TWI741937B - Judgment system for suitability of talents and implementation method thereof - Google Patents

Abstract

Judgment system for the suitability of talents and implementation method thereof are disclosed. The present invention provides a calculation model based on voiceprint features related to each personality to obtain a personality information from a voiceprint of one of users under test, or obtain a group of the personality information from each of the voiceprint of a group of the users under test. In this way, the judgment system for the suitability of talents and implementation method thereof can immediately obtain the personality and career suggestions of the users, and obtain the compatibility between the personality information of the user and the personality information of the group of the users.

Description

System and method for judging the suitability of talents

A system and method for judging the suitability between people and jobs, especially the system and method for judging the suitability of talents through voiceprint recognition technology to understand personal characteristics from voiceprint characteristics and analyze the degree of professional suitability.

Function refers to a combination of knowledge, skills, behaviors and attitudes. When applied to work, it is used as a reference basis for checking whether they are competent for a certain task. Among them, behaviors and attitudes are judged based on difficult previous academic qualifications and qualifications. , Most of them are checked in the form of psychological tests or scales; and psychological tests are divided into two major types: spoken and written languages and non-verbal characters. The main method of psychological testing is the test of spoken and written language through question and answer or written answer. Implementation is relatively easy and fast. However, language testing is more standardized and has fewer controllable variables. It is not suitable for people who have difficulty in language or text recognition. It is also difficult to compare subjects with different language and cultural backgrounds, and it is easy to be The tester deliberately manipulates the test results, and cannot accurately reflect the behavior and attitude of the testees. Non-language tests include various tests that use drawings, tools, and objects as the test medium. The testees use, identify, and Explain or operate the test medium in real time to reflect the psychological image to the tester, Non-verbal and written tests are suitable for people with language difficulties, and it is also suitable for comparing subjects with different language and cultural backgrounds. It is also difficult for subjects to deliberately lead to certain results. However, comparative language and written tests have a high cost of implementation. Shortcomings such as long implementation time; in addition, most tests can only be used to understand personality briefly after being administered, and cannot be applied to interviews and interviews immediately based on the evaluation results. For example, after understanding the personality of the interviewer, it cannot focus on personality characteristics. Adjust the content of interviews. In addition, job seekers can only understand the company’s ecology based on the company’s public information and one-sided information on the Internet, so that when planning a career, the department can only choose salary and benefits as the basis for selection. Whether you can get along well with the company culture or your own character and department; accordingly, how to effectively improve the method of character evaluation by learning so that it can achieve the advantages of efficiency, accuracy and popularization is what the industry needs. .

In view of the above-mentioned problems, the inventor of the present invention has conducted research and improvement on personality analysis methods based on years of experience in related industries; for this reason, the main purpose of the present invention is to provide a system and method for judging the suitability of talents.

In order to achieve the above objectives, the system and method for judging the suitability of talents of the present invention includes a server, a voice capture device, and a client device. The server is based on a voiceprint information and a corresponding personality information. With the supervised learning method as the core, a calculation model is constructed; then the voiceprint information to be measured is captured through the voice capture device, and the server is used to calculate the corresponding information. Corresponding personality, and then compare this personality information with the database in the server, the user terminal device can receive a personality analysis information, so that the user can quickly and timely understand the personality of the person to be tested, and personality-related Suggestions and responses.

In order for your reviewer to have a clear understanding of the purpose, technical features and effects of the present invention after implementation, the following descriptions and illustrations are used for illustration, please refer to it.

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: Client 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 steps

D4: Personality Information

S5: Personality analysis steps

D5: Personality analysis information

S6: Results output steps

D6: Correction information

S7: Model correction steps

D7: Group personality information

S8: Steps to group fit

D8: fit information

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.

Figure 3 is a flow chart of the implementation of the present invention.

Figure 4 is a schematic diagram (1) of the implementation of the present invention.

Figure 5 is a schematic diagram (2) of the implementation of the present invention.

Figure 6 is a schematic diagram of the implementation of the present invention (3).

Figure 7 is a schematic diagram of the implementation of the present invention (4).

Figure 8 shows another embodiment (1) of the present invention.

Figure 9 shows another embodiment (2) of the present invention.

Figure 10 is another embodiment (3) of the present invention.

Please refer to "Figure 1" and "Figure 2", which are schematic diagrams (1) and (2) of the composition of the present invention. As shown in the figure, the talent suitability judging system 1 of the present invention includes a server 11 In addition, there is a voice capture device 12, and a user terminal device 13 which is connected to the server 11. The following is an example of the function of each component: (1) The server 11 has an arithmetic processing module 111, and also includes a voiceprint The acquisition module 112, a voiceprint processing module 113, a storage module 114, and a data analysis module 115 are connected to the arithmetic processing module 111 for information; wherein the arithmetic processing module 111 is used to run the server 11, and To drive the actions of the above-mentioned modules, the arithmetic processing module 111 has functions such as logical operations, temporarily storing the results of calculations, and storing the position of execution instructions, and may be a central processing unit (CPU), but is not limited to this; (2) The voiceprint capture module 112 can receive a voiceprint information to be measured. The voiceprint information to be tested can be converted based on a voice, or the voiceprint capture module 112 can capture audiovisual files to obtain the voiceprint information to be measured. To measure the voiceprint information, the voiceprint information to be measured can be digital or analog voiceprint information such as uncompressed, lossy compression, lossless compression, or a combination thereof, but not limited to this; (3) Voiceprint processing mode The group 113 can perform one or a combination of the received voiceprint information to be measured, including noise reduction, preprocess, and feature extraction (Feature Extraction), to purify the voiceprint information to be measured to facilitate data analysis Module 115 is used, where the pre-processing (Preprocess) can include pre-emphasis (Pre-emphasis), frame (Frame), window (Window), endpoint detection (Endpoint Detection), but not Limit, extract feature parameters (Feature The Extraction method can include Linear Predictive Coding Coefficient (LPCC), Mel-frequency Cepstrum Coefficient (MFCC), etc., but not limited to this; (4) The storage module 114 can For storing electronic data, it can be a solid state disk (Solid State Disk or Solid State Drive), a hard disk (Hard Disk Drive, HDD) but not limited to this; the data storage module 114 further includes a training database 1141 And a personality database 1142. The training database 1141 stores at least one voiceprint information and at least one personality information corresponding to it; the personality database 1142 stores personality analysis information corresponding to the personality information. Analytical Information Department is the analysis and characteristics of personality characteristics, such as: behavioral characteristics of personality performance, suitable positions, suitable learning methods, representative characters of the personality, responses to various situations, communication strategies, etc., but not (5) The data analysis module 115 uses artificial intelligence (AI), machine learning (Machine Learning), deep learning (Deep Learning) and other integrated computing modes and their combinations, but not limited to this It is based on the voiceprint information in the training database 1141 as the input data, and the personality information as the target data. Among them, the voiceprint information includes the frequency, period, wavelength, vibration, wave pattern, speech rate, etc. in the voiceprint. Voiceprint features, but not limited to this. The supervised learning method is used as the core to construct an arithmetic model; and the data analysis module 115 can generate corresponding personality information based on the voiceprint information to be measured, and can be based on Produced sex Personality information, the corresponding personality analysis information is retrieved from the personality database 1142; (6) The voice capture device 12 is a transducer that can convert voices into electronic signals, such as microphones, microphones, and microphones. Not limited to this, the voice capture device 12 is used to capture voices and convert the voices into voiceprint information to be tested; (7) The client device 13 is a device that can receive personality analysis information and is used by the tester or For those to be tested, it can be, for example, computers, tablets, smart phones, monitors, printers, projectors, speakers, etc., but not limited to this.

Please refer to "Figure 3", which is the flow chart of the implementation of the present invention. Please also refer to "Figure 1" and "Figure 2". : (1) A data analysis module training step S1: Please refer to "Figure 4" for matching. The data analysis module 115 takes the supervised learning method as the core, constructs an arithmetic model, and is based on the sound in the training database 1141. The pattern information D3 is used as the input data, and the personality information D4 is used as the target data for training. Among them, the voiceprint information D3 includes the frequency, period, wavelength, vibration, wave pattern, speech speed and other characteristics of the voiceprint in the voiceprint. Not limited to this, the tester can first use various questionnaires and personality test tools to obtain the voiceprint information D3 corresponding to the specific personality information D4, for example: use the Enneagram test for a group of audiences and record their voices together , You can get each voiceprint information D3 corresponding to each personality information D4 of Enneagram, and create training data based on it The database 1141 is to use the training database 1141 to train the data analysis module 115. The above-mentioned Enneagram test is only an example, but not limited to this; (2) Step S2 of a radio reception: please refer to "Section 5" Figure", the tester can use the voice capture device 12 to capture a voice D1, where the voice D1 may include but is not limited to capturing the voice of the subject’s live, online speaking, or the voice containing the subject’s video and audio files, and Convert it into the voiceprint information D2 to be tested and send it to the server 11. The voiceprint capture module 112 can also directly parse the audio-visual file containing the subject to be tested, extract the voiceprint information D2 to be tested, and send it to the server 11 Receive the voiceprint information D2 to be tested, for example, use a microphone to record the voice of the job applicant during the interview, or upload a self-introduction audio file as a resume before the job interview. The voiceprint capture module 112 can use this voice File extraction of the voiceprint information D2 to be measured; (3) a voiceprint processing step S3: the voiceprint processing module 113 performs noise reduction, preprocess (Preprocess), and feature extraction (Feature Extraction) on the voiceprint information D2 to be measured. ) To purify the voiceprint information D2 to be measured for analysis and processing by the server 11; (4) a voiceprint analysis step S4: the data analysis module 115 is based on the voice to be measured after the voiceprint processing step S3 The pattern information D2 generates the corresponding personality information D4. For example, the data analysis module 115 generates the personality information D4 based on the job applicant’s voiceprint information D2 to be tested. D4 is "practice makes perfect." D2 includes voiceprint characteristics such as frequency, period, wavelength, vibration, wave pattern, speech rate, etc., but not limited to this; (5) a personality analysis step S5: please refer to "Figure 6" for data Analysis module 115 Based on the personality information D4, a personality database 1142 filters out the corresponding personality analysis information D5. For example, the data analysis module 115 is based on the personality information D4 as "practice makes perfect", and the personality database 1142 filters out "with "Patience", "caring about the completeness and quality of work" and other characteristics, and "internal service, chef, accountant (teacher), doctor, work requiring professional licenses" career recommendations; (6) a result output step S6: please refer to In "Figure 7", the server 11 sends the personality information D4 to a client device 13 for the tester or the tester to refer to.

Please refer to "Figure 8", which is another embodiment (1) of the present invention, and please refer to "Figure 1" ~ "Figure 7" in conjunction with step "Result output step S6", the present invention further includes There is a model correction step S7. After the server 11 sends the personality information D4 to a client device 13, the user can check whether the personality analysis information D5 conforms to his personality through the client device 13. If it does not conform to his personality, then The user can create a modified information D6 through the client device 13, this modified information D6 is the voiceprint information D2 to be tested this time and its corresponding correct character information D4, and send the modified information D6 to the server 11. The server 11 can use the modified information D6 as training data to modify the data analysis module 115.

Please refer to "Figure 9" and "Figure 10", and please refer to "Figure 1" ~ "Figure 7". The storage module 114 further includes at least one group personality database 1143, and members of each group Appropriateness of talents to implement the present invention Judgment system and method, the aforementioned group may be, for example, a group formed by a company, unit or department, and a plurality of members. Based on the test result, the data analysis module 115 calculates a group personality information D7, and the group personality information D7 is for this purpose The personality bias of the group, or the personality information that fits this group, the data analysis module 115 can calculate the fit between the personality information D3 and the group personality information D7 parsed by the voiceprint analysis step S4; in this way, in the voiceprint After analyzing step S4, preferably, a group fit step S8 may be performed. The data analysis module 115 transmits the fit information D8 to the user based on the fit information D8 of the personality information D3 and any one of the group personality information D7 The end device 13 outputs the execution result of step S6. In this way, if a job seeker enrolls in multiple companies at the same time and wants to make a final choice, he can refer to the fit information D8 to understand the departmental atmosphere and culture similar to his own personality. The company can also Learn about the characteristics of your own group composition through group personality information D7.

It can be seen from the above that the system and method for judging the suitability of talents of the present invention includes a server, a voice capture device, and a client device. The server can be based on a training database and use a supervised learning method. The core is to build a computing model. The server can generate 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 the tester can use The terminal device obtains the personality characteristics of the test subject; the test method using voiceprint characteristics is fast, accurate, and difficult to fake, and can promptly give suggestions and results to the tester. In addition, it can also analyze the personality of the group to obtain personal and According to the degree of fit between groups, the system and method for judging the suitability of talents of the present invention solves the problem of conventional personality The pain point of the test tool, and to achieve the goal of the current industry practice that takes into account the efficiency, accuracy, and popularity of the personality evaluation method.

However, the above are only the preferred embodiments of the present invention, and are not intended to limit the scope of implementation of the present invention; anyone who is familiar with this technique can make equal changes and modifications without departing from the spirit and scope of the present invention , Should be covered in the scope of the patent of the present invention.

To sum up, the effect of the present invention is that it possesses the patent requirements of "industrial applicability", "novelty" and "progressiveness" of the invention; the applicant filed a patent for invention with the Bureau in accordance with the provisions of the Patent Law Application.

1: Talent suitability judgment system

11: server

12: Sound capture device

13: Client device

Claims (10)

A system for judging the suitability of talents, comprising: a voice capturing device for capturing at least one voice and converting it into a voiceprint information to be measured; a server connected to the voice capturing device information, which includes a calculation Processing module, another voiceprint acquisition module, voiceprint processing module, storage module, and a data analysis module are connected with the information of the operation processing module; the operation processing module is used to run the server The voiceprint processing module is used to purify the voiceprint information to be measured; the storage module includes a training database and a personality database, and the training database stores at least one voiceprint information and at least one personality information, The voiceprint information is the frequency, period, wavelength, amplitude, wave type, and speed of speech in the voiceprint, and the voiceprint information and the personality information are corresponded to each other using the nineteen-type personality test. At least one personality analysis information corresponding to the personality information; the data analysis module is based on the voiceprint information in the training database as the input data, the personality information is the target data, and the supervised learning method is the core. Construct a computing model; the data analysis module generates the personality information based on the voiceprint information to be measured; the data analysis module generates the personality analysis information based on the personality information and the personality database; and A client device is connected with the server information for receiving the personality analysis information. The system for judging the suitability of talents according to claim 1, wherein the character analysis information includes a character performance characteristic, a suitable position, a suitable learning method, a character representative, and a face of various situations One or a combination of the following response, or a communication strategy. The system for judging the suitability of talents according to claim 1, wherein the data analysis module can be modified based on a modified information. The system for judging the suitability of talents according to claim 1, wherein the data analysis module further generates a group of personality information based on a plurality of the voiceprint information to be measured. The system for judging the suitability of talents according to claim 4, wherein the storage module further includes a group personality database storing at least one group personality information. The system for judging the suitability of talents according to claim 4, wherein the data analysis module calculates a fit information based on the personality information of the group and the personality information. A method for judging the suitability of talents, comprising: a data analysis module training step: a server uses at least one voiceprint information stored in a training database as input data, and stores it in the training database and the voiceprint At least one personality information corresponding to the information is used as target data for training, and a supervised learning method is used to construct an arithmetic model, where the voiceprint information is the frequency, period, wavelength, amplitude, wave type, and speed of speech in the voiceprint. The voiceprint information and the personality information are corresponded with each other by using the nineteen-type personality test; a radio step: a voice capture device captures at least one voice, converts it into a voiceprint information to be tested, and sends it to the server A voiceprint processing step: the server purifies the voiceprint information to be measured; a voiceprint analysis step: the server executes the calculation model to generate the personality information using the voiceprint information to be measured; a personality analysis step: The server filters out a corresponding personality analysis information from a personality database based on the personality information; and a result output step: the server sends the personality information to a client device. The method for judging the suitability of talents according to claim 7, which further includes a model modification step: the server modifies the calculation model based on a modification information. The method for judging the suitability of talents according to claim 7, wherein the voiceprint analysis step further includes generating a group personality information based on a plurality of the voiceprint information to be measured. The method for judging the suitability of talents according to claim 9, which further includes a group fit step: the server calculates a fit based on the personality information of the group and the personality information.

Images