Method and system for enterprise employee social security compliance management based on knowledge graph

Abstract

The invention discloses a method and system for enterprise employee social security compliance management based on a knowledge graph, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting employee basic data and employee social security data corresponding to each enterprise in real time, and adding an enterprise identifier for each piece of employee basic data and employee social security data; social security policy data are obtained, a policy change time sequence is constructed based on the social security policy data, and the effective time, the region range, the applicable crowd and the specific terms of each social security policy are recorded; in response to an enterprise employee social security compliance management request, inputting the employee basic data, the employee social security data and the social security policy data of the corresponding enterprise as an original data set into an enterprise employee social security compliance management model, and outputting a social security adjustment strategy, the problems that in the prior art, policy changes cannot be dynamically adapted, the social security states of employees cannot be compared in real time, and the cost optimal adjustment strategy cannot be automatically generated are solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and particularly to a method and system for enterprise employee social insurance compliance management based on a knowledge graph. Background Art

[0002] In enterprise operation management, employee social insurance compliance management is crucial. Social insurance policies are regional and time-sensitive, and will be dynamically adjusted over time, involving complex contents such as effective time, regional scope, applicable population, and specific terms. At the same time, employees' basic data and social insurance data are continuously generated. Traditional management methods rely on manual sorting of policies and data checking, which are prone to errors due to policy understanding deviations and large amounts of data, and it is difficult to respond to the enterprise compliance management requirements in a timely manner.

[0003] With the expansion of enterprise scale and the improvement of policy complexity, the problems of low efficiency and poor accuracy in manual management have become increasingly prominent, and it is impossible to effectively determine the social insurance status of employees, calculate adjustment costs, and formulate strategies.

[0004] Therefore, there is an urgent need for a method that can achieve enterprise employee social insurance compliance management with the help of a knowledge graph. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for enterprise employee social insurance compliance management based on a knowledge graph, which can achieve enterprise employee social insurance compliance management with the help of a knowledge graph, and improve the efficiency and compliance of social insurance management.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for enterprise employee social insurance compliance management based on a knowledge graph, comprising: Real-time collecting employees' basic data and social insurance data corresponding to each enterprise, adding an enterprise identifier to each piece of employees' basic data and social insurance data, where the employees' basic data includes employee ID, name, gender, age, employment time, position, rank, household register, branch company / department, and contract type; Obtaining social insurance policy data, constructing a policy change time series based on the social insurance policy data, and recording the effective time, regional scope, applicable population, and specific terms of each social insurance policy; In response to a management request for enterprise employee social insurance compliance, inputting the employees' basic data, social insurance data, and social insurance policy data of the corresponding enterprise as a raw data set into an enterprise employee social insurance compliance management model, where the enterprise employee social insurance compliance management model includes an input layer, a data processing layer, an encoding layer, a graph update layer, an analysis layer, a calculation layer, a decision layer, and an output layer; The input layer is used to receive the raw data set; The data processing layer is used to process the original data set to obtain a standard data set; The encoding layer is used to encode the standard data in the standard data set to obtain a keyword field set with data timestamps; The graph update layer is used to incrementally update the historical graph based on the key data field set with data timestamps, generate a new graph, and retain the historical graph; The analysis layer is used to compare the new graph and the historical graph to determine the employee status, and determine the social security employees to be adjusted based on the employee status; The calculation layer is used to calculate the social security adjustment cost of the social security employees to be adjusted; The decision-making layer is used to generate a social security adjustment strategy based on the social security adjustment cost and the social security employees to be adjusted; The output layer is used to output the social security adjustment strategy.

[0007] Based on the above technical solutions, the present invention can also be improved as follows: Optionally, the obtaining of the social security policy data and constructing the policy change time series based on the social security policy data includes: Constructing a policy change time series according to the time point t, the policy set in effect at the time point t, the policy set changed at the time point t, and the set T of time points.

[0008] Optionally, the data processing layer is used to process the original data set to obtain a standard data set, including: Verifying each single original data record in the original data set through a verification rule set, retaining the data records that meet all the verification rules, and forming a verified data set, where the verification rule set includes a non-empty constraint rule and a format verification rule; Applying a cleaning rule set to process the data records in the verified data set to obtain a cleaned data set; Based on a field mapping rule set, performing field conversion and value formatting on the data records in the cleaned data set to obtain a standard data set.

[0009] Optionally, the encoding layer is used to encode the standard data in the standard data set to obtain a keyword field set with data timestamps, including: Using a field name prefix extraction function to obtain a field name prefix, using a hash function to concatenate the field name prefix, field name, data timestamp, and version identifier generated based on the field value to obtain a concatenated hash result, and obtaining a keyword field set based on the concatenated hash result.

[0010] Optionally, the graph update layer is used to incrementally update the historical graph based on a set of key data fields with data timestamps, generate a new graph, and retain the historical graph, including: Construct the historical graph using a spatio-temporal knowledge graph structure. The spatio-temporal knowledge graph uses a four-dimensional spatio-temporal coordinate system mapping technology to map the historical graph, regional scope, and employee changes to the four-dimensional spatio-temporal coordinate system; Adopt a blockchain evidence storage mechanism to record the operation subject, time, and reason for each incremental update.

[0011] Optionally, the graph update layer is used to incrementally update the historical graph based on a set of key data fields with data timestamps, generate a new graph, including: Calculate the new graph through a formula; ; In the formula, is the new graph, is the historical graph, is the fusion operation, is the incremental update operation function, is the set of keyword fields with data timestamps, is the time threshold.

[0012] Optionally, the analysis layer is used to compare the new graph and the historical graph to determine the employee status, including: Construct an employee status transition matrix and quantify the employee status change probability path based on the employee status transition matrix.

[0013] A system for enterprise employee social insurance compliance management based on a knowledge graph, including: An employee data acquisition module, used to collect the basic employee data and employee social insurance data corresponding to each enterprise in real time, add an enterprise identifier to each piece of basic employee data and employee social insurance data. The basic employee data includes employee ID, name, gender, age, employment time, position, rank, household register, branch / department, and contract type; A policy data acquisition module, used to obtain social insurance policy data, construct a policy change time series based on the social insurance policy data, and record the effective time, regional scope, applicable population, and specific terms of each social insurance policy; A social insurance compliance management module, used to respond to a management request for enterprise employee social insurance compliance, and input the basic employee data, employee social insurance data, and social insurance policy data of the corresponding enterprise as an original data set into an enterprise employee social insurance compliance management model. The enterprise employee social insurance compliance management model includes an input layer, a data processing layer, an encoding layer, a graph update layer, an analysis layer, a calculation layer, a decision layer, and an output layer; The input layer is used to receive the original data set; The data processing layer is used to process the original data set to obtain a standard data set; The encoding layer is used to encode the standard data in the standard data set to obtain a keyword field set with data timestamps; The graph update layer is used to incrementally update the historical graph based on the key data field set with data timestamps, generate a new graph, and retain the historical graph; The analysis layer is used to compare the new graph and the historical graph to determine the employee status, and determine the employees whose social insurance needs to be adjusted based on the employee status; The calculation layer is used to calculate the social insurance adjustment cost of the employees whose social insurance needs to be adjusted; The decision-making layer is used to generate a social insurance adjustment strategy based on the social insurance adjustment cost and the employees whose social insurance needs to be adjusted; The output layer is used to output the social insurance adjustment strategy.

[0014] An electronic device includes a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the computer program, the steps of the method are implemented.

[0015] A non-transitory computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method are implemented.

[0016] The present invention has the following advantages: In the present invention, the method for enterprise employee social insurance compliance management based on a knowledge graph collects employee data in real time and adds an enterprise identifier, synchronously constructs a time series of policy changes, realizes the dynamic matching of employee information, social insurance data, and policies and regulations, and solves the problems of data lag and policy interpretation deviation in traditional management. Through the enterprise employee social insurance compliance management model, data is standardized, encoded, graph updated, and deeply analyzed, automatically identifying employees whose social insurance needs to be adjusted, calculating the social insurance adjustment cost of the employees whose social insurance needs to be adjusted, and generating a social insurance adjustment strategy, shortening the manual verification cycle from several days to several hours and greatly improving management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] For the purpose of illustration rather than limitation, the present invention is described in conjunction with the embodiments and drawings of the present invention, wherein: Figure 1 is a flowchart of the method for enterprise employee social insurance compliance management based on a knowledge graph in an embodiment of the present invention; Figure 2 is a schematic diagram of the main components of the system for enterprise employee social insurance compliance management based on a knowledge graph in an embodiment of the present invention; Figure 3Schematic diagram of the physical structure of the electronic device provided by the present invention. Specific embodiments

[0018] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification of the present invention and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to implement the embodiments of the present invention described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0020] It should be noted that, without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0021] Figure 1 Schematic flowchart of the method for enterprise employee social insurance compliance management based on a knowledge graph in the embodiments of the present invention. As Figure 1 shown, the method for enterprise employee social insurance compliance management based on a knowledge graph provided by the embodiments of the present invention includes the following steps S101 to S103.

[0022] S101, Real-time collect the basic employee data and employee social insurance data corresponding to each enterprise, and add an enterprise identifier to each piece of basic employee data and employee social insurance data.

[0023] The basic employee data includes employee ID, name, gender, age, start date, position, rank, household register, branch company / department, contract type (full-time / part-time / labor dispatch), etc.; it is used to identify individual employee characteristics (such as household register affecting the social insurance payment ratio), position attributes (such as high-risk positions requiring additional work injury insurance), and contract type (determining the insurance obligation).

[0024] Employee social insurance data includes social insurance number, insured types (pension / medical / unemployment / work injury / maternity), contribution base, contribution ratio, contribution status (normal / supplementary payment / interrupted), cumulative contribution years, etc. It is used to directly reflect the compliance status of employees' social insurance (such as whether the base meets the standard and whether the insurance types are complete), and support subsequent policy matching and risk analysis.

[0025] Through the docking of the enterprise HR system (such as SAP SuccessFactors, DingTalk personnel module), real-time synchronization via API interface, or batch import of Excel / CSV files, the basic employee data and employee social insurance data corresponding to each enterprise are collected in real time.

[0026] Adopt the combination of "enterprise code - timestamp", such as CN-2025-001 (CN is the short name of the enterprise, 2025 is the year, and 001 is the serial number), or use the unified social credit code (such as 91110108MA01FXXXXX). Generate a unique identifier through the UUID algorithm, or automatically extract it from the enterprise registration information (requiring docking with the industrial and commercial database).

[0027] Add an enterprise identification field to each employee data record (basic data / social insurance data) to ensure clear data attribution (such as distinguishing the social insurance records of the same employee in different subsidiaries through identification). When an enterprise has multiple management systems (such as the separation of the headquarters HR system and the branch social insurance system), cross-system data matching is achieved through the enterprise identification (such as associating the basic data of employee A at the headquarters with the social insurance data of the branch). If an enterprise identification is not obtained for a certain piece of data (such as data synchronization delay), it is automatically marked as "to be associated", triggering an early warning mechanism (such as email notification to HR for supplementary recording).

[0028] Through the API interface, real-time synchronization of key data such as employee onboarding / resignation and social insurance base adjustment is achieved (such as data automatically entering the system on the day of employee onboarding). A full-scale data verification is started at 1:00 am every day to supplement the data missed during the day and ensure the integrity of the data on the T+1 day.

[0029] S102, Obtain social insurance policy data, construct a policy change time series based on the social insurance policy data, and record the effective time, regional scope, applicable population, and specific terms of each social insurance policy.

[0030] Construct a policy change time series according to the time point t, the set of policies in effect at time point t, the set of policies changed at time point t, and the set of time points T.

[0031] Specifically, calculate the policy change time series through formula (1); Formula (1); In the formula, is the policy change time series, is the time point, is the set of policies in effect at time point t, is the set of policies that change at time point t, is the set of time points.

[0032] An example: Scenario setting Region: XX City (in 2025, involving adjustments to the social insurance base and unemployment insurance policies) Time range: (T = {2025-06-30, 2025-07-01, 2025-07-15}) (key time points for policy changes); Step 1: Define the set of policies for each time point Time point ; Set of policies in effect : Lower limit of social insurance base: 6000 yuan / month; Unemployment insurance contribution rate: 1% (enterprise + individual); Set of changed policies : No new policies are in effect ( , because the July policies have not reached the effective time); Time point ; Set of policies in effect : Lower limit of social insurance base: 6500 yuan / month (new policy); Unemployment insurance contribution rate: 1% (enterprise + individual) (old policy continues); Set of changed policies : Social insurance base policy change (new addition of "base 6500 yuan"); Time point ; Set of policies in effect : Lower limit of social insurance base: 6500 yuan / month; Unemployment insurance contribution rate: 0.8% (enterprise + individual) (new policy); Set of changed policies : Unemployment insurance policy change (rate from 1% to 0.8%).

[0033] Step 2: Substitute the data into formula (1) and calculate: .

[0034] S103. In response to the management request for the social insurance compliance of enterprise employees, input the basic employee data, employee social insurance data, and social insurance policy data of the corresponding enterprise into the enterprise employee social insurance compliance management model as the original data set.

[0035] The enterprise employee social insurance compliance management model includes an input layer, a data processing layer, an encoding layer, a graph update layer, an analysis layer, a calculation layer, a decision layer, and an output layer; The input layer is used to receive the original data set; The data processing layer is used to process the original data set to obtain a standard data set, including: Verify each single original data record in the original data set through a verification rule set, retain the data records that meet all verification rules, and form a verified data set, where the verification rule set includes a non-empty constraint rule and a format verification rule; Apply a cleaning rule set to process the data records in the verified data set to obtain a cleaned data set; Based on a field mapping rule set, perform field conversion and value formatting on the data records in the cleaned data set to obtain a standard data set; The encoding layer is used to encode the standard data in the standard data set to obtain a keyword field set with data timestamps, including: Use a field name prefix extraction function to obtain a field name prefix, use a hash function to concatenate the field name prefix, field name, data timestamp, and a version identifier generated based on the field value to obtain a concatenated hash result, and obtain a keyword field set based on the concatenated hash result.

[0036] Specifically, calculate the encoded keyword field through formula (2); Formula (2); In the formula, is the encoded keyword field, is the field name, is the data timestamp, is the field value corresponding to field name k, is the field name prefix extraction function, is the string concatenation operator, is the hash function, is the version identifier generated based on the field value; Ensure that the encoding generated for the same field name k at different times or with different values v is completely different through the timestamp and the hash function (e.g., there is no conflict in the encoding of "social insurance base" of 8500 yuan and 9000 yuan); the prefix extraction function Retain the business semantics of fields (such as "social insurance"), making the encoding results both machine-readable and human-interpretable, and reducing the understanding cost of subsequent graph construction. Bind the policy cycle (such as 2025Q3), and support quickly identifying the data that needs to be updated when the policy changes (such as automatically marking the old version data as expired after the base number adjustment).

[0037] Calculate the data timestamp through formula (3); Formula (3); In the formula, is the data timestamp, is to convert the time to the ISO 8601 format, is the millisecond-level timestamp; Based on the ISO 8601 standard format, overlay the millisecond-level timestamp to improve the time accuracy from the second level (such as 2025-07-03T14:20:30) to the millisecond level (such as 1746368430123), avoiding time conflicts in data collection in high-concurrency scenarios. The ISO 8601 format is an international standard, which is convenient for unified time expression when docking with government affairs platforms and third-party systems, reducing the format conversion cost. The data timestamp naturally supports sorting and can be directly used to judge the sequence of data updates (such as the chronological comparison of the policy effective time and the employee data collection time).

[0038] Calculate the set of key fields with data timestamps through formula (4); Formula (4); In the formula, is the set of key fields with data timestamps, is to extract the key-value from the standard data set; Convert all key-value pairs in the standard data set into the encoding set K, realizing the unified structured processing of data, providing a standardized input for the knowledge graph, ensuring that all fields are encoded through set operations, and avoiding data omission (such as forcing core fields such as "social insurance base number" and "insured types" to exist in K). Encoding can be executed in parallel by field (such as multi-threaded processing of fields such as "name" and "hire date"), improving the efficiency of large-scale data processing. If the encoding of a certain field fails (such as incorrect format), the problem data can be automatically marked and isolated to ensure the validity of the set K.

[0039] The graph update layer is used to perform incremental updates on the historical graph based on the set of key data fields with data timestamps, generate a new graph, and retain the historical graph, including: Calculate the new graph through formula (5); Formula (5); In the formula, For the new map, For historical maps, For fusion operation, is the incremental update operation function, A collection of key fields with data timestamps. is the time threshold; Based on historical graph Based on the incremental update function , integrate the new data K with timestamp (combined with time threshold T to filter valid data) into it, accurately update the map content, such as social security policy adjustments and employee data changes, which can be incrementally iterated in the original map framework without rebuilding the map. , forming a graph version chain, which can trace back historical status, such as querying the company’s past social security compliance and the impact of policy iterations, providing a complete data track for auditing and analysis.

[0040] For scenarios such as corporate employee social security data that changes dynamically but with small increments, only the changed parts are updated, greatly shortening the graph update cycle so that social security compliance analysis can be carried out in a timely manner based on the latest data. The time threshold T is used to filter invalid or outdated data to ensure that the updated information is valid and meets the time requirements. For example, only recent social security policy changes and employee data changes are processed to improve the quality of the graph and assist in accurately determining the social security compliance status.

[0041] The analysis layer is used to compare the new graph with the historical graph to determine the employee status, and determine the employees whose social insurance is to be adjusted based on the employee status, including: Constructing an employee state transition matrix, and quantifying the probability path of employee state change based on the employee state transition matrix; Determine the employee status of employee e through formula (6); Formula (6); In the formula, The employee status of employee e. To find the employee status s in the employee status set S that maximizes the result of the following expression, For the sum operation, is the number of factors involved, is the weight of the ith factor at time t, is the coefficient related to employee e, employee status s and factor i, is the ith judgment function, is a set of policy rules, is the time context, is the confidence of employee e at time t; One example is: Employee: Zhang San (Employee e), and the following changes are involved in the social security data: New graph: After July 1, 2025, the social security base is adjusted to 8,500 yuan (in line with the new policy); Historical graph: Before June 30, 2025, the social security base was 8,000 yuan (lower than the lower limit of the old policy, 8,200 yuan); Policy rules: The social security base should be ≥ 8,200 yuan (before July 1, 2025) and ≥ 8,500 yuan (after July 1, 2025); Time context: July 3, 2025 (the 3rd day after the policy comes into effect); Step 1: Define the input parameters; Set of employee statuses: ; Number of factors n: n = 2 (select two core factors, "compliance of social security base" and "policy effective time") Factor weights : (Compliance of social security base, with a higher weight because it directly affects compliance); (Policy effective time, for auxiliary judgment of whether retroactive adjustment is needed); Judgment function : ; Substitute the data: The new base of Zhang San ; ; Substitute the data: ; Coefficient : (When the base is compliant, support the "compliant" status), After the policy comes into effect, support the "compliant" status); (The base is already compliant, do not support "to be adjusted"), After the policy comes into effect, do not support "to be adjusted"); (The base is compliant, do not support "abnormal"), After the policy comes into effect, do not support "abnormal"); Because Zhang San's data is complete and the policy match is clear, the confidence level ; Step 2: Substitute into formula (6) and calculate the scores of the three statuses respectively: The score for the compliant status is 0.95, the score for the to-be-adjusted status is 0, and the score for the abnormal status is 0; Step 3: Judgment result Take the state corresponding to the maximum value: ; The calculation layer is used to calculate the social insurance adjustment cost of employees whose social insurance needs to be adjusted, including: Calculate the social insurance adjustment cost through formula (7); Formula (7); In the formula, is the social insurance adjustment cost, is an employee whose social insurance needs to be adjusted, is the set of employees whose social insurance needs to be adjusted, is the number of times of social insurance status change of employee e, is the summation operation for integer i from 1 to n, where n represents the number of time intervals, is the unit time cost change of the i-th change of employee e, is the length of the time interval of the i-th change of employee e; An example: XX Technology Company needs to adjust the social insurance base of 2 employees (due to policy changes in July 2025); Set of employees whose social insurance needs to be adjusted : Employee A: The base in June 2025 is 8000 yuan (lower than the new policy lower limit of 8500 yuan), and the adjustment needs to start from July 2025; Employee B: The base in June 2025 is 7500 yuan (lower than the new policy lower limit of 8500 yuan), and the payment needs to be made up from June 2025; Step 1: Define input parameters; Employee A: Number of times of social insurance status change (Only 1 base adjustment, effective from July 2025); Change time interval: (Cut-off time before change), (The first month after change); Length of time interval (Calculated by natural month); Unit time cost change (Base difference × social insurance payment ratio, simplified to direct difference); Employee B: Number of times of social insurance status change (Need to make up June 2025, adjust July 2025); And so on; Step 2: Substitute into formula (7) to calculate and obtain = RMB 2,500; The decision-making layer is used to generate a social insurance adjustment strategy based on the social insurance adjustment cost and the employees whose social insurance needs to be adjusted; The output layer is used to output the social insurance adjustment strategy.

[0042] Figure 2 It is a schematic diagram of the main components of the system for enterprise employee social insurance compliance management based on a knowledge graph in the embodiments of the present invention. As Figure 2 shown, the system 1 for enterprise employee social insurance compliance management based on a knowledge graph provided by an embodiment of the present invention includes an employee data acquisition module 10, a policy data acquisition module 20, and a social insurance compliance management module 30.

[0043] The employee data acquisition module 10 is used to collect in real time the basic employee data and employee social insurance data corresponding to each enterprise, add an enterprise identifier to each piece of basic employee data and employee social insurance data, and the basic employee data includes employee ID, name, gender, age, employment time, position, rank, household register, branch company / department, and contract type; The policy data acquisition module 20 is used to acquire social insurance policy data, construct a policy change time series based on the social insurance policy data, and record the effective time, regional scope, applicable population, and specific terms of each social insurance policy; The social insurance compliance management module 30 is used to, in response to a management request for enterprise employee social insurance compliance, input the basic employee data, employee social insurance data, and social insurance policy data of the corresponding enterprise into an enterprise employee social insurance compliance management model as an original data set, and the enterprise employee social insurance compliance management model includes an input layer, a data processing layer, an encoding layer, a graph update layer, an analysis layer, a calculation layer, a decision-making layer, and an output layer; The input layer is used to receive the original data set; The data processing layer is used to process the original data set to obtain a standard data set; The encoding layer is used to encode the standard data in the standard data set to obtain a keyword field set with data timestamps; The graph update layer is used to incrementally update the historical graph based on the keyword data field set with data timestamps, generate a new graph, and retain the historical graph; The analysis layer is used to compare the new graph and the historical graph to determine the employee status, and determine the employees whose social insurance needs to be adjusted based on the employee status; The calculation layer is used to calculate the social insurance adjustment cost of the employees whose social insurance needs to be adjusted; The decision-making layer is used to generate a social insurance adjustment strategy based on the social insurance adjustment cost and the employees whose social insurance needs to be adjusted; The output layer is used to output the social security adjustment strategy.

[0044] Figure 3 It is a schematic diagram of the physical structure of the electronic device provided by the embodiment of the present invention. As Figure 3 shown, the electronic device 40 includes: a processor 401 (processor), a memory 402 (memory), and a bus 403; Among them, the processor 401 and the memory 402 communicate with each other through the bus 403; The processor 401 is used to call the program instructions in the memory 402 to execute the methods provided by the above-mentioned method embodiments, so as to execute the method provided by the embodiment of the present invention.

[0045] This embodiment provides a non-transitory computer-readable storage medium. The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions cause the computer to execute the method provided by the embodiment of the present invention.

[0046] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various storage media such as ROM, RAM, magnetic disk, or optical disc that can store program codes.

[0047] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for enterprise employee social insurance compliance management based on a knowledge graph, characterized in that Including: Real-time collect the basic employee data and employee social insurance data corresponding to each enterprise, add an enterprise identifier to each piece of basic employee data and employee social insurance data, and the basic employee data includes employee ID, name, gender, age, employment time, position, rank, household register, branch company / department, and contract type; Obtain social insurance policy data, construct a policy change time series based on the social insurance policy data, and record the effective time, regional scope, applicable population, and specific terms of each social insurance policy; In response to the management request for enterprise employee social insurance compliance, input the basic employee data, employee social insurance data, and social insurance policy data of the corresponding enterprise into the enterprise employee social insurance compliance management model as the original data set. The enterprise employee social insurance compliance management model includes an input layer, a data processing layer, a coding layer, a graph update layer, an analysis layer, a calculation layer, a decision layer, and an output layer; The input layer is used to receive the original data set; The data processing layer is used to process the original data set to obtain a standard data set; The coding layer is used to encode the standard data in the standard data set to obtain a keyword field set with data timestamps; The graph update layer is used to incrementally update the historical graph based on the keyword data field set with data timestamps, generate a new graph, and retain the historical graph; The analysis layer is used to compare the new graph and the historical graph to determine the employee status, and determine the employees whose social insurance needs to be adjusted based on the employee status; The calculation layer is used to calculate the social insurance adjustment cost of the employees whose social insurance needs to be adjusted; The decision layer is used to generate a social insurance adjustment strategy based on the social insurance adjustment cost and the employees whose social insurance needs to be adjusted; The output layer is used to output the social insurance adjustment strategy.

2. The method for enterprise employee social insurance compliance management based on a knowledge graph according to claim 1, characterized in that The obtaining of the social insurance policy data and constructing the policy change time series based on the social insurance policy data includes: Construct a policy change time series according to time point t, the set of policies in effect at time point t, the set of policies that have changed at time point t, and the set of time points T.

3. The method for enterprise employee social insurance compliance management based on a knowledge graph according to claim 1, wherein, The data processing layer is used to process the original data set to obtain a standard data set, including: Verify each single original data record in the original data set through a verification rule set, retain the data records that meet all verification rules, and form a verified data set. The verification rule set includes a non-empty constraint rule and a format verification rule; Apply a cleaning rule set to process the data records in the verified data set to obtain a cleaned data set; Based on a field mapping rule set, perform field conversion and value formatting on the data records in the cleaned data set to obtain a standard data set.

4. The method for enterprise employee social insurance compliance management based on a knowledge graph according to claim 1, wherein, The coding layer is used to encode the standard data in the standard data set to obtain a keyword field set with data timestamps, including: Use a field name prefix extraction function to obtain a field name prefix, use a hash function to concatenate the field name prefix, field name, data timestamp, and a version identifier generated based on the field value to obtain a concatenated hash result, and obtain a keyword field set based on the concatenated hash result.

5. The method for enterprise employee social insurance compliance management based on a knowledge graph according to claim 4, characterized in that, The graph update layer is used to incrementally update the historical graph based on a set of key data fields with data timestamps, generate a new graph, and retain the historical graph, including: Construct the historical graph using a spatio-temporal knowledge graph structure. The spatio-temporal knowledge graph uses a four-dimensional spatio-temporal coordinate system mapping technology to map the historical graph, regional scope, and employee changes to the four-dimensional spatio-temporal coordinate system; Adopt a blockchain evidence storage mechanism to record the operation subject, time, and reason for each incremental update.

6. The method for enterprise employee social insurance compliance management based on a knowledge graph according to claim 1, wherein The graph update layer is used to incrementally update the historical graph based on a set of key data fields with data timestamps, generate a new graph, including: Calculate the new graph through a formula; ； Wherein, is the new atlas, is the historical atlas, is the fusion operation, is the incremental update operation function, is the set of keyword fields with data timestamps, is the time threshold.

7. The method for enterprise employee social insurance compliance management based on a knowledge graph according to claim 1, characterized in that, The analysis layer is used to compare the new graph and the historical graph to determine the employee status, including: Construct an employee status transition matrix and quantify the employee status change probability path based on the employee status transition matrix.

8. A system for enterprise employee social insurance compliance management based on a knowledge graph, characterized in that, Including: An employee data acquisition module, which is used to collect the basic employee data and employee social insurance data corresponding to each enterprise in real time, add an enterprise identifier to each piece of basic employee data and employee social insurance data. The basic employee data includes employee ID, name, gender, age, start date, position, rank, household register, branch / department, and contract type; A policy data acquisition module, which is used to obtain social insurance policy data, construct a policy change time series based on the social insurance policy data, and record the effective time, regional scope, applicable population, and specific terms of each social insurance policy; A social insurance compliance management module, which is used to respond to a management request for the social insurance compliance of enterprise employees, and input the basic employee data, employee social insurance data, and social insurance policy data of the corresponding enterprise into an enterprise employee social insurance compliance management model. The enterprise employee social insurance compliance management model includes an input layer, a data processing layer, an encoding layer, a graph update layer, an analysis layer, a calculation layer, a decision layer, and an output layer; The input layer is used to receive the original data set; The data processing layer is used to process the original data set to obtain a standard data set; The encoding layer is used to encode the standard data in the standard data set to obtain a set of keyword fields with data timestamps; The graph update layer is used to incrementally update the historical graph based on a set of key data fields with data timestamps, generate a new graph, and retain the historical graph; The analysis layer is used to compare the new graph and the historical graph to determine the employee status, and determine the employees whose social insurance needs to be adjusted based on the employee status; The calculation layer is used to calculate the social insurance adjustment cost of the employees whose social insurance needs to be adjusted; The decision layer is used to generate a social insurance adjustment strategy based on the social insurance adjustment cost and the employees whose social insurance needs to be adjusted; The output layer is used to output the social insurance adjustment strategy.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 7.

10. A non-transitory computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method described in any one of claims 1 to 7.

Images