Remote interview method and device, equipment, storage medium and program product

Abstract

The invention provides a remote interview method and device, electronic equipment, a computer readable storage medium and a computer program product, and relates to the technical field of information processing, in particular to the technical field of artificial intelligence such as a large language model, a neural network model and remote interview. The method comprises the following steps: in response to legal entry of a to-be-interviewed object into a preset interview space, performing information acquisition on the to-be-interviewed object by using an information acquisition device arranged in the preset interview space to obtain interview process data; performing real-time cheating detection on the interview process data, and feeding back a cheating detection prompt corresponding to an obtained real-time detection result to the interviewer object; sending a verification problem proposed by the interviewer object based on the cheating detection prompt to the to-be-interviewed object; and based on interview process data including reply information replied by the to-be-interviewed object to the verification question, evaluating the effectiveness of the remote interview of the to-be-interviewed object. The method can greatly reduce the difficulty of identifying cheating by an interviewer.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing technology, specifically to the field of artificial intelligence technology such as large language models, neural network models, and remote interviews, and especially to a remote interview method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] As large language models become increasingly powerful, the barrier to entry for their use has been significantly lowered. While they can significantly reduce the difficulty of obtaining information, they also present significant challenges during company interviews. Summary of the Invention

[0003] The embodiments of the present disclosure provide a remote interview method, apparatus, electronic device, computer-readable storage medium, and computer program product.

[0004] In a first aspect, an embodiment of the present disclosure proposes a remote interview method, comprising: in response to an interviewee legally entering a preset interview space, collecting information from the interviewee using an information collection device provided in the preset interview space to obtain interview process data; performing real-time cheating detection on the interview process data, and feeding back a cheating detection reminder corresponding to the obtained real-time detection result to the interviewer object; sending verification questions raised by the interviewer object based on the cheating detection reminder to the interviewee; and evaluating the effectiveness of the remote interview of the interviewee based on the interview process data including reply information of the interviewee to the verification questions.

[0005] In a second aspect, an embodiment of the present disclosure proposes a remote interview device, including: an information collection module, for collecting information from the interviewee in response to the interviewee legally entering a preset interview space, and obtaining interview process data, wherein the information collection module is set in the preset interview space; a detection module, for performing real-time cheating detection on the interview process data, and feeding back a cheating detection reminder corresponding to the obtained real-time detection result to the interviewer object; a sending module, for sending verification questions raised by the interviewer object based on the cheating detection reminder to the interviewee; and an evaluation module, for evaluating the effectiveness of the remote interview of the interviewee based on the interview process data including the reply information of the interviewee to the verification questions.

[0006] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can implement the remote interview method described in any implementation method of the first aspect when executing the instructions.

[0007] In a fourth aspect, an embodiment of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to implement the remote interview method described in any implementation method of the first aspect when executed.

[0008] In a fifth aspect, an embodiment of the present disclosure provides a computer program product comprising a computer program, which, when executed by a processor, can implement the remote interview method as described in any implementation manner in the first aspect.

[0009] The remote interview method provided by the embodiment of the present disclosure uses a specially established trusted interview space to conduct interviews, that is, through hardware and technical means, a trusted interview environment is provided to companies with interview needs, completely eliminating the possibility of all kinds of cheating in interviews, greatly reducing the difficulty for interviewers to identify cheating, and company interviewers only need to focus on the content of the interview; at the same time, the present disclosure also collects the interview process data of the interviewees in the interview space in real time, and performs real-time cheating detection on the interview process data, so that the interviewers can ask verification questions to the interviewees based on the real-time detection results, and thus evaluate the effectiveness of the remote interview of the interviewees based on the answer information of the interviewees to the verification questions, further improving the efficiency and accuracy of cheating detection in the online interview process.

[0010] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Other features, objects and advantages of the present disclosure will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 is an exemplary system architecture in which the present disclosure may be applied; Figure 2 A flowchart of a remote interview method provided by an embodiment of the present disclosure; Figure 3 A flowchart of another remote interview method provided by an embodiment of the present disclosure; Figure 4 A structural block diagram of a remote interview device provided in an embodiment of the present disclosure; Figure 5 A structural block diagram of an information collection module provided in an embodiment of the present disclosure; Figure 6 A schematic diagram of the structure of an electronic device suitable for executing a remote interview method provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description. It should be noted that the embodiments in the present disclosure and the features in the embodiments can be combined with each other unless there is a conflict.

[0013] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0014] Interviewing new employees is an important way for companies to manage their talent. Due to cost issues, most interviews are conducted through online meetings. During the interview process, the interviewer uses a series of questions in a certain short period of time to understand the interviewee's abilities and then decide whether to accept the interviewee into the company.

[0015] In remote interviews, candidates may resort to cheating methods such as large language models, headphone prompts, and projection glasses to quickly obtain the correct responses to the interviewer's questions and thus cheat their way through the interview. This creates significant trouble for both recruiters and hiring companies, preventing them from effectively screening suitable candidates through interviews.

[0016] The emergence of large language models has greatly increased the feasibility and concealment of cheating. Furthermore, in addition to the negative impact of the aforementioned situation when the interviewee is attempting to cheat, even if the interviewee does not actually cheat, the very possibility of such a situation can lead to distrust in the interviewer. Consequently, any unusual behavior by the interviewee can lead to suspicion of cheating, thus affecting the interviewer's evaluation.

[0017] To address the aforementioned issues in remote interviews, the current approach is to provide interview software that monitors the programs running on the interviewer's computer and projects the current desktop screen to the interviewer. However, current solutions only address some of the most obvious cheating issues related to the interviewer's computer, but a large number of low-cost cheating methods remain undetected. These include, but are not limited to, the interviewer placing their phone or other device near the computer screen (sticking it to the screen), making it impossible to tell from their eyes whether they are looking at another device. If the interviewer uses a large language model combined with voice input on their phone or other device, they can quickly generate answers to the interview questions and answer accordingly. Alternatively, the interviewer can wear headphones, with someone else providing answers to the questions through the headphones. Alternatively, the interviewer can wear projection glasses and receive prompts related to the interview questions.

[0018] Based on this, the present disclosure proposes a remote interview method that can accurately identify cheating behavior.

[0019] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the remote interview method, apparatus, electronic device, and computer-readable storage medium disclosed herein can be applied.

[0020] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0021] Users can use terminal devices 101, 102, 103 to interact with server 105 via network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 and server 105 may be installed with various applications for enabling information communication between them, such as instant messaging applications.

[0022] Terminal devices 101, 102, 103 and server 105 can be either hardware or software. When terminal devices 101, 102, 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, laptop computers, and desktop computers. When terminal devices 101, 102, 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules, or as a single software or software module, and are not specifically limited here. When server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server is software, it can be implemented as multiple software or software modules, or as a single software or software module, and are not specifically limited here.

[0023] The server 105 can provide various services through various built-in applications. Taking the provision of remote interview applications as an example, the server 105 can achieve the following effects when running remote interview applications: first, in response to the interviewee legally entering the preset interview space, the information collection device set in the preset interview space is used to collect information from the interviewee to obtain interview process data; real-time cheating detection is performed on the interview process data, and a cheating detection reminder corresponding to the obtained real-time detection result is fed back to the interviewer object; verification questions raised by the interviewer object based on the cheating detection reminder are sent to the interviewee; and based on the interview process data including the reply information of the interviewee to the verification questions, the effectiveness of the remote interview of the interviewee is evaluated.

[0024] It should be noted that, in addition to being obtained from terminal devices 101, 102, and 103 via network 104, interview process data, verification questions, and the like can also be pre-stored locally on server 105 in various ways. Therefore, when server 105 detects that such data is already stored locally (e.g., interview process data and verification questions saved before the interview assessment begins), it may choose to directly obtain such data locally. In this case, exemplary system architecture 100 may also exclude terminal devices 101, 102, 103 and network 104.

[0025] Because remote interview methods require significant computing resources and power, the remote interview methods provided in the subsequent embodiments of this disclosure are generally executed by a server 105 with significant computing power and resources. Accordingly, the remote interview apparatus is generally located within server 105. However, it should also be noted that if terminal devices 101, 102, and 103 also possess sufficient computing power and resources, terminal devices 101, 102, and 103 can also utilize the remote interview application installed thereon to perform the aforementioned operations delegated to server 105, thereby outputting the same results as server 105. In particular, in the presence of multiple terminal devices with varying computing power, if the remote interview application determines that the terminal device it is in possession of possesses significant computing power and sufficient remaining computing resources, it can delegate the aforementioned operations to that terminal device, thereby appropriately alleviating the computing pressure on server 105. Accordingly, the remote interview apparatus can also be located within terminal devices 101, 102, and 103. In this case, exemplary system architecture 100 may also exclude server 105 and network 104.

[0026] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0027] Please refer to Figure 2 , Figure 2 This is a flowchart of a remote interview method provided by an embodiment of the present disclosure, wherein process 200 includes the following steps: Step 201: In response to the interviewee legally entering the preset interview space, information collection is performed on the interviewee using an information collection device provided in the preset interview space to obtain interview process data.

[0028] Specifically, the interview space refers to a physical space specifically used for interviews. The interview space can be a closed movable room that accommodates one person, and the interview space can be isolated from external sounds. For example, the interview space can be a silent cabin. In addition, the interview space can also include a number of related equipment that meet the needs of the interview. For example, a set of network-connected computer equipment, handwriting tablet equipment, and related tables, chairs, lighting, power supplies and other equipment can be set up in the interview space. Multiple cameras can also be set up to capture panoramic images, faces, close-ups of human eyes and other images. Optionally, the interview space can also support a locked access control system. Optionally, the interview space can also include a set of network shielding equipment that can prevent the interview space from connecting to 4G / 5G cellular networks and wifi networks.

[0029] In addition, interview spaces can be set up in areas where interviews are concentrated, such as universities, urban talent centers, science and technology parks, etc., to facilitate interviews with candidates.

[0030] When the interviewee legally enters the preset interview space, the information collection device in the interview space begins to collect information about the interviewee, including but not limited to collecting the movements, voice, expression, etc. of the interviewee, to obtain interview process data.

[0031] It should be noted that the interviewee has full authorization for the interview process data collected in this step.

[0032] Step 202: Perform real-time cheating detection on the interview process data, and provide the interviewer with a cheating detection reminder corresponding to the obtained real-time detection result.

[0033] Specifically, the present disclosure can analyze real-time interview data collected to detect whether the interviewee is engaging in cheating during the interview, and provide real-time feedback to the interviewer. This allows the interviewer to promptly detect and confirm any unusual behavior (suspected cheating) from the interviewee, thereby reducing the difficulty for the interviewer in identifying cheating.

[0034] Step 203: Sending the verification questions raised by the interviewer based on the cheating detection reminder to the interviewee.

[0035] Specifically, after receiving the cheating detection reminder, the interviewer may ask corresponding verification questions to the interviewee based on the reminder, so as to confirm whether the interviewee is suspected of cheating based on verifying the cheating detection reminder.

[0036] Step 204: Based on the interview process data including the interviewee's response information to the verification questions, the effectiveness of the remote interview with the interviewee is evaluated.

[0037] Specifically, the interviewee's response information to the verification questions can help the interviewer determine whether the interviewee is suspected of cheating. The collected interview process data and the interviewee's response information to the verification questions are used together as interview process data to evaluate the effectiveness of the interviewee's remote interview, which can improve the accuracy and efficiency of judging the effectiveness of the remote interview.

[0038] The remote interview method provided by the embodiment of the present disclosure uses a specially established trusted interview space to conduct interviews, that is, through hardware and technical means, a trusted interview environment is provided to companies with interview needs, completely eliminating the possibility of all kinds of interview cheating, greatly reducing the difficulty for interviewers to identify cheating, and company interviewers only need to focus on the content of the interview; at the same time, the present disclosure also collects the interview process data of the interviewees in the interview space in real time, and performs real-time cheating detection on the interview process data, so that the interviewer can ask verification questions to the interviewees based on the real-time detection results, and thus evaluate the effectiveness of the remote interview of the interviewees based on the answer information of the interviewees to the verification questions and the collected interview process data, further improving the efficiency and accuracy of cheating detection in the online interview process.

[0039] Regarding the above Figure 2 In step 201, when collecting information about the interviewee, not only relevant information within the preset interview space can be collected, but also relevant information outside the preset interview space can be collected. The following embodiment provides a specific implementation method.

[0040] In some embodiments, the interview process data includes: image data, sound data, vibration data, and external interference signals. Step 201 uses an information collection device provided in a preset interview space to collect information from the interviewee to obtain interview process data, including: using an image collection device provided in the preset interview space to collect images of the interviewee to obtain image data; using an audio collection device provided in the preset interview space to collect sounds from the interviewee to obtain sound data; using a vibration collection device provided in the preset interview space to collect vibration signals from the interviewee to obtain vibration data; and using a signal blocking device provided on the outer shell of the preset interview space to collect external signals received after the interviewee enters the preset interview space to obtain external interference signals.

[0041] The subject to be interviewed has full authorization for the image data, sound data, vibration data and external interference signal collected in this step, and for each user involved in the external interference signal.

[0042] Specifically, an image acquisition device, such as a camera, may be provided inside the preset interview space.

[0043] In some embodiments, abnormal devices in the interview space can be identified by an image acquisition device set up inside the preset interview space.

[0044] Specifically, the image acquisition device (such as a panoramic camera) identifies whether there are other electronic devices that may be used for cheating placed on the table in the interview space, the image acquisition device (such as a front-facing human eye camera) identifies whether the interviewee is wearing intelligent glasses with lens projection, and the image acquisition device (such as other cameras) identifies whether the interviewee is wearing headphones (only communication with the amplifier is allowed during the interview, and wearing headphones is prohibited), thereby identifying abnormal devices in the interview space.

[0045] In some embodiments, the gaze of the interviewee can be recognized by an image acquisition device provided in a preset interview space.

[0046] Specifically, the interviewee's gaze can be tracked through an image acquisition device (such as a human eye camera) to identify whether the gaze remains focused on the interview computer screen. If the gaze falls elsewhere, it can be further determined whether there is a possible risk.

[0047] An audio collection device may also be provided within the preset interview space to identify sounds in the interview space. Specifically, the audio collection device may be used to identify whether there are cheating operations such as audio prompts.

[0048] A vibration acquisition device can also be installed inside the interview space to identify vibration signals within the interview space. Specifically, the vibration acquisition device can identify cheating attempts, such as those transmitted through vibration signals (Morse code) such as tapping on the table or the interview space casing.

[0049] In addition to data collected from within the interview space, the interview process data also includes external interference signals collected by a signal blocking device on the interview space's outer shell. If the blocked external interference signals contain data related to the interview, it indicates, to a certain extent, that the interviewee is likely to have cheated.

[0050] The disclosed embodiment obtains interview process data by collecting various data collected inside and outside the interview space, making the obtained interview process data more comprehensive, and thus the interview effectiveness evaluated based on the interview process data more accurate.

[0051] against Figure 2 In step 204, when evaluating the effectiveness of this remote interview, the collected external interference signal may be an encrypted signal. In order to extract effective information from the external interference signal, a series of processing is required for the external interference signal. A specific implementation method is given below.

[0052] In some embodiments, the external interference signal is decoded according to the signal type to obtain plaintext data; step 204: based on the interview process data including the reply information of the interviewee to the interview questions, the effectiveness of the remote interview of the interviewee is evaluated, including: based on the plaintext data in the interview process data including the reply information of the interviewee to the interview questions, the effectiveness of the remote interview of the interviewee is evaluated.

[0053] Wherein, each user involved in the external interference signal has full authorization to process the external interference signal.

[0054] Specifically, assuming that the external interference signal includes a cheating signal related to the interview, the cheating signal may be encrypted and then transmitted. Therefore, the external interference signal may be an encrypted signal. After the external interference signal is collected, the external decoding signal can also be decoded to obtain the plaintext data.

[0055] Signal types may include digital signals and analog signals. Digital signals can be encrypted using binary encryption, while analog signals are continuous signals that cannot be directly encrypted using digital encryption algorithms. Analog scrambling can generally be used for encryption. In some embodiments, signals can also be classified based on their source, with different encryption methods set for different signal categories.

[0056] The present disclosure performs decoding based on the signal type to which the external interference signal belongs, thereby improving decoding efficiency and accuracy.

[0057] The plaintext data obtained by decoding the external interference signal can directly and clearly determine whether the external interference signal is a cheating signal related to the interview. Based on the plaintext data, the effectiveness of the remote interview of the interviewee can be evaluated, which can improve the accuracy and efficiency of the evaluation.

[0058] In some embodiments, since there are many signals outside the interview space, in order to save storage space, the external interference signal can be compressed after being collected. The collected external interference signal can also be pre-processed to eliminate interference signals that are obviously unrelated to the interview, so as to save storage space and improve the efficiency of cheating detection.

[0059] against Figure 2 In step 202, real-time cheating detection is performed on the interview process data, and a cheating detection reminder corresponding to the obtained real-time detection result is fed back to the interviewer. Real-time cheating detection can be performed using a neural network model through feature extraction, a large language model, or other methods, thereby providing a detection reminder to the interviewer. The following embodiment provides a specific implementation method.

[0060] In some embodiments, real-time cheating detection is performed on interview process data, and a cheating detection reminder corresponding to the obtained real-time detection result is fed back to the interviewer object, including: continuously collected interview process data and interview cheating detection instructions are input into a preset large language model as prompt information to obtain a real-time output cheating suspicion degree and suspected evidence for explaining the output cheating suspicion degree; the real-time output cheating suspicion degree is matched with a corresponding suspected reminder identifier according to the size of the suspicion degree; wherein a correspondence between cheating suspicion degrees of different sizes and different suspected reminder identifiers is pre-established; and a cheating detection reminder including a suspected reminder identifier and suspected evidence matching the real-time output cheating suspicion degree is fed back to the interviewer object.

[0061] Among them, the interviewees have full authorization to process the collected interview process data.

[0062] Specifically, the large language model not only outputs the final cheating suspicion level corresponding to the interview data, but also outputs the suspected evidence corresponding to the output cheating suspicion level. Based on this suspected evidence, the interviewee can easily reconfirm the obtained cheating suspicion level, thereby improving the accuracy of cheating identification.

[0063] Optionally, based on the output cheating suspicion level and the suspected evidence corresponding to the cheating suspicion level, the large language model or the prompt words of the large language model may be updated to improve the accuracy of the output of the large language model.

[0064] In addition, different suspected reminder identifications are matched based on different cheating suspicions, which can help interviewers quickly identify the suspected cheating of interviewees.

[0065] In some embodiments, different suspected reminder marks differ in at least one of the following aspects: color, shape, size, and whether interactive; wherein the interactive method includes at least one of clicking, moving, and hiding.

[0066] Specifically, the color can be the same color, but with different depths corresponding to different suspected cheating levels. This allows for quicker identification of the likelihood of cheating by the interviewee based on the depth. Alternatively, different colors can be selected based on different suspected cheating levels, though this disclosure is not limited thereto. Alternatively, different degrees of suspected cheating can be distinguished based on the shape or size of the suspected warning marker.

[0067] The more suspected the interviewee is of cheating, the more prominent the corresponding suspected warning mark can be, to quickly alert the interviewer. For example, the more suspected the interviewee is of cheating, the larger the suspected warning mark, the darker the color, and the more prominent the shape.

[0068] In addition, different interaction methods can be set for suspected warning signs according to different cheating suspicions. For example, for suspected warning signs with low cheating suspicion, the interviewer can ignore them and the corresponding interaction method can be set to hide. However, for suspected warning signs with high cheating suspicion, the interviewer needs to pay close attention to them. The corresponding interaction method can be set to move them to a preset area for key monitoring. The corresponding interaction method can also be set to click, and by clicking, the interviewer can obtain suspected evidence of the suspected cheating suspicion corresponding to the suspected warning sign with high cheating suspicion, making it easier for the interviewer to determine the specific cheating behavior of the interviewee.

[0069] In addition, in the real-time detection process based on the interview video stream, as the interview process data increases and changes, as well as the interviewee's response information based on different verification questions, there may be a change in the suspicion of cheating. At this time, the corresponding user interface changes can be displayed on the interviewer's terminal device. For example, when the suspicion of cheating of the interviewee increases, the color of the corresponding suspected reminder mark will deepen, the space will increase, and a barrage will pop up, or target detection will be performed on the interview video stream, the target detection frame of the interviewee will be selected, and a bubble prompt will pop up near the target detection frame to remind the interviewer. Conversely, when the suspicion of cheating of the interviewee decreases, the color of the corresponding suspected reminder mark will become lighter, the space will decrease, the barrage will disappear, and so on.

[0070] In the disclosed embodiment, by distinguishing one or more of the suspected reminder marks in color, shape, size, and whether they are interactive, the interviewer can quickly determine the possibility of the corresponding interviewee cheating, thereby helping the interviewer to make a quick judgment.

[0071] against Figure 2 Step 203: Verification questions raised by the interviewer based on the cheating detection reminder are sent to the interviewee. These verification questions may be based on the interview scenario, the interviewee's interview responses, or questions unrelated to the interview. The following embodiment provides a specific implementation method.

[0072] In some embodiments, the cheating detection reminder further includes targeted question suggestions for determining the credibility of the suspected evidence. Step 203 sends the verification questions raised by the interviewer based on the cheating detection reminder to the interviewee, including: in response to the interviewer raising the verification questions based on the targeted question suggestions included in the cheating detection reminder, sending the verification questions raised by the interviewer to the interviewee.

[0073] Specifically, cheating detection includes suspected evidence corresponding to the suspected warning indicator. The large language model can also generate corresponding verification questions based on the suspected evidence, allowing the interviewer to confirm the accuracy of the output cheating suspicion level.

[0074] For example, assuming that the suspected evidence corresponding to the suspected reminder mark is that the interviewee takes something out of his pocket and holds it in his hand, the verification question may be "Do you have anything in your hand?" or "Please stretch out your hands", etc., to facilitate the interviewer to confirm whether the interviewee has any interview-related items in his hand, and thus determine whether the interviewee is suspected of cheating.

[0075] In some embodiments, the reply information includes: reply behavior and reply voice, and the reply behavior includes changes in facial expressions.

[0076] The answering behavior refers to the interviewee's behavior in answering the verification question. The answering behavior may include movements, facial expressions, and time intervals when answering the verification question.

[0077] Specifically, the interviewer's verification questions are based on the targeted question suggestions included in the cheating detection alert. If the interviewee deliberately hides their answers to the verification questions, their facial expression suddenly becomes tense, or there are long pauses between responses, this indicates a high likelihood of cheating. Conversely, if the interviewee calmly answers the verification questions, it's highly likely that they haven't cheated.

[0078] The response voice refers to the voice of the interviewee's response to the verification question. The response voice may include the content of the response to the verification question and the fluency of the response voice.

[0079] Specifically, if the interviewee's answer to the verification question is irrelevant to the verification question, or the answer is halting and incoherent, it means that the interviewee is deliberately avoiding the question, which largely indicates that the interviewee is cheating.

[0080] The disclosed embodiment can help the interviewer accurately determine whether the interviewee is suspected of cheating based on the interviewee's response information to the verification question.

[0081] The present disclosure can also calculate the comprehensive cheating confidence of the interviewee in real time based on the cheating detection results of each of the above dimensions, thereby determining the effectiveness of the remote interview based on the comprehensive cheating confidence. A specific implementation method is given below.

[0082] In some embodiments, step 204 evaluates the effectiveness of the remote interview of the interviewee based on the interview process data including the answer information of the interviewee to the verification question, including: determining a comprehensive cheating confidence based on each cheating suspicion corresponding to the interview process data including the answer information; in response to the comprehensive cheating confidence exceeding a preset confidence threshold, determining that the remote interview of the interviewee is not valid; in response to the comprehensive cheating confidence not exceeding the preset confidence threshold, determining that the remote interview of the interviewee is valid.

[0083] Among them, the cheating suspicion degree includes the cheating suspicion degree determined based on the interview process data collected inside the interview space, the cheating suspicion degree determined based on the plaintext data in the external signal collected from the interview space shell, and the cheating suspicion degree determined based on the answer information of the interviewee to the verification questions.

[0084] The confidence threshold can be determined based on the interviewee's position, the company's corporate culture, and so on. For example, if the interviewee's position is a high-risk position (such as fund management, confidential R&D, senior management, etc.), which has high credit requirements, then the confidence threshold can be set lower. Conversely, for some low-risk positions (such as grassroots positions), the confidence threshold can be set higher. In addition, if the company's corporate culture attaches great importance to cheating, then the confidence threshold can be set lower. Conversely, the confidence threshold can be set higher. Of course, the confidence threshold can also be set based on experience, and a reasonable confidence threshold can also be determined by calculating historical data. This disclosure does not impose any restrictions on this.

[0085] The disclosed embodiment comprehensively considers the cheating suspicion of each interviewee and compares it with a preset confidence threshold to evaluate the effectiveness of the remote interview of the interviewee, thereby making the evaluation result more accurate.

[0086] When determining the comprehensive cheating confidence based on each cheating suspicion level, calculation can be performed based on a preset weight, a preset neural network model, or a preset language eye model. The following embodiment provides a specific implementation method.

[0087] In some embodiments, a comprehensive cheating confidence is determined based on each cheating suspicion degree corresponding to the interview process data containing the reply information, including: determining the comprehensive cheating confidence based on the maximum value, minimum value and average value of each cheating suspicion degree corresponding to the interview process data containing the reply information.

[0088] Please refer to Figure 3 , Figure 3 This is a flowchart of another remote interview method provided by an embodiment of the present disclosure, wherein process 300 includes the following steps: Step 301: In response to the interviewee legally entering the preset interview space, information collection is performed on the interviewee using an information collection device provided in the preset interview space to obtain interview process data.

[0089] Step 302: Perform real-time cheating detection on the interview process data, and provide the interviewer with a cheating detection reminder corresponding to the obtained real-time detection result.

[0090] Step 303: Sending the verification questions raised by the interviewer based on the cheating detection reminder to the interviewee.

[0091] Step 304: Based on the interview process data including the interviewee's response information to the verification questions, evaluate whether the remote interview with the interviewee is effective.

[0092] The above steps 301-304 are similar to the following Figure 2 Steps 201-204 shown are consistent. For the same content, please refer to the corresponding part of the previous embodiment and will not be repeated here.

[0093] If the remote interview with the interviewee is valid, then step 306 is executed: no processing is performed. If the remote interview with the interviewee is invalid, then step 305 is executed.

[0094] Step 305: In response to the remote interview of the interviewee not being valid, a historical interview score is generated for the interviewee, and the historical interview score is shared in a position pool associated with the remote interview.

[0095] Specifically, the present disclosure can generate a historical interview score for the interviewee based on the interview process data of the interviewee's response information to the verification questions, so that the interviewer can refer to the historical interview score when the interviewee applies for a position related to this remote interview to obtain an initial impression of the interviewee.

[0096] In some embodiments, the historical interview scores can be compiled over a certain period of time. Optionally, these historical interview scores are not visible to the interviewee by default, but the interviewee can request to view them. With the employer's consent, the interviewee can view their historical interview scores. If they disagree with the scores or the judgment of cheating, they can apply for manual review and appeal. If the appeal is successful, the corresponding interviewer will be notified simultaneously.

[0097] The disclosed embodiment generates a historical interview score corresponding to the interviewee, so that the interviewer can refer to the historical interview score when the interviewee applies for a position related to the current remote interview, thereby obtaining an initial impression of the interviewee and improving interview efficiency.

[0098] The remote interview method provided by the embodiment of the present disclosure uses a specially established trusted interview space to conduct interviews, that is, through hardware and technical means, a trusted interview environment is provided to companies with interview needs, completely eliminating the possibility of all kinds of cheating in interviews, greatly reducing the difficulty for interviewers to identify cheating, and company interviewers only need to focus on the content of the interview; at the same time, the present disclosure also collects the interview process data of the interviewees in the interview space in real time, and performs real-time cheating detection on the interview process data, so that the interviewers can ask verification questions to the interviewees based on the real-time detection results, and thus evaluate the effectiveness of the remote interview of the interviewees based on the answer information of the interviewees to the verification questions, further improving the efficiency and accuracy of cheating detection in the online interview process.

[0099] Further references Figure 4 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a remote interview device. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0100] like Figure 4 As shown, the remote interview device 400 of this embodiment may include: an information collection module 401, a detection module 402, a sending module 403, and an evaluation module 404. Information collection module 401 is configured to collect information from an interviewee upon their legal entry into a pre-set interview space, obtaining interview process data. Information collection module 401 is located in the pre-set interview space. Detection module 402 is configured to perform real-time cheating detection on the interview process data and provide the interviewer with a cheating detection alert corresponding to the real-time detection result. Sending module 403 is configured to send verification questions posed by the interviewer based on the cheating detection alert. Evaluation module 404 is configured to evaluate the effectiveness of the interviewee's remote interview based on the interview process data, including the interviewee's responses to the verification questions.

[0101] In this embodiment, the specific processing of the information collection module 401, the detection module 402, the sending module 403 and the evaluation module 404 and the technical effects thereof can be referred to in the respective Figure 2 The relevant descriptions of steps 201-204 in the corresponding embodiment are not repeated here.

[0102] refer to Figure 5 , Figure 5 This is a structural block diagram of an information collection module 401 provided in an embodiment of the present disclosure.

[0103] In some embodiments, the information acquisition module 401 includes an image acquisition submodule 501, a sound acquisition submodule 502, a vibration acquisition submodule 503, and a signal blocking module 504. The image acquisition submodule 501 is provided in a preset interview space and is used to acquire images of the interviewee to obtain image data; the sound acquisition submodule 502 is provided in the preset interview space and is used to acquire sounds of the interviewee to obtain sounds data; the vibration acquisition submodule 503 is provided in the preset interview space and is used to acquire vibration signals of the interviewee to obtain vibration data; the signal blocking submodule 504 is provided on the outer shell of the preset interview space and is used to acquire external signals received after the interviewee enters the preset interview space and obtain external interference signals; the interview process data includes: image data, sound data, vibration data, and external interference signals.

[0104] In some embodiments, the remote interview device further includes a decoding module configured to decode the external interference signal according to its signal type to obtain plaintext data. The evaluation module 404 is specifically configured to evaluate the effectiveness of the remote interview conducted by the interviewee based on the plaintext data in the interview process data, including the interviewee's responses to the interview questions.

[0105] In some embodiments, the detection module 402 is specifically used to input the continuously collected interview process data stream and interview cheating detection indication as prompt information into a preset large language model to obtain a real-time output of cheating suspicion and suspected evidence for explaining the output cheating suspicion; match the real-time output cheating suspicion with a corresponding suspected reminder identifier according to the size of the suspicion; wherein, a correspondence between cheating suspicions of different sizes and different suspected reminder identifiers is pre-established; and feedback is given to the interviewer object, including a suspected reminder identifier and suspected evidence that matches the real-time output cheating suspicion.

[0106] In some embodiments, different suspected reminder marks differ in at least one of the following aspects: color, shape, size, and whether interactive; wherein the interactive method includes at least one of clicking, moving, and hiding.

[0107] In some embodiments, the cheating detection reminder also includes targeted question suggestions for determining the credibility of suspected evidence; the sending module 403 is specifically used to send the verification questions raised by the interviewer object to the interviewee in response to the interviewer object raising verification questions based on the targeted question suggestions included in the cheating detection reminder.

[0108] In some embodiments, the remote interview device further includes an acquisition module for acquiring response information of the interviewee to the verification question through an information collection device; wherein the response information includes: response behavior and response voice, and the response behavior includes changes in facial expressions.

[0109] In some embodiments, the evaluation module 404 is specifically used to determine a comprehensive cheating confidence based on each cheating suspicion corresponding to the interview process data containing the response information; in response to the comprehensive cheating confidence exceeding a preset confidence threshold, determine that the remote interview with the interviewee is not valid; in response to the comprehensive cheating confidence not exceeding the preset confidence threshold, determine that the remote interview with the interviewee is valid.

[0110] In some embodiments, when the evaluation module 404 executes the step of determining the comprehensive cheating confidence based on the various cheating suspicions corresponding to the interview process data containing the reply information, it is specifically used to determine the comprehensive cheating confidence based on the maximum value, minimum value and average value of the various cheating suspicions corresponding to the interview process data containing the reply information.

[0111] In some embodiments, the remote interview device further includes a sharing module for generating a historical interview score for the interviewee in response to the remote interview of the interviewee being invalid, and sharing the historical interview score in a position pool associated with the remote interview.

[0112] This embodiment exists as an apparatus embodiment corresponding to the above-mentioned method embodiment. The remote interview apparatus provided by this embodiment uses a specially established credible interview space to conduct interviews. That is, through hardware and technical means, it provides a credible interview environment for companies with interview needs, completely eliminating the possibility of all kinds of cheating in interviews, greatly reducing the difficulty for interviewers to identify cheating, and corporate interviewers only need to focus on the content of the interview; at the same time, the present disclosure also collects the interview process data of the interviewees in the interview space in real time, and performs real-time cheating detection on the interview process data, so that the interviewer can ask verification questions to the interviewees based on the real-time detection results, and thus evaluate the effectiveness of the remote interview of the interviewees based on the answer information of the interviewees to the verification questions, further improving the efficiency and accuracy of cheating detection in the online interview process.

[0113] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the remote interview method described in any of the above embodiments can be implemented when the at least one processor executes them.

[0114] According to an embodiment of the present disclosure, the present disclosure further provides a readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to implement the remote interview method described in any of the above embodiments when executed.

[0115] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, which, when executed by a processor, can implement the remote interview method described in any of the above embodiments.

[0116] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0117] like Figure 6 As shown, 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. RAM 603 may also store various programs and data required for the operation of device 600. Computing unit 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to bus 604.

[0118] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0119] Computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 601 performs the various methods and processes described above, such as the remote interviewing method. For example, in some embodiments, the remote interviewing method may 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 device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by computing unit 601, one or more steps of the remote interviewing method described above may be performed. Alternatively, in other embodiments, computing unit 601 may be configured to perform the remote interviewing method via any other suitable means (e.g., via firmware).

[0120] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A 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 machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein 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 the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 can be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, 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 a local area network (LAN), a wide area network (WAN), and the Internet.

[0125] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers and establishing a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host. This is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and virtual private server (VPS) services.

[0126] According to the technical solution of the embodiment of the present disclosure, interviews are conducted with the help of a specially established trusted interview space, that is, through hardware and technical means, a trusted interview environment is provided to companies with interview needs, completely eliminating the possibility of all kinds of cheating in interviews, greatly reducing the difficulty for interviewers to identify cheating, and company interviewers only need to focus on the content of the interview; at the same time, the present disclosure also collects the interview process data of the interviewees in the interview space in real time, and performs real-time cheating detection on the interview process data, so that the interviewers can ask verification questions to the interviewees based on the real-time detection results, and thus evaluate the effectiveness of the remote interview of the interviewees based on the answer information of the interviewees to the verification questions, further improving the efficiency and accuracy of cheating detection in the online interview process.

[0127] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0128] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A remote interview method, comprising: In response to the interviewee legally entering the preset interview space, collecting information from the interviewee using an information collection device provided in the preset interview space to obtain interview process data; Performing real-time cheating detection on the interview process data, and feeding back a cheating detection reminder corresponding to the obtained real-time detection result to the interviewer subject; Sending the verification questions raised by the interviewer based on the cheating detection reminder to the interviewee; Based on the interview process data including the response information of the interviewee to the verification question, the effectiveness of the remote interview of the interviewee is evaluated.

2. The method according to claim 1, wherein The method of collecting information from the interviewee using the information collection device provided in the preset interview space to obtain interview process data includes: Using an image acquisition device provided in the preset interview space to acquire an image of the interviewee to be interviewed, to obtain image data; Using an audio collection device provided in the preset interview space to collect the voice of the interviewee to obtain voice data; Using a vibration collection device provided in the preset interview space to collect vibration signals from the interviewee to obtain vibration data; A signal blocking device provided on the outer shell of the preset interview space is used to collect external signals received after the interviewee enters the preset interview space to obtain an external interference signal; wherein, the interview process data includes: the image data, the sound data, the vibration data and the external interference signal.

3. The method according to claim 2, further comprising: Decoding the external interference signal according to its signal type to obtain plaintext data; Correspondingly, the evaluating the effectiveness of the remote interview of the interviewee based on the interview process data including the response information of the interviewee to the interview questions includes: The effectiveness of the remote interview of the interviewee is evaluated based on the plaintext data in the interview process data including the reply information of the interviewee to the interview questions.

4. The method according to claim 1, wherein The performing real-time cheating detection on the interview process data and feeding back a cheating detection reminder corresponding to the obtained real-time detection result to the interviewer object includes: The continuously collected interview process data stream and interview cheating detection indicators are input into a preset large language model as prompt information, and the real-time output of the cheating suspicion level and the suspected evidence used to explain the output cheating suspicion level is obtained; Matching the real-time output cheating suspicion degree with a corresponding suspicion warning mark according to the suspicion degree; wherein a correspondence between different cheating suspicion degrees and different suspicion warning marks is pre-established; Feedback to the interviewer object is a cheating detection reminder including a suspected reminder mark and suspected evidence that matches the real-time output cheating suspicion level.

5. The method according to claim 4, wherein Different suspected warning signs differ in at least one of the following aspects: Color, shape, size, and whether it is interactive; among which, the interactive method includes: at least one of clicking, moving, and hiding.

6. The method according to claim 4, wherein: The cheating detection reminder also includes targeted questioning suggestions for determining the credibility of the suspected evidence; Correspondingly, sending the verification question raised by the interviewer based on the cheating detection reminder to the interviewee includes: In response to the interviewer object raising the verification question based on the targeted question suggestion included in the cheating detection reminder, the verification question raised by the interviewer object is sent to the interviewee.

7. The method according to claim 6, further comprising: The information collection device is used to obtain the response information of the interviewee to the verification question; wherein the response information includes: response behavior and response voice, and the response behavior includes changes in facial expression.

8. The method according to claim 4, wherein The evaluating the effectiveness of the remote interview of the interviewee based on the interview process data including the response information of the interviewee to the verification question includes: determining a comprehensive cheating confidence level based on each cheating suspicion level corresponding to the interview process data including the response information; In response to the comprehensive cheating confidence exceeding a preset confidence threshold, determining that the remote interview of the interviewee is not valid; In response to the comprehensive cheating confidence not exceeding the preset confidence threshold, it is determined that the remote interview of the interviewee is valid.

9. The method according to claim 8, wherein The determining of the comprehensive cheating confidence level based on each cheating suspicion level corresponding to the interview process data including the answer information includes: The comprehensive cheating confidence is determined based on the maximum value, the minimum value, and the average value of each cheating suspicion degree corresponding to the interview process data containing the answer information.

10. The method according to any one of claims 1 to 9, further comprising: In response to the remote interview of the interviewee not being valid, a historical interview score is generated for the interviewee, and the historical interview score is shared in a position pool associated with the remote interview.

11. A remote interview device comprising: An information collection module is configured to collect information about an interviewee in response to the interviewee legally entering the preset interview space, and obtain interview process data, wherein the information collection module is provided in the preset interview space; A detection module, configured to perform real-time cheating detection on the interview process data and provide the interviewer with a cheating detection reminder corresponding to the obtained real-time detection result; A sending module, configured to send the verification questions raised by the interviewer based on the cheating detection reminder to the interviewee; The evaluation module is used to evaluate the effectiveness of the remote interview of the interviewee based on the interview process data including the response information of the interviewee to the verification question.

12. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the remote interview method according to any one of claims 1 to 10.

13. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the remote interview method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, wherein when the computer program is executed by a processor, the steps of the remote interview according to any one of claims 1 to 10 are implemented.

Images