Video advertisement putting method and system based on fragmentation time

Abstract

The invention provides a video advertisement putting method and system based on fragmented time, and relates to the technical field of data processing, and the method comprises the following steps: obtaining a user history browsing video, and extracting a time feature and a type feature; associating the browsing features with the type features to obtain a time-type feature association curve; generating a predicted advertisement putting table; according to the degree of the time-type feature association curve matched with the video currently browsed by the user, and according to the calculated video end time and the user browsing end time, screening the predicted advertisement putting table; and randomly putting an advertisement from the predicted advertisement putting table. According to the method, the time features and the type features of the videos browsed by the user historically are obtained, the time-type feature correlation curve is obtained, the video browsed by the current user is compared with the correlation curve, and the fragmented time difference is utilized, so that the put advertisement is corrected, and the proper advertisement is accurately put after the current video is played, and the user experience is improved. And the video browsing experience of users is ensured.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for delivering video advertisements based on fragmented time. Background Art

[0002] Short videos are short videos, which are a way of disseminating Internet content. They are generally videos of less than 5 minutes in length that are disseminated on new Internet media. With the popularization of mobile terminals and the acceleration of the Internet, short, flat and high-traffic content has gradually gained the favor of major platforms, fans and capital.

[0003] The rise of short videos has made people's video browsing time more fragmented, and the time for receiving information has also become more scattered and brief. In related technologies, a series of behavioral data of users on short video platforms can represent the user's preference and attention to certain keywords. Therefore, by analyzing the user's attention preferences based on these behavioral data, we can dig out the keywords that the user may want to focus on, so as to facilitate subsequent accurate advertising push.

[0004] However, short videos themselves have the characteristics of short playback time and fragmented user browsing time. If irrelevant advertisements are directly inserted into short videos, it will greatly affect the user's short video browsing experience. Therefore, it is advisable to place advertisements before and after the short video is played. In addition, users' browsing types vary greatly and browsing time is uncertain, which still makes it extremely difficult to place video advertisements in fragmented time.

[0005] Therefore, a method and system for delivering video advertisements based on fragmented time is desired, which can accurately deliver advertisements during fragmented video browsing without affecting the user's video browsing experience. Summary of the invention

[0006] In order to solve the above problems, the embodiments of the present application provide a method and system for video advertising delivery based on fragmented time, which obtains the time characteristics and type characteristics of the user's historically browsed videos, obtains a time-type feature association curve, compares the current user's browsed videos with the association curve, and uses the fragmented time difference to correct the delivered advertisements, so that appropriate advertisements can be accurately delivered after the current video is played, thereby ensuring the user's video browsing experience and ensuring that the delivered advertisements are in line with the user's browsing patterns and preferences.

[0007] In a first aspect, an embodiment of the present application provides a method for delivering video advertisements based on fragmented time, the method comprising: S100: Obtain the user's historical video browsing time and video browsing type, and extract time features and type features; S200: Associating the time feature with the type feature to obtain a time-type feature association curve; S300: Generate an estimated advertisement delivery table according to the type characteristics and time characteristics; S400: Determine whether the video currently browsed by the user matches the time-type feature association curve, if yes, execute step S500; otherwise, directly execute step S600; S500: Calculate the video end time and the user browsing end time based on the time-type feature association curve and the currently browsed video, and further filter the expected advertisement delivery table based on the time difference; S600: Randomly placing an advertisement from the expected advertisement placement table; When executing step S100, it specifically includes: S110: Obtain a video that is being played by the user end and whose playing time is not less than a predetermined time value, and obtain the time when the playing time reaches the predetermined time value as the video browsing time; S120: acquiring, according to the file data of the video being played by the user end, video style information, video source information and video evaluation information of the video being played by the user end as a browsing video type; S130: Recording the video browsing time and the video browsing types for no less than a predetermined number of days, and extracting time features and type features; When executing step S200, it specifically includes: S210: recording at least one time feature and at least one type feature extracted in step S100; S220: selecting at least three type features with the highest correspondence to the type of videos browsed by the user at each time feature; S230: selecting at least three time features with the highest correspondence to the time when the user browses the video for each type feature; S240: Calculate the correlation degree between each time feature and each type feature, draw the time-type feature correlation curve in the rectangular coordinate system, and obtain the coverage range of the time-type feature correlation curve; when executing step S240, multiple correlation curves can be obtained, and these correlation curves form at least one range interval on the coordinate system, forming a time-type feature correlation curve coverage range area, which represents the user's habit of browsing video time and browsing video type.

[0008] As one of the preferred embodiments of the present invention, when executing step S300, it specifically includes: S310: Obtaining type features and the type of video currently browsed by the user, and extracting an advertisement delivery library; S320: Selecting an advertisement suitable for the time from the advertisement delivery library according to the time feature and the current video browsing time of the user, and generating a table of estimated delivery advertisements.

[0009] As one of the preferred embodiments of the present invention, when executing step S400, it specifically includes: S410: Obtain the time and type of the video currently browsed by the user, and mark the point corresponding to the time and type of the currently browsed video on a rectangular coordinate system; S420: Determine whether the point is located in the coverage of the time-type feature association curve. If so, it matches and executes step S500; otherwise, it does not match and directly executes step S600.

[0010] As one of the preferred embodiments of the present invention, when executing step S500, it specifically includes: S510: Obtain the time and type of the video currently browsed by the user, and mark the point corresponding to the time and type of the currently browsed video on a rectangular coordinate system; S520: Calculate the average distance between the point and the boundary of the coverage range of the time-type feature association curve to obtain the end time of the user browsing; S530: Calculate the end time of the video according to the total length of the video and the current browsing progress information; S540: Further filter the expected advertisement delivery table according to the time difference between the video end time and the user browsing end time.

[0011] As one of the preferred embodiments of the present invention, when executing step S540, specifically: If the time difference between the end time of the user's browsing and the end time of the video is not positive, the advertisement with the shortest advertisement time is selected as the estimated advertisement table; If the time difference between the video end time and the user browsing end time is positive, and the time difference is not greater than the longest single advertisement time, then select advertisements whose advertisement time is greater than the time difference as the estimated advertisement table; If the time difference between the video end time and the user browsing end time is positive, and the time difference is greater than the longest single advertisement time, the estimated advertisement delivery table is filtered according to the currently browsed video content.

[0012] In a second aspect, an embodiment of the present application provides a video advertisement delivery system based on fragmented time, the system comprising: Feature extraction module; Feature association module; Advertisement table generation module; Judgment module; Advertisement table screening module; Advertisement delivery module; The feature extraction module obtains the user's historical video browsing time and browsing video type, and extracts the time feature and type feature; the feature association module associates the browsing feature with the type feature to obtain the time-type feature association curve; the advertisement table generation module generates an estimated advertisement table based on the type feature and time feature; the judgment module determines whether the user's current browsing video matches the time-type feature association curve, and if so, the advertisement table screening module is enabled; otherwise, the advertisement delivery module is directly enabled; the advertisement table screening module calculates the video end time and the user browsing end time based on the time-type feature association curve and the current browsing video, and further filters the estimated advertisement table based on the time difference; the advertisement delivery module randomly delivers an advertisement from the estimated advertisement table.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method provided in any possible implementation manner of the first aspect is implemented.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method provided in any possible implementation manner of the first aspect is implemented.

[0015] The beneficial effects of the present invention are: The time characteristics and type characteristics of the user's historically browsed videos are obtained to obtain the time-type characteristic association curve. The current user's browsed videos are compared with the association curve, and the fragmented time difference is used to correct the advertising. This allows for accurate delivery of appropriate ads after the current video is finished playing, ensuring the user's video browsing experience and ensuring that the advertising is in line with the user's browsing patterns and preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of a method for delivering video advertisements based on fragmented time is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0019] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0020] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0021] Example 1: See Figure 1 , Figure 1 : is a flow chart of a method for delivering video advertisements based on fragmented time provided in an embodiment of the present application. In an embodiment of the present application, the method includes: S100: Obtain the user's historical video browsing time and video browsing type, and extract time features and type features; In the embodiment of the present application, when step S100 is executed, it specifically includes: S110: Obtain a video that is being played by the user end and whose playing time is not less than a predetermined time value, and obtain the time when the playing time reaches the predetermined time value as the video browsing time; S120: acquiring, according to the file data of the video being played by the user end, video style information, video source information and video evaluation information of the video being played by the user end as a browsing video type; When executing step S120, information tags of the played video are extracted, and the information tags include video style information tags, played video source information tags and played video evaluation information tags; S130: Record the video browsing time and video browsing type for no less than a predetermined number of days, and extract time features and type features.

[0022] Generally speaking, the time and type of videos browsed by users through the user terminal on different dates will be different. For example, anime was browsed at 12:04 on the first day, TV was browsed at 12:15 on the second day, and variety shows were browsed at 15:34 on the third day. However, in a longer date record, certain patterns can still be obtained. For example, between 12:00 and 12:30 (probably lunch time), there are multiple browsing of anime videos; for another example, the frequency of watching variety shows is relatively high and distributed between 18:00 and 20:00.

[0023] Therefore, it is necessary to extract time features and type features based on the user's video browsing records over a period of time.

[0024] S200: Associating the browsing feature with the type feature to obtain a time-type feature association curve; In the embodiment of the present application, when step S200 is executed, it specifically includes: S210: recording at least one time feature and at least one type feature extracted in step S100; S220: selecting at least three type features with the highest correspondence to the type of videos browsed by the user at each time feature; S230: selecting at least three time features with the highest correspondence to the time when the user browses the video for each type feature; S240: Calculate the correlation value between each time feature and each type feature, draw a time-type feature correlation curve in a rectangular coordinate system, and obtain the coverage range of the time-type feature correlation curve.

[0025] In the embodiment of the present application, when step S200 is actually executed, First, a time curve of users watching videos is established. In a rectangular coordinate system, the X-axis is time, and the Y-axis is whether the video is watched or not. When the video is watched, the Y-axis value is 1, and when the video is not watched, the Y-axis value is 0. At this time, the time curve of whether all users watch videos is a square wave curve. Multiple square wave curves of whether users watch videos in several days are obtained. The multiple square wave curves are accumulated and curve fitting is performed to form a standard curve of the user's video watching time. This is the time characteristic curve of the user watching the video, and the feature vector pointing to the time characteristic curve at each time point is a time feature recorded in step S210; Then, a Z axis is added to the rectangular coordinate system to form a three-dimensional rectangular coordinate system, where the Z axis represents the viewing video type. Each video type is assigned a value, and the z axis value of the viewing video is recorded at each point of the time characteristic curve (two-dimensional curve) to obtain the viewing video type point in the Z axis direction. The feature vector pointing to the viewing video type point on each point of the time characteristic curve (two-dimensional curve) is a type feature recorded in step S210; There may be multiple feature vectors pointing to the viewing video type point at each time feature curve point. When executing step S220, at least three type features (video type feature vectors) at each time feature (point of the time feature curve) are selected; Counting at least three type features at each time feature to obtain a viewing time value corresponding to each type feature, and selecting at least three most frequent time features when watching each video feature, which is step S230; According to at least three type features at a time feature in step S220 and at least three viewing time features corresponding to each type feature in step S230, the correlation degree value between each time feature and each type feature can be calculated, and the sum b of the type feature vector corresponding to each time feature is multiplied by the sum c of the time feature vector corresponding to each type feature to obtain the correlation degree value K between the corresponding time feature and the corresponding type feature, and the correlation degree values ​​of multiple time features and multiple type features are plotted in the three-dimensional rectangular coordinate system established in step S210 to obtain a time-type feature correlation curve, which is step S240.

[0026] It should be noted that when executing step S240, multiple association curves can be obtained, which form at least one range interval on a three-dimensional rectangular coordinate system, forming a time-type feature association curve coverage area, which represents the user's habit of browsing video time and browsing video types.

[0027] S300: Generate an estimated advertisement delivery table according to the type characteristics and time characteristics; In the embodiment of the present application, when step S300 is executed, it specifically includes: S310: Obtaining type features and the type of video currently browsed by the user, and extracting an advertisement delivery library; S320: Selecting an advertisement suitable for the time from the advertisement delivery library according to the time feature and the current video browsing time of the user, and generating a table of estimated delivery advertisements.

[0028] S400: Determine whether the video currently browsed by the user matches the time-type feature association curve, if yes, execute step S500; otherwise, directly execute step S600; In the embodiment of the present application, when step S400 is executed, it specifically includes: S410: Obtain the time and type of the video currently browsed by the user, and mark the point corresponding to the time and type of the currently browsed video on a rectangular coordinate system; S420: Determine whether the point is located in the coverage of the time-type feature association curve. If so, it matches and executes step S500; otherwise, it does not match and directly executes step S600.

[0029] S500: Calculate the video end time and the user browsing end time based on the time-type feature association curve and the currently browsed video, and further filter the expected advertisement delivery table based on the time difference; In the embodiment of the present application, when step S500 is executed, it specifically includes: S510: Obtain the time and type of the video currently browsed by the user, and mark the point corresponding to the time and type of the currently browsed video on a rectangular coordinate system; S520: Calculate the average distance between the point and the boundary of the coverage range of the time-type feature association curve to obtain the end time of the user browsing; S530: Calculate the end time of the video according to the total length of the video and the current browsing progress information; S540: Further filter the expected advertisement delivery table according to the time difference between the video end time and the user browsing end time.

[0030] In the embodiment of the present application, when step S540 is executed, specifically: If the time difference between the end time of the user's browsing and the end time of the video is not positive, the advertisement with the shortest advertisement time is selected as the estimated advertisement table; If the time difference between the video end time and the user browsing end time is positive, and the time difference is not greater than the longest single advertisement time, then select advertisements whose advertisement time is greater than the time difference as the estimated advertisement table; If the time difference between the video end time and the user browsing end time is positive, and the time difference is greater than the longest single advertisement time, the estimated advertisement delivery table is filtered according to the currently browsed video content.

[0031] S600: Randomly deliver an advertisement from the expected delivery advertisement table.

[0032] In an embodiment of the present application, after the current video is finished playing, randomly selected advertisements are delivered, which not only ensures the amount of advertisements delivered, but also achieves accurate advertisement delivery, which is suitable for the user's current time and attention type, and ensures the user's video browsing experience.

[0033] The present invention discloses a method for delivering video advertisements based on fragmented time, which obtains the time characteristics and type characteristics of the user's historically browsed videos, obtains a time-type characteristic association curve, compares the current user's browsed videos with the association curve, and utilizes the fragmented time difference to correct the delivered advertisements, so that after the current video is played, a suitable advertisement is accurately delivered, thereby ensuring the user's video browsing experience.

[0034] Embodiment 2: Based on Embodiment 1, the logic of the present invention is further explained in the embodiments of the present application: It can be known that the present invention inserts advertisements in short videos, and short videos themselves have the characteristics of short playback time and fragmented user browsing time. If irrelevant advertisements are directly inserted into short videos, it will greatly affect the user's short video browsing experience. Therefore, it is necessary to place advertisements before and after the short video is played. Moreover, the user's browsing types vary greatly and the browsing time is uncertain, which still makes it extremely difficult to place video advertisements in fragmented time. The present invention is designed to solve the above defects.

[0035] Therefore, in the present invention, the time characteristics and type characteristics of the user's historically browsed videos are obtained to obtain a time-type characteristic association curve, and the current user's browsed video is compared with the association curve, and the fragmented time difference is used to correct the placement of advertisements, so that after the current video is played, the appropriate advertisements are accurately placed to ensure the user's video browsing experience. It can be seen that the starting point of the present invention has two parts, namely: 1. According to the above contents, “short videos have the characteristics of short playback time and fragmented user browsing time” and “user browsing types vary greatly and browsing time is uncertain”, it can be known that the present invention is to calculate the browsing rules (browsing types and browsing time) of short videos. 2. According to the previous content that "directly inserting irrelevant advertisements into short videos will greatly affect the user's short video browsing experience", it can be known that the present invention is to place appropriate types of advertisements in short videos to avoid user disgust, thereby improving the user's short video browsing experience.

[0036] Based on the above: Steps S100 and S200 in the present invention are to obtain the time characteristics and type characteristics of the user's historical browsing videos, obtain the time-type characteristic association curve, calculate the user's historical browsing rules and preferences for short videos, and achieve the purpose of the above-mentioned point 1; The purpose of steps S300 to S600 in the present invention is to bring the current video information into the video browsing rules based on the user's historical short video browsing rules and preferences when the user is currently browsing short videos, and perform multiple advertisement screenings through rule matching, user browsing time, etc., to select the most suitable advertisement type and duration to avoid user disgust, thereby improving the user's short video browsing experience and achieving the purpose of the second point above.

[0037] Specifically: Fragmented time in the present invention has two meanings. The first is that the video browsed by the user is itself a short video with the essence of fragmented browsing; the second is that placing advertisements in short videos is also fragmented placement; in step S200 of the present invention, the obtained time-type feature association curve has multiple association curves, and these association curves form at least one range interval on the coordinate system, forming a time-type feature association curve coverage area, which represents the user's browsing video time and browsing video type habits. The set; in step S300, the expected advertising table is generated according to the type characteristics and time characteristics of the user's historical browsing of short videos, that is, the first step of screening has been performed according to the user's browsing habits, and advertisements that "cater to the user's taste" have been selected; in step S400, the user's current browsing video data is matched with the historical browsing rules, and then in step S500, the second step of advertisement screening is performed according to the difference between the end time of the current browsing video and the browsing end time under the historical browsing rules, and further "caters to the user's taste" advertisements are selected.

[0038] In summary, the present invention focuses on obtaining the user's historical browsing patterns and preferences from the user's historical browsing video data, and screening the advertisements of the currently browsed video based on these patterns and the user's browsing situation to ensure that the advertisements delivered are in line with the user's browsing patterns and preferences.

[0039] Embodiment 3: The embodiment of the present application provides a video advertisement delivery system based on fragmented time, the system comprising: Feature extraction module; Feature association module; Advertisement table generation module; Judgment module; Advertisement table screening module; Advertisement delivery module; The feature extraction module obtains the user's historical video browsing time and browsing video type, and extracts the time feature and type feature; the feature association module associates the browsing feature with the type feature to obtain the time-type feature association curve; the advertisement table generation module generates an estimated advertisement table based on the type feature and time feature; the judgment module determines whether the user's current browsing video matches the time-type feature association curve, and if so, the advertisement table screening module is enabled; otherwise, the advertisement delivery module is directly enabled; the advertisement table screening module calculates the video end time and the user browsing end time based on the time-type feature association curve and the current browsing video, and further filters the estimated advertisement table based on the time difference; the advertisement delivery module randomly delivers an advertisement from the estimated advertisement table.

[0040] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0041] It can be understood that the devices provided in the embodiments of the present invention are all applicable to the method described in Embodiment 1. The specific functions of each module can refer to the above method flow and will not be described in detail here.

[0042] Embodiment 4, an electronic device provided by the embodiment of the present invention is used to implement the method described in embodiment 1. The electronic device may include: at least one central processor, at least one network interface, a control interface, a memory, and at least one communication bus.

[0043] Among them, the communication bus is used to realize the connection, communication and information exchange between various components.

[0044] The network interface may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0045] Among them, the control interface is used to output control operations according to instructions.

[0046] The central processing unit may include one or more processing cores. The central processing unit uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data according to the method described in the first embodiment by running or executing instructions, programs, code sets or instruction sets stored in the memory, and calling data stored in the memory.

[0047] The memory may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory includes a non-transitory computer-readable storage medium. The memory may be used to store instructions, programs, codes, code sets or instruction sets. The memory may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), and methods for implementing the above-mentioned embodiment 1; the data storage area may store data involved in each of the above method embodiments, etc.

[0048] The present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method described in the first embodiment is implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0049] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0050] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0051] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0052] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional units in the various embodiments of the present invention 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. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units.

[0053] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including 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 method described in each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk, etc., various media that can store program codes.

[0054] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0055] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising 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, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device comprising the elements.

[0056] The above contents are further detailed descriptions of the present invention in combination with specific preferred implementation modes, and it cannot be determined that the specific embodiments of the present invention are limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for delivering video advertisements based on fragmented time, characterized in that: include: S100: Obtain the user's historical video browsing time and video browsing type, and extract time features and type features; S2 00: Associate the time feature with the type feature to obtain the time-type feature association curve; S300: Generate an estimated advertisement delivery table according to the type characteristics and time characteristics; S400: Determine whether the video currently browsed by the user matches the time-type feature association curve, if yes, execute step S500; otherwise, directly execute step S600; S500: Calculate the video end time and the user browsing end time based on the time-type feature association curve and the currently browsed video, and further filter the expected advertisement delivery table based on the time difference; S600: Randomly placing an advertisement from the expected advertisement placement table; When executing step S100, it specifically includes: S110: Obtain a video that is being played by the user end and whose playing time is not less than a predetermined time value, and obtain the time when the playing time reaches the predetermined time value as the video browsing time; S120: acquiring, according to the file data of the video being played by the user end, video style information, video source information and video evaluation information of the video being played by the user end as a browsing video type; S130: Recording the video browsing time and the video browsing types for no less than a predetermined number of days, and extracting time features and type features; When executing step S200, it specifically includes: S210: recording at least one time feature and at least one type feature extracted in step S100; S220: selecting at least three type features with the highest correspondence to the type of videos browsed by the user at each time feature; S230: selecting at least three time features with the highest correspondence to the time when the user browses the video for each type feature; S240: Calculate the correlation degree between each time feature and each type feature, draw the time-type feature correlation curve in the rectangular coordinate system, and obtain the coverage range of the time-type feature correlation curve; when executing step S240, multiple correlation curves can be obtained, and these correlation curves form at least one range interval on the coordinate system, forming a time-type feature correlation curve coverage range area, which represents the user's habit of browsing video time and browsing video type.

2. The method for delivering video advertisements based on fragmented time according to claim 1, characterized in that: When executing step S300, it specifically includes: S310: Obtaining type features and the type of video currently browsed by the user, and extracting an advertisement delivery library; S320: Selecting an advertisement suitable for the time from the advertisement delivery library according to the time feature and the current video browsing time of the user, and generating a table of estimated delivery advertisements.

3. The method for delivering video advertisements based on fragmented time according to claim 1, characterized in that: When executing step S400, it specifically includes: S410: Obtain the time and type of the video currently browsed by the user, and mark the point corresponding to the time and type of the currently browsed video on a rectangular coordinate system; S420: Determine whether the point is located in the coverage of the time-type feature association curve. If so, it matches and executes step S500; otherwise, it does not match and directly executes step S600.

4. The method for delivering video advertisements based on fragmented time according to claim 1, characterized in that: When executing step S500, it specifically includes: S510: Obtain the time and type of the video currently browsed by the user, and mark the point corresponding to the time and type of the currently browsed video on a rectangular coordinate system; S520: Calculate the average distance between the point and the boundary of the coverage range of the time-type feature association curve to obtain the end time of the user browsing; S530: Calculate the end time of the video according to the total length of the video and the current browsing progress information; S540: Further filter the expected advertisement delivery table according to the time difference between the video end time and the user browsing end time.

5. The method for delivering video advertisements based on fragmented time according to claim 4, characterized in that: When executing step S540, specifically: If the time difference between the end time of the user's browsing and the end time of the video is not positive, the advertisement with the shortest advertisement time is selected as the estimated advertisement table; If the time difference between the video end time and the user browsing end time is positive, and the time difference is not greater than the longest single advertisement time, then select the advertisements whose advertisement time is greater than the time difference as the estimated advertisement table; If the time difference between the video end time and the user browsing end time is positive, and the time difference is greater than the longest single advertisement time, the estimated advertisement delivery table is filtered according to the currently browsed video content.

6. A video advertisement delivery system based on fragmented time, characterized in that: include: Feature extraction module; Feature association module; Advertisement table generation module; Judgment module; Advertisement table screening module; Advertisement delivery module; The feature extraction module obtains the user's historical video browsing time and video browsing type, and extracts time features and type features; The feature association module associates the browsing feature with the type feature to obtain a time-type feature association curve; the advertisement table generation module generates an estimated advertisement table based on the type feature and time feature; the judgment module determines whether the user's current browsing video matches the time-type feature association curve, and if so, the advertisement table screening module is enabled; otherwise, the advertisement delivery module is directly enabled; the advertisement table screening module calculates the video end time and the user browsing end time based on the time-type feature association curve and the current browsing video, and further filters the estimated advertisement table based on the time difference; the advertisement delivery module randomly delivers an advertisement from the estimated advertisement table.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images