Search

CN-122022748-A - Enterprise human resource management system based on artificial intelligence

CN122022748ACN 122022748 ACN122022748 ACN 122022748ACN-122022748-A

Abstract

The invention relates to the technical field of human resource management, and discloses an enterprise human resource management system based on artificial intelligence, which comprises an image construction module, a scene simulation module, a characteristic simulation module, an employee screening module and a potential prediction module, wherein the image construction module is used for constructing a digital twin image which is updated regularly, the scene simulation module is used for simulating an enterprise virtual scene, the characteristic simulation module is used for simulating intrinsic potential characteristics, the employee screening module is used for screening potential employees from the employees, the potential prediction module is used for identifying culture indexes and preparing culture management information.

Inventors

  • LI SUZHEN

Assignees

  • 首聘(北京)科技有限公司

Dates

Publication Date
20260512
Application Date
20260130

Claims (10)

  1. 1. An artificial intelligence-based enterprise human resource management system, comprising: the portrait construction module is used for dynamically matching the multi-mode data of the staff with the portrait bit to construct a digital twin portrait which is provided with update nodes and is updated regularly; the scene simulation module is used for extracting an image tag of the digital twin image, making scene demands by taking the image tag as a scene core, and simulating an enterprise virtual scene matched with the scene demands; The feature simulation module is used for importing the digital twin image into the enterprise virtual scene, dynamically simulating the enterprise virtual scene under a simulation mechanism and simulating the intrinsic potential feature; The staff screening module is used for converting the intrinsic potential characteristics into characteristic scores, calculating comprehensive potential scores through the characteristic scores, and screening potential staff from staff; the potential prediction module is used for forming the multi-mode data and the intrinsic potential characteristics into comprehensive identification data, identifying the culture indexes through the potential quantitative identification model, and preparing culture management information of potential staff according to the culture indexes.
  2. 2. The artificial intelligence based enterprise human resource management system of claim 1, wherein the multimodal data includes hardware performance features, software behavior features, and test feedback features; the hardware performance characteristics comprise performance assessment values, assessment prepositions, participation project grades, project completion degrees and business skill curves; The software behavior characteristics comprise effective channel rate, cooperation tendency rate, decision accuracy rate, conflict interaction rate and compression resistance level; the test feedback features include problem coping ideas, policy risk preferences, and learning agility.
  3. 3. The artificial intelligence-based enterprise human resource management system of claim 2, wherein the method for constructing the digital twin portraits comprises the following steps: Removing repeated data and error data in the multi-mode data, and converting the multi-mode data into a uniform format to obtain format data; Simulating a basic image by a digital twin technology, establishing three label layers distributed by wrapping inside and outside in the basic image, and sequentially marking the label layers as an external layer, an internal layer and a potential layer according to the sequence from outside to inside; setting A annular distributed image positions in an external layer, an internal layer and a potential layer respectively, and importing hardware performance characteristics, software behavior characteristics and test feedback characteristics into the image positions of the external layer, the internal layer and the potential layer one by taking one characteristic corresponding to one image position as a standard; removing blank image bits, and constructing a channel with a bidirectional transmission function between two adjacent image bits, and marking the channel as an image channel; An update node having an update period is arranged on all the portrait channels to promote the conversion of the basic portrait into a digital twin portrait.
  4. 4. An artificial intelligence based enterprise human resource management system in accordance with claim 3, wherein the portrayal labels include cross-department resource conflicts, sudden public relations crisis, new product policy ramifications and team morale dips; The extraction method of the portrait tag comprises the following steps: Marking multi-mode data of an external layer, an internal layer and a potential layer in the digital twin portrait as index data by taking an updating period as a standard to obtain first index data, second index data and third index data; respectively comparing the first index data, the second index data and the third index data with standard labels in a label database in a consistent mode, and marking the standard labels with basically consistent and completely consistent comparison results as effective labels; and repeatedly comparing all the effective labels, and marking the effective labels with the repeated phenomenon as portrait labels to obtain B portrait labels.
  5. 5. The artificial intelligence based enterprise human resource management system of claim 4, wherein the simulation method of the enterprise virtual scenario is as follows: inquiring the identity information and the working information of the staff through a human resource database, binding and summarizing the identity information and the working information, and generating basic information; taking the portrait tag as a scene core, taking basic information as a scene contour, and combining the scene core and the scene contour into scene requirements to obtain B scene requirements; B scene demands are led into the intelligent scene engine one by one, scene authority and scene logic of the intelligent scene engine are set, and enterprise virtual scenes corresponding to the B scene demands are simulated.
  6. 6. The system for managing human resources of an enterprise based on artificial intelligence according to claim 5, wherein the simulation mechanism is to simulate all the intrinsic potential features as the end of one dynamic simulation, and to simulate the overlap ratio of any two adjacent intrinsic potential features greater than the calibrated overlap threshold as the end of all dynamic simulation.
  7. 7. The artificial intelligence based enterprise human resource management system of claim 6, wherein the intrinsic potential features include business decision features, communication features, resource allocation features, administrative management features, and risk prevention and control features; The simulation method of the intrinsic potential features comprises the following steps: A10, arranging B enterprise virtual scenes into a scene queue, and importing digital twin portraits into the first enterprise virtual scene in the scene queue; a11, initializing simulation parameters in an enterprise virtual scene, sending dynamic simulation instructions to the enterprise virtual scene, simulating intrinsic potential characteristics, and carrying out integrity analysis on the intrinsic potential characteristics; a12, repeatedly executing A11 when the intrinsic potential feature is not in the complete state, and executing A13 when the intrinsic potential feature is in the complete state; And A13, eliminating the simulated enterprise virtual scene in the scene queue, importing the digital twin images into the rest enterprise virtual scenes positioned at the first position in the field Jing Duilie, and repeatedly executing A11-A13 until the coincidence ratio of any two adjacent intrinsic potential features is larger than the calibrated coincidence threshold value, and obtaining the intrinsic potential features.
  8. 8. The artificial intelligence based enterprise human resource management system of claim 7, wherein the feature scores include business decision scores, communication scores, resource allocation scores, administrative scores, and risk prevention scores; the screening method of potential staff comprises the following steps: inquiring professional attributes of staff in enterprises, and indexing a corresponding coefficient set from a database by taking the professional attributes as index references; respectively giving a business decision score, a communication score, a resource allocation score, an administration score and a risk prevention and control score to weight coefficients in the coefficient set, and calculating a comprehensive potential score by carrying out weighted summation on the weight coefficients; and carrying out potential analysis on the comprehensive potential scores of the employees, and marking the employees with the comprehensive potential scores larger than a preset potential score threshold as potential employees.
  9. 9. The artificial intelligence based enterprise human resource management system of claim 8, wherein the cultivation indicators include professional direction, management level, molding cycle and revenue value; professional directions include personnel organization, technical development and financial management; The management level comprises a high layer, a middle layer and a base layer; The molding cycle included one month, six months, and twelve months.
  10. 10. The artificial intelligence based enterprise human resource management system of claim 9, wherein the culture management information is divided into three blocks, the first block is a history block, the second block is a test block, the third block is a culture block, multi-modal data is imported in the history block, intrinsic potential features are imported in the test block, and culture indexes are imported in the culture block to generate the culture management information.

Description

Enterprise human resource management system based on artificial intelligence Technical Field The invention relates to the technical field of human resource management, in particular to an enterprise human resource management system based on artificial intelligence. Background Along with the expansion of enterprise scale and the aggravation of market competition, human resource management has become an important component of enterprise core competitiveness, and human resource management systems based on Excel tables or simple databases have difficulty in meeting the requirements of enterprises for accurate identification, scientific evaluation and efficient culture of potential talents, so that accurate identification of potential talents in enterprises is required by means of artificial intelligence, and the efficient management effect of human resources is achieved. The patent application with the publication number of CN115204849A discloses an enterprise human resource management method and system based on artificial intelligence, comprising the following steps of receiving the self-evaluation information of all new staff, receiving resource configuration information, obtaining new staff position allocation information according to the matching degree of all the new staff's posts and the number of people required by each post, splitting the total post matters of each post according to the number of people required by each post and the matching degree of the specific post matters of the corresponding new staff, and obtaining post matters allocation information; When the existing human resource management system is used for identifying and evaluating potential staff, staff portraits are generally constructed based on historical static data, so that the staff portraits cannot be dynamically associated with real-time work performance changes of the staff, hysteresis exists in data on which follow-up human resource decisions depend, the real performance of the staff in a complex and changeable enterprise real management scene cannot be comprehensively and accurately simulated by adopting an evaluation mode of artificial subjective experience, deep capability characteristics of the staff in a key situation are difficult to scientifically and comprehensively find, the evaluation result is often high in subjectivity and limitation, and the management effect of human resources is further reduced. In view of the above, the present invention proposes an artificial intelligence-based enterprise human resource management system to solve the above-mentioned problems. Disclosure of Invention In order to overcome the defects in the prior art and achieve the purposes, the invention provides the technical scheme that the enterprise human resource management system based on artificial intelligence comprises: the portrait construction module is used for dynamically matching the multi-mode data of the staff with the portrait bit to construct a digital twin portrait which is provided with update nodes and is updated regularly; the scene simulation module is used for extracting an image tag of the digital twin image, making scene demands by taking the image tag as a scene core, and simulating an enterprise virtual scene matched with the scene demands; The feature simulation module is used for importing the digital twin image into the enterprise virtual scene, dynamically simulating the enterprise virtual scene under a simulation mechanism and simulating the intrinsic potential feature; The staff screening module is used for converting the intrinsic potential characteristics into characteristic scores, calculating comprehensive potential scores through the characteristic scores, and screening potential staff from staff; the potential prediction module is used for forming the multi-mode data and the intrinsic potential characteristics into comprehensive identification data, identifying the culture indexes through the potential quantitative identification model, and preparing culture management information of potential staff according to the culture indexes. Further, the multi-modal data includes hardware performance characteristics, software behavior characteristics, and test feedback characteristics; the hardware performance characteristics comprise performance assessment values, assessment prepositions, participation project grades, project completion degrees and business skill curves; The software behavior characteristics comprise effective channel rate, cooperation tendency rate, decision accuracy rate, conflict interaction rate and compression resistance level; the test feedback features include problem coping ideas, policy risk preferences, and learning agility. Further, the method for constructing the digital twin image comprises the following steps: Removing repeated data and error data in the multi-mode data, and converting the multi-mode data into a uniform format to obtain format data; Simulating a basic image by a dig