TW202230231A - Judgment system for suitability of talents and implementation method thereof - Google Patents
Judgment system for suitability of talents and implementation method thereof Download PDFInfo
- Publication number
- TW202230231A TW202230231A TW110102159A TW110102159A TW202230231A TW 202230231 A TW202230231 A TW 202230231A TW 110102159 A TW110102159 A TW 110102159A TW 110102159 A TW110102159 A TW 110102159A TW 202230231 A TW202230231 A TW 202230231A
- Authority
- TW
- Taiwan
- Prior art keywords
- information
- character
- voiceprint
- server
- module
- Prior art date
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
一種應用於人、職之間適性度判斷的系統及方法,尤指透過聲紋辨識技術,由聲紋特徵了解個人特質並分析職業適性度的人才適性度判斷系統及方法。A system and method for judging suitability between people and jobs, especially a talent suitability judging system and method for understanding personal characteristics from voiceprint features and analyzing occupational suitability through voiceprint recognition technology.
職能指的是一組知識、技能、行為與態度的組合,應用於工作上,則作為檢視是否能夠勝任某項任務的參考依據,其中,行為與態度由於較難以過往的學歷、資歷作為判斷依據,大多以心理測驗或量表的形式做檢核;而心理測驗又區分為語言文字及非語言文字兩大種類,語言文字通過問答或筆答進行的測試,為心理測試的主要方式,其編製和實施都相對容易具有快速,然而,語言文字類測試比較規範化,可控變數較少,不適用於語言或文字識別有困難的人,而且難以比較不同語言文化背景的被測試者,並且容易讓被測試者刻意操控測試結果,而無法準確的反應被試者的行為與態度;而非語言文字類測試,則包括各種通過畫圖、工具、實物為測試媒介的測試,被測試者通過使用、辨認、解釋或實時操作測試媒介,向測試者反映出心理顯像,非語言文字類測試適用於有語文表達障礙的人,也適合比較語言文化背景不同的被測試者,亦難以讓被試者刻意導向某些結果,但對比語言文字類測試卻有著施作成本高及實施時間長等缺點;此外,多數測驗在施作後,僅能簡單了解性格,不能立即根據評估結果,應用於面試、面談當下,例如:在了解面談者的性格後,卻無法針對性格特性做面談內容的調整,另,求職者僅能根據公司公開資訊及網路上之片面資訊了解公司生態,使得在做職涯規劃時,係往往只能依照薪資、福利作為挑選依據,而無法得知自己和公司文化,或是自己的性格能否和部門相處容價;據此,如何能有效改善習知評測性格的方法,使其能達到兼顧效率、準確、普及之優點,實為目前業界所需。Function refers to the combination of a set of knowledge, skills, behaviors and attitudes. When applied to work, it is used as a reference for checking whether one is competent for a certain task. Among them, behaviors and attitudes are judged based on the more difficult past education and qualifications. , most of which are checked in the form of psychological tests or scales; and psychological tests are divided into two types: verbal and non-verbal. It is relatively easy and fast to implement. However, language tests are relatively standardized and have few controllable variables. They are not suitable for people who have difficulty in language or text recognition, and it is difficult to compare test subjects with different language and cultural backgrounds, and it is easy to make the test subjects difficult. The tester deliberately manipulates the test results, and cannot accurately reflect the behavior and attitude of the subjects; non-verbal tests include various tests that use drawings, tools, and real objects as the test medium. Explain or operate the test medium in real time to reflect the psychological image to the tester. Non-verbal tests are suitable for people with language impairments, and are also suitable for comparing testees with different language and cultural backgrounds, and it is difficult for the testee to deliberately guide the test. Some results, but compared with language tests, have disadvantages such as high implementation cost and long implementation time; in addition, after most tests are administered, they can only briefly understand personality, and cannot be applied to interviews and interviews immediately based on the evaluation results. For example, after understanding the personality of the interviewee, it is impossible to adjust the content of the interview according to the personality characteristics. In addition, job seekers can only understand the company's ecology based on the company's public information and partial information on the Internet, so that when making career planning, Departments often can only choose based on salary and benefits, but cannot know their own and company culture, or whether their personality can get along with the department; based on this, how can we effectively improve the traditional methods of evaluating personality so that It can achieve the advantages of taking into account the efficiency, accuracy and popularization, which is actually required by the current industry.
有鑒於上述的問題,本發明人係依據多年來從事相關行業的經驗,針對性格分析方法進行研究及改進;緣此,本發明之主要目的在於提供一種人才適性度判斷系統及方法。In view of the above-mentioned problems, the inventors of the present invention research and improve the personality analysis method based on years of experience in related industries; therefore, the main purpose of the present invention is to provide a talent suitability judgment system and method.
為達上述的目的,本發明之人才適性度判斷系統及方法包含有一伺服器、一聲音擷取裝置、及一使用者端裝置,伺服器基於一聲紋資訊、及相對應的一性格資訊,以監督式學習法做為核心,架構一運算模型;再透過聲音擷取裝置擷取一待測聲紋資訊,並利用伺服器運算,以得出其相對應的性格,再將此性格資訊與伺服機中資料庫進行比對,係可由使用者端裝置接收一性格分析資訊,以供使用者快速、及時的了解待測試者的性格,以及性格相關的建議和應對。In order to achieve the above-mentioned purpose, the system and method for judging human suitability of the present invention includes a server, a voice capture device, and a user-end device. The server is based on voiceprint information and a corresponding character information, With the supervised learning method as the core, a computing model is constructed; then a voiceprint information to be tested is captured through a voice capture device, and the server is used for calculation to obtain its corresponding character, and then the character information is combined with The database in the server is compared, and a character analysis information can be received by the user terminal device, so that the user can quickly and timely understand the character of the person to be tested, as well as suggestions and responses related to the character.
為使 貴審查委員得以清楚了解本發明之目的、技術特徵及其實施後之功效,茲以下列說明搭配圖示進行說明,敬請參閱。In order to enable your examiners to clearly understand the purpose, technical features and effects of the present invention, the following descriptions are combined with the diagrams for illustration, please refer to.
請參閱「第1圖」及「第2圖」,其為本發明之組成示意圖(一)及(二),如圖中所示,本發明之人才適性度判斷系統1,包含有一伺服器11,另有一聲音擷取裝置12、及一使用者端裝置13與伺服器11資訊連結,以下例示各組成要件的功能:
(1) 伺服器11具有一運算處理模組111,另包含有一聲紋擷取模組112、一聲紋處理模組113、儲存模組114、及一數據分析模組115與運算處理模組111資訊連接;其中,運算處理模組111供以運行伺服器11,及驅動上述各模組之作動,運算處理模組111具備有邏輯運算、暫存運算結果、保存執行指令位置等功能,可以為中央處理器(Central Processing Unit,CPU),但不以此為限;
(2) 聲紋擷取模組112可接收一待測聲紋資訊,此待測聲紋資訊可基於一聲音轉換而來,亦可透過聲紋擷取模組112擷取影音檔案而得到待測聲紋資訊,所述之待測聲紋資訊可為數位或類比之無壓縮、有損壓縮、無損壓縮等聲紋資訊或其組合,但不以此為限;
(3) 聲紋處理模組113可將接收到的待測聲紋資訊進行包含有降噪、前處理(Preprocess)、及提取特徵參數(Feature Extraction)之其中一種或其組合,純化待測聲紋資訊,以利數據分析模組115使用,其中,前處理(Preprocess)可包含有預強調(Pre-emphasis)、取音框(Frame)、加窗(Window)、端點偵測(Endpoint Detection),但不以此為限,提取特徵參數(Feature Extraction)方法可包含有線性預估係數(Linear Predictive Coding Coefficient, LPCC)、梅爾倒頻譜係數(Mel-frequency Cepstrum Coefficient, MFCC)等,但不以此為限;
(4) 儲存模組114可供以儲存電子資料,其可以為固態硬碟(Solid State Disk or Solid State Drive)、硬碟(Hard Disk Drive,HDD)但不以此為限;資料儲存模組114更包含有一訓練資料庫1141及一性格資料庫1142,所述的訓練資料庫1141儲存有至少一聲紋資訊、及與之相對應的至少一性格資訊;性格資料庫1142儲存有與性格資訊相對應的性格分析資訊,性格分析資訊係為性格特性的解析及特徵,例如:性格表現的行為特點、適合的職務、合適的學習方法、性格的代表人物、面對各式情境下的反應、溝通策略等,但不以此為限;
(5) 數據分析模組115係為使用人工智慧(Artificial Intelligence,AI)、機器學習(Machine Learning)、深度學習(Deep Learning)等整合運算模式及其組合,但不以此為限,其基於訓練資料庫1141中的聲紋資訊做為輸入資料,性格資訊做為目標資料,其中,聲紋資訊係包含聲紋中的頻率、週期、波長、振福、波型、語速等聲紋特徵,但不以此為限,以監督式學習法做為核心,架構一運算模型;且數據分析模組115可基於待測聲紋資訊,產生其相對應的性格資訊,並可基於產生之性格資訊,由性格資料庫1142擷取出相對應的性格分析資訊;
(6) 聲音擷取裝置12係為可將聲音轉換成電子訊號的換能器,例如:話筒、微音器、麥克風,但不以此為限,聲音擷取裝置12供以擷取聲音,並將聲音轉換為待測聲紋資訊;
(7) 使用者端裝置13為可接收性格分析資訊的裝置,並供測試者或待測者參閱,可例如為:電腦、平板、智慧型手機、 顯示器、印表機、投影機、揚聲器等,但不以此為限。
Please refer to "Fig. 1" and "Fig. 2", which are schematic diagrams (1) and (2) of the present invention. As shown in the figures, the human
請參閱「第3圖」,其為本發明之實施流程圖,並請搭配參閱「第1圖」及「第2圖」,如圖中所示,本發明之人才適性度判斷方法實施步驟如下:
(1) 一數據分析模組訓練步驟S1:請搭配參閱「第4圖」,數據分析模組115以監督式學習法做為核心,架構一運算模型,並基於訓練資料庫1141中的聲紋資訊D3做為輸入資料,性格資訊D4做為目標資料進行訓練,其中,聲紋資訊D3係包含聲紋中的頻率、週期、波長、振福、波型、語速等聲紋特徵,但不以此為限,測試者係可先利用各式問卷及性格測驗工具,得到特定性格資訊D4對應的聲紋資訊D3,例如:對一群受眾使用九型人格測驗,並將其聲音一併紀錄,即可得到九型人格各性格資訊D4對應的各聲紋資訊D3,並以此建立訓練資料庫1141,以利用訓練資料庫1141對數據分析模組115進行訓練,上述之九型人格測驗僅為舉例說明,但不以此為限;
(2) 一收音步驟S2:請搭配參閱「第5圖」,測試者係可利用聲音擷取裝置12擷取一聲音D1,其中聲音D1可包含但不限於擷取待測者現場、線上說話之聲音、或含有待測者影音檔案之聲音,並將其轉換為待測聲紋資訊D2傳送至伺服器11,亦可由聲紋擷取模組112直接解析包含有待測者之影音檔案,擷取出待測聲紋資訊D2,並由伺服器11接收待測聲紋資訊D2,例如:於求職者面試當下以麥克風收錄其聲音,或求職者於面試前,上傳一段口說自我介紹音檔作為履歷,聲紋擷取模組112係可由此音檔擷取出待測聲紋資訊D2;
(3) 一聲紋處理步驟S3:聲紋處理模組113將待測聲紋資訊D2進行降噪、前處理(Preprocess)、及提取特徵參數(Feature Extraction)之其中一種或其組合,純化待測聲紋資訊D2,以利伺服器11分析處理;
(4) 一聲紋解析步驟S4:數據分析模組115基於經過聲紋處理步驟S3之待測聲紋資訊D2,產生其相對應的性格資訊D4,例如:數據分析模組115係基於求職者的待測聲紋資訊D2產生性格資訊D4為「熟能生巧的務實者」;其中,待測聲紋資訊D2係包含有聲紋之頻率、週期、波長、振福、波型、語速等聲紋特徵,但不以此為限;
(5) 一性格分析步驟S5:請搭配參閱「第6圖」數據分析模組115基於性格資訊D4由一性格資料庫1142篩選出對應的一性格分析資訊D5,例如:數據分析模組115係基於性格資訊D4為「熟能生巧的務實者」,由性格資料庫1142篩選出「具備耐心」、「在意做事的完整度與品質」等特質,及「內勤、廚師、會計(師)、醫生、需要專業證照的工作」之職業推薦;
(6) 一結果輸出步驟S6:請搭配參閱「第7圖」,伺服器11將性格資訊D4傳送至一使用者端裝置13,供測試者或待測者參閱。
Please refer to "Fig. 3", which is a flow chart of the implementation of the present invention, and please refer to "Fig. 1" and "Fig. 2" in combination. As shown in the figures, the implementation steps of the talent suitability judgment method of the present invention are as follows :
(1) A data analysis module training step S1: Please refer to “Fig. 4” for reference. The
請參閱「第8圖」,其為本發明之另一實施例(一),並請搭配參閱「第1圖」~「第7圖」,承步驟「結果輸出步驟S6」,本發明更包含有一模型修正步驟S7,當伺服器11將性格資訊D4傳送至一使用者端裝置13後,使用者可透過使用者端裝置13查看性格分析資訊D5是否符合自身性格,若不符合自身性格,則使用者可透過使用者端裝置13建立一修正資訊D6,此修正資訊D6為此次待測聲紋資訊D2、及其相對應之正確的性格資訊D4,並將此修正資訊D6傳送至伺服器11,伺服器11係可將此修正資訊D6作為訓練資料,以修正數據分析模組115。Please refer to "Fig. 8", which is another embodiment (1) of the present invention, and please refer to "Fig. 1" ~ "Fig. 7" in conjunction with the step "result output step S6", the present invention further includes There is a model correction step S7. After the
請參閱「第9圖」及「第10圖」,並請搭配參閱「第1圖」~「第7圖」,儲存模組114更包含有至少一群體性格資料庫1143,且各群體之成員係實施本發明之人才適性度判斷系統及方法,前述之群體可例如為:企業、單位或部門、及複數成員所形成之團體,由數據分析模組115基於測試結果,計算出一群體性格資訊D7,群體性格資訊D7為此群體之性格偏向,或與此群體相契合的性格資訊,數據分析模組115係可計算由聲紋解析步驟S4解析出之性格資訊D3、及群體性格資訊D7之契合度;如此,在聲紋解析步驟S4後,優選的,可執行一群體契合度步驟S8,數據分析模組115基於性格資訊D3與任一群體性格資訊D7之一契合度資訊D8,並將契合度資訊D8傳送至使用者端裝置13以執行結果輸出步驟S6,如此,若求職者同時錄取多家企業,欲做最終選擇時,係可參考契合度資訊D8,以了解與自身性格相仿的部門氛圍及文化,企業亦可透過群體性格資訊D7了解自身群體組成之特性。Please refer to "Picture 9" and "Picture 10", and please refer to "
由上所述可知,本發明之人才適性度判斷系統及方法,包含有一伺服器、一聲音擷取裝置、及一使用者端裝置,伺服器可基於訓練資料庫,以監督式學習法做為核心,架構一運算模型,伺服器係可基於聲音擷取裝置擷取之待測聲紋資訊,產生一性格資訊,並藉由比對性格資料庫,產生一性格分析資訊,測試者係可利用使用者端裝置獲取待測者之性格特性;利用聲紋特徵之測試方法具有快速、精準、難以造假等特性,能及時給予測試者建議及結果,此外,更可透過分析群體性格,得出個人與群體之間的契合度,據此,本發明之人才適性度判斷系統及方法,解決了習知性格測驗工具之痛點,並達到目前業界實務所需兼顧效率、準確、普及的性格評測方法之目的。From the above, it can be seen that the system and method for judging talent suitability of the present invention includes a server, a sound capture device, and a user-end device. The server can be based on a training database and use a supervised learning method. The core is to construct an operation model, the server can generate a personality information based on the voiceprint information to be tested captured by the voice capture device, and generate a personality analysis information by comparing the personality database, which can be used by the tester. The terminal device obtains the personality characteristics of the test subject; the test method using the voiceprint characteristics has the characteristics of fast, accurate, and difficult to fake, and can give the test subject advice and results in a timely manner. The degree of fit between groups, according to this, the talent suitability judgment system and method of the present invention solves the pain point of the conventional personality test tools, and achieves the efficiency, accuracy and popularization of personality evaluation methods required by current industry practice. Purpose.
唯,以上所述者,僅為本發明之較佳之實施例而已,並非用以限定本發明實施之範圍;任何熟習此技藝者,在不脫離本發明之精神與範圍下所作之均等變化與修飾,皆應涵蓋於本發明之專利範圍內。However, the above descriptions are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention; anyone familiar with the art can make equal changes and modifications without departing from the spirit and scope of the present invention. , all should be covered within the patent scope of the present invention.
綜上所述,本發明之功效,係具有發明之「產業可利用性」、「新穎性」與「進步性」等專利要件;申請人爰依專利法之規定,向 鈞局提起發明專利之申請。To sum up, the effect of the present invention is that it has the patent requirements of "industrial applicability", "novelty" and "progressiveness" of the invention; the applicant should file an invention patent with the Jun Bureau in accordance with the provisions of the Patent Law Application.
1:人才適性度判斷系統 11:伺服器 111:運算處理模組 112:聲紋擷取模組 113:聲紋處理模組 115:數據分析模組 114:儲存模組 1141:訓練資料庫 1142:性格資料庫 1143:群體性格資料庫 12:聲音擷取裝置 13:使用者端裝置 S1:數據分析模組訓練步驟 D1:聲音 S2:收音步驟 D2:待測聲紋資訊 S3:聲紋處理步驟 D3:聲紋資訊 S4:聲紋解析步驟 D4:性格資訊 S5:性格分析步驟 D5:性格分析資訊 S6:結果輸出步驟 D6:修正資訊 S7:模型修正步驟 D7:群體性格資訊 S8:群體契合度步驟 D8:契合度資訊 1: Talent suitability judgment system 11: Server 111: Operation processing module 112: Voiceprint Capture Module 113:Voiceprint processing module 115: Data Analysis Module 114: Storage Module 1141: Training database 1142: Personality Database 1143: Group Personality Database 12: Sound capture device 13: User device S1: Data analysis module training steps D1: sound S2: Radio Steps D2: Voiceprint information to be tested S3: Voiceprint processing steps D3: Voiceprint Information S4: Voiceprint Analysis Step D4: Personality Information S5: Steps of Personality Analysis D5: Personality Analysis Information S6: Result output step D6: Correction information S7: Model Correction Step D7: Group Personality Information S8: Group fit step D8: fit information
第1圖,為本發明之組成示意圖(一)。 第2圖,為本發明之組成示意圖(二)。 第3圖,為本發明之實施流程圖。 第4圖,為本發明之實施示意圖(一)。 第5圖,為本發明之實施示意圖(二)。 第6圖,為本發明之實施示意圖(三)。 第7圖,為本發明之實施示意圖(四)。 第8圖,為本發明之另一實施例(一)。 第9圖,為本發明之另一實施例(二)。 第10圖,為本發明之另一實施例(三)。 Figure 1 is a schematic diagram (1) of the composition of the present invention. Figure 2 is a schematic diagram (2) of the composition of the present invention. Fig. 3 is a flow chart of the implementation of the present invention. FIG. 4 is a schematic diagram (1) of the implementation of the present invention. FIG. 5 is a schematic diagram (2) of the implementation of the present invention. Fig. 6 is a schematic diagram (3) of the implementation of the present invention. FIG. 7 is a schematic diagram (4) of the implementation of the present invention. FIG. 8 is another embodiment (1) of the present invention. Fig. 9 is another embodiment (2) of the present invention. Fig. 10 is another embodiment (3) of the present invention.
1:人才適性度判斷系統 1: Talent suitability judgment system
11:伺服器 11: Server
12:聲音擷取裝置 12: Sound capture device
13:使用者端裝置 13: User device
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110102159A TWI741937B (en) | 2021-01-20 | 2021-01-20 | Judgment system for suitability of talents and implementation method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110102159A TWI741937B (en) | 2021-01-20 | 2021-01-20 | Judgment system for suitability of talents and implementation method thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI741937B TWI741937B (en) | 2021-10-01 |
TW202230231A true TW202230231A (en) | 2022-08-01 |
Family
ID=80782384
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110102159A TWI741937B (en) | 2021-01-20 | 2021-01-20 | Judgment system for suitability of talents and implementation method thereof |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI741937B (en) |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7917366B1 (en) * | 2000-03-24 | 2011-03-29 | Exaudios Technologies | System and method for determining a personal SHG profile by voice analysis |
ES2535858T3 (en) * | 2007-08-24 | 2015-05-18 | Deutsche Telekom Ag | Procedure and device for the classification of partners |
TWI657433B (en) * | 2017-11-01 | 2019-04-21 | 財團法人資訊工業策進會 | Voice interactive device and voice interaction method using the same |
CN109451188B (en) * | 2018-11-29 | 2022-03-18 | 平安科技(深圳)有限公司 | Method and device for differential self-help response, computer equipment and storage medium |
CN111554304A (en) * | 2020-04-25 | 2020-08-18 | 中信银行股份有限公司 | User tag obtaining method, device and equipment |
CN111694940A (en) * | 2020-05-14 | 2020-09-22 | 平安科技(深圳)有限公司 | User report generation method and terminal equipment |
-
2021
- 2021-01-20 TW TW110102159A patent/TWI741937B/en active
Also Published As
Publication number | Publication date |
---|---|
TWI741937B (en) | 2021-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Warden | Speech commands: A dataset for limited-vocabulary speech recognition | |
CN107818798B (en) | Customer service quality evaluation method, device, equipment and storage medium | |
US20180197548A1 (en) | System and method for diarization of speech, automated generation of transcripts, and automatic information extraction | |
CN115413348B (en) | System and method for automatically verifying and quantifying interview question answers | |
Lu et al. | Stresssense: Detecting stress in unconstrained acoustic environments using smartphones | |
US9754503B2 (en) | Systems and methods for automated scoring of a user's performance | |
CN110457432A (en) | Interview methods of marking, device, equipment and storage medium | |
US11238869B2 (en) | System and method for reconstructing metadata from audio outputs | |
JP6649461B1 (en) | Program, information processing apparatus and information processing method | |
CN111275444A (en) | Contract signing-based double recording method and device, terminal and storage medium | |
US20040193409A1 (en) | Systems and methods for dynamically analyzing temporality in speech | |
CN112232276A (en) | Emotion detection method and device based on voice recognition and image recognition | |
CN115796653A (en) | Interview speech evaluation method and system | |
CN115331804A (en) | Multi-modal psychological disease diagnosis method, computer device and storage medium | |
Chou et al. | An AI mock-interview platform for interview performance analysis | |
Kothalkar et al. | Automatic screening to detect’at risk’child speech samples using a clinical group verification framework | |
TW202230231A (en) | Judgment system for suitability of talents and implementation method thereof | |
Khazaleh et al. | An investigation into the reliability of speaker recognition schemes: analysing the impact of environmental factors utilising deep learning techniques | |
Shrivastava et al. | Puzzling out emotions: a deep-learning approach to multimodal sentiment analysis | |
CN116071032A (en) | Human resource interview recognition method and device based on deep learning and storage medium | |
KR102523808B1 (en) | Methord and device of performing ai interview for foreigners | |
Lahiri et al. | Interpersonal synchrony across vocal and lexical modalities in interactions involving children with autism spectrum disorder | |
Ramanarayanan et al. | Using vision and speech features for automated prediction of performance metrics in multimodal dialogs | |
CN113691382A (en) | Conference recording method, conference recording device, computer equipment and medium | |
Rasipuram et al. | A comprehensive evaluation of audio-visual behavior in various modes of interviews in the wild |