CN112989205A

CN112989205A - Media file recommendation method, device, medium and electronic equipment

Info

Publication number: CN112989205A
Application number: CN202110402468.3A
Authority: CN
Inventors: 王晶冰
Original assignee: Beijing Youzhuju Network Technology Co Ltd
Current assignee: Beijing Youzhuju Network Technology Co Ltd
Priority date: 2021-04-14
Filing date: 2021-04-14
Publication date: 2021-06-18

Abstract

The disclosure relates to a media file recommendation method, a device, a medium and an electronic device. The method comprises the following steps: responding to a media file creation request from a user, and acquiring historical media file information related to a historical media file created by the user; determining a target language corresponding to the user; generating a recommended media case with the language being the target language according to the historical media case information; and displaying the recommended media file. Therefore, when a user sends a media file creation request, the media file which is satisfactory for the user and is in the target language can be automatically generated according to the historical media file information related to the historical media file created by the user, the method and the device are convenient and quick, and the user does not need to input any information, so that the generation efficiency of the media file is improved, the media creative production threshold is reduced, and the user experience is improved.

Description

Media file recommendation method, device, medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a medium, and an electronic device for recommending a media file.

Background

The file is an important component of media (such as advertisements and articles) creativity and is an important factor influencing media conversion, and intelligent file generation can help users to quickly capture hotspot expression modes and improve media file generation efficiency and effect. In addition, many of the users who are in the sea lack the ability to write cross-language media documents, and the intelligent generation of multi-language media documents can greatly reduce the threshold for creating media creatives. Therefore, how to quickly generate the media file of the corresponding language which is satisfactory to the user becomes the key point of the intelligent generation of the media file.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

In a first aspect, the present disclosure provides a method for recommending a media file, including:

responding to a media file creation request from a user, and acquiring historical media file information related to a historical media file created by the user;

determining a target language corresponding to the user;

generating a recommended media case with the language being the target language according to the historical media case information;

and displaying the recommended media file.

In a second aspect, the present disclosure provides a media file recommendation device, including:

the acquisition module is used for responding to a media file creation request from a user and acquiring historical media file information related to a historical media file created by the user;

the determining module is used for determining a target language corresponding to the user;

the generating module is used for generating a recommended media file with the language being the target language determined by the determining module according to the historical media file information acquired by the acquiring module;

and the display module is used for displaying the recommended media file generated by the generation module.

In a third aspect, the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processing apparatus, performs the steps of the method provided by the first aspect of the present disclosure.

In a fourth aspect, the present disclosure provides an electronic device comprising:

a storage device having a computer program stored thereon;

processing means for executing the computer program in the storage means to implement the steps of the method provided by the first aspect of the present disclosure.

In the technical scheme, in response to a media file creation request from a user, historical media file information related to a historical media file created by the user is acquired; determining a target language corresponding to a user; and then, generating a recommended media file with the target language according to the historical media file information, and displaying the recommended media file. Therefore, when a user sends a media file creation request, the media file which is satisfactory for the user and is in the target language can be automatically generated according to the historical media file information related to the historical media file created by the user, the method and the device are convenient and quick, and the user does not need to input any information, so that the generation efficiency of the media file is improved, the media creative production threshold is reduced, and the user experience is improved.

Additional features and advantages of the disclosure will be set forth in the detailed description which follows.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale. In the drawings:

FIG. 1 is a flow chart illustrating a method of media document recommendation, according to an example embodiment.

FIG. 2 is a flow diagram illustrating a method of obtaining historical media document information relating to a historical media document created by a user, according to an example embodiment.

FIG. 3 is a flow diagram illustrating a method for generating a recommended media case in a target language in accordance with an exemplary embodiment.

FIG. 4 is a block diagram illustrating a media document recommendation device according to an exemplary embodiment.

FIG. 5 is a block diagram illustrating an electronic device in accordance with an example embodiment.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.

FIG. 1 is a flow chart illustrating a method of media document recommendation, according to an example embodiment. As shown in fig. 1, the method includes S101 to S104.

In S101, history media pattern information related to a history media pattern created by a user is acquired in response to a media pattern creation request from the user.

In the present disclosure, the media document may be an advertising document, a public number document, a user guidance document, or the like. Moreover, the user can perform media document creation through a media creative creation platform on a terminal (e.g., a smart phone, a tablet computer, etc.) or a server. After the user logs in the media creative production platform, a media file creation request can be initiated.

In S102, a target language corresponding to the user is determined.

In this disclosure, the target language corresponding to the user may be a language most frequently used in a historical media file created by the user, may also be a language matched with the current login address of the user (for example, if the login address is china, the matched language is chinese, that is, the target language is chinese), and may also be a current language of a platform for making a media currently logged in by the user, which is not specifically limited in this disclosure.

Wherein, the most frequently used language can be determined by the following method:

firstly, acquiring the latest N first media titles in a historical media file created by a user; then, determining the language of each first media title; and finally, determining the language with the most occurrence times in the languages of each first media title as the most frequently used language.

In S103, a recommended media document in the target language is generated based on the history media document information.

In S104, the recommended media copy is shown.

The following is a detailed description of a specific embodiment of acquiring history media document information related to a history media document created by a user in S101. In particular, historical media pattern information relating to a user-created historical media pattern may be obtained in a number of ways. In one embodiment, this may be achieved by S1011 and S1012 shown in fig. 2.

In S1011, media data of the history media pattern created by the user is acquired.

In one embodiment, the media data includes the last N first media titles, i.e., the N media titles that the user has recently created.

In another embodiment, the media data may include information about the last M media topics.

In the present disclosure, the media theme may be a specific category of media, for example, a user may create three media themes of jacket, pants and underwear after logging in the media creative production platform. The related information of the media topic may include identification information (e.g., ID) of the media topic, and may also include a plurality of landing page texts and media titles under the media topic, where the landing page texts are used for jumping to corresponding media body content.

In yet another embodiment, in order to improve the accuracy of the subsequently generated recommended media files and thus enhance the user satisfaction, the media data includes the related information of the latest N first media titles and the latest M media topics.

Note that the N, M may be a value preset by the user, or may be a default empirical value (for example, N is 8, and M is 10), and they may be equal or not, and are not particularly limited in the present disclosure.

In S1012, keywords in the media data are extracted, and the extracted keywords are determined as history media pattern information related to the history media pattern created by the user.

In another embodiment, historical media pattern information associated with a user-created historical media pattern may be obtained by: and determining the keywords corresponding to the user according to the pre-constructed corresponding relationship between the user and the keywords to serve as historical media file information.

In this disclosure, the correspondence relationship is established based on the historical media file created by the user. Specifically, the correspondence relationship may be established by the following steps (1) and (2):

(1) acquiring media data of a historical media file created by a user;

(2) and extracting keywords in the media data, and determining the extracted keywords as keywords corresponding to the user.

A detailed description will be given below of a specific embodiment of extracting keywords from the media data in the above-described S1012 and the above-described step (2). Specifically, the media data includes the latest N first media titles and the latest M related information of the media topics, and at this time, the keywords in the media data can be extracted through the following steps (i) to (iii).

Generating a first keyword according to the latest N first media titles;

generating a second keyword according to the related information of the latest M media themes;

and combining the first key words and the second key words to obtain the key words in the media data.

A detailed description will be given below of a specific embodiment of generating the first keyword from the latest N first media titles in the above-described step (i).

In one embodiment, for each first media title in the latest N first media titles, firstly, performing word segmentation on the first media title, and then determining words belonging to a pre-constructed keyword library among words obtained after word segmentation as keywords in the first media title; and combining the keywords in the first media titles to serve as the first keywords.

In another embodiment, for each first media title in the latest N first media titles, inputting the first media title into a first keyword generation model trained in advance to obtain a keyword in the first media title; the keywords in each first media title are merged as first keywords. Therefore, the keywords in each first media title can be automatically extracted through the first keyword generation model, and convenience and rapidness are achieved.

In the present disclosure, the first keyword generation model may be, for example, a transform model, a Long Short-Term Memory (LSTM) model, or the like.

In yet another embodiment, Named Entity Recognition (NER) may be performed separately for each first media title to obtain at least one Named Entity in each first media title; at least one named entity in each first media title is merged as a first keyword. Therefore, the keywords in each first media title can be automatically extracted through the NER, and the method is convenient and quick.

The following describes in detail a specific embodiment of generating the second keyword according to the related information of the latest M media topics in the step two.

In one embodiment, first, a second media title under each of the latest M media topics is obtained, that is, all media titles under each of the latest M media topics are obtained; then, for each second media title, performing word segmentation on the second media title, and determining words in each word obtained after word segmentation and belonging to a pre-constructed keyword library as keywords in the second media title; and combining the keywords in the second media titles to serve as second keywords.

In another embodiment, the related information includes identification information, and at this time, for each media topic in the latest M media topics, the identification information of the media topic may be input into a second keyword generation model trained in advance to obtain a keyword corresponding to the media topic; and combining the keywords corresponding to the media topics to serve as second keywords. Therefore, the keywords corresponding to the media topics can be automatically extracted through the second keyword generation model, and convenience and rapidness are achieved.

In yet another embodiment, the related information includes a second media title under each media topic. At this time, the named entity identification can be respectively carried out on each second media title to obtain at least one named entity in each second media title; thereafter, at least one named entity in each second media title is merged as a second keyword. Therefore, the keywords corresponding to all media topics can be automatically extracted through the NER, and convenience and rapidness are achieved.

In yet another embodiment, the related information includes identification information and a second media title under each media topic. At this time, the named entity identification can be respectively carried out on each second media title to obtain at least one named entity in each second media title; meanwhile, aiming at each media theme, inputting the identification information of the media theme into a second keyword generation model trained in advance to obtain keywords corresponding to the media theme; and then combining at least one named entity in each second media title and the keyword sum corresponding to each media subject to serve as a second keyword. Therefore, the comprehensiveness of the determined second keyword can be ensured, so that the historical media file information related to the historical media file created by the user is more comprehensive, the accuracy of the subsequently generated recommended media file is improved, and the satisfaction degree of the user is improved.

In the present disclosure, the second keyword generation model may be, for example, a transform model, an LSTM model, or the like.

A detailed description will be given below of a specific embodiment of generating a recommended media file in the target language based on the historical media file information in S103. Specifically, it can be realized by S1031 to S1034 shown in fig. 3.

In S1031, it is determined whether or not there is a keyword in the target language in the history media pattern information.

In the present disclosure, if there is a keyword in the target language in the historical media pattern information, S1032 is executed; if there is no keyword in the target language in the history media file information, S1033 is executed.

In S1032, a recommended media case is generated based on the keyword in the target language.

In S1033, the history media file information is translated into the target language.

In S1034, a recommended media document is generated based on the translated historical media document information.

A detailed description will be given below of a specific embodiment of generating a recommended media file based on the keyword in the target language in S1032.

In one embodiment, the recommended media case may be generated directly from the keywords in the target language. Specifically, the keyword may be input into a pre-trained media case generation model for each keyword in the target language to obtain a media case corresponding to the keyword; and taking the media files corresponding to the keywords as recommended media files together. The media pattern generation model may be, for example, a transform model or an LSTM model.

In another embodiment, to further improve the efficiency of generating the media document, the recommended media document may be generated by:

judging whether the number of the keywords with the language being the target language is greater than K or not; if the number of the keywords with the target language is larger than K, determining K target keywords from the keywords with the target language, and then generating a recommended media case according to the K target keywords; and if the number of the keywords with the language as the target language is less than or equal to K, generating the recommended media case directly according to the keywords with the language as the target language.

In the present disclosure, since the specific implementation manner of generating the recommended media case according to the K target keywords is similar to the above-mentioned specific implementation manner of generating the recommended media case directly according to the keywords in the target language, the detailed description is omitted here.

In addition, the specific manner of generating the recommended media file in S1034 according to the translated historical media file information is similar to the specific manner of generating the recommended media file according to the keyword in S1032 according to the language as the target language, and the details of this disclosure are not repeated.

The following is a detailed description of a specific embodiment of determining K target keywords from the keywords in the target language.

In one embodiment, K target keywords may be randomly selected from the keywords in the target language.

In another embodiment, a target industry corresponding to a user may be determined; and then, determining K keywords with the highest relevance to the target industry from the keywords with the target language as K target keywords.

In this disclosure, the target industry corresponding to the user may be the industry that is most frequently involved in the historical media copy created for the user.

Wherein the above-mentioned most frequently involved industries may be determined by:

firstly, acquiring the latest M media themes in a historical media file created by a user; then, determining the industry related to each media theme; and finally, determining the industries with the highest occurrence frequency in the industries related to each media theme as target industries.

In addition, the relevance of each keyword to the target industry in the keywords with the target language can be determined by the following method:

aiming at each keyword in the keywords with the target language, inputting the keyword into a pre-trained keyword-industry classification model to obtain a probability distribution corresponding to the keyword, wherein the probability distribution comprises the probability that the keyword belongs to each preset industry, the sum of the probabilities is equal to 1, and each preset industry comprises the target industry; and then, determining the probability of the keyword belonging to the target industry in the probability distribution corresponding to the keyword as the correlation degree of the keyword and the target industry.

Based on the same inventive concept, the disclosure also provides a media file recommendation device. As shown in fig. 4, the apparatus 400 includes: an obtaining module 401, configured to respond to a media document creation request from a user, and obtain historical media document information related to a historical media document created by the user; a determining module 402, configured to determine a target language corresponding to the user; a generating module 403, configured to generate, according to the historical media scenario information obtained by the obtaining module 401, a recommended media scenario in the target language determined by the determining module 402; a display module 404, configured to display the recommended media scenario generated by the generating module 403.

Optionally, the obtaining module 401 is configured to determine, according to a pre-established correspondence between the user and the keyword, the keyword corresponding to the user as the historical media scenario information, where the correspondence is established based on the historical media scenario created by the user.

Optionally, the corresponding relationship is established by a construction apparatus, wherein the construction apparatus includes: the media data acquisition module is used for acquiring media data of the historical media file created by the user, wherein the media data comprises related information of the latest N first media titles and/or the latest M media themes; and the extraction module is used for extracting the keywords in the media data acquired by the media data acquisition module and determining the extracted keywords as the keywords corresponding to the user.

The construction device may be independent of the media document recommendation device 400, or may be integrated into the media document recommendation device 400, and the disclosure is not limited thereto.

Optionally, the obtaining module 401 includes: the acquisition submodule is used for acquiring the media data of the historical media file created by the user, wherein the media data comprises the related information of the latest N first media titles and/or the latest M media themes; and the extraction submodule is used for extracting the keywords in the media data and determining the extracted keywords as historical media file information related to the historical media file created by the user.

Optionally, the media data includes related information of the latest N first media titles and the latest M media topics; in a case where the correspondence relationship is established by the construction apparatus, the extraction module includes: the first generation submodule is used for generating a first keyword according to the latest N first media titles; the second generation submodule is used for generating a second keyword according to the related information of the latest M media topics; the first merging submodule is used for merging the first keyword and the second keyword to obtain a keyword in the media data; in a case where the obtaining module 401 includes the obtaining sub-module and the extracting sub-module, the extracting sub-module includes: the first generation submodule is used for generating a first keyword according to the latest N first media titles; the second generation submodule is used for generating a second keyword according to the related information of the latest M media topics; the first merging submodule is used for merging the first keyword and the second keyword to obtain a keyword in the media data;

optionally, the first generation submodule includes: the first input sub-module is used for inputting the first media title into a pre-trained first keyword generation model aiming at each first media title to obtain keywords in the first media title; a second merging submodule, configured to merge keywords in each of the first media titles to serve as first keywords; or, the first entity identifying submodule is configured to perform named entity identification on each first media title respectively to obtain at least one named entity in each first media title; and the third merging submodule is used for merging at least one named entity in each first media title as a first keyword.

Optionally, the related information includes identification information and a second media title under each of the media topics; the second generation submodule includes: the second named entity identification submodule is used for respectively carrying out named entity identification on each second media title to obtain at least one named entity in each second media title; the second input sub-module is used for inputting the identification information of the media topics into a pre-trained second keyword generation model aiming at each media topic to obtain keywords corresponding to the media topics; and the fourth merging submodule is used for merging at least one named entity in each second media title and the keyword corresponding to each media theme to be used as a second keyword.

Optionally, the generating module 403 includes: the judging submodule is used for judging whether the historical media case information has the keywords with the language being the target language; and a third generation submodule, configured to generate the recommended media case according to the keyword in the target language if the keyword in the target language exists in the historical media case information.

Optionally, the third generation submodule includes: a determining submodule, configured to determine K target keywords from the keywords in the target language if the number of the keywords in the target language is greater than K; and the pattern generation submodule is used for generating the recommended media pattern according to the K target keywords.

Optionally, the determining sub-module includes: the industry determining submodule is used for determining a target industry corresponding to the user; and the keyword determining submodule is used for determining K keywords with the highest relevance to the target industry from the keywords with the target language as the K target keywords.

Optionally, the generating module 403 further includes: a translation submodule, configured to translate the historical media case information into the target language if there is no keyword with a language of the target language; and the fourth generation submodule is used for generating the recommended media file according to the historical media file information obtained after translation.

The present disclosure also provides a computer readable medium, on which a computer program is stored, which when executed by a processing device, implements the steps of the above-mentioned media document recommendation method provided by the present disclosure.

Referring now to fig. 5, a schematic diagram of an electronic device (e.g., a terminal device or a server) 500 suitable for use in implementing embodiments of the present disclosure is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program performs the above-described functions defined in the methods of the embodiments of the present disclosure when executed by the processing device 501.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: responding to a media file creation request from a user, and acquiring historical media file information related to a historical media file created by the user; determining a target language corresponding to the user; generating a recommended media case with the language being the target language according to the historical media case information; and displaying the recommended media file.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented by software or hardware. The name of the module does not in some cases form a limitation on the module itself, for example, the determining module may also be described as a "module that determines the target language corresponding to the user".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Example 1 provides a media document recommendation method, according to one or more embodiments of the present disclosure, including: responding to a media file creation request from a user, and acquiring historical media file information related to a historical media file created by the user;

determining a target language corresponding to the user;

and displaying the recommended media file.

Example 2 provides the method of example 1, the obtaining historical media document information related to the user-created historical media document, comprising: and determining keywords corresponding to the user according to a pre-constructed corresponding relationship between the user and the keywords as the historical media file information, wherein the corresponding relationship is established based on the historical media file created by the user.

Example 3 provides the method of example 2, the correspondence being established by: acquiring media data of the historical media file created by the user, wherein the media data comprises related information of the latest N first media titles and/or the latest M media themes; and extracting keywords in the media data, and determining the extracted keywords as keywords corresponding to the user.

Example 4 provides the method of example 1, the obtaining historical media document information related to the user-created historical media document, comprising: acquiring media data of the historical media file created by the user, wherein the media data comprises related information of the latest N first media titles and/or the latest M media themes; and extracting keywords in the media data, and determining the extracted keywords as historical media file information related to the historical media file created by the user.

Example 5 provides the method of example 3 or example 4, the media data comprising information about the last N first media titles and the last M media topics; the extracting of the keywords in the media data includes: generating a first keyword according to the latest N first media titles; generating a second keyword according to the related information of the latest M media topics; and combining the first keyword and the second keyword to obtain the keywords in the media data.

Example 6 provides the method of example 5, wherein generating the first keyword from the most recent N first media titles comprises: inputting the first media title into a first keyword generation model trained in advance aiming at each first media title to obtain keywords in the first media title; combining keywords in each first media title to serve as first keywords; the related information includes identification information, and the generating of the second keyword according to the related information of the latest M media topics includes: for each media theme, inputting the identification information of the media theme into a pre-trained second keyword generation model to obtain keywords corresponding to the media theme; combining the keywords corresponding to each media theme to serve as second keywords; or respectively carrying out named entity identification on each first media title to obtain at least one named entity in each first media title; merging at least one named entity in each of the first media titles as a first keyword.

Example 7 provides the method of example 6, the related information including identification information and a second media title under each of the media topics, in accordance with one or more embodiments of the present disclosure; generating a second keyword according to the related information of the latest M media topics, wherein the generating of the second keyword comprises: respectively carrying out named entity identification on each second media title to obtain at least one named entity in each second media title; for each media theme, inputting the identification information of the media theme into a pre-trained second keyword generation model to obtain keywords corresponding to the media theme; and combining at least one named entity in each second media title and the keyword corresponding to each media theme to serve as a second keyword.

Example 8 provides the method of any one of examples 2-4, wherein generating the recommended media case in the target language based on the historical media case information, according to one or more embodiments of the present disclosure, includes: judging whether the historical media file information has keywords with the language being the target language; and if the historical media case information contains the key words with the language being the target language, generating the recommended media case according to the key words with the language being the target language.

Example 9 provides the method of example 8, the generating the recommended media case according to the keyword in the target language according to the language, including: if the number of the keywords with the language being the target language is larger than K, K target keywords are determined from the keywords with the language being the target language; and generating the recommended media file according to the K target keywords.

Example 10 provides the method of example 9, the determining K target keywords from the keywords in the target language according to one or more embodiments of the present disclosure includes: determining a target industry corresponding to the user; and determining K keywords with the highest relevance to the target industry from the keywords with the target language as the K target keywords.

Example 11 provides the method of example 8, the generating a recommended media case in the target language according to the historical media case information, further including: if no keyword with the language of the target language exists, translating the historical media file information into the target language; and generating the recommended media file according to the historical media file information obtained after translation.

Example 12 provides a media document recommendation apparatus, according to one or more embodiments of the present disclosure, comprising: the acquisition module is used for responding to a media file creation request from a user and acquiring historical media file information related to a historical media file created by the user; the determining module is used for determining a target language corresponding to the user; the generating module is used for generating a recommended media file with the language being the target language determined by the determining module according to the historical media file information acquired by the acquiring module; and the display module is used for displaying the recommended media file generated by the generation module.

Example 13 provides a computer-readable medium, on which is stored a computer program that, when executed by a processing device, implements the steps of the method of any of examples 1-11, in accordance with one or more embodiments of the present disclosure.

Example 14 provides, in accordance with one or more embodiments of the present disclosure, an electronic device, comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to carry out the steps of the method of any of examples 1-11.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.

Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. 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.

Claims

1. A method for recommending media documents, comprising:

determining a target language corresponding to the user;

and displaying the recommended media file.

2. The method of claim 1, wherein obtaining historical media pattern information related to the historical media pattern created by the user comprises:

and determining keywords corresponding to the user according to a pre-constructed corresponding relationship between the user and the keywords as the historical media file information, wherein the corresponding relationship is established based on the historical media file created by the user.

3. The method according to claim 2, wherein the correspondence is established by:

acquiring media data of the historical media file created by the user, wherein the media data comprises related information of the latest N first media titles and/or the latest M media themes;

and extracting keywords in the media data, and determining the extracted keywords as keywords corresponding to the user.

4. The method of claim 1, wherein obtaining historical media pattern information related to the historical media pattern created by the user comprises:

and extracting keywords in the media data, and determining the extracted keywords as historical media file information related to the historical media file created by the user.

5. The method according to claim 3 or 4, wherein the media data comprises information about the last N first media titles and the last M media topics;

the extracting of the keywords in the media data includes:

generating a first keyword according to the latest N first media titles;

generating a second keyword according to the related information of the latest M media topics;

and combining the first keyword and the second keyword to obtain the keywords in the media data.

6. The method of claim 5, wherein generating a first keyword based on the most recent N first media titles comprises:

inputting the first media title into a first keyword generation model trained in advance aiming at each first media title to obtain keywords in the first media title; combining keywords in each first media title to serve as first keywords; or

Respectively carrying out named entity identification on each first media title to obtain at least one named entity in each first media title; merging at least one named entity in each of the first media titles as a first keyword.

7. The method of claim 5, wherein the related information comprises identification information and a second media title under each of the media topics;

generating a second keyword according to the related information of the latest M media topics, wherein the generating of the second keyword comprises:

respectively carrying out named entity identification on each second media title to obtain at least one named entity in each second media title;

for each media theme, inputting the identification information of the media theme into a pre-trained second keyword generation model to obtain keywords corresponding to the media theme;

and combining at least one named entity in each second media title and the keyword corresponding to each media theme to serve as a second keyword.

8. The method according to any one of claims 2-4, wherein said generating a recommended media case in the target language based on the historical media case information comprises:

judging whether the historical media file information has keywords with the language being the target language;

and if the historical media case information contains the key words with the language being the target language, generating the recommended media case according to the key words with the language being the target language.

9. The method of claim 8, wherein said generating the recommended media case based on the keyword in the target language comprises:

if the number of the keywords with the language being the target language is larger than K, K target keywords are determined from the keywords with the language being the target language;

and generating the recommended media file according to the K target keywords.

10. The method according to claim 9, wherein said determining K target keywords from the keywords in the target language comprises:

determining a target industry corresponding to the user;

and determining K keywords with the highest relevance to the target industry from the keywords with the target language as the K target keywords.

11. The method of claim 8, wherein generating the recommended media case in the target language based on the historical media case information further comprises:

if no keyword with the language of the target language exists, translating the historical media file information into the target language;

and generating the recommended media file according to the historical media file information obtained after translation.

12. A media document recommendation device, comprising:

13. A computer-readable medium, on which a computer program is stored, characterized in that the program, when being executed by processing means, carries out the steps of the method of any one of claims 1-11.

14. An electronic device, comprising:

a storage device having a computer program stored thereon;

processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 11.