CN113946744A - Data processing method, device, server and storage medium - Google Patents
Data processing method, device, server and storage medium Download PDFInfo
- Publication number
- CN113946744A CN113946744A CN202010688165.8A CN202010688165A CN113946744A CN 113946744 A CN113946744 A CN 113946744A CN 202010688165 A CN202010688165 A CN 202010688165A CN 113946744 A CN113946744 A CN 113946744A
- Authority
- CN
- China
- Prior art keywords
- time interval
- multimedia data
- interactive
- user account
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 30
- 230000002452 interceptive effect Effects 0.000 claims abstract description 201
- 230000003993 interaction Effects 0.000 claims description 25
- 238000000034 method Methods 0.000 abstract description 14
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008685 targeting Effects 0.000 description 4
- 230000000717 retained effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 241000272878 Apodiformes Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/44—Browsing; Visualisation therefor
- G06F16/447—Temporal browsing, e.g. timeline
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present disclosure relates to a data processing method, apparatus, server and storage medium, the method comprising: determining a non-interactive time interval without interactive operation on a user account according to historical operation data on the user account; pushing target multimedia data to the user account in the non-interactive time interval; obtaining feedback operation of the user account on the target multimedia data; determining whether the non-interactive time interval is an untrusted time interval or not according to the feedback operation; and when the non-interactive time interval is determined to be the non-confidence time interval, processing the historical multimedia data with the recording time falling into the non-confidence time interval. According to the embodiment, the accuracy of predicting the multimedia data conforming to the user by using the historical multimedia data can be improved, so that the multimedia data can be accurately pushed.
Description
Technical Field
The present disclosure relates to the field of internet technologies, and in particular, to a data processing method, an apparatus, a server, and a storage medium.
Background
At present, there are many media playing APPs (applications), and a user can select favorite multimedia data (such as music or pictures) to listen to or watch through the media playing APPs; these media playing APPs usually form a song list by collecting multimedia data (i.e., historical multimedia data) that a user has listened to or watched historically, so as to predict and recommend multimedia data that matches the user. Therefore, the multimedia data recommended to the user by the media playing APP strongly depends on the historical multimedia data of the user collected by the media playing APP, so that the reasonable collection of the historical multimedia data to predict the multimedia data conforming to the user is very important.
In practical applications, although historical multimedia data under various scenes can be collected, under some scenes, such as driving and rest of a user, the user usually does not interfere with the playing of the multimedia data of the media playing APP, and at this time, the collected historical multimedia data does not really conform to the multimedia data of the user, and if the historical multimedia data is used to predict the multimedia data conforming to the user, a negative effect is exerted on the prediction result. Therefore, how to reasonably process the historical multimedia data so as to improve the accuracy of predicting the multimedia data which conforms to the user is an urgent problem to be solved.
Disclosure of Invention
The present disclosure provides a data processing method, apparatus, server and storage medium to at least solve the problem of how to reasonably process historical multimedia data in the related art, thereby improving the accuracy of predicting multimedia data that conforms to a user. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a data processing method, including:
determining a non-interactive time interval without interactive operation on a user account according to historical operation data on the user account;
pushing target multimedia data to the user account in the non-interactive time interval;
obtaining feedback operation on the target multimedia data on the user account;
determining whether the non-interactive time interval is an untrusted time interval or not according to the feedback operation; the historical multimedia data with the non-confidence time interval representing and recording time falling into cannot reflect the multimedia characteristic information of the user account;
when the non-interactive time interval is determined to be an untrusted time interval, processing the historical multimedia data of which the recording time falls within the untrusted time interval.
In one embodiment, after the determining whether the non-interaction time interval is an untrusted time interval according to the feedback operation, the method further includes:
when the non-interactive time interval is determined to be a confidence time interval, processing the historical multimedia data of which the recording time falls into the confidence time interval.
In one embodiment, the determining, according to the historical operation data, a non-interactive time interval in which there is no interactive operation on the user account includes:
acquiring historical operation data; the historical operation data comprises interactive operation on a user account and operation time corresponding to the interactive operation;
acquiring a time interval between the operation time of the adjacent interactive operation;
counting overlapped time intervals overlapped among a plurality of time intervals;
and taking the overlapping time interval as a non-interactive time interval.
In one embodiment, the regarding the overlapping time interval as a non-interactive time interval includes:
and taking the overlapping time interval with the time length larger than a preset threshold value as a non-interactive time interval.
In one embodiment, the pushing target multimedia data to the user account in the non-interactive time interval includes:
receiving a multimedia data random recommendation instruction sent by the user account; the multimedia data random recommendation instruction comprises instruction sending time;
when the instruction sending time falls into the non-interactive time interval, target multimedia data are obtained; the target multimedia data is multimedia data which cannot meet the multimedia characteristic information of the user account;
and pushing the target multimedia data to the user account.
In one embodiment, the feedback operation includes a handover operation on the target multimedia data, and the determining whether the non-interactive time interval is an untrusted time interval according to the feedback operation includes:
determining whether the switching operation of the target multimedia data in the non-interactive time interval reaches a preset switching frequency;
if the switching operation does not reach the preset switching frequency, determining the non-interactive time interval as an untrusted time interval;
and if the switching operation reaches a preset switching frequency, determining the non-interactive time interval as a confidence time interval.
In one embodiment, the feedback operation includes a fast forward operation on the target multimedia data, and the determining whether the non-interactive time interval is an untrusted time interval according to the feedback operation includes:
determining whether the fast forward operation on the target multimedia data in the non-interactive time interval reaches a preset fast forward frequency;
if the fast forward operation does not reach the preset fast forward frequency, determining the non-interactive time interval as an untrusted time interval;
and if the fast forwarding operation reaches a preset fast forwarding frequency, determining the non-interactive time interval as a confidence time interval.
In one embodiment, when the non-interactive time interval is determined to be an untrusted time interval, processing the historical multimedia data with the recording time falling within the untrusted time interval includes:
when the non-interactive time interval is determined to be an untrusted time interval, removing multimedia data by taking the historical multimedia data with the recording time falling into the untrusted time interval as a target;
using the historical multimedia data except the target removal multimedia data as multimedia data for predicting multimedia feature information satisfying the user account.
In one embodiment, when the non-interactive time interval is determined to be a confidence time interval, processing the historical multimedia data whose recording time falls within the confidence time interval includes:
when the non-interactive time interval is determined to be a confidence time interval, reserving the historical multimedia data with the recording time falling into the confidence time interval as a target to reserve the multimedia data;
and using the target reserved multimedia data as multimedia data for predicting multimedia characteristic information meeting the user account.
According to a second aspect of the embodiments of the present disclosure, there is provided a data processing apparatus including:
the non-interaction time interval determining unit is configured to execute non-interaction time intervals, wherein the non-interaction time intervals are determined to be free of interaction operation on the user account according to historical operation data on the user account;
a target multimedia data pushing unit configured to perform pushing of target multimedia data to the user account during the non-interactive time interval;
a feedback operation acquisition unit configured to perform a feedback operation of acquiring the target multimedia data on the user account;
an untrusted time interval determination unit configured to perform determining whether the untrusted time interval is an untrusted time interval according to the feedback operation; the historical multimedia data with the non-confidence time interval representing and recording time falling into cannot reflect the multimedia characteristic information of the user account;
a first history multimedia data processing unit configured to perform processing the history multimedia data of which the recording time falls within an untrusted time interval when the untrusted time interval is determined to be an untrusted time interval.
In one embodiment, the apparatus further comprises:
a second history multimedia data processing unit configured to perform processing of the history multimedia data of which the recording time falls within a confidence time interval when the non-interactive time interval is determined to be the confidence time interval.
In one embodiment, the non-interactive time interval determination unit is further configured to perform obtaining historical operation data; the historical operation data comprises interactive operation on a user account and operation time corresponding to the interactive operation; acquiring a time interval between the operation time of the adjacent interactive operation; counting overlapped time intervals overlapped among a plurality of time intervals; and taking the overlapping time interval as a non-interactive time interval.
In one embodiment, the non-interactive time interval determining unit is further configured to perform the overlapping time interval with a time length greater than a preset threshold as the non-interactive time interval.
In one embodiment, the target multimedia data pushing unit is further configured to execute a multimedia data random recommendation instruction sent by receiving the user account; the multimedia data random recommendation instruction comprises instruction sending time; when the instruction sending time falls into the non-interactive time interval, target multimedia data are obtained; the target multimedia data is multimedia data which cannot meet the multimedia characteristic information of the user account; and pushing the target multimedia data to the user account.
In one embodiment, the feedback operation includes a handover operation on the target multimedia data, and the untrusted time interval determination unit is further configured to perform determining whether the handover operation on the target multimedia data in the non-interactive time interval reaches a preset handover frequency; if the switching operation does not reach the preset switching frequency, determining the non-interactive time interval as an untrusted time interval; and if the switching operation reaches a preset switching frequency, determining the non-interactive time interval as a confidence time interval.
In one embodiment, the feedback operation includes a fast forward operation on the target multimedia data, and the untrusted time interval determination unit is further configured to perform determining whether the fast forward operation on the target multimedia data in the untrusted time interval reaches a preset fast forward frequency; if the fast forward operation does not reach the preset fast forward frequency, determining the non-interactive time interval as an untrusted time interval; and if the fast forwarding operation reaches a preset fast forwarding frequency, determining the non-interactive time interval as a confidence time interval.
In one embodiment, the first historical multimedia data processing unit is further configured to perform, when the non-interaction time interval is determined to be an untrusted time interval, removing multimedia data targeting historical multimedia data whose recording time falls within the untrusted time interval; using the historical multimedia data except the target removal multimedia data as multimedia data for predicting multimedia feature information satisfying the user account.
In one embodiment, the second historical multimedia data processing unit is further configured to perform, when the non-interactive time interval is determined to be a confidence time interval, targeting the historical multimedia data of which the recording time falls within the confidence time interval to retain the multimedia data; and using the target reserved multimedia data as multimedia data for predicting multimedia characteristic information meeting the user account.
According to a third aspect of the embodiments of the present disclosure, there is provided a server, including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the data processing method of the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a storage medium including: the instructions in the storage medium, when executed by a processor of a server, enable the server to perform the data processing method of the first aspect described above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product, the program product comprising a computer program, the computer program being stored in a readable storage medium, from which at least one processor of a device reads and executes the computer program, so that the device performs the data processing method of the first aspect described above.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
in the embodiment of the disclosure, according to historical operation data of a user account on historical multimedia data, a non-interactive time interval without interactive operation on the user account is determined, and then target multimedia data is pushed to the user account in the non-interactive time interval, wherein the non-interactive time interval is a time interval in which the user account does not normally execute operation, so that whether the non-interactive time interval is an untrusted time interval or not can be determined according to feedback operation, and when the non-interactive time interval is determined to be the untrusted time interval, historical multimedia data with corresponding processing recording time falling into the untrusted time interval is determined. In this embodiment, whether the non-interactive time interval is the untrusted time interval is determined according to the feedback operation of the user account on the target multimedia data in the non-interactive time interval, and the historical multimedia data falling into the untrusted time interval is processed reasonably according to whether the non-interactive time interval is the untrusted time interval, so that the accuracy of predicting the multimedia data conforming to the user by using the historical multimedia data is improved, and the accurate pushing of the multimedia data is further realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a diagram illustrating an application environment for a method of data processing, according to an exemplary embodiment.
FIG. 2 is a flow chart illustrating a method of data processing according to an exemplary embodiment.
FIG. 3 is a flow chart illustrating another method of data processing according to an example embodiment.
FIG. 4 is a block diagram illustrating a data processing apparatus according to an example embodiment.
Fig. 5 is an internal block diagram of a server according to an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The data processing method provided by the present disclosure may be applied to the application environment shown in fig. 1. Wherein the terminal 110 interacts with the server 120 through the network. The server 120 determines a non-interactive time interval without interactive operation on the user account according to historical operation data of the user account on the historical multimedia data, pushes target multimedia data to the user account in the non-interactive time interval, and obtains feedback operation of the user account on the target multimedia data, so that whether the non-interactive time interval is an untrusted time interval or not is determined according to the feedback operation, and when the non-interactive time interval is the untrusted time interval, the historical multimedia data with recording time falling into the untrusted time interval is processed.
The terminal 110 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 120 may be implemented by an independent server or a server cluster formed by a plurality of servers.
Fig. 2 is a flowchart illustrating a data processing method according to an exemplary embodiment, where the data processing method is used in the server 120, as shown in fig. 2, and includes the following steps.
In step S210, a non-interactive time interval in which no interactive operation exists on the user account is determined according to the historical operation data on the user account.
Specifically, the user account can log in an APP, such as a media playing APP like a music player, on the terminal by using the user account, when listening to multimedia data, the multimedia data is recorded as historical multimedia data on the APP, and recording time corresponding to the historical multimedia data is recorded, and then the historical multimedia data and the recording time of the user account can be collected and uploaded to the server for storage. Therefore, after the user account uses APP for a period of time, a large amount of historical multimedia data of the user account can be collected at the server.
The multimedia data may include music, pictures, videos, animations, and the like, and the historical multimedia data refers to music, pictures, videos, animations, and the like that have been listened to or watched through a certain user account.
In practical application, in order to push more multimedia data which accord with user preferences corresponding to the user account for the user account, historical multimedia data collected on an APP can be used as sample data, and the sample data is input into a recommendation algorithm to predict the multimedia data which accord with the user account and push the multimedia data; however, some historical multimedia data that are not really liked by the user account may affect the accuracy of the prediction result if all the historical multimedia data are used as sample data and input to the recommendation algorithm together for predicting the multimedia data that satisfy the user account, and therefore, the historical multimedia data need to be filtered.
In this embodiment, the interactive operation of the user account is recorded in the server, and the interactive operation includes, but is not limited to, a click operation, a press operation, a slide operation, a gesture operation, and the like, where an operation object of the interactive operation refers to the user account, specifically, refers to any APP of the user account, such as a media playing APP, a reading APP, and the like. Of course, the embodiment may also be limited to only the interactive operation recorded on the media playing APP of the user account.
Specifically, for example, click operation when starting the APP or agreeing on the multimedia data, press operation when starting the recognition function, slide operation when switching the multimedia data, or other interactive operations that can pass through gesture operation and APP, the user account interacts once with the APP each time, and the APP can all record the interactive operation corresponding to the user account and upload to the server.
In practical application, when a user uses an APP for a period of time through a user account, the interactive operation on the user account has a relevant record in a server during the period of time; in this embodiment, according to a certain fixed period, for example, three days or one week, the interactive operation and the operation time in this period are extracted and analyzed, and a rule is searched to find a non-interactive time interval in which no interactive operation exists on the user account.
The non-interactive time interval refers to a time interval within which the user account does not perform any interactive operation on the APP, and at this time, the user of the user account may be in a scene of driving, resting, and the like, such as 8: 30-9: 00, the user may be traveling on the drive-in-work trip, e.g., 10: 00-11:00, the user may be at rest, so interaction with APP is not usually done.
In step S212, the target multimedia data is pushed to the user account during the non-interactive time interval.
In this embodiment, after the non-interactive time interval is determined, the server pushes the target multimedia data to the user account in the non-interactive time interval, and the user account can play the target multimedia data through the APP after receiving the target multimedia data. Wherein the target multimedia data may be multimedia data that is not liked by the user account. For example, taking music as an example, assuming that the user account is predicted not to like classical music, classical music such as "swan lake", "moonlight song", "hummingbird" and the like may be pushed in the non-interactive time interval.
The server predicts the favorite multimedia data of the user account according to the historical multimedia data uploaded by the user account, so that the multimedia data conforming to the user account and the multimedia data not conforming to the user account can be obtained; the multimedia data that does not conform to the user account is the target multimedia data of the embodiment. Specifically, the target multimedia data may be predicted by inputting historical multimedia data of a certain period of time in the past as sample data into a recommendation algorithm, for example, the historical multimedia data of the sample data may be adjusted according to an actual situation, which is not limited in this embodiment.
In addition, the target multimedia data can also be multimedia data which is manually marked by the user and is not liked, and the marked multimedia data can be pushed to the user account to be played in a non-interactive time interval as the target multimedia data.
In step S214, a feedback operation of the user account on the target multimedia data is acquired.
After finding out a regular non-interactive time interval, the embodiment randomly pushes the multimedia data predicted at present as target multimedia data to a user account and plays the target multimedia data in the non-interactive time interval; and recording and uploading feedback operation of the user account to the server during the playing of the target multimedia data in the non-interactive time interval. Wherein the feedback operation may be a music switching operation or a fast forward operation.
In step S216, determining whether the non-interactive time interval is an untrusted time interval according to the feedback operation; the non-confidence time interval represents that the historical multimedia data with the recording time falling into the data can not reflect the multimedia characteristic information of the user account.
The non-interactive time interval refers to a time interval in which interactive operation is not usually performed on the user account, and since the user of the user account may be at rest or in a driving process in the time interval, if the feedback operation on the user account is recorded in the non-interactive time interval, it is indicated that the feedback operation in the non-interactive time interval is capable of reflecting the multimedia feature information of the user account, and therefore, whether the non-interactive time interval is the non-confidence time interval or not can be determined according to the feedback operation on the target multimedia data by the user account in the non-interactive time interval.
Specifically, the multimedia feature information refers to information such as a data type, a playing time, an author, and the like corresponding to the multimedia data that can reflect the user account. For example, if the multimedia data is music, the data type corresponding to the music may be a pop music type, the playing time may be 3-5 minutes, and the author may be a singer or composer singing the music.
In this embodiment, the untrusted time interval refers to historical multimedia data recorded in the time interval, which may be listened to or watched during a user rest or driving corresponding to the user account, and since the user does not usually perform an interactive operation on the user account in the time interval, the historical multimedia data in the time interval is untrusted, and if the historical multimedia data is used as sample data, the predicted result of the multimedia data will be negatively affected.
In step S218, when the non-interactive time interval is determined as the untrusted time interval, the history multimedia data whose recording time falls within the untrusted time interval is processed.
In this embodiment, after the non-interactive time interval is determined to be the untrusted time interval, the historical multimedia data with the recording time falling into the untrusted time interval may be processed from the historical multimedia data collected by the media play APP, for example, the historical multimedia data with the recording time falling into the untrusted time interval may be filtered from the historical multimedia data collected by the media play APP, so as to extract the historical multimedia data that can be used for prediction, thereby improving the accuracy of predicting the multimedia data that conforms to the user.
In the data processing method, whether the non-interactive time interval is the non-confidence time interval or not is determined according to the feedback operation of the user on the target multimedia data in the non-interactive time interval, and the historical multimedia data falling into the non-confidence time interval is reasonably processed according to whether the non-interactive time interval is the non-confidence time interval, so that the accuracy of predicting the multimedia data conforming to the user by utilizing the historical multimedia data is improved, and the accurate pushing of the multimedia data is realized.
Fig. 3 is a flow chart illustrating another data processing method according to an exemplary embodiment, and as shown in fig. 3, the data processing method is used in the server 120, and includes the following steps:
in step S310, a non-interactive time interval in which no interactive operation exists on the user account is determined according to the historical operation data on the user account.
In this embodiment, when the user account listens to the multimedia data, the multimedia data is recorded as historical multimedia data, and the recording time corresponding to the historical multimedia data is uploaded to the server for storage. The historical multimedia data may be used to predict multimedia data that conforms to the user account.
The historical operation record comprises interactive operation on the user account and operation time corresponding to the interactive operation, wherein the interactive operation does not exist on the user account in a time interval between adjacent interactive operations, so that a non-interactive time interval in which the interactive operation does not exist on the user account can be further determined based on the time interval between adjacent interactive operations.
In an exemplary embodiment, in step S310, determining, according to historical operation data of the user account, a non-interaction time interval in which no interactive operation exists for the user account may specifically include:
acquiring historical operation data; the historical operation data comprises interactive operation on the user account and operation time corresponding to the interactive operation;
acquiring a time interval between operation times of adjacent interactive operations;
counting overlapped time intervals overlapped among the multiple time intervals;
the overlapping time interval is taken as a non-interactive time interval.
In this embodiment, the non-interactive time interval may be determined by analyzing and counting historical operation data during a specified period, such as historical operation data during a week or a month.
Specifically, a plurality of time intervals are determined according to the operation time between adjacent interactive operations in the historical operation data. For example, if the user a operates the APP at 9:00, does not perform any interaction with the user account of the APP for the subsequent 40 minutes, and then performs interaction again with the APP at 9:40, the time interval between the adjacent interactions is 9:00-9: 40. It is understood that since there is no interactive operation in the time interval 9:00-9:40, the time interval is a time interval in which there is no interactive operation, and can be used to further determine whether it is a non-interactive time interval.
And after the plurality of time intervals are obtained, taking the overlapping time interval with overlapping in the plurality of time intervals as the non-interactive time interval. Three days are taken as a specified period, and the time interval between adjacent interactive operations counted on the first day is assumed to be 9:00-9:40, 12: 00-12: 50, 17: 00-17: 30, the time interval between adjacent interoperation counted the next day is 9:00-9: 30, 12: 00-12: 20, 16: 00-17: 00, the time interval between adjacent interoperation counted on the third day is 9:00-9: 30, 12: 00-12: 30, 17: 00-17: from 30, it can be counted that the overlap time interval is 9:00-9: 30 and 12: 00-12: 20.
in this embodiment, by specifying the time interval between adjacent interactive operations in the period, the time interval in which no interactive operation is performed on the user account regularly can be found as the non-interactive time interval.
In an exemplary embodiment, in step S310, determining, according to historical operation data of the user account, a non-interaction time interval in which no interactive operation exists for the user account, which may specifically include:
and taking the overlapping time interval with the time length larger than the preset threshold value as a non-interactive time interval.
Optionally, in this embodiment, the overlapping time interval is found by using the time interval between the interactive operations in the specified period, but if the overlapping time intervals are all regarded as the non-interactive time intervals, for example, the overlapping time interval with a short time length is regarded as the non-interactive time interval, which is not beneficial to subsequently recording the feedback operation on the user account, so that the overlapping time interval with a time length greater than the preset threshold is regarded as the non-interactive time interval.
For example, assuming that the preset threshold is set to 30 minutes, it is assumed that an overlap time interval of 9 is obtained: 00-9: 30 and 12: 00-12: 20, due to overlapping time intervals 12: 00-12: 20 less than 30 minutes, overlapping time interval 9:00-9: 30 is greater than 30 minutes, so the overlap time interval 9:00-9: 30 as non-interactive time intervals.
In step S312, the target multimedia data is pushed to the user account during the non-interactive time interval.
When a user logs in a media playing APP through a user account, the user can randomly listen to multimedia data, namely, the user enters a random recommendation mode, and at the moment, the server can randomly push the multimedia data to the user account.
In an exemplary embodiment, step 312, pushing the target multimedia data to the user account in the non-interactive time interval may specifically include:
receiving a multimedia data random recommendation instruction sent by a user account; the multimedia data random recommendation instruction comprises instruction sending time;
when the instruction sending time falls into a non-interactive time interval, acquiring target multimedia data;
and pushing the target multimedia data to the user account.
The target multimedia data is multimedia data which cannot meet the multimedia characteristic information of the user account, specifically multimedia data which does not meet the user account, namely multimedia data which is disliked by the user account.
In this embodiment, after the non-interactive time interval is determined, since the multimedia data conforming to the user account is already predicted, the multimedia data not conforming to the user account can be obtained, and the multimedia data not conforming to the user account is pushed to the user account for playing in the non-interactive time interval.
It can be understood that if the multimedia data that does not conform to the user account is played in the non-interactive time interval, for example, the multimedia data that does not conform to the user account is played while listening to locally downloaded music, which may cause a sense of incongruity to the user, therefore, the present embodiment is configured to enter a multimedia data random recommendation mode (e.g., a music random recommendation mode) and send the target multimedia data to the user account randomly in the non-interactive time interval, so that the multimedia data that does not conform to the user account is played on the APP, so as to further obtain a feedback operation on the target multimedia data on the user account in the non-interactive time interval.
In step S314, a feedback operation on the target multimedia data on the user account is acquired.
In step S316, it is determined whether the non-interactive time interval is an untrusted time interval according to the feedback operation.
In this embodiment, the non-interactive time interval is a time interval in which an interactive operation is not usually performed on the user account, and therefore, if a feedback operation is found in the non-interactive time interval, it is indicated that the feedback operation in the non-interactive time interval is in a state of expressing the preference of the user for the multimedia data, so that the feedback operation in the non-interactive time interval can be obtained, and it is determined whether the non-interactive time interval is an untrusted time interval, that is, it is determined whether the historical multimedia data whose recording time falls in the non-interactive time interval is authentic and can be used as sample data.
In an exemplary embodiment, in step S316, the feedback operation includes a switching operation on the target multimedia data, and determining whether the non-interaction time interval is the untrusted time interval according to the feedback operation may specifically include:
determining whether the switching operation of the target multimedia data in the non-interactive time interval reaches a preset switching frequency;
if the switching operation does not reach the preset switching frequency, determining the non-interactive time interval as an untrusted time interval;
and if the switching operation reaches the preset switching frequency, determining the non-interactive time interval as a confidence time interval.
The feedback operation on the target multimedia data includes a switching operation on the target multimedia data, and the preset switching frequency may be one time, two times, or three times, which is not limited in this embodiment.
In this embodiment, when the target multimedia data is continuously pushed to the user account in the non-interactive time interval, that is, the multimedia data that the user account does not like is the target multimedia data, if the user account does not perform the switching operation on the disliked multimedia data and continuously pushes the disliked multimedia data of the user account for several times, for example, three times, and the user account does not perform the switching operation, the non-interactive time interval is an untrusted time interval, so that the historical multimedia data whose recording time falls into the untrusted time interval is untrusted; if the user account performs switching operation on the disliked multimedia data, and the user account performs switching operation continuously for several times, for example, continuously pushes the disliked multimedia data of the user account for three times, the non-interactive time interval is a confidence time interval, and therefore historical multimedia data with recording time falling into the confidence time interval is credible.
In an exemplary embodiment, in step S316, the feedback operation includes a fast forward operation on the target multimedia data, and determining whether the non-interactive time interval is an untrusted time interval according to the feedback operation specifically includes:
determining whether a fast forward operation on the target multimedia data in a non-interactive time interval reaches a preset fast forward frequency;
if the fast forward operation does not reach the preset fast forward frequency, determining the non-interactive time interval as an untrusted time interval;
and if the fast forward operation reaches the preset fast forward frequency, determining the non-interactive time interval as a confidence time interval.
The feedback operation on the target multimedia data includes a fast forward operation on the target multimedia data, and the preset fast forward frequency may be one time, two times, or three times.
In this embodiment, when target multimedia data, that is, multimedia data that is not preferred by a user account, is continuously pushed to the user account in a non-interactive time interval, if the user account does not perform a fast-forward operation on the preferred multimedia data for several times, for example, the preferred multimedia data is continuously pushed for three times, and the user account does not perform the fast-forward operation, it indicates that the non-interactive time interval is an untrusted time interval, and further indicates that historical multimedia data whose recording time falls into the untrusted time interval is untrusted; if the user account carries out fast forward operation on the disliked multimedia data for several times, for example, pushes the disliked multimedia data for three times, and the user account carries out fast forward operation, the non-interaction time interval is a confidence time interval, and historical multimedia data with the recording time falling into the confidence time interval is credible.
Of course, in addition to determining whether the time interval is an untrusted time interval through the switching operation or the fast forwarding operation, or through a combination of the switching operation and the fast forwarding operation, it may also be determined whether the time interval is an untrusted time interval according to other feedback operations, which is not limited in this embodiment.
In step S318, when the non-interactive time interval is determined as the untrusted time interval, the process records the history multimedia data whose time falls within the untrusted time interval.
The historical multimedia data with the recording time falling into the untrusted time interval is not trusted, so that the historical multimedia data with the recording time falling into the untrusted time interval can be processed, such as filtering, to obtain historical multimedia data for prediction, i.e. sample data for inputting a recommendation algorithm.
In an exemplary embodiment, in step S318, when the non-interaction time interval is determined as the untrusted time interval, the processing the historical multimedia data whose recording time falls into the untrusted time interval may specifically include:
when the non-interactive time interval is determined to be an untrusted time interval, removing the multimedia data by taking the historical multimedia data with the recording time falling into the untrusted time interval as a target;
and using the historical multimedia data except the target removal multimedia data as the multimedia data for predicting the multimedia characteristic information meeting the user account.
The multimedia data meeting the multimedia characteristic information of the user account refers to multimedia data conforming to the user account, that is, multimedia data liked by the user account.
For the historical multimedia data falling into the untrusted time interval, the user preference cannot be reflected, so that the historical multimedia data is not suggested to be used for prediction, the historical multimedia data of the untrusted time interval can be used as the target to remove the multimedia data, and other historical multimedia data except the target to remove the multimedia data can be used as the historical multimedia data for prediction, namely, sample data for inputting a recommendation algorithm, so that the prediction accuracy of the multimedia data can be improved.
For example, assume that the recording time of the historical multimedia data is 20: 30, the untrusted time interval is 20:00-21:00, and if the recording time falls into the untrusted time interval, the historical multimedia data can be removed as the target removal multimedia data.
In step S320, when the non-interactive time interval is determined as the confidence time interval, the process records the history multimedia data whose time falls within the confidence time interval.
The historical multimedia data with the recording time falling into the confidence time interval is credible, so that the historical multimedia data with the recording time falling into the confidence time interval can be processed to obtain historical multimedia data for prediction, namely sample data for inputting a recommendation algorithm.
In an exemplary embodiment, in step S320, when the non-interaction time interval is determined as a confidence time interval, the processing the historical multimedia data whose recording time falls within the confidence time interval may specifically include:
when the non-interactive time interval is determined as the confidence time interval, taking the historical multimedia data with the recording time falling into the confidence time interval as target reserved multimedia data;
and reserving the target reserved multimedia data as multimedia data for predicting multimedia characteristic information meeting the user account.
The multimedia data meeting the multimedia characteristic information of the user account refers to multimedia data conforming to the user account, that is, multimedia data liked by the user account.
The historical multimedia data falling into the confidence time interval can reflect the preference of the user account, so that the historical multimedia data is suggested to be used for prediction, the historical multimedia data in the confidence time interval can be used as target reserved multimedia data, only the target reserved multimedia data is used as the historical multimedia data for prediction, namely sample data for inputting a recommendation algorithm, and the prediction accuracy of the multimedia data can be improved.
For example, assume that the recording time of the historical multimedia data is 20:00, the confidence time interval is 19:00-20:00, and if the recording time falls into the confidence time interval, the historical multimedia data can be reserved as target reserved multimedia data.
Of course, the above processing method of only using the target retained multimedia data as the historical multimedia data for prediction may be used when the amount of the historical multimedia data is large, and when the historical multimedia data is rare, the processing method of removing the target retained multimedia data from the historical multimedia data and then using the removed target retained multimedia data as the historical multimedia data for prediction may be selected according to actual conditions, and the processing method may be flexibly changed.
In the embodiment, historical multimedia data listened to by a user account is collected, and the historical multimedia data of a confidence time interval or an untrusted time interval in which the recording time falls is identified through statistical analysis, so that historical multimedia data which can be used for prediction can be further obtained from the historical multimedia data according to the confidence time interval or the untrusted time interval.
It should be understood that although the various steps in the flow charts of fig. 2-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-3 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
FIG. 4 is a block diagram illustrating a data processing apparatus according to an example embodiment. Referring to fig. 4, the apparatus includes a non-interactive time interval determination unit 410, a target multimedia data pushing unit 412, a feedback operation acquisition unit 414, an untrusted time interval determination unit 416, and a first history multimedia data processing unit 418.
A non-interaction time interval determination unit 410 configured to perform determining a non-interaction time interval in which no interaction operation exists for the user account according to the historical operation data for the user account.
A target multimedia data pushing unit 412 configured to perform pushing of the target multimedia data to the user account during the non-interactive time interval.
A feedback operation obtaining unit 414 configured to perform a feedback operation of obtaining the target multimedia data by the user account.
An untrusted time interval determination unit 416 configured to perform determining, according to a feedback operation, whether the untrusted time interval is an untrusted time interval; the non-confidence time interval represents that the historical multimedia data with the recording time falling into the data can not reflect the multimedia characteristic information of the user account.
A first history multimedia data processing unit 418 configured to perform processing of history multimedia data whose recording time falls within an untrusted time interval when the untrusted time interval is determined as the untrusted time interval.
In one embodiment, the data processing apparatus further includes:
and the second historical multimedia data processing unit is configured to process the historical multimedia data of which the recording time falls into the confidence time interval when the non-interactive time interval is determined as the confidence time interval.
In one embodiment, the non-interaction time interval determination unit 410 is further configured to perform obtaining historical operation data; the historical operation data comprises interactive operation on the user account and operation time corresponding to the interactive operation; acquiring a time interval between operation times of adjacent interactive operations; counting overlapped time intervals overlapped among the multiple time intervals; the overlapping time interval is taken as a non-interactive time interval.
In one embodiment, the non-interactive time interval determining unit 410 is further configured to perform an overlapping time interval with a time length greater than a preset threshold as the non-interactive time interval.
In one embodiment, the target multimedia data pushing unit 412 is further configured to execute a multimedia data random recommendation instruction sent by the receiving user account; the multimedia data random recommendation instruction comprises instruction sending time; when the instruction sending time falls into a non-interactive time interval, acquiring target multimedia data; the target multimedia data is multimedia data which cannot meet the multimedia characteristic information of the user account; and pushing the target multimedia data to the user account.
In one embodiment, the feedback operation includes a handover operation on the target multimedia data, and the untrusted time interval determining unit 416 is further configured to perform determining whether the handover operation on the target multimedia data in the non-interactive time interval reaches a preset handover frequency; if the switching operation does not reach the preset switching frequency, determining the non-interactive time interval as an untrusted time interval; and if the switching operation reaches the preset switching frequency, determining the non-interactive time interval as a confidence time interval.
In one embodiment, the feedback operation includes a fast forward operation on the target multimedia data, and the untrusted time interval determination unit 416 is further configured to perform determining whether the fast forward operation on the target multimedia data in the non-interactive time interval reaches a preset fast forward frequency; if the fast forward operation does not reach the preset fast forward frequency, determining the non-interactive time interval as an untrusted time interval; and if the fast forward operation reaches the preset fast forward frequency, determining the non-interactive time interval as a confidence time interval.
In one embodiment, the first historical multimedia data processing unit 418 is further configured to perform removing the multimedia data targeting the historical multimedia data having the recording time falling within the untrusted time interval when the untrusted time interval is determined as the untrusted time interval; and using the historical multimedia data except the target removal multimedia data as the multimedia data for predicting the multimedia characteristic information meeting the user account.
In one embodiment, the second history multimedia data processing unit is further configured to perform, when the non-interactive time interval is determined to be a confidence time interval, retaining the multimedia data targeting the history multimedia data whose recording time falls within the confidence time interval; and reserving the target reserved multimedia data as multimedia data for predicting multimedia characteristic information meeting the user account.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 5 is a block diagram illustrating an apparatus 500 for performing the above-described data processing method according to an exemplary embodiment. For example, the device 500 may be a server. Referring to fig. 5, device 500 includes a processing component 520 that further includes one or more processors and memory resources, represented by memory 522, for storing instructions, such as applications, that are executable by processing component 520. The application programs stored in memory 522 may include one or more modules that each correspond to a set of instructions. Further, the processing component 520 is configured to execute instructions to perform the data processing method described above.
The device 500 may also include a power component 524 configured to perform power management for the device 500, a wired or wireless network interface 525 configured to connect the device 500 to a network, and an input/output (I/O) interface 528. Device 500 may operate based on an operating system stored in memory 522 such as Window 55 over, Mac O5X, Unix, Linux, FreeB5D, or the like.
In an exemplary embodiment, a storage medium comprising instructions, such as the memory 522 comprising instructions, executable by the processor of the device 500 to perform the above-described method is also provided. The storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, there is also provided a computer program product, the program product comprising a computer program stored in a readable storage medium, from which at least one processor of a device reads and executes the computer program, causing the device to perform the data processing method described in any one of the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A data processing method, comprising:
determining a non-interactive time interval without interactive operation on a user account according to historical operation data on the user account;
pushing target multimedia data to the user account in the non-interactive time interval;
obtaining feedback operation of the user account on the target multimedia data;
determining whether the non-interactive time interval is an untrusted time interval or not according to the feedback operation; the historical multimedia data with the non-confidence time interval representing and recording time falling into cannot reflect the multimedia characteristic information of the user account;
when the non-interactive time interval is determined to be an untrusted time interval, processing the historical multimedia data of which the recording time falls within the untrusted time interval.
2. The data processing method of claim 1, wherein after the determining whether the non-interaction time interval is an untrusted time interval according to the feedback operation, further comprising:
when the non-interactive time interval is determined to be a confidence time interval, processing the historical multimedia data of which the recording time falls into the confidence time interval.
3. The data processing method of claim 1, wherein the determining, according to the historical operation data for the user account, the non-interactive time interval for which there is no interactive operation for the user account comprises:
acquiring historical operation data; the historical operation data comprises interactive operation on the user account and operation time corresponding to the interactive operation;
acquiring a time interval between the operation time of the adjacent interactive operation;
counting overlapped time intervals overlapped among a plurality of time intervals;
and taking the overlapping time interval as a non-interactive time interval.
4. The data processing method of claim 1, wherein the pushing of the target multimedia data to the user account during the non-interactive time interval comprises:
receiving a multimedia data random recommendation instruction sent by the user account; the multimedia data random recommendation instruction comprises instruction sending time;
when the instruction sending time falls into the non-interactive time interval, target multimedia data are obtained; the target multimedia data is multimedia data which cannot meet the multimedia characteristic information of the user account;
and pushing the target multimedia data to the user account.
5. The data processing method of claim 1, wherein the feedback operation comprises a handover operation for the target multimedia data, and wherein the determining whether the non-interactive time interval is an untrusted time interval according to the feedback operation comprises:
determining whether the switching operation of the target multimedia data in the non-interactive time interval reaches a preset switching frequency;
if the switching operation does not reach the preset switching frequency, determining the non-interactive time interval as an untrusted time interval;
and if the switching operation reaches a preset switching frequency, determining the non-interactive time interval as a confidence time interval.
6. The data processing method of claim 1, wherein when the non-interactive time interval is determined to be an untrusted time interval, processing the historical multimedia data with the recording time falling within the untrusted time interval comprises:
when the non-interactive time interval is determined to be an untrusted time interval, removing multimedia data by taking the historical multimedia data with the recording time falling into the untrusted time interval as a target;
using the historical multimedia data except the target removal multimedia data as multimedia data for predicting multimedia feature information satisfying the user account.
7. The data processing method of claim 2, wherein when the non-interactive time interval is determined to be a confidence time interval, processing the historical multimedia data with the recording time falling within the confidence time interval comprises:
when the non-interactive time interval is determined to be a confidence time interval, reserving the historical multimedia data with the recording time falling into the confidence time interval as a target to reserve the multimedia data;
and using the target reserved multimedia data as multimedia data for predicting multimedia characteristic information meeting the user account.
8. A data processing apparatus, comprising:
the non-interaction time interval determining unit is configured to execute non-interaction time intervals, wherein the non-interaction time intervals are determined to be free of interaction operation on the user account according to historical operation data on the user account;
a target multimedia data pushing unit configured to perform pushing of target multimedia data to the user account during the non-interactive time interval;
a feedback operation acquisition unit configured to perform a feedback operation of acquiring the target multimedia data on the user account;
an untrusted time interval determination unit configured to perform determining whether the untrusted time interval is an untrusted time interval according to the feedback operation; the historical multimedia data with the non-confidence time interval representing and recording time falling into cannot reflect the multimedia characteristic information of the user account;
a first history multimedia data processing unit configured to perform processing the history multimedia data of which the recording time falls within an untrusted time interval when the untrusted time interval is determined to be an untrusted time interval.
9. A server, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the data processing method of any one of claims 1 to 7.
10. A storage medium in which instructions, when executed by a processor of a server, enable the server to perform a data processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010688165.8A CN113946744A (en) | 2020-07-16 | 2020-07-16 | Data processing method, device, server and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010688165.8A CN113946744A (en) | 2020-07-16 | 2020-07-16 | Data processing method, device, server and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113946744A true CN113946744A (en) | 2022-01-18 |
Family
ID=79326557
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010688165.8A Pending CN113946744A (en) | 2020-07-16 | 2020-07-16 | Data processing method, device, server and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113946744A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776999A (en) * | 2016-12-07 | 2017-05-31 | 北京小米移动软件有限公司 | Multi-medium data recommends method and device |
| US20180196696A1 (en) * | 2017-01-06 | 2018-07-12 | International Business Machines Corporation | Optimizing timeouts and polling intervals |
| CN108470041A (en) * | 2018-02-12 | 2018-08-31 | 维沃移动通信有限公司 | A kind of information search method and mobile terminal |
| CN108683744A (en) * | 2018-05-22 | 2018-10-19 | 北京小鱼在家科技有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN109189951A (en) * | 2018-07-03 | 2019-01-11 | 上海掌门科技有限公司 | A kind of multimedia resource recommended method, equipment and storage medium |
| CN109618204A (en) * | 2018-12-12 | 2019-04-12 | 百度在线网络技术（北京）有限公司 | Multimedia resource playing method and device |
| CN110659701A (en) * | 2019-10-09 | 2020-01-07 | 京东数字科技控股有限公司 | Information processing method, information processing apparatus, electronic device, and medium |
| CN110870322A (en) * | 2017-07-14 | 2020-03-06 | 索尼公司 | Information processing apparatus, information processing method, and program |
| CN110958470A (en) * | 2019-12-09 | 2020-04-03 | 北京字节跳动网络技术有限公司 | Multimedia content processing method, device, medium and electronic equipment |
-
2020
- 2020-07-16 CN CN202010688165.8A patent/CN113946744A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106776999A (en) * | 2016-12-07 | 2017-05-31 | 北京小米移动软件有限公司 | Multi-medium data recommends method and device |
| US20180196696A1 (en) * | 2017-01-06 | 2018-07-12 | International Business Machines Corporation | Optimizing timeouts and polling intervals |
| CN110870322A (en) * | 2017-07-14 | 2020-03-06 | 索尼公司 | Information processing apparatus, information processing method, and program |
| CN108470041A (en) * | 2018-02-12 | 2018-08-31 | 维沃移动通信有限公司 | A kind of information search method and mobile terminal |
| CN108683744A (en) * | 2018-05-22 | 2018-10-19 | 北京小鱼在家科技有限公司 | Information-pushing method, device, computer equipment and storage medium |
| CN109189951A (en) * | 2018-07-03 | 2019-01-11 | 上海掌门科技有限公司 | A kind of multimedia resource recommended method, equipment and storage medium |
| CN109618204A (en) * | 2018-12-12 | 2019-04-12 | 百度在线网络技术（北京）有限公司 | Multimedia resource playing method and device |
| CN110659701A (en) * | 2019-10-09 | 2020-01-07 | 京东数字科技控股有限公司 | Information processing method, information processing apparatus, electronic device, and medium |
| CN110958470A (en) * | 2019-12-09 | 2020-04-03 | 北京字节跳动网络技术有限公司 | Multimedia content processing method, device, medium and electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| CHI HAROLD LIU ET AL.: "Personalized Multimedia Recommendations for Cloud-Intergrated Cyber-Physical Systems", 《IEEE SYSTEMS JOURNAL》, vol. 11, no. 1, 19 June 2015 (2015-06-19), pages 106 - 117, XP011642583, DOI: 10.1109/JSYST.2015.2440431 * |
| 扈中凯 等: "基于用户评论挖掘的产品推荐算法", 《浙江大学学报(工学版)》, no. 08, 15 August 2013 (2013-08-15), pages 160 - 170 * |
| 杨海燕 等: "基于草图的超视频构造方法及关键技术研究", 《计算机研究与发展》, no. 02, 15 February 2011 (2011-02-15), pages 115 - 121 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112511854B (en) | Live video highlight generation method, device, medium and equipment | |
| CN110047515B (en) | Audio identification method, device, equipment and storage medium | |
| US11310326B2 (en) | Methods and apparatus to facilitate meter to meter matching for media identification | |
| CN104813357A (en) | Systems and methods for live media content matching | |
| CN101444092A (en) | Video reproduction device, video reproduction method, and video reproduction program | |
| TW200402654A (en) | A system and method for providing user control over repeating objects embedded in a stream | |
| CN112565775B (en) | Method, device and storage medium for audio and video transcoding | |
| EP3690674A1 (en) | Method for recommending video content | |
| CN113505272B (en) | Control method and device based on behavior habit, electronic equipment and storage medium | |
| CN113407773A (en) | Short video intelligent recommendation method and system, electronic device and storage medium | |
| US10534777B2 (en) | Systems and methods for continuously detecting and identifying songs in a continuous audio stream | |
| CN111277898A (en) | Content pushing method and device | |
| CN110795026B (en) | Hot spot data identification method, device, equipment and storage medium | |
| CN110569447B (en) | Network resource recommendation method and device and storage medium | |
| KR102386817B1 (en) | Apparatus for music sorting based on User preference and device applied to the same | |
| CN109561339A (en) | The treating method and apparatus of video file | |
| CN109729428B (en) | Television channel video audience statistical method and device | |
| CN113946744A (en) | Data processing method, device, server and storage medium | |
| CN111083534A (en) | Method and equipment for providing recommended video list | |
| US8943528B1 (en) | Probabilistic matching of television program audio signals | |
| CN107484015B (en) | Program processing method and device and terminal | |
| CN113747233B (en) | Music replacement method and device, electronic equipment and storage medium | |
| CN106844683B (en) | Information sharing method and device | |
| CN115705378A (en) | Resource recommendation method and device and electronic equipment | |
| CN109558402B (en) | Data storage method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |