Video authenticity determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a video authenticity determination method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a target video for a target housing resource; determining a first similarity between the target video and the target reference video; if the first similarity is greater than or equal to a first threshold value, determining that the target video is a real field shot video; wherein the target reference video is a video in a reference video set corresponding to the target housing resource, and each reference video in the reference video set comprises a second type of video blocks and a first type of video blocks and is a real shot video of the target housing resource; the second similarity determined by any two reference videos based on the second type of video blocks is greater than or equal to a second threshold value. By applying the technical scheme provided by the embodiment of the invention, whether the target video is the real on-site shot video corresponding to the to-be-displayed housing resource can be accurately determined, and the real effectiveness of the target video is determined.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a method, device, electronic device and storage medium for determining video authenticity. Background Art

[0002] With the development of Internet technology, more and more people conduct house transactions through online platforms. Brokers or landlords can upload videos containing house information and display them on online platforms. Users can search for house information through online platforms to find houses that match their needs. In order to ensure the authenticity of the videos uploaded by brokers or landlords, online platforms require brokers or landlords to take on-site photos of houses, and the videos obtained by brokers or landlords after taking on-site photos of houses can be uploaded to the online platform.

[0003] However, how to accurately determine whether the video uploaded by the broker or landlord is authentic and valid, that is, to determine whether the video uploaded by the broker or landlord is a real on-site video corresponding to the house to be displayed, is a technical problem that technicians in this field urgently need to solve. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and storage medium for determining the authenticity of a video, so as to accurately determine whether a target video is a real on-site video shot of a target property.

[0005] In order to solve the above technical problems, this application provides the following technical solutions:

[0006] In a first aspect, a method for determining video authenticity is provided, comprising:

[0007] Get targeted videos for targeted listings;

[0008] Determining a first similarity between the target video and the target reference video according to a similarity between a first type of video block included in the target video and a first type of video block included in the target reference video;

[0009] If the first similarity is greater than or equal to a first threshold, determining that the target video is a real, field-shot video;

[0010] Among them, the target reference video is a video in the reference video set corresponding to the target property; each reference video in the reference video set includes a second-category video block and a first-category video block, which is a real-shot video of the target property, and a second similarity between any two reference videos determined based on the second-category video block is greater than or equal to a second threshold; the first-category video block includes a plurality of video blocks shot based on a plurality of advanced process shooting steps, and the second-category video block includes a plurality of video blocks shot based on a plurality of basic process shooting steps, and the plurality of basic process shooting steps are before the plurality of advanced process shooting steps.

[0011] Optionally, the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video is determined by the following steps:

[0012] For each first-category video block included in the target video, determining a corresponding first-category video block in a target reference video; the shooting steps corresponding to the first-category video block in the target reference video are the same as the shooting steps corresponding to the current first-category video block in the target video;

[0013] Performing feature extraction operations on the current first-category video block in the target video and the corresponding first-category video block in the target reference video respectively;

[0014] According to the extracted features, the similarity between the current first-category video block in the target video and the corresponding first-category video block in the target reference video is determined.

[0015] Optionally, determining the first similarity between the target video and the target reference video according to the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video includes:

[0016] Determine the similarity between each first-category video block included in the target video and a corresponding first-category video block in the target reference video;

[0017] The average value, maximum value, minimum value or median value of the similarity between each first-category video block included in the target video and the corresponding first-category video block in the target reference video is determined as the first similarity between the target video and the target reference video.

[0018] Optionally, before obtaining the target video for the target house, the method further includes:

[0019] Obtain multiple real-life videos of the target property;

[0020] For a first real-shot video and a second real-shot video among the multiple real-shot videos, determining a second similarity between the first real-shot video and the second real-shot video according to a similarity between a second type of video block included in the first real-shot video and a second type of video block included in the second real-shot video;

[0021] If the second similarity is greater than or equal to the second threshold, determining the first real-shot video and the second real-shot video as reference videos in a reference video set corresponding to the target house;

[0022] The first real-shot video and the second real-shot video are any two real-shot videos among the multiple real-shot videos;

[0023] Each of the multiple real-shot videos includes the second-category video blocks and the first-category video blocks, and the second-category video blocks included in each real-shot video include video blocks shot one-to-one based on each basic process shooting step, and the first-category video blocks included in each real-shot video include video blocks shot one-to-one based on each advanced process shooting step.

[0024] Optionally, the similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video is determined by the following steps:

[0025] For each second-category video block included in the first real-shot video, determining a corresponding second-category video block in the second real-shot video; the shooting steps corresponding to the second-category video block corresponding to the second real-shot video are the same as the shooting steps corresponding to the current second-category video block in the first real-shot video;

[0026] Performing feature extraction operations on the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video respectively;

[0027] According to the extracted features, a similarity between a current second-category video block in the first real-shot video and a corresponding second-category video block in the second real-shot video is determined.

[0028] Optionally, determining the second similarity between the first real-shot video and the second real-shot video according to the similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video includes:

[0029] Determine a similarity between each second-category video block included in the first real-shot video and a corresponding second-category video block in the second real-shot video;

[0030] The average value, maximum value, minimum value or median value of the similarity between each second-category video block included in the first real-shot video and the corresponding second-category video block in the second real-shot video is determined as the second similarity between the first real-shot video and the second real-shot video.

[0031] Optionally, when the first similarity is less than the first threshold, the method further includes:

[0032] Output a review prompt message to manually determine whether the target video is a real field-shot video.

[0033] In a second aspect, a video authenticity determination device is provided, comprising:

[0034] A first obtaining unit, used to obtain a target video for a target house;

[0035] A first determining unit, configured to determine a first similarity between the target video and the target reference video according to a similarity between a first type of video block included in the target video and a first type of video block included in a target reference video;

[0036] A second determining unit, configured to determine that the target video is a real video shot when the first similarity is greater than or equal to a first threshold;

[0037] Among them, the target reference video is a video in the reference video set corresponding to the target property; each reference video in the reference video set includes a second-category video block and a first-category video block, which is a real-shot video of the target property, and a second similarity between any two reference videos determined based on the second-category video block is greater than or equal to a second threshold; the first-category video block includes a plurality of video blocks shot based on a plurality of advanced process shooting steps, and the second-category video block includes a plurality of video blocks shot based on a plurality of basic process shooting steps, and the plurality of basic process shooting steps are before the plurality of advanced process shooting steps.

[0038] According to a third aspect, an electronic device is provided, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for determining video authenticity as described in the first aspect are implemented.

[0039] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for determining video authenticity as described in the first aspect are implemented.

[0040] In a fifth aspect, a computer program product is provided, which includes computer instructions, which are stored in a computer-readable storage medium and are suitable for being read and executed by a processor, so that an electronic device having the processor performs the steps of the video authenticity determination method as described in the first aspect.

[0041] By applying the technical solution provided in the embodiment of the present application, the second similarity determined based on the second type of video block of any two reference videos in the reference video set corresponding to the target house source is greater than or equal to the second threshold value, which ensures the accuracy and reliability of the reference video set corresponding to the target house source, and the target reference video is a video in the reference video set, so the accuracy and reliability of the target reference video corresponding to the target house source are also guaranteed, and the second similarity of any two reference videos in the reference video set is determined only based on the second type of video block, which reduces the workload of similarity processing of the reference video. After obtaining the target video for the target house source, the first type of video block included in the target video is compared with the first type of video block included in the accurate target reference video, and the first similarity determined based on the first type of video block between the target video and the target reference video is obtained. Because the target reference video is a real-shot video of the target house source, when the first similarity is large, it can be determined that the target video is a real-shot video of the target house source, which realizes the accurate determination of the authenticity and validity of the target video, and the first similarity is determined only based on the first type of video block, which reduces the workload of similarity processing between the target video and the target reference video.

[0042] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A schematic diagram of simplifying the process shooting steps in the related technology to obtain a complete video;

[0044] Figure 2 This is a flowchart of a method for determining video authenticity in an embodiment of the present application;

[0045] Figure 3 This is a schematic diagram of the structure of a video authenticity determination device in an embodiment of the present application;

[0046] Figure 4 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] The core of this application is to provide a method for determining the authenticity of a video, which can be applied to scenarios such as the rental and sale of real estate such as office buildings and residential buildings or house introductions.

[0049] After the network platform obtains that the broker or landlord and other housing information publishers have a shooting demand for the target house, it can first determine whether there is a reference video corresponding to the target house uploaded by other housing information publishers in the network platform. The reference video corresponding to the target house can be at least one field shooting video obtained by at least one other housing information publisher according to the full process shooting steps and confirmed by the network platform. If it exists, the process steps of the current broker or current landlord shooting the house can be simplified. For example, in one embodiment, the full process shooting steps for a certain office building house can include eight shooting steps, namely, building unit identification board, water sign, upstairs process, corridor environment, room number, door opening action, gesture verification, and indoor environment. If there is a reference video for the office building house, the process steps of the broker or landlord shooting the house can be simplified to only shooting the fifth to eighth steps. In the full process shooting steps, the first four steps can be called basic process shooting steps, and the last four steps can be called advanced process shooting steps. If there is a reference video corresponding to the target property uploaded by other property information publishers on the network platform, the video blocks shot by the current broker or current landlord according to the last four steps can be combined with the video blocks shot according to the basic process shooting steps in the reference video to obtain a complete video for the office building property. Then the broker or landlord can upload the video blocks shot according to the last four steps or the complete video for the office building property as the target video.

[0050] For example, Figure 1As shown, the house information filled in by the broker or landlord can be obtained first, and the target house can be determined based on the house information; then the benchmark video corresponding to the target house can be obtained through the benchmark video library, and the benchmark video is a real-shot video obtained according to the full process shooting steps, that is, a field shot video; then the simplified process shooting steps are determined; after the video blocks shot by the broker or landlord according to the simplified process shooting steps are obtained, the video blocks shot according to the simplified process shooting steps can be used as the target video of the target house, or the video blocks shot according to the simplified process shooting steps can be combined with the video blocks shot according to the basic process shooting steps included in the benchmark video to obtain a complete video of the target house and use it as the target video of the target house.

[0051] In an embodiment of the present application, a plurality of video blocks obtained by shooting corresponding to a plurality of advanced process shooting steps may be referred to as first-category video blocks, and a plurality of video blocks obtained by shooting corresponding to a plurality of basic process shooting steps may be referred to as second-category video blocks.

[0052] The target video for the target property can be any video uploaded by the agent or landlord to be released for the target property. Optionally, the target video can be a combination of video blocks obtained by shooting according to the advanced process shooting steps, which is an incomplete video of the target property, that is, the target video only includes the first type of video blocks. Optionally, the target video can be a combination of video blocks obtained by shooting according to the advanced process shooting steps and video blocks obtained by shooting according to the basic process shooting steps included in the reference video corresponding to the target property, which is a complete video of the target property, that is, the target video includes the second type of video blocks and the first type of video blocks. The reference video corresponding to the target property includes the second type of video blocks and the first type of video blocks.

[0053] After obtaining the target video, the first similarity between the target video and the target reference video can be determined based on the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video. If the first similarity is greater than or equal to a first threshold, it can be determined that the target video is a real field shot video.

[0054] The second similarity determined based on the second type of video blocks of any two reference videos in the reference video set corresponding to the target house is greater than or equal to the second threshold value, which ensures the accuracy and reliability of the reference video set corresponding to the target house, and the target reference video is a video in the reference video set, so the accuracy and reliability of the target reference video corresponding to the target house are also guaranteed, and the second similarity of any two reference videos in the reference video set is determined only based on the second type of video blocks, which reduces the workload of similarity processing of the reference videos. After obtaining the target video for the target house, the first type of video blocks included in the target video are compared with the first type of video blocks included in the accurate target reference video, and the first similarity determined based on the first type of video blocks between the target video and the target reference video is obtained. Because the target reference video is a real-shot video of the target house, when the first similarity is large, it can be determined that the target video is a real-shot video of the target house, which realizes the accurate determination of the authenticity and validity of the target video, and the first similarity is determined only based on the first type of video blocks, which reduces the workload of similarity processing between the target video and the target reference video.

[0055] See also Figure 2 FIG. 1 is a flowchart of a method for determining video authenticity provided by an embodiment of the present application. The method may include the following steps:

[0056] S210: Obtain a target video for a target house.

[0057] The target video can be any video uploaded by the agent or landlord for the target property to be released.

[0058] Optionally, the target video may be a combination of video blocks obtained by shooting according to the shooting steps of the advanced process, which is an incomplete video of the target house, that is, the target video only includes the first type of video blocks.

[0059] Optionally, the target video can be a combination of the video blocks obtained by shooting according to the advanced process shooting steps and the video blocks obtained by shooting according to the basic process shooting steps included in the benchmark video corresponding to the target property, which is a complete video of the target property, that is, the target video includes the second category video blocks and the first category video blocks.

[0060] S220: Determine a first similarity between the target video and the target reference video according to a similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video.

[0061] The target reference video is a video in the reference video set corresponding to the target property. Each reference video in the reference video set includes a second-category video block and a first-category video block, which is a real-shot video of the target property. The second similarity determined based on the second-category video block between any two reference videos is greater than or equal to a second threshold. The first-category video block includes a plurality of video blocks shot based on a plurality of advanced process shooting steps, and the second-category video block includes a plurality of video blocks shot based on a plurality of basic process shooting steps, and the plurality of basic process shooting steps are before the plurality of advanced process shooting steps.

[0062] In an embodiment of the present application, each house source may correspond to a reference video set. When the publishing requirements of the broker or landlord for the target house source are obtained, the reference video set corresponding to the target house source may be determined according to the publishing requirements. Each reference video in the reference video set includes a second-category video block and a first-category video block. The first-category video block includes a plurality of video blocks corresponding to the shooting steps of a plurality of advanced processes, and the second-category video block includes a plurality of video blocks corresponding to the shooting steps of a plurality of basic processes. Each shooting step corresponds to a video block.

[0063] For example, the full-process shooting steps for a certain office building can be eight shooting steps, namely, the building unit sign, water sign, the process of going upstairs, the corridor environment, the room number, the door opening action, the gesture verification, and the indoor environment. Among them, the first four shooting steps can be basic process shooting steps, and the last four shooting steps can be advanced process shooting steps. Each shooting step corresponds to a video block. For example, there is a video block corresponding to shooting the building unit sign, a video block corresponding to shooting the water sign, a video block corresponding to shooting the process of going upstairs, a video block corresponding to shooting the corridor environment, a video block corresponding to shooting the room number, a video block corresponding to shooting the door opening action, a video block corresponding to shooting the gesture verification, and a video block corresponding to shooting the indoor environment. Connect the video blocks corresponding to these shooting steps in order of shooting time to form a complete video. Each benchmark video corresponding to the target house is a complete video for the target house.

[0064] The reference video set corresponding to the target house source can be obtained by pre-shooting the target house source on the spot. Multiple real-shot videos corresponding to the target house source can be compared, and the second similarity of any two real-shot videos can be determined based on the second-type video blocks. For any two real-shot videos corresponding to the target house source, if the second similarity of the two real-shot videos is greater than or equal to the second threshold, the two real-shot videos can be used as the reference videos corresponding to the target house source. If the second similarity of the two real-shot videos is less than the second threshold, they can be left unprocessed or discarded. The set of determined reference videos is the reference video set. In other words, the second similarity of any two reference videos in the reference video set corresponding to the target house source is greater than or equal to the second threshold. The second similarity of any two reference videos in the reference video set corresponding to the target house source is determined based on the similarity of the second-type video blocks included in one reference video and the second-type video blocks included in the other reference video in the arbitrary two reference videos.

[0065] The second threshold can be set and adjusted according to actual conditions.

[0066] After obtaining the target video for the target house, a reference video may be selected from the reference video set corresponding to the target house as the target reference video. Alternatively, a reference video may be randomly selected from the reference video set corresponding to the target house as the target reference video. Alternatively, the reference video with the earliest shooting time in the reference video set corresponding to the target house may be used as the target reference video. Alternatively, the reference video with the closest shooting time to the current time in the reference video set corresponding to the target house may be used as the target reference video.

[0067] The first type of video blocks included in the target video are compared with the first type of video blocks included in the target reference video, and the first similarity between the target video and the target reference video can be determined according to the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video.

[0068] S230: If the first similarity is greater than or equal to the first threshold, determine that the target video is a real video shot on the spot.

[0069] It can be understood that the reference video in the reference video set corresponding to the target property is a pre-confirmed field-shot video of the target property, and the target reference video is a video in the reference video set corresponding to the target property, so the target reference video has a certain degree of accuracy and reliability.

[0070] After determining the first similarity between the target video and the target reference video based on the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video, the first similarity can be compared with the first threshold. If the first similarity is greater than or equal to the first threshold, it can be considered that the target video and the target reference video are highly similar, and the target reference video is a real-shot video that has been confirmed in advance to be a judgment benchmark, so it can be determined that the target video is a real-shot video of the target house. If the first similarity is less than the first threshold, whether the target video is a real-shot video needs further confirmation.

[0071] By applying the method provided in the embodiment of the present application, the second similarity determined based on the second type of video block for any two reference videos in the reference video set corresponding to the target house source is greater than or equal to the second threshold value, which ensures the accuracy and reliability of the reference video set corresponding to the target house source, and the target reference video is a video in the reference video set, so the accuracy and reliability of the target reference video corresponding to the target house source are also guaranteed, and the second similarity of any two reference videos in the reference video set is determined only based on the second type of video block, which reduces the workload of similarity processing of the reference video. After obtaining the target video for the target house source, the first type of video block included in the target video is compared with the first type of video block included in the accurate target reference video, and the first similarity determined based on the first type of video block between the target video and the target reference video is obtained. Because the target reference video is a real-shot video of the target house source, when the first similarity is large, it can be determined that the target video is a real-shot video of the target house source, which realizes the accurate determination of the authenticity and validity of the target video, and the first similarity is determined only based on the first type of video block, which reduces the workload of similarity processing between the target video and the target reference video.

[0072] In some embodiments of the present application, the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video may be determined by the following steps:

[0073] For each first-category video block included in the target video, determining a corresponding first-category video block in the target reference video; the shooting steps corresponding to the corresponding first-category video block in the target reference video are the same as the shooting steps corresponding to the current first-category video block in the target video;

[0074] Performing feature extraction operations on the current first-category video block in the target video and the corresponding first-category video block in the target reference video respectively;

[0075] Based on the extracted features, the similarity between the current first-category video block in the target video and the corresponding first-category video block in the target reference video is determined.

[0076] For the convenience of description, the above steps are combined for explanation.

[0077] In an embodiment of the present application, the full process shooting steps may include multiple basic process shooting steps and multiple advanced process shooting steps, wherein the multiple basic process shooting steps are before the multiple advanced process shooting steps, or it can be understood that the basic process shooting steps are the initial part of the full process shooting steps, and the advanced process shooting steps are the subsequent part of the full process shooting steps.

[0078] For example, the full-process shooting steps include eight shooting steps in sequence, namely, the building unit identification plate, water sign, the process of going upstairs, the corridor environment, the room number, the door opening action, gesture verification, and the indoor environment. Among them, the basic process shooting steps may include the initial part of the steps, such as the first four steps, which correspond to the shooting steps of the building unit identification plate, water sign, the process of going upstairs, and the corridor environment, respectively. The advanced process shooting steps may include the subsequent part of the steps, such as the last four steps, which correspond to the shooting steps of the room number, the door opening action, gesture verification, and the indoor environment. The above-mentioned basic process shooting steps are the first four steps or the advanced process shooting steps are the last four steps as an example, wherein the basic process shooting steps may also include the first three steps. At this time, the advanced process shooting steps include the last five steps, and this application does not limit this.

[0079] After obtaining the target video for the target house, the first-category video blocks included in the target video can be compared with the first-category video blocks included in the target reference video. That is, for each first-category video block included in the target video, determine the corresponding first-category video block in the target reference video. The shooting steps corresponding to the corresponding first-category video block in the target reference video are the same as the shooting steps corresponding to the current first-category video block in the target video. The current first-category video block in the target video refers to the first-category video block in the target video that is currently being operated on. Then, feature extraction operations are performed on the current first-category video block in the target video and the corresponding first-category video block in the target reference video, respectively, and based on the extracted features, the similarity between the current first-category video block in the target video and the corresponding first-category video block in the target reference video is determined.

[0080] Optionally, the features extracted by the feature extraction operation performed on the video block in the embodiment of the present application may include key point features, edge features, inter-frame difference features, color histogram features, etc., that is, the feature extraction operation may be to extract key point features, edge features, inter-frame difference features, color histogram features, etc. for the housing features in the video block corresponding to the current step.

[0081] Optionally, the image frames of the current first-category video block in the target video may be first extracted, and a feature extraction operation may be performed on each image frame to obtain a feature set corresponding to the current first-category video block in the target video; similarly, the image frames of the corresponding first-category video block in the target reference video may be extracted, and a feature extraction operation may be performed on each image frame to obtain a feature set corresponding to the corresponding first-category video block in the target reference video; the two feature sets may be compared, and the similarity between the current first-category video block in the target video and the corresponding first-category video block in the target reference video may be determined based on the comparison result.

[0082] For example, the advanced process shooting steps corresponding to the first type of video block include the shooting steps of the room number, the door opening action, the gesture verification, and the indoor environment. The shooting steps of the room number correspond to the room number video block, the shooting steps of the door opening action correspond to the door opening action video block, the shooting steps of the gesture verification correspond to the gesture verification video block, and the shooting steps of the indoor environment correspond to the indoor environment video block. For example, if the current first type of video block in the target video is a room number video block, then the corresponding first type of video block in the target reference video is also a room number video block, and the corresponding shooting steps are all shooting steps of the room number. Among them, if the room number is unique, that is, only the main door has a room number, then the room number is the house number of the main door; if the room number is not unique, that is, the main door has a room number and the room indoors also has a room number, then the room number can be the house number of the main door, or it can be the house number of the main door and the room number of the room.

[0083] The room number video block included in the target video is compared with the room number video block included in the target benchmark video to obtain the similarity corresponding to the room number video block; the door opening action video block included in the target video is compared with the door opening action video block included in the target benchmark video to obtain the similarity corresponding to the door opening action video block; the gesture verification video block included in the target video is compared with the gesture verification video block included in the target benchmark video to obtain the similarity corresponding to the gesture verification video block; the indoor environment video block included in the target video is compared with the indoor environment video block included in the target benchmark video to obtain the similarity corresponding to the indoor environment video block.

[0084] For example, if the current first-category video block in the target video is a room number video block, the corresponding first-category video block in the target reference video is a room number video block, and the corresponding shooting steps are all shooting steps of the room number, then the image frames of the current first-category video block in the target video can be extracted first, and feature extraction operations for the room number are performed on each image frame to obtain a feature set for the room number corresponding to the current first-category video block in the target video; similarly, image frames of the corresponding first-category video block in the target reference video are extracted, and feature extraction operations for the room number are performed on each image frame to obtain a feature set for the room number corresponding to the corresponding first-category video block in the target reference video; the two feature sets are compared, and based on the comparison results, the similarity between the current first-category video block in the target video and the corresponding first-category video block in the target reference video with respect to the room number is determined.

[0085] Based on the above operations, the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video can be accurately determined, providing a guarantee for the smooth progress of subsequent operations.

[0086] In some embodiments of the present application, step S220 determines the first similarity between the target video and the target reference video according to the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video, and may include the following steps:

[0087] Determine the similarity between each first-category video block included in the target video and a corresponding first-category video block in the target reference video;

[0088] The average value, maximum value, minimum value or median value of the similarity between each first-category video block included in the determined target video and the corresponding first-category video block in the target reference video is determined as the first similarity between the target video and the target reference video.

[0089] For the convenience of description, the above steps are combined for explanation.

[0090] In an embodiment of the present application, the similarity between each first-category video block included in the target video and the corresponding first-category video block in the target reference video can be first determined, and the first similarity between the target video and the target reference video can be determined based on the similarity between each first-category video block included in the target video and the corresponding first-category video block in the target reference video.

[0091] Optionally, an average value of the similarities between each first-category video block included in the determined target video and a corresponding first-category video block in the target reference video may be determined as the first similarity between the target video and the target reference video.

[0092] Optionally, the maximum value, minimum value or median value of the similarity between each first-category video block included in the determined target video and the corresponding first-category video block in the target reference video may be determined as the first similarity between the target video and the target reference video.

[0093] It is understandable that if the target video for the target house is actually shot after simplifying the shooting process steps based on the reference video of the target house, and the target video only includes the first type of video blocks, then the first similarity only needs to be determined based on the first type of video blocks. If the target video for the target house is actually shot after simplifying the shooting process steps based on the reference video of the target house, and the target video includes the second type of video blocks and the first type of video blocks, then the second type of video blocks included in the target video are consistent with the second type of video blocks included in the target reference video, and there is no need for comparison, but the first type of video blocks included in the target video are not completely consistent with the first type of video blocks included in the target reference video, and the first similarity can be determined based on the first type of video blocks.

[0094] That is, in one embodiment of the present application, the target video may include only the first type of video blocks, and the reference video includes the second type of video blocks and the first type of video blocks.

[0095] In another embodiment of the present application, the target video may include the second-category video blocks and the first-category video blocks, and the reference video may include the second-category video blocks and the first-category video blocks.

[0096] Optionally, in the scheme of determining the maximum value of the similarities between each first-category video block included in the determined target video and the corresponding first-category video block in the target reference video as the first similarity between the target video and the target reference video, if the maximum value is 100%, the maximum value is eliminated and the second maximum value is determined as the first similarity between the target video and the target reference video, so as to effectively exclude cheating behavior.

[0097] In some embodiments of the present application, before obtaining the target video for the target house in step S210, the method may further include the following steps:

[0098] Obtain multiple real-life videos of the target property;

[0099] For a first real-shot video and a second real-shot video among the multiple real-shot videos, determining a second similarity between the first real-shot video and the second real-shot video according to a similarity between a second type of video block included in the first real-shot video and a second type of video block included in the second real-shot video;

[0100] If the second similarity is greater than or equal to the second threshold, determining the first real-shot video and the second real-shot video as reference videos in the reference video set corresponding to the target house;

[0101] The first real-shot video and the second real-shot video are any two real-shot videos among the multiple real-shot videos;

[0102] Each of the multiple real-shot videos includes a second-category video block and a first-category video block. The second-category video blocks included in each real-shot video include video blocks shot one-to-one based on each basic process shooting step. The first-category video blocks included in each real-shot video include video blocks shot one-to-one based on each advanced process shooting step. The second-category video blocks and the first-category video blocks each include multiple video blocks.

[0103] Among them, in order to obtain multiple real-shot videos of the target house including the second type of video blocks and the first type of video blocks, the shooting steps of the multiple real-shot videos of the stored target house can be identified to obtain multiple real-shot videos including the second type of video blocks and the first type of video blocks.

[0104] For the convenience of description, the above steps are combined for explanation.

[0105] In an embodiment of the present application, the full process shooting steps may include multiple basic process shooting steps and multiple advanced process shooting steps, wherein the multiple basic process shooting steps are before the multiple advanced process shooting steps, or it can be understood that the basic process shooting steps are the initial part of the full process shooting steps, and the advanced process shooting steps are the subsequent part of the full process shooting steps.

[0106] The target house can be filmed in real time in advance to obtain multiple real-time videos of the target house. It can be considered that the real-time video is obtained by filming in real time according to the full process shooting steps in order to obtain the benchmark video of the target house. Each of the multiple real-time videos includes a second-category video block and a first-category video block. The second-category video block included in each real-time video includes a video block shot one-to-one based on each basic process shooting step, and the first-category video block included in each real-time video includes a video block shot one-to-one based on each advanced process shooting step. For example, there are four basic process shooting steps and four advanced process shooting steps. Then, each real-time video includes a second-category video block including a total of four video blocks, each of which corresponds to a basic process shooting step, and each real-time video includes a first-category video block including a total of four video blocks, each of which corresponds to an advanced process shooting step, that is, each real-time video includes eight video blocks and is a complete video.

[0107] After obtaining multiple real-shot videos of the target house, for a first real-shot video and a second real-shot video in the multiple real-shot videos, similarity between the second-category video blocks included in the first real-shot video and the second-category video blocks included in the second real-shot video can be determined. The first real-shot video and the second real-shot video are any two real-shot videos in the multiple real-shot videos.

[0108] For example, the basic process shooting steps correspond to the shooting steps of the building unit sign, the water sign, the process of going upstairs, and the corridor environment. The shooting steps of the building unit sign correspond to the building unit sign video block, the shooting steps of the water sign correspond to the water sign video block, the shooting steps of the process of going upstairs correspond to the process of going upstairs video block, and the shooting of the corridor environment corresponds to the corridor environment video block. These video blocks are the second type of video blocks. The video block of the building unit sign included in the first real-shot video is compared with the video block of the building unit sign included in the second real-shot video to obtain the similarity corresponding to the building unit sign video block, the water sign video block included in the first real-shot video is compared with the water sign video block included in the second real-shot video to obtain the similarity corresponding to the water sign video block, the video block of the process of going upstairs included in the first real-shot video is compared with the video block of the process of going upstairs included in the second real-shot video to obtain the similarity corresponding to the video block of going upstairs, and the video block of the corridor environment included in the first real-shot video block is compared with the video block of the corridor environment included in the second real-shot video to obtain the similarity corresponding to the corridor environment video block.

[0109] According to the similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video, a second similarity between the first real-shot video and the second real-shot video is determined.

[0110] The second similarity is compared with a second threshold value. If the second similarity is greater than or equal to the second threshold value, the first real-shot video and the second real-shot video are determined as reference videos in a reference video set corresponding to the target house.

[0111] It is understandable that if there is a reference video of the target house, the shooting process steps can be simplified when the shooting requirements for the target house are obtained. The simplified process steps are the basic process shooting steps. Therefore, it is necessary to ensure that the second-category video blocks obtained by shooting based on the basic process shooting steps included in any two reference videos in the reference video set have a high similarity. When obtaining the reference video set corresponding to the target video, the second-category video blocks included in the first real-shot video of the target house and the second-category video blocks included in the second real-shot video can be compared to obtain the corresponding similarity, and further based on the obtained similarity, the second similarity of the current two real-shot videos is determined, and then further based on the second similarity, it is determined whether the current two real-shot videos can be used as the reference video of the target house. Ensure the accuracy of the reference video of the target house.

[0112] In some embodiments of the present application, the similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video may be determined by the following steps:

[0113] For each second-category video block included in the first real-shot video, determining a corresponding second-category video block in the second real-shot video; the shooting steps corresponding to the corresponding second-category video block in the second real-shot video are the same as the shooting steps corresponding to the current second-category video block in the first real-shot video;

[0114] Performing feature extraction operations on the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video respectively;

[0115] According to the extracted features, the similarity between the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video is determined.

[0116] For the convenience of description, the above steps are combined for explanation.

[0117] In an embodiment of the present application, for each second-category video block included in the first real-shot video, the corresponding second-category video block in the second real-shot video is determined. The shooting steps corresponding to the corresponding second-category video block in the second real-shot video are the same as the shooting steps corresponding to the current second-category video block in the first real-shot video. The current second-category video block in the first real-shot video refers to the second-category video block in the first real-shot video that is targeted by the current operation. Then, feature extraction operations are performed on the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video, respectively, and based on the extracted features, the similarity between the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video is determined.

[0118] For example, if the current second-category video block in the first real-shot video is a corridor environment video block, then the corresponding second-category video block in the second real-shot video is also a corridor environment video block, and the corresponding shooting steps are all shooting steps of the corridor environment.

[0119] Optionally, the features extracted by the feature extraction operation performed on the video block in the embodiment of the present application may include key point features, edge features, inter-frame difference features, color histogram features, etc.

[0120] Optionally, you can first extract image frames of the current second-category video block in the first real-shot video, perform feature extraction operations on each image frame, and obtain a feature set corresponding to the current second-category video block in the first real-shot video; similarly, extract image frames of the corresponding second-category video block in the second real-shot video, perform feature extraction operations on each image frame, and obtain a feature set corresponding to the corresponding second-category video block in the second real-shot video; compare the two feature sets, and determine the similarity between the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video based on the comparison result.

[0121] For example, if the current second-category video block in the first real-shot video is a building unit identification board video block, and the corresponding second-category video block in the second real-shot video is a building unit identification board video block, and the corresponding shooting steps are all shooting steps of the building unit identification board, then the image frames of the current second-category video block in the first real-shot video can be extracted first, and feature extraction operations for the building unit identification are performed on each image frame to obtain a feature set for the building unit identification corresponding to the current second-category video block in the first real-shot video; similarly, image frames of the corresponding second-category video block in the second real-shot video are extracted, and feature extraction operations for the building unit identification are performed on each image frame to obtain a feature set for the building unit identification corresponding to the corresponding second-category video block in the second real-shot video; the two feature sets are compared, and based on the comparison results, the similarity between the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video with respect to the building unit identification is determined.

[0122] Based on the above operations, the similarity between each second-category video block included in the first real-shot video and the corresponding second-category video block included in the second real-shot video can be determined, providing a basis for subsequent determination of the second similarity.

[0123] In some embodiments of the present application, determining the second similarity between the first real-shot video and the second real-shot video according to the similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video may include the following steps:

[0124] Determine a similarity between each second-category video block included in the first real-shot video and a corresponding second-category video block in the second real-shot video;

[0125] The average value, maximum value, minimum value or median value of the similarity between each second-category video block included in the determined first real-shot video and the corresponding second-category video block in the second real-shot video is determined as the second similarity between the first real-shot video and the second real-shot video.

[0126] For the convenience of description, the above steps are combined for explanation.

[0127] In an embodiment of the present application, the similarity between each second-category video block included in the first real-shot video and the corresponding second-category video block in the second real-shot video can be first determined, and the second similarity between the first real-shot video and the second real-shot video can be determined based on the similarity between each second-category video block included in the first real-shot video and the corresponding second-category video block in the second real-shot video.

[0128] Optionally, an average value of the similarities between each second-category video block included in the first real-shot video and a corresponding second-category video block in the second real-shot video may be determined as the second similarity between the first real-shot video and the second real-shot video.

[0129] Optionally, the maximum value, minimum value or median value of the similarity between each second-category video block included in the determined first real-shot video and the corresponding second-category video block in the second real-shot video can be determined as the second similarity between the first real-shot video and the second real-shot video.

[0130] Optionally, in the scheme of determining the maximum value of the similarities between each second-category video block included in the determined first real-shot video and the corresponding second-category video block in the second real-shot video as the second similarity between the first real-shot video and the second real-shot video, if the maximum value is 100%, the maximum value can be eliminated and the second maximum value can be determined as the second similarity between the first real-shot video and the second real-shot video, so as to effectively eliminate cheating behavior.

[0131] In some embodiments of the present application, when the first similarity between the target video and the target reference video is less than a first threshold, the method may further include the following steps:

[0132] Output a review prompt message to manually determine whether the target video is a real field-shot video.

[0133] In an embodiment of the present application, if the first similarity between the target video and the target reference video is greater than or equal to the first threshold, it can be directly determined that the target video is a real field shot video, and the review can be confirmed to be passed, allowing the upload of the target video.

[0134] If the first similarity between the target video and the target reference video is less than the first threshold, it is impossible to directly determine whether the target video is a real and field-shot video, and a review prompt message can be output to manually determine whether the target video is a real and field-shot video. For example, manually compare whether the first type of video blocks included in the target video are similar to the first type of video blocks included in the target reference video, or manually determine whether the target video is the first real and field-shot video for the target house. This can avoid the occurrence of misjudgment due to video quality, or avoid the occurrence of misjudgment due to the lack of a reference video for the target house or the use of different reference videos.

[0135] In some embodiments of the present application, when it is determined that the target video is a real field-shot video, the method may further include the following steps:

[0136] Add the complete video corresponding to the target video to the reference video set corresponding to the target listing.

[0137] In an embodiment of the present application, if the target video is a video obtained by simplifying the process based on the reference video corresponding to the target house, and the target video only includes the first type of video blocks, then when it is determined that the target video is a real and real shot video, the target video can be supplemented based on the second type of video blocks included in the reference video corresponding to the target house, and the complete video corresponding to the target video is added to the reference video set corresponding to the target house. First, determine whether the target video is a real and real shot video, and then, if it is determined that it is a real and real shot video, supplement to obtain a complete video. If it is determined that it is not a real and real shot video, there is no need to supplement it, which can save resources.

[0138] If the target video is a video obtained by simplifying the process based on the reference video corresponding to the target house, but the target video includes the second type of video blocks and the first type of video blocks, then the target video is already a complete video. If it is determined that the target video is a real video shot on the spot, the complete video corresponding to the target video can be added to the reference video set corresponding to the target house. In this case, the second type of video blocks included in the target video are supplemented based on the second type of video blocks included in the reference video.

[0139] In either of the above situations, the second-category video blocks in the complete video corresponding to the target video have a greater similarity with the second-category video blocks included in the reference video.

[0140] Therefore, when it is determined that the target video is a real field-shot video, the complete video corresponding to the target video can be added to the reference video set corresponding to the target house to expand the reference video set of the target house.

[0141] In some embodiments of the present application, for the reference video set corresponding to any house source, it can be cleaned up according to the set rules to maintain the accuracy of the reference video set. For example, according to the time rule, the reference videos in the reference video set whose shooting time is greater than or equal to the third threshold from the current time are cleaned up. Or, according to the video clarity rule, if the number of reference videos included in the reference video set is greater than or equal to the fourth threshold, the reference videos in the reference video set whose clarity is less than or equal to the fifth threshold can be cleaned up. The third threshold, the fourth threshold, and the fifth threshold can be set and adjusted according to actual conditions.

[0142] The technical solutions provided in the embodiments of the present application are described above. For ease of understanding, the technical solutions provided in the embodiments of the present application are described below by comparison with related technologies.

[0143] In a possible implementation of the house listing release in the related art, the broker takes a real-life photo of a house listing, and can shoot according to the full process shooting steps (such as steps 1-8), or according to the simplified process shooting steps (such as steps 5-8), and finally obtains the house listing video, and uploads the house listing video to the video library. At the same time, the broker can trigger the house listing release, and the post to be published is stored in the post library. The posts and videos (including the house listing video and the benchmark video) are matched with the minimum stock keeping unit (sku), and after matching, they are submitted for review. The consistency of the house listing video and the benchmark video is manually reviewed. If the review is successful, the rights and interests can be marked, including the configuration of value-added and package, and the rights and interests marking information is written back to the post to be published, and then the post to be published can be allowed to be published on the network platform. At the same time, the review results, such as the house listing review status and the video review status, can be updated, indicating that the house listing video uploaded to the video library is available, rather than unreviewed or failed to be reviewed. In the field of house listings, sku refers to the same building, the same building, and the same floor.

[0144] In this possible implementation, the consistency of the benchmark video and the listing video needs to be manually verified each time, which requires the reviewers to spend a long time on the review, resulting in low work efficiency and high review costs. In addition, if the video uploaded by the broker is mistakenly identified as the benchmark video, the subsequent manual review of the video will be inaccurate. Furthermore, there is a misjudgment rate in manual review, and long-term and large-scale review tasks will also lead to a high misjudgment rate.

[0145] In view of this situation, in a possible implementation method of the housing source release of the embodiment of the present application, the broker takes a field photo of a certain housing source, and can take photos according to the full process shooting steps (such as steps 1-8), or take photos according to the simplified process shooting steps (such as steps 5-8), and finally obtains the target video of the target housing source. The target video is uploaded to the video library. At the same time, the broker can trigger the housing source release, and the post to be released is stored in the post library. The posts and videos (including the target video and the reference video) are sku matched. After matching, the target video and the target reference video in the reference video set are compared. If they are consistent, the target video can be directly confirmed as a real and effective field video shot for the target housing source, and the audit is confirmed to be passed. If they are inconsistent, the consistency audit can be confirmed by manual audit. If the audit is successful, the rights and interests can be marked, and the rights and interests marking information can be written back to the post library, so as to allow the posts to be released to be published on the network platform. At the same time, the audit results, such as the housing source audit status and the video audit status, can be updated, indicating that the target video uploaded to the video library is available, rather than unaudited or audit failed. The reference video set here is obtained in advance through reference comparison, which can ensure the accuracy of the reference video.

[0146] In an embodiment of the present application, a similar video recognition technology is introduced. By comparing the similarity of a benchmark video with the similar video recognition technology, the accuracy of the benchmark video can be improved. When reviewing newly added property videos, the accuracy of video review can be improved.

[0147] By comparing the target video with the target reference video, a clear comparison result can be provided to the reviewer. If the video similarity is high, the reviewer can directly confirm it without the need for manual review. Only when the video similarity is low, manual review is required, which helps to improve review efficiency and reduce the false review rate.

[0148] Corresponding to the above method embodiment, the embodiment of the present application further provides a video authenticity determination device. The video authenticity determination device described below and the video authenticity determination method described above can refer to each other.

[0149] See also Figure 3 As shown, the video authenticity determination device 300 may include the following units:

[0150] A first obtaining unit 310 is used to obtain a target video for a target house;

[0151] A first determining unit 320, configured to determine a first similarity between the target video and the target reference video according to a similarity between a first type of video block included in the target video and a first type of video block included in the target reference video;

[0152] A second determination unit 330, configured to determine that the target video is a real shot video when the first similarity is greater than or equal to a first threshold;

[0153] Among them, the target reference video is a video in the reference video set corresponding to the target property; each reference video in the reference video set includes a second-category video block and a first-category video block, which is a real-shot video of the target property, and the second similarity determined based on the second-category video block between any two reference videos is greater than or equal to a second threshold; the first-category video block includes a plurality of video blocks shot based on a plurality of advanced process shooting steps, and the second-category video block includes a plurality of video blocks shot based on a plurality of basic process shooting steps, and the plurality of basic process shooting steps are before the plurality of advanced process shooting steps.

[0154] By using the device provided in the embodiment of the present application, the second similarity determined based on the second type of video block between any two reference videos in the reference video set corresponding to the target house source is greater than or equal to the second threshold value, which ensures the accuracy and reliability of the reference video set corresponding to the target house source, and the target reference video is a video in the reference video set, so the accuracy and reliability of the target reference video corresponding to the target house source are also guaranteed, and the second similarity between any two reference videos in the reference video set is determined only based on the second type of video block, which reduces the workload of similarity processing of the reference video. After obtaining the target video for the target house source, the first type of video block included in the target video is compared with the first type of video block included in the accurate target reference video, and the first similarity determined based on the first type of video block between the target video and the target reference video is obtained. Because the target reference video is a real-shot video of the target house source, when the first similarity is large, it can be determined that the target video is a real-shot video of the target house source, which realizes the accurate determination of the authenticity and validity of the target video, and the first similarity is determined only based on the first type of video block, which reduces the workload of similarity processing between the target video and the target reference video.

[0155] In some embodiments of the present application, the first determining unit 320 is further configured to determine the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video through the following steps:

[0156] For each first-category video block included in the target video, determining a corresponding first-category video block in the target reference video; the shooting steps corresponding to the corresponding first-category video block in the target reference video are the same as the shooting steps corresponding to the current first-category video block in the target video;

[0157] Performing feature extraction operations on the current first-category video block in the target video and the corresponding first-category video block in the target reference video respectively;

[0158] Based on the extracted features, the similarity between the current first-category video block in the target video and the corresponding first-category video block in the target reference video is determined.

[0159] In some embodiments of the present application, the first determining unit 320 is specifically configured to:

[0160] Determine the similarity between each first-category video block included in the target video and a corresponding first-category video block in the target reference video;

[0161] The average value, maximum value, minimum value or median value of the similarity between each first-category video block included in the determined target video and the corresponding first-category video block in the target reference video is determined as the first similarity between the target video and the target reference video.

[0162] In some embodiments of the present application, the first determining unit 320 is further configured to:

[0163] Before obtaining a target video for a target property, obtain multiple real-shot videos of the target property;

[0164] For a first real-shot video and a second real-shot video among the multiple real-shot videos, determining a second similarity between the first real-shot video and the second real-shot video according to a similarity between a second type of video block included in the first real-shot video and a second type of video block included in the second real-shot video;

[0165] If the second similarity is greater than or equal to the second threshold, determining the first real-shot video and the second real-shot video as reference videos in the reference video set corresponding to the target house;

[0166] The first real-shot video and the second real-shot video are any two real-shot videos among the multiple real-shot videos;

[0167] Each of the multiple real-shot videos includes a second-category video block and a first-category video block. The second-category video blocks included in each real-shot video include video blocks shot one-to-one based on each basic process shooting step. The first-category video blocks included in each real-shot video include video blocks shot one-to-one based on each advanced process shooting step.

[0168] In some embodiments of the present application, the first determining unit 320 is further configured to:

[0169] The similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video is determined by the following steps:

[0170] For each second-category video block included in the first real-shot video, determining a corresponding second-category video block in the second real-shot video; the shooting steps corresponding to the corresponding second-category video block in the second real-shot video are the same as the shooting steps corresponding to the current second-category video block in the first real-shot video;

[0171] Performing feature extraction operations on the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video respectively;

[0172] According to the extracted features, the similarity between the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video is determined.

[0173] In some embodiments of the present application, the first determining unit 320 is specifically configured to:

[0174] Determine a similarity between each second-category video block included in the first real-shot video and a corresponding second-category video block in the second real-shot video;

[0175] The average value, maximum value, minimum value or median value of the similarity between each second-category video block included in the determined first real-shot video and the corresponding second-category video block in the second real-shot video is determined as the second similarity between the first real-shot video and the second real-shot video.

[0176] In some embodiments of the present application, the video authenticity determination apparatus 300 further includes an output unit, which is used to:

[0177] When the first similarity is less than the first threshold, a review prompt message is output to manually determine whether the target video is a real field-shot video.

[0178] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0179] Corresponding to the above method embodiments, the embodiments of the present application also provide an electronic device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the various processes of the above-mentioned video authenticity determination method embodiments are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0180] like Figure 4 4 is a schematic diagram of a structure of an electronic device, which may include: a processor 410, a memory 411, a communication interface 412 and a communication bus 413. The processor 410, the memory 411 and the communication interface 412 communicate with each other through the communication bus 413.

[0181] In the embodiment of the present application, the processor 410 may be a central processing unit (CPU), an application specific integrated circuit, a digital signal processor, a field programmable gate array or other programmable logic devices, etc.

[0182] The processor 410 may call a computer program stored in the memory 411 . Specifically, the processor 410 may execute operations in the embodiment of the video authenticity determination method.

[0183] The memory 411 is used to store one or more programs, which may include program codes, and the program codes include computer operation instructions. In the embodiment of the present application, the memory 411 stores at least a program for implementing the following functions:

[0184] Get targeted videos for targeted listings;

[0185] Determine a first similarity between the target video and the target reference video according to a similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video;

[0186] If the first similarity is greater than or equal to the first threshold, determining that the target video is a real field-shot video;

[0187] Among them, the target reference video is a video in the reference video set corresponding to the target property; each reference video in the reference video set includes a second-category video block and a first-category video block, which is a real-shot video of the target property, and the second similarity determined based on the second-category video block between any two reference videos is greater than or equal to a second threshold; the first-category video block includes a plurality of video blocks shot based on a plurality of advanced process shooting steps, and the second-category video block includes a plurality of video blocks shot based on a plurality of basic process shooting steps, and the plurality of basic process shooting steps are before the plurality of advanced process shooting steps.

[0188] In one possible implementation, the memory 411 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function (such as a video comparison function, a video acquisition function), etc.; the data storage area may store data created during use, such as video data, comparison data, etc.

[0189] In addition, the memory 411 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0190] The communication interface 412 may be an interface of a communication module, and is used to connect to other devices or systems.

[0191] Of course, it should be noted that Figure 4 The structure shown does not constitute a limitation on the electronic device in the embodiment of the present application. In actual applications, the electronic device may include Figure 4 More or fewer components than shown, or combinations of certain components.

[0192] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, each process of the above-mentioned video authenticity determination method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it is not repeated here. Among them, the computer-readable storage medium, such as a read-only memory (Read-Only Memory, referred to as ROM), a random access memory (Random Access Memory, referred to as RAM), a disk or an optical disk, etc.

[0193] In addition, the embodiment of the present application also provides a computer program product or a computer program, which may include computer instructions, which may be stored in a computer-readable storage medium. The processor of the electronic device reads the computer instructions from the computer-readable storage medium, and the processor may execute the computer instructions so that the electronic device performs the description of the method for determining the authenticity of the video in the corresponding embodiment above, so it will not be repeated here. In addition, the description of the beneficial effects of using the same method will not be repeated. For technical details not disclosed in the computer program product or computer program embodiment involved in this application, please refer to the description of the method embodiment of this application.

[0194] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0195] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0196] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0197] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present application can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0198] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0199] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0200] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0201] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0202] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks, or optical disks.

[0203] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining video authenticity, characterized in that: include: Get targeted videos for targeted listings; Determining a first similarity between the target video and the target reference video according to a similarity between a first type of video block included in the target video and a first type of video block included in the target reference video; If the first similarity is greater than or equal to a first threshold, determining that the target video is a real, field-shot video; The target reference video is a video in the reference video set corresponding to the target house; Each benchmark video in the benchmark video set includes a second-category video block and the first-category video block, which is a real-shot video of the target property. The second similarity between any two benchmark videos determined based on the second-category video block is greater than or equal to a second threshold; the first-category video block includes a plurality of video blocks shot based on a plurality of advanced process shooting steps, and the second-category video block includes a plurality of video blocks shot based on a plurality of basic process shooting steps, and the plurality of basic process shooting steps are before the plurality of advanced process shooting steps.

2. The method according to claim 1, characterized in that The similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video is determined by the following steps: For each first-category video block included in the target video, determining a corresponding first-category video block in a target reference video; the shooting steps corresponding to the first-category video block in the target reference video are the same as the shooting steps corresponding to the current first-category video block in the target video; Performing feature extraction operations on the current first-category video block in the target video and the corresponding first-category video block in the target reference video respectively; According to the extracted features, the similarity between the current first-category video block in the target video and the corresponding first-category video block in the target reference video is determined.

3. The method according to claim 1, characterized in that The determining, according to the similarity between the first type of video blocks included in the target video and the first type of video blocks included in the target reference video, a first similarity between the target video and the target reference video comprises: Determine the similarity between each first-category video block included in the target video and a corresponding first-category video block in the target reference video; The average value, maximum value, minimum value or median value of the similarity between each first-category video block included in the target video and the corresponding first-category video block in the target reference video is determined as the first similarity between the target video and the target reference video.

4. The method according to claim 1, characterized in that Before obtaining the target video for the target house, the method further includes: Obtain multiple real-life videos of the target property; For a first real-shot video and a second real-shot video among the multiple real-shot videos, determining a second similarity between the first real-shot video and the second real-shot video according to a similarity between a second type of video block included in the first real-shot video and a second type of video block included in the second real-shot video; If the second similarity is greater than or equal to the second threshold, determining the first real-shot video and the second real-shot video as reference videos in a reference video set corresponding to the target house; The first real-shot video and the second real-shot video are any two real-shot videos among the multiple real-shot videos; Each of the multiple real-shot videos includes the second-category video blocks and the first-category video blocks, and the second-category video blocks included in each real-shot video include video blocks shot one-to-one based on each basic process shooting step, and the first-category video blocks included in each real-shot video include video blocks shot one-to-one based on each advanced process shooting step.

5. The method according to claim 4, characterized in that The similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video is determined by the following steps: For each second-category video block included in the first real-shot video, determining a corresponding second-category video block in the second real-shot video; the shooting steps corresponding to the second-category video block corresponding to the second real-shot video are the same as the shooting steps corresponding to the current second-category video block in the first real-shot video; Performing feature extraction operations on the current second-category video block in the first real-shot video and the corresponding second-category video block in the second real-shot video respectively; According to the extracted features, a similarity between a current second-category video block in the first real-shot video and a corresponding second-category video block in the second real-shot video is determined.

6. The method according to claim 4, characterized in that The determining, according to the similarity between the second type of video blocks included in the first real-shot video and the second type of video blocks included in the second real-shot video, the second similarity between the first real-shot video and the second real-shot video comprises: Determine a similarity between each second-category video block included in the first real-shot video and a corresponding second-category video block in the second real-shot video; The average value, maximum value, minimum value or median value of the similarity between each second-category video block included in the first real-shot video and the corresponding second-category video block in the second real-shot video is determined as the second similarity between the first real-shot video and the second real-shot video.

7. The method according to any one of claims 1 to 6, characterized in that When the first similarity is less than the first threshold, the method further includes: Output a review prompt message to manually determine whether the target video is a real field-shot video.

8. A video authenticity determination device, characterized in that: include: A first obtaining unit, used to obtain a target video for a target house; A first determining unit, configured to determine a first similarity between the target video and the target reference video according to a similarity between a first type of video block included in the target video and a first type of video block included in a target reference video; A second determining unit, configured to determine that the target video is a real video shot when the first similarity is greater than or equal to a first threshold; The target reference video is a video in the reference video set corresponding to the target house; Each benchmark video in the benchmark video set includes a second-category video block and the first-category video block, which is a real-shot video of the target property. The second similarity between any two benchmark videos determined based on the second-category video block is greater than or equal to a second threshold; the first-category video block includes a plurality of video blocks shot based on a plurality of advanced process shooting steps, and the second-category video block includes a plurality of video blocks shot based on a plurality of basic process shooting steps, and the plurality of basic process shooting steps are before the plurality of advanced process shooting steps.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the video authenticity determination method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the video authenticity determination method according to any one of claims 1 to 7 are implemented.

Images