CN111400517A - Information pushing and information publishing method and device - Google Patents

Information pushing and information publishing method and device Download PDF

Info

Publication number
CN111400517A
CN111400517A CN202010201534.6A CN202010201534A CN111400517A CN 111400517 A CN111400517 A CN 111400517A CN 202010201534 A CN202010201534 A CN 202010201534A CN 111400517 A CN111400517 A CN 111400517A
Authority
CN
China
Prior art keywords
media content
published
topic
content
contents
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
Application number
CN202010201534.6A
Other languages
Chinese (zh)
Inventor
王子昂
苏凯
闫颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing ByteDance Network Technology Co Ltd
Original Assignee
Beijing ByteDance Network Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing ByteDance Network Technology Co Ltd filed Critical Beijing ByteDance Network Technology Co Ltd
Priority to CN202010201534.6A priority Critical patent/CN111400517A/en
Publication of CN111400517A publication Critical patent/CN111400517A/en
Pending legal-status Critical Current

Links

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
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • 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
    • G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/483—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • 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
    • G06F16/951—Indexing; Web crawling techniques

Abstract

The disclosure provides an information pushing method and device and an information publishing method and device, wherein the information pushing method comprises the following steps: acquiring media contents to be issued uploaded by a user side; determining resource contents of the media content to be published under multiple dimensions, and generating a feature vector corresponding to the media content to be published based on the resource contents under the multiple dimensions; determining reference media contents matched with the media contents to be published in a media content library based on the feature vectors corresponding to the reference media contents in the media content library and the feature vectors of the media contents to be published; and sending the determined topic label corresponding to the reference media content to the user side as a recommended topic label.

Description

Information pushing and information publishing method and device
Technical Field
The disclosure relates to the technical field of internet, in particular to an information pushing method, an information publishing method and an information pushing device.
Background
Generally, when a user publishes media content, a topic tag corresponding to the media content can be added to the media content, so that when the user browsing the media content searches or browses the topic, the user can view the media content according to the topic tag corresponding to the media content.
However, there may be instances where the user publishing the media content and the user browsing the media content may not have a consistent understanding of the media content. For example, for the same media content, a user browsing the media content may consider the topic tag corresponding to the media content to be humorous, and a user publishing the media content may consider the topic tag corresponding to the media content to be a pet, so that the media content cannot be accurately pushed for the user browsing the media content, and meanwhile, the published media content cannot be viewed by a user with a demand, thereby reducing the accuracy of pushing the media content.
Disclosure of Invention
The embodiment of the disclosure at least provides an information pushing method, an information publishing method and an information pushing device.
In a first aspect, an embodiment of the present disclosure provides an information pushing method, including:
acquiring media contents to be issued uploaded by a user side;
determining resource contents of the media content to be published under multiple dimensions, and generating a feature vector corresponding to the media content to be published based on the resource contents under the multiple dimensions;
determining reference media contents matched with the media contents to be published in a media content library based on the feature vectors corresponding to the reference media contents in the media content library and the feature vectors of the media contents to be published;
and sending the determined topic label corresponding to the reference media content to the user side as a recommended topic label.
In an optional embodiment, determining resource content of the media content to be published in multiple dimensions includes:
determining a plurality of the following resource contents corresponding to the media content to be published:
the content publishing system comprises a plurality of pictures corresponding to the media content to be published, special effect content corresponding to the media content to be published, dubbing content corresponding to the media content to be published and title content corresponding to the media content to be published.
In an optional implementation manner, if the resource content in the multiple dimensions includes multiple pictures corresponding to the media content to be published; determining a plurality of pictures corresponding to the media content to be published according to the following steps:
and performing equal-interval frame extraction on the media content to be issued according to a preset time interval, and extracting the plurality of pictures.
In an alternative embodiment, the feature vector corresponding to each reference media content in the media content library is determined according to the following steps:
acquiring each reference media content;
for each reference media content, determining resource content of the reference media content in multiple dimensions, and generating a feature vector of the reference media content based on the resource content in the multiple dimensions.
In an optional implementation manner, determining, based on a feature vector corresponding to each reference media content in a media content library and a feature vector of the media content to be published, a reference media content in the media content library that matches the media content to be published includes:
inputting the feature vector corresponding to the reference media content and the feature vector of the media content to be published into a correlation degree detection model, and determining the correlation degree between the reference media content and the media content to be published; the relevancy detection model is obtained by training a plurality of training samples based on the relevancy among the marked different media contents; or calculating cosine similarity between the feature vector corresponding to the reference media content and the feature vector corresponding to the media content to be published, and determining the cosine similarity as the correlation between the reference media content and the media content to be published;
and determining the reference media content matched with the media content to be published in a media content library based on the correlation degree between the reference media content and the media content to be published.
In an optional implementation manner, sending the determined topic tag corresponding to the reference media content to the user end as a recommended topic tag includes:
obtaining each selected topic tag corresponding to the reference media content;
and carrying out duplicate removal processing on each selected topic label and then pushing the processed topic label to the user side.
In an optional implementation manner, the sending each selected topic tag to the user side after performing deduplication processing includes:
performing deduplication processing on each selected topic label to obtain at least one candidate topic label;
and selecting a recommended topic tag from the at least one candidate topic tag according to the user behavior data corresponding to the at least one candidate topic tag, and sending the recommended topic tag to the user terminal.
In an optional embodiment, the user behavior data includes: the media content playing amount corresponding to the candidate topic label and/or the frequency of selecting the candidate topic label.
In a second aspect, an embodiment of the present disclosure provides an information publishing method, including:
acquiring media content to be published, and sending the media content to be published to a server;
receiving a recommended topic tag which is fed back by the server and corresponds to the media content to be published;
and displaying the recommended topic tag on a publishing information editing page corresponding to the media content to be published.
In an optional implementation manner, displaying the recommended topic tag on a publishing information editing page corresponding to the media content to be published includes:
and displaying the recommended topic tag below a topic selection button in the published information editing page.
In a third aspect, an embodiment of the present disclosure further provides an information pushing apparatus, including:
the media content acquisition module is used for acquiring media content to be issued uploaded by a user side;
the characteristic vector generation module is used for determining resource contents of the media content to be published under multiple dimensions and generating a characteristic vector corresponding to the media content to be published based on the resource contents under the multiple dimensions;
the reference media content determining module is used for determining reference media content matched with the media content to be published in the media content library based on the feature vector corresponding to each reference media content in the media content library and the feature vector of the media content to be published;
and the topic sending module is used for sending the determined topic label corresponding to the reference media content to the user side as a recommended topic.
In an optional implementation manner, the feature vector generation module, when determining resource content of the media content to be published in multiple dimensions, is configured to:
determining a plurality of the following resource contents corresponding to the media content to be published:
the content publishing system comprises a plurality of pictures corresponding to the media content to be published, special effect content corresponding to the media content to be published, dubbing content corresponding to the media content to be published and title content corresponding to the media content to be published.
In an optional implementation manner, the feature vector generation module determines a plurality of pictures corresponding to the media content to be published according to the following steps:
and performing equal-interval frame extraction on the media content to be issued according to a preset time interval, and extracting the plurality of pictures.
In an optional implementation manner, the reference media content determining module determines a feature vector corresponding to each reference media content in the media content library according to the following steps:
acquiring each reference media content;
for each reference media content, determining resource content of the reference media content in multiple dimensions, and generating a feature vector of the reference media content based on the resource content in the multiple dimensions.
In an optional implementation manner, when determining, based on the feature vector corresponding to each reference media content in the media content library and the feature vector of the media content to be published, a reference media content in the media content library that matches the media content to be published, the reference media content determining module is configured to:
inputting the feature vector corresponding to the reference media content and the feature vector of the media content to be published into a correlation degree detection model, and determining the correlation degree between the reference media content and the media content to be published; the relevancy detection model is obtained by training a plurality of training sample media contents based on the relevancy among the marked different media contents; or calculating cosine similarity between the feature vector corresponding to the reference media content and the feature vector corresponding to the media content to be published, and determining the cosine similarity as the correlation between the reference media content and the media content to be published;
and determining the reference media content matched with the media content to be published in a media content library based on the correlation degree between the reference media content and the media content to be published.
In an optional implementation manner, when the determined topic tag corresponding to the reference media content is sent to the user end as a recommended topic tag, the topic sending module is configured to:
obtaining each selected topic tag corresponding to the reference media content;
and carrying out duplicate removal processing on each selected topic label and then pushing the processed topic label to the user side.
In an optional implementation manner, the topic transmission module, after performing deduplication processing on each selected topic tag, transmits the topic tag to the user side, and is configured to:
performing deduplication processing on each selected topic label to obtain at least one candidate topic label;
and selecting a recommended topic tag from the at least one candidate topic tag according to the user behavior data corresponding to the at least one candidate topic tag, and sending the recommended topic tag to the user terminal.
In an alternative embodiment, the user behavior data includes: the media content playing amount corresponding to the candidate topic label and/or the frequency of selecting the candidate topic label.
In a fourth aspect, an embodiment of the present disclosure further provides an information issuing apparatus, including:
the media content sending module is used for acquiring media content to be published and sending the media content to be published to the server;
the topic receiving module is used for receiving the recommended topic labels which are fed back by the server and correspond to the media contents to be published;
and the display module is used for displaying the recommended topic tag on a publishing information editing page corresponding to the media content to be published.
In an optional implementation manner, when the publishing information editing page corresponding to the media content to be published shows the recommended topic tag, the presentation module is configured to:
and displaying the recommended topic tag below a topic selection button in the published information editing page.
In a fifth aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions being executed by the processor to perform the steps of the information pushing method described in the first aspect above or any one of the possible embodiments of the first aspect above or to perform the steps of the information issuing method described in the second aspect above or any one of the possible embodiments of the second aspect.
In a sixth aspect, this application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and the computer program is executed by a processor to perform the steps of the information pushing method described in the first aspect, or any one of the possible implementations of the first aspect, or to perform the steps of the information publishing method described in the second aspect, or any one of the possible implementations of the second aspect.
In the information push method provided by the embodiment of the disclosure, the feature vectors corresponding to the media content to be published are generated by determining the resource content of the acquired media content to be published under multiple dimensions and based on the resource content under the multiple dimensions; determining reference media contents matched with the media contents to be published in the media content library based on the feature vectors corresponding to the reference media contents in the media content library and the feature vectors of the media contents to be published; the determined topic labels corresponding to the reference media content are sent to the user side as recommended topic labels, the user selects the topic labels by referring to the selected topic labels, namely, the user selects the topic labels by referring to the understanding of other users on the media content to be released, so that the topic labels can be selected more accurately, the user viewing the media content can search for more accurate media content based on the input topic labels, and further the effective viewing rate of the media content is improved.
In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.
Fig. 1 shows a flowchart of an information pushing method provided by an embodiment of the present disclosure;
FIG. 2 is a schematic interface diagram illustrating a published information editing page provided by an embodiment of the present disclosure;
fig. 3 shows a flowchart of an information publishing method provided by an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of an information pushing apparatus provided in an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram illustrating an information distribution apparatus provided in an embodiment of the present disclosure;
fig. 6 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure;
fig. 7 shows a schematic diagram of another electronic device provided by an embodiment of the disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.
Before the media content is published, the media content publisher can add the corresponding topic tag to the media content to be published, so that the media content viewer can search the corresponding media content after inputting the topic tag, and the media content is searched. Generally, when a media content publisher adds a topic tag to media content to be published, the topic tag corresponding to the media content to be published can be determined based on a text search mode, and the searched topic tag is added to the media content to be published, or the media content publisher can input the topic tag of the media content to be published according to understanding of the media content to be published. For example, the media content a to be published includes an animal a, and the media content publisher may determine the name of the animal a in the media content a to be published in a manner of inputting text description to perform searching, and add the determined animal name as a topic tag of the media content to be published to the media content to be published, or determine a "dog" as a topic tag of the media content to be published when the media content publisher determines that the animal in the media content a to be published is a dog.
When a media content viewer views media content, the media content corresponding to the topic tag may be determined by inputting the topic tag, but for the same media content, the understanding of the media content publisher and the media content viewer may be inconsistent, for example, the media content viewer may consider that the topic tag corresponding to the media content a to be published is life, fun, and the like. Therefore, when the media content viewer inputs the living and/or fun topic tags, the media content to be published A cannot be searched, namely, the media content to be published cannot be accurately viewed by the required media content viewer, and the viewing accuracy of the media content is reduced.
Therefore, the embodiment of the present disclosure provides an information pushing method, which determines reference media content in a media content library, which is matched with the acquired media content to be published, and sends a selected topic tag corresponding to the determined reference media content to a user side, so that the user side selects the topic tag for reference, and the user side selects the topic tag with reference to understanding of each other user on the media content to be published, so that the topic tag can be selected more accurately, and the effective viewing rate of the media content is further improved.
For the convenience of understanding the embodiments of the present disclosure, a detailed description will be first given of an information pushing method disclosed in the embodiments of the present disclosure.
Example one
The embodiment of the present disclosure provides an information push method, which is applied to a server, and referring to a flowchart of the information push method shown in fig. 1, the method includes S101-S104, and the specific process is as follows:
s101, media contents to be issued uploaded by a user side are obtained.
Here, the media content to be published may be media content downloaded, shot, and produced by a user corresponding to the user side, and the media content to be published may be a video, a picture, and the like. When the media content to be published is a video to be published, the video to be published can be a video meeting the requirement of set duration, for example, the duration of the media content to be published is less than 3 minutes and more than 30 seconds; when the media content to be published is pictures, the number of the pictures to be published can be designed according to needs, for example, the number of the pictures to be published can be 1, 5, 10, and the like.
In the embodiment of the present disclosure, the description focuses on the media content to be published as the video to be published.
S102, determining resource contents of the media content to be published under multiple dimensions, and generating a feature vector corresponding to the media content to be published based on the resource contents under the multiple dimensions.
Exemplarily, after determining the resource content of the media content to be published in multiple dimensions, vectorizing the resource content in each dimension to obtain a vector corresponding to the resource content in each dimension; and generating a feature vector corresponding to the media content to be published based on the vector corresponding to the resource content in each dimension.
The plurality of dimensions may include a plurality of dimensions such as image, special effects, score, title, etc. Here, the resource contents of the media content to be published in multiple dimensions can be respectively determined, the media content to be published is represented by the feature vectors corresponding to the resource contents in different dimensions, and the publishing intention of the media content to be published can be more comprehensively covered.
Determining resource contents of the media content to be published under multiple dimensions may include:
determining a plurality of the following resource contents corresponding to the media contents to be published:
the method comprises the steps of obtaining a plurality of pictures corresponding to the media content to be published, special effect content corresponding to the media content to be published, score content corresponding to the media content to be published and title content corresponding to the media content to be published.
For example, the multiple pictures corresponding to the media content to be published in the resource content may be determined according to the following steps: and according to a preset time interval, performing equal-interval frame extraction on the media content to be published, and extracting a plurality of pictures.
For example, if the preset time interval is 1 second and the duration of the media content B to be published is 1 minute, one frame of picture may be extracted from the media content B to be published every second, so as to obtain 60 frames of pictures corresponding to the media content B to be published. The preset time interval can be determined according to the media content to be published, that is, if the time length of the media content to be published is longer, the preset time interval can be larger; if the duration of the media content to be distributed is short, the preset time interval may be small. For example, if the duration of the media content to be released is 1 minute, the preset time interval may be 1 second; if the duration of the media content to be released is 30 seconds, the preset time interval may be 0.5 seconds.
Or, the preset time interval may also be determined according to the priori knowledge, for example, if after multiple tests, the number of extracted pictures is 60 frames, and the accuracy of selecting the topic tag is the highest, it may be determined that the number of extracted pictures corresponding to the media content to be published is 60 frames, and when the duration corresponding to the media content to be published is 2 minutes, the preset time interval may be 2 seconds, that is, one frame of picture is extracted from the media content to be published every 2 seconds; when the time duration corresponding to the media content to be published is 30 seconds, the preset time interval may be 0.5 seconds, that is, one frame of picture is extracted from the media content to be published every 0.5 seconds.
For example, feature extraction may be performed on each frame of picture to obtain a feature vector of each frame of picture, and then the feature vectors of each frame of picture are subjected to fusion processing to obtain a feature vector corresponding to each frame of picture, that is, the feature vector corresponding to the resource content in the picture dimension is obtained. When feature extraction is carried out, feature extraction can be carried out on each frame of picture through a feature extraction network (a convolutional neural network is generally used), and feature vectors of the picture under multiple dimensions such as color, texture and shape are obtained; or, the difference information between different pictures, the same information and the feature information of each frame of picture can be extracted from multiple frames of pictures, and a feature vector corresponding to the media content to be published is generated based on the obtained multiple pieces of feature information, so that the feature vector corresponding to the resource content under the picture dimension is obtained.
The special effect content can be in various forms such as a dynamic effect, a time effect, a decoration effect and the like, for example, the decoration effect of stars can be added to the to-be-released media content, so that the effect of twinkling stars can be seen in the to-be-released media content when the to-be-released media content is viewed; the user can select a special effect content from preset special effect contents to generate media contents to be published, or the user can select a special effect content from the preset special effect contents to add the selected special effect content to the media contents to generate the media contents to be published when uploading the generated media contents to the user side. A feature vector can be determined for each special-effect content, and a title corresponding to the special-effect content and the corresponding feature vector can be stored in an associated manner; therefore, after the media content to be published is obtained, the title of the special effect content corresponding to the media content to be published can be determined, and the feature vector corresponding to the special effect content is obtained based on the title. When determining the feature vector for the special effect content, a feature extraction network, generally a convolutional neural network, may be used, and specifically, the plurality of special effect pictures corresponding to the special effect content may be input into the convolutional neural network for feature extraction to obtain the feature vector of each special effect picture in a plurality of dimensions, such as color, texture, shape, and the like, and the features of the plurality of special effect pictures corresponding to the special effect content are subjected to fusion processing to obtain the feature vector corresponding to the special effect content.
For the soundtrack in the resource content, in specific implementation, the feature information such as corresponding speed, melody, beat, rhythm, timbre and the like may be extracted from the soundtrack, and the extracted feature information is digitized to obtain the feature vector corresponding to the soundtrack, and similarly, the feature vector extraction process may be implemented through a feature extraction network.
The title content corresponding to the media content to be published in the resource content is explained, the title content corresponding to the media content to be published is obtained, word segmentation processing can be performed on the title content of the media content to be published, keywords (such as words with practical significance after removing dummy words) in the title content are extracted, word feature vectors (represented by multiple dimensions such as semantics and word frequency) of the keywords are subjected to fusion processing, and the feature vector corresponding to the title content is obtained.
S103, determining the reference media content matched with the media content to be released in the media content library based on the feature vectors corresponding to the reference media content in the media content library and the feature quantity of the media content to be released.
In the embodiment of the disclosure, a feature vector corresponding to each reference media content in the media content library may be determined, and the reference media content matched with the media content to be published is determined based on the feature vector of the media content to be published and the feature vector corresponding to each reference media content.
For example, the feature vector corresponding to each reference media content in the media content library may be determined according to the following steps:
obtaining each reference media content;
for each reference media content, determining resource content of the reference media content in multiple dimensions, and generating a feature vector of the reference media content based on the resource content in the multiple dimensions.
For example, historically uploaded media content may be determined as reference media content; alternatively, a part of the media content may be selected from the historically uploaded media contents as the reference media content. For example, media content with a click through rate greater than a first threshold and/or media content with a number of comments greater than a second threshold may be selected as the reference media content.
Here, a feature vector corresponding to each reference media content in the media content library may be preset and determined based on the steps provided in the embodiment of the present disclosure, where for each reference media content, resource content of the reference media content in multiple dimensions of information is determined, and the feature vector corresponding to the reference media content is generated based on the resource content in multiple dimensions. For example, if the resource content corresponding to the media content to be published is a plurality of pictures corresponding to the media content to be published and a title content corresponding to the media content to be published, the resource content corresponding to each reference media content may be a plurality of pictures corresponding to the reference media content and a title content corresponding to the reference media content. The process of generating the feature vector of the reference media content based on the resource content of each reference media content in multiple dimensions is the same as the process of generating the feature vector of the media content to be published, and the specific process may refer to the above description, and is not described in detail here.
In an optional implementation manner, determining, based on the feature vector corresponding to each reference media content in the media content library and the feature vector of the media content to be published, a reference media content in the media content library that matches the media content to be published may include:
inputting the characteristic vector corresponding to the reference media content and the characteristic vector of the media content to be published into a correlation degree detection model, and determining the correlation degree between the reference media content and the media content to be published; the correlation degree detection model is obtained by training a plurality of training samples based on the correlation degree among different marked media contents; or calculating cosine similarity between the feature vector corresponding to the reference media content and the feature vector corresponding to the media content to be published, and determining the cosine similarity as the correlation between the reference media content and the media content to be published;
and determining the reference media content matched with the media content to be published in the media content library based on the correlation between each reference media content and the media content to be published.
For example, a plurality of training sample media contents marked with correlation degrees between different media contents may be obtained, the plurality of training sample media contents are input into a designed neural network (i.e., input into a correlation degree detection model), and the neural network is trained until the accuracy of the neural network meets a set threshold.
In the embodiment of the disclosure, the feature vectors of the media content to be published and the feature vector corresponding to each reference media content may be input to the correlation detection model, so as to obtain the correlation between each reference media content and the media content to be published.
Or, under the condition that a correlation detection model is not adopted, the cosine similarity between the feature vector of each reference media content and the feature vector of the media content to be issued can be directly calculated. The cosine similarity value can represent the similarity between individuals, so the cosine similarity value can be determined as the correlation between the media content to be published and the reference media content, wherein the higher the similarity between the reference media content and the media content to be published is, the higher the corresponding correlation is. Therefore, the cosine similarity between the feature vector of each reference media content and the feature vector of the media content to be published can be calculated, and the cosine similarity is determined as the correlation between the reference media content and the media content to be published.
In the embodiment of the disclosure, the reference media content matched with the media content to be published in the media content library can be determined based on the correlation between each reference media content and the media content to be published. For example, a relevancy threshold may be set, and the reference media content with the relevancy greater than the set relevancy threshold is determined as the reference media content matched with the media content to be published; or, the target number of the reference media contents matched with the media contents to be published may also be set, and the reference media contents with a larger degree of correlation and the target number are selected from the media content library as the reference media contents matched with the media contents to be published.
And S104, sending the determined topic tag corresponding to the reference media content to the user side as a recommended topic tag.
In the embodiment of the disclosure, the topic tag corresponding to each reference media content matched with the media content to be published can be determined, and the determined topic tag is sent to the user side.
Exemplarily, the sending the determined topic tag corresponding to the reference media content to the user end as the recommended topic tag includes:
acquiring each selected topic label corresponding to the reference media content;
and carrying out duplicate removal processing on each selected topic label and then pushing the processed topic label to a user side.
For example, the reference media content matched with the media content to be published includes reference media content a and reference media content B, each selected topic tag corresponding to the reference media content a may include a cat, a smile and a life, and each selected topic tag corresponding to the reference media content B may include a cat, a humor and a life, so that it can be known that the topic tags "life and cat" are repeated, each selected topic tag is subjected to deduplication processing to obtain the topic tags "cat, smile, life and humor", and the topic tags obtained after deduplication processing are pushed to the user side.
Exemplarily, the sending each selected topic tag to the user side after performing deduplication processing includes:
performing deduplication processing on each selected topic label to obtain at least one candidate topic label;
and selecting a recommended topic tag from the at least one candidate topic tag according to the user behavior data corresponding to the at least one candidate topic tag, and sending the recommended topic tag to the user terminal. Wherein the user behavior data authorized by the user comprises: the media content playing amount corresponding to the candidate topic label and/or the frequency of selecting the candidate topic label.
Here, after performing deduplication processing on each selected topic tag, the number of obtained topic tags may be large, and at this time, the topic tags obtained after deduplication may be filtered according to the media content playing amount corresponding to the candidate topic tags and/or the number of times the candidate topic tags are selected, and the filtered topic tags may be sent to the user end. For example, the corresponding topic tag whose media content playback amount is greater than the playback amount threshold may be selected to be sent to the client as the recommended topic tag, for example, if the media content corresponding to a certain candidate topic tag includes media content a, media content B, and media content C, if the total playback amount of these media contents is 2000 times and the playback amount threshold is 1000 times, the candidate topic tag may be sent to the client as the recommended topic tag; or, the number of times that each topic tag in the candidate topics is selected as a topic tag may be determined, and the candidate topic tags that are selected as topic tags with the number of times greater than the number of times threshold are sent to the client as recommended topic tags, for example, the candidate topic tags include candidate topic tag a, candidate topic tag B, and candidate topic tag C, and statistics shows that the number of times that candidate topic tag a is selected as a topic tag is 50 times, the number of times that candidate topic tag B is selected as a topic tag is 110 times, the number of times that candidate topic tag C is selected as a topic tag is 150 times, and the number of times threshold is 100 times, and then it is determined that candidate topic tag B and candidate topic tag C are sent to the client as recommended topic tags; or, the media content playing amount corresponding to the candidate topic tag and the number of times that the candidate topic tag is selected may be considered comprehensively, and specifically, the candidate topic tag whose corresponding media content playing amount is greater than the playing amount threshold and the number of times that the candidate topic tag is selected as the topic tag is greater than the number threshold may be selected and sent to the user end as the recommended topic tag.
In the method, the characteristic vector corresponding to the media content to be published is generated by determining the resource content of the acquired media content to be published under multiple dimensions and based on the resource content under the multiple dimensions; determining reference media contents matched with the media contents to be published in the media content library based on the feature vectors corresponding to the reference media contents in the media content library and the feature vectors of the media contents to be published; the determined topic labels corresponding to the reference media content are sent to the user side as recommended topic labels, the user selects the topic labels by referring to the selected topic labels, namely, the user selects the topic labels by referring to the understanding of other users on the media content to be released, so that the topic labels can be selected more accurately, the user viewing the media content can search for more accurate media content based on the input topic labels, and further the effective viewing rate of the media content is improved.
For example, an interface schematic diagram of the publishing information editing page is shown in fig. 2, where fig. 2 includes a text introduction input box located at the top of the interface and a to-be-published media content display box, then, the received recommended topic tags, that is, # recommended topic tag a, # recommended topic tag B, # recommended topic tag C, etc., may be introduced to basic information, that is, location information of the user end (the user may add corresponding location information at the location of the interface), and permission information for viewing the to-be-published media content (for example, setting a permission of who can see the media content, which permission may include disclosure, only self-viewing, partial viewing, etc.); the lowermost panel may include a draft box operation button, and a distribution operation button. The user can input the text introduction corresponding to the media content to be published, such as a title and the like, in the text introduction input box; the to-be-published media content display frame is used for displaying the to-be-published media content uploaded by the user; the user can select a required recommended topic tag from the received recommended topic tags; the user can store the information on the published information editing interface in the draft box by triggering the draft box operation button; the user can trigger the release operation button to indicate the information release on the release information editing interface to the preset position.
Example two
An embodiment of the present disclosure provides an information publishing method, which is applied to a client, and referring to a flowchart of the information publishing method shown in fig. 3, the method includes S301 to S303, and the specific process is as follows:
s301, acquiring media content to be published, and sending the media content to be published to a server;
s302, receiving a recommended topic tag corresponding to the media content to be published, which is fed back by the server;
and S303, displaying the recommended topic tag on a publishing information editing page corresponding to the media content to be published.
In the embodiment of the disclosure, the client can send the acquired media content to be published to the server; the server determines a recommended topic tag corresponding to the media content to be published based on the acquired media content to be published, and sends the recommended topic tag to the client; the client receives the recommended topic tags corresponding to the media content to be published, which are fed back by the server, and can display the recommended topic tags on the published information editing page corresponding to the media content to be published, so that a user corresponding to the client can directly select the topic tags corresponding to the media content to be published based on the displayed recommended topic tags, add the selected topic tags to the media content to be published, and complete the publishing of the media content.
In one possible implementation manner, the displaying of the recommended topic tag on the publishing information editing page corresponding to the media content to be published includes:
and displaying the recommended topic tag below the topic selection button in the published information editing page.
For example, the received recommended topic tag may be displayed below the topic selection button, or may be displayed at any position in the published information editing page, where the display position of the recommended topic tag may be designed as needed. Specifically, the recommended topic tag may include topic tag identification information, and the topic tag identification information may be any regular graph or an irregular graph, for example, the topic tag identification information may be "#, # and so on.
It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.
Based on the same inventive concept, an information pushing device corresponding to the information pushing method and an information publishing device corresponding to the information publishing method are also provided in the embodiments of the present disclosure, and because the principle of solving the problem of the information pushing device in the embodiments of the present disclosure is similar to the information pushing method in the embodiments of the present disclosure, and the principle of solving the problem of the information publishing device in the embodiments of the present disclosure is similar to the information publishing method in the embodiments of the present disclosure, the implementation of the device may refer to the implementation of the method, and repeated parts are not described again.
EXAMPLE III
Based on the same concept, an embodiment of the present disclosure provides an information pushing apparatus, referring to a schematic structural diagram of an information pushing apparatus shown in fig. 4, where the apparatus includes:
a media content obtaining module 401, configured to obtain media content to be published uploaded by a user side;
a feature vector generation module 402, configured to determine resource content of the media content to be published in multiple dimensions, and generate a feature vector corresponding to the media content to be published based on the resource content in the multiple dimensions;
a reference media content determining module 403, configured to determine, based on a feature vector corresponding to each reference media content in a media content library and a feature vector of the media content to be published, reference media content in the media content library that is matched with the media content to be published;
a topic sending module 404, configured to send the determined topic tag corresponding to the reference media content to the user end as a recommended topic tag.
In an optional implementation manner, the feature vector generation module 402, when determining resource content of the media content to be published in multiple dimensions, is configured to:
determining a plurality of the following resource contents corresponding to the media content to be published:
the content publishing system comprises a plurality of pictures corresponding to the media content to be published, special effect content corresponding to the media content to be published, dubbing content corresponding to the media content to be published and title content corresponding to the media content to be published.
In an optional implementation manner, the feature vector generation module 402 determines a plurality of pictures corresponding to the media content to be published according to the following steps:
and performing equal-interval frame extraction on the media content to be issued according to a preset time interval, and extracting the plurality of pictures.
In an alternative embodiment, the reference media content determining module 403 determines the feature vector corresponding to each reference media content in the media content library according to the following steps:
acquiring each reference media content;
for each reference media content, determining resource content of the reference media content in multiple dimensions, and generating a feature vector of the reference media content based on the resource content in the multiple dimensions.
In an optional implementation manner, the reference media content determining module 403, when determining, based on the feature vector corresponding to each reference media content in the media content library and the feature vector of the media content to be published, a reference media content in the media content library that matches the media content to be published, is configured to:
inputting the feature vector corresponding to the reference media content and the feature vector of the media content to be published into a correlation degree detection model, and determining the correlation degree between the reference media content and the media content to be published; the relevancy detection model is obtained by training a plurality of training sample media contents based on the relevancy among the marked different media contents; or calculating cosine similarity between the feature vector corresponding to the reference media content and the feature vector corresponding to the media content to be published, and determining the cosine similarity as the correlation between the reference media content and the media content to be published;
and determining the reference media content matched with the media content to be published in a media content library based on the correlation degree between the reference media content and the media content to be published.
In an optional implementation manner, the topic transmission module 404, when transmitting the determined topic tag corresponding to the reference media content to the user end as a recommended topic tag, is configured to:
obtaining each selected topic tag corresponding to the reference media content;
and carrying out duplicate removal processing on each selected topic label and then pushing the processed topic label to the user side.
In an optional implementation manner, the topic transmission module 404, after performing deduplication processing on each selected topic tag, transmits the topic tag to the user side, and is configured to:
performing deduplication processing on each selected topic label to obtain at least one candidate topic label;
and selecting a recommended topic tag from the at least one candidate topic tag according to the user behavior data corresponding to the at least one candidate topic tag, and sending the recommended topic tag to the user terminal.
In an alternative embodiment, the user behavior data includes: the media content playing amount corresponding to the candidate topic label and/or the selected times corresponding to the candidate topic label.
In some embodiments, the functions of the apparatus provided in the embodiments of the present disclosure or the included templates may be used to execute the method described in the above method embodiments, and specific implementation thereof may refer to the description of the above method embodiments, and for brevity, no further description is provided here.
The information pushing device provided by the embodiment of the present disclosure has the same technical features as the information pushing method provided by the first embodiment, so that the same technical problems can be solved, and the same technical effects can be achieved.
Example four
Based on the same concept, the embodiment of the present disclosure provides an information distribution apparatus, referring to a schematic structural diagram of an information distribution apparatus shown in fig. 5, the apparatus including:
the media content sending module 501 is configured to obtain media content to be published, and send the media content to be published to a server;
a topic receiving module 502, configured to receive a recommended topic tag corresponding to the media content to be published, where the recommended topic tag is fed back by the server;
a displaying module 503, configured to display the recommended topic tag on a publishing information editing page corresponding to the media content to be published.
In an optional implementation manner, when the publishing information editing page corresponding to the media content to be published shows the recommended topic tag, the presenting module 503 is configured to:
and displaying the recommended topic tag below a topic selection button in the published information editing page.
EXAMPLE five
Based on the same technical concept, the embodiment of the disclosure also provides an electronic device. Referring to fig. 6, a schematic structural diagram of an electronic device 600 provided in the embodiment of the present disclosure includes a processor 601, a memory 602, and a bus 603. The memory 602 is used for storing execution instructions and includes a memory 6021 and an external memory 6022; the memory 6021 is also referred to as an internal memory, and is configured to temporarily store the operation data in the processor 601 and the data exchanged with the external memory 6022 such as a hard disk, the processor 601 exchanges data with the external memory 6022 through the memory 6021, and when the electronic device 600 operates, the processor 601 communicates with the memory 602 through the bus 603, so that the processor 601 executes the following instructions:
acquiring media contents to be issued uploaded by a user side;
determining resource contents of the media content to be published under multiple dimensions, and generating a feature vector corresponding to the media content to be published based on the resource contents under the multiple dimensions;
determining reference media contents matched with the media contents to be published in a media content library based on the feature vectors corresponding to the reference media contents in the media content library and the feature vectors of the media contents to be published;
and sending the determined topic label corresponding to the reference media content to the user side as a recommended topic label.
In one possible design, the instructions that may be executed by the processor 601 further include:
determining a plurality of the following resource contents corresponding to the media content to be published:
the content publishing system comprises a plurality of pictures corresponding to the media content to be published, special effect content corresponding to the media content to be published, dubbing content corresponding to the media content to be published and title content corresponding to the media content to be published.
In one possible design, the instructions that may be executed by the processor 601 further include:
and performing equal-interval frame extraction on the media content to be issued according to a preset time interval, and extracting the plurality of pictures.
In one possible design, the instructions that may be executed by the processor 601 further include:
acquiring each reference media content;
for each reference media content, determining resource content of the reference media content in multiple dimensions, and generating a feature vector of the reference media content based on the resource content in the multiple dimensions.
In one possible design, the instructions that may be executed by the processor 601 further include:
inputting the feature vector corresponding to the reference media content and the feature vector of the media content to be published into a correlation degree detection model, and determining the correlation degree between the reference media content and the media content to be published; the relevancy detection model is obtained by training a plurality of training sample media contents based on the relevancy among the marked different media contents; or calculating cosine similarity between the feature vector corresponding to the reference media content and the feature vector corresponding to the media content to be published, and determining the cosine similarity as the correlation between the reference media content and the media content to be published;
and determining the reference media content matched with the media content to be published in a media content library based on the correlation degree between the reference media content and the media content to be published.
In one possible design, the instructions that may be executed by the processor 601 further include:
obtaining each selected topic tag corresponding to the reference media content;
and carrying out duplicate removal processing on each selected topic label and then pushing the processed topic label to the user side.
In one possible design, the instructions that may be executed by the processor 601 further include:
performing deduplication processing on each selected topic label to obtain at least one candidate topic label;
and selecting a recommended topic tag from the at least one candidate topic tag according to the user behavior data corresponding to the at least one candidate topic tag, and sending the recommended topic tag to the user terminal.
In one possible design, the instructions that may be executed by the processor 601 further include:
the user behavior data includes: the media content playing amount corresponding to the candidate topic label and/or the selected times corresponding to the candidate topic label.
Based on the same technical concept, the embodiment of the disclosure also provides another electronic device. Referring to fig. 7, a schematic structural diagram of an electronic device 700 provided in the embodiment of the present disclosure includes a processor 701, a memory 702, and a bus 703. The memory 702 is used for storing execution instructions and includes a memory 7021 and an external memory 7022; the memory 7021 is also referred to as an internal memory, and is used to temporarily store operation data in the processor 701 and data exchanged with an external memory 7022 such as a hard disk, the processor 701 exchanges data with the external memory 7022 through the memory 7021, and when the electronic device 700 is operated, the processor 701 and the memory 702 communicate with each other through the bus 703, so that the processor 701 executes the following instructions:
acquiring media content to be published, and sending the media content to be published to a server;
receiving a recommended topic tag which is fed back by the server and corresponds to the media content to be published;
and displaying the recommended topic tag on a publishing information editing page corresponding to the media content to be published.
In one possible design, the instructions that may be executed by the processor 701 further include:
and displaying the recommended topic tag below a topic selection button in the published information editing page.
EXAMPLE six
The embodiments of the present disclosure also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the information pushing method in the foregoing method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.
The computer program product of the information push method provided in the embodiments of the present disclosure includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the steps of the information push method in the embodiments of the method described above, which may be referred to in the embodiments of the method specifically, and are not described herein again.
The embodiment of the present disclosure further provides another computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the information distribution method in the foregoing method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.
The computer program product of the information issuing method provided in the embodiment of the present disclosure includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute steps of the information issuing method in the above method embodiment, which may be referred to specifically in the above method embodiment, and are not described herein again.
The embodiments of the present disclosure also provide a computer program, which when executed by a processor implements any one of the methods of the foregoing embodiments. The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims (14)

1. An information pushing method, comprising:
acquiring media contents to be issued uploaded by a user side;
determining resource contents of the media content to be published under multiple dimensions, and generating a feature vector corresponding to the media content to be published based on the resource contents under the multiple dimensions;
determining reference media contents matched with the media contents to be published in a media content library based on the feature vectors corresponding to the reference media contents in the media content library and the feature vectors of the media contents to be published;
and sending the determined topic label corresponding to the reference media content to the user side as a recommended topic label.
2. The information pushing method according to claim 1, wherein determining resource contents of the media content to be published in multiple dimensions comprises:
determining a plurality of the following resource contents corresponding to the media content to be published:
the content publishing system comprises a plurality of pictures corresponding to the media content to be published, special effect content corresponding to the media content to be published, dubbing content corresponding to the media content to be published and title content corresponding to the media content to be published.
3. The information push method according to claim 2, wherein if the resource content in the multiple dimensions includes multiple pictures corresponding to the media content to be distributed; determining a plurality of pictures corresponding to the media content to be published according to the following steps:
and performing equal-interval frame extraction on the media content to be issued according to a preset time interval, and extracting the plurality of pictures.
4. The information pushing method according to claim 1, wherein the feature vector corresponding to each reference media content in the media content library is determined according to the following steps:
acquiring each reference media content;
for each reference media content, determining resource content of the reference media content in multiple dimensions, and generating a feature vector of the reference media content based on the resource content in the multiple dimensions.
5. The information pushing method according to claim 1, wherein determining, based on the feature vector corresponding to each reference media content in the media content library and the feature vector of the media content to be published, the reference media content in the media content library that matches the media content to be published comprises:
inputting the feature vector corresponding to the reference media content and the feature vector of the media content to be published into a correlation degree detection model, and determining the correlation degree between the reference media content and the media content to be published; the relevancy detection model is obtained by training a plurality of training samples based on the relevancy among the marked different media contents; alternatively, the first and second electrodes may be,
calculating cosine similarity between the feature vector corresponding to the reference media content and the feature vector corresponding to the media content to be published, and determining the cosine similarity as the correlation between the reference media content and the media content to be published;
and determining the reference media content matched with the media content to be published in a media content library based on the correlation degree between each reference media content and the media content to be published.
6. The information pushing method according to claim 1, wherein sending the determined topic tag corresponding to the reference media content to the user end as a recommended topic tag comprises:
obtaining each selected topic tag corresponding to the reference media content;
and carrying out duplicate removal processing on each selected topic label and then pushing the processed topic label to the user side.
7. The information pushing method according to claim 6, wherein the step of sending each selected topic tag to the user side after performing deduplication processing comprises:
performing deduplication processing on each selected topic label to obtain at least one candidate topic label;
and selecting a recommended topic tag from the at least one candidate topic tag according to the user behavior data corresponding to the at least one candidate topic tag, and sending the recommended topic tag to the user terminal.
8. The information pushing method according to claim 7, wherein the user behavior data includes: the media content playing amount corresponding to the candidate topic label and/or the frequency of selecting the candidate topic label.
9. An information distribution method, comprising:
acquiring media content to be published, and sending the media content to be published to a server;
receiving a recommended topic tag which is fed back by the server and corresponds to the media content to be published;
and displaying the recommended topic tag on a publishing information editing page corresponding to the media content to be published.
10. The information distribution method according to claim 9, wherein the presenting of the recommended topic tag on the distribution information editing page corresponding to the media content to be distributed includes:
and displaying the recommended topic tag below a topic selection button in the published information editing page.
11. An information pushing apparatus, comprising:
the media content acquisition module is used for acquiring media content to be issued uploaded by a user side;
the characteristic vector generation module is used for determining resource contents of the media content to be published under multiple dimensions and generating a characteristic vector corresponding to the media content to be published based on the resource contents under the multiple dimensions;
the reference media content determining module is used for determining reference media content matched with the media content to be published in the media content library based on the feature vector corresponding to each reference media content in the media content library and the feature vector of the media content to be published;
and the topic sending module is used for sending the determined topic label corresponding to the reference media content to the user side as a recommended topic.
12. An information distribution apparatus, comprising:
the media content sending module is used for acquiring media content to be published and sending the media content to be published to the server;
the topic receiving module is used for receiving the recommended topic labels which are fed back by the server and correspond to the media contents to be published;
and the display module is used for displaying the recommended topic tag on a publishing information editing page corresponding to the media content to be published.
13. An electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory communicate with each other through the bus when the electronic device is operated, and the machine-readable instructions are executed by the processor to execute the steps of the information pushing method according to any one of claims 1 to 8 or execute the steps of the information issuing method according to any one of claims 9 to 10.
14. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed by a processor, performs the steps of the information pushing method according to any one of claims 1 to 8, or performs the steps of the information distribution method according to any one of claims 9 to 10.
CN202010201534.6A 2020-03-20 2020-03-20 Information pushing and information publishing method and device Pending CN111400517A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010201534.6A CN111400517A (en) 2020-03-20 2020-03-20 Information pushing and information publishing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010201534.6A CN111400517A (en) 2020-03-20 2020-03-20 Information pushing and information publishing method and device

Publications (1)

Publication Number Publication Date
CN111400517A true CN111400517A (en) 2020-07-10

Family

ID=71435272

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010201534.6A Pending CN111400517A (en) 2020-03-20 2020-03-20 Information pushing and information publishing method and device

Country Status (1)

Country Link
CN (1) CN111400517A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111859156A (en) * 2020-08-04 2020-10-30 上海风秩科技有限公司 Method and device for determining release crowd, readable storage medium and electronic equipment
CN111897996A (en) * 2020-08-10 2020-11-06 北京达佳互联信息技术有限公司 Topic label recommendation method, device, equipment and storage medium
CN112035687A (en) * 2020-08-28 2020-12-04 北京字节跳动网络技术有限公司 Method and device for issuing multimedia content, electronic equipment and storage medium
CN112087667A (en) * 2020-09-10 2020-12-15 北京字节跳动网络技术有限公司 Information processing method and device and computer storage medium
CN113239286A (en) * 2021-04-21 2021-08-10 珠海大横琴科技发展有限公司 Information recommendation method and device
CN114357278A (en) * 2020-09-28 2022-04-15 腾讯科技（深圳）有限公司 Topic recommendation method, device and equipment
CN114578999A (en) * 2020-11-16 2022-06-03 深圳市万普拉斯科技有限公司 Image sharing method and device and terminal equipment

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915359A (en) * 2014-03-14 2015-09-16 华为技术有限公司 Theme label recommending method and device
CN110737801A (en) * 2019-10-14 2020-01-31 腾讯科技（深圳）有限公司 Content classification method and device, computer equipment and storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104915359A (en) * 2014-03-14 2015-09-16 华为技术有限公司 Theme label recommending method and device
CN110737801A (en) * 2019-10-14 2020-01-31 腾讯科技（深圳）有限公司 Content classification method and device, computer equipment and storage medium

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111859156A (en) * 2020-08-04 2020-10-30 上海风秩科技有限公司 Method and device for determining release crowd, readable storage medium and electronic equipment
CN111859156B (en) * 2020-08-04 2024-02-02 上海秒针网络科技有限公司 Method and device for determining distribution crowd, readable storage medium and electronic equipment
CN111897996A (en) * 2020-08-10 2020-11-06 北京达佳互联信息技术有限公司 Topic label recommendation method, device, equipment and storage medium
CN111897996B (en) * 2020-08-10 2023-10-31 北京达佳互联信息技术有限公司 Topic label recommendation method, device, equipment and storage medium
CN112035687A (en) * 2020-08-28 2020-12-04 北京字节跳动网络技术有限公司 Method and device for issuing multimedia content, electronic equipment and storage medium
WO2022042401A1 (en) * 2020-08-28 2022-03-03 北京字节跳动网络技术有限公司 Multimedia content publishing method and apparatus, electronic device, and storage medium
CN112087667A (en) * 2020-09-10 2020-12-15 北京字节跳动网络技术有限公司 Information processing method and device and computer storage medium
CN114357278A (en) * 2020-09-28 2022-04-15 腾讯科技（深圳）有限公司 Topic recommendation method, device and equipment
CN114357278B (en) * 2020-09-28 2024-03-19 腾讯科技（深圳）有限公司 Topic recommendation method, device and equipment
CN114578999A (en) * 2020-11-16 2022-06-03 深圳市万普拉斯科技有限公司 Image sharing method and device and terminal equipment
CN113239286A (en) * 2021-04-21 2021-08-10 珠海大横琴科技发展有限公司 Information recommendation method and device

Similar Documents

Publication Publication Date Title
CN111400517A (en) Information pushing and information publishing method and device
Zitnick et al. Adopting abstract images for semantic scene understanding
CN110737783B (en) Method and device for recommending multimedia content and computing equipment
CN108959586B (en) Identifying textual terms in response to a visual query
WO2018072513A1 (en) Advertisement information pushing method and apparatus, and system, server and computer readable medium
CN112084268A (en) Method and device for displaying search results and computer storage medium
CN111143610A (en) Content recommendation method and device, electronic equipment and storage medium
CN111259173B (en) Search information recommendation method and device
US20120099784A1 (en) Chromatic matching game
CN106951571B (en) Method and device for labeling application with label
CN110325986A (en) Article processing method, device, server and storage medium
CN105512180B (en) A kind of search recommended method and device
CN113536172B (en) Encyclopedia information display method and device and computer storage medium
EP2874102A2 (en) Generating models for identifying thumbnail images
CN110166811A (en) Processing method, device and the equipment of barrage information
CN116894711A (en) Commodity recommendation reason generation method and device and electronic equipment
CN113836448A (en) Information display method and device, computer equipment and storage medium
CN111753204B (en) Information pushing method and device, electronic equipment and storage medium
CN116610858A (en) Information distribution method, device, electronic equipment and storage medium
Chen Real-time interactive micro movie placement marketing system based on discrete-event simulation
CN111859156B (en) Method and device for determining distribution crowd, readable storage medium and electronic equipment
US10860636B2 (en) Method and apparatus for searching cartoon
CN113255349A (en) Information processing method and device and computer storage medium
CN110764676B (en) Information resource display method and device, electronic equipment and storage medium
CN111597469A (en) Display position determining method and device, electronic equipment and storage medium

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Applicant after: Douyin Vision Co.,Ltd.

Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Applicant before: Tiktok vision (Beijing) Co.,Ltd.

Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Applicant after: Tiktok vision (Beijing) Co.,Ltd.

Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Applicant before: BEIJING BYTEDANCE NETWORK TECHNOLOGY Co.,Ltd.