CN113822589A

CN113822589A - Intelligent interviewing method, device, equipment and storage medium

Info

Publication number: CN113822589A
Application number: CN202111147864.2A
Authority: CN
Inventors: 赵明; 田科; 章宏武; 吴中勤
Original assignee: Beijing Century TAL Education Technology Co Ltd
Current assignee: Beijing Century TAL Education Technology Co Ltd
Priority date: 2021-09-29
Filing date: 2021-09-29
Publication date: 2021-12-21

Abstract

The application provides an intelligent interview method, an intelligent interview device, intelligent interview equipment and a storage medium. In some embodiments of the present application, the intelligent interview apparatus obtains resume text and job description text of the job hunting user; extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; the intelligent interviewing device extracts the application positions of the job hunting users from the position description text; the intelligent interviewing device selects a question from a preset question bank according to the capability label and the engaging position of the job hunting user, selects a question matched with the personal capability and the engaging position of the job hunting user to conduct an interviewing process, reasonably evaluates the capability of the job hunting user, and improves the accuracy of capability evaluation of the job hunting user.

Description

Intelligent interviewing method, device, equipment and storage medium

Technical Field

The present application relates to the field of data processing technologies, and in particular, to an intelligent interview method, apparatus, device, and storage medium.

Background

The traditional talent recruitment interview method is represented as follows: the recruiter issues positions, waits for or searches resumes, invites interviews on a large scale, interviews on site, tries on a written basis, etc. The recruitment process needs to consume a long time period, each link needs manual participation, and resumes need to be manually participated at all levels, so that a large amount of manpower, financial resources and time cost are consumed. Therefore, intelligent interviews are produced at the right moment.

Currently, intelligent interviewing cannot objectively assess the ability of an interviewer.

Disclosure of Invention

The application provides an intelligent interview method, an intelligent interview device, intelligent interview equipment and an intelligent interview storage medium from multiple aspects, and the intelligent interview method, the intelligent interview device, the intelligent interview equipment and the intelligent interview storage medium are used for improving the accuracy of capability evaluation of job hunting users.

The embodiment of the application provides an intelligent interview method, which comprises the following steps:

acquiring a resume text and a job description text;

extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; and

extracting the application positions of the job hunting users from the position description text;

and selecting a topic from a preset topic library according to the capability label and the recruitment position of the job hunting user.

The embodiment of the present application further provides an intelligent interview device, including:

the acquisition module is used for acquiring the resume text and the job description text;

the first extraction module is used for extracting keywords according to the resume text and the job description text to obtain a capability tag of the job hunting user; and

the second extraction module is used for extracting the application positions of the job hunting users from the position description text;

and the selection module is used for selecting a topic from a preset topic library according to the capability label and the recruitment position of the job hunting user.

An embodiment of the present application further provides an electronic device, including:

a processor; and

a memory for storing a program, wherein the program is stored in the memory,

wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method described above.

Embodiments of the present application also provide a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the above method.

In some embodiments of the present application, the intelligent interview apparatus obtains resume text and job description text of the job hunting user; extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; the intelligent interviewing device extracts the application positions of the job hunting users from the position description text; the intelligent interviewing device selects a question from a preset question bank according to the capability label and the engaging position of the job hunting user, selects a question matched with the personal capability and the engaging position of the job hunting user to conduct an interviewing process, reasonably evaluates the capability of the job hunting user, and improves the accuracy of capability evaluation of the job hunting user.

Drawings

Further details, features and advantages of the disclosure are disclosed in the following description of exemplary embodiments, taken in conjunction with the accompanying drawings, in which:

fig. 1 is a schematic structural diagram of an interview system provided in an exemplary embodiment of the present application;

FIG. 2 is a partial diagram of a knowledge-graph provided in an exemplary embodiment of the present application;

FIG. 3 is a flowchart of a method of an intelligent interview method provided by an exemplary embodiment of the present application;

FIG. 4 is a flowchart of a method for providing an intelligent interview method according to another exemplary embodiment of the present application;

fig. 5 is a schematic diagram of a frame structure of an intelligent interview apparatus according to an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description. It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

At present, the intelligent interviewing method screens questions through the posts of job hunting users, and the interviewing is difficult to master the abilities of all aspects of the job hunting users, so that the job hunting users cannot be reasonably evaluated.

In some embodiments of the present application, the intelligent interview apparatus obtains a resume text and a job description text of the job hunting user; extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; the intelligent interviewing device extracts the application positions of the job hunting users from the position description text; the intelligent interviewing device selects a question from a preset question bank according to the capability label and the engaging position of the job hunting user, selects a question matched with the personal capability and the engaging position of the job hunting user to conduct an interviewing process, reasonably evaluates the capability of the job hunting user, and improves the accuracy of capability evaluation of the job hunting user.

The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic structural diagram of an intelligent interview system 10 according to an exemplary embodiment of the present application. As shown in fig. 1, the intelligent interview system 10 includes a job hunting user terminal 10a, an interview apparatus 10b and an interviewer terminal 10 c. The user terminal 10a, the interview apparatus 10b and the interviewer terminal 10c as presented in fig. 1 are only exemplary and are not limited in their implementation. The job hunting user uploads the electronic resume to the interviewing equipment 10b through the job hunting user terminal 10a, the interviewing equipment 10b receives the electronic resume of the job hunting user and automatically interviews the job hunting user, and an interviewing result of the job hunting user is generated; the interview equipment 10b sends the interview result to the interviewer terminal 10c for the interviewer to view the interview result.

The job hunting user terminal 10a, the interviewer terminal 10c and the interviewing equipment 10b are connected in a wired or wireless mode. Optionally, the user terminal 10a and the interviewer terminal 10c may establish a communication connection with the interview device 10b in a communication manner such as WIFI, bluetooth, infrared, or the user terminal 10a and the interviewer terminal 10c may also establish a communication connection with the interview device 10b through a mobile network. The network format of the mobile network may be any one of 2G (gsm), 2.5G (gprs), 3G (WCDMA, TD-SCDMA, CDMA2000, UTMS), 4G (LTE), 4G + (LTE +), WiMax, and the like.

In this embodiment, the job-seeking user terminal 10a refers to a device used by the user and having functions of computing, accessing internet, communicating and the like required by the user, and may be, for example, a smart phone, a tablet computer, a personal computer, a wearable device and the like. The job hunting user terminal 10a includes at least one processing unit and at least one memory. The number of processing units and memories depends on the configuration and type of terminal equipment. The Memory may include volatile, such as RAM, non-volatile, such as Read-Only Memory (ROM), flash Memory, etc., or both. The memory typically stores an Operating System (OS), one or more application software programs, and may also store program data and the like. In addition to the processing unit and the memory, the job hunting user terminal 10a may also include basic configurations such as a network card chip, an IO bus, and audio/video components. Optionally, depending on the implementation of the job-seeking user terminal 10a, the job-seeking user terminal 10a may also include some peripheral devices, such as a keyboard, a mouse, a stylus, a printer, and the like. These peripheral devices are well known in the art and will not be described in detail herein.

In this embodiment, the interviewer terminal 10c is a device used by the user and having functions of computing, accessing internet, communicating, and the like, and may be, for example, a smart phone, a tablet computer, a personal computer, a wearable device, and the like.

In this embodiment, the interview apparatus 10b may be an intelligent terminal apparatus or a server. When the interview equipment 10b is a server, the implementation form of the server is not limited in this embodiment, and the server may be a conventional server, a cloud host, a virtual center, or other server equipment. The server device mainly includes a processor, a hard disk, a memory, a system bus, and the like, and is similar to a general computer architecture.

In this embodiment, the job hunting user uploads an electronic resume by using the job hunting user terminal 10a, and after the interview equipment 10b receives the resume text and the job description text, the interview equipment 10b extracts keywords according to the resume text and the job description text to obtain a capability tag of the job hunting user; the interview equipment 10b selects a question from a preset question bank according to the capability label and the job position of the job hunting user; the interviewing equipment 10b provides the questions to job seeking users for the job seeking users to answer the questions; the interview equipment 10b generates interview results of job hunting users according to the acquired answer results of the job hunting users for the questions; the interview equipment 10b sends the interview result to the interviewer terminal 10 c; after receiving the interview result, the interviewer terminal 10c displays the interview result on the electronic display screen of the interviewer terminal for the interviewer to check.

It should be noted that the job description text refers to a text for describing the recruitment requirement of the recruiter. Usually, the job description text contains the application positions of the job hunting users. And the capability label is a keyword for reflecting the skill of the job hunting user for applying the job position.

In this embodiment, the interview equipment 10b extracts keywords according to the resume text and the job description text to obtain the capability label of the job hunting user. In one implementation, the interview device 10b enters the resume text and job description text into an existing resume content understanding model to obtain capability labels for job-seeking users. For example, the resume text "1, proficient Python, is proficient at list, tuple, set operations. 2. And when the Git is used skillfully, codes and job description texts can be submitted, deleted and combined, and the codes and the job description texts are input into an existing resume content understanding model to obtain capability labels 'proficient Python' and 'skillful use Git' of the job hunting user. The job description text can be referred to the definition of the job description text, and is not illustrated here.

In the present embodiment, the interview apparatus 10b extracts the employment position of the job hunting user from the position description text. One way in which this can be accomplished is that the interview apparatus 10b can search for the keyword "job application position" and take the text content after the "job application position" as the job application position.

In another embodiment, if the electronic resume is of a picture type, the interview equipment 10b extracts keywords from the resume text and the job description text to obtain the capability label of the job-seeking user, and one realizable way is that the interview equipment 10b performs resume text region detection on the electronic resume to obtain a resume region picture; the interview equipment 10b performs text recognition on the resume area picture to obtain a resume text; and inputting the resume text and the job description text into an existing resume content understanding model to obtain the capability label of the job hunting user. Optionally, the interview equipment 10b performs resume text region detection on the electronic resume by using the text detection model to obtain a resume region picture; the interview equipment 10b performs text recognition on the resume area picture by using the text recognition model to obtain a resume text. For example, the interview equipment 10b performs resume text region detection on the electronic resume by using a text detection model to obtain a text containing "1", proficient Python development, and has better understanding on multithreading and coroutiny. 2. Familiar web development frameworks such as: django, Tornado, flash, familiar with the design idea of object-oriented, have knowledge of the common design mode "resume area pictures; the interviewing equipment 10b performs text recognition on the resume area picture by using a text recognition model to obtain a resume text: "1" is developed by Python, and has better understanding on multithreading and coroutine. 2. Familiar web development frameworks such as: django, Tornado, flash, familiar with object-oriented design ideas, and known about common design patterns. And b, converting the resume text: "1" is developed by Python, and has better understanding on multithreading and coroutine. 2. Familiar web development frameworks such as: django, Tornado and Flask are familiar with the design idea of object-oriented design and know the common design mode. "inputting resume content understanding model with job description text to obtain capability label of job seeking user" 1, mastered Python development, 2, mastered Django, flash frame and rest mode ".

Before using the text detection model, the text recognition model and the resume content understanding model, the text detection model, the text recognition model and the resume content understanding model need to be trained, and the training processes of the text detection model, the text recognition model and the resume content understanding model are explained in sequence as follows: training the text detection model: firstly, a large number of resume text image samples to be recognized are collected, different subject objects possibly encountered in various text detection scenes are covered as much as possible, and therefore sample coverage rate is improved. And then, labeling the resume text regions on the training sample to obtain the actual distribution condition of the resume text regions on the resume text image sample to be identified.

The labeled training samples may then be input into a neural network model. In the neural network model, the training samples can be subjected to operations such as feature extraction, calculation and the like according to the model parameters, and the output layer of the neural network model outputs the detection result of the resume text region. And then, the loss function layer of the neural network model can calculate the loss function according to the difference between the detection result of the resume text region output by the output layer and the real resume text region on the training sample. If the loss function does not meet the set requirement, the model parameters can be adjusted, and iterative training is continued. And when the loss function of the neural network model meets the set requirement, obtaining the trained text detection model.

Training the text recognition model: a large number of text images to be recognized are collected, and different subject objects possibly encountered in various text recognition scenes are covered as much as possible, so that the sample coverage rate is improved. Then, the text on the training sample can be labeled to obtain the actual distribution condition of the text on the text image to be recognized.

The labeled training samples may then be input into a neural network model. In the neural network model, the training samples can be subjected to operations such as feature extraction, calculation and the like according to the model parameters, and the output layer of the neural network model outputs a text recognition result. Then, the loss function layer of the neural network model can calculate the loss function according to the difference between the text recognition result output by the output layer and the real text on the training sample. If the loss function does not meet the set requirement, the model parameters can be adjusted, and iterative training is continued. And when the loss function of the neural network model meets the set requirement, obtaining the trained text recognition model.

The training process of the resume content understanding model comprises the following steps: a large number of resume text samples and position description text samples corresponding to the resume text samples are collected, different subject objects possibly encountered in various content understanding scenes are covered as much as possible, and therefore sample coverage rate is improved. And then, labeling the capability labels on the training samples to obtain the actual distribution conditions of the capability labels corresponding to the resume text samples and the position description text samples.

The labeled training samples may then be input into a neural network model. In the neural network model, operations such as feature extraction and calculation can be performed on the training samples according to model parameters, and the capability labels are output by an output layer of the neural network model. Then, the loss function layer of the neural network model can calculate the loss function according to the difference between the capability label output by the output layer and the real capability label on the training sample. If the loss function does not meet the set requirement, the model parameters can be adjusted, and iterative training is continued. When the loss function of the neural network model meets the set requirement, the resume content understanding model after training can be obtained.

It should be noted that the capability label in the embodiment of the present application indicates a skill of an application position corresponding to the application of a job hunting user. Capability tags for job hunting users of the application developer include, but are not limited to: proficient in Python, basic understanding of Python, proficient in Git, proficient in flash frame, etc.

In the above embodiment, the interview apparatus 10b selects a topic from the preset topic library based on the capability tag and the job position of the job hunting user. One way to realize the job hunting is to select a first topic from a preset topic library according to the capability label and the job position of the job hunting user; outputting a first question; responding to the answer information of the job hunting user for the first question, and obtaining an answer result of the first question after judging the question; selecting a second question from a preset question bank according to the answer result of the first question; and sequentially executing the selection of the subsequent topics until the selection of the preset number of topics is completed.

It should be noted that the knowledge graph includes sub-graphs corresponding to a plurality of capability labels, each sub-graph includes a corresponding capability label node and a knowledge point node connected to the capability label node, and a connection relationship between the capability label node and the knowledge point node indicates that an association relationship exists between a capability label corresponding to the capability label node and a knowledge point corresponding to the knowledge point node. Capability label nodes include, but are not limited to: the Python base is proficient in Python, proficient in Git, proficient in flash frame and other capability label nodes. For example, as shown in fig. 2, a subgraph corresponding to the capability label "Python basis", the knowledge point node corresponding to the Python basis includes: the system comprises a Numpy node, a Pandas node, a Flask frame node, a Djago frame node and a basic grammar node, wherein the nodes are connected with a Python basic node, and the Pandas node comprises a CSV processing sub-node and an Excel processing sub-node.

In the above embodiment, the interview apparatus 10b selects a question from the preset question bank according to the competence label and the job position of the job hunting user. One way to realize the method is to search a target knowledge point node connected with a capability label node corresponding to a capability label from an existing interview knowledge graph, wherein the interview knowledge graph comprises the capability label node and a knowledge point node connected with the capability label node, and the connection relation between the capability label node and the knowledge point node indicates that the capability label corresponding to the capability label node has an association relation with the knowledge point corresponding to the knowledge point node; according to the level of the applicable position, inquiring a mapping relation table of the level of the applicable position and the capacity matching degree coefficient to obtain a target capacity matching degree coefficient, wherein each question carries the capacity matching degree coefficient; and randomly selecting a question with a target capability matching degree coefficient from the sub-question banks corresponding to the target knowledge point nodes, wherein the preset question bank comprises a plurality of sub-question banks corresponding to the plurality of knowledge point nodes one by one.

The interview equipment 10b selects a first topic from a preset topic library according to the capability label and the job position of the job hunting user. One way to achieve this is that the interview equipment 10b searches the target knowledge point nodes connected with the capability label nodes corresponding to the capability labels from the existing interview knowledge graph; according to the level of the applicable position, inquiring a mapping relation table of the level of the applicable position and the capacity matching degree coefficient to obtain a target capacity matching degree coefficient, wherein each question carries the capacity matching degree coefficient; and randomly selecting a first topic with the capability matching degree coefficient as the target capability matching degree coefficient from the sub-topic library corresponding to the target knowledge point node, wherein the preset topic library comprises a plurality of sub-topic libraries corresponding to a plurality of knowledge point nodes one by one. Optionally, according to the level of the employment position, inquiring a mapping relation table of the level of the employment position and the capability matching degree coefficient to obtain a plurality of candidate capability matching degree coefficients; and selecting a target capability matching degree coefficient meeting a preset matching degree condition from the plurality of candidate capability matching degree coefficients.

For example, the ability tags corresponding to job hunting users include: the method comprises the steps that a java base and a Python base are adopted, wherein the java base corresponds to 10 knowledge point nodes, the Python base corresponds to 10 knowledge point nodes, each knowledge point node corresponds to a question bank, and a total of 20 knowledge point nodes connected with the java base and the Python base are searched from an existing interview knowledge graph; the method comprises the steps that an application position is a primary development engineer, a mapping relation table of the level of the application position and an ability matching degree coefficient is inquired to obtain a plurality of candidate ability matching degree coefficients 0.3 and 0.4, and the largest candidate ability matching degree coefficient is selected from the candidate ability matching degree coefficients 0.3 and 0.4 to serve as a target ability matching degree coefficient; and randomly selecting a first topic with the capability matching degree coefficient of 0.4 from the sub-topic library corresponding to the 20 knowledge point nodes.

In one embodiment, the interview equipment 10b plays a first question to the job seeking user in a voice mode, the job seeking user answers in the voice mode, the interview equipment 10b collects the answering voice of the job seeking user for the question, and the matching degree of the answering text of the first question and the corresponding standard answer is calculated to obtain the score of the first question as the answering result of the first question.

In the above embodiment, the interview apparatus 10b selects the second question from the preset question bank according to the answer result of the first question. One way to implement this is that the interview equipment 10b determines a target question difficulty coefficient of a second question according to the answer result of a first question, wherein each question carries a question difficulty coefficient; judging whether the question with the target question difficulty coefficient exists in a sub-question bank where the first question is located; if so, selecting a topic with a target topic difficulty coefficient from a sub-topic library in which the first topic is located, and taking the topic as a second topic; and if not, randomly selecting a second topic with the target topic difficulty coefficient from other topic libraries, wherein the other topic libraries are the residual topic libraries except the topic library where the first topic is located in all the topic libraries corresponding to all the target knowledge point nodes corresponding to the capability labels of the job-seeking users.

The interview equipment 10b selects a second question from the preset question bank according to the answer result of the first question. One way to realize the method is to determine a target question difficulty coefficient of a second question according to the answering result of a first question, wherein each question carries a question difficulty coefficient; judging whether the question with the target question difficulty coefficient exists in a sub-question bank where the first question is located; if so, selecting a topic with a target topic difficulty coefficient from a sub-topic library in which the first topic is located, and taking the topic as a second topic; and if not, randomly selecting a second topic with the target topic difficulty coefficient from other topic libraries, wherein the other topic libraries are the residual topic libraries except the topic library where the first topic is located in all the topic libraries corresponding to all the target knowledge point nodes corresponding to the capability labels of the job-seeking users.

Optionally, the interview equipment 10b determines the target question difficulty coefficient of the second question according to the answer result of the question of the job hunting user in the first turn. One way to achieve this is to determine whether the score of the first topic is greater than or equal to a set score threshold; if yes, calculating a target subject difficulty coefficient of a second subject in a first mode according to the subject difficulty coefficient of the first subject and the score of the first subject, wherein the target subject difficulty coefficient is larger than the subject difficulty coefficient of the first subject; and if not, calculating a target topic difficulty coefficient of a second topic in a second calculation mode according to the topic difficulty coefficient of the first topic and the score of the first topic, wherein the target topic difficulty coefficient is smaller than the topic difficulty coefficient of the first topic.

For example, the relationship between the ability matching degree coefficient δ, the matching degree weight β, and the topic difficulty coefficient γ is as follows:

，

wherein i is a positive integer, δ is a capability matching degree coefficient, β is a matching degree weight, and γ is a topic difficulty coefficient.

Target topic difficulty factor

The calculation formula of (a) is as follows:

wherein gamma is the matching degree coefficient of the answer and gamma is epsilon (0, 1), i is the number of the question, s is the score of each question,

a target topic difficulty coefficient;

if the score of the first topic is 70 points, calculating by using a first calculation formula in the calculation formulas of the target topic difficulty coefficients to obtain a target topic difficulty coefficient; and if the score of the first topic is 50 points, calculating by using a second calculation formula in the calculation formula of the target topic difficulty coefficient to obtain the target topic difficulty coefficient.

And after the second question is answered, selecting the next question in sequence according to the answer result of the previous question until the preset number of questions are selected.

In this embodiment, the interview equipment 10b generates an interview result of the job-seeking user according to the answer result of the question. One way to implement this is to calculate the total score of all the questions of the job-seeking user according to the score of each question; if the total scores of all the questions of the job hunting user are larger than or equal to the total score threshold value, generating a result of interviewing passing of the job hunting user; and if the total score of all the questions of the job hunting user is smaller than the total score threshold, generating a result that the interview of the job hunting user fails.

The interview equipment 10b compares the answer result of each question with the corresponding standard answer, calculates the score of each question, and can calculate the score of the question according to the existing matching degree calculation formula. The interviewing device 10b uses the total score of the job hunting user as the job matching degree between the job hunting user and the applicable job, and optionally calculates the total score m of the job hunting user according to the capability matching degree coefficient δ, the matching degree weight β, the topic difficulty coefficient γ, and the score of each topic, and the calculation formula is as follows:

wherein k is the total number of questions, and i is each question;

weight of degree of match

Wherein α is the distance between each node;

after calculating the total score of the job hunting users, if the total score of the job hunting users is greater than or equal to the total score threshold, the interview equipment 10b generates a result that the job hunting users interview; and if the total score of the job hunting users is smaller than the total score threshold, generating a result that the interview of the job hunting users fails. It should be noted that, the total score threshold is not limited in the embodiments of the present application, and the total score threshold may be adjusted according to actual situations. For example, the total score threshold is 60 points, and if the total score of the job hunting users is 70 points, a result that the job hunting users have interviewed is generated, and if the total score of the job hunting users is 30 points, a result that the job hunting users have not interviewed is generated.

The technical solution of the present application is described in the following example of a pilot process:

resume texts of job hunting user A and job hunting user B can be obtained through resume recognition as shown in Table 1:

TABLE 1

The following understanding results can be obtained through the resume content understanding model as shown in Table 2

TABLE 2

Through analysis of the model on two job hunting users, a first round of topic table 3 is obtained (only partial topics are in the table):

TABLE 3

The process of the job hunting user A for answering the questions is as follows:

the interview apparatus 1 Python has which data structures.

Job hunting user a: int, float, str …

Interview equipment-how to convert int type data into str type. (δ =0.8, β =0.5, γ = 0.3)

……

Interview equipment how git submitted the code.

Job hunting user A, git add, git commit … …

The job hunting user A answers the two questions, and the job hunting user B answers the three questions. The contents are as in table 4 (only partial answer example in table):

TABLE 4

The scoring results for each topic for job hunting user a and job hunting user B are shown in table 5: (score of only a part of subjects in the table)

TABLE 5

According to the calculation, the following results are obtained:

mA=0.8*0.5*0.3*100+0.6*0.5*0.4*100+0.7*0.5*0.5*100+0.4*0.6*0.4*60+0.3*0.6*0.46*100+0.7*0.6*0.56*40+0.4*0.5*0.4*100+0.364*0.5*0.5*100 =82；

mB=0.1*0.1*0.3*100+0.1*0.1*0.4*100+0.1*0.1*0.5*100+0.8*0.5*0.7*30+0.6*0.5*0.67*80+0.5*0.5*0.75*10+0.5*0.2*0.5*10+0.1*0.2*0.49*15+0.7*0.2*0.505*20=29.616；

the job hunting user a scores 82 points. As can be seen, job hunting user A scores 82 and passes interviews, while job hunting user B scores 29.616 and fails interviews.

In the system embodiment of the application, the intelligent interview device acquires a resume text and a job description text of a job hunting user; extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; the intelligent interviewing device extracts the application positions of the job hunting users from the position description text; the intelligent interviewing device selects a question from a preset question bank according to the capability label and the engaging position of the job hunting user, selects a question matched with the personal capability and the engaging position of the job hunting user to conduct an interviewing process, reasonably evaluates the capability of the job hunting user, and improves the accuracy of capability evaluation of the job hunting user.

In addition to the intelligent interview system 10 provided above, some embodiments of the present application also provide an intelligent interview method, which can be applied to the intelligent interview system 10, but is not limited to the intelligent interview system 10 provided in the above embodiments. Fig. 3 is a flowchart illustrating a method for topic processing according to an exemplary embodiment of the present application. As shown in fig. 3, the method includes:

s301: acquiring a resume text and a job description text;

s302: extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; and

s303: extracting the application positions of the job hunting users from the position description text;

s304: and selecting a topic from a preset topic library according to the capability label and the application position of the job hunting user.

In this embodiment, the interview device as the execution subject of the method may be an intelligent terminal device or a server, and when the interview device is a server, the implementation form of the server is not limited in this embodiment, and the server may be a conventional server, a cloud host, a virtual center, or other server devices. The server device mainly includes a processor, a hard disk, a memory, a system bus, and the like, and is similar to a general computer architecture.

In this embodiment, a job hunting user uploads an electronic resume by using a job hunting user terminal, and after receiving a resume text and a job description text, an interview device extracts keywords according to the resume text and the job description text to obtain a capability tag of the job hunting user; the interviewing equipment selects a question from a preset question bank according to the capability label and the job position of the job hunting user; the interviewing equipment provides the questions for job hunting users so that the job hunting users can answer the questions; the interview equipment generates interview results of job hunting users according to the acquired answer results of the job hunting users for the questions; the interview equipment sends the interview result to the interviewer terminal; and after receiving the interview result, the interview officer terminal displays the interview result on an electronic display screen of the interview officer terminal for the interview officer to check.

In this embodiment, the interview equipment extracts keywords according to the resume text and the job description text to obtain the capability tag of the job hunting user. In one implementation, the interview equipment inputs the resume text and the job description text into an existing resume content understanding model to obtain the capability labels of the job hunting users. For example, the resume text "1, proficient Python, is proficient at list, tuple, set operations. 2. And when the Git is used skillfully, codes and job description texts can be submitted, deleted and combined, and the codes and the job description texts are input into an existing resume content understanding model to obtain capability labels 'proficient Python' and 'skillful use Git' of the job hunting user.

In this embodiment, the interview equipment extracts the application positions of the job hunting users from the position description text. One way to implement this is that the interviewing equipment can search for the keyword "job application position" and take the text content after the "job application position" as the job application position.

In another embodiment, if the electronic resume is of a picture type, the interview equipment extracts keywords from the resume text and the job description text to obtain a capability label of the job hunting user, and one realizable mode is that the interview equipment detects the resume text region of the electronic resume to obtain a resume region picture; the interview equipment performs text recognition on the resume area picture to obtain a resume text; and inputting the resume text and the job description text into an existing resume content understanding model to obtain the capability label of the job hunting user. Optionally, the interview equipment performs resume text region detection on the electronic resume by using the text detection model to obtain a resume region picture; and the interviewing equipment performs text recognition on the resume area picture by using the text recognition model to obtain a resume text. For example, the interview equipment utilizes a text detection model to perform resume text region detection on the electronic resume to obtain a text containing '1', proficient Python development and better understand multithreading and corollary. 2. Familiar web development frameworks such as: django, Tornado, flash, familiar with the design idea of object-oriented, have knowledge of the common design mode "resume area pictures; the interview equipment performs text recognition on the resume area picture by using a text recognition model to obtain a resume text: "1" is developed by Python, and has better understanding on multithreading and coroutine. 2. Familiar web development frameworks such as: django, Tornado, flash, familiar with object-oriented design ideas, and known about common design patterns. And b, converting the resume text: "1" is developed by Python, and has better understanding on multithreading and coroutine. 2. Familiar web development frameworks such as: django, Tornado and Flask are familiar with the design idea of object-oriented design and know the common design mode. "inputting resume content understanding model with job description text to obtain capability label of job seeking user" 1, mastered Python development, 2, mastered Django, flash frame and rest mode ".

In the above embodiment, the interview apparatus 10b selects a topic from the preset topic library based on the capability tag and the job position of the job hunting user. One way to realize the job hunting is to select a first topic from a preset topic library according to the capability label and the job position of the job hunting user; outputting a first question; responding to the answering information of the job hunting user aiming at the first question, and calculating the answering result of the first question; selecting a second question from a preset question bank according to the answer result of the first question; and sequentially executing the selection of the subsequent topics until the selection of the preset number of topics is completed.

It should be noted that the knowledge graph includes sub-graphs corresponding to a plurality of capability labels, each sub-graph includes a corresponding capability label node and a knowledge point node connected to the capability label node, and a connection relationship between the capability label node and the knowledge point node indicates that an association relationship exists between a capability label corresponding to the capability label node and a knowledge point corresponding to the knowledge point node. Capability label nodes include, but are not limited to: the Python foundation is skillfully used by Python, mastered Git, skillfully used by Git, mastered flash frame, skillfully used by flash frame and other root nodes. For example, as shown in fig. 2, a subgraph corresponding to the capability label "Python basis" includes: the system comprises a Numpy node, a Pandas node, a Flask frame node, a Djago frame node and a basic grammar node, wherein the nodes are connected with a Python basic node, and the Pandas node comprises a CSV processing sub-node and an Excel processing sub-node.

In the above embodiment, the interview equipment selects a question from the preset question bank according to the ability label and the job application position of the job hunting user. One way to realize the method is to search a target knowledge point node connected with a capability label node corresponding to a capability label from an existing interview knowledge graph, wherein the interview knowledge graph comprises the capability label node and a knowledge point node connected with the capability label node, and the connection relation between the capability label node and the knowledge point node indicates that the capability label corresponding to the capability label node has an association relation with the knowledge point corresponding to the knowledge point node; according to the level of the applicable position, inquiring a mapping relation table of the level of the applicable position and the capacity matching degree coefficient to obtain a target capacity matching degree coefficient, wherein each question carries the capacity matching degree coefficient; and randomly selecting a question with a target capability matching degree coefficient from the sub-question banks corresponding to the target knowledge point nodes, wherein the preset question bank comprises a plurality of sub-question banks corresponding to the plurality of knowledge point nodes one by one.

The interview equipment selects a first topic from a preset topic library according to the capability label and the job application position of the job hunting user. One way to implement is that the interview equipment searches the target knowledge point nodes connected with the capability label nodes corresponding to the capability labels from the existing interview knowledge graph; according to the level of the applicable position, inquiring a mapping relation table of the level of the applicable position and the capacity matching degree coefficient to obtain a target capacity matching degree coefficient, wherein each question carries the capacity matching degree coefficient; and randomly selecting a first topic with the capability matching degree coefficient as the target capability matching degree coefficient from the sub-topic library corresponding to the target knowledge point node, wherein the preset topic library comprises a plurality of sub-topic libraries corresponding to a plurality of knowledge point nodes one by one. Optionally, according to the level of the employment position, inquiring a mapping relation table of the level of the employment position and the capability matching degree coefficient to obtain a plurality of candidate capability matching degree coefficients; and selecting a target capability matching degree coefficient meeting a preset matching degree condition from the plurality of candidate capability matching degree coefficients.

In one embodiment, the interview equipment plays a first question to a job seeking user in a voice mode, the job seeking user answers in the voice mode, the interview equipment collects answering voices of the job seeking user for the question, matching degree calculation is carried out on answer texts of the first question and corresponding standard answers, and scores of the first question are obtained and serve as answer results of the first question.

In the above embodiment, the interview equipment selects the second question from the preset question bank according to the answer result of the first question. One way to realize the method is that the interview equipment determines a target question difficulty coefficient of a second question according to the answer result of a first question, wherein each question carries a question difficulty coefficient; judging whether the question with the target question difficulty coefficient exists in a sub-question bank where the first question is located; if so, selecting a topic with a target topic difficulty coefficient from a sub-topic library in which the first topic is located, and taking the topic as a second topic; and if not, randomly selecting a second topic with the target topic difficulty coefficient from other topic libraries, wherein the other topic libraries are the residual topic libraries except the topic library where the first topic is located in all the topic libraries corresponding to all the target knowledge point nodes corresponding to the capability labels of the job-seeking users.

And the interviewing equipment selects a second question from a preset question bank according to the answer result of the first question. One way to realize the method is to determine a target question difficulty coefficient of a second question according to the answering result of a first question, wherein each question carries a question difficulty coefficient; judging whether the question with the target question difficulty coefficient exists in a sub-question bank where the first question is located; if so, selecting a topic with a target topic difficulty coefficient from a sub-topic library in which the first topic is located, and taking the topic as a second topic; and if not, randomly selecting a second topic with the target topic difficulty coefficient from other topic libraries, wherein the other topic libraries are the residual topic libraries except the topic library where the first topic is located in all the topic libraries corresponding to all the target knowledge point nodes corresponding to the capability labels of the job-seeking users.

Optionally, the interview equipment determines the target question difficulty coefficient of the second question according to the answer result of the question of the job hunting user in the first turn. One way to achieve this is to determine whether the score of the first topic is greater than or equal to a set score threshold; if yes, calculating a target subject difficulty coefficient of a second subject in a first mode according to the subject difficulty coefficient of the first subject and the score of the first subject, wherein the target subject difficulty coefficient is larger than the subject difficulty coefficient of the first subject; and if not, calculating a target topic difficulty coefficient of a second topic in a second calculation mode according to the topic difficulty coefficient of the first topic and the score of the first topic, wherein the target topic difficulty coefficient is smaller than the topic difficulty coefficient of the first topic.

In this embodiment, the interview equipment generates interview results of job hunting users according to answer results of the questions. One way to implement this is to calculate the total score of all the questions of the job-seeking user according to the score of each question; if the total scores of all the questions of the job hunting user are larger than or equal to the total score threshold value, generating a result of interviewing passing of the job hunting user; and if the total score of all the questions of the job hunting user is smaller than the total score threshold, generating a result that the interview of the job hunting user fails.

The interview equipment compares the answer result of each question with the corresponding standard answer, calculates the score of each question, and can calculate the score of the question according to the existing matching degree calculation formula. The interviewing equipment takes the total score of the job hunting users as the job position matching degree of the job hunting users and the applicable job positions, and optionally calculates the total score m of the job hunting users according to the capability matching degree coefficient delta, the matching degree weight beta, the topic difficulty coefficient gamma and the score of each topic, wherein the calculation formula is as follows:

wherein k is the total number of questions, and i is each question;

weight of degree of match

Wherein α is the distance between each node;

after the interview equipment calculates and obtains the total score of the job hunting users, if the total score of the job hunting users is larger than or equal to a total score threshold value, generating an interview passing result of the job hunting users; and if the total score of the job hunting users is smaller than the total score threshold, generating a result that the interview of the job hunting users fails. It should be noted that, the total score threshold is not limited in the embodiments of the present application, and the total score threshold may be adjusted according to actual situations. For example, the total score threshold is 60 points, and if the total score of the job hunting users is 70 points, a result that the job hunting users have interviewed is generated, and if the total score of the job hunting users is 30 points, a result that the job hunting users have not interviewed is generated.

Based on the description of the above embodiments, fig. 4 is a schematic flow chart of another intelligent interview method provided in the embodiments of the present application. As shown in fig. 4, the method includes:

s401: acquiring a resume text and a job description text of a job hunting user;

s402: extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user;

s403: extracting the application positions of the job hunting users from the position description text;

s404: selecting a question from a preset question bank according to the capability label and the engaging position of the job hunting user;

s405: playing the title to the job hunting user in a voice mode;

s406, collecting the answering voice of job hunting users for the question;

s407: and generating an interview result of the job hunting user according to the answering voice.

In this embodiment, the implementation manner of each step of this embodiment can refer to the description of each embodiment, which is not described herein again.

In the method embodiment of the application, the intelligent interview device acquires a resume text and a job description text of a job hunting user; extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; the intelligent interviewing device extracts the application positions of the job hunting users from the position description text; the intelligent interviewing device selects a question from a preset question bank according to the capability label and the engaging position of the job hunting user, selects a question matched with the personal capability and the engaging position of the job hunting user to conduct an interviewing process, reasonably evaluates the capability of the job hunting user, and improves the accuracy of capability evaluation of the job hunting user.

Fig. 5 is a schematic structural diagram of an intelligent interview apparatus 50 according to an embodiment of the present disclosure. As shown in fig. 5, the intelligent interview apparatus 50 includes: an acquisition module 51, a first extraction module 52, a second extraction module 53 and a selection module 54.

An obtaining module 51, configured to obtain a resume text and a job description text;

the first extraction module 52 is configured to perform keyword extraction according to the resume text and the job description text to obtain a capability tag of the job hunting user; and

the second extraction module 53 is configured to extract an application position of the job hunting user from the position description text;

and the selecting module 54 is configured to select a topic from a preset topic library according to the capability tag and the job position of the job hunting user.

Optionally, a generating module 55 is further included;

and the generating module 55 is configured to generate an interview result of the job hunting user according to the answer result of the job hunting user for the question, where the answer result of the question is calculated according to the acquired answer information of the job hunting user for each question.

Optionally, when selecting a topic from a preset topic library according to the capability tag and the job position of the job hunting user, the selecting module 54 is specifically configured to:

selecting a first topic from a preset topic library according to the capability label and the engaging position of the job hunting user;

outputting the first title;

responding to the answer information of the job hunting user for the first question, and obtaining an answer result of the first question after judging the question;

selecting a second question from a preset question bank according to the answer result of the first question;

and sequentially executing the selection of the subsequent topics until the selection of the preset number of topics is completed.

Optionally, the selecting module 54 is specifically configured to, when selecting a question from the preset question bank according to the capability label and the job position of the job hunting user:

searching a target knowledge point node connected with a capability label node corresponding to a capability label from an existing interview knowledge graph, wherein the interview knowledge graph comprises the capability label node and a knowledge point node connected with the capability label node, and the connection relation between the capability label node and the knowledge point node indicates that the capability label corresponding to the capability label node has an association relation with the knowledge point corresponding to the knowledge point node; and

according to the level of the employment position, inquiring a mapping relation table of the level of the employment position and the capability matching degree coefficient to obtain a target capability matching degree coefficient, wherein each question carries the capability matching degree coefficient;

and randomly selecting a question with a target capability matching degree coefficient from the sub-question banks corresponding to the target knowledge point nodes, wherein the preset question bank comprises a plurality of sub-question banks corresponding to the plurality of knowledge point nodes one by one.

Optionally, the selecting module 54 is specifically configured to, when the mapping relationship table between the level of the employment position and the capability matching degree coefficient is queried according to the level of the employment position to obtain the target capability matching degree coefficient:

according to the level of the employment position, inquiring a mapping relation table of the level of the employment position and the capability matching degree coefficient to obtain a plurality of candidate capability matching degree coefficients;

and selecting a target capability matching degree coefficient meeting a preset matching degree condition from the plurality of candidate capability matching degree coefficients.

Optionally, when the second question is selected from the preset question bank according to the answer result of the first question, the selecting module 54 is specifically configured to:

determining a target question difficulty coefficient of a second question according to the answering result of the first question, wherein each question carries a question difficulty coefficient;

judging whether the question with the target question difficulty coefficient exists in a sub-question bank where the first question is located;

if so, selecting a topic with a target topic difficulty coefficient from a sub-topic library in which the first topic is located, and taking the topic as a second topic;

and if not, randomly selecting a second topic with the target topic difficulty coefficient from other topic libraries, wherein the other topic libraries are the residual topic libraries except the topic library where the first topic is located in all the topic libraries corresponding to all the target knowledge point nodes corresponding to the capability labels of the job-seeking users.

Optionally, the selecting module 54 is specifically configured to, when determining the target topic difficulty coefficient of the second topic according to the answer result of the first topic:

judging whether the score of the first track of subject is larger than or equal to a set score threshold value, wherein the score of the first track of subject is used as the answer result of the first track of subject;

if yes, calculating a target subject difficulty coefficient of a second subject in a first mode according to the subject difficulty coefficient of the first subject and the score of the first subject, wherein the target subject difficulty coefficient is larger than the subject difficulty coefficient of the first subject;

and if not, calculating a target topic difficulty coefficient of a second topic in a second calculation mode according to the topic difficulty coefficient of the first topic and the score of the first topic, wherein the target topic difficulty coefficient is smaller than the topic difficulty coefficient of the first topic.

Optionally, the generating module 55, when responding to the answer information of the job-seeking user for the first topic, is specifically configured to:

and calculating the matching degree of the answer information of the first question and the corresponding standard answer to obtain the score of each question as the answer result of the first question.

Optionally, when the generating module 55 outputs the first track of title, it is specifically configured to:

playing a first title to a job hunting user in a voice mode;

responding to the answer information of the job hunting user aiming at the first question, calculating the answer result of the first question, and comprising the following steps:

collecting answering voice of a first question answered by a job hunting user in a voice mode;

and performing text conversion on the answer voice of the first question to obtain an answer text of the first question, and performing matching degree calculation on the answer text of the first question and a corresponding standard answer to obtain a score of the first question as an answer result of the first question.

Optionally, the first extracting module 52 is specifically configured to, when extracting the keyword according to the resume text and the job description text to obtain the capability tag of the job hunting user:

and inputting the resume text and the job description text into an existing resume content understanding model to obtain the capability label of the job hunting user.

Optionally, the answer result of the question is a score of the question, and the generating module 55 is specifically configured to, when generating an interview result of the job-seeking user according to the answer result of the question:

calculating the total scores of all the questions of the job seeking user according to the score of each question;

if the total scores of all the questions of the job hunting user are larger than or equal to the total score threshold value, generating a result of interviewing passing of the job hunting user;

and if the total score of all the questions of the job hunting user is smaller than the total score threshold, generating a result that the interview of the job hunting user fails.

The apparatus shown in fig. 5 can execute the intelligent interview method provided by the foregoing embodiments, and reference may be made to the related description of the foregoing embodiments for a part of this embodiment that is not described in detail. The implementation process and technical effect of the technical solution can be referred to the description in the foregoing embodiments, and are not described herein again.

An exemplary embodiment of the present disclosure also provides an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor. The memory stores a computer program executable by the at least one processor, the computer program, when executed by the at least one processor, is for causing the electronic device to perform a method according to an embodiment of the present disclosure.

The disclosed exemplary embodiments also provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is for causing the computer to perform a method according to an embodiment of the present disclosure.

The exemplary embodiments of the present disclosure also provide a computer program product comprising a computer program, wherein the computer program, when being executed by a processor of a computer, is adapted to cause the computer to carry out the method according to the embodiments of the present disclosure.

Referring to fig. 6, a block diagram of a structure of an electronic device 600, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The calculation unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the electronic device 600 are connected to the I/O interface 605, including: an input unit 606, an output unit 607, a storage unit 608, and a communication unit 609. The input unit 606 may be any type of device capable of inputting information to the electronic device 600, and the input unit 606 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device. Output unit 607 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. Storage unit 604 may include, but is not limited to, magnetic or optical disks. The communication unit 609 allows the electronic device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and/or a chipset, such as a bluetooth (TM) device, a WiFi device, a WiMax device, a cellular communication device, and/or the like.

The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 601 performs the respective methods and processes described above. For example, in some embodiments, the aforementioned intelligent interview methods can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 600 via the ROM 602 and/or the communication unit 609. In some embodiments, the computing unit 601 may be configured to perform the above-described intelligent interview method in any other suitable manner (e.g., by means of firmware).

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

In the device and storage medium embodiment of the application, the intelligent interview device acquires a resume text and a job description text of a job hunting user; extracting keywords according to the resume text and the job description text to obtain a capability label of the job hunting user; the intelligent interviewing device extracts the application positions of the job hunting users from the position description text; the intelligent interviewing device selects a question from a preset question bank according to the capability label and the engaging position of the job hunting user, selects a question matched with the personal capability and the engaging position of the job hunting user to conduct an interviewing process, reasonably evaluates the capability of the job hunting user, and improves the accuracy of capability evaluation of the job hunting user.

Claims

1. An intelligent interview method comprising:

acquiring a resume text and a job description text;

2. The method of claim 1, wherein after selecting a topic from a preset topic library based on the capability tags and the job positions of the job hunting users, the method further comprises:

and generating an interview result of the job hunting user according to the answering result of the job hunting user aiming at the question, wherein the answering result of the question is obtained after the acquired answering information of the job hunting user aiming at the question is judged.

3. The method of claim 1, wherein selecting a topic from a preset topic library based on the capability tag and the job position of the job hunting user comprises:

outputting the first title;

4. The method of claim 1, wherein selecting a topic from a predetermined topic library based on the competency label and the job position of the job hunting user comprises:

searching a target knowledge point node connected with the capability label node corresponding to the capability label from an existing interview knowledge graph, wherein the interview knowledge graph comprises the capability label node and a knowledge point node connected with the capability label node, and the connection relation between the capability label node and the knowledge point node indicates that the capability label corresponding to the capability label node has an association relation with the knowledge point corresponding to the knowledge point node; and

and randomly selecting a question with the target capability matching degree coefficient from the sub-question banks corresponding to the target knowledge point nodes, wherein the preset question bank comprises a plurality of sub-question banks corresponding to the plurality of knowledge point nodes one by one.

5. The method of claim 4, wherein the step of querying a mapping relationship table between the level of the employment position and the capability matching degree coefficient according to the level of the employment position to obtain the target capability matching degree coefficient comprises:

6. The method of claim 3, wherein selecting a second question from the predetermined question bank according to the answer result of the first question comprises:

and if not, randomly selecting a second topic with the target topic difficulty coefficient from other topic libraries, wherein the other topic libraries are the rest topic libraries except the topic library where the first topic is located in all the topic libraries corresponding to all the target knowledge point nodes corresponding to the capability tag of the job-seeking user.

7. The method of claim 6, wherein determining the target topic difficulty coefficient for the second topic according to the answer result of the first topic comprises:

8. The method of claim 3, wherein calculating the answer result of the first topic in response to the answer information of the job-seeking user for the first topic comprises:

and calculating the matching degree of the answer information of the first question and the corresponding standard answer to obtain the score of the first question as the answer result of the first question.

9. The method of claim 3, outputting a first track topic, comprising:

playing the first title to a job hunting user in a voice mode;

collecting answering voice of a first question answered by the job hunting user in a voice mode;

10. The method of claim 1, wherein extracting keywords from the resume text and the job description text to obtain a capability tag of the job hunting user comprises:

11. The method of claim 2, wherein the answer result of the question is a score of the question, and the generating of the interview result of the job-seeking user according to the answer result of the question comprises:

if the total scores of all the questions of the job hunting user are larger than or equal to a total score threshold value, generating a result of interviewing passing of the job hunting user;

and if the total score of all the questions of the job hunting user is smaller than a total score threshold value, generating a result that the interview of the job hunting user fails.

12. An intelligent interview apparatus comprising:

13. An electronic device, comprising:

a processor; and

a memory for storing a program, wherein the program is stored in the memory,

wherein the program comprises instructions which, when executed by the processor, cause the processor to carry out the method according to any one of claims 1-11.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1-11.