TW202143122A - Resume scoring method and system wherein the resume scoring system includes a plurality of regular expressions, a vector generation model, and a scoring model - Google Patents
Resume scoring method and system wherein the resume scoring system includes a plurality of regular expressions, a vector generation model, and a scoring model Download PDFInfo
- Publication number
- TW202143122A TW202143122A TW109114559A TW109114559A TW202143122A TW 202143122 A TW202143122 A TW 202143122A TW 109114559 A TW109114559 A TW 109114559A TW 109114559 A TW109114559 A TW 109114559A TW 202143122 A TW202143122 A TW 202143122A
- Authority
- TW
- Taiwan
- Prior art keywords
- history
- model
- content
- training
- resume
- Prior art date
Links
Images
Landscapes
- Supplying Of Containers To The Packaging Station (AREA)
- Manufacturing Of Electric Cables (AREA)
- Controls For Constant Speed Travelling (AREA)
- Machine Translation (AREA)
Abstract
Description
本發明是有關於一種辦公室自動化方法,特別是指一種根據履歷自動產生評分的方法。The present invention relates to an office automation method, in particular to a method for automatically generating scores based on resumes.
在現今社會中,一般企業進行徵才作業時,第一關多會以求職者所提供的履歷作為依據進行篩選,然而對於徵才企業而言,當收到數以萬計的履歷時,多是由人資部門逐一審核每份履歷內容以篩選適合的求職者,此一作法不僅勞心勞力,同時亦有可能由於各人見解不同或是人為疏失,造成履歷誤篩選的問題。In today's society, when general companies conduct job recruitment, the first pass will be based on the resume provided by job applicants. However, for talent recruitment companies, when they receive tens of thousands of resumes, they often The human resources department reviews the content of each resume one by one to select suitable job applicants. This method is not only laborious, but also may cause the problem of erroneous selection of resumes due to different opinions or human errors.
有鑑於此,勢必需要提出一種全新解決方案,以解決目前審核履歷過度耗費時間人力成本以及容易產生履歷誤篩選的問題。In view of this, it is bound to be necessary to propose a new solution to solve the current problems of excessive time-consuming and labor-intensive review of resumes and the possibility of misselection of resumes.
因此,本發明的目的,即在提供一種協助評估履歷的履歷評分方法Therefore, the purpose of the present invention is to provide a resume scoring method that assists in evaluating resumes.
另外,本發明的另一目的,在於提供一種協助評估履歷的履歷評分系統。In addition, another object of the present invention is to provide a history scoring system that assists in evaluating history.
於是,本發明履歷評分方法,由一伺服端實施,該履歷包含一求職者填寫的一學經歷內容,及一個人介紹的自傳內容,該伺服端包含多個正規表示式、一向量生成模型,及一評分模型,該每一正規表示式具有一預定關鍵字,該向量生成模型用以根據一由文字構成的內容產生一文本向量,該評分模型依據該正規表示式產生的結果和該向量生成模型產生的文本向量產生一分數,該履歷評分方法包含一步驟(A)、一步驟(B),及一步驟(C)。Therefore, the resume scoring method of the present invention is implemented by a server. The resume includes a content of academic experience filled in by a job applicant and an autobiographical content introduced by a person. The server includes multiple formal expressions, a vector generation model, and A scoring model, each of the regular expressions has a predetermined keyword, the vector generation model is used to generate a text vector based on a content composed of words, the scoring model is based on the result of the regular expression and the vector generation model The generated text vector generates a score. The resume scoring method includes one step (A), one step (B), and one step (C).
在該步驟(A)中,當該伺服端接收到該相關於該求職者的履歷時,對於每一正規表示式,該伺服端根據該學經歷內容利用該正規表示式獲得該學經歷內容中對應於該正規表示式之預定關鍵字的關鍵字內容,其中每一正規表示式之預定關鍵字及其對應的關鍵字內容構成一對應的關鍵字組合。In this step (A), when the server receives the resume related to the job applicant, for each formal expression, the server uses the formal expression to obtain the content of the academic experience according to the content of the academic experience The keyword content corresponding to the predetermined keyword of the regular expression, wherein the predetermined keyword of each regular expression and its corresponding keyword content constitute a corresponding keyword combination.
在該步驟(B)中,該伺服端根據該自傳內容,利用該向量生成模型產生一對應該自傳內容的文本向量。In this step (B), the server uses the vector generation model to generate a text vector corresponding to the autobiographical content based on the autobiographical content.
在該步驟(C)中,該伺服端根據每一關鍵字組合及該文本向量,利用該評分模型產生一對應該履歷的分數。In this step (C), the server uses the scoring model to generate a score corresponding to the history according to each keyword combination and the text vector.
再者,本發明履歷評分系統,用以對一履歷產生評分,並經由一通訊網路連接一管理端,該履歷包含一求職者填寫的一學經歷內容,及一個人介紹的自傳內容,該履歷評分系統包含一通訊模組、一儲存模組,及一處理模組。Furthermore, the resume scoring system of the present invention is used to generate a score on a resume and connect it to a management terminal via a communication network. The resume includes the content of an academic experience filled in by a job applicant and the autobiographical content introduced by a person. The system includes a communication module, a storage module, and a processing module.
該通訊模組連接至該通訊網路,該儲存模組儲存有多個正規表示式、一向量生成模型,及一評分模型,該每一正規表示式具有一預定關鍵字,該向量生成模型用以根據一由文字構成的內容產生一文本向量,該評分模型依據該正規表示式產生的結果和該向量生成模型產生的文本向量產生一分數。The communication module is connected to the communication network, the storage module stores a plurality of normal expressions, a vector generation model, and a scoring model, each of the normal expressions has a predetermined keyword, and the vector generation model is used for A text vector is generated based on a content composed of words, and the scoring model generates a score based on the result of the regular expression and the text vector generated by the vector generation model.
該處理模組電連接該通訊模組及該儲存模組,其中,當該處理模組透過該通訊模組接收到來自該管理端且該相關於該求職者的履歷時,對於每一正規表示式,該處理模組根據該學經歷內容,利用該正規表示式獲得該學經歷內容中對應於該正規表示式之預定關鍵字的關鍵字內容,其中每一正規表示式之預定關鍵字及其對應的關鍵字內容構成一對應的關鍵字組合,並根據該自傳內容,利用該向量生成模型產生一對應該自傳內容的文本向量,以及根據每一關鍵字組合及該文本向量,利用該評分模型產生一對應該履歷的分數。The processing module is electrically connected to the communication module and the storage module, wherein, when the processing module receives the resume related to the job applicant from the management terminal through the communication module, for each regular expression According to the content of the learning experience, the processing module uses the formal expression to obtain the keyword content corresponding to the predetermined keyword of the formal expression in the learning experience content, wherein the predetermined keyword of each formal expression and its The corresponding keyword content constitutes a corresponding keyword combination, and according to the autobiographical content, the vector generation model is used to generate a text vector corresponding to the autobiographical content, and the scoring model is used according to each keyword combination and the text vector Generate a score corresponding to the resume.
本發明的功效在於:藉由該伺服端產生對應該履歷的分數,相關工作人員可參考分數篩選求職者,不僅節省審核每份履歷的時間人力成本,同時避免人為因素所導致的履歷誤篩選問題。The effect of the present invention is that the server generates scores corresponding to the resumes, and the relevant staff can refer to the scores to screen job applicants, which not only saves the time and labor cost of reviewing each resume, but also avoids the problem of misselecting resumes caused by human factors. .
在本發明被詳細描述之前,應當注意在以下的說明內容中,類似的元件是以相同的編號來表示。Before the present invention is described in detail, it should be noted that in the following description, similar elements are denoted by the same numbers.
參閱圖1,本發明履歷評分系統的一第一實施例,由一伺服端1來實施,該伺服端1透過一通訊網路100連接至一管理端2,並包含一通訊模組11、一儲存模組12,及一處理模組13。Referring to FIG. 1, a first embodiment of the history scoring system of the present invention is implemented by a
該通訊模組11透過該通訊網路100連接至該管理端2。The communication module 11 is connected to the
該儲存模組12儲存有多個正規表示式、多筆歷史履歷、一向量生成模型,及一評分模型,該每一正規表示式具有一預定關鍵字,該每一歷史履歷具有一相關於一歷史求職者個人介紹的自傳內容、多筆相關於該歷史求職者學經歷的關鍵字組合、一相關於該自傳內容的文本向量,及一相關於該歷史履歷的分數,該向量生成模型用以根據一由文字構成的內容產生一文本向量,該評分模型依據該正規表示式產生的結果和該向量生成模型產生的文本向量產生一分數。The
該處理模組13電連接該通訊模組11及該儲存模組12,並根據一相關於一求職者的履歷產生一對應該履歷的分數,其中該履歷包含該求職者填寫的一學經歷內容,及一相關於該求職者個人介紹的自傳內容。The
參閱圖2、圖3,及圖4,本發明履歷評分方法,包含一向量生成模型訓練程序、一評分模型訓練程序,及一評分程序。Referring to FIG. 2, FIG. 3, and FIG. 4, the history scoring method of the present invention includes a vector generation model training program, a scoring model training program, and a scoring program.
參閱圖2,該向量生成模型訓練程序包含一步驟301、一步驟302、一步驟303、一步驟304,及一步驟305,並說明該處理模組13如何根據該等歷史履歷調整精進該向量生成模型。Referring to Figure 2, the vector generation model training program includes a
在該步驟301中,該處理模組13根據該等歷史履歷的自傳內容及文本向量,利用一深度學習演算法,建立一用以根據一由文字構成的內容產生一文本向量的第二訓練模型,例如BERT或XLNet等訓練模型。In
在該步驟302中,該處理模組13根據每一歷史履歷所對應的自傳內容,利用該第二訓練模型產生分別對應每一歷史履歷的多個訓練文本向量。In this
在該步驟303中,對於每一歷史履歷,該處理模組13判斷對應該歷史履歷的該文本向量及該訓練文本向量的相似度是否大於一預設閥值。在該第一實施例中,該處理模組13根據一相似度比對演算法,例如餘弦相似度(cosine similarity),獲得該歷史履歷的該文本向量及該訓練文本向量之間的相似度。當該處理模組13判斷相似度並未大於該預設閥值時,該處理模組13調整該第二訓練模型並重新進行該步驟302,亦即該步驟304,當該處理模組13判斷相似度大於該預設閥值時,該處理模組13將該第二訓練模型作為用以根據一由文字構成的內容產生一文本向量的該向量生成模型,亦即該步驟305。In
參閱圖3,該評分模型訓練程序包含一步驟401、一步驟402、一步驟403、一步驟404,及一步驟405,並說明該處理模組13如何根據該等歷史履歷調整精進該評分模型。Referring to FIG. 3, the scoring model training procedure includes a
在該步驟401中,該處理模組13將所儲存的多筆歷史履歷區分為一訓練子集及一測試子集,其中該訓練子集中所包括的該等歷史履歷與該測試子集中所包括的該等歷史履歷,其數量可以相等亦可以有所差別。In
在該步驟402中,該處理模組13根據該訓練子集中每一歷史履歷所對應的該關鍵字組合、該文本向量,及該分數,利用一機器學習演算法,例如邏輯斯迴歸(Logistic Regression)、隨機森林(Random Forest)、梯度提升技術(Gradient Boosting)、人工神經網路(Artificial Neural Network)等等,建立一根據該等關鍵字組合及該文本向量產生一訓練分數的第一訓練模型。In
在該步驟403中,該處理模組13根據該訓練子集及該測試子集中每一歷史履歷所對應的該關鍵字組合、該文本向量,及該分數,判斷該第一訓練模型是否過度擬合或擬合不足,當判斷該第一訓練模型過度擬合或擬合不足時,該處理模組13調整該第一訓練模型並重新判斷調整後的該第一訓練模型是否過度擬合或擬合不足,亦即該步驟404,當判斷該第一訓練模型並未過度擬合及擬合不足時,該處理模組13將該第一訓練模型作為依據該正規表示式產生的結果和該向量生成模型產生的文本向量產生一分數的該評分模型,亦即該步驟405。In
參閱圖4,該評分程序包含一步驟501、一步驟502、一步驟503,及一步驟504,並說明該處理模組13如何根據該履歷產生對應該履歷的該分數。Referring to FIG. 4, the scoring procedure includes a
在該步驟501中,當該處理模組13透過該通訊模組11接收到該來自該管理端2且相關於該求職者的該履歷時,對於每一正規表示式,該處理模組13根據該履歷的該學經歷內容利用該正規表示式獲得該學經歷內容中對應於該正規表示式之預定關鍵字的關鍵字內容,其中每一正規表示式之預定關鍵字及其對應的關鍵字內容構成一對應的關鍵字組合。在該第一實施例中,該等正規表示式之預定關鍵字分別為「最高學歷」、「工作經歷」、「英文能力」,則該處理模組13根據該等正規表示式所獲得的關鍵字內容分別對應為「成功大學電機系碩士」、「台積電研發部門3年」、「多益測驗870分」,而「最高學歷:成功大學電機系碩士」為一對應「最高學歷」的關鍵字組合,類似地,對應「工作經歷」、「英文能力」的關鍵字組合分別為「工作經歷:台積電研發部門3年」、「英文能力:多益測驗870分」。In
在該步驟502中,該處理模組13根據該履歷的該自傳內容,利用該向量生成模型產生一對應該自傳內容的文本向量。值得一提的是,該向量生成模型可為該步驟305所確認的該向量生成模型。In
在該步驟503中,該處理模組13根據每一關鍵字組合及該文本向量,利用該評分模型產生一對應該履歷的分數。值得一提的是,該評分模型可為該步驟405所確認的該評分模型。In
在該步驟504中,該處理模組13儲存該履歷的該自傳內容、每一關鍵字組合、該文本向量,及該分數為該等歷史履歷之其中一者。藉此,可累積該等歷史履歷之數量,以使該評分模型及該向量生成模型之訓練樣本更多元,藉由持續追蹤及調整訓練和測試樣本來精進所獲得之該評分模型及該向量生成模型。In the
參閱圖5,本發明履歷評分方法的一第二實施例類似於該第一實施例,其相同之處不再贅述,其相異之處在於,在該第二實施例中,該儲存模組12還儲存有一用以根據一由文字構成的內容產生一摘要的摘要生成模型,而該儲存模組12所儲存的該每一歷史履歷還具有一相關於所對應之歷史履歷的該自傳內容的摘要,而在該步驟504前還包含一摘要程序,說明該處理模組13如何根據該履歷的自傳內容,產生一對應該履歷之自傳內容的摘要,並包括一步驟601、一步驟602、一步驟603、一步驟604、一步驟605、及一步驟606。Referring to FIG. 5, a second embodiment of the resume scoring method of the present invention is similar to the first embodiment, and the similarities are not repeated here. The difference is that in the second embodiment, the
在該步驟601中,該處理模組13根據該等歷史履歷的該等自傳內容及該等摘要,利用一深度學習演算法,例如遞迴神經網路,建立一根據一由文字構成的內容產生一摘要的訓練模型,例如GPT-2或Transformer等模型。In this
在該步驟602中,該處理模組13根據每一歷史履歷所對應的自傳內容,利用該訓練模型產生分別對應每一歷史履歷的多個訓練摘要。In
在該步驟603中,對於每一歷史履歷,該處理模組13判斷對應該歷史履歷的該摘要及該訓練摘要的相似度是否大於另一預設閥值。在本實施例中,該處理模組13利用一相似度比對演算法,例如餘弦相似度(cosine similarity),獲得該歷史履歷的該摘要及該訓練摘要之間的相似度。當判斷相似度並未大於該另一預設閥值時,該處理模組13調整該訓練模型並重新進行該步驟602,亦即該步驟604,當判斷相似度大於該另一預設閥值時,該處理模組13確定該訓練模型為一用以根據一由文字構成的內容產生一摘要的摘要生成模型,亦即該步驟605。In this
在該步驟606中,當該處理模組13透過該通訊模組11接收到該來自該管理端2且相關於該求職者的履歷時,該處理模組13根據該履歷的該自傳內容,利用該摘要生成模型產生一對應該自傳內容的摘要。In
此外,在該第二實施例中,在該步驟504中,該處理模組13儲存該履歷的該自傳內容、每一關鍵字組合、該文本向量、該分數,及該摘要為該等歷史履歷之其中一者。In addition, in the second embodiment, in the
綜上所述,本發明履歷評分方法,藉由該處理模組13根據該等正規表示式、該向量生成模型,及該評分模型產生一對應該履歷的分數,藉此,能夠節省相關工作人員對於每一履歷進行評估篩選的時間人力成本,同時由於統一藉由該處理模組根據該評分模型產生該分數,一併避免了由於各人見解相異或是人為失誤所造成的問題,例如履歷誤篩選或是誤評分,此外,藉由該處理模組13根據該摘要生成模型產生一對應該自傳內容的摘要,藉此,當審核履歷者對於某些分數的履歷感到興趣時,可透過該摘要迅速地更進一步了解該求職者,進而節省閱讀整份履歷所花費的時間人力成本,故確實能達成本發明的目的。In summary, the history scoring method of the present invention uses the
惟以上所述者,僅為本發明的實施例而已,當不能以此限定本發明實施的範圍,凡是依本發明申請專利範圍及專利說明書內容所作的簡單的等效變化與修飾,皆仍屬本發明專利涵蓋的範圍內。However, the above are only examples of the present invention. When the scope of implementation of the present invention cannot be limited by this, all simple equivalent changes and modifications made in accordance with the scope of the patent application of the present invention and the content of the patent specification still belong to Within the scope covered by the patent of the present invention.
1:伺服端
100:通訊網路
11:通訊模組
12:儲存模組
13:處理模組
2:管理端
301~305:步驟
401~405:步驟
501~504:步驟
601~606:步驟1: Server
100: Communication network
11: Communication module
12: Storage module
13: Processing module
2:
本發明的其他的特徵及功效,將於參照圖式的實施方式中清楚地呈現,其中: 圖1是一方塊圖,說明本發明履歷評分系統的一第一實施例經由一通訊網路連接一管理端; 圖2是一流程圖,說明該第一實施例所執行的本發明履歷評分方法之一向量生成模型訓練程序; 圖3是一流程圖,說明該第一實施例所執行的本發明履歷評分方法之一評分模型訓練程序; 圖4是一流程圖,說明該第一實施例所執行的本發明履歷評分方法之一評分程序;及 圖5是一流程圖,說明一第二實施例所執行的本發明履歷評分方法之一摘要程序。Other features and effects of the present invention will be clearly presented in the embodiments with reference to the drawings, in which: Figure 1 is a block diagram illustrating a first embodiment of the resume scoring system of the present invention connected to a management terminal via a communication network; Figure 2 is a flowchart illustrating a vector generation model training program executed by the first embodiment of the resume scoring method of the present invention; Fig. 3 is a flowchart illustrating a scoring model training procedure performed by the first embodiment of the resume scoring method of the present invention; Fig. 4 is a flowchart illustrating a scoring procedure of the resume scoring method of the present invention executed by the first embodiment; and FIG. 5 is a flowchart illustrating a summary procedure of the resume scoring method of the present invention executed by a second embodiment.
1:伺服端1: Server
100:通訊網路100: Communication network
11:通訊模組11: Communication module
12:儲存模組12: Storage module
13:處理模組13: Processing module
2:管理端2: Management side
Claims (12)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109114559A TWI776146B (en) | 2020-04-30 | 2020-04-30 | Resume scoring method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109114559A TWI776146B (en) | 2020-04-30 | 2020-04-30 | Resume scoring method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202143122A true TW202143122A (en) | 2021-11-16 |
TWI776146B TWI776146B (en) | 2022-09-01 |
Family
ID=80783110
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109114559A TWI776146B (en) | 2020-04-30 | 2020-04-30 | Resume scoring method and system |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI776146B (en) |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2503477B1 (en) * | 2011-03-21 | 2017-08-30 | Tata Consultancy Services Limited | A system and method for contextual resume search and retrieval based on information derived from the resume repository |
CA2942627A1 (en) * | 2014-03-14 | 2015-09-17 | Pande SALIL | Career analytics platform |
CN107291715A (en) * | 2016-03-30 | 2017-10-24 | 阿里巴巴集团控股有限公司 | Resume appraisal procedure and device |
CN107590133A (en) * | 2017-10-24 | 2018-01-16 | 武汉理工大学 | The method and system that position vacant based on semanteme matches with job seeker resume |
CN108874928B (en) * | 2018-05-31 | 2024-02-02 | 平安科技(深圳)有限公司 | Resume data information analysis processing method, device, equipment and storage medium |
CN109345198A (en) * | 2018-09-17 | 2019-02-15 | 平安科技(深圳)有限公司 | Resume selection method, apparatus, computer equipment and storage medium |
CN109636337A (en) * | 2018-12-12 | 2019-04-16 | 北京唐冠天朗科技开发有限公司 | A kind of talent's base construction method and electronic equipment based on big data |
CN109948120B (en) * | 2019-04-02 | 2023-03-14 | 深圳市前海欢雀科技有限公司 | Binary resume parsing method |
CN110516261A (en) * | 2019-09-03 | 2019-11-29 | 北京字节跳动网络技术有限公司 | Resume appraisal procedure, device, electronic equipment and computer storage medium |
TWM599954U (en) * | 2020-04-30 | 2020-08-11 | 中國信託商業銀行股份有限公司 | Resume scoring system |
-
2020
- 2020-04-30 TW TW109114559A patent/TWI776146B/en active
Also Published As
Publication number | Publication date |
---|---|
TWI776146B (en) | 2022-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106339756B (en) | Generation method, searching method and the device of training data | |
Xia et al. | MVCWalker: Random walk-based most valuable collaborators recommendation exploiting academic factors | |
Olive et al. | A quest for a one-size-fits-all neural network: early prediction of students at risk in online courses | |
Tang et al. | Smart recommendation for an evolving e-learning system: Architecture and experiment | |
US10585784B2 (en) | Regression testing question answering cognitive computing systems by applying ground truth virtual checksum techniques | |
US20190050731A1 (en) | Automated commentary for online content | |
US20120311030A1 (en) | Inferring User Interests Using Social Network Correlation and Attribute Correlation | |
US8032469B2 (en) | Recommending similar content identified with a neural network | |
US10395258B2 (en) | Brand personality perception gap identification and gap closing recommendation generation | |
CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
CN106251261B (en) | Training scheme generation method and device | |
CN110210933A (en) | A kind of enigmatic language justice recommended method based on generation confrontation network | |
Karimi et al. | A deep model for predicting online course performance | |
Hosseini et al. | A study of concept-based similarity approaches for recommending program examples | |
CN114567815B (en) | Pre-training-based adaptive learning system construction method and device for lessons | |
Sajeev et al. | Effective web personalization system based on time and semantic relatedness | |
Ozcaglar et al. | Entity personalized talent search models with tree interaction features | |
TWM599954U (en) | Resume scoring system | |
Gadelha et al. | Traceability recovery between bug reports and test cases-a Mozilla Firefox case study | |
Do et al. | A fuzzy approach to detect spammer groups | |
TW202143122A (en) | Resume scoring method and system wherein the resume scoring system includes a plurality of regular expressions, a vector generation model, and a scoring model | |
Rio | Text message categorization of collaborative learning skills in online discussion using support vector machine | |
Celikkan et al. | A consolidated approach for design pattern recommendation | |
Phuong et al. | Collaborative filtering by multi-task learning | |
US20230088444A1 (en) | Unified platform of an artificial intelligence (ai) based test generator and test training system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GD4A | Issue of patent certificate for granted invention patent |