CN106156270B - Multimedia data push method and device - Google Patents

Abstract

The present disclosure relates to a method for pushing multimedia data, belonging to the field of the Internet. The method includes: acquiring rhythm level information of each multimedia data in a plurality of multimedia data stored in a multimedia database; for each user account in the plurality of user accounts , based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, determine the character characteristic value of the user account; Multimedia data matching the character feature value of the account; push the selected multimedia data to the terminal corresponding to the user account. The present disclosure improves the efficiency of the server pushing multimedia data to the terminal by pushing the multimedia data matching the temperament type of the user account to the terminal.

Description

Multimedia data push method and device

technical field

The present disclosure relates to the field of the Internet, and in particular, to a method and device for pushing multimedia data.

Background technique

With the development of technology, there are more and more terminals designed for children's learning and education, such as story machines. Story machines allow children to appreciate music, listen to stories, and more. At the same time, the server can push multimedia data to each terminal, thereby enriching the playback of multimedia data by the terminal.

At present, the server pushes the multimedia data to the terminal as follows: the server obtains the history record of the terminal playing the multimedia data, obtains the multimedia data similar in style to the multimedia data in the history record based on the history record, and pushes the obtained multimedia data to terminal.

SUMMARY OF THE INVENTION

In order to overcome the problems existing in the related art, the present disclosure provides a method and device for pushing multimedia data.

According to a first aspect of the embodiments of the present disclosure, there is provided a method for pushing multimedia data, the method comprising:

Obtain the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database;

For each user account in the plurality of user accounts, determine the character characteristic value of the user account based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data;

Based on the character characteristic value of the user account, selecting multimedia data matching the character characteristic value of the user account from the plurality of multimedia data;

Pushing the selected multimedia data to the corresponding terminal of the user account.

Optionally, obtaining the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database, including:

For each multimedia data in the plurality of multimedia data, determine the data duration of the multimedia data and the data frequency of the multimedia data in multiple units of time within the data duration;

determining the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the plurality of unit times;

Based on the frequency average value, the rhythm level information of the multimedia data is acquired from the stored correspondence between the frequency average value range and the rhythm level information.

Optionally, determining the character characteristic value of the user account based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, including:

For each multimedia data in the multimedia data that has been played by the user account within the specified time period in the plurality of multimedia data, based on the rhythm level information of the multimedia data, from the stored rhythm level information and the level weight In the corresponding relationship between, obtain the level weight of the multimedia data;

Determine the playing quantity of the played multimedia data, the total playing time of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and the user account's switching weight. user age;

The total playing duration of each multimedia data in the played multimedia data is divided by the user age of the user account to obtain the average playing duration of each multimedia data in the played multimedia data;

Based on the number of plays, the average play duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, each of the played multimedia data The grade weight of the multimedia data and the user age of the user account determine the character characteristic value of the user account.

Optionally, based on the number of plays, the average play duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, the played multimedia data The grade weight of each multimedia data in the data and the user age of the user account determine the character characteristic value of the user account, including:

Based on the number of playbacks, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and each multimedia data in the played multimedia data The level weight of the user account and the user age of the user account are determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, the C is the character characteristic value of the user account, the n is the number of playbacks, and the D(i) is the playback duration of the i-th multimedia data in the n pieces of multimedia data Average value, the Pace(i) is the grade weight of the i-th multimedia data, the frequency is the switching weight of the user account to the played multimedia data, and the age is the user age of the user account .

Optionally, selecting the multimedia data matching the character characteristic value of the user account from the plurality of multimedia data based on the character characteristic value of the user account, including:

Get the character trait values of all registered user accounts;

Determine the average value of the character characteristic, the average value of the character characteristic is the average value of the character characteristic value of all the registered user accounts;

Determine the temperament type of the user account based on the character characteristic average value and the character characteristic value of the user account;

Based on the temperament type of the user account, obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information;

Based on the rhythm level information of each of the plurality of multimedia data, multimedia data matching the rhythm level information of the user account is selected from the plurality of multimedia data.

According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for pushing multimedia data, the apparatus comprising:

an acquisition module, to acquire the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database;

A determination module, for each user account in a plurality of user accounts, based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, determine the character characteristic value of the user account;

a selection module, configured to select multimedia data matching the character characteristic value of the user account from the plurality of multimedia data based on the character characteristic value of the user account;

A push module, configured to push the selected multimedia data to the terminal corresponding to the user account.

Optionally, the obtaining module includes:

a first determining unit, configured to, for each multimedia data in the plurality of multimedia data, determine the data duration of the multimedia data and the data frequency of the multimedia data in a plurality of units of time within the data duration;

a second determining unit, configured to determine the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the plurality of units of time;

A first acquiring unit, configured to acquire, based on the frequency average, the rhythm level information of the multimedia data from the stored correspondence between the frequency average range and the rhythm level information.

Optionally, the determining module includes:

The second acquiring unit is configured to, for each multimedia data in the multimedia data that has been played by the user account within the specified time period in the plurality of multimedia data, based on the rhythm level information of the multimedia data, from the stored In the correspondence between the rhythm level information and the level weight, obtain the level weight of the multimedia data;

a third determining unit, configured to determine the playing quantity of the played multimedia data, the total playing duration of each multimedia data in the played multimedia data, the switching of the played multimedia data by the user account weight and user age of said user account;

A computing unit for dividing the total playing duration of each multimedia data in the played multimedia data by the user age of the user account to obtain the average playing duration of each multimedia data in the played multimedia data ;

The fourth determination unit is configured to be based on the number of playbacks, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, the The rank weight of each multimedia data in the played multimedia data and the user age of the user account determine the character characteristic value of the user account.

Optionally, the fourth determining unit includes:

Based on the number of playbacks, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and each multimedia data in the played multimedia data The level weight of the user account and the user age of the user account are determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, the C is the character characteristic value of the user account, the n is the number of playbacks, and the D(i) is the playback duration of the i-th multimedia data in the n pieces of multimedia data Average value, the Pace(i) is the grade weight of the i-th multimedia data, the frequency is the switching weight of the user account to the played multimedia data, and the age is the user age of the user account .

Optionally, the selection module includes:

The third obtaining unit is used to obtain the character characteristic values of all registered user accounts;

a fifth determining unit, configured to determine an average value of character characteristics, where the average value of character characteristics is the average value of character characteristic values of all the registered user accounts;

A sixth determining unit, configured to determine the temperament type of the user account based on the character characteristic average value and the character characteristic value of the user account;

a fourth obtaining unit, configured to obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information based on the temperament type of the user account;

A selection unit, configured to select multimedia data matching the rhythm level information of the user account from the multiple multimedia data based on the rhythm level information of each multimedia data in the multiple multimedia data.

According to a third aspect of the embodiments of the present disclosure, there is provided an apparatus for pushing multimedia data, the apparatus comprising:

processor;

memory for storing processor-executable instructions;

wherein the processor is configured to:

Obtain the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database;

For each user account in the plurality of user accounts, determine the character characteristic value of the user account based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data;

Based on the character characteristic value of the user account, selecting multimedia data matching the character characteristic value of the user account from the plurality of multimedia data;

Pushing the selected multimedia data to the terminal corresponding to the user account.

The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: In the embodiments of the present disclosure, the server may acquire the rhythm level information of each multimedia data among the plurality of multimedia data stored in the multimedia database and the character of the plurality of user accounts feature value, and according to the character feature value of each user account in the multiple user accounts, select multimedia data that matches the character feature value from the plurality of multimedia data, and push the character feature to the terminal corresponding to the user account. Therefore, the multimedia data pushed by the server to the terminal is more targeted, and at the same time, the multimedia data pushed by the server will be more in line with the playback preferences and habits of the user account, which improves the efficiency of the server pushing multimedia data to the terminal.

It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description serve to explain the principles of the invention.

Fig. 1 is a flowchart of a method for pushing multimedia data according to an exemplary embodiment.

Fig. 2 is a flow chart of another method for pushing multimedia data according to an exemplary embodiment.

Fig. 3A is a structural block diagram of a multimedia data push device according to an exemplary embodiment.

Fig. 3B is a structural block diagram of an acquisition module according to an exemplary embodiment.

Fig. 3C is a structural block diagram of a determination module according to an exemplary embodiment.

Fig. 3D is a structural block diagram of a selection module according to an exemplary embodiment.

Fig. 4 is a structural block diagram of another apparatus for pushing multimedia data according to an exemplary embodiment.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with some aspects of the invention as recited in the appended claims.

Before explaining the embodiments of the present disclosure in detail, the application scenarios of the embodiments of the present disclosure are first introduced. At present, after the server acquires the playback record of the multimedia data played by the terminal, it can analyze the multimedia data in the playback record, so as to push multimedia data similar in style to the multimedia data in the playback record to the terminal. However, because the push is only based on the style of the multimedia data, the pushed multimedia data may not be what the user likes, and when the multimedia data is obtained and pushed, the pushed multimedia data is not connected with the real needs of the user, so that the Pushed multimedia data lacks accuracy. In addition, only the multimedia data with similar styles are pushed, and the push form is relatively simple. Therefore, the embodiments of the present disclosure provide a method for pushing multimedia data, which enables the server to push the multimedia data in a targeted manner, improves the accuracy of pushing the multimedia data, and enriches the way of acquiring the pushed multimedia data. The efficiency of pushing multimedia data is improved.

Fig. 1 is a flowchart of a method for pushing multimedia data according to an exemplary embodiment. As shown in Fig. 1 , the method is used in a server and includes the following steps.

In step 101, rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database is obtained.

In step 102, for each user account in the plurality of user accounts, based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, the character characteristic value of the user account is determined.

In step 103, based on the character characteristic value of the user account, multimedia data matching the character characteristic value of the user account is selected from the plurality of multimedia data.

In step 104, the selected multimedia data is pushed to the terminal corresponding to the user account.

In the embodiment of the present disclosure, the server may acquire the rhythm level information of each multimedia data among the multiple multimedia data stored in the multimedia database and the character characteristic value of the multiple user accounts, and according to each user account of the multiple user accounts character characteristic value, select the multimedia data matching the character characteristic value from the plurality of multimedia data, and push the multimedia data matching the character characteristic characteristic value to the terminal corresponding to the user account, so that the server pushes the multimedia data to the terminal It is more targeted, and at the same time, the multimedia data pushed by the server will be more in line with the user account's playing preferences and habits, which improves the efficiency of the server pushing the multimedia data to the terminal.

Optionally, obtain the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database, including:

For each multimedia data in the plurality of multimedia data, determine the data duration of the multimedia data and the data frequency of the multimedia data in a plurality of units of time within the data duration;

Determine the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the plurality of unit times;

Based on the frequency average value, the rhythm level information of the multimedia data is acquired from the stored correspondence between the frequency average value range and the rhythm level information.

Optionally, based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, determine the character characteristic value of the user account, including:

For each multimedia data in the multimedia data that has been played by the user account within the specified time period in the plurality of multimedia data, based on the rhythm level information of the multimedia data, the correspondence between the stored rhythm level information and the level weight is obtained. In the relationship, obtain the grade weight of the multimedia data;

Determine the number of plays of the played multimedia data, the total playing time of each multimedia data in the played multimedia data, the switching weight of the user account to the played multimedia data and the user age of the user account;

Divide the total playing duration of each multimedia data in this played multimedia data by the user age of this user account, obtain the playing duration average value of each multimedia data in this played multimedia data;

Based on the number of plays, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and the level weight of each multimedia data in the played multimedia data and the user age of the user account to determine the character characteristic value of the user account.

Optionally, based on the number of plays, the average value of the playing duration of each multimedia data in the played multimedia data, the switching weight of the user account to the played multimedia data, each multimedia data in the played multimedia data The level weight of the user account and the user age of the user account, determine the character characteristic value of the user account, including:

Based on the number of plays, the average play duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, the level weight of each multimedia data in the played multimedia data, and The user age of the user account is determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, C is the character characteristic value of the user account, n is the number of playbacks, D(i) is the average playback duration of the i-th multimedia data in the n multimedia data, and Pace(i) is the The rank weight of the i-th multimedia data, frequency is the switching weight of the user account to the played multimedia data, and age is the user age of the user account.

Optionally, based on the character feature value of the user account, multimedia data matching the character feature value of the user account is selected from the plurality of multimedia data, including:

Get the character trait values of all registered user accounts;

Determine the average value of the character characteristic, the average value of the character characteristic is the average value of the character characteristic value of all the registered user accounts;

Determine the temperament type of the user account based on the average character characteristic value and the character characteristic value of the user account;

Based on the temperament type of the user account, obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information;

Based on the rhythm level information of each of the plurality of multimedia data, multimedia data matching the rhythm level information of the user account is selected from the plurality of multimedia data.

All the above-mentioned optional technical solutions can be combined to form optional embodiments of the present disclosure, which are not repeated in the embodiments of the present disclosure.

FIG. 2 is a flowchart of a method for pushing multimedia data according to an exemplary embodiment. Referring to FIG. 2 , the method includes the following steps.

In step 201, the server acquires rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database.

In this step, for each multimedia data in the plurality of multimedia data, the server determines the data duration of the multimedia data and the data frequency of the multimedia data in a plurality of units of time within the data duration; The data duration and the data frequencies of the multiple unit times determine the frequency average value of the multimedia data; based on the frequency average value, obtain the multimedia data from the stored correspondence between the frequency average value range and the rhythm level information rhythm level information.

Wherein, the operation of the server determining the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the plurality of unit times may be: adding the data frequencies in the plurality of unit times to obtain the first A numerical value, dividing the first numerical value by the data duration of the multimedia data to obtain a second numerical value, and determining the second numerical value as the frequency average of the multimedia data.

It should be noted that the unit time may be set in advance, for example, the unit time may be 20 seconds, 30 seconds, 1 minute, etc., which is not specifically limited in this embodiment of the present disclosure.

For example, when the server determines that the data duration of multimedia data A is 3 minutes, and the data frequencies of the multimedia data A in three units of time within the data duration of 3 minutes are 2000Hz, 4000Hz, and 2400Hz, respectively, the server will 2000Hz, 4000Hz and 2400Hz is added to obtain a first value of 8400Hz, and the first value of 8400Hz is divided by the data duration of the multimedia data for 3 minutes to obtain a second value of 2800Hz. The second value of 2800Hz is determined as the frequency average of the multimedia data.

In addition, since the data duration of the multimedia data may not be divided into an integer unit time, in the embodiment of the present disclosure, after the data duration of the multimedia data is divided into unit time, the remaining duration that cannot constitute a unit time is discarded by default, The remaining duration may also be determined as a unit time, which is also not specifically limited in this embodiment of the present disclosure.

For example, the data duration of multimedia data B is 3 minutes and 10 seconds, and the unit time is 1 minute. After dividing the data duration of multimedia data B into 3 unit times, there is a remaining duration of 10 seconds, and the remaining duration can be 10 seconds are discarded by default.

It should be noted that the rhythm level information is used to describe the rhythm level of the multimedia data. In this embodiment of the present disclosure, the rhythm level information can be divided into fast, normal, slow, and slow, and of course, other rhythm level information can also be included. This embodiment of the present disclosure does not specifically limit this.

Wherein, based on the frequency average value, the server obtains the rhythm level information of the multimedia data from the stored correspondence between the frequency average value range and the rhythm level information. The operation may be: the server obtains the frequency average value range and the rhythm level information. For multiple frequency average ranges in the corresponding relationship between the information, the frequency average value of the multimedia data is compared with the multiple frequency average value ranges to determine the frequency average value range where the frequency average value of the multimedia data is located, and then The rhythm level information corresponding to the determined frequency average range is determined as the rhythm level information of the multimedia data.

For example, the server determines that the frequency average value of the multimedia data A is 2800 Hz, and obtains a plurality of frequency average value ranges in the corresponding relationship between the frequency average value range and the rhythm level information as shown in Table 1. Compare the frequency average 2800Hz with multiple frequency average ranges, and determine that the frequency average range where the frequency average 2800Hz is located is 5000Hz>=Pace>2000Hz, so as to determine that the rhythm level information corresponding to the frequency average range is "normal" , and the rhythm level information "normal" is determined as the rhythm level information of the multimedia data A.

Table 1

Frequency average range Rhythm Level Information Pace>5000Hz fast 5000Hz>=Pace>2000Hz ordinary 2000Hz>=Pace>500Hz soothing 500Hz>=Pace slow

It should be noted that, in the embodiment of the present disclosure, only the corresponding relationship between the frequency average range and the rhythm level information shown in Table 1 is used as an example for description, and does not constitute a limitation to the embodiment of the present disclosure.

It should also be noted that the server may set the corresponding relationship between the frequency average range and the rhythm level information in advance, which is not specifically limited in this embodiment of the present disclosure.

In step 202, for each user account in the plurality of user accounts, the server determines the character characteristic value of the user account based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data.

Wherein, based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, the operation of determining the character characteristic value of the user account may include the steps of the following (1)-(4):

(1): for each multimedia data in the multimedia data that the user account has played in the specified time period in the plurality of multimedia data, the server is based on the rhythm level information of the multimedia data, from the stored rhythm level information and level In the corresponding relationship between the weights, the level weight of the multimedia data is obtained.

It should be noted that the specified time period may be set in advance, for example, the specified time period may be 3 days, 7 days, 10 days, etc., which is not specifically limited in this embodiment of the present disclosure.

For example, the rhythm level information of the multimedia data A is "normal". From the correspondence between the rhythm level information and the level weight shown in Table 2, it is determined that the level weight corresponding to the "normal" rhythm level information is 0.8. The level weight 0.8 is determined as the level weight of the multimedia data A.

Table 2

Rhythm Level Information rank weight fast 1 ordinary 0.8 soothing 0.5 slow 0.1

It should be noted that, in the embodiment of the present disclosure, only the corresponding relationship between the rhythm level information and the level weight shown in Table 2 is used as an example for description, and does not constitute a limitation to the embodiment of the present disclosure.

It should also be noted that the corresponding relationship between the rhythm level information and the level weight may also be set in advance, which is not specifically limited in the embodiment of the present disclosure.

(2): the server determines the number of plays of the played multimedia data, the total playing time of each multimedia data in the played multimedia data, the switching weight of the user account to the played multimedia data and the user account User age.

Wherein, when the user account plays the multimedia data online, the server can record the playback quantity of the multimedia data played by the user account in real time; when the user account plays the multimedia data offline, the terminal real-time Record the playback quantity of multimedia data played by the user account, and send the offline playback quantity to the server every specified time period, so that the server can determine the playback quantity of multimedia data played by the user account within the specified time period.

It should be noted that, in the embodiment of the present disclosure, the server can not only determine the playback quantity of the multimedia data played by the user account within the specified time period in the above-mentioned manner, but also determine in other manners, which is not covered by the embodiment of the present disclosure. Make specific restrictions.

Similarly, the operation of the server determining the total playing time of each multimedia data in the multimedia data played by the user account within the specified time period can also be as follows: when the user account plays the multimedia data in an online manner, the server can Record the total playing time of the multimedia data played by the user account in real time; when the user account plays the multimedia data offline, the terminal records the total playing time of the multimedia data played by the user account in real time, and records the total playing time of the multimedia data played by the user account in real time. The total offline playing time is sent to the server, so that the server can determine the total playing time of the multimedia data played by the user account within the specified time period.

It should be noted that, in the embodiment of the present disclosure, the server can not only determine the total playback duration of the multimedia data played by the user account within the specified time period in the above-mentioned manner, but also determine in other ways. No specific limitation is made.

In addition, the operation of the server determining the switching weight of the played multimedia data of the user account may be as follows: the server may obtain the switching rate of the played multimedia data of each user account in the registered user accounts, and assign all user accounts to the played multimedia data. After adding up the switching rates of the played multimedia data, divide it by the number of users of all user accounts to obtain the average switching rate, and calculate the sum of the switching rate of the played multimedia data for each user account and the average switching rate Based on the switching rate ratio, the switching weight of the user account to the played multimedia data is determined from the corresponding relationship between the switching rate ratio range and the switching weight.

The server may compare the switching rate ratio with the multiple switching rate ratio ranges to determine the switching rate ratio range where the switching rate ratio is located, and then determine the switching weight corresponding to the determined switching rate ratio range as the user The switching weight of the account to the played multimedia data.

For example, the corresponding relationship between the switching rate ratio range and switching weight is shown in Table 2. When the user account is user account ID1, and the server calculates that the switching rate ratio f/F is 100%, the switching rate ratio is 100 % is compared with the multiple switching rate ratio ranges, and it is determined that the switching rate ratio 100% is first within the switching rate ratio range 1+10%>=f/F>1-10%, therefore, determine the switching ratio corresponding to the switching rate ratio The weight is 0.8, so it is determined that the switching weight of the user account ID1 to the played multimedia data is 0.8.

table 3

Switching rate ratio range switch weight f/F>1+10% 1 1+10%>=f/F>1-10% 0.8 1-10%>=f/F 0.5

It should be noted that, in the embodiment of the present disclosure, only the corresponding relationship between the ratio range of the switching rate and the switching weight shown in Table 3 is used as an example for description, and does not constitute a limitation to the embodiment of the present disclosure.

It should also be noted that, the corresponding relationship between the switching rate ratio range and the switching rate weight may be set in advance, which is not specifically limited in this embodiment of the present disclosure.

Wherein, the server may obtain the user information of the user account carried in the login request when receiving the login request sent by the terminal, and the user information includes the age of the user, or when the server needs to determine the character characteristic value of the user account , to obtain the user information of the user account, which is not specifically limited in this embodiment of the present disclosure.

It should be noted that the user information is used to describe the information of the user of the user account, and the user information may include not only the user's age, but also other options, such as the user's nickname, the user's registration time, and the user's level. There is no specific limitation on this.

It should also be noted that, in this embodiment of the present invention, the terminal may be a story machine or other devices, such as a mobile phone, a computer, a smart TV, etc., which are not specifically limited in the embodiments of the present disclosure.

(3): The server divides the total playing duration of each multimedia data in the played multimedia data by the user age of the user account, and obtains the average playing duration of each multimedia data in the played multimedia data.

For example, if the server obtains the multimedia data that has been played by the user account for 3 days in the specified time period as multimedia data B, and the user age of the user account ID1 is 6 years old, the server determines that the total playing time of the multimedia data B within 3 days is 30 minutes Then, divide the total playing time of the multimedia data B by 30 minutes by the user's age of 6 to obtain an average playing time of the multimedia data B of 5 minutes.

It should be noted that, in this embodiment of the present disclosure, the server may perform step (1) first, and then perform steps (2) and (3) in sequence, or the server may perform steps (2) and (3) first, Step (1) is then executed, that is, in the embodiment of the present disclosure, the server is not restricted to obtain the grade weight of each multimedia data in the multimedia data played by the user account of the multimedia data, determine that the user account is at a specified time The number of played multimedia data in the segment, the total playing time of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, the user age of the user account and the played multimedia data. The order of the average playback duration of each multimedia data in the played multimedia data. Wherein, since the average playback duration of each multimedia data in the played multimedia data is determined by the age of the user, the server must determine the average playback duration of each multimedia data in the played multimedia data before determining the average playback duration of each multimedia data in the played multimedia data. Determines the user age for this user account.

(4): the server is based on the number of plays, the average value of playing duration of each multimedia data in the played multimedia data, the switching weight of the user account to the played multimedia data, each of the played multimedia data The grade weight of the multimedia data and the user age of the user account determine the character characteristic value of the user account.

Wherein, the server may be based on the number of playbacks, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the user account for the played multimedia data, and each multimedia data in the played multimedia data. The level weight of the user account and the user age of the user account are determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, C is the character characteristic value of the user account, n is the number of playbacks, D(i) is the average playback duration of the i-th multimedia data in the n multimedia data, and Pace(i) is the The rank weight of the i-th multimedia data, frequency is the switching weight of the user account to the played multimedia data, and age is the user age of the user account.

In step 203, the server selects multimedia data matching the character characteristic value of the user account from the plurality of multimedia data based on the character characteristic value of the user account.

In this step, the server obtains the character characteristic values of all registered user accounts; determines the average character value of the character characteristic, and the character characteristic average value is the average value of the character characteristic values of all the registered user accounts; value and the character characteristic value of the user account to determine the temperament type of the user account; based on the temperament type of the user account, obtain the rhythm grade of the user account from the stored correspondence between the temperament type and the rhythm grade information information; based on the rhythm level information of each multimedia data in the plurality of multimedia data, selecting multimedia data matching the rhythm level information of the user account from the plurality of multimedia data.

Wherein, the operation of the server determining the temperament type of the user account based on the average value of the character characteristic and the character characteristic value of the user account may be: calculating the character characteristic ratio between the character characteristic value of the user account and the average value of the character characteristic ; Based on the character characteristic ratio, the temperament type of the user account is determined from the corresponding relationship between the character characteristic ratio range and the temperament type.

The server may compare the character characteristic ratio of the user account with the multiple character characteristic ratio ranges to determine the character characteristic ratio range in which the character characteristic ratio of the user account is located, and then compare the temperament corresponding to the determined character characteristic ratio range. The type is determined as the temperament type of the user account.

For example, the corresponding relationship between the character feature ratio range and temperament type is shown in Table 4. The server calculates that the character feature ratio C/C0 is 152%, and the character feature ratio of the user account ID1 is 152% and the multiple Compare the character feature ratio range, and determine that the character feature ratio of the user account ID1 is located in the character feature ratio range C/C0>150%. Therefore, it is determined that the temperament type corresponding to the character feature ratio of 152% is choleric, and the temperament type is choleric. The temperament is determined as the temperament type of the user account ID1.

Table 4

character trait ratio range temperament type C/C0>150% Bile matter 150%>=C/C0>120% bloody 120%>=C/C0>80% mucous 80%>=C/C0 Depression

It should be noted that, in the embodiment of the present disclosure, only the corresponding relationship between the character characteristic ratio range and the temperament type shown in Table 4 is used as an example for description, and does not constitute a limitation to the embodiment of the present disclosure.

It should be noted that, the corresponding relationship between the character characteristic ratio range and the temperament type can be set in advance.

In addition, the server can not only select the multimedia data matching the character characteristic value of the user account from the plurality of multimedia data in the above-mentioned manner. Selection can also be made in other ways. For example, the server can make selections through character feature values, or directly through character feature values and rhythm level information, and can also make selections through character feature values and frequency average ranges. The embodiment does not specifically limit this.

Suppose, taking the operation mode of the server selecting by the character characteristic value as an example, the operation mode may be: the server may compare the character characteristic value of the user account with a plurality of character characteristic ranges, and determine where the character characteristic value of the user account is located. and select the multimedia data corresponding to the character characteristic value range from the stored correspondence between the character characteristic value range and the multimedia data as the multimedia data matching the character characteristic value of the user account.

For example, the correspondence between the character feature value range and the multimedia data is shown in Table 5. The server compares the character feature value 496 of the user account ID1 with the multiple character feature value ranges, and determines the character feature of the user account ID1 The value is located in the character feature ratio range C>450. Therefore, it is determined that the multimedia data corresponding to the character feature value 496 is multimedia data A, multimedia data E and multimedia data F. Therefore, select multimedia data A, multimedia data E and multimedia data F. It is multimedia data that matches the character feature value 496 of the user account ID1.

table 5

It should be noted that, in the embodiments of the present disclosure, only the correspondence between the character feature value ranges shown in Table 5 and the multimedia data is used as an example for description, and does not constitute a limitation to the embodiments of the present disclosure.

It should also be noted that the correspondence between the character feature value range and the multimedia data may be set in advance.

In step 204, the server pushes the selected multimedia data to the terminal corresponding to the user account.

It should be noted that, in this embodiment of the present disclosure, since the server selects the rhythm level information matching the rhythm level information of the user account from the plurality of multimedia data based on the rhythm level information of each multimedia data in the plurality of multimedia data The multimedia data may include the multimedia data that has been played by the user account. Therefore, the server can filter out the multimedia data that has been played by the user account in the selected multimedia data, and push the remaining multimedia data after filtering to the user. The terminal corresponding to the account. Of course, the server may not perform filtering, but push all the selected multimedia data to the terminal corresponding to the user account, which is not specifically limited in this embodiment of the present disclosure.

In the embodiment of the present disclosure, the server may acquire the rhythm level information of each multimedia data in the plurality of multimedia data stored in the multimedia database and the character characteristic value of each user account in the plurality of user accounts, wherein, due to the The character characteristic value is the age of the user through the user account, the switching rate of the user account to the played multimedia data, the total data duration of each multimedia data in the played multimedia data, and each of the played multimedia data. The rhythm level information of the multimedia data is calculated, and the temperament type of the user account is determined according to the character characteristic value. Therefore, when the server selects multimedia data matching the temperament type from the plurality of multimedia data, and pushes the selected multimedia data to the terminal corresponding to the user account, the multimedia data pushed by the server can be more targeted. And because the server pushes multimedia according to the temperament of the user account, the multimedia data pushed by the server will conform to the user account's playing preferences and habits, thereby improving the efficiency of the server pushing multimedia data to the terminal.

Fig. 3A is a structural block diagram of a multimedia data push device according to an exemplary embodiment. 3A , the apparatus includes an acquisition module 301 , a determination module 302 , a selection module 303 and a push module 304 .

Obtaining module 301, obtaining the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database;

A determination module 302, for each user account in a plurality of user accounts, based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, determine the character characteristic value of the user account;

A selection module 303, for selecting multimedia data matching the character characteristic value of the user account from the plurality of multimedia data based on the character characteristic value of the user account;

The push module 304 is configured to push the selected multimedia data to the terminal corresponding to the user account.

Optionally, referring to FIG. 3B, the obtaining module 301 includes:

The first determining unit 3011 is used to, for each multimedia data in the plurality of multimedia data, determine the data duration of the multimedia data and the data frequency of the multimedia data in multiple unit times within the data duration;

A second determining unit 3012, configured to determine the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the multiple unit times;

The first obtaining unit 3013 is configured to obtain, based on the frequency average, the rhythm level information of the multimedia data from the stored correspondence between the frequency average range and the rhythm level information.

Optionally, referring to FIG. 3C, the determining module 302 includes:

The second obtaining unit 3021 is configured to, for each multimedia data in the multimedia data that has been played by the user account within the specified time period in the plurality of multimedia data, based on the rhythm level information of the multimedia data, from the stored rhythm level From the correspondence between the information and the level weight, obtain the level weight of the multimedia data;

The third determining unit 3022 is configured to determine the playback quantity of the played multimedia data, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and the user age of the user account;

Calculation unit 3023 is used to divide the playing total duration of each multimedia data in this played multimedia data by the user age of this user account, obtains the playing duration average value of each multimedia data in this played multimedia data;

The fourth determination unit 3024 is used for the average value of the playing duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data on the user account, the played multimedia data on the The rank weight of each multimedia data in the user account and the user age of the user account determine the character characteristic value of the user account.

Optionally, the fourth determining unit 3024 includes:

Based on the number of plays, the average play duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, the level weight of each multimedia data in the played multimedia data, and The user age of the user account is determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, the C is the character characteristic value of the user account, the n is the number of playbacks, the D(i) is the average playback duration of the i-th multimedia data in the n multimedia data, and the Pace( i) is the grade weight of the i-th multimedia data, the frequency is the switching weight of the user account to the played multimedia data, and the age is the user age of the user account.

Optionally, referring to FIG. 3D, the selection module 303 includes:

The third obtaining unit 3031 is used to obtain the character characteristic values of all registered user accounts;

The fifth determination unit 3032 is used to determine the average value of the character characteristic, the average value of the character characteristic being the average value of the character characteristic value of all the registered user accounts;

The sixth determining unit 3033 is used to determine the temperament type of the user account based on the average value of the character characteristic and the character characteristic value of the user account;

The fourth obtaining unit 3034 is used to obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information based on the temperament type of the user account;

A selection unit, configured to select multimedia data matching the rhythm level information of the user account from the plurality of multimedia data based on the rhythm level information of each multimedia data in the plurality of multimedia data.

In the embodiment of the present disclosure, the server may acquire the rhythm level information of each multimedia data in the plurality of multimedia data stored in the multimedia database and the character characteristic value of each user account in the plurality of user accounts, wherein, due to the The character characteristic value is the age of the user through the user account, the switching rate of the user account to the played multimedia data, the total data duration of each multimedia data in the played multimedia data, and each of the played multimedia data. The rhythm level information of the multimedia data is calculated, and the temperament type of the user account is determined according to the character characteristic value. Therefore, when the server selects multimedia data matching the temperament type from the plurality of multimedia data, and pushes the selected multimedia data to the terminal corresponding to the user account, the multimedia data pushed by the server can be more targeted. And because the server pushes multimedia according to the temperament of the user account, the multimedia data pushed by the server will conform to the user account's playing preferences and habits, thereby improving the efficiency of the server pushing multimedia data to the terminal.

Regarding the apparatus in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be described in detail here.

FIG. 4 is a block diagram of an apparatus 400 for pushing multimedia data according to an exemplary embodiment. For example, the apparatus 400 may be provided as a server. 4, apparatus 400 includes processing component 422, which further includes one or more processors, and a memory resource, represented by memory 432, for storing instructions executable by processing component 422, such as an application program. An application program stored in memory 432 may include one or more modules, each corresponding to a set of instructions.

Device 400 may also include a power supply assembly 426 configured to perform power management of device 400 , a wired or wireless network interface 450 configured to connect device 400 to a network, and an input output (I/O) interface 458 . Device 400 may operate based on an operating system stored in memory 432, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

Additionally, the processing component 422 is configured to execute instructions to perform the following methods:

Obtain the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database;

For each user account in the plurality of user accounts, determine the character characteristic value of the user account based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data;

Based on the character characteristic value of the user account, selecting multimedia data matching the character characteristic value of the user account from the plurality of multimedia data;

The selected multimedia data is pushed to the terminal corresponding to the user account.

Optionally, obtain the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database, including:

For each multimedia data in the plurality of multimedia data, determine the data duration of the multimedia data and the data frequency of the multimedia data in a plurality of units of time within the data duration;

Determine the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the plurality of unit times;

Based on the frequency average value, the rhythm level information of the multimedia data is acquired from the stored correspondence between the frequency average value range and the rhythm level information.

Optionally, based on the rhythm level information of the multimedia data played by the user account in the plurality of multimedia data, determine the character characteristic value of the user account, including:

For each multimedia data in the multimedia data that has been played by the user account within the specified time period in the plurality of multimedia data, based on the rhythm level information of the multimedia data, the correspondence between the stored rhythm level information and the level weight is obtained. In the relationship, obtain the grade weight of the multimedia data;

Determine the number of plays of the played multimedia data, the total playing time of each multimedia data in the played multimedia data, the switching weight of the user account to the played multimedia data and the user age of the user account;

Divide the total playing duration of each multimedia data in this played multimedia data by the user age of this user account, obtain the playing duration average value of each multimedia data in this played multimedia data;

Based on the number of plays, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and the level weight of each multimedia data in the played multimedia data and the user age of the user account to determine the character characteristic value of the user account.

Optionally, based on the number of plays, the average value of the playing duration of each multimedia data in the played multimedia data, the switching weight of the user account to the played multimedia data, each multimedia data in the played multimedia data The level weight of the user account and the user age of the user account, determine the character characteristic value of the user account, including:

Based on the number of plays, the average play duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, the level weight of each multimedia data in the played multimedia data, and The user age of the user account is determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, C is the character characteristic value of the user account, n is the number of playbacks, D(i) is the average playback duration of the i-th multimedia data in the n multimedia data, and Pace(i) is the The rank weight of the i-th multimedia data, frequency is the switching weight of the user account to the played multimedia data, and age is the user age of the user account.

Optionally, based on the character feature value of the user account, multimedia data matching the character feature value of the user account is selected from the plurality of multimedia data, including:

Get the character trait values of all registered user accounts;

Determine the average value of the character characteristic, the average value of the character characteristic is the average value of the character characteristic value of all the registered user accounts;

Determine the temperament type of the user account based on the average character characteristic value and the character characteristic value of the user account;

Based on the temperament type of the user account, obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information;

Based on the rhythm level information of each of the plurality of multimedia data, multimedia data matching the rhythm level information of the user account is selected from the plurality of multimedia data.

In the embodiment of the present disclosure, the server may acquire the rhythm level information of each multimedia data in the plurality of multimedia data stored in the multimedia database and the character characteristic value of each user account in the plurality of user accounts, wherein, due to the The character characteristic value is the age of the user through the user account, the switching rate of the user account to the played multimedia data, the total data duration of each multimedia data in the played multimedia data, and each of the played multimedia data. The rhythm level information of the multimedia data is calculated, and the temperament type of the user account is determined according to the character characteristic value. Therefore, when the server selects multimedia data matching the temperament type from the plurality of multimedia data, and pushes the selected multimedia data to the terminal corresponding to the user account, the multimedia data pushed by the server can be more targeted. And because the server pushes multimedia according to the temperament of the user account, the multimedia data pushed by the server will conform to the user account's playing preferences and habits, thereby improving the efficiency of the server pushing multimedia data to the terminal.

Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or conventional techniques in the art not disclosed by this disclosure . The specification and examples are to be regarded as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

It should be understood that the present invention is not limited to the precise structures described above and illustrated in the accompanying drawings, and that various modifications and changes may be made without departing from its scope. The scope of the present invention is limited only by the appended claims.

Claims (7)

1. a multimedia data push method, is characterized in that, described method comprises: Obtain the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database; For each user account in a plurality of user accounts, and for each multimedia data in the multimedia data in the plurality of multimedia data that the user account has played within a specified time period, a rhythm level based on the multimedia data information, from the stored correspondence between the rhythm level information and the level weight, obtains the level weight of the multimedia data; Determine the playing quantity of the played multimedia data, the total playing time of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and the user account's switching weight. The age of the user, the playing quantity of each multimedia data includes the playing quantity when the each multimedia data is played online and the playing quantity when playing offline, and the total playing time of each multimedia data includes the playing quantity of each multimedia data. The total playing time of data when playing online and the total playing time when playing offline; The total playing duration of each multimedia data in the played multimedia data is divided by the user age of the user account to obtain the average playing duration of each multimedia data in the played multimedia data; Based on the number of plays, the average play duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, each of the played multimedia data The grade weight of the multimedia data and the user age of the user account determine the character characteristic value of the user account; Get the character trait values of all registered user accounts; Determine the average value of the character characteristic, the average value of the character characteristic is the average value of the character characteristic value of all the registered user accounts; Calculate the character characteristic ratio between the character characteristic value of the user account and the character characteristic average value; based on the character characteristic ratio, determine the user account from the correspondence between the character characteristic ratio range and the temperament type type of atmosphere; Based on the temperament type of the user account, obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information; Based on the rhythm level information of each multimedia data in the plurality of multimedia data, selecting multimedia data matching the rhythm level information of the user account from the plurality of multimedia data; Filtering out the multimedia data played by the user account in the selected multimedia data, and pushing the remaining multimedia data after filtering to the terminal corresponding to the user account; Wherein, the operation of determining the switching weight of the user account to the played multimedia data includes: Obtain the switching rate of each user account in the registered user accounts to the played multimedia data, after adding up the switching rates of all user accounts to the played multimedia data, divide by the number of users of all user accounts, Obtain the average value of the switching rate, and calculate the switching rate ratio between the switching rate of each user account to the played multimedia data and the switching rate average value; based on the switching rate ratio, from the switching rate ratio range and switching In the corresponding relationship between the weights, the switching weight of the user account to the played multimedia data is determined. 2. The method of claim 1, wherein the acquisition of the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database comprises: For each multimedia data in the plurality of multimedia data, determine the data duration of the multimedia data and the data frequency of the multimedia data in multiple units of time within the data duration; determining the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the plurality of unit times; Based on the frequency average value, the rhythm level information of the multimedia data is acquired from the stored correspondence between the frequency average value range and the rhythm level information. 3. method as claimed in claim 1, is characterized in that, described based on the play duration average value of each multimedia data in described playing quantity, described played multimedia data, described user account number to played multimedia The switching weight of the data, the grade weight of each multimedia data in the played multimedia data, and the user age of the user account, determine the character characteristic value of the user account, including: Based on the number of playbacks, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and each multimedia data in the played multimedia data The level weight of the user account and the user age of the user account are determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, the C is the character characteristic value of the user account, the n is the number of playbacks, and the D(i) is the playback duration of the i-th multimedia data in the n pieces of multimedia data Average value, the Pace(i) is the grade weight of the i-th multimedia data, the frequency is the switching weight of the user account to the played multimedia data, and the age is the user age of the user account . 4. A multimedia data push device, wherein the device comprises: an acquisition module, to acquire the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database; a determination module, comprising: a second acquisition unit, a third determination unit, a calculation unit and a fourth determination unit; The second acquisition unit is used for each user account in the plurality of user accounts, and for each multimedia data in the multimedia data that has been played by the user account in the plurality of multimedia data within a specified time period , based on the rhythm grade information of the multimedia data, obtain the grade weight of the multimedia data from the stored correspondence between the rhythm grade information and the grade weight; The third determination unit is used to determine the playback quantity of the played multimedia data, the total playback duration of each multimedia data in the played multimedia data, and the user account's response to the played multimedia data. The switching weight of the user account and the user age of the user account, the playing quantity of each multimedia data includes the playing quantity when the each multimedia data is played online and the playing quantity when playing offline, and the playing quantity of the each multimedia data. The total playing time includes the total playing time when each multimedia data is played online and the total playing time when playing offline; The computing unit is used to divide the total playing duration of each multimedia data in the played multimedia data by the user age of the user account to obtain the playing duration of each multimedia data in the played multimedia data. average value; The fourth determining unit is configured to, based on the number of plays, the average play duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, the The grade weight of each multimedia data and the user age of the user account in the played multimedia data, determine the character characteristic value of the user account; a selection module, comprising: a third acquisition unit, a fifth determination unit, a sixth determination unit, a fourth acquisition unit and a selection unit; The third obtaining unit is used to obtain the character characteristic values of all registered user accounts; The fifth determining unit is configured to determine the average value of the character characteristics, and the average value of the character characteristics is the average value of the character characteristic values of all the registered user accounts; The sixth determining unit is used to calculate the character characteristic ratio between the character characteristic value of the user account and the character characteristic average value; In the corresponding relationship, determine the temperament type of the user account; The fourth obtaining unit is configured to obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information based on the temperament type of the user account; The selection unit is configured to select multimedia data matching the rhythm level information of the user account from the plurality of multimedia data based on the rhythm level information of each multimedia data in the plurality of multimedia data; a push module, configured to filter out the multimedia data played by the user account in the selected multimedia data, and push the remaining multimedia data after filtering to the terminal corresponding to the user account; Wherein, the third determining unit is also used for: Obtain the switching rate of each user account in the registered user accounts to the played multimedia data, after adding up the switching rates of all user accounts to the played multimedia data, divide by the number of users of all user accounts, Obtain the average value of the switching rate, and calculate the switching rate ratio between the switching rate of each user account to the played multimedia data and the switching rate average value; based on the switching rate ratio, from the switching rate ratio range and switching In the corresponding relationship between the weights, the switching weight of the user account to the played multimedia data is determined. 5. The apparatus of claim 4, wherein the acquiring module comprises: a first determining unit, configured to, for each multimedia data in the plurality of multimedia data, determine the data duration of the multimedia data and the data frequency of the multimedia data in a plurality of units of time within the data duration; a second determining unit, configured to determine the average frequency of the multimedia data based on the data duration of the multimedia data and the data frequencies in the plurality of units of time; A first acquiring unit, configured to acquire, based on the frequency average, the rhythm level information of the multimedia data from the stored correspondence between the frequency average range and the rhythm level information. 6. The apparatus of claim 4, wherein the fourth determining unit comprises: Based on the number of playbacks, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and each multimedia data in the played multimedia data The level weight of the user account and the user age of the user account are determined by the following formula to determine the character characteristic value of the user account:

Wherein, in the above formula, the C is the character characteristic value of the user account, the n is the number of playbacks, and the D(i) is the playback duration of the i-th multimedia data in the n pieces of multimedia data Average value, the Pace(i) is the grade weight of the i-th multimedia data, the frequency is the switching weight of the user account to the played multimedia data, and the age is the user age of the user account . 7. A device for pushing multimedia data, wherein the device comprises: processor; memory for storing processor-executable instructions; wherein the processor is configured to: Obtain the rhythm level information of each multimedia data in a plurality of multimedia data stored in the multimedia database; For each user account in a plurality of user accounts, and for each multimedia data in the multimedia data in the plurality of multimedia data that the user account has played within a specified time period, a rhythm level based on the multimedia data information, from the stored correspondence between the rhythm level information and the level weight, obtains the level weight of the multimedia data; Determine the playing quantity of the played multimedia data, the total playing time of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and the user account's switching weight. The age of the user, the playing quantity of each multimedia data includes the playing quantity when the each multimedia data is played online and the playing quantity when playing offline, and the total playing time of each multimedia data includes the playing quantity of each multimedia data. The total playing time of data when playing online and the total playing time when playing offline; The total playing duration of each multimedia data in the played multimedia data is divided by the user age of the user account to obtain the average playing duration of each multimedia data in the played multimedia data; Based on the number of playbacks, the average playback duration of each multimedia data in the played multimedia data, the switching weight of the played multimedia data by the user account, and each of the played multimedia data The grade weight of the multimedia data and the user age of the user account determine the character characteristic value of the user account; Get the character trait values of all registered user accounts; Determine the average value of the character characteristic, the average value of the character characteristic is the average value of the character characteristic value of all the registered user accounts; Calculate the character characteristic ratio between the character characteristic value of the user account and the character characteristic average value; based on the character characteristic ratio, determine the user account from the correspondence between the character characteristic ratio range and the temperament type type of atmosphere; Based on the temperament type of the user account, obtain the rhythm grade information of the user account from the stored correspondence between the temperament type and the rhythm grade information; Based on the rhythm level information of each multimedia data in the plurality of multimedia data, selecting multimedia data matching the rhythm level information of the user account from the plurality of multimedia data; Filtering out the multimedia data played by the user account in the selected multimedia data, and pushing the remaining multimedia data after filtering to the terminal corresponding to the user account; Wherein, the operation of determining the switching weight of the user account to the played multimedia data includes: acquiring the switching rate of each user account in the registered user accounts to the played multimedia data; After adding the switching rates of the played multimedia data, divide by the number of users of all user accounts to obtain the average switching rate, and calculate the switching rate and switching of the played multimedia data for each user account. The switching rate ratio between the rate averages; based on the switching rate ratio, the switching weight of the user account to the played multimedia data is determined from the correspondence between the switching rate ratio range and the switching weight.

Images