personalized needs of subsidy issuance for different enterprises.

[0057] The first model uses natural language understanding technology to perform semantic analysis on user-uploaded subsidy application form templates, extracting multiple fields that employees need to fill in or confirm, as well as calculation rules for target fields. For example, the calculation rules for the multiple fields and target fields listed above can be extracted, but this application does not limit this.

[0058] The display editing module 120 is used to provide a visual configuration interface, which displays the calculation rules of multiple fields and target fields extracted by the first large model, so that users (such as legal personnel or human resources management personnel) can check whether the calculation rules of the extracted multiple fields and target fields are incorrect and whether they need to be adjusted.

[0059] The configuration interface features input controls, such as input boxes. These controls allow users to modify and confirm calculation rules for multiple fields and target fields, as well as enter field constraints. Specifically, users can use the input controls to add, delete, or modify calculation rules for fields and / or target fields. If the user determines that the extracted calculation rules for multiple fields and target fields are correct, or that the modified calculation rules meet expectations, they can use the input controls to confirm the final calculation rules for multiple fields and target fields. Furthermore, the input controls allow users to enter field constraints. Constraints may include field type, field length, field entry range, and inter-field relationships. For example, field entry ranges may include: age must be greater than or equal to 16 or 18 years old, length of service must be greater than one year, department affiliation must be Department A or Department B, and subsidy amount must be less than 50,000 yuan. Inter-field relationships represent matching and / or significant relationships between at least two fields, such as requiring an ID number to match an employee's name or requiring a subsidy amount to be less than or equal to 20% of pre-tax salary.

[0060] In this way, non-technical personnel (such as legal personnel or human resources management personnel) do not need to program, but can use natural language through a visual configuration interface to directly adjust the calculation rules of fields and target fields, thereby lowering the development and maintenance thresholds of subsidy distribution tools.

[0061] In some embodiments, the second large model processing module 130 is further divided into three core units, namely a compliance verification unit 131, a backend configuration unit 132 and a frontend configuration unit 133, which respectively implement compliance verification, backend configuration and frontend generation.

[0062] The compliance verification unit 131 can be used to retrieve, through the second model, legal regulations related to subsidy disbursement and the internal regulations of the enterprise to which the template belongs, such as the latest labor law regulations, personal income tax law regulations, corporate income tax law regulations, and employee subsidy-related documents of the enterprise to which the template belongs. The compliance verification unit 131 can also be used to automatically perform compliance verification on calculation rules and constraints based on legal regulations and internal regulations. For example, it can verify whether the constraints on age, length of service, and subsidy amount comply with the requirements of legal regulations and internal enterprise regulations, and verify whether the calculation rules for subsidy amount comply with the requirements of legal regulations and internal enterprise regulations.

[0063] In this way, the compliance verification unit 131 calls the second largest model to retrieve the laws and regulations and internal corporate systems related to subsidy issuance, and automatically verifies whether the calculation rules and constraints configured by the user meet the compliance requirements. This can avoid omissions in manual policy review, ensure that subsidy issuance is legal and compliant, and reduce corporate legal risks.

[0064] The backend configuration unit 132 can be used to convert the calculation rules and constraints of multiple fields confirmed by the user and the target field into a system-executable parameter template through the second large model after the compliance check is successful, and build an application programming interface (API) for accessing the backend based on the parameter template.

[0065] Specifically, after the compliance check succeeds, the backend configuration unit 132 can convert the multiple fields confirmed by the user in natural language, the calculation rules and constraints of the target field into a machine-readable parameter template (Schema) such as JSON format by calling the second large model. Among them, the parameter template can include the field name, constraints, the calculation rules of the target field, and the mapping relationship between each field and the corresponding field in the database. Then, the second large model can build an API for accessing the backend based on the parameter template, such as POST / api / ...

[0066] In this way, the second largest model automatically generates structured parameters and accesses the backend API, eliminating the need for manual coding by users and improving development efficiency.

[0067] Accordingly, the front-end configuration unit 133 may be used to create a subsidy payment declaration page according to the parameter template, and to establish an association between the subsidy payment declaration page and the back-end based on the application programming interface. Figure 3 The subsidy payment application page is shown schematically. Figure 3 As shown, the subsidy application page can be used to interact with employees and complete the completion and display of subsidy application forms. That is, based on the parameter template generated by the back-end configuration unit 132, the front-end configuration unit 133 can automatically construct the subsidy application page by calling the second model and establish data interaction with the back-end API to enable employees to complete, submit, and display subsidy application forms.

[0068] The embodiment of the present application provides an employee subsidy payment configuration system based on a large model. Through the natural language understanding ability of the large model, it automatically parses the subsidy application form template uploaded by the user and completes the configuration of the back-end and front-end subsidy payment application pages, reducing manual intervention and improving configuration efficiency. Moreover, it can be developed directly by non-technical personnel (such as legal personnel or human resources management personnel) through natural language, and the configuration of the back-end and front-end pages can be achieved without professional programmers, which reduces communication costs and reduces the difficulty of enterprise (especially small and medium-sized enterprises) development tools. In addition, the automatic conversion of parameter templates and the automatic construction of application programming interfaces also avoid manual coding, allowing the system to quickly adapt to changes in different subsidy policies.

[0069] Furthermore, this application uses a large-scale model to search and compare legal provisions and internal corporate regulations in real time, ensuring that subsidy rules meet the latest compliance requirements. This automated compliance verification reduces human error and avoids legal disputes or financial losses caused by non-compliant grants. Furthermore, through a visual configuration interface and parameterized configuration, this application allows non-technical personnel to quickly adjust subsidy rules, improving system maintainability.

[0070] The following describes in detail the various modules / units in the employee subsidy payment configuration system based on the large model in conjunction with some embodiments.

[0071] In the employee subsidy payment configuration system, constraints are used to ensure that the subsidy application data filled in by employees complies with business rules, data specifications and compliance requirements. In some embodiments, constraints include but are not limited to field type, field length, field filling range and the relationship between fields. Among them, for example, field types can include text input (text), number (number), drop-down selection (select), date (date) and read-only fields (readonly). The field length limits the input length of text or number to prevent data overflow or invalid input, such as a field with less than 10 characters. The field filling range limits the optional range of input values ​​to avoid illegal value submission, such as age must be greater than or equal to 16 years old or 18 years old, the department to which one belongs must be Department A or Department B, the subsidy amount must be less than 50,000, etc. The relationship between fields is used to characterize the matching relationship and / or size relationship between at least two fields, such as the ID number must match the employee name, and the subsidy amount must be less than or equal to 20% of the pre-tax salary.

[0072] Accordingly, during back-end configuration, the back-end configuration unit 132 can map each field to the corresponding field in the database by calling the second largest model to obtain the mapping relationship between each field and the corresponding field in the database. Then, based on the multiple fields confirmed by the user, the calculation rules of the target field, the constraints and the mapping relationship, a machine-readable JSON format parameter template (Schema), i.e., a configuration file, is generated. When generating the parameter template, the second largest model can set the field type, field length, field filling range and the association relationship between the multiple fields in the parameter template according to the constraints. And, based on the mapping relationship, the mapping relationship between each field in the parameter template and the corresponding field in the database is set.

[0073] Accordingly, during the front-end configuration, the front-end configuration unit 133 can match the corresponding user interface components (UI components) according to the field type of each field by calling the second large model, and automatically arrange the user interface components according to the preset field priority. For example, when the field type is text, the corresponding UI component can be a text input box. When the field type is number, the corresponding UI component can be a number input box. When the field type is select, the corresponding UI component can be a drop-down selection box. Each UI component can be automatically arranged according to the preset field priority, such as the UI component corresponding to the employee name field is arranged in the first column, the UI component corresponding to the ID number field is arranged in the second column, the UI component corresponding to the age field is arranged in the third column, and so on. This application does not limit this.

[0074] In addition, the front-end configuration unit 133 can also convert the constraints in the parameter template into front-end verification logic by calling the second largest model, such as verifying whether the ID number filled in by the employee meets the preset format, verifying whether the age filled in by the employee is within the preset range, etc., and synchronize the front-end verification logic to the back-end. In this way, real-time verification can be performed when the employee fills in the form, reducing the error rate of employee filling in and avoiding invalid submission. The front-end configuration unit 133 can also establish the submission logic for the information filled in by the employee by calling the second largest model. For example, a submit button is set on the subsidy payment application page, and the submit button can trigger access to the back-end API, thereby sending the data filled in by the employee to the back-end for processing.

[0075] Considering that when users set some constraints involving subsidy application eligibility fields (such as age, length of service, etc.), they may need to manually review a large number of legal documents or internal company documents, which is a large workload and is prone to missing key terms or misunderstanding details. In view of this, in some embodiments, this application calls the first model to directly query and parse legal regulations and internal company regulations to complete the automatic configuration of terms matching and constraints, thereby reducing the burden on users, reducing the error rate of configuring constraints, and improving the efficiency of configuring constraints.

[0076] Specifically, in some embodiments, the configuration interface may be provided with a query control. This query control may be used to support users in querying the laws and regulations related to subsidy disbursement and the internal regulations of the enterprise to which the template belongs, and to parse the target laws and regulations and / or internal regulations selected by the user using the first model to obtain key fields and their constraints associated with the target laws and regulations and / or internal regulations, and to automatically configure the constraints of the key fields based on the parsed results.

[0077] For example, if the First Largest Model query reveals that a certain subsidy-related legal regulation requires "the subsidy must be no less than 180 yuan per month," the user selects the regulation and the First Largest Model parses it, identifying the key field as "subsidy amount" and the constraint as "no less than 180 yuan per month." Based on the parsed results, the First Largest Model automatically configures the constraint for the subsidy amount field, converting "no less than 180 yuan per month" to min_value:180, for example.

[0078] Considering that when the backend is deployed in a public cloud environment, there may be a potential risk of employee privacy data leakage. In view of this, in some embodiments, the configuration interface is provided with a sensitive field marking switch, forcing users to mark fields that need to be desensitized, such as marking sensitive fields such as ID card number, mobile phone number and bank card number. In this way, when employees fill in the information of these sensitive fields, they can desensitize the information of these sensitive fields locally, such as replacing it with a mask or hash value, and then transmit the desensitized information to the backend so that the backend can generate the subsidy application form.

[0079] Furthermore, to address the issue of employee privacy data leakage, permissions can be set for different users on subsidy application forms stored in the database. For example, legal personnel can only view rule logic, while HR requires permission to access specific employee data. Furthermore, all data access actions can be logged, such as "User X queried employee Y's subsidy application form," and the access logs are encrypted and stored.

[0080] According to some embodiments of the present application, optionally, after the compliance check, the compliance check unit 131 can also be used to output a compliance report. Among them, the compliance report may include calculation rules or constraints that failed the check, referenced laws and regulations or internal regulations, and correction suggestions. For example, an example of a compliance report is as follows: the calculation rule of the subsidy amount "housing subsidy = employee basic salary × 25%" is wrong, which violates the company's internal regulations that "housing subsidy shall not exceed 20% of employee basic salary". The correction suggestion is: it is recommended to modify the calculation rule of the subsidy amount to "housing subsidy = employee basic salary × 19%".

[0081] The compliance verification unit 131 may also support one-click adoption of correction suggestions. After the user selects one-click adoption of the correction suggestion, the calculation rules or constraints that fail the verification are automatically replaced based on the correction suggestion.

[0082] When filling out subsidy application information, employees may have questions about the meaning of form fields, calculation rules, or filling requirements. Traditional email / telephone consultations require multiple department transfers (such as HR → Finance → Legal Affairs), with a long average response time. Some employees may give up on consultations due to the complex process, resulting in a high error rate in subsequent filling. Therefore, in some embodiments, the subsidy application page is equipped with a chat portal, which can support employees to initiate consultations or submit complaints when they have questions about the meaning of form fields, calculation rules, or filling requirements.

[0083] In some embodiments, the chat portal has an "anonymous mode" option. When an employee selects "anonymous mode," the system automatically hides their identity information, such as "User A," to achieve anonymized chat.

[0084] According to some embodiments of the present application, optionally, the employee subsidy payment configuration system may also include a consultation response module for automatically responding to employee consultation questions through the second largest model; and when an employee applies for a manual response, the second largest model is used to perform keyword recognition on the employee consultation questions, and questions involving calculation rules and constraints are automatically assigned to legal personnel for processing, and questions involving employee personal information are automatically assigned to human resources management personnel for processing.

[0085] The second-largest model automatically identifies the type of question. Simple questions can be answered directly by the AI, while complex questions can be assigned to the appropriate personnel. For example, if an employee asks, "Why is my transportation allowance 200 yuan less than my colleagues?" the second-largest model can automatically push the individual allowance calculation details, display the referenced laws and regulations or internal company regulations, and provide a complaint entry, alleviating the employee's concerns and facilitating their complaint.

[0086] In this way, by setting up a chat entrance and consultation response module, the combination of AI-based responses and manual diversion responses can help employees conduct better consultation and communication, solve the questions that employees have when filling out the form, improve the efficiency of employee consultation, and reduce the error rate of employee filling out and the cost of enterprise service operation.

[0087] Based on the large-model-based employee subsidy payment configuration system 10 provided in the above embodiment, the present application also provides a large-model-based employee subsidy payment configuration method, which can be implemented based on the employee subsidy payment configuration system 10.

[0088] Figure 4 A flow chart of a method for distributing employee subsidies based on a large model provided in an embodiment of the present application. Figure 4 As shown, the employee subsidy payment configuration method based on the large model may include the following steps S401 to S405.

[0089] S401: Analyze the subsidy application form template uploaded by the user by calling the first model, extract multiple fields that need to be filled in or confirmed by the employee and calculation rules of the target field, and the target field includes at least the subsidy amount field.

[0090] S402: Display calculation rules of multiple fields and target fields through a configuration interface, and receive user modification and confirmation information on the calculation rules of multiple fields and target fields, and field constraints.

[0091] S403: The second largest model is used to retrieve the legal regulations related to subsidy issuance and the internal regulations of the enterprise to which the template belongs, and the calculation rules and constraints are verified for compliance based on the legal regulations and internal regulations.

[0092] S404: After the compliance check is successful, the multiple fields confirmed by the user, the calculation rules and constraints of the target field are converted into a parameter template executable by the system through the second largest model, and an application programming interface for accessing the backend is built based on the parameter template, where the parameter template contains the field name, constraints, the calculation rules of the target field, and the mapping relationship between each field and the corresponding field in the database.

[0093] S405: Create a subsidy payment declaration page based on the parameter template, and establish an association between the subsidy payment declaration page and the backend based on the application programming interface; the subsidy payment declaration page is used to interact with employees to complete the filling and display of the subsidy declaration form.

[0094] The specific process of steps S401 to S405 has been described in detail above and will not be repeated here.

[0095] The embodiment of the present application provides a method for configuring employee subsidy issuance based on a large model. Through the natural language understanding ability of the large model, it automatically parses the subsidy application form template uploaded by the user and completes the configuration of the back-end and front-end subsidy issuance application pages, reducing manual intervention and improving configuration efficiency. Moreover, it can be developed directly by non-technical personnel (such as legal personnel or human resources management personnel) through natural language, and the configuration of the back-end and front-end pages can be achieved without professional programmers, which reduces communication costs and reduces the difficulty of enterprise (especially small and medium-sized enterprises) development tools. In addition, the automatic conversion of parameter templates and the automatic construction of application programming interfaces also avoid manual coding, allowing the system to quickly adapt to changes in different subsidy policies.

[0096] Furthermore, this application uses a large-scale model to search and compare legal provisions and internal corporate regulations in real time, ensuring that subsidy rules meet the latest compliance requirements. This automated compliance verification reduces human error and avoids legal disputes or financial losses caused by non-compliant grants. Furthermore, through a visual configuration interface and parameterized configuration, this application allows non-technical personnel to quickly adjust subsidy rules, improving system maintainability.

[0097] According to some embodiments of the present application, optionally, the constraints include field type, field length, field filling range and the relationship between fields. The second largest model converts the calculation rules and constraints of multiple fields confirmed by the user, the target field, and the relationship between fields into a parameter template executable by the system, including: setting the field type, field length, field filling range and the relationship between fields of multiple fields in the parameter template according to the constraints; and mapping each field to the corresponding field in the database, and setting the mapping relationship between each field and the corresponding field in the database in the parameter template. According to the parameter template, a subsidy payment declaration page is created, and based on the application programming interface, an association between the subsidy payment declaration page and the back end is established, including: matching the corresponding user interface components according to the field type of each field, and automatically arranging the user interface components according to the preset field priority; converting the constraints in the parameter template into front-end verification logic, and synchronizing the front-end verification logic to the back end; and establishing the submission logic for the information filled in by employees.

[0098] According to some embodiments of the present application, optionally, the employee subsidy issuance configuration method based on the big model also includes: in response to the user's query operation through the query control, querying the legal regulations related to the subsidy issuance and the internal regulations of the enterprise to which the template belongs, and parsing the target legal regulations and / or target internal regulations selected by the user through the first big model to obtain the key fields and constraints associated with the target legal regulations and / or target internal regulations, and automatically configuring the constraints of the key fields according to the parsing results.

[0099] According to some embodiments of the present application, optionally, the configuration interface is further provided with a sensitive field marking switch, forcing the user to mark the fields that need to be desensitized.

[0100] According to some embodiments of the present application, optionally, the employee subsidy payment configuration method based on a large model also includes: outputting a compliance report, the compliance report includes calculation rules or constraints that have not passed the verification, referenced laws and regulations or internal regulations, and correction suggestions, and supports one-click adoption of correction suggestions, automatically replacing the calculation rules or constraints that have not passed the verification based on the correction suggestions.

[0101] According to some embodiments of the present application, optionally, a chat portal is provided on the subsidy payment application page, which supports employees to initiate consultations or make complaints when they have questions about the meaning of form fields, calculation rules or filling requirements.

[0102] According to some embodiments of the present application, optionally, the employee subsidy payment configuration method based on the large model also includes: automatically replying to employee consultation questions through the second large model; and when the employee applies for a manual reply, performing keyword recognition on the employee consultation questions through the second large model, automatically assigning questions involving calculation rules and constraints to legal personnel for processing, and automatically assigning questions involving employee personal information to human resources management personnel for processing.

[0103] The electronic device in the embodiment of the present application can be a user terminal device, a server, other computing devices, or a cloud server. Figure 5 This is a hardware structure diagram of an electronic device according to an embodiment of the present application. The electronic device may include a processor 501 and a memory 502 storing computer program instructions. When the processor 501 executes the computer program instructions, the process or function of any of the above-mentioned embodiments is implemented.

[0104] Specifically, the processor 501 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application. The memory 502 may include a large-capacity memory for data or instructions. For example, the memory 502 may be at least one of the following: a hard disk drive (HDD), a read-only memory (ROM), a random access memory (RAM), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, a universal serial bus (USB) drive, or other physical / tangible memory storage device. For another example, the memory 502 may include a removable or non-removable (or fixed) medium. For another example, the memory 502 may be inside or outside the integrated gateway disaster recovery device. The memory 502 may be a non-volatile solid-state memory. In other words, the memory 502 typically includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with computer-executable instructions, and when the software is executed (such as by one or more processors), the operations described in the method of the embodiments of the present application may be performed. The processor 501 implements the process or function of any of the large model-based employee subsidy payment configuration methods in the above embodiments by reading and executing computer program instructions stored in the memory 502 .

[0105] In one example, Figure 5 The electronic device shown may also include a communication interface 503 and a bus 510. The processor 501, memory 502, and communication interface 503 are connected via the bus 510 and communicate with each other. The communication interface 503 is primarily used to implement communication between the various modules, devices, units, and / or equipment in the embodiments of the present application. The bus 510 includes hardware, software, or both, and can couple the components of the online data traffic metering device to each other. For example, the bus may include at least one of the following: an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industrial Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Area Bus (VLB) bus, or other suitable buses. The bus 510 may include one or more buses. Although the embodiments of the present application describe or illustrate a specific bus, the embodiments of the present application may consider any suitable bus or interconnection method.

[0106] In combination with the methods in the above embodiments, an embodiment of the present application also provides a computer-readable storage medium, which stores computer program instructions. When the computer program instructions are executed by a processor, they implement the process or function of any of the large model-based employee subsidy payment configuration methods in the above embodiments.

[0107] In addition, an embodiment of the present application also provides a computer program product, which stores computer program instructions. When the computer program instructions are executed by a processor, they implement the process or function of any of the large model-based employee subsidy payment configuration methods in the above embodiments.

[0108] The flowcharts and / or block diagrams of the methods, devices, systems and computer program products of the embodiments of the present application are described above by way of example, and various aspects thereof are described. It should be understood that each box in the flowchart and / or block diagram or a combination thereof may be implemented by computer program instructions, or may be implemented by dedicated hardware that performs a specified function or action, or may be implemented by a combination of dedicated hardware and computer instructions. For example, these computer program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to form a machine that enables these instructions executed by such a processor to enable the implementation of the functions / actions specified in each box in the flowchart and / or block diagram or a combination thereof. Such a processor may be a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit.

[0109] The functional blocks shown in the block diagram of the embodiment of the present application can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc.; when implemented in software, it is a program or code segment used to perform the required task. The program or code segment can be stored in a memory or transmitted on a transmission medium or a communication link via a data signal carried in a carrier. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0110] It should be noted that the present application is not limited to the specific configurations and processes described above or shown in the figures. The above is only a specific implementation method of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the described system, device, module or unit can refer to the corresponding process in the method embodiment without further description. It should be understood that the scope of protection of the present application is not limited to this. Any technician familiar with the technical field can think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A system for distributing employee subsidies based on a large model, characterized by: include: An analysis and extraction module is used to analyze the subsidy application form template uploaded by the user by calling the first model, extract multiple fields that need to be filled in or confirmed by the employee, and calculation rules for the target field, where the target field includes at least the subsidy amount field; A display and editing module is used to display the calculation rules of the extracted multiple fields and target fields through a configuration interface. The configuration interface is provided with input controls, which are used to support users to modify and confirm the calculation rules of the multiple fields and target fields, as well as input field constraints; The second largest model processing module includes a compliance verification unit, a backend configuration unit, and a frontend configuration unit, wherein: The compliance verification unit is used to retrieve the legal regulations related to subsidy issuance and the internal regulations of the enterprise to which the template belongs through the second largest model, and to perform compliance verification on the calculation rules and constraints based on the legal regulations and internal regulations; After compliance verification is successful, the backend configuration unit is used to convert the multiple fields confirmed by the user, the calculation rules and constraints of the target field into a parameter template that can be executed by the system through the second largest model. Based on the parameter template, an application programming interface for accessing the backend is built. The parameter template includes the field name, constraints, the calculation rules of the target field, and the mapping relationship between each field and the corresponding field in the database. The front-end configuration unit is used to create a subsidy payment declaration page based on the parameter template, and to establish an association between the subsidy payment declaration page and the back-end based on the application programming interface; the subsidy payment declaration page is used to interact with employees to complete the filling and display of the subsidy declaration form.

2. The system according to claim 1, wherein: The constraints include field type, field length, field filling range, and the relationship between fields. The backend configuration unit is specifically used to set the field type, field length, field filling range, and the relationship between fields of multiple fields in the parameter template according to the constraints; and map each field to the corresponding field in the database, and set the mapping relationship between each field and the corresponding field in the database in the parameter template; The front-end configuration unit is specifically used to match the corresponding user interface components according to the field type of each field, and automatically arrange the user interface components according to the preset field priority; convert the constraints in the parameter template into front-end verification logic, and synchronize the front-end verification logic to the back-end; and establish the submission logic for the information filled in by employees.

3. The system according to claim 1, wherein: The configuration interface is also provided with a query control, which is used to support users in querying the laws and regulations related to subsidy issuance and the internal regulations of the enterprise to which the template belongs, and to parse the target laws and regulations and / or target internal regulations selected by the user through the first model to obtain the key fields and constraints associated with the target laws and regulations and / or target internal regulations, and automatically configure the constraints of the key fields based on the parsing results.

4. The system according to claim 1, wherein: The configuration interface also has a sensitive field marking switch, forcing users to mark fields that need to be desensitized.

5. The system according to claim 1, wherein: The compliance verification unit is also used to output compliance reports, which include calculation rules or constraints that failed verification, referenced laws and regulations or internal regulations, and correction suggestions. It also supports one-click adoption of correction suggestions, automatically replacing calculation rules or constraints that failed verification based on the correction suggestions.

6. The system according to claim 1, wherein: The subsidy payment application page is equipped with a chat portal, which allows employees to initiate consultations or make complaints when they have questions about the meaning of form fields, calculation rules or filling requirements.

7. The system according to claim 1, wherein: The system also includes a consultation response module for automatically responding to employee consultation questions using the second model; When employees request manual responses, the second largest model will be used to identify keywords in the questions asked by employees, and questions involving calculation rules and constraints will be automatically assigned to legal personnel for processing, while questions involving employee personal information will be automatically assigned to human resources management personnel for processing.

8. A method for allocating employee subsidies based on a large model, characterized in that: include: By calling the first model to analyze the subsidy application form template uploaded by the user, multiple fields that need to be filled in or confirmed by the employee and the calculation rules of the target field are extracted. The target field includes at least the subsidy amount field; The calculation rules of multiple fields and target fields are displayed through the configuration interface, and the user is allowed to modify and confirm the calculation rules of multiple fields and target fields, as well as the constraints of the fields; The second model retrieves the legal regulations related to subsidy disbursement and the internal regulations of the enterprise to which the template belongs, and performs compliance verification on the calculation rules and constraints based on the legal regulations and internal regulations; After the compliance check is successful, the second model converts the multiple fields confirmed by the user, the calculation rules and constraints of the target field into a parameter template that the system can execute. Based on the parameter template, an application programming interface for accessing the backend is built. The parameter template contains the field name, constraints, the calculation rules of the target field, and the mapping relationship between each field and the corresponding field in the database. Based on the parameter template, a subsidy payment declaration page is created, and based on the application programming interface, an association is established between the subsidy payment declaration page and the backend; among them, the subsidy payment declaration page is used to interact with employees to complete the filling and display of the subsidy declaration form.

9. An electronic device, characterized in that: The electronic device includes: a processor and a memory storing computer program instructions; when the electronic device executes the computer program instructions, the employee subsidy payment configuration method based on the large model as claimed in claim 8 is implemented.

10. A computer program product, characterized in that It includes computer program instructions, which, when executed by a processor, implement the employee subsidy payment configuration method based on a large model as claimed in claim 8.

Images