Video ringback tone pushing method, apparatus and device, storage medium and program product

Abstract

Disclosed in the present disclosure are a video ringback tone pushing method, apparatus and device, a storage medium and a program product. The method comprises: during a call setup process, pushing a first video ringback tone to a calling user and a called user on the basis of first behavior information of the calling user and second behavior information of the called user; during an active call process, pushing a second video ringback tone to the calling user and the called user; and after the call is terminated, synchronizing tag information, which corresponds to the first video ring backtone pushed during the call setup process, and tag information, which corresponds to the second video ringback tone pushed during the active call process, to a set application program of both user terminals of the calling user and the called user, such that the set application program performs video recommendation on the basis of the tag information.

Description

Video ringtone pushing method, device, equipment, storage medium and program product

[0001] Cross-reference to Related Applications

[0002] The present application claims priority to Chinese Patent Application No. 202411151674.1 filed on August 21, 2024 in China, the contents of which are incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of video ringtone, and particularly relates to a video ringtone pushing method, device, equipment, storage medium and program product. BACKGROUND

[0004] Video ringtone is a characteristic service of Voice over Long-Term Evolution (VoLTE), which evolves "ringtone for listening" into "ringtone for watching". A user dials a voice call or a video call under the VoLTE network, and sees a video content before the call is connected. The current video ringtone is issued to the user in a one-way transmission manner, and a streaming media video is played in the early stage of the call connection. The content of the video ringtone can be pushed to the hit user group based on user portrait, group relationship, geographical location, etc.

[0005] However, the video ringtone pushing manner in the related art recommends in the granularity of an associated user group, the adaptation of the video ringtone to the individual user is low, and real-time and accurate recommendation cannot be achieved. Meanwhile, the video ringtone is only pushed to a single mobile phone screen for display, and the topic interaction between the video ringtone and the two parties of the call is poor. SUMMARY

[0006] In view of the problems in the related art, the embodiments of the present disclosure provide a video ringtone pushing method, device, equipment, storage medium and program product, which can achieve real-time and accurate video ringtone recommendation adapted to the current behavior habit of the user, and improve the topic interaction between the video ringtone and the two parties of the call.

[0007] In a first aspect, the embodiments of the present disclosure provide a video ringtone pushing method applied to a server, comprising:

[0008] In the call process, first video ringtone pushing is performed on the calling user and the called user according to first behavior information of the calling user and second behavior information of the called user;

[0009] In the call process, second video ringtone pushing is performed on the calling user and the called user;

[0010] After the call ends, the first video ringtone pushed during the call and the second video ringtone pushed during the call are synchronized to the setting application of the user terminal of the calling user and the called user, so that the setting application recommends a video according to the tag information.

[0011] Optionally, the first video ringtone pushing to the calling user and the called user according to the first behavior information of the calling user and the second behavior information of the called user comprises:

[0012] Receiving the first behavior information and the first location information reported by the user terminal of the calling user; wherein the first behavior information comprises: the calling user watching the setting target content information on the setting application for more than a preset time length or having an interactive behavior in a setting time period;

[0013] Receiving the second behavior information and the second location information reported by the user terminal of the called user; wherein the second behavior information comprises: the called user watching the setting target content information on the setting application for more than the preset time length or having an interactive behavior in the setting time period;

[0014] According to the first behavior information, the first location information, the second behavior information and the second location information, the first video ringtone of the calling user and the first video ringtone of the called user are determined, and the corresponding first video ringtone is pushed to the user terminals of the calling user and the called user respectively.

[0015] Optionally, the first video ringtone of the calling user and the first video ringtone of the called user are determined according to the first behavior information, the first location information, the second behavior information and the second location information, comprising:

[0016] Matching the first category tag corresponding to each setting target content information in the first behavior information with the second category tag corresponding to each setting target content information in the second behavior information;

[0017] When the same and / or associated second category tag as the first category tag is matched, the first video ringtone of the calling user and the first video ringtone of the called user are determined according to the first category tag and the same and / or associated second category tag as the first category tag, the first location information and the second location information.

[0018] Optionally, the first video ringtone of the calling user and the first video ringtone of the called user are determined according to the first category tag and the same second category tag as the first category tag, the first location information and the second location information, comprising:

[0019] determine a first target label according to the matched same consumption attribute label corresponding to the scenario of the first category label and the first location information;

[0020] determine at least one first video of the calling user according to the first target label;

[0021] prioritize at least one first video, and take the first video at the top of the ranking as the first video ringback tone of the calling user;

[0022] determine a second target label according to the matched same consumption attribute label corresponding to the scenario of the second category label and the second location information;

[0023] determine at least one second video of the called user according to the second target label;

[0024] prioritize at least one second video, and take the second video at the top of the ranking as the first video ringback tone of the called user.

[0025] Optionally, determining the first video ringback tone of the calling user and the first video ringback tone of the called user according to the first category label, the second category label associated with the first category label, the first location information and the second location information, comprises:

[0026] determine a third target label according to the similarity between the associated first category label and the second category label;

[0027] determine at least one third video of the calling user according to the third target label and the consumption attribute label corresponding to the scenario of the first location information;

[0028] prioritize at least one third video, and take the third video at the top of the ranking as the first video ringback tone of the calling user;

[0029] determine at least one fourth video of the called user according to the third target label and the consumption attribute label corresponding to the scenario of the second location information;

[0030] prioritize at least one fourth video, and take the fourth video at the top of the ranking as the first video ringback tone of the called user.

[0031] Optionally, the second video ringback tone pushing to the calling user and the called user comprises:

[0032] perform entity recognition on content of a call between the calling user and the called user to obtain a keyword of the content of the call;

[0033] perform sentiment analysis on the content of the call between the calling user and the called user to obtain sentiment information of the content of the call;

[0034] when the keyword belongs to a preset named entity and the sentiment information belongs to a preset positive sentiment, determine at least one fifth video according to the keyword and the sentiment information;

[0035] perform priority sorting on the at least one fifth video to obtain a first video push queue of the calling user and a second video push queue of the called user;

[0036] push a third video in the first video push queue as a second video ringtone of the calling user to a user terminal of the calling user;

[0037] push a third video in the second video push queue as a second video ringtone of the called user to a user terminal of the called user.

[0038] In a second aspect, the embodiments of the present disclosure provide a video ringtone push method applied to a user terminal, comprising:

[0039] display a first video ringtone pushed by a video ringtone platform on a user interface during a call process, wherein the first video ringtone is determined according to first behavior information of a calling user or second behavior information of a called user;

[0040] display a second video ringtone pushed by the video ringtone platform on the user interface during a through process;

[0041] after the call ends, receive label information sent by the video ringtone platform, and synchronize the label information to a set application program, so that the set application program performs video recommendation according to the label information; wherein the label information includes label information corresponding to the first video ringtone pushed during the call process and the second video ringtone pushed during the call process.

[0042] In a third aspect, the embodiments of the present disclosure provide a video ringtone push device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the video ringtone push method in any one of the first aspect or the video ringtone push method in any one of the second aspect.

[0043] In a fourth aspect, the embodiments of the present disclosure provide a computer readable storage medium storing a computer program, wherein the computer program controls a device where the computer readable storage medium is located to perform the video ringback tone pushing method according to any one of the first aspect or the video ringback tone pushing method according to any one of the second aspect when the computer program is running.

[0044] In a fifth aspect, the embodiments of the present disclosure provide a computer program product comprising computer programs / instructions, which, when executed by a processor, implement the video ringback tone pushing method according to any one of the first aspect or the video ringback tone pushing method according to any one of the second aspect.

[0045] Compared with the related art, the video ringback tone pushing method, device, equipment, storage medium and program product of the embodiments of the present disclosure can push the first video ringback tone to the calling user and the called user according to the first behavior information of the calling user and the second behavior information of the called user in the calling process, push the second video ringback tone to the calling user and the called user in the calling process, and synchronize the tag information corresponding to the first video ringback tone pushed in the calling process and the second video ringback tone pushed in the calling process to the setting application program of the user terminal of the calling user and the called user after the calling process, so that the setting application program performs video recommendation according to the tag information. The embodiments of the present disclosure can realize real-time and accurate video ringback tone recommendation adapting to the current behavior habits of the calling user and the called user, and can recommend the video ringback tone associated with the calling content of the calling user and the called user, thereby improving the topic interaction between the video ringback tone and the calling parties. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the present disclosure, the drawings used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can also be obtained by those skilled in the art without creative labor.

[0047] FIG. 1 is a flowchart of a video ringback tone pushing method according to an embodiment of the present disclosure;

[0048] FIG. 2 is an interface change diagram of the first video ringback tone playing before calling according to an embodiment of the present disclosure;

[0049] FIG. 3 is an interface change diagram of the second video ringback tone playing in calling according to an embodiment of the present disclosure;

[0050] FIG. 4 is an interface diagram of the third video ringback tone playing after calling according to an embodiment of the present disclosure;

[0051] FIG. 5 is an interactive flowchart of a video ringtone push according to an embodiment of the present disclosure;

[0052] FIG. 6 is another flowchart of a video ringtone push method according to an embodiment of the present disclosure;

[0053] FIG. 7 is a structural block diagram of a video ringtone push device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present disclosure will be clearly and completely described with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present disclosure.

[0055] It can be understood that the various numbers involved in the embodiments of the present disclosure are only for the convenience of differentiation, and do not limit the scope of the present application. The size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and inherent logic.

[0056] In the embodiments of the present disclosure, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. The terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitation, the elements defined by the statement "include" do not exclude the presence of other identical elements in the process, method, article or device including the elements. The term "a plurality of or several" means two or more. The term "at least one" means one or more. The term "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone. The character " / " generally represents an "or" relationship between the front and rear associated objects.

[0057] Referring to FIG. 1, FIG. 1 is a flowchart of a video ringtone push method according to an embodiment of the present disclosure. The video ringtone push method specifically includes:

[0058] S11: during the call process, according to the first behavior information of the calling user and the second behavior information of the called user, performing first video CRBT pushing on the calling user and the called user;

[0059] S12: during the call process, according to the first behavior information of the calling user and the second behavior information of the called user, performing first video CRBT pushing on the calling user and the called user;

[0060] S13: after the call ends, synchronizing the tag information corresponding to the first video CRBT pushed during the call process and the second video CRBT pushed during the call process to the setting application of the user terminal of the calling user and the called user, so that the setting application performs video recommendation according to the tag information.

[0061] It should be noted that the video CRBT pushing method described in the embodiments of the present disclosure can be executed by a server, which can be a video CRBT platform or a CRBT real-time decision node; wherein the CRBT real-time decision node can be a unit / module integrated in the video CRBT platform, or a third-party platform or server independent of the video CRBT platform, which is not specifically limited in the embodiments of the present disclosure. In the following, taking the CRBT real-time decision node as a third-party platform or server independent of the video CRBT platform as an example, the video CRBT pushing method described in the present disclosure is described.

[0062] When the calling user initiates a call to the called user, during the call process, the CRBT real-time decision node collects the first behavior information of the calling user on the setting application on the user terminal of the calling user and the second behavior information of the called user on the setting application on the user terminal of the called user, such as browsing / viewing content in the setting application in a short period of time, and interactive behaviors such as liking, commenting, collecting, sharing, downloading, adding to cart, etc. on the browsing / viewing content, and then determines the first video CRBT to be pushed to the user terminal of the calling user based on the first behavior information of the calling user, determines the first video CRBT to be pushed to the user terminal of the called user based on the second behavior information of the called user, and pushes the corresponding first video CRBT to the user terminals of the calling and called users through the video CRBT platform. The user terminals of the calling and called users play the corresponding first video CRBT on the user interface after receiving the first video CRBT, and the interface change of the first video CRBT before the call is shown in FIG. 2, realizing real-time accurate video CRBT recommendation adapting to the current behavior habits of the calling and called users before the call.

[0063] After the called user answers the phone, during the call, the CRBT real-time decision node identifies the call content between the calling user and the called user in real time, finds out the keywords and emotional information of the current call content, and determines at least one second video CRBT of the calling user and the called user and the order thereof based on the keywords and emotional information of the current call content; then the second video CRBT is pushed to the user terminals of the calling user and the called user in sequence through the video CRBT platform according to the order of the second video CRBT, and the user terminals of the calling user and the called user continue to play the second video CRBT on the user interface after receiving the second video CRBT and after the first video CRBT played before the call is ended, the interface change of the second video CRBT played during the call is shown in FIG. 3, so as to associate the video CRBT with the call content, recommend the video CRBT related to the topic of the call content, and improve the topic interaction between the video CRBT and the two parties of the call.

[0064] After the calling user or the called user hangs up the phone and the call is ended, the CRBT real-time decision node sends the tag information of all the first video CRBTs pushed before the call and all the second video CRBTs pushed during the call to the user terminals of the calling user and the called user; then the user terminals of the calling user and the called user synchronize the tag information to the setting application installed in the user terminals, so that the setting application in the user terminals of the calling user and the called user screens out the content with the closest tag from the content library of the setting application, and pushes the screened content to the user interface of the corresponding user terminal for playing, so as to realize the accurate recommendation of the application on the Internet side, the interface of the third video CRBT played after the call is ended is shown in FIG. 4, and the cross-screen transmission of the browsing content / viewing content of the calling user and the called user and the extension of the call topic can be realized after the call is ended.

[0065] It should be noted that the user terminal can be a terminal device with a mobile communication function and a video playing function, such as a mobile phone, a tablet computer, a smart watch, etc., which is not specifically limited in the embodiments of the present disclosure.

[0066] Optionally, the first video CRBT pushing to the calling user and the called user according to the first behavior information of the calling user and the second behavior information of the called user comprises:

[0067] receiving the first behavior information and the first location information reported by the user terminal of the calling user; wherein the first behavior information comprises: the set target content information watched by the calling user on the setting application for more than a preset time length or with an interactive behavior in a set time period;

[0068] receive second behavior information and second location information reported by the user terminal of the called user; wherein the second behavior information comprises: set target content information of the called user on the set application program in the set time period and watching the preset time length or having an interactive behavior;

[0069] determine the first video ringtone of the calling user and the first video ringtone of the called user according to the first behavior information, the first location information, the second behavior information and the second location information, and push the corresponding first video ringtone to the user terminals of the calling user and the called user respectively.

[0070] Exemplarily, the set application program (such as live broadcast, short video, shopping application program) of the user terminal and the ringtone real-time decision node are pre-established with a reporting mechanism, when it is monitored that the reporting condition is met, the set target content information (such as video, live broadcast, commodity information content, which is not limited in the embodiment of the present disclosure) meeting the reporting condition is reported to the ringtone real-time decision node by the preset application program of the user terminal. Wherein, the reporting condition is that the watching / page staying time of the set target content information exceeds the preset time length or has the interactive behavior of liking, commenting, collecting, sharing, downloading, adding shopping, etc. in the set time period from the current time.

[0071] Before the call, the user terminal will report its own location information to the ringtone real-time decision node, such as the user terminal of the calling user reporting its own first location information, and the user terminal of the called user reporting its own second location information. Then the ringtone real-time decision node makes a first video ringtone decision for the calling user and the called user according to the first behavior information (i.e. the set target content information meeting the reporting condition) and the first location information of the calling user, and the second behavior information (i.e. the set target content information meeting the reporting condition) and the second location information of the called user, and pushes the first video ringtone of the calling user and the first video ringtone of the called user to the user terminals of the calling user and the called user respectively, so as to realize real-time and accurate video ringtone recommendation based on the behavior habits of the calling user and the called user in a short time.

[0072] It should be noted that the present embodiment does not make specific limitation on the value of the set time period and the preset time length, for example, the set time period can be 24 hours, 48 hours, 72 hours, etc., and the preset time length can be 15s, 30s, 40s, etc.

[0073] Optionally, the determining the first video ringtone of the calling user and the first video ringtone of the called user according to the first behavior information, the first location information, the second behavior information and the second location information comprises:

[0074] matching a first category label corresponding to each of the set target content information in the first behavior information with a second category label corresponding to each of the set target content information in the second behavior information;

[0075] when a second category label same as and / or associated with the first category label is matched, determining the first video ringtone of the calling user and the first video ringtone of the called user according to the first category label and the second category label same as and / or associated with the first category label, the first location information and the second location information.

[0076] In one embodiment, determining the first video ringtone of the calling user and the first video ringtone of the called user according to the first category label and the second category label same as the first category label, the first location information and the second location information comprises:

[0077] for the matched first category label and the second category label same as the first category label, determining a first target label according to a consumption attribute label in a scene corresponding to the first category label and the first location information;

[0078] determining at least one first video of the calling user according to the first target label;

[0079] prioritizing the at least one first video and taking the first video at the top of the priority as the first video ringtone of the calling user;

[0080] determining a second target label according to a consumption attribute label in a scene corresponding to the second category label and the second location information;

[0081] determining at least one second video of the called user according to the second target label;

[0082] prioritizing the at least one second video and taking the second video at the top of the priority as the first video ringtone of the called user.

[0083] Further, determining the first target label according to the consumption attribute label in the scene corresponding to the first category label and the first location information comprises:

[0084] performing similarity matching between the consumption attribute label in the scene corresponding to the first category label and the first location information;

[0085] when there is a consumption attribute label with a similarity greater than a first similarity threshold to the first category label in a scenario corresponding to the first location information, taking the consumption attribute label with the similarity greater than the first similarity threshold to the first category label as the first target label;

[0086] when there is no consumption attribute label with a similarity greater than the first similarity threshold to the first category label in a scenario corresponding to the first location information, taking the first category label as the first target label.

[0087] Similarly, determining the first video ringtone of the calling user and the first video ringtone of the called user according to the first category label, the second category label associated with the first category label, the first location information, and the second location information includes:

[0088] for the matched associated first category label and second category label, determining a third target label according to the similarity between the associated first category label and second category label;

[0089] determining at least one third video of the calling user according to the third target label and a consumption attribute label in a scenario corresponding to the first location information;

[0090] prioritizing at least one third video, and taking the third video at the top of the priority as the first video ringtone of the calling user;

[0091] determining at least one fourth video of the called user according to the third target label and a consumption attribute label in a scenario corresponding to the second location information;

[0092] prioritizing at least one fourth video, and taking the fourth video at the top of the priority as the first video ringtone of the called user.

[0093] determining at least one third video of the calling user according to the third target label and a consumption attribute label in a scenario corresponding to the first location information includes:

[0094] performing similarity matching between the third target label and a consumption attribute label in a scenario corresponding to the first location information;

[0095] when there is a consumption attribute label with a similarity greater than a first similarity threshold to the third target label in a scenario corresponding to the first location information, determining at least one third video of the calling user according to the consumption attribute label with the similarity greater than the first similarity threshold to the third target label;

[0096] when the scene corresponding to the first location information does not exist a consumption attribute label with a similarity to the third target label greater than the first similarity threshold, determining at least one third video of the calling user according to the first category label.

[0097] determining the third target label according to the similarity between the associated first category label and the second category label, comprising:

[0098] calculating the similarity between the associated first category label and the second category label, and taking the first category label and the second category label with a similarity greater than a preset fourth similarity threshold as the third target label.

[0099] Exemplarily, the decision and issuing process of the first video ringtone of the calling and called users is as follows: after the calling user's reported set target content information and first location information satisfying the reporting condition and the called user's reported set target content information and second location information satisfying the reporting condition are received by the ringtone real-time decision node, the above information is preprocessed, wherein the preprocessing includes but is not limited to data cleaning, feature extraction, etc. Then the set target content information of the calling and called users after preprocessing is classified, and the first category label to which the set target content information of the calling user belongs and the second category label to which the set target content information of the called user belongs are determined; then the above first category label and second category label are matched to determine whether there is a second category label identical and / or associated with the first category label. Wherein, the Jaccard similarity coefficient between the first category label and the second category label can be calculated as the similarity between the first category label and the second category label, when the similarity between the first category label and the second category label is greater than the second similarity threshold, it is determined that the first category label and the second category label exist the same / overlap, triggering the first video ringtone pushing condition; when the similarity between the first category label and the second category label is not greater than the second similarity threshold but greater than the third similarity threshold, it is determined that the first category label and the second category label exist the association, also triggering the first video ringtone pushing condition.

[0100] Meanwhile, the first location information and the second location information are converted into longitude and latitude coordinates, and the position corresponding to the longitude and latitude coordinates of the calling and called users in the electronic map is determined, and it is judged whether there is a scene with obvious consumption attribute (such as shopping mall, restaurant, bar, etc.) in the set range of the calling and called users with the corresponding longitude and latitude coordinates as the center.

[0101] It should be noted that the values of the second similarity threshold and the third similarity threshold are not specifically limited in the embodiments of the present disclosure, and the user can set them as needed; for example, the first similarity threshold can be 90%, and the second similarity threshold can be 70%.

[0102] When the first video ringtone pushing condition is triggered, if there are the same first category label and second category label, if there is a scene with obvious consumption attribute in the set range of the caller user with the corresponding latitude and longitude coordinate as the center, a consumption attribute label (such as the type of goods sold, the brand, etc.) with a similarity greater than the first similarity threshold between the first category label and the scene is screened out, and at least one first video is generated in real time using the consumption attribute label or at least one first video corresponding to the consumption attribute label is screened out from the video ringtone library, as the first video ringtone of the caller user; if there is no scene with obvious consumption attribute in the set range of the caller user with the corresponding latitude and longitude coordinate as the center, the influence of the geographical location of the caller user is ignored, and at least one first video is generated in real time using the first category label or at least one first video corresponding to the first category label is screened out from the video ringtone library, as the first video ringtone of the caller user. It should be understood that the second video generation and screening process of the called user is the same as the first video generation and screening process of the caller user described above, and will not be repeated here.

[0103] It should be noted that the value of the first similarity threshold is not specifically limited in the embodiments of the present disclosure, and the user can set it as needed; for example, the first similarity threshold can be 80%.

[0104] When the first video ringtone pushing condition is triggered, if there are the same first category label and second category label, first, the similarity between the vectors of the associated first category label and second category label is calculated; then the similarity of the semantic and syntactic characteristics between the two labels is captured according to the similarity; for example, the meaning of each first category label and consumption attribute label is analyzed using natural language processing technology, specifically, the first category label and the second category label are converted into vectors through a word embedding (Word Embedding) model, then the similarity between the vector of the first category label and the vector of the second category label is calculated, and the vector of the first category label and the second category label with a similarity greater than the fourth similarity threshold are screened out as the third target label.

[0105] When there is a scene with obvious consumption attributes within the set range of the corresponding latitude and longitude coordinates of the calling user, consumption attribute tags (such as the types of goods sold, brands, etc.) with a similarity greater than the first similarity threshold are screened out between the third target tag and the scene, and at least one third video is generated in real time using the consumption attribute tag or at least one third video corresponding to the consumption attribute tag is screened from the video ringback tone library as the first video ringback tone of the calling user. If there is no scene with obvious consumption attributes within the set range of the corresponding latitude and longitude coordinates of the calling user, the influence of the geographical location of the calling user is ignored, and at least one third video is generated in real time using the first category tag or at least one third video corresponding to the first category tag is screened from the video ringback tone library as the first video ringback tone of the calling user. It should be understood that the fourth video generation and screening process of the called user is the same as the third video generation and screening process of the calling user described above, and will not be repeated here.

[0106] It should be noted that the value of the fourth similarity threshold is not specifically limited in the embodiments of the present disclosure, and the user can set it as needed; for example, the fourth similarity threshold can be 80%. The word embedding model can use existing Word2Vec, GloVe or BERT model, etc., which is not specifically limited in the embodiments of the present disclosure.

[0107] The ringback tone real-time decision node takes the at least one first video or the at least one third video determined above as the push video content range of the first video ringback tone of the calling user, and performs push priority sorting of the first video or the second video of the calling user, takes the at least one second video or the at least one fourth video as the push video content range of the first video ringback tone of the called user, and performs push priority sorting of the second video or the fourth video of the called user to complete the recall and sorting of the first video ringback tone.

[0108] Among them, the priority of different tags can be preset, and then the corresponding first video or second video (second video or fourth video) is sorted according to the priority of the tag to which the first video or third video (second video or fourth video) belongs. It should be understood that since the behavior habits of the called user in a short period of time for the set application program and the behavior habits of the calling user in a short period of time for the set application program can be different, the second video or fourth video of the called user screened out is different from the first video or third video of the calling user, and the priority sorting of the first video ringback tone of the called user is different from the priority sorting of the first video ringback tone of the calling user, and the first video ringback tone of the called user recommended by the subsequent ringback tone real-time decision node is also different from the first video ringback tone of the calling user.

[0109] The color ring real-time decision node pushes the first video or the third video ranked first based on the priority ranking result to the video color ring platform. The video color ring platform pushes the received first video or third video as the first video color ring to the user terminal of the calling user to play the first video color ring on the user interface of the user terminal of the calling user. The first video color ring pushing of the called party user is the same, which is not repeated here.

[0110] In the embodiments of the present disclosure, before the call, based on the common behavior habits of the calling party and the called party in the short term, combined with the geographical position, when the behavior habit similarity overlaps or has similarity, the video color ring platform pushes the first video color ring of the same type (i.e. the type of video corresponding to the common behavior habit) but different pictures for the calling party and the called party, increases the exposure of the same type of video color ring in a limited time, realizes real-time accurate video color ring recommendation before the call.

[0111] Optionally, the second video color ring pushing to the calling user and the called user comprises:

[0112] Performing entity recognition on the call content between the calling user and the called user to obtain keywords of the call content;

[0113] Performing sentiment analysis on the call content between the calling user and the called user to obtain sentiment information of the call content;

[0114] When the keywords belong to a preset named entity and the sentiment information belongs to a preset positive sentiment, determining at least one fifth video according to the keywords and the sentiment information;

[0115] Prioritizing at least one fifth video to obtain a first video pushing queue of the calling user and a second video pushing queue of the called user;

[0116] Pushing a third video in the first video pushing queue as a second video color ring of the calling user to the user terminal of the calling user;

[0117] Pushing a third video in the second video pushing queue as a second video color ring of the called user to the user terminal of the called user.

[0118] Exemplarily, after the called user answers the phone, the color ring real-time decision node extracts and analyzes the call content, and pushes a second video color ring to the calling and called parties based on the analysis result. Specifically, the color ring real-time decision node first converts the call content of the current round into text, decomposes the text into words or phrases, identifies entities (such as names, places, brands, and product categories) and parts of speech (such as nouns, verbs, and adjectives) in the text, and performs sentiment analysis on the text to analyze whether it belongs to positive, negative, or neutral sentiment. When the preset named entity, such as brand name, star (name), product name, and place, is hit, and the text has positive sentiment, the second video color ring push to the calling and called parties is triggered.

[0119] After triggering the second video color ring push, the color ring real-time decision node generates content in real time or selects video content from the video color ring library according to the identified entities and sentiment information of the call content, obtains at least one fifth video, and sorts the fifth videos according to the different push priorities of the calling and called parties to obtain a first video push queue of the calling party and a second video push queue of the called party.

[0120] Among them, the priorities of different labels of the calling and called parties can be preset, and then the calling and called parties are sorted according to the priorities of the labels to which the fifth videos belong.

[0121] The color ring real-time decision node pushes the fifth videos to the video color ring platform in turn based on the first video push queue of the calling party, and pushes the fifth videos to the video color ring platform in turn based on the second video push queue of the called party. Then the video color ring platform sends the fifth videos in the corresponding queue to the calling and called parties as the second video color ring, so that the calling and called parties can continue to see the second video color ring of the same type but different pictures on the screen of the user terminal after watching the first video color ring.

[0122] The second video color ring play rules of the user terminals of the calling and called parties are the same, and are as follows:

[0123] After the first video color ring is played, the video color ring platform pushes multiple second video color rings to the user interface for cyclic playing.

[0124] Further, the cyclic playing of the multiple second video color rings pushed by the video color ring platform after the first video color ring is played includes:

[0125] After the first video color ring is played, the video color ring platform pushes multiple second video color rings to the user interface for cyclic playing.

[0126] When the call is not ended within the set time before the end of the first pushed multiple second video ringtones, after the end of the first pushed multiple second video ringtones, the next pushed multiple second video ringtones are played in sequence on the user interface until the end of the playing of all the second video ringtones pushed by the video ringtone platform;

[0127] When the call is not ended after the end of the playing of all the second video ringtones pushed by the video ringtone platform, all the second video ringtones pushed by the video ringtone platform are played repeatedly on the user interface.

[0128] Taking the calling user as an example, the playing rules of the second video ringtones are as follows:

[0129] The first video push queue is first issued by the ringtone real-time decision node, and the fifth video in positions 1-5 is pushed to the user terminal in sequence by the video ringtone platform. The user terminal first continues to play the first video ringtone played before the call is connected, and then plays the fifth video in position 1 from the beginning after the first video ringtone is played, and then plays the fifth videos in positions 1-5 in sequence. When the fifth video in position 5 is about to end, the ringtone real-time decision node is triggered by the video ringtone platform, the fifth video in positions 6-10 in the first video push queue is pushed to the user terminal in sequence by the video ringtone platform, and the user terminal plays the fifth video in position 6 from the beginning after the fifth video in position 5 is played, and then plays the fifth videos in positions 6-10 in sequence. The subsequent is similar, and the playing of the fifth videos in the first video push queue is completed.

[0130] When the playing of the fifth videos in the first video push queue is completed, and the call is not ended, and the call topic is not changed, the fifth video in position 1 in the first video push queue is played in sequence. If the call topic is switched, the fifth video in position 1 in the first video push queue is played in sequence according to the new call topic.

[0131] It should be understood that when the entity and emotion information corresponding to the call content changes, it can be understood that the call topic is switched, and accordingly, the first video push queue generated based on the entity and emotion information of the call content will also change.

[0132] After the calling user or the called user hangs up the phone and the call ends, the video ringback platform synchronizes the tag information of the first video ringback pushed before the call and the second video ringback pushed during the call and the call end time to the user terminal, and the user terminal synchronizes the tag information to the set application program (such as an Internet application program, a shopping application program, a news application program, etc.) installed in the user terminal. Based on the tag information, the set application program matches the closest video / page content in its own content library, so that when the calling user uses the set application program within a certain time (such as within 24 hours after the call ends), the matched video / page content is pushed to the user interface for display, thereby strengthening the promotion effect and accurate pushing of the video ringback content.

[0133] The overall interaction process of the video ringback pushing will be described in detail below in combination with FIG. 5, and the specific process is as follows:

[0134] Step 1: The calling user A initiates a call to the called user B;

[0135] Step 2: The ringback real-time decision node pushes the first video ringback to the video ringback platform; wherein the first video ringback is recommended in real time according to the video / live broadcast / goods information browsed by the calling user and the called user and the current positions of the calling user and the called user;

[0136] Step 3a: The video ringback platform issues the first video ringback to the user terminal of the calling user A;

[0137] Step 3b: The video ringback platform issues the first video ringback to the user terminal of the calling user B;

[0138] Step 4a: The user terminal of the calling user A plays the first video ringback;

[0139] Step 4b: The user terminal of the calling user A plays the first video ringback;

[0140] Step 5: The called user B answers the call;

[0141] Step 6: The ringback real-time decision node pushes the second video ringback to the video ringback platform; wherein the second video ringback is recommended in real time according to the call content of the calling user and the called user;

[0142] Step 7a: The video ringback platform issues the second video ringback to the user terminal of the calling user A in multiple paths;

[0143] Step 7b: The video ringback platform issues the second video ringback to the user terminal of the calling user B in multiple paths;

[0144] Step 8a: The user terminal of the calling user A continues to play the first video ringback, and after the first video ringback is played, the second video ringback in the queue is played in sequence;

[0145] Step 8b: the user terminal of the calling user B continues to play the first video ringtone, and after the first video ringtone is played, the second video ringtone in the queue is played in sequence;

[0146] Step 9: the call ends, and the video ringtone platform synchronizes the tag information and the call end time of the first video ringtone and the second video ringtone to the user terminals of the calling user and the called user;

[0147] Step 10: the user terminals of the calling user and the called user synchronize the tag information and the call end time of the first video ringtone and the second video ringtone to the setting application;

[0148] Step 11: the setting application matches the closest content in the content library according to the tag information, and pushes the content to the user terminals of the calling user and the called user after the call ends.

[0149] Compared with the related art, the embodiments of the present disclosure push the video ringtone based on the common behavior habits and geographical positions of the calling user and the called user in a short period before the call, push the video ringtones with similar types but different pictures to the calling user and the called user with distinction when the similarity of the behavior habits of the calling user and the called user overlaps or has similarity, push the video ringtones with similar types but different pictures to the calling user and the called user with distinction based on the call content of the calling user and the called user when the preset named entity is hit and the call content has positive emotion, synchronize the video ringtones pushed before the call and during the call to various setting applications, and when the calling user and the called user use the setting application in a certain period of time, filter out the video similar to the video ringtones pushed before the call and during the call from the content library, and push the video to the content recommendation waterfall flow, which can realize the real-time and accurate video ringtone recommendation adapting to the current behavior habits of the calling user and the called user, and can recommend the video ringtone associated with the call content of the calling user and the called user, improve the topic interaction between the video ringtone and the calling user and the called user, realize the cross-screen transmission of the similar video content, and create the scalable and common-topic video ringtone media service.

[0150] Referring to FIG. 6, FIG. 6 is another flowchart of a video ringtone pushing method provided by the embodiments of the present disclosure. The video ringtone pushing method is applied to a user terminal, and specifically includes:

[0151] S21: in a calling process, a first video ringtone pushed by a video ringtone platform is displayed on a user interface; wherein the first video ringtone is determined according to first behavior information of a calling user or second behavior information of a called user;

[0152] S22: in a calling process, a second video ringtone pushed by the video ringtone platform is displayed on the user interface;

[0153] S23: receiving label information sent by the video ringback platform after the call ends, and synchronizing the label information to a set application program, so that the set application program recommends a video according to the label information; wherein the label information includes label information corresponding to a first video ringback pushed in a calling process and a second video ringback pushed in a calling process.

[0154] In an optional embodiment, the displaying of the second video ringback pushed by the video ringback platform on the user interface comprises:

[0155] After the playing of the first video ringback ends, the video ringback platform pushes a plurality of the second video ringbacks on the user interface in a loop.

[0156] In an optional embodiment, the playing of the plurality of the second video ringbacks pushed by the video ringback platform on the user interface in a loop after the playing of the first video ringback ends comprises:

[0157] After the playing of the first video ringback ends, the video ringback platform pushes a plurality of the second video ringbacks on the user interface in a loop.

[0158] When the call does not end within a set time before the playing of the plurality of the second video ringbacks pushed for the first time ends, after the playing of the plurality of the second video ringbacks pushed for the first time ends, the video ringback platform pushes a plurality of the second video ringbacks for the next time on the user interface in a loop until the playing of all the second video ringbacks pushed by the video ringback platform ends.

[0159] When the call does not end after the playing of all the second video ringbacks pushed by the video ringback platform ends, the video ringback platform repeatedly plays all the second video ringbacks on the user interface.

[0160] It should be noted that the working process of the video ringback push method applied to a user terminal in the embodiments of the present disclosure can refer to the working process of the video ringback push method applied to a video ringback platform or a ringback real-time decision node in the above-mentioned embodiments, and the technical effects achieved are the same as those of the video ringback push method applied to a video ringback platform or a ringback real-time decision node in the above-mentioned embodiments, which will not be described herein again.

[0161] Referring to FIG. 7, FIG. 7 is a structural block diagram of a video ringback push device provided by the embodiments of the present disclosure. The video ringback push device comprises a processor 11, a memory 12, and a computer program stored in the memory 12 and executable on the processor 11. The processor 11 implements the steps in the above-mentioned various video ringback push method embodiments, such as steps S11-S13 or steps S21-S23, when executing the computer program.

[0162] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 11 to complete the present disclosure. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the video ringtone pushing device.

[0163] The video ringtone pushing device can include, but is not limited to, the processor 11, the memory 12. Those skilled in the art can understand that the schematic diagram is only an example of the video ringtone pushing device, and does not constitute a limitation on the video ringtone pushing device, and can include more or less components than the diagram, or combine certain components, or different components, for example, the video ringtone pushing device can also include an input / output device, a network access device, a bus, etc.

[0164] The processor 11 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The processor 11 is the control center of the video ringtone pushing device, which connects various parts of the entire video ringtone pushing device through various interfaces and lines.

[0165] The memory 12 can be used to store the computer programs and / or modules, and the processor 11 realizes various functions of the video ringback push device by running or executing the computer programs and / or modules stored in the memory 12, and calling the data stored in the memory 12. The memory 12 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), and the like. In addition, the memory 12 can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0166] When the modules / units of the video ringback push device are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the processor 11 executes the computer program, the steps of the above-mentioned various method embodiments can be realized. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0167] It should be noted that the working process of the video ringback push device described in the embodiments of the present disclosure can refer to the working process of the video ringback push method described in the above-mentioned embodiments, and the technical effects achieved are the same as those of the video ringback push method described in the above-mentioned embodiments, which will not be described here.

[0168] It should be noted that the apparatus embodiments described above are merely illustrative, and the units described as separate units can or can not be physically separate, and the units displayed as units can or can not be physical units, i.e. can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. In addition, the connection relationship between the modules in the apparatus embodiment provided by the present disclosure indicates that there is a communication connection between them, which can be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0169] The above is the preferred embodiment of the present disclosure, and it should be noted that those skilled in the art can make many improvements and refinements without departing from the principles of the present disclosure, and these improvements and refinements are also considered within the protection scope of the present disclosure.

Claims

1. A video ringtone pushing method applied to a server, the method comprising: pushing a first video ringtone to a calling user and a called user according to first behavior information of the calling user and second behavior information of the called user during a call process; pushing a second video ringtone to the calling user and the called user during a call process; synchronizing tag information corresponding to the first video ringtone pushed during the call process and the second video ringtone pushed during the call process to a setting application program of a user terminal of the calling user and the called user after the call process, so that the setting application program recommends a video according to the tag information.

2. The video ringtono push method of claim 1, wherein, The pushing of the first video ringtone to the calling user and the called user according to the first behavior information of the calling user and the second behavior information of the called user comprises: receiving first behavior information and first location information reported by a user terminal of the calling user; wherein the first behavior information comprises: set target content information watched by the calling user on a setting application program for more than a preset time length or with an interactive behavior in a set time period; receiving second behavior information and second location information reported by a user terminal of the called user; wherein the second behavior information comprises: set target content information watched by the called user on the setting application program for the preset time length or with the interactive behavior in the set time period; determining a first video ringtone of the calling user and a first video ringtone of the called user according to the first behavior information, the first location information, the second behavior information and the second location information, and pushing corresponding first video ringtones to the user terminals of the calling user and the called user respectively.

3. The video ringtono push method of claim 2, wherein, The determination of the first video ringtone of the calling user and the first video ringtone of the called user according to the first behavior information, the first location information, the second behavior information and the second location information comprises: matching first category tags corresponding to each set target content information in the first behavior information with second category tags corresponding to each set target content information in the second behavior information; when matching to a second category tag same as and / or associated with the first category tag, determining the first video ringtone of the calling user and the first video ringtone of the called user according to the first category tag and the second category tag same as and / or associated with the first category tag, the first location information and the second location information.

4. The video ringtono push method of claim 3, wherein, The determination of the first video ringtone of the calling user and the first video ringtone of the called user according to the first category tag and the second category tag same as the first category tag, the first location information and the second location information comprises: determining a first target tag according to a consumption attribute tag in a scene corresponding to the matched first category tag and the first location information; determining at least one first video of the calling user according to the first target tag. prioritizing at least one of the first videos, and taking the first video at the top of the priority as the first video ringback tone of the calling user; determining a second target label according to the matched consumption attribute label in the scenario corresponding to the second location information and the second category label; determining at least one second video of the called user according to the second target label; prioritizing at least one of the second videos, and taking the second video at the top of the priority as the first video ringback tone of the called user.

5. The video ringtono push method of claim 3, wherein, determining the first video ringback tone of the calling user and the first video ringback tone of the called user according to the first category label, the second category label associated with the first category label, the first location information and the second location information, including: determining a third target label according to the similarity between the associated first category label and second category label; determining at least one third video of the calling user according to the third target label and the consumption attribute label in the scenario corresponding to the first location information; prioritizing at least one of the third videos, and taking the third video at the top of the priority as the first video ringback tone of the calling user; determining at least one fourth video of the called user according to the third target label and the consumption attribute label in the scenario corresponding to the second location information; prioritizing at least one of the fourth videos, and taking the fourth video at the top of the priority as the first video ringback tone of the called user.

6. The video ringtono push method of claim 2, wherein, The second video ringback tone pushing to the calling user and the called user includes: performing entity recognition on the call content between the calling user and the called user to obtain keywords of the call content; performing sentiment analysis on the call content between the calling user and the called user to obtain sentiment information of the call content; when the keywords belong to a preset named entity and the sentiment information belongs to a preset positive sentiment, determining at least one fifth video according to the keywords and the sentiment information; prioritizing at least one of the fifth videos to obtain a first video pushing queue of the calling user and a second video pushing queue of the called user; taking the third video in the first video pushing queue as the second video ringback tone of the calling user, and pushing to the user terminal of the calling user; taking the third video in the second video pushing queue as the second video ringback tone of the called user, and pushing to the user terminal of the called user.

7. A video ringback tone pushing method applied to a user terminal, the method comprising: displaying a first video ringback tone pushed by a video ringback tone platform on a user interface during a calling process; wherein the first video ringback tone is determined according to first behavior information of a calling user or second behavior information of a called user; displaying a second video ringback tone pushed by the video ringback tone platform on the user interface during a through process; After the call ends, label information sent by the video ringback platform is received, and the label information is synchronized to a set application program, so that the set application program performs video recommendation according to the label information; wherein the label information includes label information corresponding to a first video ringback pushed in a calling process and a second video ringback pushed in a calling process.

8. A video ringtones push device, comprising: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the video ringback pushing method according to any one of claims 1 to 6 or the video ringback pushing method according to claim 7 when executing the computer program.

9. A computer-readable storage medium storing a computer program, wherein, The computer readable storage medium is controlled to perform the video ringback pushing method according to any one of claims 1 to 6 or the video ringback pushing method according to claim 7 when the computer program is running.

10. A computer program product, comprising computer programs / instructions, which, when executed by a processor, implement the video ringback pushing method according to any one of claims 1 to 6 or the video ringback pushing method according to claim 7.

Images