CN114764474A - Efficient and accurate internal post recommendation flow system - Google Patents
Efficient and accurate internal post recommendation flow system Download PDFInfo
- Publication number
- CN114764474A CN114764474A CN202110046838.4A CN202110046838A CN114764474A CN 114764474 A CN114764474 A CN 114764474A CN 202110046838 A CN202110046838 A CN 202110046838A CN 114764474 A CN114764474 A CN 114764474A
- Authority
- CN
- China
- Prior art keywords
- post
- qbs
- company
- information
- efficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/107—Computer-aided management of electronic mailing [e-mailing]
Abstract
The invention provides an efficient and accurate internal post recommendation process system. The efficient and accurate internal post recommendation flow system comprises the following steps: s1: establishing a customized QBSAI model, and constructing artificial intelligence data modeling suitable for a company by inputting two parameters of a typical post description and a post level list of each post type of the company; s2: positions are recommended through the QBSAI model which is constructed. According to the efficient and accurate internal post recommendation process system provided by the invention, the QBS analyzes and understands each post description and analyzes and extracts post information characteristics, so that effective classification of post information is realized, the accuracy is higher and the system is more reliable, and the QBS divides a list and current post information of employees by utilizing the function information of internal human resources of a company, so that the problem that a resume is unavailable due to unwilling to upload and unwilling to update, personal information sensitivity and the like is caused and the like is solved.
Description
Technical Field
The invention relates to the field of post recommendation, in particular to an efficient and accurate internal post recommendation flow system.
Background
How to intelligently match job seeker information and recruitment post information and recommend a proper post to a potential job seeker is always a problem concerned by a recruitment enterprise, job seekers, hunting and job hunting website, and the solution generally mainly comprises two types: the first scheme is as follows: and searching resume information of job seekers by using the keywords or searching the keywords of the full text of the recruitment post, and finally finding the post matched with the job post through manual matching and screening. And then, performing position recommendation, wherein the scheme II comprises the following steps: the job seeker tags own skills, on the other hand, the company issuing the post tags key skills or work experience of the recruited post, and intelligent and accurate post recommendation is finally achieved through system or artificial intelligence matching.
Firstly, in the process of matching the posts, the technical scheme must involve manual intervention, and the human intervention of the scheme one mainly refers to that a person analyzes whether the job seeker is matched with the post; according to the second scheme, post information or job seeker information needs to be labeled manually, so that information classification is carried out; secondly, for internal recruitment, because of the information sensitivity of the resume, the willingness of internal staff to upload the resume and prepare the resume is low, and therefore if the resume information does not exist, the system cannot acquire the skill characteristics of job seekers to recommend positions; thirdly, the willingness of the job seeker to upload or update the resume is low, so that the pushed post information is not suitable for the job seeker due to the fact that the matched data source is missing or inaccurate.
In the prior art, when the number of job positions to be recruited is large or changes all the time, manual intervention is much, much time is needed, each post must be labeled manually, intelligent automation is not realized, in addition, resume information analysis of staff is needed to determine the post suitable for recommendation, which relates to the problem of personal information leakage, and thirdly, for most potential job seekers, no habit of uploading resumes or updating resumes exists, which results in inaccurate data sources for information matching. The problem that the accuracy of the final recommended position is low is that different keywords can appear in the position description and the job seeker working experience, but the keywords are not used for describing the position or the job seeker per se and only assist in describing information, and therefore the accuracy of the recommendation is necessarily low. Third, for most potential job seekers, there is no habit of uploading or updating resumes, which results in inaccurate data sources for information matching. And finally, the accuracy rate of the recommended positions is low.
Therefore, it is necessary to provide an efficient and accurate internal position recommendation process system to solve the above technical problems.
Disclosure of Invention
The invention provides an efficient and accurate internal post recommendation flow system, which solves the problems that job description information classification is carried out manually, so that the workload of a recruitment department is large, a job seeker cannot accurately classify self resume information, label classification information is updated unwillingly or untimely, so that real job hunting skills cannot be matched for post push, keyword search and matching result in low matching accuracy, and job seeker resume lacks or data is not updated, so that data source information is unreliable.
In order to solve the technical problem, the efficient and accurate internal post recommendation flow system provided by the invention comprises the following steps:
s1: establishing a customized QBS AI model, and constructing artificial intelligence data modeling suitable for a company by inputting two parameters of a typical post description and a post level list of each post type of the company;
s2: recommending positions through the established QBS AI model;
the S2 comprises S21, S22, S23, S24 and S25, the S21 is used for acquiring post information, the S22 is used for acquiring employee information, the S23 is used for matching employees and post functions and sending mails, the S24 is used for a manpower resource team, and the S25 is used for the employees to view contents in recommended mails.
Preferably, the S21 obtains the post information as a post description, which mainly includes a function name, a post level, a post description, and a post requirement, by the QBS reading the post details of the recruited post in the designated folder, and then semantically understands the post description through the created QBS AI model; and outputting the function name of the recruiting position.
Preferably, the step S22 acquires the employee information as QBS, and acquires and outputs the current job name, the post level, and the post name of the employee by connecting to an employee authentication system inside the company.
Preferably, the S23 matches the employee and the post function and sends a mail to the QBS system, matches the post and the employee' S function name, recommends the post belonging to the same function category and having a higher rank than the current employee to the employee according to the post hierarchy list inside the company, and sends the post in the form of a mail.
Preferably, the colleagues using the QBS system as the human resources by the S24 can log in the QBS system through their internal employee numbers and passwords, and in the form of a browser, including logging in the QBS system, management by a QBS subscriber, adding position information, setting the QBS system, viewing position recommendation history records, and record query.
Preferably, the staff of S25 checks the content in the recommendation mail, and the staff clicks the position code in the recommendation mail and transfers the position code to a detail page on an internal recruitment website of the position, or the staff clicks a cancel subscription button at the bottom of the system to cancel receiving the position recommendation mail.
Preferably, in the S1 creating a customized QBS AI model, the QBS model performs unsupervised learning on the input post descriptions according to the input post characteristics of each typical post description and the post hierarchy list of the company, and then autonomously creates a set of rules for data classification, the rules mainly depend on a TF-IDF algorithm, but the algorithm is optimized by QBS, so that an artificial intelligence data modeling suitable for the company can be directly created by reading the typical post descriptions and the post hierarchy list of the company, the accuracy can be up to 70%, and the finally created QBS AI data modeling can be divided according to the typical post characteristics of each company, and for what new input post description, the post belongs to which category in the post hierarchy list of the company can be accurately divided.
Compared with the related art, the efficient and accurate internal post recommendation process system provided by the invention has the following beneficial effects:
1. the QBS system automatically carries out full-text semantic understanding on the recruitment post by an intelligent system, analyzes post information characteristic extraction, realizes effective classification of post information, saves time and energy of a recruitment department in information classification, simultaneously makes up for insufficient experience of some newly-entered recruitment departments in recruitment post classification, and ensures that classification standards and quality of all posts are highly consistent and controllable.
2. The QBS analyzes and extracts the post information characteristics by performing semantic analysis and understanding on each post description, realizes effective classification of the post information, and has higher accuracy and more reliability.
3. The QBS utilizes the function information of the internal human resources of the company to divide the list and the current position information of the staff, and effectively solves the problem that the resume is unavailable due to the reasons that the resume is unwilling to upload and update, and the personal information is sensitive and cannot be used.
4. Through the QBS system, the number, frequency and information receivers sending push positions at each time can be easily customized in a company according to requirements so as to meet the requirement of flowing of internal posts.
5. The QBS system can ensure that all potential job seekers can be brought into the audience range of the flowing of the posts through accurately pushing the post information without any input of internal staff, and on the other hand, the workload of staff spending on resume preparation and updating is saved, and third, the recommended post information is related to the staff, so that the effective transmission of the information is realized, and the success rate of post pushing is greatly improved.
6. The method has the advantages that complicated butt joint and expansion of other internal systems are not involved, only the functions of the employees are inquired from the internal employee systems, whether the employees are still in the positions or not and the position level contents are needed, the typical position description data and the position hierarchy list of each position are used for establishing an AI model, the position details are put into a specified folder, the matching of the internal posts of the whole company can be completed, and the effect of position recommendation is carried out according to the functions of the employees, so that the method has strong universality and flexibility.
Drawings
Fig. 1 is a schematic diagram of an efficient and accurate internal station recommendation flow system provided by the present invention.
Detailed Description
The invention is further described with reference to the following figures and embodiments.
Please refer to fig. 1 in combination, wherein fig. 1 is a schematic diagram of an efficient and accurate internal post recommendation process system provided by the present invention. An efficient and accurate internal post recommendation flow system comprises the following steps:
s1: establishing a customized QBS AI model, and constructing artificial intelligence data modeling suitable for a company by inputting two parameters of a typical post description and a post level list of each post type of the company;
s2: recommending positions through the constructed QBS AI model;
the S2 comprises S21, S22, S23, S24 and S25, the S21 is used for acquiring post information, the S22 is used for acquiring employee information, the S23 is used for matching employees and post functions and sending mails, the S24 is used for a manpower resource team, and the S25 is used for the employees to view contents in recommended mails.
Preferably, the S21 obtains the post information as a post description, which mainly includes a function name, a post level, a post description, and a post requirement, by the QBS reading the post details of the recruited post in the designated folder, and then semantically understands the post description through the created QBS AI model; and outputting the function name of the recruiting position.
The step S22 of obtaining employee information is that the QBS obtains and outputs the current function name, the post level, and the post name of the employee by connecting with an employee authentication system (or other systems storing employee function information) inside the company.
And the step S23 matches the employees with the functions of the posts and sends a mail to the QBS system for matching according to the names of the posts and the employees, recommends posts which belong to the same function category and are at the same level or higher than the current level of the employees to the employees according to a post level list in the company, and sends the posts in a mail mode.
The colleagues using the QBS system as the human resources by the S24 can log in the QBS system through the internal employee numbers and passwords of the colleagues and use the browser mode, wherein the colleagues include logging in the QBS system, management of QBS subscribers, position information increase, setting of the QBS system, viewing of position recommendation history records and record inquiry, and the management of the QBS subscribers includes a list of newly added subscribers, cancelled subscribers and current subscribers.
And the S25 staff checks the content in the recommended mails, namely the staff clicks the position codes in the recommended mails and transfers the position codes to a detail page on an internal recruitment website of the position, or the staff clicks a cancel subscription button at the bottom of the system to cancel the reception of the position recommended mails.
In the S1, a customized QBS AI model is created, the QBS model can perform unsupervised learning on the input post description according to the input post characteristics of each typical post description and a post level list of a company, then a set of rules for data classification is automatically created, the rules mainly depend on a TF-IDF algorithm, but the algorithm is optimized through QBS, artificial intelligent data modeling suitable for the company can be directly created by reading the typical post description and the post level list of the company, the accuracy can be over 70 percent, the finally created QBS AI data modeling can respect the typical post characteristics of each company for division, and the newly input post description can accurately divide which category the post belongs to the post level list of the company.
Compared with the related art, the efficient and accurate internal post recommendation process system provided by the invention has the following beneficial effects:
1. the QBS system automatically carries out full-text semantic understanding on the recruitment posts by an intelligent system, analyzes post information characteristic extraction, realizes effective classification of post information, saves time and energy of recruitment departments in information classification, simultaneously makes up for insufficient experience of some newly-entered recruitment departments in recruitment post classification, and ensures that classification standards and quality of all posts are highly consistent and controllable.
2. The QBS analyzes and extracts the post information characteristics by performing semantic analysis and understanding on each post description, realizes effective classification of the post information, and has higher accuracy and more reliability.
3. The QBS utilizes the function information of the internal human resources of the company to divide the list and the current position information of the staff, and effectively solves the problem that the resume is unavailable due to the reasons that the resume is unwilling to upload and update, and the personal information is sensitive and cannot be used.
4. Through QBS system, the company can easily customize the quantity, frequency and information receiver of sending the propelling movement position each time according to the demand to satisfy the mobile demand of inside post.
5. The QBS system can ensure that all potential job seekers can be brought into the audience range of the flowing of the posts through accurately pushing the post information without any input of internal staff, and on the other hand, the workload of staff spending on resume preparation and updating is saved, and third, the recommended post information is related to the staff, so that the effective transmission of the information is realized, and the success rate of post pushing is greatly improved.
6. The method has the advantages that the complicated butt joint and expansion of other internal systems are not involved, only the functions of the staff are required to be inquired from the internal staff system, whether the staff is still in position or not, the position level content is required, the typical position description data and the position hierarchy list of each position are used for establishing an AI model, the position details are put into a specified folder, the internal post matching of the whole company can be completed, and the position recommendation effect is realized according to the functions of the staff, so that the method has strong universality and flexibility.
The above description is only an embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are included in the scope of the present invention.
Claims (7)
1. An efficient and accurate internal post recommendation flow system is characterized by comprising the following steps:
s1: establishing a customized QBS AI model, and constructing artificial intelligence data modeling suitable for a company by inputting two parameters of a typical post description and a post level list of each post type of the company;
s2: recommending positions through the established QBS AI model;
the S2 comprises S21, S22, S23, S24 and S25, the S21 is used for acquiring post information, the S22 is used for acquiring employee information, the S23 is used for matching employees and post functions and sending mails, the S24 is used for a manpower resource team, and the S25 is used for the employees to view contents in recommended mails.
2. The efficient and accurate internal post recommendation process system according to claim 1, wherein said S21 obtains post information for QBS by reading post details of a recruited post in a designated folder, mainly including a function name, a post level, a post description, a post requirement, and then semantically understanding the post description through the created QBS AI model; and outputting the function name of the recruiting position.
3. The efficient and accurate internal post recommendation process system according to claim 1, wherein the S22 obtains employee information as QBS, and obtains and outputs current job title, post level and post name of the employee by connecting with an internal employee authentication system of the company.
4. The efficient and accurate internal post recommendation process system according to claim 1, wherein the S23 matches employees and post functions and sends mails to QBS system to match the post and employee function names, according to the internal post hierarchy list of the company, posts belonging to the same function category and having higher level than the current employee are recommended to the employee and sent by mail.
5. The efficient and accurate internal post recommendation process system according to claim 1, wherein the S24 staff members using the QBS system for human resources can log in the QBS system through their internal employee numbers and passwords and go through a browser format, including logging in the QBS system, QBS subscriber management, adding position information, setting the QBS system, viewing post recommendation history and record query.
6. The efficient and accurate internal post recommendation process system according to claim 1, wherein the S25 employee checks the content in the recommendation mail to find the job code in the recommendation mail clicked by the employee and transfers to the detail page of the internal recruitment website of the job, or the employee clicks a cancel subscription button at the bottom of the system to cancel the reception of the job recommendation mail.
7. An efficient and accurate internal position recommendation process system according to claim 1, the S1 creates a customized QBS AI model that will be based on the job characteristics of each of the input representative job descriptions, and the company' S job hierarchy list, unsupervised learning is carried out on the input post description, then a set of data classification rules is automatically established, the rules are mainly based on TF-IDF algorithm, but the algorithm is optimized by QBS, artificial intelligence data modeling suitable for companies can be directly established by reading the typical position description and the position hierarchy list of the company, the accuracy can be more than 70 percent, the finally established QBS AI data modeling can respect the typical position characteristics of each company for division, for the description of what newly entered position, it is possible to accurately classify which category in the hierarchical list of positions of the company the position belongs to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046838.4A CN114764474A (en) | 2021-01-14 | 2021-01-14 | Efficient and accurate internal post recommendation flow system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110046838.4A CN114764474A (en) | 2021-01-14 | 2021-01-14 | Efficient and accurate internal post recommendation flow system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114764474A true CN114764474A (en) | 2022-07-19 |
Family
ID=82362848
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110046838.4A Pending CN114764474A (en) | 2021-01-14 | 2021-01-14 | Efficient and accurate internal post recommendation flow system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114764474A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115526590A (en) * | 2022-09-16 | 2022-12-27 | 深圳今日人才信息科技有限公司 | Efficient human-sentry matching and re-pushing method combining expert knowledge and algorithm |
| CN116595973A (en) * | 2023-05-19 | 2023-08-15 | 广东职教桥数据科技有限公司 | Post function identification method based on natural language processing classification technology |
-
2021
- 2021-01-14 CN CN202110046838.4A patent/CN114764474A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115526590A (en) * | 2022-09-16 | 2022-12-27 | 深圳今日人才信息科技有限公司 | Efficient human-sentry matching and re-pushing method combining expert knowledge and algorithm |
| CN115526590B (en) * | 2022-09-16 | 2023-08-04 | 深圳今日人才信息科技有限公司 | Efficient person post matching and re-pushing method combining expert knowledge and algorithm |
| CN116595973A (en) * | 2023-05-19 | 2023-08-15 | 广东职教桥数据科技有限公司 | Post function identification method based on natural language processing classification technology |
| CN116595973B (en) * | 2023-05-19 | 2023-10-03 | 广东职教桥数据科技有限公司 | Post function identification method based on natural language processing classification technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210209109A1 (en) | Method, apparatus, device, and storage medium for intention recommendation | |
| US11068663B2 (en) | Session embeddings for summarizing activity | |
| US20190384861A1 (en) | Real-time graph traversals for network-based recommendations | |
| US11544308B2 (en) | Semantic matching of search terms to results | |
| CN106682150B (en) | Information processing method and device | |
| US20140214711A1 (en) | Intelligent job recruitment system and method | |
| CN104834668A (en) | Position recommendation system based on knowledge base | |
| CN114764474A (en) | Efficient and accurate internal post recommendation flow system | |
| US20140089303A1 (en) | Method and system for identifying job candidates | |
| US10305829B2 (en) | Database systems and methods for integrating data items collected from multiple data sources | |
| US20200151647A1 (en) | Recommending jobs based on title transition embeddings | |
| US20190197483A1 (en) | Large-scale aggregation and verification of location data | |
| CA2305344A1 (en) | On-line recruiting system with improved candidate and position profiling | |
| US11799819B2 (en) | Enhancing online contents based on digital alliance data | |
| US20030204436A1 (en) | Survey data gathering | |
| US11080272B2 (en) | Entity resolution techniques for matching entity records from different data sources | |
| CN100485688C (en) | Method for structural information issue and search at network environment | |
| Montoya et al. | A knowledge base for personal information management | |
| CN109460467B (en) | Method for constructing network information classification system | |
| US20200186487A1 (en) | Recommending communication paths to connect with new contacts based on digital alliance data | |
| CN113204644B (en) | Government affair encyclopedia construction method based on knowledge graph | |
| Antonova et al. | Review of technology solutions for knowledge management | |
| US11308426B2 (en) | Sequence modeling for searches | |
| KR102058960B1 (en) | Method and apparatus for collecting user data | |
| US20200210499A1 (en) | Automatically linking pages in a website |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xu Kaiyong Inventor after: Huang Yanfen Inventor after: Song Yaohua Inventor after: Zhang Jihe Inventor after: Du Tiao Inventor after: Zhang Yifan Inventor before: Xu Kaibing Inventor before: Huang Yanfen Inventor before: Song Yaohua Inventor before: Zhang Jihe Inventor before: Du Tiao Inventor before: Zhang Yifan |
|
| CB03 | Change of inventor or designer information |