Method and apparatus for video recommendation, refrigerator with a display screen

Abstract

This application relates to the field of information processing technology, and discloses a method for video recommendation. The method includes: obtaining a reference image; identifying a face area in the reference image to obtain a face image; obtaining person relationship information based on the face image; and determining a recommended video based on the person relationship information. By identifying a face image from a reference image, obtaining person relationship information based on the face image, and being able to more personalized determine a recommended video suitable for viewing in a multi-person scenario according to different person relationships, the experience of multiple users watching videos simultaneously is improved. This application also discloses a device for video recommendation and a refrigerator with a display screen.

Description

Technical Field

[0001] This application relates to the field of information processing technologies, and for example, relates to a method, a device, and a refrigerator with a display screen for video recommendation. Background Art

[0002] With the development of technologies, more and more refrigerators are equipped with display screens and support video playback. When people are doing housework in the kitchen, they can watch videos such as movies and cooking tutorials from the Internet through such smart refrigerators with screens. And there are often multiple family members in the kitchen, and each member has their own interested videos, and situations where opinions differ often occur. In order to enable multiple users in front of the current refrigerator to have a better experience when watching videos together, how to determine videos suitable for multiple users to watch together in a multi-person scenario is a problem to be solved.

[0003] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related technologies:

[0004] Existing technologies are difficult to determine suitable recommended videos in a multi-person scenario. Summary of the Invention

[0005] To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. The summary is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments, but rather serves as a preface to the subsequent detailed description.

[0006] Embodiments of the present disclosure provide a method, a device, and a refrigerator with a display screen for video recommendation to solve the technical problem of how to determine videos suitable for watching in a multi-person scenario.

[0007] In some embodiments, the method includes:

[0008] Obtain a reference image;

[0009] Identify the face region in the reference image to obtain a face image;

[0010] Obtain person relationship information based on the face image;

[0011] Determine a recommended video according to the person relationship information.

[0012] In some embodiments, the device includes: a processor and a memory storing program instructions, and the processor is configured to execute the above method for video recommendation when executing the program instructions.

[0013] In some embodiments, the refrigerator with a display screen includes: the above device for video recommendation.

[0014] The method, apparatus, and refrigerator with a display screen provided by the embodiments of the present disclosure can achieve the following technical effects: By recognizing a face image through a reference image, obtaining person relationship information based on the face image, and being able to more personalized determine recommended videos suitable for viewing in a multi-person scenario according to different person relationships, thereby enhancing the experience of multiple users watching videos simultaneously.

[0015] The above general description and the following description are only exemplary and explanatory, and are not used to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] One or more embodiments are exemplarily illustrated by corresponding drawings. These exemplary illustrations and the drawings do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation, and among them:

[0017] Figure 1 is a schematic diagram of a method for video recommendation provided by an embodiment of the present disclosure;

[0018] Figure 2 is a schematic diagram of an apparatus for video recommendation provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] In order to be able to more comprehensively understand the features and technical content of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the drawings. The attached drawings are only for reference and explanation, and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of explanation, sufficient understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be shown in a simplified manner.

[0020] In the embodiments of the present disclosure, terms such as "first" and "second" in the specification and claims of the embodiments of the present disclosure and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0021] Unless otherwise specified, the term "plurality" means two or more.

[0022] In the embodiments of the present disclosure, the character " / " means that the front and rear objects are in an "or" relationship. For example, A / B means: A or B.

[0023] The term "and / or" describes the relationship between objects and indicates that there can be three relationships. For example, A and / or B means: A or B, or, A and B, these three relationships.

[0024] Combine Figure 1 As shown, an embodiment of the present disclosure provides a method for video recommendation, including:

[0025] Step S101, obtain a reference image;

[0026] Step S102, identify the face region in the reference image to obtain a face image;

[0027] Step S103, obtain person relationship information according to the face image;

[0028] Step S104, determine a recommended video according to the person relationship information.

[0029] By using the method for video recommendation provided by the embodiment of the present disclosure, a face image is identified through a reference image, person relationship information is obtained according to the face image, and a recommended video suitable for multiple users to watch can be determined more personalized according to different person relationships, thereby improving the experience of multiple users watching videos simultaneously.

[0030] Optionally, obtaining person relationship information according to the face image includes: obtaining age information corresponding to the face image; obtaining person relationship information according to the number of face images and the corresponding age information.

[0031] Optionally, obtaining age information corresponding to the face image includes: extracting features from the face image to obtain face feature parameters; obtaining age information according to the face feature parameters. Optionally, preprocess the face image; perform feature extraction on the preprocessed face image based on the local Gabor binary pattern operator to obtain face feature parameters. Estimate the age of the face feature parameters according to the support vector regression function to obtain the age information corresponding to each face region in the reference image.

[0032] Optionally, obtaining person relationship information according to the number of face images and the corresponding age information includes: matching the person relationship information corresponding to the number of face images and the age information from a pre-stored relationship database.

[0033] In some embodiments, the pre-stored relational database stores the relationship information corresponding to the number of face images and age information. For example, in some embodiments, if the number of face images is 2 and the age information satisfies that one person is between 3 and 12 years old and the other person is between 30 and 40 years old, the corresponding relationship information is the parent-child relationship; if the number of face images is 2 and the age information satisfies that both are between 30 and 40 years old or between 40 and 50 years old, the corresponding relationship information is the friend relationship.

[0034] Optionally, determining a recommended video according to the relationship information includes: determining a recommended video type according to the relationship information; determining a set of recommended videos according to the recommended video type; selecting a second reference video from the set of recommended videos, and using the videos not selected in the set of recommended videos as alternative videos; determining a recommended video according to the similarity between the alternative videos and the second reference video.

[0035] Optionally, determining a recommended video type according to the relationship information includes: matching a video viewing record corresponding to the relationship information from the pre-stored historical record database; determining a first reference video according to the video viewing record; determining a recommended video type according to the first reference video.

[0036] Optionally, the video viewing record includes: the historical video information of the last viewing; or, the historical video information with the viewing duration reaching a set threshold in the most recent time; or, the historical video information with the most viewing times. Correspondingly, determining the video corresponding to the historical video information of the last viewing as the first reference video; or, determining the video corresponding to the historical video information with the viewing duration reaching a set threshold in the most recent time as the first reference video; or, determining the video corresponding to the historical video information with the most viewing times as the first reference video.

[0037] Optionally, determining a recommended video type according to the first reference video includes: obtaining the lift of the alternative type and the type of the first reference video; determining a recommended video type according to the lift; the lift is the probability of containing the alternative type under the condition of containing the type of the first reference video within a set time period; using the alternative type corresponding to the lift that meets the set conditions as the recommended video type.

[0038] Optionally, select t set time periods, and detect the video types viewed within each set time period, and the time lengths of each time period are the same. Calculate to obtain the probability Lift(Dy→B of containing the a-th alternative type under the condition of containing the type of the first reference video within the set time period a ) that is, the lift of the a-th alternative type and the type of the first reference video, Support(Dy∩B a) is the ratio of the number of set time periods containing the a-th alternative type under the condition of containing the type of the first reference video to the number of detections. Support(Dy) is the ratio of the number of set time periods containing the type of the first reference video to the number of detections. Support(B a ) is the ratio of the number of set time periods containing the a-th alternative type to the number of detections. Dy is the type of the first reference video, and B a is the a-th alternative type. a is a positive integer, θ is a set error avoidance value, and 0 < θ < 0.01. The alternative type corresponding to the maximum lift is taken as the recommended video type. For example, 8 time periods are selected, each time period is 4 hours, and the video type detection example table shown in Table 1 is obtained. If the type of the first reference video is an action video, the first alternative type B 1 is a comedy video, the second alternative type B 2 is a variety show, the third alternative type B 3 is an animation, the fourth alternative type B 4 is a documentary, and θ is 0.001. Then Support(Dy) is 0.5, Support(B 1 ) is 0.75, Support(B 2 ) is 0.625, Support(B 3 ) is 0.375, Support(B 4 ) is 0.5, Support(Dy∩B 1 ) is 0.375, Support(Dy∩B 2 ) is 0.375, Support(Dy∩B 3 ) is 0.125, Support(Dy∩B 4 ) is 0. Then Lift(Dy→B 1 ) is 375 / 376, Lift(Dy→B 2 ) is 750 / 627, Lift(Dy→B 3 ) is 250 / 377, Lift(Dy→B 4 ) is 0. Then the second alternative type, that is, the variety show, is taken as the recommended video type. The above solution is convenient for finding the relevance between videos, convenient for mining users' viewing behaviors, so as to better recommend videos for users.

[0039] Time period 1 Action videos, comedy videos, variety shows, cartoons Time period 2 Action videos, comedy videos, variety shows Time period 3 Action videos, comedy videos Time period 4 Action videos, variety shows Time period 5 Documentaries, comedy videos, variety shows, cartoons Time period 6 Documentaries, comedy videos, variety shows Time period 7 Documentaries, comedy videos Time period 8 Documentaries, cartoons

[0040] Table 1 Video type detection example table

[0041] In some embodiments, videos corresponding to the recommended video types are placed in the recommended video set. If there are videos that have been watched in the recommended video set, then the video with the longest viewing time in the recommended video set is selected as the second reference video, and the other videos not selected in the recommended video set are used as alternative videos; if there are no videos that have been watched in the recommended video set, then a video is randomly selected from the recommended video set as the second reference video, and the other videos not selected in the recommended video set are used as alternative videos.

[0042] Optionally, obtain the similarity between each alternative video and the second reference video; select the alternative video corresponding to the maximum similarity as the recommended video; or, select the alternative video corresponding to the minimum similarity as the recommended video; or, select the alternative videos corresponding to the similarity within a set range as the recommended videos. Optionally, selecting the alternative videos corresponding to the similarity within a set range as the recommended videos includes: using the alternative videos corresponding to the similarity ranked within a set interval as the recommended videos. Further, the obtained recommended videos are recommended to the user. Determining the recommended videos based on the second reference video makes the recommended videos more refined and targeted.

[0043] Optionally, obtaining the similarity between each alternative video and the second reference video includes:

[0044] Extract the first set of introduction text keywords from the introduction text corresponding to each alternative video, and extract the second set of introduction text keywords from the introduction text corresponding to the second reference video; obtain the similarity between each alternative video and the second reference video based on the first set of introduction text keywords and the second set of introduction text keywords. Optionally, obtain the union of the first set of introduction text keywords and the second set of introduction text keywords, calculate the keyword frequencies of the first set of introduction text keywords and the second set of introduction text keywords respectively, and perform term frequency vectorization processing on the first set of introduction text keywords and the second set of introduction text keywords. Calculate to obtain the similarity sim i , c i,j is the j-th term frequency vector in the first set of introduction text keywords corresponding to the i-th alternative video, and ce j is the j-th term frequency vector in the second set of introduction text keywords corresponding to the second reference video, where i, j, and n are all positive integers, and 1 ≤ j ≤ n.

[0045] Optionally, obtaining the similarity between each alternative video and the second reference video includes:

[0046] Extract the first set of introduction text keywords from the introduction texts corresponding to each alternative video, and extract the second set of introduction text keywords from the introduction text corresponding to the second reference video; obtain the similarity between each alternative video and the second reference video based on the first set of introduction text keywords and the second set of introduction text keywords. Optionally, obtain the union of the first set of introduction text keywords and the second set of introduction text keywords, calculate the keyword frequencies of the first set of introduction text keywords and the second set of introduction text keywords respectively, and perform term frequency vectorization processing on the first set of introduction text keywords and the second set of introduction text keywords. Extract the first set of review text keywords from the review texts corresponding to each alternative video, extract the second set of review text keywords from the review text corresponding to the second reference video, obtain the union of the first set of review text keywords and the second set of review text keywords, calculate the keyword frequencies of the first set of review text keywords and the second set of review text keywords respectively, and perform term frequency vectorization processing on the first set of review text keywords and the second set of review text keywords. Calculate

[0047]

[0048] Obtain the similarity sim between the i-th alternative video and the second reference video i , c i,j is the j-th term frequency vector in the first set of introduction text keywords corresponding to the i-th alternative video, ce j is the j-th term frequency vector in the second set of introduction text keywords corresponding to the second reference video, p i,j is the j-th term frequency vector in the first set of review text keywords corresponding to the i-th alternative video, pe j is the j-th term frequency vector in the second set of review text keywords corresponding to the second reference video, where i, j, and n are all positive integers, and 1 ≤ j ≤ n. The above solution not only considers the similarity degree of video introductions but also reflects the similarity degree of comments on the video, integrating the similarity degree of video introductions and the similarity degree of video comments. The above integration method makes the similarity degree with the higher similarity in both the similarity degree of video introductions and the similarity degree of video comments have a greater proportion in the similarity sim i , which better balances the two recommendation influencing factors of user comment similarity and content similarity, making the recommended videos more in line with the viewing interests of users or more likely to bring a sense of freshness to users, thereby improving the experience of users when obtaining video recommendations.

[0049] Optionally, after determining the recommended video, play the recommended video on a refrigerator with a display screen. In this way, the videos played on the refrigerator are suitable for viewing in a multi-person scenario, enhancing the experience of multiple users watching videos simultaneously.

[0050] Combined with Figure 2As shown in the figure, an embodiment of the present disclosure provides a device for video recommendation, which includes a processor 100 and a memory 101 storing program instructions. Optionally, the device may further include a communication interface 102 and a bus 103. Among them, the processor 100, the communication interface 102, and the memory 101 can complete mutual communication through the bus 103. The communication interface 102 can be used for information transmission. The processor 100 can call the program instructions in the memory 101 to execute the method for video recommendation in the above embodiment.

[0051] In addition, when the program instructions in the above-mentioned memory 101 are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0052] The memory 101, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 100 executes functional applications and data processing by running the program instructions / modules stored in the memory 101, that is, implements the method for video recommendation in the above embodiment.

[0053] The memory 101 may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the terminal device, etc. In addition, the memory 101 may include a high-speed random access memory and may also include a non-volatile memory.

[0054] The device for video recommendation provided by the embodiment of the present disclosure identifies a face image by referring to an image, obtains person relationship information based on the age information corresponding to the face image and the number of face images, and can more personalized determine recommended videos suitable for viewing in a multi-person scenario according to different person relationships, thereby improving the experience of multiple users watching videos simultaneously.

[0055] An embodiment of the present disclosure provides a refrigerator with a display screen, which includes the above-mentioned device for video recommendation.

[0056] The refrigerator with a display screen provided by the embodiment of the present disclosure identifies a face image by referring to an image, obtains person relationship information based on the age information corresponding to the face image and the number of face images, and can more personalized determine recommended videos suitable for viewing in a multi-person scenario according to different person relationships, thereby improving the experience of multiple users watching videos simultaneously.

[0057] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are configured to execute the above-mentioned method for video recommendation.

[0058] An embodiment of the present disclosure provides a computer program product, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is caused to execute the above-mentioned method for video recommendation.

[0059] The above-mentioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0060] The technical solution of the embodiment of the present disclosure may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The foregoing storage medium may be a non-transient storage medium, including: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or may also be a transient storage medium.

[0061] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. Embodiments merely represent possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing embodiments and do not limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations of one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups of these. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, or apparatus comprising the element. Herein, each embodiment may focus on the differences from other embodiments, and the same or similar parts among the embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts may refer to the description of the method parts.

[0062] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner may depend on the specific application and design constraints of the technical solution. The skilled person may use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The skilled person can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0063] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.

[0064] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the block can occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks can also occur in a different order than disclosed in the description. Sometimes, there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. Each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for video recommendation, characterized in that, it includes: Obtain a reference image; Identify the face region in the reference image to obtain a face image; Obtain person relationship information according to the face image; Determine recommended videos according to the person relationship information; Determine recommended videos according to the person relationship information, including: matching video viewing records corresponding to the person relationship information from a pre-stored historical record database; determining a first reference video according to the video viewing records; obtaining the promotion degree between the alternative type and the type of the first reference video; determining the recommended video type according to the promotion degree; the promotion degree is the probability of containing the alternative type under the condition of containing the type of the first reference video within a set time period; taking the alternative type corresponding to the promotion degree that meets the set conditions as the recommended video type; determining a recommended video set according to the recommended video type; selecting a second reference video from the recommended video set, and taking the videos not selected in the recommended video set as alternative videos; determining the recommended video according to the similarity between the alternative videos and the second reference video.

2. The method according to claim 1, characterized in that, obtaining person relationship information according to the face image includes: Obtain age information corresponding to the face image; Obtain person relationship information according to the number of the face images and the corresponding age information.

3. The method according to claim 2, characterized in that, obtaining age information corresponding to the face image includes: Extract face feature parameters from the face image; Obtain age information according to the face feature parameters.

4. The method according to claim 2, characterized in that, obtaining person relationship information according to the number of the face images and the corresponding age information includes: Match person relationship information corresponding to the number of the face images and the age information from a pre-stored relationship database.

5. The method according to claim 1, characterized in that, the video viewing records include: Historical video information of the last viewing; or, Historical video information with the viewing duration reaching a set threshold in the most recent viewing; or, Historical video information with the most viewing times.

6. A device for video recommendation, including a processor and a memory storing program instructions, characterized in that, the processor is configured to execute the method for video recommendation according to any one of claims 1 to 5 when executing the program instructions.

7. A refrigerator with a display screen, characterized in that, it includes the device for video recommendation according to claim 6.

Images