Method for Identifying Abnormal Behaviors of Bidding Evaluation Experts during Remote Bidding Evaluation Video Conference

Abstract

The present application provides a method for identifying abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference, which relates to the technical field of bid invitation and evaluation. The method includes: during the process of a bid evaluation expert conducting remote bid evaluation on a preset project through a video conference bid evaluation tool, obtaining the facial video image of the bid evaluation expert; performing human body detection on the facial video image to identify the human body parts included in the facial video image; determining whether the human body parts belong to the same human body; and in the case where the human body parts do not belong to the same human body, determining that there is an intrusion by others in the bid evaluation room where the bid evaluation expert is located. Thus, it realizes the automatic determination of whether there is an intrusion by others in the bid evaluation room where the bid evaluation expert is located during the remote bid evaluation process, and reduces the labor cost of manual monitoring.

Description

Technical Field

[0001] This application relates to the technical field of tendering and bidding, and particularly to a method for identifying abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference. Background Art

[0002] Tendering and bid evaluation is a form of comprehensive economic responsibility system to promote competition in the infrastructure field. Generally, several construction units participate in the project bidding, and the tendering unit (such as the construction unit) selects the best one. The construction unit with a short construction period, low cost, high quality, and good reputation will be awarded the project task by the tendering unit. Therefore, the bid evaluation process is particularly important.

[0003] Currently, remote off-site bid evaluation can be used for bid evaluation. During the process of remote off-site bid evaluation, it is necessary to monitor whether there are abnormal behaviors such as someone breaking into the bid evaluation room where the bid evaluation experts are located. In the related art, during the process of remote off-site bid evaluation, usually the project manager monitors the bid evaluation process of the bid evaluation experts through the pictures of the bid evaluation experts displayed on the video conference display interface to determine whether there are the above abnormal behaviors. In this way, the bid evaluation experts need to continuously watch the video conference display interface, resulting in high labor costs. Summary of the Invention

[0004] This application proposes a method for identifying abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference to solve the technical problem of high labor costs existing in the method for identifying abnormal behaviors during remote off-site bid evaluation in the related art.

[0005] A first aspect embodiment of this application proposes a method for identifying abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference. The method includes: during the process of a bid evaluation expert remotely evaluating a preset project through a video conference bid evaluation tool, obtaining the facial video picture of the bid evaluation expert; performing human detection on the facial video picture to identify the human body parts included in the facial video picture; determining whether the human body parts belong to the same human body; and in the case where the human body parts do not belong to the same human body, determining that someone has broken into the bid evaluation room where the bid evaluation expert is located.

[0006] In a second aspect embodiment of the present application, an apparatus for determining abnormal behavior of a bid evaluation expert during a remote bid evaluation video conference is proposed. The apparatus includes: an acquisition module, configured to acquire a facial video image of the bid evaluation expert during the process of the bid evaluation expert remotely evaluating a preset project through a video conference bid evaluation tool; an identification module, configured to perform human body detection on the facial video image to identify human body parts included in the facial video image; a judgment module, configured to judge whether the human body parts belong to the same human body; a first determination module, configured to determine that someone has broken into the bid evaluation room where the bid evaluation expert is located when the human body parts do not belong to the same human body.

[0007] In a third aspect embodiment of the present application, an electronic device is proposed. The electronic device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it executes the method for determining abnormal behavior of a bid evaluation expert during a remote bid evaluation video conference as described in the first aspect embodiment.

[0008] In a fourth aspect embodiment of the present application, a computer-readable storage medium is proposed. A computer program is stored thereon, and when the program is executed by a processor, it implements the method for determining abnormal behavior of a bid evaluation expert during a remote bid evaluation video conference as proposed in the first aspect embodiment of the present application.

[0009] In a fifth aspect embodiment of the present application, a computer program product is proposed. The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the method for determining abnormal behavior of a bid evaluation expert during a remote bid evaluation video conference as proposed in the first aspect embodiment of the present application.

[0010] The technical solutions provided by the embodiments of the present application have the following beneficial effects:

[0011] By acquiring the facial video image of the bid evaluation expert during the process of the bid evaluation expert remotely evaluating a preset project through a video conference bid evaluation tool, performing human body detection on the facial video image to identify preset human body parts included in the facial video image, judging whether the human body parts belong to the same human body, and determining that someone has broken into the bid evaluation room where the bid evaluation expert is located when the human body parts do not belong to the same human body, it realizes the automatic determination of whether someone has broken into the bid evaluation room where the bid evaluation expert is located during the remote bid evaluation process, and reduces the labor cost of manual monitoring.

[0012] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of embodiments in conjunction with the accompanying drawings, where:

[0014] Figure 1 It is a schematic structural diagram of the intelligent remote bid evaluation supervision system provided by the embodiment of the present application;

[0015] Figure 2 It is another schematic structural diagram of the intelligent remote bid evaluation supervision system provided by the embodiment of the present application;

[0016] Figure 3 It is an interaction schematic diagram of the project manager, bid evaluation experts, supervision platform, and bid supervision personnel provided by the embodiment of the present application;

[0017] Figure 4 It is a schematic flowchart of the method for identifying abnormal behaviors of bid evaluation experts during the remote bid evaluation video conference provided by the embodiment of the present application;

[0018] Figure 5 It is a schematic structural diagram of the device for identifying abnormal behaviors of bid evaluation experts during the remote bid evaluation video conference provided by the embodiment of the present application;

[0019] Figure 6 It is a schematic structural diagram of an electronic device provided by the embodiment of the present application. Detailed Embodiments

[0020] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0021] The method for identifying abnormal behaviors of bid evaluation experts during the remote bid evaluation video conference in the embodiments of the present application can be applied to the intelligent remote bid evaluation supervision platform of the intelligent remote bid evaluation supervision system. First, the intelligent remote bid evaluation supervision system of the embodiments of the present application will be described below with reference to the accompanying drawings.

[0022] Figure 1 It is a schematic structural diagram of the intelligent remote bid evaluation supervision system provided by the embodiment of the present application.

[0023] As Figure 1 shown, the intelligent remote bid evaluation supervision system may include a smart tendering platform 110 and an intelligent remote bid evaluation supervision platform 120 that are communicatively connected. Among them, the smart tendering platform 110 includes a video conference bid evaluation tool 111.

[0024] Among them, the intelligent tendering platform 110 is used to handle tendering and procurement operations; the video conferencing bid evaluation tool 111 is used for bid evaluation experts to enter a virtual meeting room through the video conferencing bid evaluation tool 111 and conduct remote bid evaluation on a preset project in the virtual meeting room; the intelligent remote bid evaluation supervision platform 120, hereinafter referred to as the supervision platform 120, is used to intelligently supervise the bid evaluation process of bid evaluation experts on a preset project. The preset project refers to the project that the bid evaluation experts are currently evaluating, and it can be set arbitrarily according to needs. The bid evaluation experts can be any bid evaluation expert participating in the bid evaluation work of the preset project.

[0025] Specifically, the supervision platform 120 can be deployed on the enterprise cloud, integrating the enterprise's cloud desktop resource devices, and developing a software and hardware support platform for the bid evaluation visualization supervision center based on computer vision analysis technology, remote video conferencing technology, and remote video monitoring technology, with functions such as querying real-time videos, historical videos, and intelligent early warning.

[0026] Among them, the supervision platform 120 can include a basic service layer, a platform service layer, and an application service layer from bottom to top. Among them, the basic service layer can include modules such as enterprise cloud, cloud desktop, and video monitoring, which are used to provide the basic services required for the operation of the supervision platform 120. The platform service layer can include audio and video communication service modules, message queue service modules, embedded security service modules, search engine service modules, distributed storage service modules, distributed computing service modules, virtualization service modules, centralized computing service modules, signaling service modules, and media service modules, which are used to provide corresponding services. The application service layer can include service modules such as a video monitoring management module that provides video monitoring management services, a video fusion module that provides video recording and fusion services, a video conferencing service module that provides video conferencing services, and an intelligent analysis and early warning module that provides intelligent analysis and early warning of video data to provide various services.

[0027] In addition, the supervision platform 120 can also provide a visualization large screen, a display interface for the virtual meeting room, etc.

[0028] The intelligent tendering platform 110 is used to handle tendering and procurement operations, that is, all tendering and procurement operations are carried out on the intelligent tendering platform 110.

[0029] The video conferencing bid evaluation tool 111 can be understood as a sub-application program in the intelligent tendering platform 110. Bid evaluation experts and other relevant personnel in the bid evaluation work such as project managers can log in to the video conferencing bid evaluation tool 111 through the intelligent tendering platform 110. When logging in, identity verification is carried out through the intelligent tendering platform 110. After logging in to the video conferencing bid evaluation tool 111, the video conferencing bid evaluation tool 111 can run independently.

[0030] Taking the bid evaluation experts as an example, when the bid evaluation experts log in to the video conferencing bid evaluation tool 111, the intelligent recruitment platform 110 can implement the identity verification of the bid evaluation experts through face recognition technology. After the identity verification is passed, the bid evaluation experts can perform relevant bid evaluation operations through the video conferencing bid evaluation tool 111; when the identity verification fails, the video conferencing bid evaluation tool 111 can prompt the experts that the identity verification fails and does not allow logging in. If the current bid evaluation expert has not collected a face image, the video conferencing bid evaluation tool 111 can prompt the bid evaluation expert to collect the face image first.

[0031] After the bid evaluation experts log in to the video conferencing bid evaluation tool 111, they can enter the virtual meeting room and conduct remote bid evaluation in the virtual meeting room. During the process of the bid evaluation experts evaluating the preset project, the supervision platform 120 can conduct intelligent supervision on the bid evaluation process.

[0032] The intelligent remote bid evaluation supervision system will be introduced in detail below.

[0033] Specifically, the video conferencing bid evaluation tool 111 is deeply integrated with a video conferencing tool and a bid evaluation tool. Among them, the bid evaluation tool is used to process the bidding and procurement business. On the basis of meeting the basic functions of video conferencing such as audio and video communication, text message communication, screen desktop sharing, file sharing, and application sharing, the video conferencing tool is deeply integrated with the bid evaluation tool, so as to be organically integrated with the bidding and procurement business and meet the business needs of different user roles (such as bid evaluation experts and project managers) during the remote bid evaluation process.

[0034] When it is necessary to evaluate a preset project, the project manager can first create a virtual meeting room for the video conferencing bid evaluation. Specifically, the project manager can log in to the video conferencing bid evaluation tool 111, and on the display interface of the video conferencing bid evaluation tool 111 after successful login, click the enter button with the function of entering the display interface of the preset project. Furthermore, the video conferencing bid evaluation tool 111 can display the display interface of the project manager of the preset project. It should be noted that after different user roles click the enter button, the video conferencing bid evaluation tool 111 will display different display interfaces of the preset project for different user roles. For example, for the project manager, it will display the display interface of the project manager of the preset project. Through this interface, the project manager can create a virtual meeting room corresponding to the preset project. For the bid evaluation experts, the video conferencing bid evaluation tool 111 will display the display interface of the bid evaluation experts of the preset project. Through this interface, the bid evaluation experts can enter the created virtual meeting room corresponding to the preset project to evaluate the preset project.

[0035] When the video conferencing bid evaluation tool 111 displays the project manager display interface of a preset project, the project manager can click the meeting creation button with the function of creating a meeting on this interface to trigger a video conferencing creation request. Correspondingly, the video conferencing bid evaluation tool 111 can send the video conferencing creation request to the supervision platform 120, where the video conferencing creation request includes the meeting information of the preset project. Among them, the meeting information can include the project information of the preset project, such as any information related to the preset project, such as the project name, project identifier, bid evaluation time, bid evaluation location, etc. of the preset project. Or, the meeting information can include the project information of the preset project and the expert information, where the expert information includes, for example, any information related to each bid evaluation expert who needs to participate in the bid evaluation work of this preset project, such as the name, identifier, age, ID number, mobile phone number, etc. of each bid evaluation expert.

[0036] After receiving the video conferencing creation request, the supervision platform 120 can create a virtual meeting room according to the meeting information of the preset project and generate a video conference number corresponding to the virtual meeting room, and then send the video conference number to the video conferencing bid evaluation tool 111 to notify the video conferencing bid evaluation tool 111 that the virtual meeting room has been created. After receiving the video conference number, the video conferencing bid evaluation tool 111 can display a prompt message indicating that the video conference has been created to prompt the project manager that the video conference has been created. Among them, the creation of the virtual meeting room and the generation of the corresponding video conference number can be executed by the module providing the video conferencing creation service in the application service layer of the supervision platform 120.

[0037] Correspondingly, the video conferencing bid evaluation tool 111 is also used to: send a video conferencing creation request to the intelligent remote bid evaluation supervision platform 120, and the video conferencing creation request includes the meeting information of the preset project;

[0038] The intelligent remote bid evaluation supervision platform 120 is also used to: after receiving the video conferencing creation request, create a virtual meeting room according to the meeting information of the preset project, generate a video conference number corresponding to the virtual meeting room, and send the video conference number to the video conferencing bid evaluation tool 111.

[0039] Among them, the video conference number is used to uniquely identify the corresponding virtual meeting room, and the video conference number is automatically generated by the supervision platform 120. The generation rule can refer to related technologies and will not be elaborated here.

[0040] Since the project manager only needs to click the meeting creation button, the video conferencing bid evaluation tool 111 can interact with the supervision platform 120, and the supervision platform 120 automatically creates a virtual meeting room, thus realizing that the project manager can automatically create a virtual meeting room for bid evaluation of the preset project with one click.

[0041] It should be noted that the above process is described by taking a virtual meeting room as an example. In actual applications, multiple virtual meeting rooms can be created through the above process according to needs, and this application places no restrictions on this.

[0042] After creating a virtual meeting room for evaluating a preset project, any evaluation expert participating in the evaluation work of the preset project can enter the virtual meeting room through the video conferencing evaluation tool 111 to evaluate the preset project. Specifically, taking one of the evaluation experts as an example, after the video conferencing evaluation tool 111 used by the evaluation expert receives the video conference number sent by the supervision platform 120, it can associate the video conference number with the preset project, store it under the preset project, and display a "Join Video Conference" button after the evaluation expert participating in the evaluation work of the preset project enters the evaluation expert display interface of the preset project. The evaluation expert can click the "Join Video Conference" button, and then the video conferencing evaluation tool 111 can, in response to detecting a touch operation on the "Join Video Conference" button, obtain the video conference number associated with the preset project, start the video conferencing tool, and then send the video conference number to the video conferencing tool to enter the virtual meeting room corresponding to the video conference number through the video conferencing tool. After entering the virtual meeting room corresponding to the video conference number, the evaluation expert can start evaluating the preset project.

[0043] Correspondingly, the video conferencing evaluation tool 111 is further configured to: receive the video conference number sent by the intelligent remote evaluation supervision platform 120; enter the virtual meeting room according to the video conference number.

[0044] Thus, it is realized that the evaluation expert can join the created virtual meeting room with one click through the "Join Video Conference" button. It should be noted that the above embodiment is described by taking the evaluation expert entering the created virtual meeting room as an example. In actual applications, relevant personnel of the preset project such as the project manager, supervisor, and evaluation expert can all enter the display interface of the preset project through the video conferencing evaluation tool 111 and join the virtual meeting room of the preset project with one click through the "Join Video Conference" button to hold a video conference. Since one can only join the created virtual meeting room through the "Join Video Conference" button after logging in to the video conferencing evaluation tool 111 and entering the display interface of the preset project, and cannot enter the virtual meeting room for evaluation through other means, the evaluation process is made safer and more confidential. In addition, before the relevant personnel of the preset project enter the virtual meeting room, the identity of the entering personnel can be verified to further improve the security and confidentiality of the evaluation process. Also, before the relevant personnel of the preset project enter the virtual meeting room, the video conferencing evaluation tool 111 can also remind the matters needing attention during the video conference, and then enter the virtual meeting room to participate in the video conference after the relevant personnel of the preset project agree.

[0045] The project manager creates a virtual meeting room with one click based on the video conferencing bid evaluation tool, and the bid evaluation experts join the virtual meeting room with one click based on the video conferencing bid evaluation tool, so that it is not necessary to manually form a video conference in advance, nor is it necessary to manage the video conference account password separately. Through simple operations, remote bid evaluation for preset projects can be carried out, improving the efficiency of remote bid evaluation, and the security and confidentiality of the bid evaluation process are high.

[0046] In the embodiment of the present application, the bid evaluation experts participating in the bid evaluation work of the preset project can be obtained by pre-drawing from the expert database. Correspondingly, referring to Figure 2 , the intelligent remote bid evaluation supervision system may further include an expert extraction platform 130 communicatively connected to the intelligent bidding platform 110, which is used to extract bid evaluation experts participating in the bid evaluation work of the preset project from multiple candidate bid evaluation experts included in the expert database. Among them, the expert database can be independent of the expert extraction platform 130 or configured in the expert extraction platform 130, and the expert extraction platform 130 can update the expert information of multiple candidate bid evaluation experts in the expert database. Among them, the expert information of the candidate bid evaluation experts can include any information related to the bid evaluation experts, such as the specialty, age, province or city where they are located, whether they are employed, education background, position, etc.

[0047] Specifically, the intelligent bidding platform 110 may include an extraction button with an expert extraction function. When it is necessary to extract bid evaluation experts participating in the bid evaluation work of the preset project, the person with the extraction permission can first input the project information and extraction requirements of the preset project and click the extraction button in the intelligent bidding platform 110 to trigger an expert extraction request. Correspondingly, the intelligent bidding platform 110 can send an expert extraction request to the expert extraction platform 130, where the expert extraction request may include the project information and extraction requirements of the preset project. Among them, the project information can include any information related to the preset project, such as project identification, bid evaluation time, bid evaluation location, etc.; the extraction requirements can include requirements for the specialty, age, province or city where they are located, whether they are employed, education background, position, etc. of the required extracted bid evaluation experts, as well as requirements to be avoided during extraction, such as not extracting those with abnormal bid evaluation behaviors.

[0048] After receiving the expert extraction request, the expert extraction platform 130 can extract the bid evaluation experts corresponding to the preset project and meeting the extraction requirements from the expert database, and send the expert information of the extracted bid evaluation experts to the intelligent bidding platform 110. Among them, the expert information of the bid evaluation experts can include any information related to the bid evaluation experts, such as the specialty, age, province or city where they are located, whether they are employed, education background, position, etc.

[0049] It should be noted that in the embodiments of the present application, the evaluation experts who enter the created virtual meeting room corresponding to the preset project for bid evaluation are the evaluation experts extracted by the expert extraction platform 130 according to the project information and extraction requirements of the preset project. After the intelligent recruitment platform 110 receives the expert information of the evaluation experts extracted by the expert extraction platform 130, the video conference bid evaluation tool 111 can determine which evaluation experts are for the bid evaluation of the preset project based on the expert information of the evaluation experts corresponding to the preset project that has been extracted. Then, after these evaluation experts log in to the video conference bid evaluation tool 111, a bid evaluation expert display interface for the preset project is displayed, so that these evaluation experts can click the join video conference button displayed on the bid evaluation expert display interface of the preset project and join the virtual meeting room corresponding to the preset project for bid evaluation with one click.

[0050] Furthermore, after the experts are extracted, the extracted evaluation experts can also be notified by means of text messages, phone calls, instant messaging, etc. And in order for the supervision platform 120 to supervise the bid evaluation process of the evaluation experts extracted by the expert extraction platform 130, the intelligent recruitment platform 110 can also synchronize the expert information of the evaluation experts extracted by the expert extraction platform 130 to the supervision platform 120. That is, the intelligent recruitment platform 110 is also used to synchronize the expert information and project information of the evaluation experts to the intelligent remote bid evaluation supervision platform 120.

[0051] In the embodiments of the present application, the bid evaluation agency, bid evaluation sub-center, bid evaluation room, and bid evaluation seats can be deployed in such a way that one bid evaluation agency includes at least one bid evaluation sub-center, one bid evaluation sub-center includes at least one bid evaluation room, and one bid evaluation room includes at least one bid evaluation seat. The supervision platform 120 can manage the bid evaluation agency, bid evaluation sub-center, bid evaluation room, and bid evaluation seats in advance. For example, it can pre-store the identifiers of at least one bid evaluation sub-center included in at least one bid evaluation agency, the identifiers of at least one bid evaluation room included in each bid evaluation sub-center, and the identifiers of at least one bid evaluation seat included in each bid evaluation room. And when the video conference bid evaluation tool 111 is installed in the terminal device corresponding to the bid evaluation seat, the video conference bid evaluation tool 111 can automatically generate a seat code and bind the seat code to the identifier of the bid evaluation seat stored in the supervision platform 120. Among them, the terminal device can be any device capable of running the video conference bid evaluation tool 111, such as a computer.

[0052] For each bid evaluation expert who enters the virtual meeting room through the video conferencing bid evaluation tool 111 to conduct remote bid evaluation on a preset project, the video conferencing bid evaluation tool 111 can determine the bid evaluation position where the bid evaluation expert is located. Thus, the first camera in the terminal device at the bid evaluation position where the bid evaluation expert is located or the second camera connected to the terminal device can collect the facial video image of the bid evaluation expert in real time, and the video conferencing bid evaluation tool 111 can collect the screen operation image of the display interface of the terminal device in real time. Thus, the video conferencing bid evaluation tool 111 can obtain the facial video image and the screen operation image of the bid evaluation expert during the bid evaluation process of the preset project in real time, and then send the facial video image and the screen operation image to the supervision platform 120. Among them, the video conferencing bid evaluation tool 111 can send the facial video image and the screen operation image of the bid evaluation expert during the bid evaluation process of the preset project to the video conferencing service module in the supervision platform 120 in real time.

[0053] In addition, for each bid evaluation expert who successfully logs in to the video conferencing bid evaluation tool 111, the supervision platform 120 can determine the bid evaluation position and the bid evaluation room where the bid evaluation expert is located, and then retrieve the monitoring image of the bid evaluation room where the bid evaluation expert is located collected by the third camera installed in the bid evaluation room where the bid evaluation expert is located (that is, the bid evaluation room where the bid evaluation position of the video conferencing bid evaluation tool 111 is located), and obtain the monitoring image of the bid evaluation room where the bid evaluation expert is located in real time during the bid evaluation process of the preset project when the bid evaluation expert enters the virtual meeting room. Among them, the video monitoring management module in the supervision platform 120 can obtain the supervision image of the bid evaluation room where the bid evaluation expert is located in real time.

[0054] Furthermore, the supervision platform 120 can evaluate the bid evaluation process of each bid evaluation expert for the preset project according to the facial video images, screen operation images of each bid evaluation expert and the monitoring images of the bid evaluation rooms where each bid evaluation expert is located. Among them, the intelligent analysis and warning module in the supervision platform 120 can evaluate the bid evaluation process of each bid evaluation expert for the preset project.

[0055] In the embodiment of the present application, evaluating the bid evaluation process of each bid evaluation expert may include identifying whether there is at least one of the following abnormal behaviors in the evaluation process of each bid evaluation expert: the bid evaluation expert views other display interfaces unrelated to the bid evaluation project through the terminal device, the bid evaluation expert uses a communication device, the bid evaluation expert is not the expert himself / herself, the bid evaluation expert leaves the post or someone breaks into the bid evaluation room where the bid evaluation expert is located. When it is identified that the bid evaluation expert has at least one of the above abnormal behaviors, a warning message can be output. Among them, the warning message may include information such as the project information of the current preset project, the expert information of the bid evaluation expert with abnormal behavior, the warning content (such as not being the expert himself / herself, leaving the post or someone breaking in), the warning time, and the warning evidence photo (a screenshot of the facial video image, the screen operation image or the monitoring image), etc.

[0056] Specifically, for each bid evaluation expert, during the bid evaluation process of the preset project by the bid evaluation expert, the supervision platform 120 can, based on the facial video image of the bid evaluation expert, or the facial video image combined with the monitoring image of the bid evaluation room where the bid evaluation expert is located, identify whether the bid evaluation expert has at least one of the following abnormal behaviors during the bid evaluation process: the bid evaluation expert is not the expert himself / herself, the bid evaluation expert leaves the post, or someone else breaks into the bid evaluation room where the bid evaluation expert is located; based on the screen operation image of the terminal device where the video conference bid evaluation tool 111 is located, identify whether the bid evaluation expert views other display interfaces unrelated to the bid evaluation project through the terminal device; based on the facial video image of the bid evaluation expert, or the facial video image combined with the monitoring image of the bid evaluation room where the bid evaluation expert is located, use communication device detection technology to detect whether the bid evaluation expert uses communication devices such as mobile phones. Among them, the bid evaluation expert leaving the post can mean that the bid evaluation expert does not conduct bid evaluation at the bid evaluation position.

[0057] That is, in the embodiment of the present application, the supervision platform 120 is specifically used for: obtaining the facial video image of the bid evaluation expert, the screen operation image of the terminal device where the video conference bid evaluation tool is located, and the monitoring image of the bid evaluation room where the bid evaluation expert is located; among them, the facial video image, the screen operation image, and the monitoring image are collected in real time during the bid evaluation process of the preset project by the bid evaluation expert; based on the facial video image, the screen operation image, and the monitoring image, evaluate the bid evaluation process of the preset project by the bid evaluation expert. In the embodiment of the present application, the supervision platform 120 is specifically used for: during the bid evaluation process of the preset project by the bid evaluation expert, based on the facial video image, identify the abnormal behaviors of the bid evaluation expert during the bid evaluation process, where the abnormal behaviors include at least one of the following behaviors: the bid evaluation expert is not the expert himself / herself, the bid evaluation expert leaves the post, or someone else breaks into the bid evaluation room where the bid evaluation expert is located.

[0058] Further, after the supervision platform 120 obtains the facial video images of each bid evaluation expert, the screen operation images of the terminal devices where the video conference bid evaluation tools 111 are located, and the monitoring images of the bid evaluation rooms where each bid evaluation expert is located, it can also record these three types of images in real time respectively to obtain facial video data, screen operation video data, and monitoring video data. Moreover, during the bid evaluation process of each bid evaluation expert for a preset project, the supervision platform 120 can determine which bid evaluation expert is conducting the bid evaluation for which project in which bid evaluation room, so as to associate and store the facial video data, screen operation video data, and monitoring video data with the bid evaluation expert and the preset project currently being evaluated to meet the needs of bid evaluation process data archiving and bid evaluation supervision. Furthermore, when it is necessary to display or view the facial video data, screen operation video data, and monitoring video data of a certain bid evaluation expert, the facial video data, screen operation video data, and monitoring video data associated with this bid evaluation expert can be fused to obtain the fused target audio-visual data and the fused target audio-visual data can be displayed or viewed through a display interface (that is, the facial video data, screen operation video data, and monitoring video data of a bid evaluation expert are simultaneously displayed on a display interface). When it is necessary to display or view the facial video data, screen operation video data, and monitoring video data of each bid evaluation expert for a preset bid evaluation project, the facial video data, screen operation video data, and monitoring video data of each bid evaluation expert associated with this preset project can be fused to obtain another fused target audio-visual data and the fused another target audio-visual data can be displayed or viewed through a display interface (that is, the facial video data, screen operation video data, and monitoring video data of each bid evaluation expert are simultaneously displayed on a display interface). Thus, separate recording of the three-way video data of each bid evaluation expert, fused display or viewing of the three-way video data of each bid evaluation expert, and fused display or viewing of the multi-way video data of each bid evaluation expert for a preset project can be achieved.

[0059] Among them, the recording of the facial video images and the screen operation images can be implemented by the video conference service module of the supervision platform 120, the recording of the monitoring images can be implemented by the video monitoring management module of the supervision platform 120, and the video fusion module of the supervision platform 120 can obtain the facial video data and the screen operation video data from the video conference service module and obtain the monitoring video data from the video monitoring management module, so as to further implement the fusion of the facial video data, the screen operation video data, and the monitoring video data.

[0060] Among them, the display of the target audio-visual data can be real-time display during the bid evaluation process or display as historical video data after the bid evaluation is completed, and this application does not limit this.

[0061] Among them, during the bid evaluation process, for example, when it is necessary to display the monitoring images of the bid evaluation rooms scattered in different locations, the monitoring images of the bid evaluation rooms can be connected to the video conference through the interface configuration method to meet the need for scene monitoring of the bid evaluation rooms.

[0062] Thus, during the bid evaluation process where the bid evaluation experts conduct remote bid evaluation on the preset project, the supervision platform 120 can achieve all-round integrated monitoring of the facial video images of the bid evaluation experts, the screen operation images of the terminal devices where the video conference bid evaluation tools 111 are located, and the monitoring images of the bid evaluation rooms where the bid evaluation experts are located, and can conduct real-time intelligent analysis on these images. When abnormal behaviors of the bid evaluation experts are found, intelligent early warning reminders are given, so as to achieve intelligent supervision of the bid evaluation process, timely discover and prevent abnormal behaviors in advance. In addition, the three-way video data of each bid evaluation expert can be monitored and the video recordings can be retrieved simultaneously according to the bid evaluation expert dimension or the project dimension, so as to achieve controllability, retrievability, and traceability of the entire bid evaluation process, and ensure the legality and compliance of the bid evaluation work.

[0063] In the embodiment of the present application, in addition to having the functions of querying real-time video data, historical video data, and intelligent early warning, the supervision platform 120 can also provide a visualization large screen display and a display interface for a virtual conference room to facilitate relevant personnel to monitor and view the bid evaluation process of the bid evaluation experts.

[0064] In addition, referring to Figure 2 , the supervision platform 120 can also be integrally docked with the third-party supervision platform 140. Among them, the third-party supervision platform refers to a platform used to supervise third-party services. For example, the third-party supervision platform can be a procurement supervision platform for supervising procurement transactions. The supervision platform 120 can receive the third-party early warning information sent by the third-party supervision platform 140 to centrally display and manage the third-party early warning information. Among them, the third-party early warning information sent by the procurement supervision platform can include early warning information on abnormal situations existing in third-party services such as non-payment of bid bond, existence of affiliated relationships, existence of business anomalies, existence of illegal and dishonest situations, existence of administrative penalty situations, existence of bribery and crime behaviors, and too high similarity of bid documents.

[0065] It should be noted that in the embodiments of the present application, the supervision platform 120 realizes the access of devices such as cameras, NVRs (Network Video Recorders), and DVRs (Digital Video Recorders) from different manufacturers through a unified customized system abstraction interface. Through network protocols such as device SDKs (Software Development Kits), RTMP (Real Time Messaging Protocol), ONVIF (Open Network Video Interface Forum), GB28181 (national standard protocol), and RTSP (Real Time Streaming Protocol), functions such as obtaining the real-time stream and recordings of monitoring devices, as well as setting parameters and remotely controlling the devices are realized.

[0066] Next, with reference to Figure 3 , taking the interaction process among the project manager, bid evaluation experts, supervision platform, and bid supervision personnel as an example, the method for bid evaluation based on the above intelligent remote bidding system will be described. Among them, Figure 3 is the interaction schematic diagram of the project manager, bid evaluation experts, supervision platform, and bid supervision personnel provided by the embodiments of the present application. Among them, the bid supervision personnel can be, for example, personnel who supervise the bid evaluation process such as project managers, disciplinary inspection departments, and conference staff.

[0067] With reference to Figure 3, after the project manager logs in to the video conferencing bid evaluation tool 111 (step 301) and enters the project manager display interface of the preset project, a virtual meeting room can be created with one click (step 302). When the current bid evaluation expert logs in to the video conferencing bid evaluation tool 111 (step 303), the video conferencing bid evaluation tool 111 can first determine whether the face image of the current bid evaluation expert has been pre-collected (step 304). If the face image of the current bid evaluation expert has not been collected, the current bid evaluation expert can be prompted to first perform face image collection and collect the face image of the current bid evaluation expert (step 305). If the face image of the current bid evaluation expert has been collected, then face recognition can be performed on the current bid evaluation expert (step 306), and then it can be determined whether the current bid evaluation expert is the expert himself (step 307). Specifically, the current face image of the current bid evaluation expert can be collected and compared with the pre-collected face image of the current bid evaluation expert. If they are inconsistent, it can be determined that the current bid evaluation expert is not the expert himself, and the current expert is not allowed to log in to the video conferencing bid evaluation tool. If the current face image is consistent with the pre-collected face image of the current bid evaluation expert, it can be determined that the current bid evaluation expert is the expert himself, so that the current bid evaluation expert is allowed to log in to the video conferencing bid evaluation tool 111, that is, the current bid evaluation expert can successfully log in to the video conferencing bid evaluation tool 111 (step 308). After the current bid evaluation expert successfully logs in to the video conferencing bid evaluation tool 111 and enters the bid evaluation expert display interface of the preset project, the virtual meeting room created by the project manager can be joined with one click (step 309), and the preset project can be evaluated (step 310). After the evaluation is completed, the video conferencing bid evaluation tool can be exited (step 311).

[0068] After the current bid evaluation expert logs in to the video conferencing bid evaluation tool 111, the supervision platform 120 can determine the bid evaluation seat and bid evaluation room where the current bid evaluation expert is located, and retrieve the monitoring video of the bid evaluation room collected by the third camera installed in the bid evaluation room where the current bid evaluation expert is located. In addition, after the current bid evaluation expert enters the virtual meeting room, the video conferencing bid evaluation tool 111 can send the facial video of the current bid evaluation expert collected in real time by the first camera in the terminal device of the bid evaluation seat where the bid evaluation expert is located or the second camera connected to the terminal device, and the screen operation video collected by the video conferencing bid evaluation tool 111 in real time from the display interface of the terminal device to the supervision platform 120. Thus, the supervision platform 120 can obtain the monitoring video of the bid evaluation room where the current bid evaluation expert is located (step 312), and obtain the facial video and screen operation video of the current bid evaluation expert (step 313), and then record and fuse the three videos separately (step 314) to obtain the target audio-visual data.

[0069] In addition, during the bid evaluation process of the current bid evaluation expert for the preset project, the supervision platform 120 can perform intelligent analysis on the facial video image of the current bid evaluation expert (step 315), and then determine whether the current bid evaluation expert has abnormal behaviors such as not being the expert himself, leaving the post, or someone breaking into the bid evaluation room where he is located (step 316). If not, continue to perform intelligent analysis on the facial video image of the current bid evaluation expert. If the current bid evaluation expert has abnormal behaviors, warning information can be pushed to warn the bid supervision personnel through the supervision platform.

[0070] After receiving the warning from the supervision platform 120, the bid supervision personnel can process the warning in a timely manner (step 317). When processing the warning, the bid supervision personnel can view the target audio-visual data recorded and integrated by the supervision platform (step 318) to find evidence of the abnormal behaviors of the current bid evaluation expert.

[0071] In summary, the intelligent remote bid evaluation supervision system of the embodiments of the present application can facilitate the efficient and safe entry of bid evaluation experts into the virtual meeting room through the video conference bid evaluation tool, and conduct remote bid evaluation on the preset project in the virtual meeting room. Moreover, the supervision platform can be used to intelligently supervise the bid evaluation process of the bid evaluation experts for the preset project. And through the supervision platform in the intelligent remote bid evaluation supervision system, it is possible to achieve all-round integrated monitoring of the facial video image of the bid evaluation expert, the screen operation image of the terminal device where the video conference bid evaluation tool is located, and the monitoring image of the bid evaluation room where the bid evaluation expert is located, and can perform real-time intelligent analysis on these images. When abnormal behaviors of the bid evaluation expert are found, intelligent warning reminders are given, so as to achieve intelligent supervision of the bid evaluation process, timely discover and prevent abnormal behaviors at an early stage. In addition, according to the bid evaluation expert dimension or project dimension, the three-way video data of each bid evaluation expert can be monitored and the video recordings can be viewed simultaneously, so as to realize the controllability, retrievability, and traceability of the entire bid evaluation process, and ensure the legality and compliance of the bid evaluation work.

[0072] Based on the above intelligent remote bid evaluation supervision system, the present application provides a method, device, electronic device, and storage medium for determining abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference. Next, the method, device, electronic device, and storage medium for determining abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference according to the embodiments of the present application will be described with reference to the accompanying drawings.

[0073] Figure 4 It is a flowchart showing the method for determining abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference provided by the embodiments of the present application.

[0074] It should be noted that the method for determining abnormal behaviors of evaluation experts during the remote bid evaluation video conference provided in the embodiments of the present application can be executed by an abnormal behavior determination device for evaluation experts during the remote bid evaluation video conference. Hereinafter, the abnormal behavior determination device for evaluation experts during the remote bid evaluation video conference will be simply referred to as the abnormal behavior determination device. This abnormal behavior determination device can be configured in an intelligent remote bid evaluation supervision platform to automatically determine whether there are others breaking into the bid evaluation room of the evaluation expert during the remote bid evaluation process and reduce the labor cost of manual monitoring.

[0075] As Figure 4 shown, the method for determining abnormal behaviors of evaluation experts during the remote bid evaluation video conference may include the following steps:

[0076] Step 401, during the process of an evaluation expert conducting remote bid evaluation on a preset project through a video conference bid evaluation tool, obtain the facial video image of the evaluation expert.

[0077] Among them, the preset project refers to the project that the evaluation expert is currently evaluating.

[0078] Among them, the facial video image is collected in real time by the first camera installed in the terminal device or the second camera connected to the terminal device during the bid evaluation process.

[0079] In the embodiments of the present application, during the process of an evaluation expert conducting remote bid evaluation on a preset project through a video conference bid evaluation tool, the video conference bid evaluation tool can determine the bid evaluation position of the evaluation expert. Thus, the first camera in the terminal device of the bid evaluation position where the evaluation expert is located, or the second camera connected to the terminal device, can collect the facial video image of the evaluation expert in real time. After the video conference bid evaluation tool obtains the facial video image of the evaluation expert collected by the first camera or the second camera, it can send the facial video image to the abnormal behavior determination device in real time. Correspondingly, during the process of an evaluation expert conducting remote bid evaluation on a preset project through a video conference bid evaluation tool, the abnormal behavior determination device can obtain the facial video image of the evaluation expert in real time.

[0080] Step 402, perform human body detection on the facial video image to identify the human body parts included in the facial video image.

[0081] Step 403, determine whether the human body parts belong to the same human body.

[0082] Among them, the human body part can include any body part of the human body, such as at least one of the head, left hand, right hand, left leg, right leg, left foot, right foot, upper body, whole body, etc. Among them, the upper body can be the upper body including the head or the upper body not including the head, and this application does not limit this. The whole body can be the whole body including the head or the whole body not including the head, and this application does not limit this.

[0083] Identifying the human body parts included in the facial video frame can include identifying the part information of each human body part included in the facial video frame. Furthermore, the abnormal behavior determination device can determine whether the human body parts in the facial video frame belong to the same human body according to the part information of the human body parts included in the identified facial video frame. Among them, the part information of the human body part can include the position information and quantity information of the human body part. Among them, the position information can include the position coordinates of the detection frame to which the corresponding human body part belongs. The quantity information can include the quantity of the same type of human body parts included in the facial video frame, such as the quantity of the left hand, the quantity of the right hand, etc.

[0084] In the embodiment of this application, a human body detection model can be pre-trained. The input of the human body detection model is an image, and the output is the part information of the human body parts included in the image. Among them, the part information of the human body part can include the position information and quantity information of the human body part. Furthermore, after obtaining the facial video frame of the evaluation expert, the facial video frame can be input into the trained human body detection model to perform human body detection on the facial video frame by using the trained human body detection model, so as to obtain the part information of the human body parts included in the facial video frame. Furthermore, the abnormal behavior determination device can determine whether the human body parts in the facial video frame belong to the same human body according to the part information of the human body parts included in the facial video frame identified by the human body detection model.

[0085] Among them, the human body detection model can be any neural network model capable of realizing human body detection, and this application does not limit the type of the human body detection model.

[0086] The human body detection model can be obtained by training the initial human body detection model in a deep learning manner by using preset training data. The training process can refer to related technologies, and this application will not elaborate on this. Compared with other machine learning methods, deep learning performs better on large datasets. Among them, the preset training data can include multiple sample images, and each sample image is labeled with the sample part information of the human body parts included therein. Among them, the sample part information can include the sample position information and sample quantity information of the human body parts included in the sample image.

[0087] It should be noted that in the remote bid evaluation video conference scenario of the embodiments of the present application, the probability that at least one of the head, upper body, and whole body appears in the facial video image of the bid evaluation expert is relatively high. Therefore, when using the trained human body detection model to perform human body detection on the facial video image in the embodiments of the present application, the human body parts that need to be recognized may only include at least one of the head, upper body, and whole body. Moreover, the preset training data used for training the initial human body detection model may include a large number of sample images containing at least one of the head, upper body, and whole body in this scenario. The sample images are labeled with the sample part information of at least one of the head, upper body, and whole body contained therein, so as to improve the recognition accuracy of the trained human body detection model for the head, upper body, and whole body in this scenario through big data learning using a large number of sample images containing at least one of the head, upper body, and whole body.

[0088] When the human body parts included in the recognized facial video image include at least one of the head, upper body, and whole body, the abnormal behavior determination device may adopt the following method to determine whether the human body parts belong to the same human body according to the part information of the human body parts included in the recognized facial video image:

[0089] According to the quantity information of the human body parts included in the facial video image, determine whether the quantity of the same type of human body parts included in the facial video image is greater than the quantity of this type of human body parts included in a normal single human body. If so, it can be determined that the human body parts included in the recognized facial video image do not belong to the same human body. If not, the abnormal behavior determination device may determine whether the regions where the human body parts are located are adjacent to each other according to the position information of each human body part recognized by the human body recognition model in the facial video image. If the regions where the human body parts are located are not adjacent to each other, it can be determined that the human body parts included in the recognized facial video image do not belong to the same human body. If the regions where the human body parts are located are adjacent to each other, it can be determined that the human body parts included in the recognized facial video image belong to the same human body.

[0090] For example, assume that the number of heads included in the facial video image recognized by the human body detection model is 2, then it can be determined that the human body parts included in the recognized facial video image do not belong to the same human body.

[0091] Or, assume that the number of heads included in the facial video image recognized by the human body detection model is 1, the number of upper bodies without heads is 1, but the region where the head is located is in the lower left corner of the facial video image, and the upper body without a head is in the upper right corner of the facial video image, and the two regions are not adjacent, then it can be determined that the head and the upper body included in the recognized facial video image do not belong to the same human body.

[0092] Step 404, when the human body parts do not belong to the same human body, it is determined that someone has broken into the evaluation committee expert's evaluation room.

[0093] In the embodiment of the present application, when the abnormal behavior recognition device determines that the human body parts in the facial video image do not belong to the same human body, it can be determined that someone has broken into the evaluation committee expert's evaluation room; when it is determined that the human body parts in the facial video image belong to the same human body, it is determined that there is no one else breaking into the evaluation committee expert's evaluation room.

[0094] In addition, when performing human body detection on the facial video image and no human body parts are recognized in the facial video image, the subsequent steps can be stopped.

[0095] It should be noted that in the embodiment of the present application, during the entire process of remote bid evaluation, the facial video image of the evaluation committee expert can be obtained at a preset time interval, and at the moment when the facial video image of the evaluation committee expert is obtained, it is determined whether there is anyone else breaking into the evaluation committee expert's evaluation room according to the facial video image obtained at that moment. Among them, the preset time interval can be set arbitrarily according to needs, for example, it can be set to 30 seconds, 20 seconds, etc. Compared with continuously monitoring manually whether there is anyone else breaking into the evaluation committee expert's evaluation room during the entire process of remote bid evaluation, the method for recognizing abnormal behavior of evaluation committee experts during the remote bid evaluation video conference provided by the embodiment of the present application can reduce labor costs.

[0096] In the embodiment of the present application, after it is determined that someone has broken into the evaluation committee expert's evaluation room, a warning message can be output to prompt the project manager or other bid supervision personnel that there is an abnormal behavior of the evaluation committee expert during the bid evaluation process. Among them, the warning message can include information such as the project information of the current preset project, the expert information of the evaluation committee expert with abnormal behavior, the warning content (such as someone has broken into the evaluation committee expert's evaluation room), the warning time, and the warning evidence photo (such as a screenshot of the facial video image), etc.

[0097] In addition, it can be understood that the evaluation committee expert needs to log in to the video conference bid evaluation tool to conduct remote bid evaluation on the preset project through the video conference bid evaluation tool. In the embodiment of the present application, when the evaluation committee expert logs in to the video conference bid evaluation tool, the abnormal behavior recognition device can also determine whether the evaluation committee expert currently performing the login operation is the evaluation committee expert himself. When it is determined that it is the evaluation committee expert himself who logs in, it is determined that the evaluation committee expert has successfully logged in to the video conference bid evaluation tool, and then during the bid evaluation process, it is determined whether there is anyone else breaking into the evaluation committee expert's evaluation room. That is, the method provided by the embodiment of the present application can also include before the evaluation committee expert conducts remote bid evaluation on the preset project through the video conference bid evaluation tool:

[0098] Authenticate the identity of the bid evaluation experts, and when the identity authentication of the bid evaluation experts is passed, determine that the bid evaluation experts have successfully logged in to the video conference bid evaluation tool.

[0099] Specifically, when the bid evaluation expert registers the expert account of the video conference bid evaluation tool, the abnormal behavior determination device can collect the face image of the bid evaluation expert himself. When the bid evaluation expert logs in to the video conference bid evaluation tool, the abnormal behavior determination device can collect the current face image of the bid evaluation expert who is currently performing the login operation, and compare the current face image with the pre-collected face image of the bid evaluation expert himself. If the current face image is consistent with the pre-collected face image of the bid evaluation expert himself, it can be determined that the bid evaluation expert who is currently performing the login operation is the bid evaluation expert himself, that is, the identity authentication of the bid evaluation expert is passed, and it is determined that the bid evaluation expert who is currently performing the login operation has successfully logged in to the video conference bid evaluation tool. If the current face image is inconsistent with the pre-collected face image of the bid evaluation expert himself, it can be determined that the bid evaluation expert who is currently performing the login operation is not the bid evaluation expert himself, that is, the identity authentication of the bid evaluation expert fails, and thus the bid evaluation expert who is currently performing the login operation is not allowed to log in to the video conference bid evaluation tool.

[0100] Among them, the face features in the current face image can be extracted, and the face features in the current face image can be matched with the known face features of the bid evaluation expert to obtain the matching degree between the face features in the current face image and the known face features, and then the matching degree can be compared with the preset matching degree threshold to determine whether the current face image is consistent with the pre-collected face image of the bid evaluation expert himself. Among them, the known face features of the bid evaluation expert are the face features extracted from the pre-collected face image of the bid evaluation expert himself.

[0101] In summary, in the method for determining abnormal behavior of bid evaluation experts during the remote bid evaluation video conference in the embodiments of the present application, during the process of the bid evaluation experts remotely evaluating a preset project through the video conference bid evaluation tool, the facial video screen of the bid evaluation experts is obtained, and human body detection is performed on the facial video screen to identify the preset human body parts included in the facial video screen, and it is determined whether the human body parts belong to the same human body. In the case where the human body parts do not belong to the same human body, it is determined that someone has broken into the bid evaluation room where the bid evaluation expert is located, realizing the automatic determination of whether someone has broken into the bid evaluation room where the bid evaluation expert is located during the remote bid evaluation process, and reducing the labor cost of manual monitoring.

[0102] As described above Figure 4 Corresponding to the method for determining abnormal behavior of bid evaluation experts during the remote bid evaluation video conference provided in the above Figure 4The method for determining the abnormal behavior of the evaluation experts during the remote bid evaluation video conference provided by the embodiment corresponds to the method for determining the abnormal behavior of the evaluation experts during the remote bid evaluation video conference provided by this application. Therefore, the implementation manner of the method for determining the abnormal behavior of the evaluation experts during the remote bid evaluation video conference is also applicable to the device for determining the abnormal behavior of the evaluation experts during the remote bid evaluation video conference provided by the embodiments of this application, and will not be described in detail in the embodiments of this application.

[0103] Figure 5 It is a schematic structural diagram of the device for determining the abnormal behavior of the evaluation experts during the remote bid evaluation video conference provided by the embodiments of this application.

[0104] As Figure 5 shown, the device 500 for determining the abnormal behavior of the evaluation experts during the remote bid evaluation video conference may include: an acquisition module 510, an identification module 520, a judgment module 530, and a first determination module 540.

[0105] Among them, the acquisition module 510 is configured to acquire the facial video image of the evaluation expert during the process of the evaluation expert remotely evaluating a preset project through the video conference bid evaluation tool;

[0106] The identification module 520 is configured to perform human body detection on the facial video image to identify the human body parts included in the facial video image;

[0107] The judgment module 530 is configured to judge whether the human body parts belong to the same human body;

[0108] The first determination module 540 is configured to determine that there is an intrusion of others in the evaluation room where the evaluation expert is located when the human body parts do not belong to the same human body.

[0109] As a possible implementation manner of the embodiments of this application, the human body parts include at least one of the head, upper body, and whole body;

[0110] The identification module 520 is specifically configured to:

[0111] Adopt a trained human body detection model to perform human body detection on the facial video image to identify the part information of the human body parts included in the facial video image; the part information includes position information and quantity information;

[0112] Among them, the human body detection model is trained by means of deep learning using preset training data; the preset training data includes a plurality of sample images, and each sample image is labeled with the sample part information of the human body parts included therein;

[0113] Correspondingly, the judgment module is specifically configured to:

[0114] Judge whether the human body parts belong to the same human body according to the part information of the human body parts.

[0115] As a possible implementation of the embodiment of the present application, the abnormal behavior recognition device 500 for the evaluation experts during the remote bid evaluation video conference further includes:

[0116] A determination module, configured to authenticate the identity of the evaluation expert, and determine that the evaluation expert has successfully logged in to the video conference bid evaluation tool when the identity authentication of the evaluation expert passes.

[0117] As a possible implementation of the embodiment of the present application, the abnormal behavior recognition device 500 for the evaluation experts during the remote bid evaluation video conference further includes:

[0118] A second recognition module, configured to recognize that no one else has broken into the bid evaluation room where the evaluation expert is located when the human body parts belong to the same human body.

[0119] The abnormal behavior recognition device for the evaluation experts during the remote bid evaluation video conference in the embodiment of the present application obtains the facial video image of the evaluation expert during the process of the evaluation expert remotely evaluating a preset project through the video conference bid evaluation tool, performs human body detection on the facial video image to identify the preset human body parts included in the facial video image, determines whether the human body parts belong to the same human body, and when the human body parts do not belong to the same human body, recognizes that someone else has broken into the bid evaluation room where the evaluation expert is located, realizing the automatic recognition of whether someone else has broken into the bid evaluation room where the evaluation expert is located during the remote bid evaluation process, and reducing the labor cost of manual monitoring.

[0120] To implement the above embodiment, the present application further proposes an electronic device, which may include: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it executes the abnormal behavior recognition method for the evaluation experts during the remote bid evaluation video conference proposed in the first aspect embodiment of the present application as described above.

[0121] It should be noted that the above explanation of the embodiment of the abnormal behavior recognition method for the evaluation experts during the remote bid evaluation video conference proposed in the first aspect embodiment is also applicable to the electronic device of this embodiment, and will not be repeated here.

[0122] The electronic device in the embodiment of the present application obtains the facial video image of the evaluation expert during the process of the evaluation expert remotely evaluating a preset project through the video conference bid evaluation tool, performs human body detection on the facial video image to identify the preset human body parts included in the facial video image, determines whether the human body parts belong to the same human body, and when the human body parts do not belong to the same human body, recognizes that someone else has broken into the bid evaluation room where the evaluation expert is located, realizing the automatic recognition of whether someone else has broken into the bid evaluation room where the evaluation expert is located during the remote bid evaluation process, and reducing the labor cost of manual monitoring.

[0123] To implement the above embodiments, the present application also proposes a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, it implements the method for identifying abnormal behaviors of bid evaluation experts during the remote bid evaluation video conference proposed in the foregoing first aspect embodiment of the present application.

[0124] To implement the above embodiments, the present application also provides a computer program product, which includes a computer program that implements the method for identifying abnormal behaviors of bid evaluation experts during the remote bid evaluation video conference proposed in the foregoing first aspect embodiment of the present application when executed by a processor.

[0125] Figure 6 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0126] As Figure 6 shown, the electronic device may include:

[0127] A memory 601, a processor 602, and a computer program stored on the memory 601 and executable on the processor 602.

[0128] When the processor 602 executes the program, it implements Figure 4 the method for identifying abnormal behaviors of bid evaluation experts during the remote bid evaluation video conference provided in the embodiment shown.

[0129] Further, the electronic device may further include:

[0130] A communication interface 603 for communication between the memory 601 and the processor 602.

[0131] The memory 601 is used to store a computer program executable on the processor 602.

[0132] The memory 601 may include a high-speed RAM memory and may also include a non-volatile memory, such as at least one disk memory.

[0133] The processor 602 is used to implement Figure 4 the method for identifying abnormal behaviors of bid evaluation experts during the remote bid evaluation video conference described in the embodiment shown when executing the program.

[0134] If the memory 601, the processor 602, and the communication interface 603 are implemented independently, the communication interface 603, the memory 601, and the processor 602 can be interconnected via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 it is represented by only a thick line in Figure 6 , but this does not mean that there is only one bus or one type of bus.

[0135] Optionally, in a specific implementation, if the memory 601, the processor 602, and the communication interface 603 are integrated on a single chip, the memory 601, the processor 602, and the communication interface 603 can communicate with each other via an internal interface.

[0136] The processor 602 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0137] In the description of this specification, the descriptions with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0138] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0139] Any process or method description represented in the flowchart or described otherwise herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logic function or process. The scope of the preferred embodiments of the present application includes additional implementations, where functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0140] The logic and / or steps represented in the flowchart or described otherwise herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0141] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0142] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above-described embodiment methods can be completed by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0143] In addition, in each of the embodiments of the present application, the functional units can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0144] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for identifying abnormal behaviors of bid evaluation experts during a remote bid evaluation video conference, characterized in that, The method is applied to the intelligent remote bid evaluation supervision platform of the intelligent remote bid evaluation supervision system, and the intelligent remote bid evaluation supervision platform is deployed on the enterprise cloud; the intelligent remote bid evaluation supervision system further includes a smart tendering platform for processing bidding and procurement operations and an expert extraction platform communicatively connected to the smart tendering platform. The expert extraction platform is used to extract bid evaluation experts participating in the bid evaluation work of a preset project from multiple candidate bid evaluation experts included in the expert database according to project information and extraction requirements. The video conferencing bid evaluation tool in the smart tendering platform is used to, when it is necessary to conduct bid evaluation on a preset project, the project manager clicks the meeting creation button in the video conferencing bid evaluation tool to automatically create a virtual meeting room with one click, and send the video conference number of the virtual meeting room to the video conferencing bid evaluation tool. The project manager, the supervisor, and the bid evaluation experts participating in the bid evaluation work of the preset project all enter the display interface of the preset project through the video conferencing bid evaluation tool, and can only join the virtual meeting room of the preset project with one click through the join video conference button in the display interface; The method includes: Authenticate the identity of the bid evaluation expert through the smart tendering platform, and when the identity authentication of the bid evaluation expert passes, determine that the bid evaluation expert has successfully logged in to the video conferencing bid evaluation tool; During the process of the bid evaluation expert conducting remote bid evaluation on the preset project through the video conferencing bid evaluation tool, the intelligent remote bid evaluation supervision platform is used to obtain and store the facial video images of the bid evaluation expert in real time, and the video conferencing bid evaluation tool is used to obtain and store the screen operation images of the terminal device and the monitoring video images of each bid evaluation expert in the bid evaluation room in real time. The facial video images, the screen operation images, and the monitoring video images are associated with the bid evaluation expert and the preset project being evaluated currently and stored, so that when it is necessary to view the facial video images, screen operation images, and monitoring video images of the bid evaluation expert, the facial video images, screen operation images, and monitoring video images associated with the bid evaluation expert are fused, and the fused target audio-visual data is displayed; among them, during the process of conducting remote bid evaluation on the preset project, the monitoring video images are also connected to the video conference through the interface configuration method; Use a trained human body detection model to perform human body detection on the facial video images to identify the part information of the human body parts included in the facial video images; the part information includes position information and quantity information; among them, the human body detection model is trained by means of deep learning using preset training data; the preset training data includes multiple sample images, and each sample image is labeled with the sample part information of the human body part included therein; the human body part includes at least one of the head, upper body, and whole body; Judge whether the human body parts belong to the same human body according to the part information of the human body parts; In the case that the human body parts do not belong to the same human body, automatically determine that someone has broken into the bid evaluation room where the bid evaluation expert is located.

2. The method according to claim 1, characterized in that, After determining whether the human body parts belong to the same human body, the following steps are further included: When the human body parts belong to the same human body, it is determined that no one has broken into the evaluation room where the evaluation experts are located.

3. An abnormal behavior recognition device for evaluation experts during a remote bid evaluation video conference, characterized in that, The device is applied to the intelligent remote bid evaluation supervision platform of the intelligent remote bid evaluation supervision system, and the intelligent remote bid evaluation supervision platform is deployed on the enterprise cloud; the intelligent remote bid evaluation supervision system further includes a smart bidding platform for processing bidding and procurement operations and an expert extraction platform communicatively connected to the smart bidding platform. The expert extraction platform is used to extract evaluation experts participating in the bid evaluation work of a preset project from multiple candidate evaluation experts included in the expert database according to project information and extraction requirements. The video conferencing bid evaluation tool in the smart bidding platform is used when it is necessary to conduct bid evaluation on a preset project. The project manager can automatically create a virtual meeting room with one click through the meeting creation button in the video conferencing bid evaluation tool, and send the video conference number of the virtual meeting room to the video conferencing bid evaluation tool. The project manager, supervisor, and evaluation experts participating in the bid evaluation work of the preset project all enter the display interface of the preset project through the video conferencing bid evaluation tool, and can only join the virtual meeting room of the preset project with one click through the join video conference button in the display interface; The device includes: A determination module, configured to authenticate the identity of the evaluation expert through the smart bidding platform, and determine that the evaluation expert has successfully logged in to the video conferencing bid evaluation tool when the identity authentication of the evaluation expert is passed; An acquisition module, configured to, during the process of the evaluation expert remotely evaluating the preset project through the video conferencing bid evaluation tool, obtain and store the facial video images of the evaluation expert in real time through the intelligent remote bid evaluation supervision platform, obtain and store the screen operation images of the terminal device and the monitoring video images of each evaluation expert in the bid evaluation room in real time through the video conferencing bid evaluation tool, associate and store the facial video images, the screen operation images, and the monitoring video images with the evaluation expert and the preset project being evaluated currently, so as to, when it is necessary to view the facial video images, screen operation images, and monitoring video images of the evaluation expert, fuse the facial video images, screen operation images, and monitoring video images associated with the evaluation expert, and display the fused target audio-visual data; wherein, during the process of remotely evaluating the preset project, the monitoring video images are also connected to the video conference through an interface configuration method; An identification module, configured to perform human body detection on the facial video images by using a trained human body detection model to identify the part information of the human body parts included in the facial video images; the part information includes position information and quantity information; wherein, the human body detection model is trained by using deep learning with preset training data; the preset training data includes multiple sample images, and each sample image is labeled with the sample part information of the human body parts included therein; the human body parts include at least one of the head, upper body, and whole body; A judgment module, configured to judge whether the human body parts belong to the same human body according to the part information of the human body parts; A first determination module, configured to automatically determine that someone has broken into the evaluation committee room where the evaluation experts are located when the human body parts do not belong to the same human body.

4. The device according to claim 3, characterized in that, It further includes: A second determination module, configured to automatically determine that no one has broken into the evaluation committee room where the evaluation experts are located when the human body parts belong to the same human body.

5. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it executes the method for determining abnormal behaviors of evaluation experts during a remote evaluation video conference as described in claim 1 or 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for determining abnormal behaviors of evaluation experts during a remote evaluation video conference as described in claim 1 or 2.

Images