A video ringback tone recommendation method, device, equipment and readable storage medium

Abstract

The present invention provides a method, device, equipment and readable storage medium for recommending video ringback tone, wherein the method for recommending video ringback tone includes: obtaining strategy reference information related to a first user; determining the viewing probability and interest type of the first user for the video ringback tone according to the strategy reference information; recommending the video ringback tone to the target user according to the viewing probability and interest type; wherein the strategy reference information includes at least one of the following: a first duration, an average waiting duration, the identity information of the first user, the identity information of a second user communicating with the first user, and the type of video ringback tone played by the first terminal of the first user. This solution can realize differentiated ringback tone promotion based on the viewing probability and interest type of the user for the video ringback tone, improve the promotion accuracy and success rate, and well solve the problem of low accuracy of the video ringback tone promotion solution in the prior art.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a video ringback tone recommendation method, device, equipment and readable storage medium. Background Art

[0002] At present, existing video ringtone promotion plans often determine user preferences based on user browsing history, and then recommend video ringtones based on user preferences. For example, when a user browses a video ringtone page, the APP can determine the user's favorite singer based on the user's browsing history, and then use a recommendation algorithm to push some video ringtones containing the singer to the user; or, the promotion is carried out by operators selecting potential users and sending text messages in batches.

[0003] However, this current promotion method generally requires users to have some basic conditions, such as having installed a specific APP, or having watched video ringtones before. For users who have never been exposed to video ringtones or have not installed related APPs, it is impossible to obtain the user's preferences and therefore impossible to carry out accurate ringtone promotion for these user groups, which greatly affects the promotion efficiency of video ringtones.

[0004] As described above, the solutions for promoting video ringback tone in the prior art have problems such as low accuracy. Summary of the invention

[0005] The object of the present invention is to provide a video ring back tone recommendation method, device, equipment and readable storage medium to solve the problem of low accuracy of video ring back tone promotion scheme in the prior art.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a video ringback tone recommendation method, including:

[0007] Obtaining policy reference information related to the first user;

[0008] Determining, according to the policy reference information, a viewing probability and an interest type of the first user for the video ringback tone;

[0009] Recommending video ringback tones to target users according to the viewing probability and interest type;

[0010] The policy reference information includes at least one of the following: a first duration, an average waiting duration, identity information of the first user, identity information of a second user communicating with the first user, and a type of video ringback tone played by a first terminal of the first user;

[0011] The first duration is the duration from when the first user triggers a call to when the first terminal is placed in a receiving position;

[0012] The average waiting time is the time interval from when the first user triggers a call to when the call is connected;

[0013] The target user includes: at least one of the first user and a third user communicating with the first user.

[0014] Optionally, the recommending a video ringback tone to a target user according to the viewing probability and the interest type includes:

[0015] When the viewing probability is greater than or equal to the viewing threshold, recommending, according to the interest type, a video ringback tone matching the interest type to the first user and a third user whose association coefficient with the first user is greater than the association threshold;

[0016] When the viewing probability is less than a viewing threshold, a video ringback tone matching the interest type is recommended to the first user according to the interest type.

[0017] Optionally, the video ringback tone recommended to the target user carries at least one of ringback tone recommendation information and a video ringback tone subscription link.

[0018] Optionally, also include:

[0019] During the video ringback tone playing process, when the target user places the corresponding terminal in the answering position, triggering the corresponding terminal to execute the first reminder mode;

[0020] Wherein, the first reminder method includes: at least one of a voice method and a vibration method.

[0021] Optionally, determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information includes:

[0022] When the amount of the policy reference information related to the first user reaches a quantity threshold, the viewing probability and interest type of the first user for the video ringback tone are determined according to the policy reference information.

[0023] Optionally, after determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information, the method further includes:

[0024] Continue to obtain policy reference information related to the first user;

[0025] When the first condition is met, updating the viewing probability and the interest type according to at least a portion of the acquired strategy reference information;

[0026] Recommending video ringback tones to target users according to the updated viewing probability and interest type;

[0027] The first condition includes at least one of the following:

[0028] The time interval between the current time and the time when the viewing probability and the interest type were last determined reaches the interval threshold;

[0029] The amount of the policy reference information that continues to be obtained reaches a newly added threshold.

[0030] Optionally, determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information includes:

[0031] Determining, according to the policy reference information, the first user's interest type and initial viewing probability for the video ringback tone;

[0032] The recommending video ringback tone to the target user according to the viewing probability and the interest type includes:

[0033] Obtaining a final viewing probability according to the correction factor and the initial viewing probability;

[0034] According to the final viewing probability and interest type, a video ringback tone is recommended to the target user.

[0035] Optionally, the correction factor is determined based on the first information;

[0036] The first information includes at least one of: the interval between the current time and the last time a video ringback tone was recommended to the target user, and the number of times the video ringback tone was recommended to the target user within a first time period.

[0037] The embodiment of the present invention further provides a video ring back tone recommendation device, comprising:

[0038] A first acquisition module, used to acquire policy reference information related to the first user;

[0039] A first determination module, configured to determine the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information;

[0040] A first recommendation module, configured to recommend video ringback tones to target users according to the viewing probability and interest type;

[0041] The policy reference information includes at least one of the following: a first duration, an average waiting duration, identity information of the first user, identity information of a second user communicating with the first user, and a type of video ringback tone played by a first terminal of the first user;

[0042] The first duration is the duration from when the first user triggers a call to when the first terminal is placed in a receiving position;

[0043] The average waiting time is the time interval from when the first user triggers a call to when the call is connected;

[0044] The target user includes: at least one of the first user and a third user communicating with the first user.

[0045] Optionally, the recommending a video ringback tone to a target user according to the viewing probability and the interest type includes:

[0046] When the viewing probability is greater than or equal to the viewing threshold, recommending, according to the interest type, a video ringback tone matching the interest type to the first user and a third user whose association coefficient with the first user is greater than the association threshold;

[0047] When the viewing probability is less than a viewing threshold, a video ringback tone matching the interest type is recommended to the first user according to the interest type.

[0048] Optionally, the video ringback tone recommended to the target user carries at least one of ringback tone recommendation information and a video ringback tone subscription link.

[0049] Optionally, also include:

[0050] A first triggering module is used to trigger the corresponding terminal to execute a first reminder mode when the target user places the corresponding terminal in a listening position during the video ringback tone playback process;

[0051] Wherein, the first reminder method includes: at least one of a voice method and a vibration method.

[0052] Optionally, determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information includes:

[0053] When the amount of the policy reference information related to the first user reaches a quantity threshold, the viewing probability and interest type of the first user for the video ringback tone are determined according to the policy reference information.

[0054] Optionally, also include:

[0055] A second acquisition module is used to continue to acquire the policy reference information related to the first user after determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information;

[0056] A first updating module, configured to update the viewing probability and the interest type according to at least a portion of the acquired strategy reference information when a first condition is met;

[0057] A second recommendation module, configured to recommend video ringback tones to target users according to the updated viewing probability and interest type;

[0058] The first condition includes at least one of the following:

[0059] The time interval between the current time and the time when the viewing probability and the interest type were last determined reaches the interval threshold;

[0060] The amount of the policy reference information that continues to be obtained reaches a newly added threshold.

[0061] Optionally, determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information includes:

[0062] Determining, according to the policy reference information, the first user's interest type and initial viewing probability for the video ringback tone;

[0063] The recommending video ringback tone to the target user according to the viewing probability and the interest type includes:

[0064] Obtaining a final viewing probability according to the correction factor and the initial viewing probability;

[0065] According to the final viewing probability and interest type, a video ringback tone is recommended to the target user.

[0066] Optionally, the correction factor is determined based on the first information;

[0067] The first information includes at least one of: the interval between the current time and the last time a video ringback tone was recommended to the target user, and the number of times the video ringback tone was recommended to the target user within a first time period.

[0068] The embodiment of the present invention further provides a video ring back tone recommendation device, comprising a memory, a processor and a program stored in the memory and executable on the processor; when the processor executes the program, the above-mentioned video ring back tone recommendation method is implemented.

[0069] The embodiment of the present invention further provides a readable storage medium on which a program is stored. When the program is executed by a processor, the steps in the above-mentioned video ringback tone recommendation method are implemented.

[0070] The beneficial effects of the above technical solution of the present invention are as follows:

[0071] In the above scheme, the video ringback tone recommendation method obtains the strategy reference information related to the first user; determines the viewing probability and interest type of the first user for the video ringback tone according to the strategy reference information; and recommends the video ringback tone to the target user according to the viewing probability and interest type; wherein the strategy reference information includes at least one of the following: a first duration, an average waiting time, the identity information of the first user, the identity information of the second user communicating with the first user, and the type of video ringback tone played by the first terminal of the first user; the first duration is the time interval from the first user triggering the call to the placement of the first terminal in the answering position; the average waiting time is the time interval from the first user triggering the call to the call being connected; the target user includes: at least one of the first user and a third user communicating with the first user; it is possible to implement differentiated ringback tone promotion based on the user's viewing probability and interest type for the video ringback tone, improve the promotion accuracy and success rate, and well solve the problem of low accuracy of video ringback tone promotion schemes in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A schematic diagram of a video ringback tone recommendation method according to an embodiment of the present invention;

[0073] Figure 2 A schematic diagram of a framework for implementing a method for recommending a video ringback tone according to an embodiment of the present invention;

[0074] Figure 3 The specific implementation process of the video ringback tone recommendation method of the embodiment of the present invention is shown as follows Figure 1 ;

[0075] Figure 4 The specific implementation process of the video ringback tone recommendation method of the embodiment of the present invention is shown as follows Figure 2 ;

[0076] Figure 5 The figure is a schematic diagram of the structure of a video ringback tone recommendation device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0077] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0078] The present invention aims to solve the problem of low accuracy of video ringback tone promotion scheme in the existing technology and provides a video ringback tone recommendation method. Figure 1 As shown, including:

[0079] Step 11: Obtain policy reference information related to the first user;

[0080] Step 12: determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information;

[0081] Step 13: Recommend video ringback tone to the target user based on the viewing probability and interest type; wherein the policy reference information includes at least one of the following: a first duration, an average waiting time, identity information of the first user, identity information of the second user communicating with the first user, and the type of video ringback tone played by the first terminal of the first user; the first duration is the time interval from when the first user triggers a call to when the first terminal is placed in the answering position; the average waiting time is the time interval from when the first user triggers a call to when the call is connected; the target users include: at least one of the first user and a third user communicating with the first user.

[0082] The video ringback tone recommendation method can be applied to a promotion analysis module; when implemented, the promotion analysis module can be set on a ringback tone related server or on a ringback tone related platform, without limitation. The interest type can include: at least one of an interested type and an uninterested type, without limitation;

[0083] Step 13 may include: determining a video ringback tone recommendation strategy for the target user based on the viewing probability and the interest type; and recommending a video ringback tone to the target user based on the video ringback tone recommendation strategy. The video ringback tone recommendation strategy may be matched with the specific recommendation operation involved in the following content, such as: determining the video ringback tone recommendation strategy as the first strategy when the viewing probability is greater than or equal to the viewing threshold; the first strategy includes: recommending a video ringback tone matching the interest type to the first user and a third user whose correlation coefficient with the first user is greater than the correlation threshold; determining the video ringback tone recommendation strategy as the second strategy when the viewing probability is less than the viewing threshold; the second strategy includes: recommending a video ringback tone matching the interest type to the first user; no limitation is made here.

[0084] The identity information may include age and other information; the third user may include the second user, but is not limited to this;

[0085] The video ringback tone recommendation method provided in the embodiment of the present invention obtains the policy reference information related to the first user; determines the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information; and recommends the video ringback tone to the target user according to the viewing probability and interest type; wherein the policy reference information includes at least one of the following: a first duration, an average waiting time, the identity information of the first user, the identity information of the second user communicating with the first user, and the type of video ringback tone played by the first terminal of the first user; the first duration is the time interval from the first user triggering the call to the first terminal being placed in the answering position; the average waiting time is the time interval from the first user triggering the call to the call being connected; the target user includes: at least one of the first user and a third user communicating with the first user; it is possible to implement differentiated ringback tone promotion based on the user's viewing probability and interest type for the video ringback tone, improve the promotion accuracy and success rate, and well solve the problem of low accuracy of video ringback tone promotion schemes in the prior art.

[0086] Among them, recommending video ringback tone to the target user based on the viewing probability and interest type includes: when the viewing probability is greater than or equal to the viewing threshold, based on the interest type, recommending video ringback tone matching the interest type to the first user and a third user whose association coefficient with the first user is greater than the association threshold; when the viewing probability is less than the viewing threshold, based on the interest type, recommending video ringback tone matching the interest type to the first user.

[0087] In this way, the promotion of ringback tone can be carried out accurately; wherein, the recommending of video ringback tone to the target user according to the viewing probability and interest type may also include: when the viewing probability is greater than or equal to the viewing threshold, according to the interest type, recommending a video ringback tone that matches the interest type to the first user. "Recommending video ringback tone that matches the interest type" may include: recommending video ringback tone of the type of interest (such as increasing or increasing the recommendation); and / or, reducing the recommendation for video ringback tone of the type of no interest. wherein, "reducing the recommendation for video ringback tone of the type of no interest" may include: when the viewing probability is less than the viewing threshold, reducing the recommendation for video ringback tone of the type of no interest.

[0088] In the embodiment of the present invention, the video ringback tone recommended to the target user carries at least one of the ringback tone recommendation information and the video ringback tone subscription link.

[0089] This can increase the user's interest and convenience in ordering ringback tone. Regarding "ringback tone recommendation information and video ringback tone ordering link", for example: play a video ringback tone for user B, and carry the text "your good friend user A thinks this ringback tone is great (i.e. ringback tone recommendation information), set it up and try it out immediately: subscription link (i.e. video ringback tone ordering link)".

[0090] Furthermore, the video ringback tone recommendation method also includes: during the video ringback tone playback process, when the target user places the corresponding terminal in the answering position, triggering the corresponding terminal to execute a first reminder method; wherein the first reminder method includes: at least one of a voice method and a vibration method.

[0091] This can further encourage users to watch video ringback tones.

[0092] Among them, determining the viewing probability and interest type of the first user for the video ringback tone based on the policy reference information includes: when the number of policy reference information related to the first user reaches a quantity threshold, determining the viewing probability and interest type of the first user for the video ringback tone based on the policy reference information.

[0093] This can ensure the accuracy of information such as viewing probability and interest type to a certain extent.

[0094] Furthermore, after determining the viewing probability and interest type of the first user for the video ringtone according to the policy reference information, it also includes: continuing to obtain policy reference information related to the first user; when a first condition is met, updating the viewing probability and interest type according to at least a portion of the policy reference information obtained; recommending the video ringtone to the target user based on the updated viewing probability and interest type; wherein the first condition includes at least one of the following: the time interval between the current time and the last time the viewing probability and interest type were determined reaches an interval threshold; the number of the policy reference information continued to be obtained reaches a new threshold.

[0095] This can ensure the real-time viewing probability and interest type to a certain extent.

[0096] Among them, determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information includes: determining the interest type and the initial viewing probability of the first user for the video ringback tone according to the policy reference information; recommending the video ringback tone to the target user according to the viewing probability and the interest type includes: obtaining the final viewing probability according to a correction factor and the initial viewing probability; and recommending the video ringback tone to the target user according to the final viewing probability and the interest type.

[0097] This can further ensure the accuracy of the viewing probability, and thus ensure the accuracy of the ringback tone recommendation.

[0098] In an embodiment of the present invention, the correction factor is determined based on first information; the first information includes: the interval between the current time and the last time a video ringback tone was recommended to the target user, and at least one of the number of times a video ringback tone was recommended to the target user within the first time period.

[0099] In this way, the correction factor can be obtained in a diversified and accurate manner. The "first time period" may include: a specific time period before the current time (that is, the time period from a certain time in the past to the current time).

[0100] The following is an example of the video ringback tone recommendation method provided by the embodiment of the present invention, in which the answering position is taken as the ear of the user.

[0101] In view of the above technical problems, an embodiment of the present invention provides a method for recommending video ringback tone, which can be specifically implemented as a method for promoting video ringback tone in an efficient and intelligent manner, which involves: vectorizing a user's normal calling behavior, and setting N 5-dimensional vectors {X1, X2, X3, X4, X5}, where the meaning of each dimension is as follows:

[0102] X1 represents: the duration of placement next to the ear (corresponding to the first duration mentioned above);

[0103] X2 represents: average waiting time (i.e. call waiting time, the time difference between the time the call is connected and the time the call is dialed);

[0104] X3 represents: called user (corresponding to the identity information of the second user);

[0105] X4 represents: the type of video ringback tone played (corresponding to the type of video ringback tone played by the first terminal);

[0106] X5 represents: the age of the calling user (corresponding to the identity information of the first user mentioned above).

[0107] Based on the above, the i-th 5-dimensional vector can be recorded as Xi = {xi1,xi2,…,xi5}.

[0108] Specifically, X2 and X5 may be reported by the first user, and X1, X3 and X4 may be obtained from a ring back tone centralized platform, but the present invention is not limited thereto; wherein, the viewing probability may be determined based on X1 and X2 (for example, samples are divided into viewing or non-viewing types according to threshold t and X1; and then the types are corrected based on X2, for details, see the following promotion analysis); X3 may be used to determine the friendship relationship between the calling user and the called user, and the interest type may be determined based on the friendship relationship, X4 and X5, but the present invention is not limited thereto.

[0109] In this solution, the time required from the calling user dialing the number to the calling user putting the phone to the ear (i.e., the first duration) is used to predict whether the calling user has watched the video ringback tone set by the called user. If the time is short, it means that the user has not watched the video ringback tone set by the called user. If the time is long, both situations are possible.

[0110] The solution provided in the embodiment of the present invention is specifically described below with examples.

[0111] 1. Establish a probability sample;

[0112] When the calling user dials the called user's phone, the time from clicking the call to putting the phone to the ear (corresponding to the first time) is uploaded to the server (for example Figure 2 In the promotion analysis (module), the service (i.e., the server) collects samples of the data uploaded multiple times and establishes a probability model. Assuming that the user's sample set is S, when the sample size (i.e., the number of the first duration) reaches N (corresponding to the above-mentioned quantity threshold), it can be used as a reference.

[0113] Among them, the number of samples reaches N, assuming that m sample values ​​are less than the threshold t, and n sample values ​​are greater than the threshold t, N = m + n;

[0114] So:

[0115] Probability of viewing

[0116] Probability of not watching

[0117] Assume that the probability model of m samples and n samples is:

[0118] Where 0 <x<∞;

[0119] If the range of x∈[x-σ,x+σ] is satisfied, the event is considered to have occurred; where x represents the first duration, u and σ represent constants; P(A) and P(B) are on f(x).

[0120] In addition, when P(A) occurs, when the sample value is within the range of [x-σ', x+σ'], it can be considered that the user has not watched the video ringback tone. σ' represents a constant, which may be the same as or different from σ.

[0121] The solution provided by the embodiment of the present invention can be as follows Figure 2 As shown, the following steps are included:

[0122] 1. The calling user reports the vector to the promotion analysis (module);

[0123] 2. Collect data for promotion analysis and obtain ringback tone information (such as those viewed, ordered, recommended, etc. by users) and user-related information (such as friend information) from the ringback tone centralized platform;

[0124] 3. Data modeling for promotion analysis (i.e. building the above-mentioned probability model). The established model and information obtained from the ringback tone centralized platform can be used to make ringback tone recommendations later.

[0125] 2. Promotion analysis;

[0126] Based on the above probability model calculation formula, we can get the probability of users watching video ringback tone (corresponding to the above viewing probability). Now, based on the phone call vectorization behavior model (corresponding to the above vectorization of the user's normal phone call behavior), we further refine the promotion analysis as follows:

[0127] 1. Under the condition that the user is likely to watch the video ringback tone, analyzing the type of video ringback tone that the calling user is interested in (corresponding to the above interest type);

[0128] 1) The average waiting time is approximately equal to the time it is placed next to the ear (this time is the interval between dialing and connecting), indicating that the user is watching the video ringback tone very seriously and believes that the calling user is interested in it. Further analysis is conducted on the types of video ringback tone that the user is watching. The types of interest can be determined based on age group, historical data, friends' ringback tone, etc.;

[0129] 2) The average waiting time is significantly different from the time the ring tone is placed next to the ear, indicating that the calling user is not interested in this type of video ringback tone.

[0130] 2. Based on the condition that the user is likely to watch the video ringback tone, analyze and infer the interest types of the calling user's friends;

[0131] If users call a certain number frequently and are of similar age, the possibility of a close relationship is very high, and it is believed that their interests and hobbies are consistent.

[0132] 3. Under the condition that the user has a small probability of watching the video ringback tone, analyze the type of video ringback tone that the calling user is interested in;

[0133] 1) The average waiting time is approximately equal to the time it is placed next to the ear, indicating that the user is very interested in this type of video ringtone, and the weight is the highest.

[0134] 2) The average waiting time is significantly different from the time the ring tone is placed next to the ear, indicating that the calling user is not interested in this type of video ring tone or is unaware of the video ring tone service.

[0135] In this solution, the viewing probability can be determined, and then the type of video ringback tone that the user is interested in can be determined.

[0136] 3. Promotion mechanism trigger;

[0137] 1. The calling user triggers the call process and reports the call vectorization behavior data (corresponding to the above 5-dimensional data) to the promotion analysis module; it can be understood that the samples will be sent to the promotion analysis (module) all the time.

[0138] 2. If the data model of the user (corresponding to the number of samples of the above-mentioned probability model) does not reach the threshold value N, it will continue to be used for modeling analysis (which can be understood as continuing to collect samples for modeling); if the data model of the user has reached the threshold value, the first promotion condition is met (which can be understood as when there are enough samples, the probability model can be used to obtain the viewing probability (satisfying the first condition) for subsequent promotion operations); in addition, the viewing probability can be updated after reaching a certain duration or the number of samples changes (corresponding to the above-mentioned continued acquisition of the strategy reference information related to the first user; when the first condition is met, the viewing probability and interest type are updated according to at least part of the strategy reference information obtained).

[0139] 3. When the caller is likely to watch the video ringback tone, his friend promotion mechanism can be triggered. Assuming that the threshold of the call frequency is p, by calling the reported called number, users with similar age to the calling user and a call frequency greater than or equal to p (corresponding to the third user mentioned above) are obtained. This type of user can be the promotion target. This type of user has the same interests and hobbies as the calling user, triggering the promotion mechanism of the calling user's friends to push the video ringback tone that the calling user has subscribed to or is interested in. At the same time, the promotion mechanism of the calling user is triggered to push some video ringback tone of the type that the calling user is interested in. Corresponding to the above, when the viewing probability is greater than or equal to the viewing threshold, according to the interest type, the first user and the third user whose correlation coefficient with the first user is greater than the correlation threshold are recommended video ringback tone that matches the interest type.

[0140] For example, assuming that by executing the above steps, when user A is the calling user, it can be determined based on the call frequency that user A and user B are friends, and user A has a higher probability of watching video ringback tone, while user B has not set up video ringback tone. In this case, when user A calls user B, the video ringback tone server can (based on the strategy obtained from the promotion analysis) recommend the type of video ringback tone that user A is interested in to user B in the form of a video ringback tone by means of the calling video ringback tone, and can also attach the friendship between user A and user B (corresponding to the above ringback tone recommendation information) and the relevant subscription link (corresponding to the above video ringback tone subscription link) to the video ringback tone. For example, the video ringback tone can be played for user B with the text: "Your good buddy user A thinks this ringback tone is awesome, set it up and try it out immediately: subscription link". When user B actively calls user A as the calling user, regardless of whether user A has set a video ringback tone or not, the video ringback tone server can send the promotional video ringback tone to user B (for example: if user A has set a video ringback tone, the corresponding video ringback tone can be promoted to offer B; if user A has not set a video ringback tone, the default video ringback tone can be promoted to offer B), so as to achieve the purpose of accurately identifying users who have not set a video ringback tone and promoting video ringback tone based on user relationships and user preferences.

[0141] 4. When the caller is unlikely to watch (i.e., has a low probability of watching) the video ringback tone, a promotion mechanism for the caller user may be triggered.

[0142] Under the calling promotion mechanism, when the calling user calls other called users, regardless of whether the called user has set up a video ringback tone, the video ringback tone server will play a promotional video ringback tone for the calling user according to the calling user's preference category (which can be included in the strategy made by the promotion analysis module); and when it is detected that the calling user has placed the mobile phone to the ear before the call is connected, the calling user can be further prompted to watch the video ringback tone by voice or vibration, and after the call is over, the promotion success rate of the video ringback tone can be further improved by sending a video ringback tone subscription link. Corresponding to the above, when the viewing probability is less than the viewing threshold, according to the interest type, the video ringback tone matching the interest type is recommended to the first user. During the video ringback tone playback process, when the target user places the corresponding terminal in the answering position, the corresponding terminal is triggered to execute the first reminder method.

[0143] In this solution, the promotion method can be determined by the promotion analysis module and sent to the ringback tone centralized platform (the ringback tone centralized platform can interact with the ringback tone server and provide it to the ringback tone server for ringback tone promotion); but it is not limited to this. It can correspond to the above-mentioned acquisition of the policy reference information related to the first user; according to the policy reference information, the viewing probability and interest type of the first user for the video ringback tone are determined; according to the viewing probability and interest type, the video ringback tone is recommended to the target user (specifically; according to the viewing probability and interest type, the video ringback tone recommendation strategy of the target user is determined; according to the video ringback tone recommendation strategy, the video ringback tone is recommended to the target user).

[0144] 4. Promotion mechanism;

[0145] 1. For the calling user, Figure 3 As shown, including the following:

[0146] For high-probability viewing, the type of video ringback tone that the calling user is interested in can be determined, and then it can be determined whether the calling user has subscribed to the ringback tone package service; if so, the video ringback tone of interest can be promoted (based on the type of video ringback tone of interest); if not, the subscription channel can be pushed;

[0147] For low-probability viewing, the types of video ringback rings that the calling user is not interested in can be determined, and then it can be determined whether the calling user has subscribed to the ringback ring package service; if not, the subscription channel can be pushed; if so, the promotion of video ringback rings that the calling user is not interested in can be reduced (based on the types of video ringback rings that the calling user is not interested in).

[0148] 2. Targeting the called user (promotion can be based on the friend relationship with the caller), such as Figure 4 As shown, including the following:

[0149] For high-probability viewing, the type of video ringback tone that the calling user is interested in can be determined, and then the called user who is a friend of the calling user can be determined to determine whether the called user has subscribed to the ringback tone package service; if so, the video ringback tone of interest can be promoted (based on the type of video ringback tone of interest); if not, the subscription channel can be pushed;

[0150] For low-probability viewing, the types of video ringback rings that the calling user is not interested in can be determined, and then the called users who are friends of the calling user can be determined to determine whether the called users have subscribed to the ringback ring package service; if not, the subscription channel can be pushed; if so, the promotion of video ringback rings that the calling user is not interested in can be reduced (based on the types of video ringback rings that the calling user is not interested in).

[0151] 3. Promotion media;

[0152] 1) Before playing the video ringback tone of the called user, a promotional video ringback tone can be pushed first to let users who have not subscribed or are unaware of the video ringback tone service know about the video ringback tone service.

[0153] 2) After the call ends, a video ringtone promotion text message can be sent to the user.

[0154] 4. Correction factor (which may be determined according to the promotion interval (corresponding to the interval included in the above-mentioned first information), the number of times (corresponding to the number of times included in the above-mentioned first information), etc., wherein the smaller the interval, the smaller the probability result after correction by the correction factor; the larger the number of times, the smaller the probability result after correction by the correction factor, but it is not limited thereto);

[0155] If you frequently promote services to users, it may cause users to be disgusted, and in serious cases, it may cause users to leave. At this time, a correction factor can be introduced as the probability weight T([0,1]). For example, if the service has been promoted within a period of time, the weight decays; corresponding to the correction factor and the initial viewing probability, the final viewing probability is obtained. Specifically, the correction factor can be multiplied by the initial viewing probability to obtain the final viewing probability (i.e., the corrected viewing probability).

[0156] As described above, the embodiment of the present invention provides a method for promoting intelligent video ringback tone based on the actual behavior of the calling user calling the called user, and promotes the video ringback tone service by this method; which involves:

[0157] 1. Vectorize the real user calling behavior, build a sample model, and obtain the probability of the calling user watching the video ringback tone set by the called user, the type of video ringback tone the calling user likes, and other video ringback tone promotion factors. Specifically involved:

[0158] (1) When the calling user dials the called terminal number, the calling terminal collects the time from the calling user clicking the call to the calling user placing the mobile phone to the ear (corresponding to the first time), and uploads the collected time to the promotion analysis, so that the promotion analysis determines the probability of the calling user watching the video ringback tone according to the first time of the calling user, the call connection time, the corresponding video ringback tone type of the called user and the calling user information, based on the pre-established probability prediction model, and further determines the type of video ringback tone that the calling user is interested in; wherein:

[0159] The behavior vectors of users making calls include: the length of time the phone is placed next to the ear, the average waiting time, the called user, the type of video ringback tone played, and the age of the calling user. The time from the caller dialing the number to the caller placing the phone next to the ear can be used to predict whether the calling user has watched the video ringback tone set by the called user, thereby obtaining the type of video ringback tone and the promotion factors of video ringback tone that the calling user likes.

[0160] (2) Acquire the call data of the calling user, determine the call frequency between the calling user and different called users based on the call data, and determine the friend relationship of the calling user based on the call frequency between the calling user and the called user and the age of the calling user and the called user, and further determine whether the called user who is a friend of the calling user has set a video ringback tone, and then determine the video ringback tone of the called user who is a friend of the calling user as the type of video ringback tone that the calling user is interested in.

[0161] 2. Based on the promotion factor model (corresponding to the probability model), the actual situation can be simulated more realistically, which can effectively improve the promotion of video ringback tone. Specifically involved:

[0162] (1) Determine a promotion mechanism for video ringback rings based on the probability of the calling user watching the video ringback rings: 1) When the probability of the calling user watching the video ringback rings is greater than a preset probability threshold (corresponding to the above-mentioned viewing threshold), the video ringback rings can be recommended to users who are friends with the calling user and have not set up video ringback rings based on the predetermined type of video ringback rings that the calling user is interested in. The specific method is: when the above two users who are friends have a call, the video ringback rings will be promoted to the friend user by means of the calling video ringback ring (or the called video ringback ring); 2) When the probability of the calling user watching the video ringback ring is less than the preset probability threshold, the calling user can be reminded to watch the video ringback ring by vibration or voice when playing the video ringback ring of this type, and the video ringback ring can be promoted to the calling user by pushing the video ringback ring subscription address after the call ends.

[0163] Among them, under the calling promotion mechanism, when the calling user calls other called users, regardless of whether the called user has set up a video ringtone, the promotion analysis can play a promotional video ringtone for the calling user based on the calling user's preference category; and when it is detected that the calling user has placed the mobile phone to the ear before the call is connected, the calling user can be further prompted to watch the video ringtone through voice or vibration, and after the call ends, the video ringtone subscription link can be sent to further improve the promotion success rate of the video ringtone.

[0164] In summary, for users who have no habit of watching video ringback tone (such users who have no habit of watching video ringback tone often choose to put the phone to their ears and wait for the call to be answered after dialing the called number), as well as users who are not familiar with video ringback tone and have not installed relevant ringback tone APP; the video ringback tone recommendation method provided by this scheme can be adopted: on the one hand, the probability of users watching video ringback tone can be predicted through a probability model, and based on the viewing probability and user preferences, video ringback tone can be promoted to users in a targeted manner (that is, accurate identification and recommendation can be performed), wherein the user group to be promoted is accurately identified through the viewing probability, avoiding the bad experience of the user caused by indiscriminate promotion; on the other hand, promotion can also be carried out according to user preferences and social relationships, which can also greatly improve the promotion success rate.

[0165] The embodiment of the present invention also provides a video ring back tone recommendation device, such as Figure 5 As shown, including:

[0166] A first acquisition module 51 is used to acquire policy reference information related to a first user;

[0167] A first determination module 52, configured to determine the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information;

[0168] A first recommendation module 53, configured to recommend video ringback tones to target users according to the viewing probability and interest type;

[0169] The policy reference information includes at least one of the following: a first duration, an average waiting duration, identity information of the first user, identity information of a second user communicating with the first user, and a type of video ringback tone played by a first terminal of the first user;

[0170] The first duration is the duration from when the first user triggers a call to when the first terminal is placed in a receiving position;

[0171] The average waiting time is the time interval from when the first user triggers a call to when the call is connected;

[0172] The target user includes: at least one of the first user and a third user communicating with the first user.

[0173] The video ringback tone recommendation device provided in the embodiment of the present invention obtains the policy reference information related to the first user; determines the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information; and recommends the video ringback tone to the target user according to the viewing probability and interest type; wherein the policy reference information includes at least one of the following: a first duration, an average waiting time, the identity information of the first user, the identity information of the second user communicating with the first user, and the type of video ringback tone played by the first terminal of the first user; the first duration is the time interval from the first user triggering the call to the first terminal being placed in the answering position; the average waiting time is the time interval from the first user triggering the call to the call being connected; the target user includes: at least one of the first user and a third user communicating with the first user; it is possible to implement differentiated ringback tone promotion based on the user's viewing probability and interest type for the video ringback tone, improve the promotion accuracy and success rate, and well solve the problem of low accuracy of video ringback tone promotion schemes in the prior art.

[0174] Among them, recommending video ringback tone to the target user based on the viewing probability and interest type includes: when the viewing probability is greater than or equal to the viewing threshold, based on the interest type, recommending video ringback tone matching the interest type to the first user and a third user whose association coefficient with the first user is greater than the association threshold; when the viewing probability is less than the viewing threshold, based on the interest type, recommending video ringback tone matching the interest type to the first user.

[0175] In the embodiment of the present invention, the video ringback tone recommended to the target user carries at least one of the ringback tone recommendation information and the video ringback tone subscription link.

[0176] Furthermore, the video ringback tone recommendation device also includes: a first trigger module, which is used to trigger the corresponding terminal to execute a first reminder method when the target user places the corresponding terminal in a listening position during the video ringback tone playback process; wherein the first reminder method includes: at least one of a voice method and a vibration method.

[0177] Among them, determining the viewing probability and interest type of the first user for the video ringback tone based on the policy reference information includes: when the number of policy reference information related to the first user reaches a quantity threshold, determining the viewing probability and interest type of the first user for the video ringback tone based on the policy reference information.

[0178] Furthermore, the video ringback tone recommendation device also includes: a second acquisition module, used to continue to obtain the policy reference information related to the first user after determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information; a first update module, used to update the viewing probability and interest type according to at least a part of the policy reference information obtained when the first condition is met; a second recommendation module, used to recommend the video ringback tone to the target user based on the updated viewing probability and interest type; wherein the first condition includes at least one of the following: the time interval between the current time and the time when the viewing probability and interest type were last determined reaches the interval threshold; the number of the policy reference information continued to be obtained reaches the newly added threshold.

[0179] Among them, determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information includes: determining the interest type and the initial viewing probability of the first user for the video ringback tone according to the policy reference information; recommending the video ringback tone to the target user according to the viewing probability and the interest type includes: obtaining the final viewing probability according to a correction factor and the initial viewing probability; and recommending the video ringback tone to the target user according to the final viewing probability and the interest type.

[0180] In an embodiment of the present invention, the correction factor is determined based on first information; the first information includes: the interval between the current time and the last time a video ringback tone was recommended to the target user, and at least one of the number of times a video ringback tone was recommended to the target user within the first time period.

[0181] Among them, the implementation embodiments of the above-mentioned video ringback tone recommendation method are all applicable to the embodiments of the video ringback tone recommendation device, and can also achieve the same technical effect.

[0182] The embodiment of the present invention further provides a video ring back tone recommendation device, comprising a memory, a processor and a program stored in the memory and executable on the processor; when the processor executes the program, the above-mentioned video ring back tone recommendation method is implemented.

[0183] Among them, the implementation embodiments of the above-mentioned video ringback tone recommendation method are all applicable to the embodiments of the video ringback tone recommendation device, and can also achieve the same technical effect.

[0184] The embodiment of the present invention further provides a readable storage medium on which a program is stored. When the program is executed by a processor, the steps in the above-mentioned video ringback tone recommendation method are implemented.

[0185] Among them, the implementation embodiments of the above-mentioned video ringback tone recommendation method are all applicable to the embodiments of the readable storage medium and can also achieve the same technical effect.

[0186] It should be noted that many functional components described in this specification are referred to as modules in order to more particularly emphasize the independence of their implementation methods.

[0187] In the embodiment of the present invention, module can be implemented with software so that it can be executed by various types of processors. For example, an executable code module of an identification can include one or more physical or logical blocks of computer instructions, for example, it can be constructed as an object, process or function. Nevertheless, the executable code of the identified module does not need to be physically located together, but can include different instructions stored in different positions, and when these instructions are logically combined together, it constitutes a module and realizes the specified purpose of the module.

[0188] In fact, executable code module can be a single instruction or many instructions, and can even be distributed on a plurality of different code segments, distributed among different programs, and distributed across a plurality of memory devices. Similarly, operating data can be identified in the module, and can be implemented and organized in the data structure of any appropriate type according to any appropriate form. The operating data can be collected as a single data set, or can be distributed in different locations (including on different storage devices), and can only be present on a system or network as an electronic signal at least in part.

[0189] When a module can be implemented by software, considering the level of existing hardware technology, a person skilled in the art can build a corresponding hardware circuit to implement the corresponding function of the module that can be implemented by software without considering the cost. The hardware circuit includes a conventional very large scale integration (VLSI) circuit or gate array and existing semiconductors such as logic chips, transistors, or other discrete components. The module can also be implemented by a programmable hardware device, such as a field programmable gate array, a programmable array logic, a programmable logic device, etc.

[0190] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A video ringback tone recommendation method, characterized in that: include: Obtaining policy reference information related to the first user; Determining, according to the policy reference information, a viewing probability and an interest type of the first user for the video ringback tone; Recommending video ringback tones to target users according to the viewing probability and interest type; The policy reference information includes: a first duration, an average waiting duration, identity information of the first user, identity information of a second user communicating with the first user, and a type of video ringback tone played by a first terminal of the first user; The first duration is the duration from when the first user triggers a call to when the first terminal is placed in a receiving position; The average waiting time is the time interval from when the first user triggers a call to when the call is connected; The target user includes: at least one of the first user and a third user communicating with the first user; The step of recommending a video ringback tone to a target user according to the viewing probability and the interest type includes: When the viewing probability is greater than or equal to the viewing threshold, recommending, according to the interest type, a video ringback tone matching the interest type to the first user and a third user whose association coefficient with the first user is greater than the association threshold; When the viewing probability is less than a viewing threshold, a video ringback tone matching the interest type is recommended to the first user according to the interest type.

2. The video ringback tone recommendation method according to claim 1, characterized in that: The video ringback tone recommended to the target user carries at least one of the ringback tone recommendation information and the video ringback tone subscription link.

3. The video ringback tone recommendation method according to claim 1, characterized in that: Also includes: During the video ringback tone playing process, when the target user places the corresponding terminal in the answering position, triggering the corresponding terminal to execute the first reminder mode; Wherein, the first reminder method includes: at least one of a voice method and a vibration method.

4. The video ringback tone recommendation method according to claim 1, characterized in that: The determining, according to the policy reference information, the viewing probability and interest type of the first user for the video ringback tone includes: When the amount of the policy reference information related to the first user reaches a quantity threshold, the viewing probability and interest type of the first user for the video ringback tone are determined according to the policy reference information.

5. The video ringback tone recommendation method according to claim 1, characterized in that: After determining the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information, the method further includes: Continue to obtain policy reference information related to the first user; When the first condition is met, updating the viewing probability and the interest type according to at least a portion of the acquired strategy reference information; Recommending video ringback tones to target users according to the updated viewing probability and interest type; The first condition includes at least one of the following: The time interval between the current time and the time when the viewing probability and the interest type were last determined reaches the interval threshold; The amount of the policy reference information that continues to be obtained reaches a newly added threshold.

6. The video ringback tone recommendation method according to claim 1, characterized in that: The determining, according to the policy reference information, the viewing probability and interest type of the first user for the video ringback tone includes: Determining, according to the policy reference information, the first user's interest type and initial viewing probability for the video ringback tone; The recommending video ringback tone to the target user according to the viewing probability and the interest type includes: Obtaining a final viewing probability according to the correction factor and the initial viewing probability; According to the final viewing probability and interest type, a video ringback tone is recommended to the target user.

7. The video ringback tone recommendation method according to claim 6, characterized in that: The correction factor is determined based on the first information; The first information includes at least one of: the interval between the current time and the last time a video ringback tone was recommended to the target user, and the number of times the video ringback tone was recommended to the target user within a first time period.

8. A video ringback tone recommendation device, characterized in that: include: A first acquisition module, used to acquire policy reference information related to the first user; A first determination module, configured to determine the viewing probability and interest type of the first user for the video ringback tone according to the policy reference information; A first recommendation module, configured to recommend video ringback tones to target users according to the viewing probability and interest type; The policy reference information includes: a first duration, an average waiting duration, identity information of the first user, identity information of a second user communicating with the first user, and a type of video ringback tone played by a first terminal of the first user; The first duration is the duration from when the first user triggers a call to when the first terminal is placed in a receiving position; The average waiting time is the time interval from when the first user triggers a call to when the call is connected; The target user includes: at least one of the first user and a third user communicating with the first user; The step of recommending a video ringback tone to a target user according to the viewing probability and the interest type includes: When the viewing probability is greater than or equal to the viewing threshold, recommending, according to the interest type, a video ringback tone matching the interest type to the first user and a third user whose association coefficient with the first user is greater than the association threshold; When the viewing probability is less than a viewing threshold, a video ringback tone matching the interest type is recommended to the first user according to the interest type.

9. A video ring back tone recommendation device, comprising a memory, a processor, and a program stored in the memory and executable on the processor; characterized in that: When the processor executes the program, the video ringback tone recommendation method according to any one of claims 1 to 7 is implemented.

10. A readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the steps of the video ringback tone recommendation method according to any one of claims 1 to 7 are implemented.

Images