Multi-media file release method and device

[0022] In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0023] figure 1 It is a flowchart of Embodiment 1 of the multimedia file publishing method of the present invention, such as figure 1 As shown, the execution subject of this embodiment is a mobile terminal or commonly used instant messaging tools such as WeChat, QQ, and Yixin installed in the mobile terminal. The multimedia file publishing method provided in this embodiment includes the following steps.

[0024] Step 101: Obtain a multimedia file.

[0025] In this embodiment, the local multimedia files of the mobile terminal can be acquired, and the mobile terminal can be a smart phone, a tablet computer, or the like. The multimedia file can be a static picture file, a dynamic picture file, or a video file.

[0026] Step 102: Extract the key parts of the human body information displayed in the multimedia file.

[0027] In this embodiment, the key part information of the human body may be face information, iris information, ear shape information, or other information that can be identified.

[0028] In this embodiment, if the face information displayed in the multimedia file is extracted, a face detection method such as adaboost can be used to extract the face information. If the iris information or ear shape information displayed in the multimedia file is extracted, the corresponding detection method can also be used to extract the iris information or ear shape information.

[0029] In this embodiment, the multimedia file may include information about key parts of the human body of one or more people, so the key part information of the human body displayed in the extracted multimedia file may also be of one person or more than one person.

[0030] Step 103: Perform matching calculation on the key part information of the human body and the pre-stored target source image, determine the friends to be reminded, and obtain the friend information to be reminded.

[0031] In this embodiment, the target source image is stored in advance, and the target source image may be the avatars of all friends in the instant messaging tool of the mobile terminal user, or an image including the avatars of the friends. If the target source image is an image that includes an avatar of a friend, one or more friends may be included in the image.

[0032] In this embodiment, the key parts of the human body information and the pre-stored target source image can be separately extracted, and then the matching algorithm is used for matching calculation, and the correspondence between each key part information of the human body in the multimedia file and the pre-stored target source image is calculated The matching degree of the key parts, the matching degree is compared with the preset matching threshold. If it is higher than the matching threshold, it means that the key body part information matches the corresponding key body part information in a pre-stored target source image , The multimedia file contains the key body part information of a friend. If it is lower than the matching threshold, it means that the key body part information does not match the corresponding key body part information of all pre-stored target source images, and the key body part information is not the key body part information of a friend.

[0033] After matching the key part information of the human body with the pre-stored target source image, if the key part information of the human body matches the corresponding body part information in the pre-stored target source image, it is determined that the information in the multimedia file matches the target source image. The matched key body part information is the key body part information of the friend who needs to be reminded, the friend who needs to be reminded is determined according to the key body part information, and the related information of the corresponding friend is obtained.

[0034] Step 104: Publish the multimedia file, and send a message reminding to view the multimedia file to the related friend according to the information of the friend to be reminded.

[0035] In this embodiment, the multimedia file can be published in the circle of friends or group chat of the instant messaging tool, and when the multimedia file is published, a message reminding related friends to view the multimedia file is sent to related friends according to the friend information to be reminded.

[0036] In this embodiment, the friend's information may be the friend's username, email address, mobile phone number and other information that uniquely indicates the friend in the instant messaging tool.

[0037] The multimedia file publishing method provided in this embodiment includes: receiving a multimedia file sent by a mobile terminal; extracting information of key human body parts displayed in the multimedia file; performing matching calculations on the key part information of the human body with pre-stored target source images to obtain Reminder of friend information; publish the multimedia file, and send a reminder message to the relevant friend to view the multimedia file according to the friend’s information to be reminded. Because the information of the key parts of the human body in the multimedia file is matched with the image information of the friend, it can accurately remind the relevant friends to view the multimedia file, which solves the problem that the prior art cannot accurately select the friend who needs to be reminded. The multimedia file publishing efficiency With a lower problem, it is possible to accurately and intelligently select the friends who need to be reminded according to the content in the multimedia file, without the user's manual selection, which improves the publishing efficiency of the multimedia file. And it reduces user operations when users publish multimedia files, and further improves user experience.

[0038] figure 2 It is a flowchart of the second embodiment of the multimedia file publishing method of the present invention, such as figure 2 As shown, the execution subject of this embodiment is a mobile terminal or commonly used instant messaging tools such as WeChat, QQ, and Yixin installed in the mobile terminal. Therefore, the method for publishing a multimedia file provided in this embodiment is a more preferable embodiment than the first embodiment of the method for publishing a multimedia file of the present invention. The method for publishing multimedia files provided in this embodiment includes:

[0039] Step 201: Obtain a multimedia file.

[0040] Step 202: Extract the key body part information displayed in the multimedia file.

[0041] In this embodiment, the implementation of step 201 to step 202 is the same as the implementation of step 101 to step 102 in Embodiment 1 of the multimedia file publishing method of the present invention, and will not be repeated here.

[0042] Step 203: Extract key human body parts information of the target source image.

[0043] Further, in this embodiment, the pre-stored target source image is the friend's avatar or an image containing the friend's avatar. The key part information of the human body is any one of the following information: face information, iris information, and ear shape information.

[0044] In this embodiment, any key human body part information in the pre-stored target source image, iris information, and ear shape information may be extracted for matching calculation.

[0045] Step 204: Set tag information for the key body part information of the target source image.

[0046] In this embodiment, when setting the mark information for the key body part information of the target source image, such as setting mark information for the face information of the target source image, the face information of the first friend can be set as the first mark information, and the second The face information of the friend may be set as the second mark information, and the face information of the third friend may be set as the third mark information, etc. That is, the mark information set for the key body part information of different friends is different.

[0047] Step 205: Associate and store the key body part information and the tag information of the target source image with the friend information.

[0048] Further, in this embodiment, the friend's information may be the friend's username, email address, mobile phone number and other information that uniquely indicates the friend in the instant messaging tool.

[0049] In this embodiment, the key human body part information is marked in the target source image, that is, the key human body part information and the mark information in the target source image are associated and stored, and then the mark information and friend information are associated and stored through a table or other form , In order to achieve the associated storage of the key human body part information, tag information and friend information of the target source image.

[0050] In this embodiment, the key part information of the human body in the target source image has a one-to-one correspondence with the mark information, that is, one key part information of the human body can only have one mark information. The tag information and the friend information may have a one-to-one correspondence or a one-to-many relationship. If the tag information and the friend information have a one-to-one correspondence, the key body part information is the key body part information of the friend information. If the tag information and the friend information are in a one-to-many relationship, the friend information may be a mutual friend with the friend displayed in the multimedia file in addition to the friend displayed in the multimedia file. For example, a multimedia file includes the face information of "Zhang San", the mark information of the face information of "Zhang San" is "100", and the friend information stored in association with the mark information is "Zhang San" and "Li Si" ", "Li Si" is a mutual friend of "Zhang San" and the user of the instant messaging tool.

[0051] In this embodiment, if the friend information stored in association with the tag information includes multiple, the friend information can be pre-set by the user. If there is one friend information stored in association with the tag information, the friend information is in the multimedia file by default Show friend's information.

[0052] In this embodiment, step 203 to step 205 can be performed before step 201 or step 202, or can be performed after step 201 or step 202, and there is no strict time limit.

[0053] Step 206: Perform matching calculation between the key body part information and the key body part information corresponding to the target source image, and obtain label information of the corresponding part information in the target source image that matches the key body part information.

[0054] In this embodiment, feature extraction is performed on the key parts of the human body information and the key parts of the human body corresponding to the target source image, and then the matching algorithm is used for matching calculation, and the corresponding human body information of each key part of the human body in the multimedia file and the target source image is calculated. The matching degree of the key part information is compared with the preset matching threshold. If it is higher than the matching threshold, it means that the key part information of the human body corresponds to the corresponding key part information of the human body in a pre-stored target source image. Matching, so the tag information of the corresponding part information in the target source image that matches the key part information of the human body can be obtained.

[0055] Step 207: According to the tag information, obtain friend information stored in association with the tag information, and the friend information stored in association with the tag information is the friend information to be reminded.

[0056] In this embodiment, since the key body part information, tag information and friend information of the target source image are associated and stored, the friend information associated with the tag information can be obtained according to the tag information, and the friend information is the friend information that needs to be reminded . That is, the friends to be reminded are the friends displayed in the multimedia file or the common friends with the friends displayed in the multimedia file.

[0057] Step 208: Publish the multimedia file, and send a message reminding to view the multimedia file to related friends according to the friend information to be reminded.

[0058] In this embodiment, the implementation of step 208 in this embodiment is the same as the implementation of step 104 in the first embodiment of the multimedia file publishing method of the present invention, and will not be repeated here.

[0059] The multimedia file publishing method provided in this embodiment extracts the pre-stored information of the key human body parts of the target source image; sets tag information for the key human body part information of the target source image; combines the key human body part information and the tag information of the target source image Store in association with friend information. When calculating the matching calculation between the key parts of the human body and the pre-stored target source image, and obtaining the friend information that needs to be reminded, the key parts of the human body are matched with the key parts of the human body corresponding to the target source image to obtain the key parts of the human body information According to the mark information of the corresponding part information in the matched target source image, the friend information that needs to be reminded is obtained according to the mark information, which not only solves the problem of inaccurate selection of the friends who need to be reminded in the prior art, and low multimedia file publishing efficiency. It is possible to accurately and intelligently select the friends who need to be reminded according to the content in the multimedia file, without the user's manual selection, and improve the publishing efficiency of the multimedia file. Furthermore, based on the friend information stored in association, it is possible to choose to publish the multimedia file to the friend displayed in the multimedia file, or to publish the multimedia file to the mutual friend in addition to the friend, which increases the user's selectivity and further improves the user experience.

[0060] Preferably, in this embodiment, in step 208: publishing the multimedia file, and before sending a message reminding to view the multimedia file to related friends according to the information of the friend to be reminded, the method further includes: judging whether the multimedia file includes multiple needs. The key body parts information of the friend to be reminded. If the multimedia file includes the key body parts information of multiple friends who need to be reminded, insert a prompt at each key body part of the friend to be reminded displayed in the multimedia file;

[0061] Correspondingly, in step 208: publishing the multimedia file, and sending a message reminding to view the multimedia file to the relevant friend according to the information of the friend to be reminded also includes:

[0062] If it is detected that the first friend to be reminded clicks the prompt inserted in the key part of the body of the second friend to be reminded, the communication mode of the second friend to be reminded is sent to the mobile terminal of the first friend to be reminded.

[0063] Specifically, in this embodiment, if the multimedia file includes information on key human body parts of multiple friends who need to be reminded, a prompt is inserted at the key human body parts of each friend who needs to be reminded displayed in the multimedia file. The friend who needs to be reminded to prompt to open the multimedia file can click the prompt to obtain the communication method of the friend who needs to be reminded. When it is detected that the first friend to be reminded clicks the prompt inserted in the key part of the body of the second friend to be reminded, the communication method of the second friend to be reminded is sent to the mobile terminal of the first friend to be reminded.

[0064] In this embodiment, the prompt may be a small dot or a dashed box surrounding a key part of the human body or other prompts, which is not limited in this embodiment.

[0065] In this embodiment, the communication mode of the friend who needs to be reminded can be stored in association with the information of the corresponding friend. The communication method can be mobile phone number, email, etc.

[0066] In this embodiment, the first friend to be reminded and the second friend to be reminded are different friends, and the second friend to be reminded is any friend who needs to be reminded except the first friend to be reminded.

[0067] In this embodiment, a prompt is inserted into the key part of the human body of each friend who needs to be reminded displayed in the multimedia file to monitor whether the friend who needs to be reminded clicks on the corresponding prompt of other friends who need to be reminded. When the friend clicks the prompt inserted in the key part of the body of the second friend to be reminded, the communication method of the second friend to be reminded is sent to the mobile terminal of the first friend to be reminded, and the friend's communication method and image can be displayed. Correspondence enables accurate positioning between friends, reduces the link between friends to exchange communication methods, and further improves user experience.

[0068] image 3 It is a schematic structural diagram of Embodiment 1 of a multimedia file publishing apparatus of the present invention, such as image 3 As shown, the multimedia file publishing apparatus provided in this embodiment includes: an acquisition module 301, an extraction module 302, a publishing module 303, and a reminding module 304.

[0069] Among them, the obtaining module 301 is used to obtain multimedia files. The extraction module 302 is used for extracting the information of key parts of the human body displayed in the multimedia file. The obtaining module 301 is also used to perform matching calculation between the key part information of the human body and the pre-stored target source image, determine the friends to be reminded, and obtain the information of the friends to be reminded. The publishing module 303 is used to publish multimedia files. The reminding module 304 is configured to send a message reminding to view the multimedia file to the related friend according to the information of the friend to be reminded.

[0070] The multimedia file publishing device provided in this embodiment can execute figure 1 The implementation principles and technical effects of the technical solutions of the illustrated method embodiments are similar, and will not be repeated here.

[0071] Figure 4 It is a schematic structural diagram of Embodiment 2 of a multimedia file publishing apparatus according to the present invention; Figure 4 As shown, the device provided in this embodiment includes: an acquisition module 401, an extraction module 402, a publishing module 403, a reminding module 404, a setting module 405, a storage module 406, an insertion module 407, and a sending module 408.

[0072] Among them, the obtaining module 401 is used to obtain multimedia files. The extraction module 402 is used for extracting the information of the key parts of the human body displayed in the multimedia file. The obtaining module 401 is also used to perform matching calculation between the key part information of the human body and the pre-stored target source image, determine the friends to be reminded, and obtain the information of the friends to be reminded. The publishing module 403 is used to publish multimedia files. The reminder module 404 is used for sending a message reminding to view the multimedia file to the related friend according to the information of the friend to be reminded.

[0073] Further, the extraction module 402 is also used to extract information about key parts of the human body in the target source image. The setting module 405 is used to set mark information on the key parts of the human body in the target source image. The storage module 406 is used for associating and storing the key body part information and the tag information of the target source image with the friend information.

[0074] Further, the acquiring module 401 is specifically configured to: perform matching calculation between the key body part information and the key body part information corresponding to the target source image, and obtain the label information of the corresponding part information in the target source image that matches the key body part information; According to the tag information, the friend information stored in association with the tag information is obtained, and the friend information stored in association with the tag information is the friend information to be reminded.

[0075] Further, in the multimedia file publishing device provided in this embodiment, the key body part information is any one of the following information: face information, iris information, ear shape information; the target source image is a friend’s avatar or contains a friend’s avatar Image. Multimedia files include any of the following files: static picture files, dynamic picture files, and video files.

[0076] Preferably, the multimedia file publishing device provided in this embodiment further includes: an inserting module 407 and a sending module 408.

[0077] Wherein, the inserting module 407 is used for inserting prompts at the key parts of the human body of each friend to be reminded displayed in the multimedia file if the multimedia file includes information on key human body parts of multiple friends to be reminded; accordingly, The sending module 408 is used to send the communication method of the second friend to be reminded to the first friend to be reminded if it is detected that the first friend to be reminded clicks the prompt inserted in the key part of the body of the second friend to be reminded Mobile terminal.

[0078] The multimedia file publishing device provided in this embodiment can execute figure 2 The implementation principles and technical effects of the technical solutions of the illustrated method embodiments are similar, and will not be repeated here.

[0079] A person of ordinary skill in the art can understand that all or part of the steps in the foregoing method embodiments can be implemented by a program instructing relevant hardware. The aforementioned program can be stored in a readable storage medium. When the program is executed, the steps including the foregoing method embodiments are executed; and the foregoing storage medium includes: ROM, RAM, magnetic disk, or optical disk and other media that can store program codes.

[0080] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: It is still possible to modify the technical solutions described in the foregoing embodiments, or equivalently replace some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention. range.