Intelligent detection method and device for outsourcing personnel information

Abstract

The invention provides an intelligent detection method and device for outsourcing personnel information, and the method comprises the steps: obtaining outsourcing personnel data which comprises contract information, personnel entry and exit information, and attendance record information; inputting the outsourcing personnel data into an outsourcing personnel information auditing large model, and obtaining an outsourcing personnel information auditing result based on a preset outsourcing personnel information template; constructing an outsourcing personnel information auditing database; constructing an outsourcing personnel information view according to the outsourcing personnel information auditing result and an outsourcing personnel information auditing database; based on the outsourcing personnel information view, detecting the in-out state, the contract period and the attendance condition of the outsourcing personnel to obtain an information detection result of the outsourcing personnel; through information auditing based on a large model, intelligence of outsourcing personnel information detection is realized, the method can adapt to a large-scale centralized management scene, and the auditing efficiency and the auditing accuracy are effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of big data and artificial intelligence technology, and in particular relates to an intelligent detection method and device for outsourced personnel information. Background Technology

[0002] As the digital transformation of banking operations deepens, the scale of outsourced personnel continues to expand, and the full lifecycle management scenarios, including entry, changes, transfers, and exits, are becoming increasingly complex. The efficiency and accuracy of the involved material review, multi-system data collaboration, and risk supervision have become key factors affecting management quality.

[0003] Currently, outsourced personnel management heavily relies on manual operations: In scenarios involving the review of personnel entry and exit documents, staff must manually verify dozens of qualification certificates submitted by the outsourcing party, checking each item for format compliance, content completeness, and logical consistency. Only after all materials have passed review can the subsequent process proceed. In multi-system data management scenarios, it is necessary to manually integrate isolated data from contract management systems, procurement systems, attendance management systems, and outsourcing management systems to verify the consistency of information such as personnel status, contract duration, and attendance records. In risk monitoring scenarios, it is necessary to manually and regularly check for risks such as overstaying, unrenewed contracts, and attendance anomalies. However, when facing scenarios involving the centralized management of large-scale outsourced personnel, the drawbacks of this approach become increasingly prominent: On the one hand, manual operations are cumbersome and time-consuming, requiring significant manpower and making it difficult to complete the review and integration of massive amounts of materials in a short time, severely restricting overall management efficiency. On the other hand, over-reliance on manual operations is prone to problems such as oversights, data integration errors, and delayed risk identification due to human negligence, failing to guarantee the standardization and timeliness of outsourced personnel management, thereby affecting the smooth progress of business processes. Summary of the Invention

[0004] This invention provides an intelligent detection method for outsourced personnel information. Through information review based on a large model, it achieves intelligent detection of outsourced personnel information, adapting to large-scale centralized management scenarios and effectively improving review efficiency and accuracy. The intelligent detection method for outsourced personnel information includes:

[0005] Acquire outsourced personnel data, which includes contract information, personnel entry and exit information, and attendance records.

[0006] The outsourced personnel data is input into the outsourced personnel information review model, and the review results are obtained based on the preset outsourced personnel information template. The outsourced personnel information review model is obtained by training a deep learning network using historical outsourced personnel data. The deep learning network is generated by integrating natural language processing (NLP) and computer vision (CV) technologies.

[0007] Establish an outsourced personnel information review database; the outsourced personnel information review database includes material format review requirements, content completeness review requirements, and logical consistency review requirements;

[0008] Based on the results of the outsourced personnel information review and the outsourced personnel information review database, construct an outsourced personnel information view;

[0009] Based on the outsourced personnel information view, the outsourced personnel's entry and exit status, contract period, and attendance are checked to obtain the outsourced personnel information check results.

[0010] This invention provides an intelligent detection device for outsourced personnel information. Through information review based on a large model, it achieves intelligent detection of outsourced personnel information, adapting to large-scale centralized management scenarios and effectively improving review efficiency and accuracy. The intelligent detection device for outsourced personnel information includes:

[0011] The data acquisition module is used to acquire outsourced personnel data, which includes contract information, personnel entry and exit information, and attendance record information.

[0012] The information verification module is used to input outsourced personnel data into the outsourced personnel information verification model and obtain the outsourced personnel information verification result based on the preset outsourced personnel information template. The outsourced personnel information verification model is obtained by training a deep learning network using historical outsourced personnel data. The deep learning network is generated by integrating natural language processing (NLP) and computer vision (CV) technologies.

[0013] The database construction module is used to build an outsourced personnel information review database; the outsourced personnel information review database includes material format review requirements, content completeness review requirements, and logical consistency review requirements.

[0014] The information view construction module is used to construct an information view of outsourced personnel based on the review results of outsourced personnel information and the outsourced personnel information review database;

[0015] The information detection module is used to detect the outsourced personnel's entry and exit status, contract period, and attendance based on the outsourced personnel information view, and obtain the information detection results of the outsourced personnel.

[0016] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned intelligent detection method for outsourced personnel information.

[0017] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned intelligent detection method for outsourced personnel information.

[0018] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned intelligent detection method for outsourced personnel information.

[0019] In this embodiment of the invention, outsourced personnel data is acquired, including contract information, personnel entry and exit information, and attendance records. This data is then input into a large-scale outsourced personnel information review model, and review results are obtained based on a preset outsourced personnel information template. The large-scale outsourced personnel information review model is trained using historical outsourced personnel data on a deep learning network. An outsourced personnel information review database is constructed, including requirements for material format review, content completeness review, and logical consistency review. Based on the outsourced personnel information review results and the database, an outsourced personnel information view is constructed. Based on this view, the outsourced personnel's entry and exit status, contract duration, and attendance are checked to obtain the outsourced personnel information detection results. This embodiment of the invention achieves intelligent outsourced personnel information detection through large-scale model-based information review, adapting to large-scale centralized management scenarios and effectively improving review efficiency and accuracy. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0021] Figure 1 This is a flowchart of the intelligent detection method for outsourced personnel information in an embodiment of the present invention;

[0022] Figure 2 This is a specific example diagram illustrating the determination of information detection results for outsourced personnel in an embodiment of the present invention;

[0023] Figure 3 This is a specific example diagram illustrating the generation of an early warning notification in an embodiment of the present invention;

[0024] Figure 4 This is a structural example diagram of the intelligent detection device for outsourced personnel information in an embodiment of the present invention;

[0025] Figure 5 This is a specific example diagram illustrating the structure of the intelligent detection device for outsourced personnel information in an embodiment of the present invention;

[0026] Figure 6 This is a specific example diagram illustrating the structure of the intelligent detection device for outsourced personnel information in an embodiment of the present invention;

[0027] Figure 7 This is a structural diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0029] The acquisition, transmission, storage, use, and processing of data in the technical solution of this invention all comply with relevant regulations.

[0030] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of the present invention. However, they do not mean that the applicant has used or necessarily used the solution.

[0031] As mentioned earlier, existing technologies for managing outsourced personnel are mostly single-domain, independent solutions: material review relies on manual checks of the completeness and compliance of dozens of documents one by one; when adding or updating material templates and filling requirements, misunderstandings and oversights are prone to occur, and after problems are discovered, the entire process needs to be rolled back for modification, resulting in high rework rates and low efficiency; data is not shared between multiple systems, forming data silos, and relying on manual data integration makes it difficult to detect risks in real time and makes supervision difficult; processes such as changeovers and site transitions lack intelligent routing and anomaly warning mechanisms, resulting in low collaboration efficiency.

[0032] To address this issue, the inventors discovered that a closed-loop management system covering the entire lifecycle can be constructed through the organic linkage of multiple modules. They proposed an AI-based intelligent management tool for outsourced personnel. This tool generates personnel information views through data collection, intelligently recommends differentiated document templates, integrates NLP for intelligent material review, and integrates data from multiple systems for intelligent monitoring. This enables intelligent management of the entire process, including material access, process monitoring, and data detection, thereby improving the efficiency and accuracy of outsourced personnel information review.

[0033] Figure 1 This is a flowchart of the intelligent detection method for outsourced personnel information in an embodiment of the present invention, such as... Figure 1 As shown, the intelligent detection method for outsourced personnel information includes:

[0034] Step 101: Obtain outsourced personnel data, which includes contract information, personnel entry and exit information, and attendance record information;

[0035] Step 102: Input the outsourced personnel data into the outsourced personnel information review model, and obtain the outsourced personnel information review result based on the preset outsourced personnel information template; the outsourced personnel information review model is obtained by training a deep learning network using historical outsourced personnel data; the deep learning network is generated by integrating natural language processing (NLP) and computer vision (CV) technologies.

[0036] Step 103: Construct an outsourced personnel information review database; the outsourced personnel information review database includes material format review requirements, content completeness review requirements, and logical consistency review requirements;

[0037] Step 104: Based on the results of the outsourced personnel information review and the outsourced personnel information review database, construct an outsourced personnel information view;

[0038] Step 105: Based on the outsourced personnel information view, check the outsourced personnel's entry and exit status, contract period, and attendance to obtain the outsourced personnel information check results.

[0039] As shown in Figure 1, the intelligent detection method for outsourced personnel information in this embodiment of the invention includes: acquiring outsourced personnel data, which includes contract information, personnel entry and exit information, and attendance record information; inputting the outsourced personnel data into a large-scale outsourced personnel information review model trained using historical outsourced personnel data, and obtaining outsourced personnel information review results based on a preset outsourced personnel information template; constructing an outsourced personnel information review database that includes material format review requirements, content completeness review requirements, and logical consistency review requirements; constructing an outsourced personnel information view based on the outsourced personnel information review results and the outsourced personnel information review database; and detecting the outsourced personnel's entry and exit status, contract period, and attendance status based on the outsourced personnel information view to obtain the outsourced personnel information detection results. Compared to existing technologies that focus on independent solutions for single-domain problems, this approach builds a comprehensive model for outsourced personnel information verification that integrates NLP technology. This model breaks down data barriers between contract management, procurement, attendance, and outsourcing management systems, establishes a database and personnel information view that includes multi-dimensional verification requirements, and combines cross-system data linkage and composite rule detection mechanisms. This enables intelligent management of outsourced personnel throughout their entire lifecycle, thereby solving the problems of data incompatibility, low efficiency of manual verification, and untimely risk detection in existing technologies, and improving the efficiency and quality of outsourced personnel verification processes.

[0040] In step 101, outsourced personnel data is obtained, which includes contract information, personnel entry and exit information, and attendance record information.

[0041] In a specific embodiment, acquiring outsourced personnel data, including contract information, personnel entry and exit information, and attendance record information, includes:

[0042] Contract Information Acquisition: By calling the contract management system through the API interface, the core contract data corresponding to the outsourced personnel is extracted, including contract number, contract name, supplier name, contract signing date, contract expiration date, agreed entry time, order information, payment progress information, etc., to ensure that the data is synchronized with the contract management system in real time without delay or deviation.

[0043] Personnel entry and exit information acquisition: Integrate with the outsourcing management system to collect data related to the entry, exit, and changes of outsourced personnel, including key information such as the name of newly added or changed personnel, qualification level, reason for addition or change, time of addition or change, time of entry application submission, time of entry approval, transfer records, time of exit application, time of exit approval, and status of permission activation or deactivation.

[0044] Attendance record information acquisition: Through the data interface of the attendance management system, the daily attendance data of outsourced personnel is obtained, including attendance check-in time, check-in location, check-in method, such as facial recognition check-in records, daily attendance status, including normal, absent, leave, consecutive check-in days, consecutive days without check-in records, etc., to achieve real-time collection and synchronization of attendance data.

[0045] Data integration and verification: Field matching and format standardization are performed on contract information, personnel entry and exit information, and attendance record information obtained from various systems. Data integrity is verified, such as ensuring that the contract number matches the corresponding personnel entry and exit information. Duplicate and invalid data are removed to form a structured dataset of outsourced personnel, providing a foundation for subsequent review and view construction.

[0046] In this embodiment, after obtaining the outsourced personnel data, the method further includes:

[0047] The acquired outsourced personnel data is subjected to data consistency verification, and usable outsourced personnel data is obtained after eliminating data conflicts.

[0048] In a specific embodiment, the acquired outsourced personnel data undergoes data consistency verification and data conflict elimination to obtain usable outsourced personnel data, including:

[0049] Cross-system data association verification: Using the contract number as the core association field, verify whether the contract expiration date in the contract management system is consistent with the personnel exit plan time in the outsourcing management system, whether the order supplier in the procurement system matches the supplier to which the personnel belong in the outsourcing management system, and whether the name and identity of the outsourced personnel in the attendance management system are consistent with the personnel identity information in the entry and exit information. Identify data conflicts such as mismatched fields and contradictory information.

[0050] Logical consistency verification: Check whether the contractually agreed entry time is earlier than the actual entry approval time, whether the contract expiration date is later than the exit application time, and whether the clock-in date in the attendance record is within the valid time period from personnel entry to exit, to avoid time logic conflicts; at the same time, verify whether the payment progress matches the contractual terms and personnel's actual attendance time, and eliminate logically contradictory data.

[0051] Data integrity verification: Check whether there are any missing required fields in the data obtained from each system, such as missing signing dates in contract information, missing clock-in methods in attendance records, and missing qualification levels in entry and exit information. Ensure that no core data is missing, mark missing data as "to be supplemented" and report it to the corresponding system.

[0052] Conflict resolution: For cross-system related conflicting data, the data from the contract management system is used as a benchmark, such as supplier information and contract terms, and the direction of correction is confirmed by manual review; for time-related logical conflicting data, the system operation log is retrieved to trace the source of data entry, and the error information is corrected according to the actual business scenario; for missing data, the corresponding outsourcing company or system maintenance personnel are notified to supplement and improve it, and the verification process is re-executed after supplementation.

[0053] Available data output: After completing all validations and conflict resolution, the data that meets the requirements of consistency, completeness, and logicality will be organized into a structured dataset, which can be used as outsourced personnel data for subsequent large model review, information view construction, and risk detection.

[0054] In step 102, the outsourced personnel data is input into the outsourced personnel information review model, and the outsourced personnel information review result is obtained based on the preset outsourced personnel information template. The outsourced personnel information review model is obtained by training a deep learning network using historical outsourced personnel data. The deep learning network is generated by integrating natural language processing (NLP) and computer vision (CV) technologies.

[0055] In this embodiment, the preset outsourced personnel information template can be determined in the following way:

[0056] Requirements for verifying the information of outsourced personnel; these requirements include the type of outsourced personnel information, the required content of the outsourced personnel information, and the format standards for the outsourced personnel information.

[0057] Based on the information verification requirements for outsourced personnel and the business scenarios of outsourced personnel, information templates for outsourced personnel under different business scenarios are determined.

[0058] In a specific embodiment, a large-scale model for verifying outsourced personnel information is first trained:

[0059] Collect historical data on outsourced personnel, including past compliant and non-compliant qualification materials, contract information, entry and exit records, attendance data, etc., and perform structured processing on the data, such as extracting key fields and labeling error types, to build a training dataset.

[0060] A deep learning network that integrates Natural Language Processing (NLP) and Computer Vision (CV) is used as the basic model architecture. The training dataset is input into the network, and the training objective is to "identify material format errors, missing content, and logical contradictions". The model parameters are iteratively optimized to finally obtain a large model for reviewing outsourced personnel information. This model can automatically identify compliance issues in outsourced personnel data and mark error points.

[0061] Preset outsourced personnel information template confirmed:

[0062] The first step is to obtain information review requirements: Collect the information review requirements from the outsourced personnel management specifications, including information types such as qualification certificates, commitment letters, application documents, attendance records, etc.; required content, such as qualification certificates must include the personnel's name, qualification level, and validity period; confidentiality commitment letters must include the signing date, company seal, and commitment terms, etc.; and format standards, such as document format as Word / PDF, scanned document resolution no less than 300dpi, date format as "YYYY-MM-DD", and file naming rules as "business scenario-company name-material name-date", etc.

[0063] The second step is to determine the template based on the business scenario: Based on the outsourced personnel's business scenarios, including onboarding, changes, transfers, probationary period assessments, and departures, match the corresponding information review requirements to generate differentiated templates. For example:

[0064] Entry scenario templates: These include templates for confidentiality commitment letters, company commitment letters, entry applications, personnel entry reports, performance commitment letters, personnel entry letters, entry notices, permission activation and deactivation status forms, company relationship statements, etc., clearly defining the essential clauses for each template, such as the entry application requiring the agreed entry time and qualification level; and format standards, such as the entry notice requiring a PDF format and an official seal.

[0065] Change and transition scenario templates: Based on the entry template, supplement the template with explanations of reasons for additions or changes, and transition approval form templates, and clarify that the change information must include the original status, the content of the change, the effective time and other essential information;

[0066] Exit scenario templates: These include exit application forms, work handover confirmation forms, and authorization cancellation certificate templates, requiring the explanation of the reason for exit and the status of contract performance.

[0067] Template-based review result generation:

[0068] The outsourced personnel data, after undergoing data consistency verification, is matched with the preset information templates for the corresponding business scenarios and input into the large-scale outsourced personnel information verification model.

[0069] The model uses NLP technology to parse textual data, such as identifying missing signing dates in commitment letters, and uses CV technology to verify scanned document data, such as detecting substandard resolution of qualification certificates. Combined with the review requirements in the template, it conducts a comprehensive review of the data's format compliance, content completeness, and logical consistency. The final output includes a review result of outsourced personnel information containing a "compliance item list, error point markers, and error type descriptions," while also generating intelligent repair suggestions to assist in subsequent local corrections.

[0070] In step 103, an outsourced personnel information review database is constructed; the outsourced personnel information review database includes material format review requirements, content completeness review requirements, and logical consistency review requirements.

[0071] In a specific embodiment, an outsourced personnel information review database is constructed, which includes requirements for material format review, content completeness review, and logical consistency review.

[0072] Material format review requirements for data entry:

[0073] Document format requirements: Clearly define the allowed formats for various submitted materials. For example, qualification certificates can be PDF or JPG scans, and commitment letters must be Word documents. The resolution of scanned documents must be no less than 300dpi, and document naming must follow the rule of "business scenario - company name - material name - date".

[0074] Field format requirements: Dates should be formatted as “YYYY-MM-DD”, qualification level descriptions should be standardized, and the character length and format of coded fields such as contract number and identity identifier should meet the standards. Format validation rules should be solidified using regular expressions.

[0075] Appearance and format requirements: PDF documents must be in editable text format, Word documents must use a consistent font and font size, and commitment letters must include a designated stamp area and signature field to avoid format confusion.

[0076] Content completeness review requirements for data entry:

[0077] Clearly categorize required fields: List the required fields by material type. For example, qualification certificates must include the personnel's name, qualification number, issuing authority, and validity period; entry applications must include the contract number, number of people entering, qualification level, reason for entry, and expected entry time; attendance records must include the name, identification, check-in time, and check-in status.

[0078] Supplementary material requirements: Background investigation materials must correspond to personnel identification information; confidentiality agreements must have a signing date and company seal; screenshots of entry notices must clearly show the recipient and sending time, ensuring that the materials are relevant to the core information without any omissions.

[0079] Logical consistency audit requirements for data entry:

[0080] Time logic rules: Set the contractual entry time to be less than or equal to the actual entry approval time, the contract expiry date to be greater than or equal to the exit application time, and the attendance check-in date to be within the valid time period from entry to exit, so as to avoid time sequence contradictions.

[0081] Related data matching rules: Ensure that the supplier name in the contract management system is consistent with the supplier to which the personnel belong in the outsourcing management system, that the order number in the procurement system is associated with the contract number, and that the payment progress corresponds with the attendance duration and the contract terms, so as to ensure the consistency of data logic across systems.

[0082] Business scenario logic rules: It is stipulated that change or transfer materials must include the original status information and an explanation of the reason for the change, and the time interval between the probation period assessment materials and the personnel's entry must comply with management specifications to avoid business process logic conflicts.

[0083] Database structured construction:

[0084] The database is structured hierarchically according to three categories: "material format - content integrity - logical consistency". Each category is further subdivided into subdirectories based on business scenarios, including entry, change, transition, and exit, to facilitate quick retrieval and access.

[0085] Each review requirement is assigned a unique identifier and applicable scenario tag, supporting the dynamic addition, modification, and deletion of review requirements. It is also synchronously linked to the large model for reviewing outsourced personnel information, ensuring that the database and model review rules are synchronized in real time, providing a unified standard basis for subsequent reviews.

[0086] In step 104, an outsourced personnel information view is constructed based on the outsourced personnel information review results and the outsourced personnel information review database.

[0087] In a specific embodiment, an outsourced personnel information view is constructed based on the outsourced personnel information review results and the outsourced personnel information review database, including:

[0088] Matching audit results with the database: The audit results of outsourced personnel information are compared one by one with the requirements of material format, content completeness, and logical consistency in the outsourced personnel information audit database to confirm whether the audit results meet the database's established standards, and to mark the clauses that failed the audit and the corresponding data issues.

[0089] Core Information Extraction and Integration: Extract key core information from the approved outsourced personnel data and integrate it according to the categories of "contract information - personnel entry and exit information - attendance record information - review status information". Specifically, this includes contract number, contract name, supplier, agreed entry time, contract expiration date, newly added or changed personnel information, entry and exit approval records, permission activation and deactivation status, daily attendance status, consecutive clock-in or absence days, review compliance status, error correction status, etc.

[0090] View Module Division and Visualization Construction: The integrated structured information is divided into multiple functional modules to construct a visual view of outsourced personnel information. The specific content of each module is as follows:

[0091] Basic Information Module: This module centrally displays core contract information and personnel identity-related data, such as contract number, supplier, personnel name, and qualification level.

[0092] Workflow Progress Module: Displays the application and approval time nodes and current process status for personnel entry, changes, transfers, and exits;

[0093] Attendance statistics module: Visually displays attendance records, attendance status percentages, number of consecutive days without attendance, and other data.

[0094] Audit feedback module: Marks the compliant items, unaccepted items and intelligent repair suggestions in the material review, and clarifies the correction progress;

[0095] Related data module: Displays the correlation between order information, payment progress, contract performance, and attendance status.

[0096] Dynamic View Updates and Synchronization: Establish a real-time linkage mechanism between the view and data from various systems. When the original data in the contract management system, outsourcing management system, and attendance management system is updated, or when the audit results change due to material corrections, the outsourced personnel information view is automatically updated to ensure that the view information is consistent with the actual data, providing real-time and accurate data support for subsequent risk detection.

[0097] Figure 2 This is a specific example diagram illustrating the determination of information detection results for outsourced personnel in an embodiment of the present invention, such as... Figure 2 As shown, based on the outsourced personnel information view, the outsourced personnel's entry and exit status, contract period, and attendance are checked to obtain the outsourced personnel information check results, which may include:

[0098] Step 201: Based on the outsourced personnel information view, determine the consistency detection result between the actual entry and exit time of personnel and the information registered in the system;

[0099] Step 202: Based on the outsourced personnel information view, determine the contract effective time and expiration time of the outsourced personnel, and generate contract expiration detection results within a preset period before the contract expires;

[0100] Step 203: Based on the outsourced personnel information view, determine the attendance risk detection results of the outsourced personnel; the attendance risk detection results include outsourced personnel having no consecutive clock-in information and abnormal clock-in location information.

[0101] In a specific embodiment, the outsourced personnel information view is used to detect the outsourced personnel's entry and exit status, contract period, and attendance to obtain information detection results, including:

[0102] Consistency check of entry and exit status:

[0103] Extract the system-registered entry approval time, exit application time, actual entry check-in time, and actual exit check-in time from the outsourced personnel information view.

[0104] Verify whether the actual entry check-in time is after the entry approval time registered in the system, whether the actual exit check-in time is before the exit application time registered in the system, and whether the actual entry and exit time interval matches the service period agreed in the contract.

[0105] Generate consistency detection results: If the time matches and meets the agreed cycle, mark it as "consistent entry and exit status"; if the actual entry check-in is earlier than the approval time, the actual exit check-in is later than the application time, or the time interval conflicts with the contract, mark it as "abnormal entry and exit status", and indicate the abnormality type and specific time difference.

[0106] Contract term testing:

[0107] Retrieve the contract effective date and contract expiration date from the information view, with the preset period set to 7 days.

[0108] The system compares the current date with the contract expiration date in real time. If the current date is less than or equal to 7 days away from the contract expiration date, it generates a contract expiration detection result, clearly indicating the contract number, expiration date, and corresponding outsourced personnel information. If the current date has exceeded the contract expiration date but the personnel have not completed the departure procedures, it generates a contract overdue departure detection result. If the current date is within the valid period from the contract's effective date to its expiration date, it generates a contract normal performance detection result.

[0109] All contract term testing results are simultaneously pushed to management personnel to remind them to promptly handle expiring contracts and personnel departure matters.

[0110] Attendance Risk Detection:

[0111] Continuous No-Check-in Detection: Extract the daily attendance status of outsourced personnel from the attendance statistics module of the information view, count the number of consecutive days without check-in records, and if the number of consecutive days without check-in is ≥3 days and the personnel's current status in the information view is on duty, generate a suspected false attendance risk detection result, indicating the personnel's name, supplier, and the start date of the consecutive no-check-in.

[0112] Anomaly detection of check-in location: Preset designated check-in areas for outsourced personnel, such as the project office location range. Compare the check-in location in the attendance record with the designated area. If the check-in location exceeds the designated area and no application for off-site work has been submitted, generate anomaly risk detection result for check-in location and record the abnormal check-in time and location information.

[0113] The results of the two types of attendance risk detection are summarized to form a complete attendance risk report, which is then synchronized to the outsourcing management system and the corresponding management personnel to assist in timely verification of abnormal situations.

[0114] Figure 3 This is a specific example diagram illustrating the generation of an early warning notification in an embodiment of the present invention, such as... Figure 3 As shown, based on the outsourced personnel information view, the outsourced personnel's entry and exit status, contract period, and attendance are detected. After obtaining the outsourced personnel information detection results, it can also include:

[0115] Step 301: Based on the information detection results of outsourced personnel, determine the abnormality type and risk level of the outsourced personnel;

[0116] Step 302: Generate an early warning notification based on the abnormality type and risk level of the outsourced personnel.

[0117] In this embodiment, the abnormal types of outsourced personnel include overstaying their visas, contract expiration, consecutive absences from attendance, and non-compliant qualifications.

[0118] In a specific embodiment, the process of generating an early warning notification based on information detection results includes:

[0119] Identify the types of abnormalities and risk levels of outsourced personnel:

[0120] Anomaly Type Matching: The outsourced personnel information detection results are matched with preset anomaly types. Among them, in the entry and exit status anomaly, if the actual exit check-in is later than the system-registered exit time or the contract has expired and the personnel have not left, it is judged as overstaying; in the contract period detection, if the expiration date is ≤7 days or has already expired, it is judged as contract expired; in the attendance risk detection, if there are ≥3 consecutive days of no check-in and the status is "on duty", it is judged as consecutive no check-in; if the outsourced personnel information review results indicate that the qualification materials are formatted incorrectly, missing in content, or do not meet the template requirements, it is judged as non-compliant with the qualification requirements.

[0121] Risk level classification: The preset risk level is three levels, namely general risk, medium risk and high risk, and the level is determined by combining the scope of the abnormal impact and the urgency of the response.

[0122] Generate early warning notification:

[0123] Warning notification template determination: Based on the anomaly type and risk level, a preset differentiated notification template is invoked. The template contains fixed fields, such as notification number, recipient, information of the anomaly personnel, detection time, anomaly type, and risk level.

[0124] Notification content filling: Fill in the test result details corresponding to the anomaly type into the template. For example, for consecutive days without attendance, you need to indicate the name of the person, the supplier, the number of consecutive days without attendance and the start date; for contract expiration, you need to indicate the contract number, the expiration date and the corresponding personnel list; for non-compliant qualifications, you need to indicate the specific non-compliant terms and intelligent repair suggestions.

[0125] Warning notification push: The push method is determined according to the risk level. General risks are pushed to the outsourcing management personnel via system in-system messages; medium risks are pushed via in-system messages + email, with a copy to the department head; high risks are pushed via in-system messages + email + SMS, urgently notifying the management personnel and the corresponding outsourcing company contact person, and specifying the deadline for handling, to ensure timely response to warning information.

[0126] The intelligent detection method for outsourced personnel information in this embodiment of the invention has been verified to have the following beneficial effects:

[0127] 1. Through the intelligent review engine that integrates NLP and CV, combined with a preset rule base and machine learning, the format, completeness and logical consistency of the qualification materials of outsourced personnel are automatically reviewed, which solves the problems of low efficiency, misunderstanding and omissions in manual review, and greatly shortens the review cycle.

[0128] 2. By collecting and verifying data in real time, data conflicts and delays are eliminated, enabling dynamic correlation of data such as contracts, personnel entry and exit, attendance, and payments. This replaces manual data integration and significantly improves data processing efficiency and accuracy.

[0129] 3. Based on outsourced personnel information view and time-series data analysis technology, it can detect abnormal scenarios such as overstaying, contract expiration, continuous absence of attendance, and non-compliance of qualifications in real time, generate multi-level risk warnings and push them through multiple channels, solve the problems of untimely risk detection and difficult supervision in existing technologies, realize cross-system risk penetration identification, and assist managers in rapid handling.

[0130] This invention also provides an intelligent detection device for outsourced personnel information, as described in the following embodiments. Since the principle behind this device's solution is similar to the intelligent detection method for outsourced personnel information, its implementation can refer to the implementation of the intelligent detection method for outsourced personnel information; repeated details will not be elaborated further.

[0131] Figure 4 This is a structural example diagram of the intelligent detection device for outsourced personnel information in an embodiment of the present invention, as shown below. Figure 4 As shown, the intelligent detection device for outsourced personnel information includes:

[0132] Data acquisition module 401 is used to acquire outsourced personnel data, which includes contract information, personnel entry and exit information, and attendance record information;

[0133] The information review module 402 is used to input outsourced personnel data into the outsourced personnel information review model and obtain the outsourced personnel information review result based on the preset outsourced personnel information template. The outsourced personnel information review model is obtained by training a deep learning network using historical outsourced personnel data. The deep learning network is generated by integrating natural language processing (NLP) and computer vision (CV) technologies.

[0134] The database construction module 403 is used to construct an outsourced personnel information review database; the outsourced personnel information review database includes material format review requirements, content completeness review requirements, and logical consistency review requirements.

[0135] The information view construction module 404 is used to construct an outsourced personnel information view based on the outsourced personnel information review results and the outsourced personnel information review database.

[0136] The information detection module 405 is used to detect the outsourced personnel's entry and exit status, contract period, and attendance based on the outsourced personnel information view, and obtain the information detection results of the outsourced personnel.

[0137] Figure 5 This is a specific example diagram of the structure of the intelligent detection device for outsourced personnel information in an embodiment of the present invention, as shown below. Figure 5 As shown in one embodiment, Figure 4 The intelligent detection device for outsourced personnel information shown in the embodiment of the present invention may further include: a data verification module 501.

[0138] In one embodiment, the data verification module 501 is specifically used for:

[0139] After obtaining the outsourced personnel data, a data consistency check is performed on the obtained outsourced personnel data to eliminate data conflicts and obtain usable outsourced personnel data.

[0140] In one embodiment, the preset outsourced personnel information template is determined in the following way:

[0141] Requirements for verifying the information of outsourced personnel; these requirements include the type of outsourced personnel information, the required content of the outsourced personnel information, and the format standards for the outsourced personnel information.

[0142] Based on the information verification requirements for outsourced personnel and the business scenarios of outsourced personnel, information templates for outsourced personnel under different business scenarios are determined.

[0143] In one embodiment, the information detection module 405 is specifically used for:

[0144] Based on the outsourced personnel information view, determine the consistency detection results between the actual entry and exit times of personnel and the information registered in the system;

[0145] Based on the outsourced personnel information view, determine the contract effective time and expiration time of the outsourced personnel, and generate contract expiration detection results within a preset period before the contract expires;

[0146] Based on the outsourced personnel information view, the attendance risk detection results of the outsourced personnel are determined; the attendance risk detection results include outsourced personnel having no consecutive clock-in information and abnormal clock-in location information.

[0147] Figure 6 This is a specific example diagram of the structure of the intelligent detection device for outsourced personnel information in an embodiment of the present invention, as shown below. Figure 6 As shown in one embodiment, Figure 4 The intelligent detection device for outsourced personnel information shown in the embodiment of the present invention may further include: an early warning module 601.

[0148] In one embodiment, the early warning module 601 is specifically used for:

[0149] Based on the outsourced personnel information view, the outsourced personnel's entry and exit status, contract period, and attendance are checked. After obtaining the information check results of the outsourced personnel, the abnormality type and risk level of the outsourced personnel are determined according to the information check results of the outsourced personnel.

[0150] Early warning notifications are generated based on the type of abnormality and risk level of outsourced personnel.

[0151] In one embodiment, the abnormal types of outsourced personnel include overstaying their visas, contract expiration, consecutive absences from attendance records, and non-compliant qualifications.

[0152] Based on the aforementioned inventive concept, such as Figure 7 As shown, the present invention also proposes a computer device 700, including a memory 710, a processor 720, and a computer program 730 stored in the memory 710 and executable on the processor 720. When the processor 720 executes the computer program 730, it implements the aforementioned intelligent detection method for outsourced personnel information.

[0153] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned intelligent detection method for outsourced personnel information.

[0154] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the aforementioned intelligent detection method for outsourced personnel information.

[0155] In this embodiment of the invention, outsourced personnel data is acquired, including contract information, personnel entry and exit information, and attendance records. This data is then input into a large-scale outsourced personnel information review model, and review results are obtained based on a preset outsourced personnel information template. The large-scale outsourced personnel information review model is trained using historical outsourced personnel data on a deep learning network. An outsourced personnel information review database is constructed, including requirements for material format review, content completeness review, and logical consistency review. Based on the outsourced personnel information review results and the database, an outsourced personnel information view is constructed. Based on this view, the outsourced personnel's entry and exit status, contract duration, and attendance are checked to obtain the outsourced personnel information detection results. This embodiment of the invention achieves intelligent outsourced personnel information detection through large-scale model-based information review, adapting to large-scale centralized management scenarios and effectively improving review efficiency and accuracy.

[0156] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0157] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0158] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0159] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0160] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligently detecting information on outsourced personnel, characterized in that, include: Acquire outsourced personnel data, which includes contract information, personnel entry and exit information, and attendance records. The outsourced personnel data is input into the outsourced personnel information review model, and the review results are obtained based on the preset outsourced personnel information template. The outsourced personnel information review model is obtained by training a deep learning network using historical outsourced personnel data. The deep learning network is generated by integrating natural language processing (NLP) and computer vision (CV) technologies. Establish an outsourced personnel information review database; the outsourced personnel information review database includes material format review requirements, content completeness review requirements, and logical consistency review requirements; Based on the results of the outsourced personnel information review and the outsourced personnel information review database, construct an outsourced personnel information view; Based on the outsourced personnel information view, the outsourced personnel's entry and exit status, contract period, and attendance are checked to obtain the outsourced personnel information check results.

2. The method as described in claim 1, characterized in that, After obtaining the outsourced personnel data, it also includes: The acquired outsourced personnel data is subjected to data consistency verification, and usable outsourced personnel data is obtained after eliminating data conflicts.

3. The method as described in claim 1, characterized in that, The preset template for outsourced personnel information is determined in the following way: Requirements for verifying the information of outsourced personnel; these requirements include the type of outsourced personnel information, the required content of the outsourced personnel information, and the format standards for the outsourced personnel information. Based on the information verification requirements for outsourced personnel and the business scenarios of outsourced personnel, information templates for outsourced personnel under different business scenarios are determined.

4. The method as described in claim 1, characterized in that, Based on the outsourced personnel information view, the following are checked: entry and exit status, contract period, and attendance record of outsourced personnel. The results of the outsourced personnel information check are obtained, including: Based on the outsourced personnel information view, determine the consistency detection results between the actual entry and exit times of personnel and the information registered in the system; Based on the outsourced personnel information view, determine the contract effective time and expiration time of the outsourced personnel, and generate contract expiration detection results within a preset period before the contract expires; Based on the outsourced personnel information view, the attendance risk detection results of the outsourced personnel are determined; the attendance risk detection results include outsourced personnel having no consecutive clock-in information and abnormal clock-in location information.

5. The method as described in claim 1, characterized in that, Based on the outsourced personnel information view, the outsourced personnel's entry and exit status, contract period, and attendance are checked. After obtaining the outsourced personnel information check results, the following are also included: Based on the information detection results of outsourced personnel, determine the abnormality type and risk level of the outsourced personnel; Early warning notifications are generated based on the type of abnormality and risk level of outsourced personnel.

6. The method as described in claim 5, characterized in that, The abnormal types of outsourced personnel include overstaying their contracts, contract expiration, continuous absence from clocking in, and non-compliant qualifications.

7. An intelligent detection device for outsourced personnel information, characterized in that, include: The data acquisition module is used to acquire outsourced personnel data, which includes contract information, personnel entry and exit information, and attendance record information. The information verification module is used to input outsourced personnel data into the outsourced personnel information verification model and obtain the outsourced personnel information verification result based on the preset outsourced personnel information template. The outsourced personnel information verification model is obtained by training a deep learning network using historical outsourced personnel data. The deep learning network is generated by integrating natural language processing (NLP) and computer vision (CV) technologies. The database construction module is used to build an outsourced personnel information review database; the outsourced personnel information review database includes material format review requirements, content completeness review requirements, and logical consistency review requirements. The information view construction module is used to construct an information view of outsourced personnel based on the review results of outsourced personnel information and the outsourced personnel information review database; The information detection module is used to detect the outsourced personnel's entry and exit status, contract period, and attendance based on the outsourced personnel information view, and obtain the information detection results of the outsourced personnel.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images