TWI731215B - Human resource management system and human resource management method - Google Patents

Abstract

A human resource management system includes an internal data server and a processing server. The internal data server is configured for storing several data lists. The processing server includes a model building module, an output input module, and a machine learning module. The model building module is configured for building several analysis models corresponding to a position according to the data lists. The input output module is configured for collecting several first data groups from an external data server and/or an internal data server. The machine learning module is configured for building an analysis list according to the analysis models and the first data groups. The input output module is configured for outputting the analysis list through a communication network.

Description

Human resource management system and human resource management method

This disclosure relates to a human resource management system and a human resource management method, and in particular, a human resource management system and a human resource management method related to artificial intelligence.

When recruiting talents, the human resources department has to select candidates who are suitable for the organization or a specific position in the organization from various channels and countless resumes, which is quite time-consuming. In addition, in the process of manpower selection, it is inevitable to bring personal subjective preferences, and thus miss potential and truly suitable talents for the enterprise.

Therefore, how to quickly find job candidates suitable for a specific position from the system to shorten the time and cost of screening and filtering by the human resources department, and establish a talent pool, provide other job matching and talent tracking, is one of the problems in this field to be improved One.

One aspect of this disclosure is to provide a human resource management 理系统。 Management system. This human resource management system includes an internal data server and a processing server. The internal data server is used to store multiple data lists. The processing server includes a model building module, an input/output module, and a machine learning module. The model creation module is used to create multiple analysis models corresponding to positions based on multiple data lists. The input/output module is used to collect multiple first data groups from the external data server and/or the internal data server. The machine learning module is used for creating an analysis list based on a plurality of analysis models and a plurality of first data sets. The input/output module is used to output the analysis list through the communication network.

Another aspect of this disclosure is to provide a human resource management method. This human resource management method includes the following steps: establishing multiple analysis models corresponding to positions based on multiple data lists; collecting multiple first data sets from an external database and/or internal database; based on multiple analysis models and multiple The first data group creates an analysis list; and outputs the analysis list through a communication network.

Therefore, according to the technical aspect of the present disclosure, the embodiments of the present disclosure provide a human resource management system and a human resource management method, and in particular, a human resource management system and a human resource management method related to artificial intelligence. In this way, the system can quickly find suitable candidates for the job, so as to shorten the time and cost of screening and filtering by the human resources department, and establish a talent pool to provide other job matching and talent tracking.

100‧‧‧Human Resource Management System

130‧‧‧Internal Data Server

150‧‧‧External Data Server

190、192‧‧‧Communication network

110‧‧‧Processing server

112‧‧‧I/O Module

113‧‧‧Model Creation Module

115‧‧‧Machine Learning Module

116‧‧‧Data Creation Module

117‧‧‧Message Generation Module

118‧‧‧Memory

170‧‧‧User Server

200‧‧‧Human Resource Management Method

S210, S230, S250, S270‧‧‧Step

In order to make the above and other objects, features, advantages of the present invention and The embodiments can be more obvious and easy to understand, and the description of the accompanying drawings is as follows: Figure 1 is a schematic diagram of a human resource management system drawn according to some embodiments of the present disclosure; and Figure 2 is a schematic diagram of a human resource management system based on the present disclosure. A schematic diagram of a human resource management method shown in some embodiments.

The following disclosure provides many different embodiments or illustrations for implementing different features of the present invention. The elements and configurations in the specific examples are used in the following discussion to simplify the disclosure. Any examples discussed are for illustrative purposes only, and will not limit the scope and significance of the present invention or its examples in any way. In addition, the present disclosure may repeatedly quote numerals and/or letters in different examples. These repetitions are for simplification and explanation, and do not specify the relationship between different embodiments and/or configurations in the following discussion.

Unless otherwise specified, the terms used in the entire specification and the scope of the patent application usually have the usual meaning of each term used in this field, in the content disclosed here, and in the special content. Some terms used to describe the present disclosure will be discussed below or elsewhere in this specification to provide those skilled in the art with additional guidance on the description of the present disclosure.

Regarding the "coupling" or "connection" used in this article, it can mean that two or more components directly make physical or electrical contact with each other, or make physical or electrical contact with each other indirectly, and "couple" or " "Connected" can also refer to the mutual operation or action of two or more elements. In this article, the terms first, second, third, etc. are used to describe various elements, components, regions, Layers and/or blocks are understandable. However, these elements, components, regions, layers and/or blocks should not be limited by these terms. These terms are only used to identify a single element, component, region, layer, and/or block. Therefore, in the following, a first element, component, region, layer and/or block may also be referred to as a second element, component, region, layer and/or block without departing from the intent of the present invention. As used herein, the term "and/or" includes any combination of one or more of the listed associated items.

Please refer to Figure 1. FIG. 1 is a schematic diagram of a human resource management system 100 according to some embodiments of the present disclosure. The human resource management system 100 includes a processing server 110, an internal data server 130, and an external data server 150. In terms of connection relationship, the processing server 110 is in communication connection with the internal data server 130, and the processing server 110 is in communication connection with the external data server 150.

The processing server 110 further includes an input/output module 112, a model building module 113, and a machine learning module 115. The model building module 113 and the machine learning module 115 are respectively coupled to the input/output module 112. The human resource management system 100 shown in FIG. 1 is only an example, and the content of the present disclosure is not limited thereto.

In operation, the internal data server 130 is used to store multiple data lists. The model establishment module 113 is used for establishing a plurality of analysis models corresponding to a specific position according to a plurality of data lists. The input/output module 112 is used to collect a plurality of first data groups from the external data server 150 and/or the internal data server 130. The machine learning module 115 is used for creating an analysis list based on a plurality of analysis models and a plurality of first data sets. I/O module 112 through communication The network 192 will output the analysis list.

For example, the internal data server 130 stores internal company employee data and historical recruiter data, and internal company employee data and historical applicant data are classified into different lists. Taking the recruitment of digital financial personnel as an example, the internal data server 130 stores a list of recruits and a list of unemployed recruits of digital financial personnel. The list of applicants for digital financial personnel includes the information of applicants who have been admitted after the application of digital financial personnel in the past years, and the list of unemployed applicants for digital financial personnel includes the information of applicants who have not been admitted after the application of digital financial personnel in the past years . Applicant's information includes background information, academic experience information, work experience information, and license information. The applicant information listed above is only for illustration, and this case is not limited to the above.

Next, the model establishment module 113 establishes an hiring analysis model corresponding to the digital financial personnel based on the hiring list of the digital financial personnel, and establishes an unemployed analysis model corresponding to the digital financial personnel based on the unemployed list. The analysis model contains multiple variables. For example, the hiring analysis model for digital financial personnel includes variable data such as the graduate department is a financial and commercial administration, the age is 28 to 30, and the license is a computer-related license. The unemployed analysis model of digital financial personnel includes variable data such as gender as male and work experience as non-financial-related work experience.

The input/output module 112 collects multiple data sets from the external data server 150 and/or the internal data server 130. For example, the I/O module 112 can collect multiple internal company employee data sets from the internal data server 130, and the I/O module 112 can also search from the external data server 150. A collection of resume data groups actively delivered by multiple job seekers. The company’s employee data group and the resume data group actively submitted by job applicants include background data, academic experience data, work experience data, and license data. The data sets listed above are only examples, and this case is not limited to the above. In some embodiments, the I/O module 112 collects the resume data group actively delivered by the job applicant from the external data server 150 via the communication network 190.

Then, the machine learning module 115 creates an analysis list based on the analysis model and the multiple data sets collected by the output and input module 112. In some embodiments, when the machine learning module 115 creates the analysis list, the machine learning module 115 is further used to calculate the relationship between each of the multiple data sets collected by the output input module 112 and the multiple analysis models. Multiple similarities, and build an analysis list based on multiple similarities. For example, suppose that the I/O module 112 collects the A data group by the internal data server 130, and the external data server 150 collects the B data group and the C data group. The machine learning module 115 respectively calculates the similarity between the A data group and the hirer analysis model of the digital financial personnel, the similarity between the A data group and the unemployed analysis model of the digital financial personnel, and the B data group and the digital finance The similarity between the hirer analysis models of the personnel, the similarity between the B data group and the unemployed analysis model of the digital financial personnel, the similarity between the C data group and the hirer analysis model of the digital financial personnel, C The similarity between the data set and the unemployed analysis model of digital financial personnel.

Assume that the similarity between the A data group and the C data group and the hiring analysis model of digital financial personnel is higher than the similarity threshold, and the similarity between the B data group and the unemployed analysis model of the digital financial personnel is higher than the similarity The degree threshold, the analysis list will contain information that the A data group and C data are more similar to the hirer analysis model, and the B data group and the unemployed analysis model are more similar.

Then, the input/output module 112 outputs the analysis list through the communication network 192. For example, the I/O module 112 outputs the analysis list to the user server 170 through the communication network 192. The human resources department can read the analysis list through the user server 170, and can filter out further interviews based on the information on the analysis list. Of applicants.

In some embodiments, the processing server 110 further includes a memory 118. The memory 118 is used to store the analysis model created by the model creation module 113.

In some embodiments, the processing server 110 further includes a message generating module 117. The message generating module 117 is used to generate notification messages, and respectively send the notification messages to the respective notification addresses of the multiple data groups on the analysis list via the input/output module 112. For example, suppose that in the analysis list, data group A and data group C are more similar to the analysis model of the recruiter, and data group A and data group C respectively include email notification addresses. The message generating module 117 generates a notification message including written test or face-to-face notification, and sends the notification message to the notification address of the email in the A data group and the notification address of the email in the C data group through the input and output module 112, To inform the applicants of the A data group and the C data group to participate in the written test or face-to-face interview.

In some embodiments, the processing server 110 further includes a data creation module 116. The data creation module 116 is used to set the respective parameter values of the multiple data groups on the analysis list, and according to the respective parameters of the multiple data groups Value, the multiple second data groups are classified into one of multiple data lists. For example, in the example presented above, suppose that the applicants in the A data group and the applicants in the C data group take the written test or interview after the admission result is the applicant of the A data group and the application of the C data group If it is not admitted, the data creation module 116 sets the parameter value of the A data group to be admitted and the parameter value of the C data group is not to be admitted. Then, the data creation module 116 classifies the A data group into the list of recruiters for digital financial personnel And classify the C data group into the unemployed list of digital financial personnel to build a talent pool. The model creation module 113 can recalculate and update the hirer analysis model and the un hired analysis model based on the updated list of hired persons and the list of un hired persons.

Please refer to Figure 2. FIG. 2 is a schematic diagram of a human resource management method 200 according to some embodiments of the present disclosure. The human resource management method 200 includes multiple steps S210, S230, S250, and S270.

In step S210, multiple analysis models corresponding to positions are established based on multiple data lists. In some embodiments, step S210 can be performed by the model building module 113 as shown in FIG. 1. For example, suppose that the internal data server 130 as shown in Figure 1 stores a list of network management personnel recruiting bank network management personnel over the years, a list of network management personnel recruited candidates, a list of network management personnel not recruited, and network management personnel List of leavers. The model building module 113 analyzes all the variables in the list of network management personnel over the years, the recruitment list of network management personnel, the non-recruitment list of network management personnel candidates, and the list of network management personnel leavers, including education, age, gender, address, seniority, and experience.

As mentioned above, after the hypothesis is analyzed, the model building module 113 Establish the competency analysis model, incompetence analysis model and potential resignation analysis model of network administrators. The eligibility analysis model includes information about male gender, with more than 3 years of work experience and registered in the Greater Taipei area. The incompetence analysis model includes information on gender, female, age under 30, and more than 5 financial licenses. The potential turnover analysis model includes information about ages 35 to 40, registered in New Taipei City, more than 3 years of work experience, and a master's degree.

In step S230, a plurality of first data groups are collected from the external database and/or the internal database. In some embodiments, step S230 may be performed by the input/output module 112 as shown in FIG. 1. For example, the I/O module 112 can collect multiple internal company employee data sets from the internal data server 130, and the I/O module 112 can also collect multiple resume data sets actively posted by job seekers from the external data server 150. . Assume that the I/O module 112 collects the A data group by the internal data server 130, and the external data server 150 collects the B data group and the C data group.

In step S250, an analysis list is created based on a plurality of analysis models and a plurality of first data sets. In some embodiments, step S250 can be performed by the machine learning module 115 as shown in FIG. 1. For example, the machine learning module 115 creates an analysis list based on the analysis model and a plurality of data sets collected by the input and output module 112. For example, the machine learning module 115 compares each of the suitability analysis model, the unfit analysis model, and the potential turnover analysis model with each of the A data group, the B data group, and the C data group collected by the output input module 112 According to the calculated similarity, the A data group, the B data group, and the C data group are classified as qualified, unsuitable, and potential leavers.

Assume that the similarity between the A data group and the competency analysis model is higher than the similarity threshold, the similarity between the B data group and the competence analysis model is higher than the similarity threshold, and the similarity between the C data group and the incompetent analysis model The degree is higher than the similarity threshold. The machine learning module 115 creates an analysis list. The analysis list contains information that the A data set and C data are relatively similar to the hirer analysis model, and the B data set and the unemployed analysis model are relatively similar information.

In step S270, the analysis list is output through the communication network. In some embodiments, step S270 can be performed by the input/output module 112 as shown in FIG. 1. For example, the I/O module 112 outputs the analysis list to the user server 170 via the communication network 192 for the human resources department to consult.

In some embodiments, the internal data server 130, the external data server 150, the processing server 110, and the user server 170 may be a central processing unit (CPU), a microprocessor (MCU), or a server. Or other arithmetic circuits or components with data access, data calculation, data storage, data transmission and reception, or similar functions. In some embodiments, the model building module 113, the machine learning module 115, the data building module 116, and the message generating module 117 may be circuits or components with data access, data calculation, data storage, or similar functions. In some embodiments, the input/output module 112 may be a circuit or element with data transmission and reception or similar functions.

As can be seen from the above-mentioned implementation of the present disclosure, the embodiments of the present disclosure provide a human resource management system and a human resource management method, and in particular, a human resource management system related to artificial intelligence. The system and human resource management methods can be used to efficiently and quickly find candidates suitable for the position through the system, so as to shorten the time and cost of screening and filtering by the human resources department, and establish a talent pool to provide other job matching and talent tracking.

Although the content of this disclosure has been disclosed in the above manner, it is not intended to limit the content of this disclosure. Anyone who is familiar with this technique can make various changes and modifications without departing from the spirit and scope of this disclosure. Therefore, this The scope of protection of the disclosed content shall be subject to the scope of the attached patent application.

100‧‧‧Human Resource Management System

130‧‧‧Internal Data Server

150‧‧‧External Data Server

190、192‧‧‧Communication network

110‧‧‧Processing server

112‧‧‧I/O Module

113‧‧‧Model Creation Module

115‧‧‧Machine Learning Module

116‧‧‧Data Creation Module

117‧‧‧Message Generation Module

118‧‧‧Memory

170‧‧‧User Server

Claims (6)

A human resource management system, including: an internal data server for storing a plurality of data lists; and a processing server, including: a model creation module for creating a position related to the data lists based on the data lists. Corresponding multiple analysis models, where the analysis models include an hiring analysis model, an unemployed analysis model, and a potential resignation analysis model; an input and output module for importing from an external data server and/or the The internal data server collects a plurality of first data sets; a machine learning module is used to create an analysis list based on the analysis models and the first data sets, and the machine learning module is used to calculate the A similarity between each of the first data group and each of the analysis models, and the analysis list is created based on the similarities; and a data creation module is used to set the analysis based on an admission result A parameter value of each of the first data sets is used to form a complex array of second data sets, and the second data sets are used to update the analysis models; wherein the input and output module is used for the analysis list through a communication network Output. The human resource management system according to claim 1, wherein the processing server further includes: a message generating module for generating a notification message and passing the input The output input module respectively sends the notification message to a notification address of each of the first data groups. The human resource management system according to claim 1, wherein the processing server further includes: a memory for storing the analysis models. A human resource management method, including: establishing a plurality of analysis models corresponding to a position based on a plurality of data lists, wherein the analysis models include an hirer analysis model, an unhired person analysis model, and a potential resignation analysis model; Collect a plurality of first data sets from an external database and/or an internal database; create an analysis list based on the analysis models and the first data sets, wherein based on the analysis models and the first data sets , The establishment of the analysis list further includes: calculating a similarity between each of the first data sets and each of the analysis models; and establishing the analysis list according to the similarities; according to an admission result To set a parameter value of each of the first data sets to form a complex array of second data sets; use the second data sets to update the analysis models; and output the analysis list through a communication network. The human resource management method as described in claim 4, wherein The human resource management method further includes: generating a notification message; and respectively sending the notification message to a notification address of each of the first data groups. The human resource management method described in claim 4 further includes: storing the analysis models.

Images