Video interview method, system, electronic device, and storage medium

Abstract

The present application relates to the online interview technical field, provide a kind of video interview method, system, electronic equipment and storage medium.The video interview method includes: in response to interview request, obtain post information and selected time period;From teacher information base, obtain the teaching data that is matched with post information and the non-course scheduling time period that is overlapped with selected time period several teacher accounts;From the several teacher accounts obtained, determine a teacher account as interviewer, and determine interview time period according to the non-course scheduling time period of interviewer and selected time period;And create interactive virtual space, the entry interface of interactive virtual space is pushed to the first terminal of initiating interview request and the second terminal of interviewer, and interactive virtual space is configured to establish the video communication between the first terminal and the second terminal in interview time period.The present application can alleviate the interview pressure of educational institution, match to suitable interviewer for each interview, improve the interview experience of interviewee, strengthen the interview effect of both sides.

Description

Technical Field

[0001] This invention relates to the field of online interview technology, and more specifically, to a video interview method, system, electronic device, and storage medium. Background Technology

[0002] The online education industry has a high demand for online teaching consultants. These consultants are mainly responsible for answering users' questions while browsing web pages, assisting teachers in delivering lessons, and helping students complete course-related tasks.

[0003] The surge in demand for online teaching consultants has led to a significant increase in interview pressure for educational institutions. Since the number of teaching supervisors responsible for interviews is very small within these institutions, coordinating the schedules of numerous job seekers and managing multiple time commitments makes rapid and efficient recruitment difficult. For job seekers, traveling to educational institutions for interviews also incurs substantial transportation costs.

[0004] Therefore, to alleviate interview pressure and improve convenience for both recruiters and job seekers, online interviews have gradually developed. However, current online interviews still have significant shortcomings in achieving rapid and effective recruitment and improving the interview experience, mainly in the following three aspects.

[0005] Firstly, most current online interviews are conducted using machines, which select interview questions from a pre-set question bank based on surveys and analyses of job seekers. This type of online interview is rather rigid and makes it difficult to engage in meaningful communication based on the progress of the interview, resulting in poor interview outcomes.

[0006] Secondly, in online interviews where both parties interact, it is difficult to match each job seeker with a suitable interviewer. As mentioned above, if the interviews are conducted by the teaching director, it requires coordination between the director and a large number of job seekers, which still cannot alleviate the interview pressure. If the interviews are not conducted by the teaching director, it is difficult to select an interviewer suitable for each interview, which affects the interview results.

[0007] Thirdly, current online interviews only provide a simple platform for both parties to communicate online, which cannot improve the interview experience or enhance the interview effect.

[0008] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0009] In view of this, the present invention provides a video interview method, system, electronic device and storage medium, which can alleviate the interview pressure of educational institutions, match a suitable interviewer for each interview, improve the interview experience of interviewees, and enhance the interview effect for both parties.

[0010] One aspect of the present invention provides a video interview method, comprising the steps of: in response to an interview request, obtaining job information and a selected time period; obtaining from a teacher information database a plurality of teacher accounts whose teaching data matches the job information and whose non-scheduled time periods overlap with the selected time period; determining one teacher account from the obtained plurality of teacher accounts as the interviewer, and determining an interview time period based on the interviewer's non-scheduled time period and the selected time period; and creating an interactive virtual space, pushing the entry interface of the interactive virtual space to a first terminal that initiated the interview request and a second terminal of the interviewer, wherein the interactive virtual space is configured to establish video communication between the first terminal and the second terminal during the interview time period.

[0011] In some embodiments, the video interview method further includes the steps of: detecting the body movements of the interviewee corresponding to the first terminal in the video stream of the interactive virtual space; and pushing reminder information to the first terminal based on the comparison between the detected body movements and preset body movements.

[0012] In some embodiments, the body movements include eye movements and hand gestures. The step of pushing reminder information to the first terminal includes: when the eye movement detection determines that the matching degree between the interviewee's eye gaze point and the target gaze area is less than a preset value, pushing a first reminder message indicating eye movement adjustment to the first terminal; when the hand gesture detection determines that the matching degree between the interviewee's hand gesture and a preset hand gesture triggers a reminder condition, pushing a second reminder message indicating hand gesture adjustment to the first terminal.

[0013] In some embodiments, the preset gesture actions include a gesture action whitelist and a gesture action blacklist, and the reminder condition is: the matching degree between the gesture action and the gesture action whitelist is less than a first preset value, or the matching degree between the gesture action and the gesture action blacklist is greater than a second preset value.

[0014] In some embodiments, the video interview method further includes the steps of: detecting whether there is a third person's image in the video stream of the interactive virtual space, other than the interviewee corresponding to the first terminal and the interviewer corresponding to the second terminal; if so, blurring the image of the third person so that the area corresponding to the image of the third person in the real-time interview video transmitted to the first terminal and the second terminal is blurred.

[0015] In some embodiments, the video interview method further includes the steps of: detecting whether there is a third person's voice in the video stream of the interactive virtual space, other than the interviewee corresponding to the first terminal and the interviewer corresponding to the second terminal; if so, weakening the third person's voice so that the content corresponding to the third person's voice in the real-time interview video transmitted to the first terminal and the second terminal is weakened.

[0016] In some embodiments, the video interview method further includes the step of: responding to a drag operation command from the first terminal, moving and scaling the real-time interview video of the interviewee and the real-time interview video of the interviewer displayed on the first terminal to the area indicated by the drag operation command, so that the real-time interview video of the interviewee and the real-time interview video of the interviewer are tiled or overlaid on the interview interface of the first terminal.

[0017] In some embodiments, the video interview method further includes the step of: in response to a new operation instruction from the second terminal, pushing the entry interface of the interactive virtual space to a third terminal of the reviewer indicated by the new operation instruction, wherein the reviewer is a teacher account in the teacher information database with greater interview privileges than the interviewer.

[0018] In some embodiments, the video interview method further includes the steps of: after the interactive virtual space is closed, generating an interactive interview video based on the real-time interview video of the interviewee recorded by the first terminal and the real-time interview video of the interviewer recorded by the second terminal, so that the real-time interview video of the interviewee and the real-time interview video of the interviewer in the interactive interview video are played synchronously in split screen; and pushing the interactive interview video to a third terminal of an auditor, wherein the auditor is a teacher account in the teacher information database with greater interview privileges than the interviewer.

[0019] In some embodiments, before the step of pushing the interactive interview video to the third terminal of the reviewer, the method further includes the following steps: segmenting the interactive interview video based on sound features to form multiple video segments, wherein the effective audio content of each video segment corresponds to a speaker, and the speaker is the interviewee or the interviewer; according to the keywords of each video segment, sequentially pairing adjacent video segments with matching keywords to form multiple sets of dialogue segments between the interviewer and the interviewee; wherein each set of dialogue segments can be played individually.

[0020] In some embodiments, after the step of forming multiple sets of dialogue segments between the interviewer and the interviewee, the method further includes the steps of: matching the keywords of each set of dialogue segments with preset keywords of the job information; obtaining dialogue segments that match the preset keywords and whose speaking time is longer than that of the interviewer, and marking them with a first tag; obtaining dialogue segments that do not match the preset keywords and / or whose speaking time is shorter than that of the interviewer, and marking them with a second tag.

[0021] In some embodiments, the video interview method further includes the steps of: obtaining a first interview score from the second terminal and a second interview score from the third terminal; and obtaining an interview result based on the first interview score and the second interview score.

[0022] In some embodiments, the step of determining a teacher account as an interviewer from the obtained teacher accounts includes: generating an interview matching score for each teacher account based on the teacher account's historical teaching scores and historical interview scores; and determining the teacher account with the highest interview matching score as the interviewer.

[0023] Another aspect of the present invention provides a video interview system applied to the video interview method described in any of the above embodiments. The video interview system includes: an interview request response module, used to respond to an interview request and obtain job information and a selected time period; an interview teacher screening module, used to obtain from a teacher information database a plurality of teacher accounts whose teaching data matches the job information and whose non-scheduled time periods overlap with the selected time period; an interview information determination module, used to determine one teacher account as the interviewer from the plurality of teacher accounts obtained, and determine the interview time period based on the interviewer's non-scheduled time period and the selected time period; and a virtual space creation module, used to create an interactive virtual space, push the entry interface of the interactive virtual space to a first terminal that initiated the interview request and a second terminal of the interviewer, and configure the interactive virtual space to establish video communication between the first terminal and the second terminal during the interview time period.

[0024] Another aspect of the present invention provides an electronic device comprising: a processor; a memory storing executable instructions of the processor; wherein the processor is configured to perform the steps of the video interview method described in any of the above embodiments by executing the executable instructions.

[0025] Another aspect of the present invention provides a computer-readable storage medium for storing a program, which, when executed, implements the steps of the video interview method described in any of the above embodiments.

[0026] The beneficial effects of this invention compared to the prior art include at least the following:

[0027] By filtering teacher accounts from the teacher information database that match teaching data with job information in interview requests and whose non-scheduled time slots overlap with the selected time slots in interview requests, each interview request is matched with a teacher who is suitable and available to be an interviewer, thus achieving effective and targeted interviews without waiting for the teaching supervisor and alleviating the interview pressure on educational institutions.

[0028] By establishing video communication between the interviewee's primary terminal and the interviewer's secondary terminal through an interactive virtual space, the interviewee and interviewer can achieve good interview interaction through the interactive virtual space, improve the interviewee's interview experience, and enhance the interview effect for both parties.

[0029] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0031] Figure 1 This diagram illustrates the steps of the video interview method in an embodiment of the present invention.

[0032] Figure 2 This illustration shows a scenario of creating an interactive virtual space between a first terminal and a second terminal in an embodiment of the present invention.

[0033] Figure 3 This diagram illustrates the interface for pushing a first reminder message to a first terminal in an embodiment of the present invention.

[0034] Figure 4 This diagram illustrates the interface for pushing a second reminder message to a first terminal in an embodiment of the present invention.

[0035] Figure 5 This diagram illustrates the interface responding to a drag operation command from a first terminal in an embodiment of the present invention.

[0036] Figure 6 This diagram illustrates an interface for pushing interactive interview videos to a third terminal in an embodiment of the present invention.

[0037] Figure 7 This diagram illustrates the modules of the video interview system in an embodiment of the present invention.

[0038] Figure 8 A schematic diagram of the structure of an electronic device in an embodiment of the present invention is shown; and

[0039] Figure 9 A schematic diagram of the structure of a computer-readable storage medium in an embodiment of the present invention is shown. Detailed Implementation

[0040] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to fully and completely convey the concept of the exemplary embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore repeated descriptions of them will be omitted.

[0041] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0042] The step numbers in the following method embodiments are only used to indicate different execution contents and do not limit the logical relationship and execution order between steps.

[0043] Figure 1 The main steps of the video interview method in the embodiment are shown below, with reference to Figure 1 As shown, the video interview method in this embodiment mainly includes: in step S110, in response to an interview request, obtaining job information and a selected time period; in step S120, obtaining several teacher accounts from the teacher information database whose teaching data matches the job information and whose non-scheduled time periods overlap with the selected time period; in step S130, determining one teacher account as the interviewer from the obtained teacher accounts, and determining the interview time period based on the interviewer's non-scheduled time period and the selected time period; and in step S140, creating an interactive virtual space, pushing the entry interface of the interactive virtual space to the first terminal that initiated the interview request and the second terminal of the interviewer, and configuring the interactive virtual space to establish video communication between the first terminal and the second terminal during the interview time period.

[0044] In step S110, the interview request is initiated by the interviewee through their primary terminal. To alleviate interview pressure, educational institutions can provide online interview options and time slot options on the recruitment pages for positions suitable for online interviews. When the interviewee selects one or more time slots from the online interview options and time slot options and submits, the educational institution's server (hereinafter referred to as the interview server) receives the interview request carrying job information and the selected time slot.

[0045] In step S120, the teacher information database is a pre-stored database in the interview server covering all teaching staff in the educational institution, including teaching supervisors and instructors. Both teaching supervisors and instructors are stored as teacher accounts in the database. Each instructor's account stores teaching data and class schedules. Teaching supervisors have greater interview privileges than instructors. By filtering teacher accounts from the database whose teaching data matches the job information and whose non-scheduled time slots overlap with the selected time slots, each interview request is matched with a suitable instructor who is available on time. This enables effective, targeted interviews without waiting for teaching supervisors, alleviating the interview pressure on educational institutions.

[0046] Matching teaching data with job information: For example, if the job information corresponds to a less commonly taught language, then teaching data containing content related to that language will be matched. Similarly, if the job information includes a required skill, then teaching data containing content related to that required skill will be matched. During the matching process, teacher accounts can be filtered based on preset priority conditions for each type of job.

[0047] In step S130, educational institutions typically have multiple instructors for a given position, resulting in multiple teacher accounts being obtained. One teacher account is then selected as the interviewer. In some implementations, an interview matching score can be generated for each teacher account based on its historical teaching and interview scores. The teacher account with the highest interview matching score is then selected as the interviewer. Historical teaching and interview scores are linked and stored with their corresponding teacher accounts. Historical teaching scores are calculated based on student ratings, reflecting the instructor's teaching ability for the position; historical interview scores are calculated based on scores from previous job seekers, reflecting the instructor's control over the interview process.

[0048] When generating interview matching scores based on historical teaching scores and historical interview scores, different weight values ​​can be set for historical teaching scores and historical interview scores to ensure that the final selected interviewer is the best match for the interview request and the most suitable for conducting the interview.

[0049] The interview time slot is usually determined to be the overlap between the interviewer's non-scheduled time slot and the selected time slot in the interview request. However, this overlapping time slot can be adjusted appropriately according to the job requirements corresponding to the interview request.

[0050] In step S140, the interactive virtual space is a virtual space for the first terminal and the second terminal to conduct video interaction during the interview period. By pushing the entry interface of the interactive virtual space to the first terminal of the interviewee who initiated the interview request and the aforementioned determined second terminal of the interviewer, when the interview server receives the connection request from the first terminal on its entry interface and the connection request from the second terminal on its entry interface, the interactive virtual space is successfully created. Thus, video communication between the first terminal and the second terminal is established through the interactive virtual space, enabling the interviewee and the interviewer to achieve good interview interaction through the interactive virtual space, improving the interviewee's interview experience and enhancing the interview effect for both parties.

[0051] Figure 2 The illustration shows a scenario where an interactive virtual space is created between a first terminal and a second terminal. (Refer to...) Figure 2 As shown, interviewee U10 uses a first terminal T10 and interviewer U20 uses a second terminal T20 to achieve video communication through the interactive virtual space 20 created by interview server S20. Initially, interview server S20 transmits the real-time interview videos of interviewee U10 and interviewer U20 to each other's terminal screens based on the video stream from the interactive virtual space. This results in the first interface area 101 of the main screen in interview interface 100 of interviewee U10's first terminal T10 displaying the real-time interview video of interviewer U20, while a small window in the second interface area 102 provides feedback on the real-time interview video of interviewee U10. Similarly, in the interview interface 200 of interviewer U20's second terminal T20, the first interface area 201 of the main screen displays the real-time interview video of interviewee U10, while a small window in the second interface area 202 provides feedback on the real-time interview video of interviewer U20, achieving the effect of face-to-face communication between interviewee U10 and interviewer U20. Among them, the first terminal T10 and the second terminal T20 can be any terminal capable of video communication, such as smartphones, tablets, or personal computers, and are not limited to any specific type of device. Figure 2 The above is the limit.

[0052] In some embodiments, by detecting and alerting the interviewee's body movements in the video stream of the interactive virtual space, the interviewee's interview experience can be further enhanced, and the interview effect can be improved. Specifically, after creating the interactive virtual space, the steps further include: detecting the body movements of the interviewee corresponding to the first terminal in the video stream of the interactive virtual space; and pushing alert information to the first terminal based on the comparison between the detected body movements and preset body movements.

[0053] In video interviews, besides the logical thinking demonstrated in speech, body language and demeanor also significantly impact the score. In face-to-face interviews, candidates are constrained by the environment and can usually manage their body language effectively. However, in video interviews, due to unfamiliarity and the less restrictive environment, many candidates unconsciously display body language that is detrimental to their score. The video stream in the interactive virtual space includes real-time interview videos from both the candidate (on a first terminal) and the interviewer (on a second terminal). The interview server detects and provides reminders regarding body language in the real-time interview video from the first terminal within the interactive virtual space video stream, helping candidates improve their interview performance.

[0054] In a specific example, the detected body movements include eye movements and hand gestures. The step of pushing reminder information to the first terminal includes: when the eye movement detection determines that the match between the interviewee's eye gaze point and the target gaze area is less than a preset value, pushing a first reminder message indicating that the eye movement should be adjusted to the first terminal; when the hand gesture detection determines that the match between the interviewee's hand gesture and the preset hand gesture triggers a reminder condition, pushing a second reminder message indicating that the hand gesture should be adjusted to the first terminal.

[0055] Eye movement detection can be achieved based on eye-tracking technology. Specifically, image processing techniques can be used to locate the pupil position and calculate the coordinates of the eye's gaze point. The degree of matching between the coordinates of the eye's gaze point and the coordinate range of the target gaze area is calculated to determine whether the interviewee is looking at the target gaze area. The target gaze area can specifically be the interview interface of the first terminal. If the degree of matching between the interviewee's eye gaze point and the target gaze area is less than a preset value, it indicates that the interviewee's gaze has deviated from the interview interface of the first terminal, and therefore the interviewee is alerted.

[0056] In one embodiment, when the match between the interviewee's eye gaze point and the target gaze area is less than a preset value and the duration reaches a preset duration, a first reminder message instructing the first terminal to adjust the eye movement can be pushed. Both the preset value and the preset duration can be set as needed.

[0057] Gesture detection can also be implemented using image processing technology. Preset gestures include a whitelist and a blacklist. The alert condition is: the interviewee's gesture matches the whitelist with a first preset value, or the whitelist matches the blacklist with a second preset value. That is, an alert is issued to the interviewee when either the whitelist match is less than the first preset value or the blacklist match is greater than the second preset value. Both the first and second preset values ​​can be set as needed.

[0058] Figure 3 The embodiment shows the interface for pushing the first reminder information to the first terminal, see reference. Figure 3 As shown, the interview interface 100 of the first terminal T10 includes a first interface area 101 displaying the real-time interview video of the interviewer U20 and a second interface area 102 displaying the real-time interview video of the interviewee U10. In a preferred embodiment, the interview interface 100 may refer only to the first interface area 101 displaying the real-time interview video of the interviewer U20. When, based on eye movement detection, it is determined that the interviewee's gaze point exceeds an area outside the interview interface 100 (e.g., continuously looking at the desktop below the interview interface 100, continuously looking at the second interface area 102 corresponding to the small window, etc.), a first reminder message instructing the first terminal T10 to adjust the eye movement is pushed. The first reminder message is, for example, Figure 3 The text reminder "Please look at the interviewer" 301 is displayed in the first interface area 101, or a flashing reminder 302 is emitted around the avatar area of ​​the interviewer U20 displayed in the first interface area 101, so as to draw the interviewee's attention back.

[0059] Figure 4 The interface shown in the embodiment pushes the second reminder information to the first terminal. (Refer to...) Figure 4 As shown, the interview interface 100 of the first terminal T10 displays the real-time interview video of the interviewer U20 in its first interface area 101, and displays the real-time interview video of the interviewee U10 in its second interface area 102. In this embodiment, the gesture blacklist includes some pre-set gestures that need to be avoided, such as tapping the table, shaking or shrugging the shoulders, and loosely shaking the arm. When the matching degree between the interviewee's gesture and the gesture blacklist is greater than a suitable first preset value, it is determined that the gesture has fallen into the gesture blacklist, and a second reminder message instructing the first terminal to adjust the gesture is pushed. The second reminder message is, for example, Figure 4 The system displays a text reminder such as "Please stop tapping the desktop" 401 in the first interface area 101, or enlarges the dotted line area showing the interviewer's incorrect gesture without obscuring the interviewer's avatar in the first interface area 101, and issues a warning reminder 402. This achieves the effect of reminding the interviewer without affecting the communication between the interviewer and the interviewer. The gesture whitelist includes a pre-set threshold range for gesture amplitude. When the interviewer's gesture amplitude is too large and exceeds the threshold range, it can easily cause screen clutter and affect the interview effect. Therefore, a second reminder message, such as a text reminder, is used to instruct the interviewer to reduce the amplitude of their gesture.

[0060] In some embodiments, by detecting and filtering the images and sounds of third parties other than the interviewee and interviewer in the video stream of the interactive virtual space, good interview interaction between the interviewee and interviewer can be further ensured, and the interview effect for both parties can be improved.

[0061] Specifically, after creating the interactive virtual space, the process includes the following steps: detecting whether there is a third person's image in the video stream of the interactive virtual space, other than the interviewee corresponding to the first terminal and the interviewer corresponding to the second terminal; if so, blurring the third person's image so that the area corresponding to the third person's image in the real-time interview video transmitted to the first and second terminals is blurred. The interviewee corresponding to the first terminal and the interviewer corresponding to the second terminal are obtained by the following method: in response to the connection request from the first and second terminals, after creating the interactive virtual space, the interview server immediately obtains the user video from the first terminal from the video stream of the interactive virtual space, locks it as the interviewee throughout the interview period, and obtains the user video from the second terminal, locks it as the interviewer throughout the interview period; the locking method can be facial recognition. Alternatively, in some implementations, the job seeker's photo information can be obtained from the interview request, and after facial feature analysis, it can be locked as the interviewee corresponding to the first terminal; and based on the determined interviewer's photo information, after facial feature analysis, it can be locked as the interviewer corresponding to the second terminal. The facial recognition and facial feature analysis use existing technologies, so they will not be described in detail here.

[0062] Third parties include anyone other than the interviewee in the video data recorded on the first terminal, and anyone other than the interviewer in the video data recorded on the second terminal. The presence of third parties can significantly impact the interaction between the interviewee and the interviewer. For example, if an interviewee is having a video interview in their dorm room and a roommate walks by or even stops in the interview, entering the live video feed viewed by the interviewer on their second terminal, it can affect the interviewee's score. Similarly, if an interviewee is focused on the interview and doesn't notice a classmate walking behind them, seeing that classmate on their first terminal's screen can also negatively influence their performance. Likewise, anyone appearing behind the interviewer can also affect the interaction between the interviewee and the interviewer.

[0063] By blurring the image of a third party, the area corresponding to the third party's image in the real-time interview video transmitted to the first and second terminals is blurred. As a result, whether it is the interviewee or the interviewer, the real-time interview video viewed on their interview interface will only clearly show the other party's and their own images and the original background, while the area corresponding to the third party's image is blurred to avoid affecting the interviewee and the interviewer.

[0064] Furthermore, after creating the interactive virtual space, the process also includes the following steps: detecting whether there is a third person's voice in the video stream of the interactive virtual space, other than the interviewee corresponding to the first terminal and the interviewer corresponding to the second terminal; if so, weakening the third person's voice so that the content corresponding to the third person's voice in the real-time interview video transmitted to the first terminal and the second terminal is weakened.

[0065] Besides the impact of a third person's image on the interview, the third person's voice can also significantly affect the interaction between the interviewee and the interviewer. For example, if an interviewer is conducting a video interview with a candidate in a conference room, and multiple interviewers are conducting video interviews with different candidates in the same conference room, the voices of multiple interviewers are likely to be mixed up, affecting the interview's effectiveness.

[0066] Therefore, by weakening the voice of a third party, the content corresponding to the voice of the third party in the real-time interview video transmitted to the first and second terminals is weakened. As a result, in the real-time interview video displayed on the interview interface, whether it is the interviewee or the interviewer, only the other party's voice is played clearly, while the content corresponding to the voice of the third party is weakened, so as to avoid affecting the interviewee and the interviewer.

[0067] In some embodiments, by allowing interviewees to drag and adjust the real-time interview video displayed on their interview interface on the first terminal, interviewees can adjust the display of the interview interface to a more suitable state to obtain the best interview experience and improve the interview effect. Specifically, after creating the interactive virtual space, the method further includes the step of: responding to the drag operation command of the first terminal, moving and scaling the real-time interview video of the interviewee and the real-time interview video of the interviewer displayed on the first terminal to the area indicated by the drag operation command, so that the real-time interview video of the interviewee and the real-time interview video of the interviewer are tiled or overlaid on the interview interface of the first terminal.

[0068] Figure 5 The interface shown in the embodiment responds to the drag operation command of the first terminal, as illustrated below. Figure 5As shown, in the initial state 5(a), the first interface area 101 of the main screen of the first terminal T10's interview interface 100 displays the real-time interview video of the interviewer U20, while a small window in the second interface area 102 displays the real-time interview video of the interviewee U10. Initial state 5(a) is a conventional display method, which is beneficial for achieving face-to-face communication. However, since different interviewees have different viewing needs for the real-time interview video, the display method of initial state 5(a) is difficult to meet the interview needs of all interviewees, and may even affect the interviewee's interview performance. For example, some interviewees want to clearly see their own real-time interview video during the video interview and adjust their interview state in real time, without having to stare at the small window for a long time, causing their gaze to wander or ignoring the interviewer's instructions. Based on this, this embodiment responds to the drag operation command of the first terminal T10 to adjust the real-time interview video displayed in the interview interface 100.

[0069] When the drag operation command of the first terminal T10 is only applied to the second interface area 102, for example, when the interviewee drags the border of the second interface area 102 to enlarge the display of the real-time interview video, then based on the drag operation command, the real-time interview video of the interviewee U10 displayed in the second interface area 102 is enlarged proportionally to form the second interface area 102' in the first adjustment state as shown in the first adjustment state 5(b). The real-time interview video of the interviewee U10 displayed in the second interface area 102' in the first adjustment state is superimposed on the real-time interview video of the interviewer U20 displayed in the first interface area 101. The area range of the second interface area 102' in the first adjustment state can be set with boundary values, for example, the boundary value is not to cover the avatar area of ​​the interviewer U20 displayed in the first interface area 101.

[0070] When the first terminal T10 simultaneously drags the first interface area 101 and the second interface area 102, based on the drag operation command, the real-time interview video of the interviewee U10 and the real-time interview video of the interviewer U20 are moved and scaled to their respective areas, so that the real-time interview videos of the interviewee U10 and the interviewer U20 are tiled. At this time, the first interface area 101' under the second adjustment state 5(c) and the second interface area 102'' under the second adjustment state 5(c) are displayed in a split-screen format on the interview interface 100 of the first terminal T10. The area range of the second interface area 102'' under the second adjustment state can also be set with boundary values, for example, with a boundary value not exceeding half of the interview interface 100.

[0071] In some embodiments, after creating the interactive virtual space, the method further includes the step of: responding to a new operation instruction from the second terminal, pushing the entry interface of the interactive virtual space to the third terminal of the reviewer indicated by the new operation instruction. The reviewer is a teacher account in the teacher information database with interview permissions greater than those of an interviewer. The reviewer corresponds to the teaching supervisor in the above embodiments.

[0072] If the interviewer has communicated with the reviewer beforehand and learned that the reviewer has available time during the video interview period, or if other interviewers determine that it is necessary to invite the reviewer to join the video interview, the interviewer can initiate a new operation command through their second terminal to push the entrance interface of the interactive virtual space to the reviewer's third terminal. When the reviewer initiates a connection request to the interactive virtual space through the entrance interface of their third terminal, the reviewer's corresponding third terminal also joins the interactive virtual space. At this time, a video connection is established between the interviewee's first terminal, the interviewer's second terminal, and the reviewer's third terminal, enabling a three-way video interview exchange.

[0073] In some embodiments, after the video interview, the video of the interaction between the interviewee and the interviewer is pushed to a third-party terminal of the reviewer for review.

[0074] Specifically, the video interview method also includes the following steps: after the interactive virtual space is closed, an interactive interview video is generated based on the real-time interview video of the interviewee recorded on the first terminal and the real-time interview video of the interviewer recorded on the second terminal, so that the real-time interview video of the interviewee and the real-time interview video of the interviewer are played synchronously in split screen; the interactive interview video is pushed to the third terminal of the reviewer, where the reviewer is a teacher account in the teacher information database with greater interview authority than the interviewer, that is, the corresponding teaching supervisor.

[0075] During the video interview, the first terminal records and feeds back the interviewee's real-time interview video, while the interview server simultaneously transmits the interviewee's real-time interview video from the first terminal to the second terminal from the video stream in the interactive virtual space. Similarly, the second terminal records and feeds back the interviewer's real-time interview video, while the interview server simultaneously transmits the interviewer's real-time interview video from the second terminal to the first terminal from the video stream in the interactive virtual space. After the interactive virtual space closes, the interview server generates an interactive interview video based on the interviewee's and interviewer's real-time interview videos and pushes it to the third terminal of the reviewer. This allows the interviewee's and interviewer's real-time interview videos to be played synchronously in split-screen on the third terminal, facilitating the reviewer's assessment of the interviewee's answers and the interviewee's responses during the interviewer's introduction.

[0076] Furthermore, to save reviewers' review time and improve review efficiency, before the step of pushing the interactive interview video to the reviewer's third terminal, the following steps are also included: segmenting the interactive interview video based on sound features to form multiple video segments, with each video segment's effective audio content corresponding to a speaker, who is either the interviewee or the interviewer; matching adjacent video segments with matching keywords in sequence according to the keywords of each video segment to form multiple dialogue segments between the interviewer and the interviewee; wherein, each dialogue segment can be played independently.

[0077] In interactive interview videos, typically only one speaker occurs at a time, such as the interviewee answering questions or the interviewer giving an introduction. Different speakers possess different vocal characteristics, including tone and timbre. Therefore, video segmentation is performed based on these vocal features. In some cases, the interviewer may utter interjections like "um" or "yes" while the interviewee is answering questions; these are not recognized as valid speech and are therefore excluded from segmentation. During segmentation, background noise and silences can be removed from the video segments to ensure that each segment contains valid speech content and corresponds to a single speaker—either the interviewee answering questions or the interviewer giving an introduction.

[0078] Next, keywords for each video segment are obtained. This can be done by first converting the audio portion of the video segment into text and then performing keyword analysis on the text. Based on the keywords of each video segment, adjacent video segments with matching keywords are sequentially paired to form multiple dialogue segments between the interviewer and the interviewee. Each dialogue segment corresponds to an interview question. Each dialogue segment can be played independently, allowing the reviewer to select specific segments for review as needed.

[0079] Figure 6 The example shown illustrates the interface for pushing interactive interview videos to a third terminal. (Refer to...) Figure 6 As shown, on the third terminal T30 of the reviewer, the interactive interview video 300 is displayed in a simultaneous split-screen format, with the real-time interview video 301 of the interviewee U10 and the real-time interview video 302 of the interviewer U20 playing simultaneously. The interactive interview video 300 contains multiple individually playable dialogue segments 300'. The reviewer can click on any dialogue segment 300' on the third terminal T30 to watch the corresponding interactive exchange between the interviewee and the interviewer.

[0080] In some embodiments, to further improve review efficiency and facilitate reviewers in quickly obtaining key dialogue segments related to job information, tags are added to each set of dialogue segments. Specifically, after the step of forming multiple sets of dialogue segments between the interviewer and the interviewee, the steps further include: matching the keywords of each set of dialogue segments with preset keywords of the job information; obtaining dialogue segments that match the preset keywords and whose interviewee's speaking time is longer than the interviewer's speaking time, and marking them with a first tag; obtaining dialogue segments that do not match the preset keywords and / or whose interviewee's speaking time does not exceed the interviewer's speaking time, and marking them with a second tag.

[0081] Conversation segments that match preset keywords and where the interviewee's speaking time exceeds the interviewer's speaking time are considered relevant to the job information and primarily represent the interviewee's thoughts. These segments provide a quick overview of the interviewee's understanding of the position, their suitability, and their ability to perform the duties. Therefore, these segments are labeled with the first tag. Conversation segments that do not match preset keywords and / or where the interviewee's speaking time does not exceed the interviewer's are likely conversations used to ease the atmosphere during the interview, or conversations where the interviewer introduces educational institutions or other background information that does not adequately demonstrate the interviewee's understanding of the job. These segments are labeled with the second tag.

[0082] Reference Figure 6 As shown, in the interactive interview video 300 pushed to the third terminal T30 of the reviewer, each dialogue segment 300' that can be played separately is tagged. The first tag "①" corresponds to the key dialogue segment, and the second tag "②" corresponds to the secondary dialogue segment. The reviewer can focus on watching and reviewing the dialogue segment 300' corresponding to the first tag "①", thereby quickly and effectively understanding the interviewee's interview performance.

[0083] Furthermore, after pushing the entry interface of the interactive virtual space to the reviewer's third terminal, or after pushing the interactive interview video to the reviewer's third terminal, the process includes the following steps: obtaining the first interview score from the second terminal and the second interview score from the third terminal; and obtaining the interview result based on the first and second interview scores. Both the interviewer and the reviewer can score the video interview through their terminals, and the final interview result for the interviewee is determined based on their scores. Depending on the interviewer's and reviewer's different interview permissions, different weights can be assigned to the first interview score and the second interview score when calculating the interview result; the specific weighting coefficients can be adjusted as needed.

[0084] In summary, the video interview method described in the above embodiments filters teacher accounts from the teacher database that match the teaching data with the job information of the interview request, and whose non-scheduled time slots overlap with the selected time slot of the interview request. For each interview request, a suitable teacher with available time is matched as the interviewer, achieving effective and targeted interviews without waiting for the teaching supervisor, thus alleviating the interview pressure on educational institutions. Furthermore, by establishing video communication between the interviewee's first terminal and the interviewer's second terminal through an interactive virtual space, the interviewee and interviewer can achieve good interview interaction through the interactive virtual space, improving the interviewee's interview experience and enhancing the interview effect for both parties. By detecting and alerting interviewees' body language in the video stream of the interactive virtual space, the interview experience is further enhanced, improving interview effectiveness. Furthermore, by detecting and filtering third parties other than the interviewee and interviewer in the video stream of the interactive virtual space, good interaction between the interviewee and interviewer is ensured, improving the interview effectiveness for both parties. In addition, after the interactive virtual space closes, the interactive interview video, which simultaneously plays the interviewee's and interviewer's real-time interview videos in split-screen mode, with each dialogue segment playable separately and tagged, is pushed to the reviewer's third-party terminal. This allows the reviewer to quickly access key interview segments, improving review efficiency.

[0085] This invention also provides a video interview system that can be applied to the video interview methods described in any of the above embodiments. For example, this video interview system can be configured in an educational institution's interview server to implement the video interview methods described in any of the above embodiments.

[0086] Figure 7 The main modules of the video interview system in the embodiment are shown, with reference to Figure 7 As shown, the video interview system 700 in this embodiment mainly includes: an interview request response module 710, used to respond to an interview request and obtain job information and a selected time period; an interview teacher screening module 720, used to obtain several teacher accounts from the teacher information database whose teaching data matches the job information and whose non-scheduled time periods overlap with the selected time period; an interview information determination module 730, used to determine one teacher account as the interviewer from the obtained teacher accounts, and determine the interview time period based on the interviewer's non-scheduled time period and the selected time period; and a virtual space creation module 740, used to create an interactive virtual space, push the entry interface of the interactive virtual space to the first terminal that initiated the interview request and the second terminal of the interviewer, and configure the interactive virtual space to establish video communication between the first terminal and the second terminal during the interview time period.

[0087] Furthermore, in some embodiments, the video interview system may also include modules for detecting the interviewee's body movements in the video stream of the interactive virtual space, modules for detecting third parties other than the interviewee and the interviewer in the video stream of the interactive virtual space, modules for generating interactive interview videos based on the interviewee's real-time interview video and the interviewer's real-time interview video, etc., to implement the video interview methods described in the above embodiments.

[0088] The aforementioned video interview system, by filtering teacher accounts from a teacher database that match teaching data with the job information in the interview request and whose non-scheduled time slots overlap with the selected time slot of the interview request, matches each interview request with a suitable teacher whose identity and availability allow, enabling effective and targeted interviews without waiting for the teaching supervisor, thus alleviating the interview pressure on educational institutions; it establishes video communication between the interviewee's first terminal and the interviewer's second terminal through an interactive virtual space, allowing for good interview interaction between the interviewee and the interviewer, improving the interviewee's interview experience and enhancing the interview effect for both parties; and through the interaction... The system detects and alerts interviewees to their body language in the video stream within the virtual space, further enhancing their interview experience and improving interview effectiveness. It also ensures positive interaction between interviewees and interviewers by detecting and filtering out third parties other than the interviewee and interviewer in the video stream within the interactive virtual space, thus improving the interview outcome for both parties. Furthermore, after the interactive virtual space closes, the system pushes the interactive interview videos—which simultaneously play the interviewee's and interviewer's real-time interview videos in a split-screen format, with each dialogue segment playable individually and tagged—to the reviewer's third-party terminal. This allows the reviewer to quickly access key interview segments, improving review efficiency.

[0089] This invention also provides an electronic device, including a processor and a memory, wherein the memory stores executable instructions, and the processor is configured to perform the steps of the video interview method described above by executing the executable instructions.

[0090] As described above, the electronic device of the present invention can select teacher accounts from the teacher information database whose teaching data matches the job information of the interview request and whose non-scheduled time period overlaps with the selected time period of the interview request. This allows for matching each interview request with a suitable teacher whose identity and availability allow, thus achieving effective and targeted interviews without waiting for the teaching supervisor, alleviating the interview pressure on educational institutions. Furthermore, by establishing video communication between the interviewee's first terminal and the interviewer's second terminal through an interactive virtual space, the interviewee and interviewer can achieve good interview interaction through the interactive virtual space, improving the interviewee's interview experience and enhancing the interview effect for both parties. And through [further details about the invention are missing from the original text]. The interactive virtual space detects and alerts interviewees' body language in the video stream, further enhancing their interview experience and improving interview effectiveness. It also ensures positive interaction between interviewees and interviewers by detecting and filtering out third parties other than the interviewee and interviewer in the video stream, improving the interview outcome for both parties. Furthermore, after the interactive virtual space closes, the interactive interview video, featuring simultaneous split-screen playback of the interviewee's and interviewer's real-time interview videos, with each dialogue segment playable individually and tagged, is pushed to the reviewer's third-party terminal. This allows the reviewer to quickly access key interview segments, improving review efficiency.

[0091] Figure 8 This is a schematic diagram of the structure of the electronic device in an embodiment of the present invention. It should be understood that... Figure 8 The modules are merely shown schematically. These modules can be virtual software modules or actual hardware modules. The merging, splitting, and addition of other modules are all within the scope of protection of this invention.

[0092] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "platform."

[0093] The following reference Figure 8 The present invention will be described in the form of an electronic device 800. Figure 8 The electronic device 800 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0094] like Figure 8 As shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different platform components (including storage unit 820 and processing unit 810), a display unit 840, etc.

[0095] The storage unit stores program code, which can be executed by the processing unit 810 to perform the steps of the video interview method described in the above embodiments. For example, the processing unit 810 can perform actions such as... Figure 1 The steps are shown.

[0096] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0097] The storage unit 820 may also include a program / utility 8204 having one or more program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0098] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0099] Electronic device 800 can also communicate with one or more external devices 900, which may be one or more of the following: keyboard, pointing device, Bluetooth device, etc. These external devices 900 enable users to interact and communicate with electronic device 800. Electronic device 800 can also communicate with one or more other computing devices, including routers and modems. This communication can be performed via input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. Network adapter 860 can communicate with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0100] This invention also provides a computer-readable storage medium for storing a program that, when executed, implements the steps of the video interview method described in the above embodiments. In some possible implementations, various aspects of this invention can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps of the video interview method described in the above embodiments.

[0101] As described above, the computer-readable storage medium of the present invention can, by filtering teacher accounts from a teacher information database that match teaching data with job information in interview requests and whose non-scheduled time periods overlap with the selected time periods of interview requests, match each interview request with a teacher of suitable identity and available time as an interviewer, thereby achieving effective and targeted interviews without waiting for teaching supervisors and alleviating the interview pressure on educational institutions; and by establishing video communication between the interviewee's first terminal and the interviewer's second terminal through an interactive virtual space, the interviewee and interviewer can achieve good interview interaction through the interactive virtual space, improving the interviewee's interview experience and enhancing the interview effect for both parties; and By detecting and alerting interviewees' body language in the video stream of the interactive virtual space, the interview experience is further enhanced, improving interview effectiveness. Furthermore, by detecting and filtering third parties other than the interviewee and interviewer in the video stream of the interactive virtual space, good interaction between the interviewee and interviewer is ensured, improving the interview effectiveness for both parties. In addition, after the interactive virtual space closes, the interactive interview video, which simultaneously plays the interviewee's and interviewer's real-time interview videos in split-screen mode, with each dialogue segment playable individually and tagged, is pushed to the reviewer's third-party terminal. This allows the reviewer to quickly access key interview segments, improving review efficiency.

[0102] Figure 9 This is a schematic diagram of the structure of the computer-readable storage medium of the present invention. (Reference) Figure 9 As shown, a program product 1000 for implementing the above-described method according to an embodiment of the present invention is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0103] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media include, but are not limited to: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0104] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0105] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device, for example, via the Internet using an Internet service provider.

[0106] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A video interview method, characterized in that, Including the following steps: In response to an interview request, obtain job information and select a time slot; From the teacher information database, obtain several teacher accounts whose teaching data matches the job information and whose non-scheduled time periods overlap with the selected time periods; One teacher account is selected from the obtained teacher accounts as the interviewer, and the interview time period is determined based on the interviewer's non-scheduled time period and the selected time period. as well as Create an interactive virtual space and push the entry interface of the interactive virtual space to the first terminal that initiated the interview request and the second terminal of the interviewer. The interactive virtual space is configured to establish video communication between the first terminal and the second terminal during the interview time period. In response to the new operation command from the second terminal, the entry interface of the interactive virtual space is pushed to the third terminal of the reviewer indicated by the new operation command. The reviewer is a teacher account in the teacher information database with greater interview authority than the interviewer. When the reviewer initiates a connection request to the interactive virtual space through the entry interface of the third terminal, the third terminal is added to the interactive virtual space, and a video connection is established between the first terminal corresponding to the interviewee, the second terminal corresponding to the interviewer, and the third terminal corresponding to the reviewer for video interview communication between the three parties.

2. The video interview method as described in claim 1, characterized in that, It also includes the following steps: Detect the body movements of the interviewee corresponding to the first terminal in the video stream of the interactive virtual space; Based on the comparison between the detected body movements and the preset body movements, a reminder message is pushed to the first terminal.

3. The video interview method as described in claim 2, characterized in that, The body movements include eye movements and hand gestures, and the steps for pushing reminder information to the first terminal include: When eye movement detection determines that the match between the interviewee's eye gaze point and the target gaze area is less than a preset value, a first reminder message instructing the first terminal to adjust the eye movement is pushed. When the matching degree between the interviewee's gesture and the preset gesture is determined based on the gesture detection, a reminder condition is triggered, and a second reminder message instructing the first terminal to adjust the gesture is pushed.

4. The video interview method as described in claim 1, characterized in that, It also includes the following steps: Detect whether there is a third person's image in the video stream of the interactive virtual space, other than the interviewee corresponding to the first terminal and the interviewer corresponding to the second terminal; If so, the image of the third person is blurred, so that the area corresponding to the image of the third person in the real-time interview video transmitted to the first terminal and the second terminal is blurred; and / or Detect whether there is a third person's voice in the video stream of the interactive virtual space, other than the interviewee corresponding to the first terminal and the interviewer corresponding to the second terminal; If so, the voice of the third person is weakened, so that the content corresponding to the voice of the third person in the real-time interview video transmitted to the first terminal and the second terminal is weakened.

5. The video interview method as described in claim 1, characterized in that, It also includes the following steps: After the interactive virtual space is closed, an interactive interview video is generated based on the real-time interview video of the interviewee recorded by the first terminal and the real-time interview video of the interviewer recorded by the second terminal, so that the real-time interview video of the interviewee and the real-time interview video of the interviewer in the interactive interview video are played synchronously in split screen. The interactive interview video is pushed to a third terminal of the reviewer, who is a teacher account in the teacher information database with greater interview privileges than the interviewer. as well as Obtain the first interview score from the second terminal and the second interview score from the third terminal, and obtain the interview result based on the first interview score and the second interview score.

6. The video interview method as described in claim 5, characterized in that, Before the step of pushing the interactive interview video to the reviewer's third terminal, the method further includes the following steps: The interactive interview video is segmented based on sound features to form multiple video segments. The effective audio content of each video segment corresponds to a speaker, who is the interviewee or the interviewer. Based on the keywords of each video segment, adjacent video segments with matching keywords are sequentially paired to form multiple sets of dialogue segments between the interviewer and the interviewee; Each of the dialogue segments can be played individually.

7. The video interview method as described in claim 6, characterized in that, Following the step of generating multiple sets of dialogue segments between the interviewer and the interviewee, the method further includes the following step: Match the keywords of each group of dialogue segments with the preset keywords of the job information; Obtain dialogue segments that match the preset keywords and whose speaking duration is longer than that of the interviewer, and label them with a first tag; Obtain dialogue segments that do not match the preset keywords and / or whose speaking time does not exceed the speaking time of the interviewer, and mark them with a second tag.

8. A video interview system, characterized in that, The video interview system, applicable to the video interview method according to any one of claims 1-7, comprises: The interview request and response module is used to respond to interview requests and obtain job information and selected time periods; The interview teacher screening module is used to obtain several teacher accounts from the teacher information database that match the teaching data with the job information and whose non-scheduled time periods overlap with the selected time periods. The interview information determination module is used to select one teacher account from several obtained teacher accounts as the interviewer, and to determine the interview time slot based on the interviewer's non-scheduled time slot and the selected time slot; and A virtual space creation module is used to create an interactive virtual space and push the entry interface of the interactive virtual space to the first terminal that initiated the interview request and the second terminal of the interviewer. The virtual space creation module configures the interactive virtual space to establish video communication between the first terminal and the second terminal during the interview time period. In response to the new operation command from the second terminal, the entry interface of the interactive virtual space is pushed to the third terminal of the reviewer indicated by the new operation command. The reviewer is a teacher account in the teacher information database with greater interview authority than the interviewer. When the reviewer initiates a connection request to the interactive virtual space through the entry interface of the third terminal, the third terminal is added to the interactive virtual space, and a video connection is established between the first terminal corresponding to the interviewee, the second terminal corresponding to the interviewer, and the third terminal corresponding to the reviewer for video interview communication between the three parties.

9. An electronic device, characterized in that, include: One processor; A memory, wherein the memory stores executable instructions of the processor; The processor is configured to perform the steps of the video interview method as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium for storing a program, characterized in that, When the program is executed, it implements the steps of the video interview method as described in any one of claims 1 to 7.

Images