Multimedia playback method, device, storage medium and electronic device

Abstract

The present application discloses a multimedia playback method, device, storage medium and electronic device, and relates to the field of Internet technology. The method includes: in response to detecting a specific object behavior of a media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information; obtaining a playback record of the target multimedia, wherein the playback record includes a playback record time point and at least one preset object identifier; comparing the target object identifier with the preset object identifier to obtain a comparison result; determining a playback time point that matches the specific object behavior according to the comparison result and the playback record time point, and playing the target multimedia according to the playback time point. The present application can effectively improve the multimedia playback effect.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a multimedia playback method, device, storage medium and electronic device. Background Art

[0002] With the development of technology, the requirements for the playback experience of multimedia such as videos are getting higher and higher. Taking the playback of video programs on smart TVs as an example, when different objects operate the TV to play video programs, different playback records are often generated. Usually, the objects have the need to play back the video programs according to the playback records.

[0003] However, there are often situations where multiple objects browse multimedia at the same time. Currently, when multimedia is played according to playback records, it is often simply played based on the time point at which the multimedia recorded by the device ended playback in history. When multiple objects browse multimedia, it is usually difficult to play it at the appropriate position, resulting in poor multimedia playback effect and poor user playback experience. Summary of the invention

[0004] The embodiment of the present application provides a solution that can effectively improve the multimedia playback effect.

[0005] The embodiments of the present application provide the following technical solutions:

[0006] According to one embodiment of the present application, a multimedia playback method includes: in response to detecting a specific object behavior of a media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information; obtaining a playback record of the target multimedia, the playback record including a playback record time point and at least one preset object identifier; comparing the target object identifier with the preset object identifier to obtain a comparison result; determining a playback time point that matches the specific object behavior based on the comparison result and the playback record time point, and playing the target multimedia based on the playback time point.

[0007] In some embodiments of the present application, the specific object behavior includes browsing participation behavior within a predetermined time period where a triggering moment of a specific playback request is located; the response to detecting the specific object behavior of a media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information, includes: if the specific playback request corresponding to the target multimedia is received, within the predetermined time period where the triggering moment of the specific playback request is located, detecting a facial image of the media browsing object located in a target area; in response to detecting the facial image, extracting facial feature information based on the facial image as feature information of the media browsing object; and generating the target object identifier based on the feature information.

[0008] In some embodiments of the present application, the target object identifier includes at least one; determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point includes: if the comparison result indicates that the at least one target object identifier is consistent with the at least one preset object identifier, then determining the playback record time point as the playback time point that matches the browsing participation behavior; the method also includes: continuing to update the browsing record information of the media browsing object for the target multimedia in the playback record.

[0009] In some embodiments of the present application, the target object identifier includes at least one; determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point includes: if the comparison result indicates that the at least one target object identifier is a subset of the at least one preset object identifier, then determining the playback record time point as the playback time point that matches the browsing participation behavior; the method also includes: generating a target browsing record, and recording the browsing record information of the media browsing object for the target multimedia in the target browsing record.

[0010] In some embodiments of the present application, the target object identifiers include multiple ones, and the playback records include multiple ones; determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point includes: if the comparison result indicates that at least two of the target object identifiers exist in different playback records, and there are at least two playback record time points in different playback records, then determining the smallest playback record time point as the playback time point that matches the browsing participation behavior; the method also includes: generating a current browsing record, and recording the browsing record information of the media browsing object for the target multimedia in the current browsing record.

[0011] In some embodiments of the present application, the specific object behavior includes a specific physiological behavior; in response to detecting the specific object behavior of the media browsing object, collecting feature information of the media browsing object, and generating a target object identification based on the feature information, includes: in response to detecting the specific physiological behavior of the media browsing object, collecting a facial image of the media browsing object; extracting facial feature information as feature information of the media browsing object based on the facial image, and generating an object identification based on the feature information; predicting an expected browsing tag of the media browsing object based on the behavior information corresponding to the specific physiological behavior; and combining the object identification and the expected browsing tag to obtain the target object identification.

[0012] In some embodiments of the present application, each of the preset object identifiers is generated by a combination of a related object identifier and a target browsing expectation tag, and the playback record time point includes multiple recording time points, and each preset object identifier corresponds to a recording time point; determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point includes: determining a preset object identifier with a target browsing expectation tag that matches the browsing expectation tag based on the comparison result, and obtaining a target preset object identifier; obtaining an object relationship network corresponding to the object identifier and the related object identifier in the target preset object identifier; performing scoring processing based on the object relationship network to obtain a browsing score for each related object identifier in the target preset object identifier; determining the preset object identifier corresponding to the related object identifier with the highest browsing score, and obtaining a target playback identifier; and determining the recording time point corresponding to the target playback identifier as the playback time point that matches the specific physiological behavior.

[0013] According to another embodiment of the present application, a multimedia playback device includes: a detection module, which is used to collect feature information of the media browsing object in response to detecting a specific object behavior of the media browsing object, and generate a target object identifier based on the feature information; an acquisition module, which is used to acquire a playback record of the target multimedia, wherein the playback record includes a playback record time point and at least one preset object identifier; a comparison module, which is used to compare the target object identifier with the preset object identifier to obtain a comparison result; and a playback module, which is used to determine a playback time point that matches the specific object behavior based on the comparison result and the playback record time point, and play the target multimedia according to the playback time point.

[0014] According to another embodiment of the present application, a storage medium stores a computer program thereon, and when the computer program is executed by a processor of a computer, the computer executes the method described in the embodiment of the present application.

[0015] According to another embodiment of the present application, an electronic device may include: a memory storing a computer program; and a processor reading the computer program stored in the memory to execute the method described in the embodiment of the present application.

[0016] In an embodiment of the present application, in response to detecting a specific object behavior of a media browsing object, characteristic information of the media browsing object is collected, and a target object identifier is generated based on the characteristic information; a playback record of the target multimedia is obtained, the playback record including a playback record time point and at least one preset object identifier; the target object identifier is compared with the preset object identifier to obtain a comparison result; based on the comparison result and the playback record time point, a playback time point that matches the specific object behavior is determined, and the target multimedia is played according to the playback time point.

[0017] In this way, the target object identifier is obtained according to the specific object behavior of the media browsing object, and the playback record corresponding to the target multimedia including at least one preset object identifier is obtained. The playback time point that matches the specific user behavior is determined through the comparison result of the target object identifier and the preset object identifier and the playback record time point. When faced with a situation where multiple objects watch multimedia at the same time, the target multimedia can be played extremely appropriately based on a playback time point that matches the specific user behavior, which can effectively improve the playback effect of the multimedia and enhance the user playback experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of a system to which the embodiments of the present application can be applied is shown.

[0020] Figure 2 A flowchart of a multimedia playback method according to an embodiment of the present application is shown.

[0021] Figure 3 A block diagram of a multimedia playback device according to an embodiment of the present application is shown.

[0022] Figure 4 A block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0024] In the following description, the specific embodiments of the present application will be described with reference to steps and symbols performed by one or more computers, unless otherwise stated. Therefore, these steps and operations will be mentioned several times as being performed by a computer, and the computer execution referred to herein includes the operation of a computer processing unit by electronic signals representing data in a structured form. This operation converts the data or maintains it at a location in the memory system of the computer, which can be reconfigured or otherwise change the operation of the computer in a manner familiar to those skilled in the art. The data structure maintained by the data is a physical location in the memory, which has specific characteristics defined by the data format. However, the principles of the present application are described in the above text, which does not represent a limitation, and those skilled in the art will understand that the various steps and operations described below can also be implemented in hardware.

[0025] It should be noted that the embodiments of the present application can legally collect and process data such as feature information of an object based on user consent or authorization.

[0026] Figure 1 FIG. 1 is a schematic diagram showing a system 100 to which an embodiment of the present application can be applied. Figure 1 As shown, the system 100 may include a terminal 101. The terminal 101 may be any computer device, such as a computer, a mobile phone, a smart watch, and a home appliance (such as a smart TV), etc. The terminal 101 may be equipped with a facial image acquisition device such as a camera.

[0027] In one implementation of this example, terminal 101 may: in response to detecting a specific object behavior of a media browsing object, collect feature information of the media browsing object, and generate a target object identifier based on the feature information; obtain a playback record of the target multimedia, wherein the playback record includes a playback record time point and at least one preset object identifier; compare the target object identifier with the preset object identifier to obtain a comparison result; determine a playback time point that matches the specific object behavior based on the comparison result and the playback record time point, and play the target multimedia based on the playback time point.

[0028] Figure 2 The flowchart of the multimedia playback method according to an embodiment of the present application is schematically shown. The execution subject of the multimedia playback method can be any device, such as Figure 1 Terminal 101 is shown.

[0029] like Figure 2 As shown, the multimedia playing method may include steps S210 to S240.

[0030] Step S210, in response to detecting a specific object behavior of a media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information; Step S220, obtaining a playback record of the target multimedia, wherein the playback record includes a playback record time point and at least one preset object identifier; Step S230, comparing the target object identifier with the preset object identifier to obtain a comparison result; Step S240, determining a playback time point that matches the specific object behavior based on the comparison result and the playback record time point, and playing the target multimedia based on the playback time point.

[0031] The media browsing object is an object that can browse multimedia, such as a user who browses a TV program. Through a camera or recording device, it is possible to detect specific object behaviors such as browsing participation behaviors (such as participating in browsing the target multimedia within a predetermined time period after triggering the target multimedia to play) or specific physiological behaviors (such as laughter, crying, or smiling faces) of the media browsing object under the agreed legal protocol mode.

[0032] Feature information is feature information of an object such as sound information or facial image information. Feature information of a media browsing object can be collected through a camera or recording device. The target object identifier is an identifier that can uniquely identify the media browsing object. Feature information is information that can uniquely characterize the media browsing object, and the target object identifier of the media browsing object can be generated based on the feature information.

[0033] The play record may be obtained from the cloud or from a local storage, etc. The target multimedia may be a television program or article content, etc. The target multimedia may be the multimedia that is indicated by the media browsing object and is desired to be viewed.

[0034] The playback record includes a playback record time point and at least one preset object identifier. The playback record time point is a specific playback time point of the target multimedia recorded when an object (such as 1 or 3, etc.) corresponding to at least one preset object identifier (such as 1 or 3, etc.) jointly watches the target multimedia (such as the playback time point of the TV when a certain viewing ends or the playback time point with specific picture content during a certain viewing, etc.). The preset object identifier is an identifier corresponding to an object in the history of a certain joint viewing of the target multimedia.

[0035] The target object identifier is compared with at least one preset object identifier in the playback record to obtain a comparison result, which may indicate the relationship between the media browsing object and historical objects that have historically participated in browsing the target multimedia, for example, the media browsing object is exactly the same as the historical object or the media browsing object belongs to a subset of the historical objects, etc.

[0036] Then, according to the comparison result and the playback record time point, the playback time point that matches the specific object behavior is determined. When there are any number of media browsing objects, a suitable playback time point can be determined and the target multimedia can be played according to the playback time point.

[0037] In this way, based on steps S210 to S240, the target object identifier is obtained according to the specific object behavior of the media browsing object, and the playback record corresponding to the target multimedia including at least one preset object identifier is obtained. The playback time point that matches the specific user behavior is determined through the comparison result between the target object identifier and the preset object identifier and the playback record time point. When facing the situation where multiple objects watch multimedia at the same time, the target multimedia can be played extremely appropriately based on a playback time point that matches the specific user behavior, which can effectively improve the playback effect of the multimedia and enhance the user playback experience.

[0038] The following describes the specific process of each step during multimedia playback.

[0039] In step S210, in response to detecting a specific object behavior of a media browsing object, characteristic information of the media browsing object is collected, and a target object identifier is generated based on the characteristic information.

[0040] In one embodiment, the specific object behavior includes browsing participation behavior within a predetermined time period where the triggering time point of the specific playback request is located; step S210, in response to detecting the specific object behavior of the media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information, includes:

[0041] If the specific playback request corresponding to the target multimedia is received, a facial image of a media browsing object located in a target area is detected within a predetermined time period at the triggering time point of the specific playback request; in response to detecting the facial image, facial feature information is extracted based on the facial image as feature information of the media browsing object; and the target object identifier is generated based on the feature information.

[0042] The specific playback request may include a playback request or a start playback request, etc. The triggering time point is the time point when the user triggers the specific playback request, the predetermined time period is the time period of predetermined length starting from the triggering time point, and the target area can be a pre-set media browsing area. Objects in the media browsing area are regarded as objects whose probability of browsing multimedia is higher than a predetermined threshold.

[0043] The facial images of the media browsing objects participating in the target multimedia viewing can be continuously collected by the image acquisition device within a predetermined time period, and the facial feature information of each collected facial image can be extracted. Based on the facial feature information as feature information, an object identifier matching the facial feature information can be obtained from the facial recognition library as a target object identifier, or a unique target object identifier can be generated based on the facial feature information. Furthermore, for each media browsing object corresponding to the browsing participation behavior, a target object identifier of each media browsing object is generated.

[0044] In one embodiment, the specific object behavior includes a specific physiological behavior; step S210, in response to detecting the specific object behavior of the media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information, includes:

[0045] In response to detecting the specific physiological behavior of the media browsing object, a facial image of the media browsing object is collected; facial feature information is extracted based on the facial image as feature information of the media browsing object, and an object identifier is generated based on the feature information; based on the behavior information corresponding to the specific physiological behavior, an expected browsing tag of the media browsing object is predicted; and the object identifier and the expected browsing tag are combined to obtain the target object identifier.

[0046] Specific physiological behaviors such as laughter, crying or smiling faces, etc., the object generating the specific physiological behavior may be one or more, which can be set according to actual conditions. After detecting the specific physiological behavior, the facial image of the media browsing object is collected to extract facial feature information as the feature information of the media browsing object, and based on the feature information, the object identifier matching the specific information is obtained from the face recognition library, or a unique object identifier corresponding to the feature information is generated based on the specific information.

[0047] For specific physiological behaviors, corresponding behavior information can be collected while being detected, such as audio feature information or image feature information of multiple facial images. Using a pre-trained prediction model based on machine learning, the behavior information can be input into a prediction module for prediction processing to predict the expected browsing label of the media browsing object. The expected browsing label can refer to a label such as a specific browsing score or a specific browsing level of the media browsing object at the current moment. At least one type of expected browsing label can be specified in advance according to needs when training the prediction model, and the prediction model can predict a type of expected browsing label that matches the behavior information based on the behavior information.

[0048] The generated expected browsing tag is combined with each object identifier respectively to obtain at least one target object identifier.

[0049] In step S220, a play record of the target multimedia is obtained, wherein the play record includes a play record time point and at least one preset object identifier.

[0050] The playback record includes a playback record time point and at least one preset object identifier. The playback record time point is a specific playback time point of the target multimedia recorded when an object (such as 1 or 3, etc.) corresponding to at least one preset object identifier (such as 1 or 3, etc.) jointly watches the target multimedia (such as the playback time point of the TV when a certain viewing ends or the playback time point with specific picture content during a certain viewing, etc.). The preset object identifier is an identifier corresponding to an object in the history of a certain joint viewing of the target multimedia.

[0051] In step S230, the target object identifier is compared with the preset object identifier to obtain a comparison result.

[0052] The target object identifier is compared with at least one preset object identifier in the playback record to obtain a comparison result, which may indicate the relationship between the media browsing object and historical objects that have historically participated in browsing the target multimedia, for example, the media browsing object is exactly the same as the historical object or the media browsing object belongs to a subset of the historical objects, etc.

[0053] In one example, the comparison result is that the target object identifier is consistent with the preset object identifier, that is, at least one target object identifier is consistent with at least one preset object identifier, for example, the target object identifier includes 2 A and B, and the preset object identifier includes 2 A and B, if the media browsing object corresponding to the target object identifier is the same as the object corresponding to the preset object identifier. In one example, the target object identifier is completely different from the preset object identifier, and there is no corresponding playback record in the history of the media browsing object. In one example, at least one target object identifier is a subset of at least one preset object identifier, for example, the target object identifier includes 1 A, and the preset object identifier includes 2 A and B. In one example, at least two target object identifiers exist in different playback records, for example, the playback records corresponding to the target multimedia include record 1 and record 2, there is 1 target object identifier A in record 1, and there is 1 target object identifier B in record 2.

[0054] Step S240, determining the playback time point that matches the specific object behavior according to the comparison result and the playback record time point, and playing the target multimedia according to the playback time point.

[0055] In one embodiment, the target object identifier includes at least one; step S240, determining the playback time point matched by the specific object behavior according to the comparison result and the playback record time point, includes:

[0056] If the comparison result indicates that the at least one target object identifier is consistent with the at least one preset object identifier, the playback record time point is determined as the playback time point matched by the browsing participation behavior; the method also includes: continuing to update the browsing record information of the media browsing object for the target multimedia in the playback record.

[0057] If at least one target object identifier is consistent with the at least one preset object identifier, then the current media browsing object has a one-to-one correspondence with the object corresponding to the preset object identifier recorded in the playback record, that is, the media browsing object this time is the same as the object recorded in the playback record. At this time, the playback record time point in the playback record can be used as the playback time point that matches the browsing participation behavior detected this time, and the target multimedia can be effectively played back. And the browsing record information is updated in the playback record, and the browsing record information can at least include the specific playback time point of the target multimedia (such as the playback time point of the TV when the viewing ends this time or the playback time point with specific screen content during the viewing, etc.).

[0058] In one embodiment, the target object identifier includes at least one; step S240, determining the playback time point matched by the specific object behavior according to the comparison result and the playback record time point, includes:

[0059] If the comparison result indicates that the at least one target object identifier is a subset of the at least one preset object identifier, the playback record time point is determined as the playback time point matched by the browsing participation behavior; the method also includes: generating a target browsing record, and recording the browsing record information of the media browsing object for the target multimedia in the target browsing record.

[0060] At least one target object identifier is a subset of the at least one preset object identifier, that is, the media browsing object this time is a part of the objects recorded in the playback record. At this time, the playback record time point in the playback record can also be used as the playback time point matching the browsing participation behavior detected this time, so that the target multimedia can be effectively played back.

[0061] At the same time, a new target browsing record is generated for the detected media browsing object, and browsing record information is recorded in the target browsing record. The browsing record information may at least include a specific playback time point of the target multimedia (such as the playback time point of the TV when the viewing ends or the playback time point with specific picture content during the viewing, etc.) and a target object identifier corresponding to the media browsing object detected this time.

[0062] In addition, in some embodiments, the preset object identifier corresponding to the target object identifier corresponding to the media browsing object detected this time may be deleted from the acquired playback record.

[0063] In one embodiment, the target object identifier includes multiple ones, and the playback record includes multiple ones; step S240, according to the comparison result and the playback record time point, determining the playback time point matched by the specific object behavior, includes:

[0064] If the comparison result indicates that at least two of the target object identifiers exist in different playback records, and there are at least two playback record time points in the different playback records, then the smallest playback record time point is determined as the playback time point matched by the browsing participation behavior; the method also includes: generating a current browsing record, and recording the browsing record information of the media browsing object for the target multimedia in the current browsing record.

[0065] The play records corresponding to the target multimedia include play record 1 and play record 2. There is a target object identifier A in play record 1 (i.e., a preset object identifier in play record 1 matches A), and there is a target object identifier B in play record 2 (i.e., a preset object identifier in play record 2 matches B). At the same time, play record 1 includes play record time 1, and play record 2 includes play record time 2. At this time, the minimum value of play record time 1 and play record time 2 is determined as the play time point matched by the browsing participation behavior, so that the target multimedia can be reliably played back.

[0066] At the same time, a new current browsing record is generated for the detected media browsing object, and browsing record information is recorded in the current browsing record. The browsing record information may at least include a specific playback time point of the target multimedia (such as the playback time point of the TV when the viewing ends or the playback time point with specific picture content during the viewing, etc.) and a target object identifier corresponding to the media browsing object detected this time.

[0067] In addition, in some embodiments, the preset object identifier corresponding to the target object identifier corresponding to the media browsing object detected this time may be deleted from the acquired playback record.

[0068] In one embodiment, each of the preset object identifiers is generated by combining a related object identifier and a target browsing expected tag, and the playback record time point includes multiple record time points, and each of the preset object identifiers corresponds to one record time point; step S240, determining the playback time point matched by the specific object behavior according to the comparison result and the playback record time point, includes:

[0069] Determine a preset object identifier with a target browsing expectation tag that matches the browsing expectation tag according to the comparison result, and obtain a target preset object identifier; obtain an object relationship network corresponding to the object identifier and related object identifiers in the target preset object identifier; perform scoring processing based on the object relationship network to obtain a browsing score for each related object identifier in the target preset object identifier; determine the preset object identifier corresponding to the related object identifier with the highest browsing score, and obtain a target playback identifier; determine the recording time point corresponding to the target playback identifier as the playback time point that matches the specific physiological behavior.

[0070] When the target object identifier is obtained by combining the object identifier and the expected browsing tag, the expected browsing tag may refer to a tag such as a specific browsing score or a specific browsing level of the media browsing object at the current moment.

[0071] The playback record time points in the playback record include multiple recording time points, each preset object identifier corresponds to a recording time point, and the target browsing expected label can refer to the specific browsing score or specific browsing level of the relevant object (the object corresponding to the relevant object identifier in the preset object identifier) ​​at the current moment.

[0072] The target object identifier and each preset object identifier have corresponding comparison results. According to the comparison results, the preset object identifier (which may include at least one) with the target browsing expected tag matching the browsing expected tag (belonging to the target object identifier) ​​can be determined, and then the target preset object identifier can be obtained.

[0073] Then, obtain the object relationship network corresponding to the object identifier in the target object identifier and the relevant object identifier in the target preset object identifier. The object relationship network is a relationship network constructed with the object identifier and the relevant object identifier as nodes and the social relationship data between the objects corresponding to the object identifier and the relevant object identifier as connecting edges. The object relationship network can be constructed in real time or obtained from a preset relationship network.

[0074] When the object relationship network is scored, the object relationship network can be converted into an adjacency matrix, and the adjacency matrix is ​​input into a pre-trained scoring model based on machine learning. The scoring model outputs the browsing score of each related object identifier in the target preset object identifier.

[0075] Then, the preset object identifier corresponding to the relevant object identifier with the highest browsing score is determined to obtain the target playback identifier; the recording time point corresponding to the target playback identifier is determined to be the playback time point matching the specific physiological behavior for playback, so that the target media can be effectively and reliably played back in any scenario.

[0076] In order to better implement the multimedia playback method provided in the embodiment of the present application, the embodiment of the present application also provides a multimedia playback device based on the multimedia playback method. The meanings of the terms are the same as those in the multimedia playback method, and the specific implementation details can refer to the description in the method embodiment. Figure 3 A block diagram of a multimedia playback device according to an embodiment of the present application is shown.

[0077] like Figure 3 As shown, the multimedia playback device 300 may include a detection module 310 , an acquisition module 320 , a comparison module 330 and a playback module 340 .

[0078] The detection module 310 can be used to collect feature information of the media browsing object in response to detecting a specific object behavior of the media browsing object, and generate a target object identifier based on the feature information; the acquisition module 320 can be used to obtain a playback record of the target multimedia, wherein the playback record includes a playback record time point and at least one preset object identifier; the comparison module 330 can be used to compare the target object identifier with the preset object identifier to obtain a comparison result; the playback module 340 can be used to determine a playback time point that matches the specific object behavior based on the comparison result and the playback record time point, and play the target multimedia based on the playback time point.

[0079] In some embodiments of the present application, the specific object behavior includes browsing participation behavior within a predetermined time period where a triggering time point of a specific playback request is located; the detection module 310 includes a first detection unit, which is used to: if the specific playback request corresponding to the target multimedia is received, detect a facial image of a media browsing object located in a target area within a predetermined time period where a triggering time point of the specific playback request is located; in response to detecting the facial image, extract facial feature information based on the facial image as feature information of the media browsing object; and generate the target object identifier based on the feature information.

[0080] In some embodiments of the present application, the target object identifier includes at least one; the playback module 340 includes a first playback processing unit, which is used to: if the comparison result indicates that the at least one target object identifier is consistent with the at least one preset object identifier, then determine the playback record time point as the playback time point that matches the browsing participation behavior; the device also includes a first updating unit, which is used to: continue to update the browsing record information of the media browsing object for the target multimedia in the playback record.

[0081] In some embodiments of the present application, the target object identifier includes at least one; the playback module 340 includes a second playback processing unit, which is used to: if the comparison result indicates that the at least one target object identifier is a subset of the at least one preset object identifier, then determine the playback record time point as the playback time point that matches the browsing participation behavior; the device also includes a second update unit, which is used to: generate a target browsing record, and record the browsing record information of the media browsing object for the target multimedia in the target browsing record.

[0082] In some embodiments of the present application, the target object identifier includes multiple, and the playback records include multiple; the playback module 340 includes a second playback processing unit, which is used to: if the comparison result indicates that at least two of the target object identifiers exist in different playback records, and there are at least two playback record time points in different playback records, then the smallest playback record time point is determined as the playback time point that matches the browsing participation behavior; the device also includes a third updating unit, which is used to: generate a current browsing record, and record the browsing record information of the media browsing object for the target multimedia in the current browsing record.

[0083] In some embodiments of the present application, the specific object behavior includes specific physiological behavior; the detection module 310 includes a second detection unit, which is used to: in response to detecting the specific physiological behavior of the media browsing object, collect a facial image of the media browsing object; extract facial feature information based on the facial image as feature information of the media browsing object, and generate an object identifier based on the feature information; predict an expected browsing tag of the media browsing object based on the behavior information corresponding to the specific physiological behavior; and combine the object identifier and the expected browsing tag to obtain the target object identifier.

[0084] In some embodiments of the present application, each of the preset object identifiers is generated by a combination of a related object identifier and a target browsing expectation tag, and the playback record time point includes multiple recording time points, and each of the preset object identifiers corresponds to a recording time point; the playback module 340 includes a fourth playback processing unit, which is used to: determine the preset object identifier with a target browsing expectation tag matching the browsing expectation tag according to the comparison result, and obtain the target preset object identifier; obtain the object relationship network corresponding to the object identifier and the related object identifier in the target preset object identifier; perform scoring processing based on the object relationship network to obtain the browsing score of each related object identifier in the target preset object identifier; determine the preset object identifier corresponding to the related object identifier with the highest browsing score, and obtain the target playback identifier; determine the recording time point corresponding to the target playback identifier as the playback time point matching the specific physiological behavior.

[0085] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0086] In addition, an embodiment of the present application further provides an electronic device, which may be a terminal or a server. Figure 4 As shown, it shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0087] The electronic device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will appreciate that Figure 4 The electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0088] The processor 401 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire computer device. By running or executing software programs and / or modules stored in the memory 402, and calling data stored in the memory 402, it executes various functions of the computer device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user pages and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

[0089] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0090] The electronic device also includes a power supply 403 for supplying power to each component. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, so as to manage charging, discharging, power consumption and other functions through the power management system. The power supply 403 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators and other arbitrary components.

[0091] The electronic device may further include an input unit 404, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0092] Although not shown, the electronic device may further include a display unit, etc., which will not be described in detail herein. Specifically in this embodiment, the processor 401 in the electronic device will load the executable files corresponding to the processes of one or more computer programs into the memory 402 according to the following instructions, and the processor 401 will run the computer programs stored in the memory 402 to implement various functions. For example, the processor 401 may perform the following steps:

[0093] In response to detecting a specific object behavior of a media browsing object, characteristic information of the media browsing object is collected, and a target object identifier is generated based on the characteristic information; a playback record of a target multimedia is obtained, wherein the playback record includes a playback record time point and at least one preset object identifier; the target object identifier is compared with the preset object identifier to obtain a comparison result; based on the comparison result and the playback record time point, a playback time point that matches the specific object behavior is determined, and the target multimedia is played according to the playback time point.

[0094] In some embodiments of the present application, the specific object behavior includes browsing participation behavior within a predetermined time period where a triggering moment of a specific playback request is located; in response to detecting the specific object behavior of a media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information, the processor 401 may execute: if the specific playback request corresponding to the target multimedia is received, within the predetermined time period where the triggering moment of the specific playback request is located, detecting a facial image of the media browsing object located in a target area; in response to detecting the facial image, extracting facial feature information based on the facial image as feature information of the media browsing object; and generating the target object identifier based on the feature information.

[0095] In some embodiments of the present application, the target object identifier includes at least one; when determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point, the processor 401 can execute: if the comparison result indicates that the at least one target object identifier is consistent with the at least one preset object identifier, then the playback record time point is determined as the playback time point that matches the browsing participation behavior; the processor 401 can also execute: continue to update the browsing record information of the media browsing object for the target multimedia in the playback record.

[0096] In some embodiments of the present application, the target object identifier includes at least one; when determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point, the processor 401 can execute: if the comparison result indicates that the at least one target object identifier is a subset of the at least one preset object identifier, then the playback record time point is determined as the playback time point that matches the browsing participation behavior; the processor 401 can also execute: generate a target browsing record, and record the browsing record information of the media browsing object for the target multimedia in the target browsing record.

[0097] In some embodiments of the present application, the target object identifier includes multiple, and the playback records include multiple; when determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point, the processor 401 can execute: if the comparison result indicates that at least two of the target object identifiers exist in different playback records, and there are at least two playback record time points in different playback records, then the smallest playback record time point is determined as the playback time point that matches the browsing participation behavior; the processor 401 can also execute: generate a current browsing record, and record the browsing record information of the media browsing object for the target multimedia in the current browsing record.

[0098] In some embodiments of the present application, the specific object behavior includes a specific physiological behavior; when the response to detecting the specific object behavior of the media browsing object, the feature information of the media browsing object is collected, and the target object identification is generated based on the feature information, the processor 401 can execute: in response to detecting the specific physiological behavior of the media browsing object, the facial image of the media browsing object is collected; based on the facial image, facial feature information is extracted as the feature information of the media browsing object, and an object identification is generated based on the feature information; based on the behavior information corresponding to the specific physiological behavior, the expected browsing tag of the media browsing object is predicted; and the object identification is combined with the expected browsing tag to obtain the target object identification.

[0099] In some embodiments of the present application, each of the preset object identifiers is generated by a combination of a related object identifier and a target browsing expectation tag, and the playback record time point includes multiple recording time points, and each preset object identifier corresponds to a recording time point; when determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point, the processor 401 can execute: determining the preset object identifier with a target browsing expectation tag that matches the browsing expectation tag based on the comparison result, and obtaining a target preset object identifier; obtaining an object relationship network corresponding to the object identifier and the related object identifier in the target preset object identifier; performing scoring processing based on the object relationship network to obtain a browsing score for each related object identifier in the target preset object identifier; determining the preset object identifier corresponding to the related object identifier with the highest browsing score, and obtaining a target playback identifier; and determining the recording time point corresponding to the target playback identifier as the playback time point that matches the specific physiological behavior.

[0100] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by a computer program, or by controlling related hardware through a computer program. The computer program may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0101] To this end, an embodiment of the present application further provides a storage medium, in which a computer program is stored. The computer program can be loaded by a processor to execute the steps in any method provided in the embodiment of the present application.

[0102] The storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0103] Since the computer program stored in the storage medium can execute the steps in any method provided in the embodiments of the present application, the beneficial effects that can be achieved by the method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0104] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0105] It should be understood that the present application is not limited to the embodiments that have been described above and shown in the accompanying drawings, but various modifications and changes may be made without departing from the scope thereof.

Claims

1. A multimedia playback method, characterized in that: include: In response to detecting a specific object behavior of a media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information; the target object identifier includes an object identifier and a browsing expectation tag; Acquire a playback record of the target multimedia, wherein the playback record includes a playback record time point and at least one preset object identifier; each preset object identifier is generated by combining a related object identifier and a target browsing expected tag, and the playback record time point includes multiple record time points, and each preset object identifier corresponds to a record time point; Comparing the target object identifier with the preset object identifier to obtain a comparison result; Determining a playback time point that matches the specific object behavior according to the comparison result and the playback record time point, and playing the target multimedia according to the playback time point; The determining, according to the comparison result and the playback record time point, the playback time point that matches the specific object behavior includes: Determine, according to the comparison result, a preset object identifier having a target expected browsing tag matching the expected browsing tag, and obtain a target preset object identifier; Acquire an object relationship network corresponding to the object identifier and relevant object identifiers in the target preset object identifier; Performing scoring processing based on the object relationship network to obtain a browsing score for each related object identifier in the target preset object identifier; Determine the preset object identifier corresponding to the related object identifier with the highest browsing score, and obtain a target playback identifier; and The recording time point corresponding to the target playback identifier is determined as the playback time point matched by the specific object behavior.

2. The method according to claim 1, characterized in that The specific object behavior includes browsing participation behavior within a predetermined time period where the triggering time point of the specific playback request is located; In response to detecting a specific object behavior of a media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information, includes: If the specific play request corresponding to the target multimedia is received, detecting a facial image of a media browsing object located in a target area within a predetermined time period at a triggering time point of the specific play request; In response to detecting the facial image, extracting facial feature information based on the facial image as feature information of the media browsing object; The target object identifier is generated based on the feature information.

3. The method according to claim 2, characterized in that The target object identifier includes at least one; and determining the playback time point matched by the specific object behavior according to the comparison result and the playback record time point includes: If the comparison result indicates that the at least one target object identifier is consistent with the at least one preset object identifier, determining the playback record time point as the playback time point matched by the browsing participation behavior; The method further includes: continuing to update and record browsing record information of the media browsing object for the target multimedia in the playback record.

4. The method according to claim 2, characterized in that: The target object identifier includes at least one; and determining the playback time point matched by the specific object behavior according to the comparison result and the playback record time point includes: If the comparison result indicates that the at least one target object identifier is a subset of the at least one preset object identifier, determining the playback record time point as the playback time point matched by the browsing participation behavior; The method further includes: generating a target browsing record, and recording browsing record information of the media browsing object for the target multimedia in the target browsing record.

5. The method according to claim 1, characterized in that The target object identifiers include multiple ones, and the playback records include multiple ones; and determining the playback time point that matches the specific object behavior according to the comparison result and the playback record time point includes: If the comparison result indicates that at least two target object identifiers exist in different playback records, and there are at least two playback record time points in different playback records, then the smallest playback record time point is determined as the playback time point matched by the specific object behavior; The method further includes: generating a current browsing record, and recording browsing record information of the media browsing object for the target multimedia in the current browsing record.

6. The method according to claim 1, characterized in that The specific object behavior includes a specific physiological behavior; in response to detecting the specific object behavior of the media browsing object, collecting feature information of the media browsing object, and generating a target object identifier based on the feature information, including: In response to detecting the specific physiological behavior of the media browsing object, collecting a facial image of the media browsing object; extracting facial feature information based on the facial image as feature information of the media browsing object, and generating an object identifier based on the feature information; Predicting the expected browsing tag of the media browsing object based on the behavior information corresponding to the specific physiological behavior; The object identifier and the expected browsing tag are combined to obtain the target object identifier.

7. A multimedia playback device, characterized in that: include: A detection module, configured to collect characteristic information of the media browsing object in response to detecting a specific object behavior of the media browsing object, and generate a target object identifier based on the characteristic information; the target object identifier includes an object identifier and a browsing expectation tag; An acquisition module is used to acquire a playback record of a target multimedia, wherein the playback record includes a playback record time point and at least one preset object identifier; each preset object identifier is generated by combining a related object identifier and a target browsing expected tag, and the playback record time point includes multiple record time points, and each preset object identifier corresponds to a record time point; A comparison module, used for comparing the target object identifier with the preset object identifier to obtain a comparison result; A playing module, used to determine a playing time point matched by the specific object behavior according to the comparison result and the playing record time point, and play the target multimedia according to the playing time point; The method of determining the playback time point that matches the specific object behavior based on the comparison result and the playback record time point includes: determining a preset object identifier having a target browsing expectation tag that matches the browsing expectation tag based on the comparison result to obtain a target preset object identifier; obtaining an object relationship network corresponding to the object identifier and related object identifiers in the target preset object identifier; performing scoring processing based on the object relationship network to obtain a browsing score for each related object identifier in the target preset object identifier; determining the preset object identifier corresponding to the related object identifier with the highest browsing score to obtain a target playback identifier; and determining the record time point corresponding to the target playback identifier as the playback time point that matches the specific object behavior.

8. A storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: a memory storing a computer program; A processor reads a computer program stored in a memory to execute the method according to any one of claims 1 to 6.

Images