阅读说明：本技术 用于视频推荐的方法及装置、带显示屏的冰箱 (Method and device for video recommendation and refrigerator with display screen ) 是由 张玉波 吴剑 周枢 费兆军 冯志群 易作为 江松 黄熠 于 2020-06-03 设计创作，主要内容包括：本申请涉及信息处理技术领域,公开一种用于视频推荐的方法。该方法包括：获取参考图像；识别所述参考图像中的人脸区域得到人脸图像；根据所述人脸图像获得人物关系信息；根据所述人物关系信息确定推荐视频。该方法通过参考图像识别出人脸图像,根据人脸图像获得人物关系信息,根据不同的人物关系能够更加个性化的确定出适合多人场景下观看的推荐视频,从而提升多个用户同时观看视频的体验。本申请还公开一种用于视频推荐的装置及带显示屏的冰箱。(The application relates to the technical field of information processing and discloses a method for recommending videos. The method comprises the following steps: acquiring a reference image; identifying a face region in the reference image to obtain a face image; acquiring character relation information according to the face image; and determining a recommended video according to the person relationship information. According to the method, the face image is identified through the reference image, the character relation information is obtained according to the face image, and the recommended video suitable for being watched under a multi-person scene can be more personalized and determined according to different character relations, so that the experience of watching videos by multiple users at the same time is improved. The application also discloses a device for video recommendation and a refrigerator with a display screen.)

1. A method for video recommendation, comprising:

acquiring a reference image;

identifying a face region in the reference image to obtain a face image;

acquiring character relation information according to the face image;

and determining a recommended video according to the person relationship information.

2. The method of claim 1, wherein obtaining the relationship information of the person from the face image comprises:

acquiring age information corresponding to the face image;

and obtaining the character relation information according to the number of the face images and the corresponding age information.

3. The method of claim 2, wherein obtaining age information corresponding to the face image comprises:

extracting the features of the face image to obtain face feature parameters;

and acquiring age information according to the face characteristic parameters.

4. The method of claim 2, wherein obtaining the relationship information of the people according to the number of the face images and the corresponding age information comprises:

and matching the figure relation information corresponding to the number of the face images and the age information from a pre-stored relation database.

5. The method of claim 1, wherein determining a recommended video according to the personal relationship information comprises:

determining a recommended video type according to the character relation information;

determining a recommended video set according to the recommended video type;

selecting a second reference video from the recommended video set, wherein the video which is not selected from the recommended video set is used as an alternative video;

and determining a recommended video according to the similarity between the alternative video and the second reference video.

6. The method of claim 5, wherein determining the recommended video type according to the personal relationship information comprises:

matching a video watching record corresponding to the character relation information from a pre-stored historical record database;

determining a first reference video from the video viewing record;

and determining a recommended video type according to the first reference video.

7. The method of claim 6, wherein the video viewing record comprises:

historical video information of the last time of watching; or the like, or, alternatively,

historical video information with the last watching time length reaching a set threshold value; or the like, or, alternatively,

historical video information with the most frequent views.

8. The method of claim 6, wherein determining a recommended video type from the first reference video comprises:

obtaining the promotion degree of the alternative type and the type of the first reference video;

determining a recommended video type according to the promotion degree;

the promotion degree is the probability that the alternative types are contained under the condition that the type of the first reference video is contained in the set time period;

and taking the alternative type corresponding to the promotion degree meeting the set condition as the recommended video type.

9. An apparatus for video recommendation comprising a processor and a memory storing program instructions, characterized in that the processor is configured to perform the method for video recommendation according to any one of claims 1 to 8 when executing the program instructions.

10. A refrigerator with a display screen, characterized in that it comprises a device for video recommendation according to claim 9.

Technical Field

The application relates to the technical field of information processing, for example, to a method and a device for video recommendation and a refrigerator with a display screen.

Background

With the development of the technology, more and more refrigerators are provided with display screens and can support video playing, people can watch videos such as movies and cooking art teaching from the internet through the intelligent refrigerator with the screen when doing housework in a kitchen, a plurality of family members often exist in the kitchen, each member has a video which is interesting to the user, and the situation of improper opinions often occurs. In order to enable a plurality of users in front of the refrigerator to have better experience when watching videos together, how to determine videos suitable for the plurality of users to watch together in a multi-user scene is a problem to be solved.

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

the existing technology is difficult to determine a proper recommended video in a multi-person scene.

Disclosure of Invention

The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview nor is intended to identify key/critical elements or to delineate the scope of such embodiments but rather as a prelude to the more detailed description that is presented later.

The embodiment of the disclosure provides a method and a device for video recommendation and a refrigerator with a display screen, so as to solve the technical problem of how to determine videos suitable for being watched under a multi-person scene.

In some embodiments, the method comprises:

acquiring a reference image;

identifying a face region in the reference image to obtain a face image;

acquiring character relation information according to the face image;

and determining a recommended video according to the person relationship information.

In some embodiments, the apparatus comprises: comprising a processor and a memory storing program instructions, the processor being configured to, upon execution of the program instructions, perform the method for video recommendation described above.

In some embodiments, the refrigerator with a display screen includes: the device for video recommendation is described above.

The method and the device for video recommendation and the refrigerator with the display screen provided by the embodiment of the disclosure can realize the following technical effects: the face image is identified through the reference image, the character relation information is obtained according to the face image, and the recommended video suitable for being watched under a multi-person scene can be more personalized and determined according to different character relations, so that the experience of watching videos by multiple users at the same time is improved.

The foregoing general description and the following description are exemplary and explanatory only and are not restrictive of the application.

Drawings

One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the accompanying drawings and not in limitation thereof, in which elements having the same reference numeral designations are shown as like elements and not in limitation thereof, and wherein:

FIG. 1 is a schematic diagram of a method for video recommendation provided by an embodiment of the present disclosure;

fig. 2 is a schematic diagram of an apparatus for video recommendation provided by an embodiment of the present disclosure.

Detailed Description

So that the manner in which the features and elements of the disclosed embodiments can be understood in detail, a more particular description of the disclosed embodiments, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. In the following description of the technology, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may be practiced without these details. In other instances, well-known structures and devices may be shown in simplified form in order to simplify the drawing.

The terms "first," "second," and the like in the description and in the claims, and the above-described drawings of embodiments of the present disclosure, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the present disclosure described herein may be made. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions.

The term "plurality" means two or more unless otherwise specified.

In the embodiment of the present disclosure, the character "/" indicates that the preceding and following objects are in an or relationship. For example, A/B represents: a or B.

The term "and/or" is an associative relationship that describes objects, meaning that three relationships may exist. For example, a and/or B, represents: a or B, or A and B.

As shown in fig. 1, an embodiment of the present disclosure provides a method for video recommendation, including:

step S101, acquiring a reference image;

s102, identifying a face area in a reference image to obtain a face image;

step S103, obtaining character relation information according to the face image;

and step S104, determining a recommended video according to the person relation information.

By adopting the method for video recommendation provided by the embodiment of the disclosure, the face image is identified through the reference image, the character relation information is obtained according to the face image, and the recommended video suitable for multiple users to watch can be more personalized and determined according to different character relations, so that the experience of watching videos by multiple users at the same time is improved.

Optionally, obtaining the person relationship information according to the face image includes: acquiring age information corresponding to the face image; and obtaining the character relation information according to the number of the face images and the corresponding age information.

Optionally, acquiring age information corresponding to the face image includes: extracting the features of the face image to obtain face feature parameters; and acquiring age information according to the face characteristic parameters. Optionally, preprocessing the face image; and performing feature extraction on the preprocessed face image based on a local Gabor binary pattern operator to obtain face feature parameters. And carrying out age estimation on the face characteristic parameters according to a support vector regression function so as to obtain age information corresponding to each face region in the reference image.

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

In some embodiments, the pre-stored relationship database pre-stores the relationship information between the number of the facial images and the age information, wherein if the number of the facial images is 2, 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 relationship information between the corresponding person and the parent is the relationship between the parent and the child; if the number of the face images is 2 and the age information is between 30 and 40 years old or between 40 and 50 years old, the corresponding person relationship information is the friendship.

Optionally, determining a recommended video according to the person relationship information includes: determining a recommended video type according to the character relation information; determining a recommended video set according to the recommended video type; selecting a second reference video from the recommended video set, wherein the video which is not selected from the recommended video set is used as an alternative video; and determining a recommended video according to the similarity between the alternative video and the second reference video.

Optionally, determining the recommended video type according to the person relationship information includes: matching a video watching record corresponding to the character relation information from a pre-stored historical record database; determining a first reference video according to the video viewing record; a recommended video type is determined from the first reference video.

Optionally, the video viewing record comprises: historical video information of the last time of watching; or, the last watching time length reaches the historical video information of the set threshold value; or historical video information with the most viewing times. Correspondingly, determining the video corresponding to the last watched historical video information as a first reference video; or determining the video corresponding to the historical video information with the latest watching time length reaching the set threshold value as a first reference video; or determining the video corresponding to the historical video information with the largest watching times as the first reference video.

Optionally, determining the recommended video type according to the first reference video includes: acquiring the promotion degree of the alternative type and the type of the first reference video; determining a recommended video type according to the promotion degree; the promotion degree is the probability that the alternative types are contained under the condition that the types of the first reference video are contained in the set time period; and taking the alternative type corresponding to the promotion degree meeting the set condition as the recommended video type.

Optionally, t set time periods are selected, the types of videos watched in the set time periods are detected, and the time lengths of the time periods are the same. ComputingObtaining the probability Lift (Dy → B) of containing the a-th candidate type under the condition of containing the type of the first reference video in the set time period_a) I.e. the promotion of the a-th candidate type with the type of the first reference video, Support (Dy &. B)_a) The set time interval number of the type containing the first reference video divided by the detection times, and support (Dy) the set time interval number of the type containing the first reference video divided by the detection timesRatio of times, Support (B)_a) The ratio of the number of the set time periods containing the a-th candidate type divided by the number of detection times, Dy being the type of the first reference video, B_aIs the a-th alternative type, a is a positive integer, theta is a set error avoidance value, 0<θ<0.01. And taking the alternative type corresponding to the maximum promotion degree as the recommended video type. For example, 8 time periods are selected, and each time period is 4 hours, so that the video type detection example table shown in table 1 is obtained. If the type of the first reference video is motion video, the 1 st alternative type B₁For comedy-like video, the 2 nd alternative type B₂For general art programs, the 3 rd alternative type B₃For cartoon, the 4 th alternative type B₄For the recording sheet, θ was 0.001. Then Support (Dy) is 0.5, Support (B)₁) 0.75, Support (B)₂) 0.625, Support (B)₃) 0.375, Support (B)₄) 0.5, Support (Dy ≈ B)₁) 0.375, Support (Dy # B)₂) 0.375, Support (Dy # B)₃) 0.125, Support (Dy ≈ B)₄) Is 0. Lift (Dy → B)₁) 375/376, Lift (Dy → B)₂) 750/627, Lift (Dy → B)₃) 250/377, Lift (Dy → B)₄) Is 0. The 2 nd alternative genre, the variety program, is taken as the recommended video genre. The scheme is convenient for finding out the relevance among the videos and mining the watching behaviors of the users so as to better recommend the videos to the users.

Time period 1	Action video, comedy video, integrated art program and cartoon
		Time period 2	Action video, comedy video and comprehensive program
Period 3	Action video and comedy video
		Time period 4	Action video and comprehensive program
Time period 5	Documentary, comedy video, comprehensive art program and cartoon
		Time period 6	Documentary, comedy video and comprehensive program
Time period 7	Documentary and comedy video
		Time period 8	Documentary and cartoon

Table 1 video type detection example table

In some embodiments, the video corresponding to the recommended video type is placed in the recommended video set. If the recommended video set has videos which are watched once, selecting the video which has the longest watching time from the recommended video set as a second reference video, and selecting other videos which are not selected from the recommended video set as alternative videos; and if no video which is watched once is in the recommended video set, randomly selecting one video from the recommended video set as a second reference video, and selecting other videos which are not selected from the recommended video set as alternative videos.

Optionally, obtaining the similarity between each alternative video and the second reference video; selecting an alternative video corresponding to the maximum similarity as a recommended video; or selecting the alternative video corresponding to the minimum similarity as the recommended video; or selecting the alternative video corresponding to the similarity in the set range as the recommended video. Optionally, selecting the alternative video corresponding to the similarity in the set range as the recommended video includes: and taking the corresponding alternative video with the similarity ranking in the set interval as the recommended video. Further, recommending the obtained recommended video to the user. And determining a recommended video according to the second reference video, so that the recommended video is more detailed and has pertinence.

Optionally, the obtaining the similarity between each candidate video and the second reference video includes:

extracting a first introduction text keyword set from the introduction texts corresponding to the alternative videos, and extracting a second introduction text keyword set from the introduction texts corresponding to the second reference video; and obtaining the similarity of each alternative video and the second reference video according to the first introduction text keyword set and the second introduction text keyword set. Optionally, a union of the first introduction text keyword set and the second introduction text keyword set is obtained, the keyword word frequency of each of the first introduction text keyword set and the second introduction text keyword set is calculated, and word frequency vectorization processing is performed on the first introduction text keyword set and the second introduction text keyword set. ComputingObtaining the similarity sim of the ith alternative video and the second reference video_i，c_i,jThe j word frequency vector, ce, in the first introduction text keyword set corresponding to the i candidate video_jAnd j and n are positive integers for the jth word frequency vector in the second introduction text keyword set corresponding to the second reference video, wherein j is more than or equal to 1 and less than or equal to n.

Optionally, the obtaining the similarity between each candidate video and the second reference video includes:

extracting a first introduction text keyword set from the introduction texts corresponding to the alternative videos, and extracting a second introduction text keyword set from the introduction texts corresponding to the second reference video; and obtaining the similarity of each alternative video and the second reference video according to the first introduction text keyword set and the second introduction text keyword set. Optionally, a union of the first introduction text keyword set and the second introduction text keyword set is obtained, the keyword word frequency of each of the first introduction text keyword set and the second introduction text keyword set is calculated, and word frequency vectorization processing is performed on the first introduction text keyword set and the second introduction text keyword set. Extracting a first comment text keyword set from comment texts corresponding to the alternative videos, extracting a second comment text keyword set from comment texts corresponding to the second reference video, acquiring a union of the first comment text keyword set and the second comment text keyword set, calculating keyword word frequencies of the first comment text keyword set and the second comment text keyword set, and performing word frequency vectorization processing on the first comment text keyword set and the second comment text keyword set. Computing

Obtaining the similarity sim of the ith alternative video and the second reference video_i，c_i,jThe j word frequency vector, ce, in the first introduction text keyword set corresponding to the i candidate video_jFor the j word frequency vector, p, in the second introduction text keyword set corresponding to the second reference video_i,jA jth word frequency vector, pe, in a first set of comment text keywords corresponding to the ith candidate video_jAnd j and n are positive integers, wherein j is more than or equal to 1 and less than or equal to n, and are j frequency vectors of the jth word in a second comment text keyword set corresponding to the second reference video. According to the scheme, the video introduction similarity of the video is considered, the similarity of the comments on the video is reflected, the video introduction similarity and the video comment similarity are fused, and the similarity of the video introduction and the video comment is higher in similarity sim due to the fusion mode_iThe medium proportion is larger, and two recommendation influence factors of similarity of user comments and similarity of contents are well balanced, so that the recommended video is more suitable for the watching interest of the user or moreThe method and the device can bring freshness to the user, so that the experience of the user when obtaining video recommendation is improved.

Optionally, after determining the recommended video, playing the recommended video on a refrigerator with a display screen. Therefore, the video played on the refrigerator is suitable for being watched under a multi-user scene, and the experience that a plurality of users watch the video at the same time is improved.

As shown in fig. 2, an apparatus for video recommendation according to an embodiment of the present disclosure includes a processor (processor)100 and a memory (memory)101 storing program instructions. Optionally, the apparatus may also include a Communication Interface (Communication Interface)102 and a bus 103. The processor 100, the communication interface 102, and the memory 101 may communicate with each other via a bus 103. The communication interface 102 may be used for information transfer. The processor 100 may call program instructions in the memory 101 to perform the method for video recommendation of the above-described embodiment.

Further, the program instructions in the memory 101 may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand-alone product.

The memory 101, which is a computer-readable storage medium, may be used for storing software programs, computer-executable programs, such as program instructions/modules corresponding to the methods in the embodiments of the present disclosure. The processor 100 executes functional applications and data processing, i.e. implements the method for video recommendation in the above embodiments, by executing program instructions/modules stored in the memory 101.

The memory 101 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal device, and the like. In addition, the memory 101 may include a high-speed random access memory, and may also include a nonvolatile memory.

According to the device for video recommendation, the face images are identified through the reference images, the person relation information is obtained according to the age information corresponding to the face images and the number of the face images, the recommended video suitable for being watched under a multi-person scene can be more personalized and determined according to different person relations, and therefore the experience that a plurality of users watch the video at the same time is improved.

The embodiment of the disclosure provides a refrigerator with a display screen, which comprises the device for video recommendation.

According to the refrigerator with the display screen, the face image is identified through the reference image, the character relation information is obtained according to the age information corresponding to the face image and the number of the face images, the recommended video suitable for being watched under a multi-person scene can be more personalized and determined according to different character relations, and therefore the experience that a plurality of users watch the video at the same time is improved.

Embodiments of the present disclosure provide a computer-readable storage medium storing computer-executable instructions configured to perform the above-described method for video recommendation.

The disclosed embodiments provide a computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the above-described method for video recommendation.

The computer-readable storage medium described above may be a transitory computer-readable storage medium or a non-transitory computer-readable storage medium.

The technical solution of the embodiments of the present disclosure may be embodied in the form of a software product, where the computer software product is stored in a storage medium and includes one or more instructions to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present disclosure. And the aforementioned storage medium may be a non-transitory storage medium comprising: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes, and may also be a transient storage medium.

The above description and drawings sufficiently illustrate embodiments of the disclosure to enable those skilled in the art to practice them. Other embodiments may incorporate structural, logical, electrical, process, and other changes. The examples merely typify possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in or substituted for those of others. Furthermore, the words used in the specification are words of description only and are not intended to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term "and/or" as used in this application is meant to encompass any and all possible combinations of one or more of the associated listed. Furthermore, the terms "comprises" and/or "comprising," when used in this application, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of other like elements in a process, method or apparatus that comprises the element. In this document, each embodiment may be described with emphasis on differences from other embodiments, and the same and similar parts between the respective embodiments may be referred to each other. For methods, products, etc. of the embodiment disclosures, reference may be made to the description of the method section for relevance if it corresponds to the method section of the embodiment disclosure.

Those of skill in the art would appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software may depend upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the disclosed embodiments. It can be clearly understood by the skilled person that, for convenience and brevity of description, the specific working processes of the system, the apparatus and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, apparatuses, etc.) may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units may be merely a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to implement the present embodiment. In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than disclosed in the description, and sometimes there is no specific order between the different operations or steps. For example, two sequential operations or steps may in fact be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. Each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.