Automatic Generation Method of Bid Evaluation Video

By automatically determining the start and end time of the evaluation video based on the project information and video recording equipment, the evaluation video is obtained from the video recording equipment and the video recording is stored in association with the project, and the separation of the evaluation video and the service system is solved. The large workload and uncertainty of recording cropping enable automatic acquisition of video and resource conservation.

CN118072409BActive Publication Date: 2024-11-08BEIJING JINGNENG TENDERING & COLLECTIVE PROCUREMENT CENT CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202311485094.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-08
Publication Date
2024-11-08
Estimated Expiration
2043-11-08

AI Technical Summary

Technical Problem

In the prior art, the evaluation and recording videos are completely separated from the business system, and the recording is recorded 24 hours a day, resulting in manual cutting and correlation, which is a large workload and uncertain factors.

Method used

By determining the start and end time of the video recording device and the evaluation video based on the project information, obtaining the evaluation video from the video recording device and storing it in association with the project, the automatic acquisition of the evaluation video is achieved, and avoiding the inconvenience caused by manual operations. Determine the factors.

Benefits of technology

It realizes automatic acquisition of the evaluation and recording video, saves the consumption of video recording equipment and storage resources, ensures the integrity and accuracy of video recording, and reduces the uncertainty of manual operations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118072409B_ABST
    Figure CN118072409B_ABST
Patent Text Reader

Abstract

The present invention relates to a method for automatically generating a bid evaluation video, the method comprising: determining a video recording device according to project information; determining a start time for automatically generating a bid evaluation video according to the project information; determining an end time for automatically generating a bid evaluation video according to a video collected by the video recording device; obtaining the bid evaluation video from the video collected by the video recording device based on the start time and the end time of the video recording; associating the bid evaluation video with the project according to the project information, and storing the association relationship and the bid evaluation video. The method of the present invention determines the start time and the end time for automatically generating a bid evaluation video according to the project information and the video collected by the video recording device, and then obtains the bid evaluation video from the video collected by the video recording device based on the start time and the end time of the video recording, thereby realizing automatic acquisition of the bid evaluation video and avoiding uncertainties caused by manual operation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method for automatically generating bid evaluation videos. Background Art

[0002] The bid evaluation video and business system are completely separated, and the video is recorded 24 hours a day in the bid evaluation room.

[0003] It is necessary to manually cut the video and associate the bid evaluation video with the bid evaluation business, which is a large workload. At the same time, manual operation will also bring some uncertainties. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a method for automatically generating bid evaluation videos.

[0006] (II) Technical solution

[0007] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0008] S101, determining a video recording device according to project information;

[0009] S102, determining the start time of automatically generating the bid evaluation video according to the project information; determining the end time of automatically generating the bid evaluation video according to the video captured by the video recording device;

[0010] S103, obtaining a bid evaluation video from a video captured by a video recording device based on the video recording start time and the video recording end time;

[0011] S104, associating the bid evaluation video with the project according to the project information, and storing the association relationship and the bid evaluation video.

[0012] Optionally, before S102, the method further includes:

[0013] S201, determining the bid evaluation start time according to the project information;

[0014] S202: 30 minutes before the start of the bid evaluation, start the video recording equipment to perform video pre-collection;

[0015] S203, identifying each pre-collected frame to determine whether a person appears;

[0016] S204, if no person appears in all pre-captured frames when the bid evaluation start time arrives, control the video recording device to perform video capture from the bid evaluation start time;

[0017] S205: If the bid evaluation start time has not yet arrived and a person has appeared in the pre-captured frame, the video recording device is controlled to capture the video from the time when the person first appears.

[0018] Optionally, the start time of automatically generating the bid evaluation video is determined according to the project information, including:

[0019] Determine the bid evaluation experts based on the project information;

[0020] The start time for automatic generation of the bid evaluation video is determined based on the time when all bid evaluation experts complete their sign-in.

[0021] Optionally, the start time of automatic generation of bid evaluation video is determined according to the time when all bid evaluation experts complete the sign-in, including:

[0022] The time when the last bid evaluation expert completes signing in is determined as the start time for automatic generation of the bid evaluation video.

[0023] Optionally, the start time of automatic generation of bid evaluation video is determined according to the time when all bid evaluation experts complete the sign-in, including:

[0024] Get the time when each bid evaluation expert first appears;

[0025] Determine the time for each bid evaluation expert to complete the sign-in;

[0026] Calculate the sign-in duration of each bid evaluation expert = time to complete sign-in - time of first appearance;

[0027] Obtain the target video captured by the video recording device; the start time of the target video is the time when the bid evaluation expert first appears, and the end time of the target video is the time when all bid evaluation experts have completed the sign-in;

[0028] Determine anomaly coefficients based on target videos;

[0029] The start time for automatic generation of the bid evaluation video is determined based on the check-in duration and abnormal coefficient of each bid evaluation expert.

[0030] Optionally, determining an abnormality coefficient according to the target video includes:

[0031] Perform character recognition on each frame of the target video to determine whether there is a target image frame; and whether there is a non-evaluation expert in the target image frame;

[0032] If the target image frame does not exist, the abnormal coefficient is determined to be 0;

[0033] If the target image frame exists, the continuity coefficient is determined according to the target image frame, and the abnormal coefficient is determined as the continuity coefficient*the total number of frames of the target image frame / the total number of frames of the target video.

[0034] Optionally, determining the continuous coefficient according to the target image frame includes:

[0035] According to the frame numbers, target image frames with consecutive frame numbers are divided into a group to obtain a target image frame grouping;

[0036] Determine the target number of image frames for each group;

[0037] Determine the average target image frame number = the sum of the target image frame numbers of all groups / number of groups;

[0038] Determine the group size difference = SQRT (SUM (the square of the difference between the number of target image frames in each group and the average number of target image frames) / number of groups); where SQRT() is a square root function and SUM() is a sum function;

[0039] Determine the continuity coefficient = number of groups * difference in group size.

[0040] Optionally, the start time of automatically generating the bid evaluation video is determined according to the check-in duration and abnormal coefficient of each bid evaluation expert, including:

[0041] Determine the average sign-in duration = (the maximum sign-in duration of all bid evaluation experts + the minimum sign-in duration of all bid evaluation experts + 4 * the sum of the sign-in duration of all bid evaluation experts / the total number of bid evaluation experts) / 6;

[0042] Calculate the abnormal value of sign-in duration = average sign-in duration * (1 + abnormal coefficient) / preset sign-in standard duration;

[0043] If the sign-in duration abnormal value is greater than 1, the start time of the automatic generation of the bid evaluation video is determined to be the time when the first bid evaluation expert first appears;

[0044] If the sign-in duration abnormal value is not greater than 1, the time when the last bid evaluation expert completes the sign-in will be determined as the start time of the automatic generation of the bid evaluation video.

[0045] Optionally, determining the end time of automatically generating the bid evaluation video according to the video captured by the video recording device includes:

[0046] The earliest of the following three times is determined as the end time of the automatically generated bid evaluation video:

[0047] The time when the bid evaluation results are uploaded, the time when the end bid evaluation button is triggered, and the preset time after the bid evaluation end time determined based on the project information.

[0048] Optionally, the preset time is 30 minutes or the time when the end frame first appears;

[0049] Among them, there is no person in the end frame.

[0050] (III) Beneficial effects

[0051] Determine the recording device according to the project information; determine the start time of the automatic generation of the bid evaluation video according to the project information; determine the end time of the automatic generation of the bid evaluation video according to the video collected by the recording device; obtain the bid evaluation video from the video collected by the recording device based on the recording start time and the recording end time; associate the bid evaluation video with the project according to the project information, and store the association relationship and the bid evaluation video. The method of the present invention determines the start time and the end time of the automatic generation of the bid evaluation video according to the project information and the video collected by the recording device, and then obtains the bid evaluation video from the video collected by the recording device based on the recording start time and the recording end time, thereby realizing the automatic acquisition of the bid evaluation video and avoiding the uncertainties caused by manual operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A schematic flow chart of a method for automatically generating a bid evaluation video provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0054] The bid evaluation video and business system are completely separated, and the video is recorded 24 hours a day in the bid evaluation room. Manual video editing is required to associate the bid evaluation video with the bid evaluation business, which is a lot of work, and manual operation will also bring some uncertainties.

[0055] Based on this, the present invention relates to a method for automatically generating a bid evaluation video, the method comprising: determining a video recording device according to project information; determining a start time for automatically generating a bid evaluation video according to the project information; determining an end time for automatically generating a bid evaluation video according to a video captured by the video recording device; obtaining a bid evaluation video from a video captured by the video recording device based on the start time and the end time of the video recording; associating the bid evaluation video with the project according to the project information, and storing the association relationship and the bid evaluation video. The method of the present invention determines the start time and the end time for automatically generating a bid evaluation video according to the project information and the video captured by the video recording device, and then obtains the bid evaluation video from the video captured by the video recording device based on the start time and the end time of the video recording, thereby realizing automatic acquisition of the bid evaluation video and avoiding uncertainties caused by manual operation.

[0056] See also Figure 1 The implementation process of the method for automatically generating bid evaluation videos provided in this embodiment is as follows:

[0057] S101, determining a video recording device according to project information.

[0058] Project information includes project name, designated bid evaluation room identification, bid evaluation time, bid evaluation expert information, etc.

[0059] This step is to determine the video recording device installed in the bid evaluation room based on the bid evaluation room identification in the project information. The video recording device will record the bid evaluation room to obtain the collected video.

[0060] However, in the prior art, the video recording equipment will record 24 hours a day, which is ineffective for video collection during non-bid evaluation time, which not only wastes the video collection resource consumption of the video recording equipment, but also wastes the consumption of storage resources for the collected video. The present invention does not record 24 hours a day, but effectively collects the video through the following steps.

[0061] That is, before executing step S102:

[0062] S201, determine the bid evaluation start time based on project information.

[0063] Because the project information includes the bid evaluation time, the earliest time determined from the bid evaluation time in the project information is used as the bid evaluation start time.

[0064] S202: 30 minutes before the start of the bid evaluation, start the video recording equipment to perform video pre-capture.

[0065] That is to say, the video recording device is turned off from the end of the last bid evaluation to 30 minutes before the start of this bid evaluation. This saves resources consumed by recording and also saves resources consumed by the storage of invalid recorded videos.

[0066] However, when step S202 is started, it is pre-capture, that is, the captured video will be cached. When the capture is determined in S204 and S205, the pre-captured video will be cleared to ensure that the captured videos are all valuable videos.

[0067] S203, identifying each pre-captured frame to determine whether a person appears.

[0068] This step will determine whether the object in each frame image is a person based on the object recognition in the existing image. If it is a person, it is determined that a person appears; otherwise, it is determined that no person appears.

[0069] This step only determines whether it is a human being, but does not determine the identity of the person.

[0070] S204: If no person appears in any of the pre-captured frames when the bid evaluation start time is reached, the video recording device is controlled to perform video capture from the bid evaluation start time.

[0071] If no person appears in any of the pre-captured frames when the bid evaluation starts, it means that the scheduled bid evaluation time has arrived, but the bid evaluation expert has not arrived. At this time, video capture will still be carried out to ensure that the video of the entire bid evaluation duration is complete.

[0072] S205: If the bid evaluation start time has not yet arrived and a person has appeared in the pre-captured frame, the video recording device is controlled to capture the video from the time when the person first appears.

[0073] If the bid evaluation start time has not arrived and a person has appeared in the pre-captured frame, it means that someone has entered the bid evaluation room before the bid evaluation started. It is possible that the bid evaluation expert arrived early, or it is possible that an abnormal person entered the bid evaluation room. At this time, it is necessary to record the person's activity video in order to confirm whether the bid evaluation is valid. Therefore, video capture begins when the person first appears.

[0074] Steps S201 to S205 ensure that the time for the video recording equipment to collect video is dynamically determined according to the security situation of the bid evaluation room, which not only avoids the waste caused by 24-hour recording, but also ensures that all content related to the bid evaluation is collected, thereby ensuring the integrity of the generated bid evaluation video.

[0075] S102, determining the start time of automatically generating the bid evaluation video according to the project information and the end time of automatically generating the bid evaluation video according to the video captured by the video recording device.

[0076] 1. The process of determining the start time of automatic generation of bid evaluation videos based on project information is as follows:

[0077] 1) Determine the bid evaluation experts based on the project information.

[0078] Because the project information includes the information of the evaluation experts, the evaluation experts are determined from the evaluation expert information in the project information. At the same time, the characteristics of the evaluation experts can also be obtained, such as face, ID, identity authentication username and password, etc.

[0079] 2) Determine the start time for automatic generation of the bid evaluation video based on the time when all bid evaluation experts complete their sign-in.

[0080] There are many ways to implement this step, and only two are described below as examples:

[0081] The first implementation method is to determine the time when the last bid evaluation expert completes the sign-in as the start time for automatically generating the bid evaluation video.

[0082] Since the identity authentication information of the bid evaluation experts will be obtained when determining the bid evaluation experts, this step can determine whether each expert has completed the sign-in based on the identity authentication information. If completed, the time when the last bid evaluation expert completed the sign-in will be determined as the start time for the automatic generation of the bid evaluation video.

[0083] For example, if the identity authentication information is a user name and a verification code, the user name and password entered by the person entering the bid evaluation room are obtained. If they are the same as the identity authentication information, it is considered that the bid evaluation expert has entered the bid evaluation room. At this time, the device for inputting the user name and password will be monitored. If the sign-in button on the device is triggered, it is considered that the bid evaluation expert has completed the sign-in, and the time when the sign-in button on the device is triggered is determined as the time when the bid evaluation expert has completed the sign-in.

[0084] For another example, if the identity authentication information is a face, the evaluation expert will face the video recording device after entering the evaluation room so that the video recording device can capture the face of the person. The captured face is compared with the face in the identity authentication information. If the two are the same, the evaluation expert is considered to have entered the evaluation room. At this time, the position of the evaluation expert in each frame will be tracked through the existing object tracking scheme in the image, and the distance between the position and the position of each device (because the device is fixed, before video acquisition in the evaluation room, the video recording device is used to test and mark the position of each device in the test image. The position will not change after marking, and the pre-marked position can be used at this time), the device with the shortest distance is identified as the device operated by the evaluation expert. If the sign-in button on the device is triggered, it is considered that the evaluation expert has completed the sign-in, and the time when the sign-in button on the device is triggered is determined as the time when the evaluation expert has completed the sign-in.

[0085] The second implementation method:

[0086] (1) Obtain the time when each bid evaluation expert first appears.

[0087] After entering the bid evaluation room, the bid evaluation expert will face the video recording device so that the video recording device can capture the person's face. This step will recognize each frame of the image based on the existing object recognition scheme in the image. If a face image is recognized and the recognized face is compared with the face in the identity authentication information, and the two are the same, then it is considered that the bid evaluation expert has entered the bid evaluation room, and the time when the person's face is first captured is determined as the time when the standard part first appears.

[0088] (2) Determine the time for each bid evaluation expert to complete the sign-in.

[0089] The time for completing the sign-in is determined in the same manner as the time for completing the sign-in in the first implementation, and will not be described in detail here.

[0090] (3) Calculate the check-in duration of each bid evaluation expert = time to complete check-in - time of first appearance.

[0091] The sign-in duration represents the length of time from when the bid evaluation expert enters the bid evaluation room to when he or she completes the sign-in.

[0092] (4) Obtain the target video captured by the video recording device.

[0093] The start time of the target video is the time when the bid evaluation expert appears for the first time, and the end time of the target video is the time when all bid evaluation experts have completed the sign-in.

[0094] The target video is actually a sub-video of the video captured by the video recording device. The target video is the total check-in time of all experts.

[0095] (5) Determine the abnormality coefficient based on the target video.

[0096] The abnormality coefficient indicates whether the entire sign-in process of the bid evaluation expert is normal. The larger the abnormality coefficient, the more abnormal the sign-in process is.

[0097] The process of determining the anomaly coefficient is:

[0098] S301, performing character recognition on each frame of the target video to determine whether there is a target image frame.

[0099] Among them, there are non-evaluation experts in the target image frame.

[0100] That is, in step S301, each frame in the target video is subjected to character recognition to determine whether there are frames of other persons besides the bid evaluation experts, i.e., other persons entering the bid evaluation room. If there are, it means that the sign-in process is abnormal, and if not, it means that the sign-in process is normal.

[0101] S302: If the target image frame does not exist, determine that the abnormal coefficient is 0.

[0102] S302 is the situation where no other personnel enter the bid evaluation room, which is considered normal, so the abnormality coefficient is 0.

[0103] S303: If the target image frame exists, determine a continuity coefficient according to the target image frame, and determine the abnormal coefficient as continuity coefficient*total number of frames of the target image frame / total number of frames of the target video.

[0104] S303 is when other people enter the bid evaluation room, which is considered abnormal, so:

[0105] S303-1 determines a continuity coefficient according to the target image frame.

[0106] The continuity coefficient represents the abnormality of entering the bid evaluation room, which is composed of two aspects. On the one hand, it is the number of times other personnel enter the bid evaluation room. The more times, the more abnormal it is. On the other hand, it is the randomness of other personnel entering. The greater the randomness, the more abnormal it is.

[0107] The implementation process is as follows:

[0108] A. According to the frame numbers, target image frames with consecutive frame numbers are divided into a group to obtain target image frame groups.

[0109] Each time another person enters the bid evaluation room, the frame numbers of the captured images are continuous. If there is a gap, it means that the person has entered twice. Therefore, by dividing the target image frames with continuous frame numbers into a group, we can know the number of times other people have entered the bid evaluation room. In other words, the number of groups is the number of times other people have entered the bid evaluation room. The target image frames in each group are the images of the same entry of other people.

[0110] B. Determine the target number of image frames for each group.

[0111] The greater the number of target image frames, the longer the time other personnel have been in the bid evaluation room.

[0112] C. Determine the average target image frame number = the sum of the target image frame numbers of all groups / number of groups.

[0113] D. Determine the group size difference = SQRT (SUM (the square of the difference between the number of target image frames in each group and the average number of target image frames) / number of groups).

[0114] Among them, SQRT() is the square root function and SUM() is the sum function.

[0115] The difference in group size indicates the degree of dispersion between the length of time other personnel enter the bid evaluation room each time. The larger the value, the greater the difference in the length of time other personnel enter the bid evaluation room each time. The smaller the value, the smaller the difference in the length of time other personnel enter the bid evaluation room each time.

[0116] E. Determine the continuity coefficient = number of groups * difference in group size.

[0117] The larger the number of groups, the more times other personnel enter the bid evaluation room, and the larger the continuity coefficient. Therefore, the number of groups is proportional to the continuity coefficient, and the difference in group size. The difference in group size indicates the degree of dispersion between the length of time other personnel enter the bid evaluation room each time. The larger the value, the greater the randomness of entering the bid evaluation room, and thus the greater the degree of abnormality, so the larger the continuity coefficient.

[0118] S303-2 determines the abnormal coefficient as the continuous coefficient*the total number of target image frames / the total number of target video frames.

[0119] The continuity coefficient represents the abnormality of entering the bid evaluation room. The larger the continuity coefficient, the more abnormal it is. Therefore, the continuity coefficient is proportional to the abnormality coefficient. The total number of target image frames / the total number of target video frames represents the proportion of the duration of other personnel to the total sign-in duration. The longer the ratio, the more disturbed the sign-in process is, and the more abnormal it is. Therefore, the total number of target image frames / the total number of target video frames are proportional to the abnormality coefficient.

[0120] (6) Determine the start time for automatic generation of the bid evaluation video based on the check-in duration and abnormal coefficient of each bid evaluation expert.

[0121] a. Determine the average sign-in duration = (the maximum sign-in duration of all bid evaluation experts + the minimum sign-in duration of all bid evaluation experts + 4*the sum of the sign-in duration of all bid evaluation experts / the total number of bid evaluation experts) / 6.

[0122] The average sign-in duration represents the average sign-in time of each evaluation expert during this bid evaluation.

[0123] b. Calculate the abnormal value of the check-in duration = average check-in duration * (1 + abnormal coefficient) / preset check-in standard duration.

[0124] The preset standard check-in duration is an empirical value, which is preset by the user. Because the time from entering the bid evaluation room to checking in is subject to certain rules and there are no abnormal situations, a check-in duration interval can be obtained through big data statistics. The standard check-in duration in this step is the maximum value of the check-in duration interval plus the maximum acceptable duration after the interference of abnormal situations. If the duration exceeds this, the check-in is considered abnormal.

[0125] The maximum acceptable duration after an abnormal interference is also a value obtained by performing big data analysis on a large number of abnormal sign-in durations under different interference conditions.

[0126] This embodiment does not limit the process of determining the standard sign-in duration.

[0127] c. If the sign-in duration abnormal value is greater than 1, the start time of the automatic generation of the bid evaluation video is determined to be the time when the first bid evaluation expert first appears.

[0128] The average sign-in duration*(1+abnormal coefficient) represents the sign-in duration in the current sign-in scenario (i.e. abnormal situation). The preset sign-in standard duration represents the maximum acceptable duration in various scenarios (i.e. abnormal situation). If the sign-in duration abnormal value is greater than 1, it means that the sign-in duration is greater than the maximum acceptable duration, indicating an abnormality. Then, the bid evaluation video will be generated from the time when the first bid evaluation expert first appears to retain the most complete bid evaluation video and assist subsequent personnel in evaluating the legality of the bid evaluation. Therefore, if the sign-in duration abnormal value is greater than 1, the start time of the automatic generation of the bid evaluation video is determined to be the time when the first bid evaluation expert first appears.

[0129] d. If the sign-in duration abnormal value is not greater than 1, the time when the last bid evaluation expert completes the sign-in will be determined as the start time of the automatic generation of the bid evaluation video.

[0130] If the sign-in duration abnormal value is greater than 1, it means that the sign-in is normal. Then the bid evaluation video will be generated from the time when the last bid evaluation expert completed the sign-in, so as to retain only the last bid evaluation process image.

[0131] Through the above process, the start time of automatic generation of bid evaluation video can be flexibly determined according to the bid evaluation process, which ensures the integrity of the bid evaluation video and reduces resource consumption.

[0132] 2. The process of determining the end time of the automatic generation of the bid evaluation video based on the video collected by the video recording device is as follows:

[0133] The earliest of the following three times is determined as the end time of the automatically generated bid evaluation video:

[0134] The time when the bid evaluation results are uploaded, the time when the end bid evaluation button is triggered, and the preset time after the bid evaluation end time determined based on the project information.

[0135] The preset time is 30 minutes or the time when the end frame appears for the first time, and there is no person in the end frame.

[0136] That is to say, the end frame is a frame in which there is no one in the bid evaluation room.

[0137] For example, the bid evaluation video is automatically generated at the start time of the bid evaluation video generation. As time goes by, if the bid evaluation expert is first monitored to upload the bid evaluation results, the automatic generation of the bid evaluation video will end at this time, and the final bid evaluation video will be obtained.

[0138] The bid evaluation video is automatically generated at the start time of the bid evaluation video generation. As time goes by, if a bid evaluation expert is first monitored to press the end bid evaluation button, then the automatic generation of the bid evaluation video will end at this time, and the final bid evaluation video will be obtained.

[0139] The bid evaluation video is automatically generated at the start time of bid evaluation video generation. As time goes by, when the latest time of the bid evaluation time in the project information (i.e., the bid evaluation end time) is reached, there is still no monitoring of the bid evaluation expert uploading the bid evaluation results, and no monitoring of a bid evaluation expert pressing the end bid evaluation button, then the bid evaluation video will be automatically generated 30 minutes after the bid evaluation end time, and the final bid evaluation video will be obtained. Alternatively, after the bid evaluation end time, it will be identified whether there is a portrait in each frame image. If it is found for the first time that there is no person (i.e., there is no person in the bid evaluation room), the bid evaluation video will be automatically generated, and the final bid evaluation video will be obtained. Alternatively, within 30 minutes after the bid evaluation end time, if it is found that there is no person in the bid evaluation room, the bid evaluation video will be automatically generated, and the final bid evaluation video will be obtained; within 30 minutes after the bid evaluation end time, there are people in the bid evaluation room, then the bid evaluation video will be automatically generated 30 minutes after the bid evaluation end time, and the final bid evaluation video will be obtained.

[0140] S103, based on the video recording start time and the video recording end time, obtaining the bid evaluation video from the video captured by the video recording device.

[0141] After determining the recording start time and the recording end time, the video captured by the recording device during this time period will be intercepted, and the intercepted video will be used as the bid evaluation video.

[0142] After the capture, the recording device can be controlled to shut down to reduce the resource usage of the recording device.

[0143] S104, associating the bid evaluation video with the project according to the project information, and storing the association relationship and the bid evaluation video.

[0144] After obtaining the bid evaluation video, it will be associated with the project (for example, based on the project name included in the project information, an association relationship between the bid evaluation video identifier and the project identifier is formed), and the association relationship and the bid evaluation video are stored to facilitate subsequent project-based inquiries on the bid evaluation video. At the same time, the bid evaluation video can also be queried and downloaded by time and recording device.

[0145] The method of this embodiment determines the recording device according to the project information; determines the start time of automatic generation of the bid evaluation video according to the project information; determines the end time of automatic generation of the bid evaluation video according to the video captured by the recording device; obtains the bid evaluation video from the video captured by the recording device based on the recording start time and the recording end time; associates the bid evaluation video with the project according to the project information, and stores the association relationship and the bid evaluation video, thereby realizing automatic acquisition of the bid evaluation video and avoiding uncertainties caused by manual operation.

[0146] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0147] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0148] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0149] It should be noted that, in the claims, any reference signs placed between parentheses shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several distinct components, and by means of a suitably programmed computer.

[0150] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example.

[0151] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments after knowing the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0152] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include these modifications and variations.

Claims

1. A method for automatically generating a bid evaluation video, characterized in that: The method comprises: S101, determining a video recording device according to project information; S102, determining a start time for automatically generating a bid evaluation video according to the project information; determining an end time for automatically generating a bid evaluation video according to the video captured by the video recording device; S103, obtaining a bid evaluation video from the video captured by the video recording device based on the video recording start time and the video recording end time; S104, associating the bid evaluation video with the project according to the project information, and storing the association relationship and the bid evaluation video; Determining the start time of automatically generating the bid evaluation video according to the project information includes: Determine the bid evaluation experts based on the project information; Determine the start time of automatic bid evaluation video generation based on the time when all bid evaluation experts complete sign-in; The start time of automatically generating the bid evaluation video is determined based on the time when all bid evaluation experts complete the sign-in, including: Get the time when each bid evaluation expert first appears; Determine the time for each bid evaluation expert to complete the sign-in; Calculate the sign-in duration of each bid evaluation expert = time to complete sign-in - time of first appearance; Obtain the target video captured by the video recording device; the start time of the target video is the time when the bid evaluation expert first appears, and the end time of the target video is the time when all bid evaluation experts have completed signing in; Determining an abnormality coefficient according to the target video; Determine the start time of automatic generation of bid evaluation video according to the check-in duration of each bid evaluation expert and the abnormal coefficient; The determining of an abnormality coefficient according to the target video includes: Performing character recognition on each frame of the target video to determine whether there is a target image frame; and determining whether there is a non-evaluation expert in the target image frame; If the target image frame does not exist, the abnormal coefficient is determined to be 0; If the target image frame exists, a continuity coefficient is determined according to the target image frame, and the abnormal coefficient is determined as the continuity coefficient*the total number of frames of the target image frame / the total number of frames of the target video; The determining of the continuous coefficient according to the target image frame comprises: According to the frame numbers, target image frames with consecutive frame numbers are divided into a group to obtain a target image frame grouping; Determine the target number of image frames for each group; Determine the average number of target image frames = the sum of the number of target image frames of all groups / number of groups; Determine the group size difference = SQRT (SUM (the square of the difference between the number of target image frames in each group and the average number of target image frames) / number of groups); where SQRT() is a square root function and SUM() is a sum function; Determine the continuity coefficient = number of groups * difference in group size.

2. The method according to claim 1, characterized in that Before S102, the method further includes: S201, determining the bid evaluation start time according to the project information; S202, 30 minutes before the start time of the bid evaluation, start the video recording device to perform video pre-capture; S203, identifying each pre-collected frame to determine whether a person appears; S204, if no person appears in all pre-captured frames when the bid evaluation start time is reached, controlling the video recording device to perform video capture from the bid evaluation start time; S205: If the bid evaluation start time has not yet arrived and a person has appeared in the pre-captured frame, control the video recording device to capture the video from the time when the person first appears.

3. The method according to claim 1, characterized in that The start time of automatically generating the bid evaluation video is determined based on the time when all bid evaluation experts complete the sign-in, including: The time when the last bid evaluation expert completes signing in is determined as the start time for automatic generation of the bid evaluation video.

4. The method according to claim 1, characterized in that: The step of determining the start time of automatically generating the bid evaluation video according to the check-in duration of each bid evaluation expert and the abnormal coefficient includes: Determine the average sign-in duration = (the maximum sign-in duration of all bid evaluation experts + the minimum sign-in duration of all bid evaluation experts + 4 * the sum of the sign-in duration of all bid evaluation experts / the total number of bid evaluation experts) / 6; Calculate the abnormal value of check-in duration = average check-in duration * (1 + abnormal coefficient) / preset check-in standard duration; If the sign-in duration abnormal value is greater than 1, the start time of the automatic generation of the bid evaluation video is determined to be the time when the first bid evaluation expert first appears; If the sign-in duration abnormal value is not greater than 1, then the abnormal coefficient determines the time when the last bid evaluation expert completes the sign-in as the start time of automatic generation of the bid evaluation video.

5. The method according to claim 1, characterized in that The step of determining the end time of automatically generating the bid evaluation video according to the video collected by the video recording device includes: The earliest of the following three times is determined as the end time of the automatically generated bid evaluation video: The time when the bid evaluation results are uploaded, the time when the end bid evaluation button is triggered, and the preset time after the bid evaluation end time determined according to the project information.

6. The method according to claim 5, characterized in that The preset time is 30 minutes or the time when the end frame first appears; There is no person in the end frame.

Citation Information

Patent Citations

  • Individual soldier device, method and system supporting case labels

    CN107018354A

  • Bidding and tendering video obtaining method based on intelligent video analysis

    CN110290346A

  • Video big data event library construction method and device and computer equipment

    CN111782869A

  • Abnormal behavior early warning system based on big data

    CN112653870A

  • Video recording method and device in remote bid evaluation video conference process

    CN114071062A