A method, apparatus, electronic device, and storage medium for determining video similarity.

Abstract

This invention relates to a video similarity determination method, apparatus, electronic device, and storage medium, comprising: acquiring a first video set corresponding to a first channel and a second video set corresponding to a second channel within a preset time period; determining a first user overlap degree between the first video and the second video, and a second user overlap degree under the influence of the number of channel users, for any first video in the first video set and any second video in the second video set; determining a third user overlap degree after removing the influence of the number of channel users based on the first user overlap degree and the second user overlap degree; determining a time correction factor between the first video and the second video affected by the upload time, and processing the third user overlap degree using the time correction factor to obtain the video similarity between the first video and the second video. Therefore, this invention removes the influence of the number of channel users and the video upload time on the obtained video similarity, improving the accuracy of video similarity.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of video processing technology, and in particular to a method, apparatus, electronic device and storage medium for determining video similarity. Background Technology

[0002] Video similarity is fundamental to video recommendation, operation, and planning management. By calculating the video similarity (i.e., user overlap) between different videos based on the number of users watching them, videos with similar content are clustered, and the clustering results are used to implement video recommendation, operation, and planning management.

[0003] As the most important feature of a video, the channel is the biggest constraint on video recommendation, operation, and planning management, with almost all video actions taking place within the same channel. However, as users' interest in and demand for videos gradually strengthens, their viewing preferences are increasingly transcending the limitations of channels. The current method of calculating video similarity for recommendation, operation, and planning management fails to consider the impact of different channel user numbers and video upload times on video similarity. It excessively amplifies the influence of channel differences and video upload times, leading to inaccurate video similarity results and consequently, inaccurate clustering results derived from video similarity. Summary of the Invention

[0004] In view of this, in order to solve the above-mentioned technical problems or some of the technical problems, the present invention provides a video similarity determination method, apparatus, electronic device and storage medium.

[0005] In a first aspect, embodiments of the present invention provide a video similarity determination method, comprising:

[0006] Get the first video set corresponding to the first channel and the second video set corresponding to the second channel within a preset time period;

[0007] For any first video in the first video set and any second video in the second video set, determine the first user overlap between the first video and the second video, and the second user overlap under the influence of the number of channel users;

[0008] Based on the first user overlap and the second user overlap, a third user overlap is determined after removing the influence of the number of channel users;

[0009] A time correction factor affecting the online time between the first video and the second video is determined, and the overlap of the third user is processed using the time correction factor to obtain the video similarity between the first video and the second video.

[0010] In an optional implementation, the method further includes:

[0011] Determine the first user set corresponding to the first channel and the second user set corresponding to the second channel, and determine the third user set corresponding to the first video and the fourth user set corresponding to the second video within the preset time period;

[0012] The second user overlap is determined in the following way:

[0013] Determine the first intersection between the first user set and the second user set, and the first union between the third user set and the fourth user set;

[0014] The overlap of the second user is determined based on the number of people corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set.

[0015] In an optional implementation, determining the second user overlap includes:

[0016] The number of users corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set are input into the second user overlap calculation formula to obtain the second user overlap; wherein, the second user overlap calculation formula includes:

[0017]

[0018] In the above formula, r s Let X∩Y represent the number of users in the first intersection, A represent the number of users in the third user set, B represent the number of users in the fourth user set, X represent the number of users in the first user set, Y represent the number of users in the second user set, and A∪B represent the number of users in the first union.

[0019] In an optional implementation, determining the third user overlap degree, after removing the influence of channel user count, based on the first user overlap degree and the second user overlap degree includes:

[0020] The first user overlap and the second user overlap are input into the third user overlap calculation formula to obtain the third user overlap; wherein, the third user overlap calculation formula includes:

[0021]

[0022] In the above formula, S ab Indicates the overlap of third-party users, r sIndicates the overlap of the second user, r AB Let X represent the first degree of overlap among users, X∩Y represent the number of people corresponding to the first intersection, A represent the number of people corresponding to the third user set, B represent the number of people corresponding to the fourth user set, X represent the number of people corresponding to the first user set, Y represent the number of people corresponding to the second user set, and A∩B represent the number of people corresponding to the second intersection between the third and fourth user sets.

[0023] In an optional implementation, the time correction factor includes: a first correction factor affected by the online duration of the first video, a second correction factor affected by the online duration of the second video, and a third correction factor affected by the online interval between the first video and the second video.

[0024] The first correction factor, the second correction factor, and the third correction factor are determined in the following manner:

[0025] Determine the preset duration corresponding to the preset time period, the first online duration of the first video in the first channel within the preset time period, the second online duration of the second video in the second channel, and the online time interval between the first video and the second video;

[0026] The minimum online duration is determined from the first online duration and the second online duration;

[0027] The first correction factor is determined based on the preset duration and the first online duration;

[0028] The second correction factor is determined based on the preset duration and the second online duration;

[0029] The third correction factor is determined based on the preset duration, the minimum online duration, and the online time interval.

[0030] In an optional implementation, determining the first correction factor based on the preset duration and the first online duration includes:

[0031] The preset duration and the first online duration are input into the first correction factor calculation formula to obtain the first correction factor; wherein, the first correction factor calculation formula includes:

[0032] α=(T a T) -kx

[0033] In the above formula, α represents the first correction factor, and T a This indicates the initial online duration, T indicates the preset duration, and -kx indicates the preset constant value.

[0034] The step of determining the second correction factor based on the preset duration and the second online duration includes:

[0035] The preset duration and the second online duration are input into the second correction factor calculation formula to obtain the second correction factor; wherein, the second correction factor calculation formula includes:

[0036] β=(T b T) -ky

[0037] In the above formula, β represents the second correction factor, and T b This indicates the second online duration, T represents the preset duration, and -ky represents the preset constant value;

[0038] The step of determining the third correction factor based on the preset duration, the minimum online duration, and the online time interval includes:

[0039] The preset duration, the minimum online duration, and the online time interval are input into the third correction factor calculation formula to obtain the third correction factor; wherein, the third correction factor calculation formula includes:

[0040] γ=(T new T) -kxy ×(dt) -kt

[0041] In the above formula, γ represents the third correction factor, and T new The minimum online duration is represented by T, the preset duration is represented by dt, the online time interval is represented by -kxy and -kt, which are both preset constant values.

[0042] In an optional implementation, the method further includes:

[0043] Determine the fifth user set corresponding to the first channel, the sixth user set corresponding to the second channel, and the third intersection between the fifth user set and the sixth user set within the preset time period;

[0044] The step of processing the overlap of the third user using the time correction factor to obtain the video similarity between the first video and the second video includes:

[0045] The number of users corresponding to the first user set is replaced with the product of the number of users corresponding to the fifth user set and the first correction factor; the number of users corresponding to the second user set is replaced with the product of the number of users corresponding to the sixth user set and the second correction factor; and the number of users corresponding to the first intersection is replaced with the product of the number of users corresponding to the third intersection and the third correction factor. These are then input into the third user overlap calculation formula, as shown below:

[0046]

[0047] In the above formula, A∩B represents the number of people corresponding to the second intersection between the third user set and the fourth user set, A represents the number of people corresponding to the third user set, B represents the number of people corresponding to the fourth user set, α represents the first correction factor, β represents the second correction factor, γ represents the third correction factor, X0 represents the number of people corresponding to the fifth user set, Y0 represents the number of people corresponding to the sixth user set, and X0∩Y0 represents the number of people corresponding to the third intersection.

[0048] The calculation result output by the third user overlap calculation formula is obtained, and the calculation result is determined as the video similarity.

[0049] Secondly, embodiments of the present invention provide a video similarity determination apparatus, comprising:

[0050] The acquisition module is used to acquire the first video set corresponding to the first channel and the second video set corresponding to the second channel within a preset time period;

[0051] The determination module is used to determine, for any first video in the first video set and any second video in the second video set, a first user overlap degree between the first video and the second video, and a second user overlap degree under the influence of the number of channel users;

[0052] The determining module is further configured to determine a third user overlap degree, after removing the influence of the number of channel users, based on the first user overlap degree and the second user overlap degree;

[0053] The determining module is further configured to determine a time correction factor between the first video and the second video affected by the online time, and use the time correction factor to process the overlap of the third user to obtain the video similarity between the first video and the second video.

[0054] Thirdly, embodiments of the present invention provide an electronic device, including: a processor and a memory, wherein the processor is configured to execute a video similarity determination program stored in the memory to implement the video similarity determination method as described above.

[0055] Fourthly, embodiments of the present invention provide a storage medium storing one or more programs, which can be executed by one or more processors to implement the video similarity determination method described above.

[0056] This invention provides a video similarity determination method, comprising: acquiring a first video set corresponding to a first channel and a second video set corresponding to a second channel within a preset time period; determining a first user overlap degree between the first video and the second video, and a second user overlap degree under the influence of the number of channel users, for any first video in the first video set and any second video in the second video set; determining a third user overlap degree after removing the influence of the number of channel users based on the first user overlap degree and the second user overlap degree; determining a time correction factor between the first video and the second video affected by the upload time, and processing the third user overlap degree using the time correction factor to obtain the video similarity between the first video and the second video. Through the above method, the video similarity between two videos from different channels obtained by this invention removes the influence of the number of channel users and the video upload time on the obtained video similarity, thus improving the accuracy of video similarity. Attached Figure Description

[0057] Figure 1 A flowchart illustrating a video similarity determination method provided in an embodiment of the present invention;

[0058] Figure 2 This is a schematic diagram of the structure of a video similarity determination device provided in an embodiment of the present invention;

[0059] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention;

[0060] In the attached diagrams above:

[0061] 10. Obtain module; 20. Confirm module;

[0062] 400. Electronic device; 401. Processor; 402. Memory; 4021. Operating system; 4022. Application program; 403. User interface; 404. Network interface; 405. Bus system. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0064] To facilitate understanding of the embodiments of the present invention, further explanations and descriptions will be provided below with reference to the accompanying drawings and specific embodiments. These embodiments do not constitute a limitation on the embodiments of the present invention.

[0065] refer to Figure 1 , Figure 1 This is a flowchart illustrating a video similarity determination method provided in an embodiment of the present invention. The video similarity determination method provided in this embodiment of the present invention includes the following steps:

[0066] S101: Obtain the first video set corresponding to the first channel and the second video set corresponding to the second channel within a preset time period.

[0067] In this embodiment, the first channel and the second channel belong to different channels of the same video website. Channels can generally be divided into TV drama channels, movie channels, game channels, children's channels, and variety show channels, etc. The first video set includes at least one first video, and similarly, the second video set includes at least one second video. The first video set belongs to the first channel, and the second video set belongs to the second channel. The first video set consists of first videos from the first channel that meet corresponding preset conditions within a preset time period, and the second video set consists of second videos from the second channel that meet corresponding preset conditions within a preset time period. Specifically, step S101, obtaining the first video set corresponding to the first channel and the second video set corresponding to the second channel within a preset time period, includes:

[0068] Get multiple first videos from the first channel within a preset time period whose video playback rate is greater than a preset threshold, to obtain a first video set; and get multiple second videos from the second channel within a preset time period whose video playback rate is greater than a preset threshold, to obtain a second video set.

[0069] In this embodiment, the preset time period represents the time period between the second preset time and the first preset time, where the first preset time is longer than the second preset time. The first and second preset times can be set according to the needs of the business, and this embodiment does not impose specific limitations on them. For example, the first preset time could be March 31, 2022, and the second preset time could be January 1, 2019. Similarly, the preset threshold can also be set according to actual needs, and this embodiment does not impose specific limitations on it.

[0070] S102: For any first video in the first video set and any second video in the second video set, determine the first user overlap between the first video and the second video, and the second user overlap under the influence of the number of channel users.

[0071] In this embodiment, when calculating the video similarity between two videos on different channels, directly calculating the video similarity based on the number of users watching the video would excessively amplify the impact of differences between channels, reducing the video similarity between two videos with the same theme and content. To avoid this problem, the user overlap between the two videos and the user overlap between the two videos under the influence of the number of users on the channel are determined. Then, a user overlap rate is calculated based on the user overlap of the two videos, removing the influence of the number of users on the channel, thus eliminating the impact of the number of users on the obtained video similarity.

[0072] In this embodiment, the first user overlap degree represents the content similarity between two videos. Specifically, the first user overlap degree can be determined in the following way, as follows.

[0073] Determine the third user set corresponding to the first video and the fourth user set corresponding to the second video within a preset time period;

[0074] Determine the second intersection between the third user set and the fourth user set, and the first union between the third user set and the fourth user set;

[0075] The overlap of the first user is determined based on the number of people corresponding to the second intersection and the number of people corresponding to the first union.

[0076] Specifically, the number of people corresponding to the second intersection and the number of people corresponding to the first union are input into the formula for calculating the first user overlap to obtain the first user overlap; wherein, the formula for calculating the first user overlap includes:

[0077]

[0078] In the above formula, r AB Let A∪B represent the first user overlap, A∪B represent the number of people corresponding to the first union, and A∩B represent the number of people corresponding to the second intersection.

[0079] In the above, the third user set consists of at least one third user, who is a user who watches the first video on the first channel within a preset time period. The fourth user set consists of at least one fourth user, who is a user who watches the second video on the second channel within a preset time period. Specifically, based on the user's registered account on the video website, when a user watches the first video on the first channel within the preset time period, that account is recorded as a user watching the first video, thus obtaining the third user set. Similarly, the fourth user set can be obtained using the same method. In detail, after obtaining the third and fourth user sets, the overlap rate of first users between the first and second videos can be calculated based on the third and fourth user sets.

[0080] In this embodiment, the second user overlap degree represents the content similarity between two videos under the influence of the number of channel users. Specifically, the second user overlap degree can be determined in the following way, as follows.

[0081] Determine the first user set corresponding to the first channel and the second user set corresponding to the second channel, and determine the third user set corresponding to the first video and the fourth user set corresponding to the second video within a preset time period;

[0082] Determine the first intersection between the first user set and the second user set, and the first union between the third user set and the fourth user set;

[0083] The overlap of the second user is determined based on the number of people corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set.

[0084] Specifically, the overlap of the second user group is determined based on the number of people corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set, including:

[0085] The number of users corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set are input into the second user overlap calculation formula to obtain the second user overlap. The second user overlap calculation formula includes:

[0086]

[0087] In the above formula, r s Let X∩Y represent the number of users in the first intersection, A represent the number of users in the third user set, B represent the number of users in the fourth user set, X represent the number of users in the first user set, Y represent the number of users in the second user set, and A∪B represent the number of users in the first union.

[0088] In the above, the first user set consists of users using the first channel, the third user set belongs to the first user set, the second user set consists of users using the second channel, and the fourth user set belongs to the second user set. Specifically, when a user uses a video website, they register an account. When they use the first channel (i.e., watch videos on the first channel), that account is recorded as the first user corresponding to the first channel. Thus, multiple first users can be obtained within a preset time period. Similarly, based on the user's registered account on the video website, when they use the second channel (i.e., watch videos on the second channel), that account is recorded as the second user corresponding to the second channel. Thus, multiple second users can be obtained within a preset time period.

[0089] S103: Determine the third user overlap degree after removing the influence of the number of channel users based on the first user overlap degree and the second user overlap degree.

[0090] In this embodiment, since the first user overlap is the content similarity between two videos, and the second user overlap is the content similarity between two videos under the influence of the number of channel users, dividing the first user overlap by the second user overlap yields the third user overlap after removing the influence of the number of channel users. Specifically, the third user overlap can be determined in the following way:

[0091] The overlap rates of the first and second users are input into the formula for calculating the overlap rate of the third user to obtain the overlap rate of the third user; wherein, the formula for calculating the overlap rate of the third user includes:

[0092]

[0093] In the above formula, S ab Indicates the overlap of third-party users, r s Indicates the overlap of the second user, r AB Let X represent the first degree of overlap among users, X∩Y represent the number of people corresponding to the first intersection, A represent the number of people corresponding to the third user set, B represent the number of people corresponding to the fourth user set, X represent the number of people corresponding to the first user set, Y represent the number of people corresponding to the second user set, and A∩B represent the number of people corresponding to the second intersection between the third and fourth user sets.

[0094] S104: Determine the time correction factor between the first video and the second video affected by the online time, and use the time correction factor to process the overlap of the third user to obtain the video similarity between the first video and the second video.

[0095] In this embodiment, the number of users in the first channel and the number of users in the second channel are values ​​that change over time and are difficult to replace with a constant value. Considering that the video upload time will affect the calculation of the video similarity between the first video and the second video, the video upload time is taken into account when calculating the video similarity between the first video and the second video. This is to correct the problem of low video similarity caused by short video upload time and large interval between the uploads of the two videos, thereby improving the accuracy of the final video similarity between the first video and the second video.

[0096] Specifically, the time correction factors include: a first correction factor affected by the online duration of the first video, a second correction factor affected by the online duration of the second video, and a third correction factor affected by the online interval between the first and second videos.

[0097] More specifically, the first correction factor, the second correction factor, and the third correction factor can be determined in the following manner, as detailed below.

[0098] Determine the preset duration corresponding to the preset time period, the first online duration of the first video in the first channel within the preset time period, the second online duration of the second video in the second channel, and the online time interval between the first video and the second video.

[0099] The minimum online duration is determined from the first online duration and the second online duration;

[0100] The first correction factor is determined based on the preset duration and the first online duration;

[0101] The second correction factor is determined based on the preset duration and the second online duration;

[0102] The third correction factor is determined based on the preset duration, minimum online duration, and online time interval.

[0103] In the above, regarding the first correction factor, the preset duration represents the difference between the first preset time and the second preset time. The first preset time is greater than the second preset time, and the first online duration is less than or equal to the preset duration. In this embodiment, when the first online time of the first video in the first channel is less than the second preset time, the first online duration is the preset duration; when the first online time of the first video in the first channel is greater than or equal to the second preset time, the first online duration is the difference between the first preset time and the first online time.

[0104] Regarding the second correction factor, the second online duration is less than or equal to a preset duration. In this embodiment, when the second online time of the second video in the second channel is less than the second preset time, the second online duration is the preset duration; when the second online time of the second video in the second channel is greater than or equal to the second preset time, the second online duration is the difference between the first preset time and the second online time.

[0105] Regarding the third correction factor, the online time interval can be determined as follows: Determine the first online time of the first video in the first channel, and determine the second online time of the second video in the second channel. When the second online time is greater than or equal to the first online time, the difference between the second and first online times is determined as the online time interval; when the second online time is less than the first online time, the difference between the first and second online times is determined as the online time interval. In this embodiment, when the first online duration is greater than or equal to the second online duration, it indicates that the first video has a longer online duration than the second video, and the second online duration is taken as the minimum online duration; when the first online duration is less than the second online duration, it indicates that the second video has a longer online duration than the first video, and the first online duration is taken as the minimum online duration.

[0106] In this embodiment, the first correction factor is determined based on the preset duration and the first online duration, including:

[0107] The preset duration and the first online duration are input into the first correction factor calculation formula to obtain the first correction factor; wherein, the first correction factor calculation formula includes:

[0108] α=(T a T) -kx

[0109] In the above formula, α represents the first correction factor, and T a This indicates the first online duration, T indicates the preset duration, and -kx indicates the preset constant value.

[0110] In this embodiment, the second correction factor is determined based on the preset duration and the second online duration, including:

[0111] The preset duration and the second online duration are input into the second correction factor calculation formula to obtain the second correction factor; wherein, the second correction factor calculation formula includes:

[0112] β=(T b T) -ky

[0113] In the above formula, β represents the second correction factor, and T b This indicates the second online duration, T represents the preset duration, and -ky represents the preset constant value.

[0114] In this embodiment, a third correction factor is determined based on a preset duration, a minimum online duration, and an online time interval, including:

[0115] The preset duration, minimum online duration, and online time interval are input into the third correction factor calculation formula to obtain the third correction factor; wherein, the third correction factor calculation formula includes:

[0116] γ=(T new T) -kxy ×(dt) -kt

[0117] In the above formula, γ represents the third correction factor, and T new The minimum online duration is represented by T, the preset duration is represented by dt, the online time interval is represented by -kxy and -kt, which are both preset constant values.

[0118] In this embodiment, the video similarity between the first video and the second video can be determined in the following manner, as detailed below.

[0119] Determine the fifth user set corresponding to the first channel, the sixth user set corresponding to the second channel, and the third intersection between the fifth and sixth user sets within a preset time period;

[0120] Replace the number of users corresponding to the first user set with the product of the number of users corresponding to the fifth user set and the first correction factor, replace the number of users corresponding to the second user set with the product of the number of users corresponding to the sixth user set and the second correction factor, and replace the number of users corresponding to the first intersection with the product of the number of users corresponding to the third intersection and the third correction factor. Input these into the third user overlap calculation formula, as shown below:

[0121]

[0122] In the above formula, A∩B represents the number of people corresponding to the second intersection between the third user set and the fourth user set, A represents the number of people corresponding to the third user set, B represents the number of people corresponding to the fourth user set, α represents the first correction factor, β represents the second correction factor, γ represents the third correction factor, X0 represents the number of people corresponding to the fifth user set, Y0 represents the number of people corresponding to the sixth user set, and X0∩Y0 represents the number of people corresponding to the third intersection.

[0123] The calculation result output by the third user overlap calculation formula is obtained, and the calculation result is determined as the video similarity.

[0124] Specifically, the fifth user group consists of users who watch the first video using the first channel within a preset time period, and the sixth user group consists of users who watch the second video using the second channel within a preset time period.

[0125] More specifically, the above formula for calculating video similarity can be further transformed into the following:

[0126]

[0127] In the above formula, T old This represents the maximum online duration between the first and second online durations; -k1, -k2, and -k3 are all preset constant values.

[0128] This invention provides a video similarity determination method that, by obtaining the video similarity between two videos from different channels using the above method, eliminates the influence of the number of channel users and the video's upload time on the obtained video similarity, thereby improving the accuracy of video similarity determination.

[0129] refer to Figure 2 , Figure 2 This is a schematic diagram of a video similarity determination device provided in an embodiment of the present invention. The video similarity determination device provided in this embodiment includes an acquisition module and a determination module. The acquisition module 10 is used to acquire a first video set corresponding to a first channel and a second video set corresponding to a second channel within a preset time period. The determination module 20 is used to determine a first user overlap degree between any first video in the first video set and any second video in the second video set, and a second user overlap degree under the influence of the number of users in the channel. The determination module 20 is further used to determine a third user overlap degree, removing the influence of the number of users in the channel, based on the first user overlap degree and the second user overlap degree. The determination module 20 is also used to determine a time correction factor between the first video and the second video, influenced by their online time, and to process the third user overlap degree using the time correction factor to obtain the video similarity between the first video and the second video.

[0130] In this embodiment, the determining module 20 is further configured to:

[0131] Determine the first user set corresponding to the first channel and the second user set corresponding to the second channel, and determine the third user set corresponding to the first video and the fourth user set corresponding to the second video within the preset time period;

[0132] Determine the first intersection between the first user set and the second user set, and the first union between the third user set and the fourth user set;

[0133] The overlap of the second user is determined based on the number of people corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set.

[0134] In this embodiment, the determining module 20 is further configured to:

[0135] The number of users corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set are input into the second user overlap calculation formula to obtain the second user overlap; wherein, the second user overlap calculation formula includes:

[0136]

[0137] In the above formula, r s Let X∩Y represent the number of users in the first intersection, A represent the number of users in the third user set, B represent the number of users in the fourth user set, X represent the number of users in the first user set, Y represent the number of users in the second user set, and A∪B represent the number of users in the first union.

[0138] In this embodiment, the determining module 20 is further configured to:

[0139] The first user overlap and the second user overlap are input into the third user overlap calculation formula to obtain the third user overlap; wherein, the third user overlap calculation formula includes:

[0140]

[0141] In the above formula, S ab Indicates the overlap of third-party users, r s Indicates the overlap of the second user, r AB Let X represent the first degree of overlap among users, X∩Y represent the number of people corresponding to the first intersection, A represent the number of people corresponding to the third user set, B represent the number of people corresponding to the fourth user set, X represent the number of people corresponding to the first user set, Y represent the number of people corresponding to the second user set, and A∩B represent the number of people corresponding to the second intersection between the third and fourth user sets.

[0142] In this embodiment, the determining module 20 is further configured to:

[0143] Determine the preset duration corresponding to the preset time period, the first online duration of the first video in the first channel within the preset time period, the second online duration of the second video in the second channel, and the online time interval between the first video and the second video;

[0144] The minimum online duration is determined from the first online duration and the second online duration;

[0145] The first correction factor is determined based on the preset duration and the first online duration;

[0146] The second correction factor is determined based on the preset duration and the second online duration;

[0147] The third correction factor is determined based on the preset duration, the minimum online duration, and the online time interval.

[0148] In this embodiment, the determining module 20 is further configured to:

[0149] The preset duration and the first online duration are input into the first correction factor calculation formula to obtain the first correction factor; wherein, the first correction factor calculation formula includes:

[0150] α=(T a T) -kx

[0151] In the above formula, α represents the first correction factor, and T a This indicates the first online duration, T indicates the preset duration, and -kx indicates the preset constant value.

[0152] In this embodiment, the determining module 20 is further configured to:

[0153] The preset duration and the second online duration are input into the second correction factor calculation formula to obtain the second correction factor; wherein, the second correction factor calculation formula includes:

[0154] β=(T b T) -ky

[0155] In the above formula, β represents the second correction factor, and T b This indicates the second online duration, T represents the preset duration, and -ky represents the preset constant value.

[0156] In this embodiment, the determining module 20 is further configured to:

[0157] The preset duration, the minimum online duration, and the online time interval are input into the third correction factor calculation formula to obtain the third correction factor; wherein, the third correction factor calculation formula includes:

[0158] γ=(T new T) -kxy ×(dt) -kt

[0159] In the above formula, γ represents the third correction factor, and T newThe minimum online duration is represented by T, the preset duration is represented by dt, the online time interval is represented by -kxy and -kt, which are both preset constant values.

[0160] In this embodiment, the determining module 20 is further configured to:

[0161] Determine the fifth user set corresponding to the first channel, the sixth user set corresponding to the second channel, and the third intersection between the fifth user set and the sixth user set within the preset time period;

[0162] The number of users corresponding to the first user set is replaced with the product of the number of users corresponding to the fifth user set and the first correction factor; the number of users corresponding to the second user set is replaced with the product of the number of users corresponding to the sixth user set and the second correction factor; and the number of users corresponding to the first intersection is replaced with the product of the number of users corresponding to the third intersection and the third correction factor. These are then input into the third user overlap calculation formula, as shown below:

[0163]

[0164] In the above formula, A∩B represents the number of people corresponding to the second intersection between the third user set and the fourth user set, A represents the number of people corresponding to the third user set, B represents the number of people corresponding to the fourth user set, α represents the first correction factor, β represents the second correction factor, γ represents the third correction factor, X0 represents the number of people corresponding to the fifth user set, Y0 represents the number of people corresponding to the sixth user set, and X0∩Y0 represents the number of people corresponding to the third intersection.

[0165] The calculation result output by the third user overlap calculation formula is obtained, and the calculation result is determined as the video similarity.

[0166] This embodiment provides a video similarity determination device that, through the above method, removes the influence of the number of channel users and the video upload time on the obtained video similarity, thereby improving the accuracy of video similarity.

[0167] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 3 The illustrated electronic device 400 includes at least one processor 401, a memory 402, at least one network interface 404, and other user interfaces 403. The various components in the electronic device 400 are coupled together via a bus system 405. It is understood that the bus system 405 is used to implement communication between these components. In addition to a data bus, the bus system 405 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in… Figure 3 The general designated all buses as Bus System 405.

[0168] The user interface 403 may include a display, keyboard, or clicking device (e.g., mouse, trackball, touchpad, or touchscreen).

[0169] It is understood that the memory 402 in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DRRAM). The memory 402 described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0170] In some implementations, memory 402 stores elements, executable units or data structures, or subsets thereof, or extended sets thereof: operating system 4021 and application program 4022.

[0171] The operating system 4021 includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application program 4022 includes various applications, such as a media player and a browser, used to implement various application functions. The program implementing the method of this embodiment can be included in the application program 4022.

[0172] In this embodiment of the invention, by calling the program or instructions stored in the memory 402, specifically the program or instructions stored in the application program 4022, the processor 401 is used to execute the method steps provided in each method embodiment, such as: obtaining a first video set corresponding to a first channel and a second video set corresponding to a second channel within a preset time period; for any first video in the first video set and any second video in the second video set, determining a first user overlap between the first video and the second video, and a second user overlap under the influence of the number of channel users; determining a third user overlap after removing the influence of the number of channel users based on the first user overlap and the second user overlap; determining a time correction factor between the first video and the second video affected by the online time, and processing the third user overlap using the time correction factor to obtain the video similarity between the first video and the second video.

[0173] The methods disclosed in the above embodiments of the present invention can be applied to processor 401, or implemented by processor 401. Processor 401 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in processor 401 or by instructions in the form of software. The processor 401 may be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software units in the decoding processor. The software units may be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 402. Processor 401 reads the information in memory 402 and, in conjunction with its hardware, completes the steps of the above method.

[0174] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0175] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0176] The electronic device provided in this embodiment may be as follows: Figure 3 The electronic device shown can perform the following: Figure 1 All steps of the method for determining the similarity of medium-length videos, thereby achieving Figure 1 For details on the technical effectiveness of the video similarity determination method shown, please refer to [link / reference]. Figure 1 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0177] This invention also provides a storage medium (computer-readable storage medium). This storage medium stores one or more programs. The storage medium may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid-state drive; the memory may also include combinations of the above types of memory.

[0178] One or more programs in the storage medium can be executed by one or more processors to implement the video similarity determination method described above, which is executed on the video similarity determination device side.

[0179] The processor is used to execute a video similarity determination program stored in the memory to implement the following steps of a video similarity determination method executed on the video similarity determination device side: obtaining a first video set corresponding to a first channel and a second video set corresponding to a second channel within a preset time period; for any first video in the first video set and any second video in the second video set, determining a first user overlap between the first video and the second video, and a second user overlap under the influence of the number of channel users; determining a third user overlap after removing the influence of the number of channel users based on the first user overlap and the second user overlap; determining a time correction factor between the first video and the second video affected by the online time, and processing the third user overlap using the time correction factor to obtain the video similarity between the first video and the second video.

[0180] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0181] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0182] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for determining video similarity, characterized in that, include: Get the first video set corresponding to the first channel and the second video set corresponding to the second channel within a preset time period; For any first video in the first video set and any second video in the second video set, determine the first user overlap between the first video and the second video, and the second user overlap under the influence of the number of channel users; Based on the first user overlap and the second user overlap, a third user overlap is determined after removing the influence of the number of channel users; Determine the time correction factor between the first video and the second video affected by the online time, and use the time correction factor to process the overlap of the third user to obtain the video similarity between the first video and the second video; The method further includes: Determine the first user set corresponding to the first channel and the second user set corresponding to the second channel, and determine the third user set corresponding to the first video and the fourth user set corresponding to the second video within the preset time period; The step of determining the third user overlap degree, after removing the influence of the number of channel users, based on the first user overlap degree and the second user overlap degree includes: The first user overlap and the second user overlap are input into the third user overlap calculation formula to obtain the third user overlap; wherein, the third user overlap calculation formula includes: In the above formula, Indicates the degree of overlap among third-party users. Indicates the degree of overlap between the second and third users. Indicates the degree of user overlap. This represents the number of users corresponding to the first intersection between the first user set and the second user set. This represents the number of people corresponding to the third user set. This represents the number of people corresponding to the fourth user set. This represents the number of people corresponding to the first user set. This represents the number of people corresponding to the second user set. This represents the number of people corresponding to the second intersection between the third user set and the fourth user set.

2. The method according to claim 1, characterized in that, The second user overlap is determined in the following way: Determine the first intersection between the first user set and the second user set, and the first union between the third user set and the fourth user set; The overlap of the second user is determined based on the number of people corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set.

3. The method according to claim 2, characterized in that, Determining the overlap of the second user includes: The number of users corresponding to the first intersection, the first union, the first user set, the second user set, the third user set, and the fourth user set are input into the second user overlap calculation formula to obtain the second user overlap; wherein, the second user overlap calculation formula includes: In the above formula, Indicates the degree of overlap between the second and third users. This represents the number of people corresponding to the first intersection. This represents the number of people corresponding to the third user set. This represents the number of people corresponding to the fourth user set. This represents the number of people corresponding to the first user set. This represents the number of people corresponding to the second user set. This represents the number of people in the first union.

4. The method according to claim 1, characterized in that, The time correction factor includes: a first correction factor affected by the online duration of the first video, a second correction factor affected by the online duration of the second video, and a third correction factor affected by the online interval between the first video and the second video; The first correction factor, the second correction factor, and the third correction factor are determined in the following manner: Determine the preset duration corresponding to the preset time period, the first online duration of the first video in the first channel within the preset time period, the second online duration of the second video in the second channel, and the online time interval between the first video and the second video; The minimum online duration is determined from the first online duration and the second online duration; The first correction factor is determined based on the preset duration and the first online duration; The second correction factor is determined based on the preset duration and the second online duration; The third correction factor is determined based on the preset duration, the minimum online duration, and the online time interval.

5. The method according to claim 4, characterized in that, The step of determining the first correction factor based on the preset duration and the first online duration includes: The preset duration and the first online duration are input into the first correction factor calculation formula to obtain the first correction factor; wherein, the first correction factor calculation formula includes: In the above formula, Indicates the first correction factor. Indicates the initial online duration. Indicates the preset duration. Indicates a preset constant value; The step of determining the second correction factor based on the preset duration and the second online duration includes: The preset duration and the second online duration are input into the second correction factor calculation formula to obtain the second correction factor; wherein, the second correction factor calculation formula includes: In the above formula, Indicates the second correction factor. Indicates the second online duration. Indicates the preset duration. Indicates a preset constant value; The step of determining the third correction factor based on the preset duration, the minimum online duration, and the online time interval includes: The preset duration, the minimum online duration, and the online time interval are input into the third correction factor calculation formula to obtain the third correction factor; wherein, the third correction factor calculation formula includes: In the above formula, Indicates the third correction factor. Indicates the minimum online duration. Indicates the preset duration. Indicates the time interval between going online. and All of these represent preset constant values.

6. The method according to claim 5, characterized in that, The method further includes: Determine the fifth user set corresponding to the first channel, the sixth user set corresponding to the second channel, and the third intersection between the fifth user set and the sixth user set within the preset time period; The step of processing the overlap of the third user using the time correction factor to obtain the video similarity between the first video and the second video includes: The number of users corresponding to the first user set is replaced with the product of the number of users corresponding to the fifth user set and the first correction factor; the number of users corresponding to the second user set is replaced with the product of the number of users corresponding to the sixth user set and the second correction factor; and the number of users corresponding to the first intersection is replaced with the product of the number of users corresponding to the third intersection and the third correction factor. These are then input into the third user overlap calculation formula, as shown below: In the above formula, This represents the number of users corresponding to the second intersection between the third and fourth user sets. This represents the number of people corresponding to the third user set. Indicates the number of users corresponding to the fourth user set. Indicates the first correction factor, Indicates the second correction factor, Indicates the third correction factor, Indicates the number of people corresponding to the fifth user set. Indicates the number of users corresponding to the sixth user set. This represents the number of people corresponding to the third intersection; The calculation result output by the third user overlap calculation formula is obtained, and the calculation result is determined as the video similarity.

7. A video similarity determination device, characterized in that, include: The acquisition module is used to acquire the first video set corresponding to the first channel and the second video set corresponding to the second channel within a preset time period; The determination module is used to determine, for any first video in the first video set and any second video in the second video set, a first user overlap degree between the first video and the second video, and a second user overlap degree under the influence of the number of channel users; The determining module is further configured to determine a third user overlap degree, after removing the influence of the number of channel users, based on the first user overlap degree and the second user overlap degree; The determining module is further configured to determine a time correction factor between the first video and the second video affected by the online time, and use the time correction factor to process the overlap of the third user to obtain the video similarity between the first video and the second video. The determining module is further configured to determine the first user set corresponding to the first channel and the second user set corresponding to the second channel, and to determine the third user set corresponding to the first video and the fourth user set corresponding to the second video within the preset time period; The determining module is further configured to input the first user overlap degree and the second user overlap degree into the third user overlap degree calculation formula to obtain the third user overlap degree; wherein, the third user overlap degree calculation formula includes: In the above formula, Indicates the degree of overlap among third-party users. Indicates the degree of overlap between the second and third users. Indicates the degree of user overlap. This represents the number of users corresponding to the first intersection between the first user set and the second user set. This represents the number of people corresponding to the third user set. This represents the number of people corresponding to the fourth user set. This represents the number of people corresponding to the first user set. This represents the number of people corresponding to the second user set. This represents the number of people corresponding to the second intersection between the third user set and the fourth user set.

8. An electronic device, characterized in that, include: A processor and a memory, the processor being configured to execute a video similarity determination program stored in the memory to implement the video similarity determination method according to any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium stores one or more programs, which can be executed by one or more processors to implement the video similarity determination method according to any one of claims 1 to 6.

Images