WO2021092934A1

WO2021092934A1 - Video data-based message pushing method and device, and computer storage medium

Info

Publication number: WO2021092934A1
Application number: PCT/CN2019/118912
Authority: WO
Inventors: 艾静雅; 柳彤; 朱大卫; 汤慧秀
Original assignee: 深圳海付移通科技有限公司
Priority date: 2019-11-15
Filing date: 2019-11-15
Publication date: 2021-05-20
Also published as: CN111684815A; CN111684815B

Abstract

The present application discloses a video data-based message pushing method and device, and a computer storage medium. Said video data-based message pushing method comprises: obtaining the current scenario information; on the basis of the current scenario information, obtaining from a pre-established mapping data table a target video data type matching with the current scenario information, said mapping data table being established by classifying the video files in a video database according to pre-set tags and by associating same with scenario information; performing message pushing according to the tag of the target video data type. The present method allows for personalized message pushing for users and enhances message pushing accuracy.

Description

Video data-based message pushing method, equipment and computer storage medium

【Technical Field】

This application relates to the field of data processing technology, in particular to a method, equipment and computer storage medium for pushing messages based on video data.

【Background technique】

With the rapid development of Internet technology, society has truly become an information age. The Internet can store massive amounts of information, bringing great convenience to people's work and life. In order to make better use of the Internet and facilitate users to quickly find the information they want in the massive information on the Internet, the research on the method of message push based on video data has been gradually developed in related technologies.

However, most of the message pushes involved in related technologies are fixed information pushes, such as pushing festival introductions on specific festivals, pushing current affairs hotspot information when major news occurs, and sending simple location information when they arrive in a new city (for example, when a user is detected). When you arrive in Shenzhen, send "Welcome to Shenzhen") and so on.

However, the information that is pushed is often not what the user wants, so the efficiency of pushing is low, and the user experience is poor.

[Summary of the invention]

The main technical problem to be solved by the application is to provide a method, equipment and computer storage medium for message push based on video data, which can provide users with personalized message push and improve the accuracy of message push.

In order to solve the above technical problems, a technical solution adopted in this application is to provide a message push method based on video data, the method includes: obtaining current scene information; based on the current scene information, from a pre-established mapping data table , Obtain the target video data category that matches the current scene information; Among them, the mapping data table is established by classifying the video files in the video database according to preset tags and associating the scene information; According to the tags of the target video data category, Push news.

In order to solve the above technical problem, another technical solution adopted in this application is: a processor and a memory electrically connected to the processor, the memory is used to store program data, and the processor is used to execute the program data to implement the above method.

In order to solve the above technical problem, another technical solution adopted in this application is to provide a computer storage medium for storing program data, which is used to implement the above method when the program data is executed by a processor.

The beneficial effect of this application is that, different from the state of the art, this application obtains the current scene information based on the current scene information from the pre-established mapping data table, and obtains the target video that matches the current scene information. Data category, so as to push the message according to the label of the target video data category. Since the mapping data table is established by classifying the video files in the video database according to the preset label and associating the scene information, the pushed message is not only the same as the current one. The scene information is associated with the historical video files and their scene information, so that the pushed messages are based on the user’s past behavior and meet the needs of the current scene, that is, the pushed messages are personalized and practical. Therefore, it can provide users with personalized message push and improve the accuracy of message push.

【Explanation of the drawings】

In order to more clearly describe the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained from these drawings without creative work.

FIG. 1 is a schematic flowchart of a first embodiment of a method for pushing a message based on video data provided by the present application;

2 is a schematic flowchart of a second embodiment of a method for pushing messages based on video data provided by the present application;

3 is another schematic flowchart of the second embodiment of the method for pushing messages based on video data provided by the present application;

4 is a schematic flowchart of a third embodiment of a method for pushing a message based on video data provided by the present application;

FIG. 5 is a schematic flowchart of a fourth embodiment of a method for pushing a message based on video data provided by the present application;

FIG. 6 is a schematic structural diagram of an embodiment of a terminal device provided by the present application;

Fig. 7 is a schematic diagram of an embodiment of a computer storage medium provided by the present application.

【Detailed ways】

The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The terms "first", "second", and "third" in the embodiments of the present application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of the features. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise specifically defined. In addition, the terms "including" and "having" and any variations of them are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes unlisted steps or units, or optionally also includes Other steps or units inherent to these processes, methods, products or equipment.

Reference to "embodiments" herein means that a specific feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art clearly and implicitly understand that the embodiments described herein can be combined with other embodiments.

Please refer to FIG. 1. FIG. 1 is a schematic flowchart of a first embodiment of a method for pushing a message based on video data provided by the present application.

The method 100 for pushing messages based on video data in this embodiment includes the following steps:

S120: Obtain current scene information.

The current scene information can be acquired through various sensors on the terminal device, or through a network channel in a networked state, or information input by the user can be acquired as the scene information.

In this embodiment, a preset frequency can be set to obtain current scene information, and the current scene information can reflect real-time scene changes.

S140: Based on the current scene information, obtain a target video data class matching the current scene information from a pre-established mapping data table.

Among them, the mapping data table is established by classifying the video files in the video database and correlating scene information according to preset tags.

After the video files in the video database are classified, they are associated with the scene information of the video files, so that a mapping data table with a corresponding relationship can be obtained.

Since the video files in the video database are the user's past shooting content or video viewing content, the mapping data table is established by classifying the video files in the video database according to preset tags and associating the scene information (of the video file) It can reflect the user's personal characteristics such as the video shooting style, hobbies, living habits, and the scene at the time.

The target video data class obtained by this method is not only related to the current scene information, but also based on the historical video file and its scene information, so it meets the real-time scene changes and the individual needs of the user at the same time.

S160: Push the message according to the tag of the target video data category.

According to the tags of the target video data category, obtain the user's interesting and useful news, and push the news.

The tag of the target video data category corresponds to a preset tag for classifying the video file, and the tag can reflect various information contained in the video file.

The method 100 for pushing messages based on video data provided in this embodiment obtains the current scene information and based on the current scene information from a pre-established mapping data table to obtain the target video data category that matches the current scene information. , So as to push the message according to the label of the target video data category. Since the mapping data table is established by classifying the video files in the video database according to the preset label and correlating the scene information, the pushed message is not only related to the current scene. Information is correlated, and based on historical video files and their scene information, so that the pushed messages are based on the user's past behaviors and meet the needs of the current scene, that is, the pushed messages are personalized and practical, so they can Provide users with personalized message push to improve the accuracy of message push.

Optionally, before S120: acquiring current scene information, it may further include:

Obtain the permission to push messages.

Obtaining the authority to perform message push, that is, acquiring the authority of the user (or device) to enable the message push function.

Among them, the method of obtaining the permission to push messages may include:

Obtain the notification that the user has enabled the message push function.

For example, when a user opens an application for the first time, the application can prompt the user to enable the message push function through a pop-up window or voice, and the user can confirm that the message push function is enabled by tapping the screen, voice control, or gesture control.

Or, get a notification that the message push function is enabled by default.

For example, the system enables the message push function by default, and at the same time that the message is pushed for the first time, the user is asked if they agree to continue pushing in the future.

It should be noted that the order of the foregoing steps in this embodiment is the order of description in this embodiment, and is not limited to the order of the method in this embodiment during execution. On the premise that this solution can be realized, some steps can be reversed in order.

Please refer to FIG. 2 and FIG. 3 in combination. FIG. 2 is a schematic flowchart of a second embodiment of a method for pushing a message based on video data provided by the present application. FIG. 3 is a schematic diagram of another flow in the second embodiment of the method for pushing messages based on video data provided by the present application.

The second embodiment of the video data-based message pushing method 100 of this application is based on the first embodiment of the video data-based message pushing method 100 of this application. Therefore, the same steps in this embodiment and the first embodiment will not be described again, you can refer to Description in the first embodiment.

In this embodiment, the method 100 for pushing messages based on video data further includes:

S220: Acquire multiple video files in the video database.

Optionally, in step S220, multiple video files in the video database and scene information of each video file can also be acquired at the same time.

S240: Classify the video files in the video database according to preset tags.

Optionally, in step S240, the video files in the video database may be classified according to preset tags and scene information of each video file.

S260: Acquire scene information of each video file.

The scene information of each video file may be, for example, information such as the time, location, and gyroscope when the video was shot or viewed.

As mentioned above, step S260 can also be executed before step S240.

S280: Establish a mapping table according to the classification of multiple video files and corresponding scene information.

Optionally, please refer to FIG. 3, step S240: classifying the video files in the video database according to preset tags, which may include:

S241: Perform framing processing on the video file in the video database to obtain multiple video frames.

S242: Input each video frame to the trained deep learning network to output a corresponding label.

Among them, the deep learning network is obtained by supervised learning training based on the video frames with pre-established corresponding relationships and preset labels.

The preset tags, for example: related information about "people" in the segmented video frame, including: single, multi-person, selfie, happy, sad, etc.; related to "travel" in the segmented video frame Information, including: seaside, grassland, desert, etc.; related information about "objects" in the segmented video frame, including: apples, pears, cars, airplanes, trains, etc.

In this embodiment, each video frame is input to a trained deep learning network to output a corresponding label. The main methods are deep learning and image semantic segmentation.

Deep learning is a branch of machine learning. It mainly refers to deep neural network algorithms. Deep neural networks have more levels than ordinary neural networks and can better capture the deep-level relationships in data. The resulting model is more accurate and is mainly used for features Learn. Through a large number of pre-input video frames and preset segmentation tags, after deep learning training, the input video frames can be automatically and quickly segmented into corresponding semantic information, that is, the tags corresponding to each video frame are output.

S243: Analyze the video files in the video database according to the output corresponding tags, and classify and generate a data list.

Optionally, step S243 may include: analyzing the video files in the video database according to the output corresponding tags and scene information of each video file, and classifying and generating a data list.

In this embodiment, the video files in the video database are classified, and a data list is generated by classifying. The corresponding tags obtained by AI automatic detection and image semantic segmentation are mainly used, and the scene information of each video file can be combined.

According to the output corresponding tags (which can also be combined with the scene information contained in the video file, such as time information, location information, gyroscope, etc.), analyze the video files in the video database, and generate a data list corresponding to the classification.

For example, Table 1 shows part of the classification:

Table 1

It can be understood that only some of the classifications are listed as examples in Table 1, and the actual classifications are generally more detailed and complicated.

Optionally, please refer to FIG. 3, step S280: establishing a mapping table according to the classification of multiple video files and corresponding scene information, which may include:

S281: Perform data link based on the data list and the corresponding scene information.

For example: after the data list is obtained, the time information contained in the video file is combined to establish a time data link; or the information contained in the video file is combined to establish a location data link.

S282: Establish a mapping data table according to the data list and the data link.

According to the data list and data link obtained in the above steps, the mapping data table can be obtained after internal processing.

Optionally, obtaining current scene information includes: obtaining current time information.

Based on the current scene information, obtain the target video data type that matches the current scene information from the pre-established mapping data table, including:

Based on the current time information, the target video data category that matches the current time information is obtained from the pre-established mapping data table.

In an application scenario, for example, the current time information obtained is "April 19, 2019". Based on the time information, the target video data type obtained from the preset mapping data table may be the associated time in the video database The scene information is the target video data category of "April 19, 2018-April 23, 2018", and the tags of multiple video files in the target video data category are obtained. Among them, a certain associated scene information is "April 23, 2018". If the tag of the video file on the 22nd of the month is "birthday", etc., you can send a reminder to the user and attach the video file at the same time. If the owner of the birthday is the user himself, it can bring memories to the user; if the birthday is someone else, the user can be reminded that the birthday is coming soon, so as not to miss the birthday of an important person.

In an application scenario, for example, the current time information obtained is "April 19, 2019". Based on the time information, the target video data type obtained from the preset mapping data table may be the associated time in the video database The scene information is the target video data category of "April 19, 2018", and the tags of multiple video files in the target video data category are obtained. Among them, a certain associated scene information is the video file of "April 19, 2018" If the tag is "happy" and other positive words, you can send messages such as "last year today" to the user and attach the video file at the same time, so that the user can recall happy things.

Optionally, acquiring current scene information includes: acquiring current location information.

Based on the current location information, the target video data category that matches the current location information is obtained from the pre-established mapping data table.

In an application scenario, for example, if the current location information is “Beijing”, it can be recognized that the user is in Beijing at this time. Based on the location information, the target video data type obtained from the preset mapping data table may be, video The associated location scene information in the database is the target video data category of "Beijing", and the tags of multiple video files in the target video data category are obtained. Among them, the tag of a certain video file can be "Travel", "Great Wall", etc., then It can send users the precautions for traveling on the Great Wall in Beijing, the suitability of the weather and temperature, etc., and the video file will be attached at the same time. Allow users to recall the people and scenes that have traveled together, and provide users with more meticulous and warm services.

In an application scenario, when a user opens a travel application (for example, Ctrip APP, Fliggy APP, etc.), for example, the current location information is obtained as "Beijing", which can identify that the user is in Beijing at this time, based on the location Information, the target video data category obtained from the preset mapping data table may be the target video data category with the associated location scene information of "tourism" and "Beijing" in the video database, and obtain multiple videos in the target video data category File tags. Among them, some video files can be tagged as "Great Wall", "Forbidden City", etc., and you can send user introductions to attractions other than "Great Wall" and "Forbidden City", allowing users to explore more things they haven't been to Tourist attractions.

Optionally, obtaining current scene information includes: obtaining current environmental parameter information.

Based on the current environmental parameter information, the target video data class that matches the current environmental parameter information is obtained from the pre-established mapping data table.

The current environmental parameter information may be weather, temperature, voice information, and so on.

In an application scenario, for example, the current environmental parameter information is obtained as the user's voice information, and the semantic analysis obtains "I want to sing." Based on the voice information, the target video data type obtained from the preset mapping data table It can be that the target video data category corresponding to the category of "entertainment" in the video database is obtained, and other tags of multiple video files in the target video data category are obtained. Among them, the tag of a certain video file is "singing", etc., you can give The user sends the nearby KTV shop and attaches the video file at the same time.

In an application scenario, for example, if the current environmental parameter information is "weather and snow", the target video data category obtained from the preset mapping data table may be the target video data of the corresponding category "weather" in the video database Category, and obtain other tags of multiple video files in the target video data category. Among them, if the tag of a certain video file is "snow", etc., you can send the user the precautions for a snowy day and attach the video file at the same time.

Optionally, acquiring the current scene information may also include: acquiring the current video file;

Perform framing processing on the current video file to obtain multiple current video frames.

Input each current video frame to the trained deep learning network to output the corresponding label as the current scene information.

Among them, the current video file refers to a video file stored in a local video library at a preset time and/or a video file cached on the network.

In an application scenario, for example, the current video file is obtained, and the current video file is framed to obtain multiple current video frames; each current video frame is input to the trained deep learning network to output the corresponding The tags "snow", "happy" and other corresponding tags are used as the current scene information. Based on the scene information, the target video data category obtained from the preset mapping data table can be the target in the video database with the corresponding category "weather" Video data category, and obtain the other tags of multiple video files in the target video data category. Among them, if the tag of a certain video file is "snow", etc., you can send the user the precautions for a snowy day and attach the video at the same time file.

It is understandable that acquiring current scene information may also include: acquiring at least two of current time information, current location information, current environmental parameter information, and current video file as current scene information.

Based on at least two of the current time information, the current location information, the current environmental parameter information, and the current video file, a target video data class matching the current environmental parameter information is obtained from a pre-established mapping data table.

In an application scenario, when a user opens a travel application (for example, Ctrip APP, Fliggy APP, etc.), for example, if the current location information is "Beijing" and the environmental parameter information is "Weather Snow", it can be identified The user is in Beijing at this time and it is snowing or is likely to snow. Based on the location information, the target video data type obtained from the preset mapping data table can be the associated scene information of "Beijing" and "Tourism" in the video database. Target video data category, and obtain the tags of multiple video files in the target video data category. Among them, the tags of some video files can be "Great Wall", "Forbidden City", etc., then "Great Wall" and "Forbidden City" can be sent to the user The introduction of other tourist attractions suitable for snowy days allows users to explore more tourist attractions that have not been visited and meet the weather conditions.

Optionally, step S220: obtaining multiple video files in the video database may include:

Obtain multiple video files in the local video library of the client and/or multiple video files cached on the network.

Optionally, before obtaining multiple video files in the local video library of the client and/or multiple video files cached on the network, it may also include: obtaining the permission to read the local video library and/or the permission to read online records .

For example, when the user opens an application for the first time, the system may prompt the user whether to choose to open the application to read the local video library and/or read the online records by means of pop-up window or voice. The user can confirm the permission of the application to read the local video library and/or the permission to read online records by tapping the screen, voice control or gesture control, etc., and then obtain the permission and/or reading of the local video library The permission to record online, so that multiple video files in the video database and the scene information of each video file can be obtained, and a mapping table can be established.

Alternatively, the system may enable the permission to read the local video library and/or the permission to read online records by default.

Please refer to FIG. 4, which is a schematic flowchart of a third embodiment of a method for pushing a message based on video data provided by the present application.

The third embodiment of the video data-based message pushing method 100 of this application is based on any of the above-mentioned embodiments of the video data-based message pushing method 100 of this application. Therefore, the same steps in this embodiment and the first embodiment will not be described again. Refer to the description in the above embodiment.

In this embodiment, step S160: performing message push according to the tag of the target video data category includes:

S161: After analyzing the tags of the target video data category, extract keywords.

After analyzing the tags of the target video data category, one or more of all tags with the highest correlation with the current scene information can be extracted as keywords. For example, when the current scene information is time information, the tags related to "birthday" and "anniversary" can be extracted as keywords; when the current scene information is location information, the tags related to "tourism" and "weather" can be extracted as keywords. "And so on are extracted as keywords.

S162: Expand the keyword to obtain the push message and push the message.

In this embodiment, using the extracted keywords, according to the deep learning method, the keywords can be expanded into a language scene, and the scene configuration text can be performed to form a set of personalized push information.

There are many ways to automatically analyze the content to form personalized information. It can be based on the same location, the same day in the past, the same behavior, the same scenes experienced, etc., or it can be combined with multiple scenarios for comprehensive analysis. When the day is happy, or when it is sad. According to the extracted keywords, some auxiliary information can be combined (for example, the corresponding introduction is generated according to the relevant scenes of artificial intelligence machine learning based on the tags, etc.), and the relevant video files in the video database are added to finally generate the push content.

For example, still taking birthdays as an example, in an application scenario, for example, the current time information obtained is "April 19, 2019". Based on the time information, the target video data class obtained from the preset mapping data table can be Yes, the associated scene information in the video database is time information and specifically is the target video data category of "April 19, 2018-April 23, 2018", and tags of multiple video files in the target video data category are obtained. Further, when creating a data list, you can combine manual confirmation methods, for example, push the video frame containing the task to the user, and let the user confirm to set the tags of the main characters, such as "self", "family", "friend", "Birthday" and so on. Therefore, if the tags of the target video category include tags such as "birthday" and "person", the tags of "birthday" and "person" can be extracted as keywords. If the owner of the birthday is identified as the user, it can be The user pushes the corresponding video file and attaches a voice or text message such as "Happy birthday to you, and may you be happy every day" to bring memories and good wishes to the user; if the owner of the birthday is a family member, it can be the user Push the corresponding video file and attach a voice or text message such as "Your family’s birthday is coming soon, don’t forget to send blessings" and other voice or text messages to remind users that the birthday of others is coming, so as not to forget the birthdays of important people.

In an application scenario, for example, the current location information (or the label corresponding to the current video file) is acquired as a landmark ancient building. Based on the location information, the target video data class acquired from the preset mapping data table may be , The associated scene information in the video database is the target video data category with the location information and the categories are "tourism" and "building", and the tags of multiple video files in the target video data category are obtained. Furthermore, by extracting tag content including design style, designer, etc. as keywords, it can be pushed to users of ancient buildings of the same type or the same period in different countries, and at the same time, users can be pushed to the user's explanations and differences of these ancient buildings. You can also push similar works of the same architect, such as Spanish designer Antonio Gaudi. If a user travels to Spain and shoots a video of a building designed by Gaudi, he can push it to the user, other local Gaudi works, and provide instructions. , Can guide users to browse, visit, etc.

Please refer to FIG. 5, which is a schematic flowchart of a fourth embodiment of a method for pushing a message based on video data provided by the present application.

Before pushing the message according to the tag of the target video data category, it includes:

S110: Acquire the current message push strategy of the client.

Wherein, the current message push strategy includes: at least one of a push cycle, a push frequency, a push scenario, and a push tag.

The method of obtaining the current message push strategy of the client may be: the message push strategy selected or edited by the user is used as the message push strategy.

The push cycle is, for example, three days, five days, seven days, or one month; the push frequency is, for example, 10 times a month or 20 times a quarter, etc.; the push scenario is for example only when you leave your place of residence, or at 8:00 a.m. every day -Push at 10:00 to facilitate travel arrangements, etc.; push the label such as "happy" to avoid causing bad memories.

The way to obtain the current message push strategy of the client may also be: use the default message push strategy as the message push strategy.

In the default message push strategy, the push cycle is, for example, every day, the push frequency is, for example, once or twice a day, the push scene is, for example, all scenes, and the push tag is, for example, to exclude "sadness".

Figure 5 shows only one embodiment. In this embodiment, the execution time or order of step S110 is not limited. For example, step S110 may be after S120 and before S140, or step S110 may be after S140 and before S160. As long as the current message push strategy of the client is obtained before the message push is performed.

S150: Determine whether the pushing condition is reached according to the current message pushing strategy.

Determine whether the push conditions are met according to the current message push strategy. For example, if the push cycle is three days, for example, the push scenario is to leave the place of residence for push, and push is carried out from 8:00 to 10:00 in the morning, according to the current location information , After getting the information that the user has left the city where he lives to go to another place, every three days and between 8:00-10:00 in the morning, push a message to the user.

If not, return to continue the step of obtaining the current scene information.

If yes, perform S160: perform a message push step according to the tag of the target video data category.

Please refer to FIG. 6, which is a schematic structural diagram of an embodiment of a terminal device provided by the present application.

In this embodiment, the terminal device 200 includes a processor 210 and a memory 220 electrically connected to the processor 210. The memory 220 is used to store program data, and the processor 210 is used to execute the program data to implement the following methods:

Obtain the current scene information; based on the current scene information, obtain the target video data class matching the current scene information from the pre-established mapping data table; among them, the mapping data table is based on the preset tags in the video database The video files are classified and established by associating scene information; push messages according to the tags of the target video data category.

Optionally, the program data executed by the processor 210 is also used to implement the following methods: obtain multiple video files in the video database; classify the video files in the video database according to preset tags; obtain the scene of each video file Information; According to the classification of multiple video files and the corresponding scene information, a mapping table is established.

Optionally, the processor 210 executing the program data is also used to implement the following method: classifying the video files in the video database according to preset tags, including: framing the video files in the video database to obtain multiple Video frames; each video frame is input to the trained deep learning network to output the corresponding label; among them, the deep learning network is obtained based on the supervised learning training of the video frame with the pre-established correspondence relationship and the preset label; According to the output corresponding tags, the video files in the video database are analyzed, and the data list is generated by classification.

Optionally, the program data executed by the processor 210 is also used to implement the following method: input each video frame to a trained deep learning network to output a corresponding label; according to the classification of multiple video files and corresponding scene information, Establish a mapping table: based on the data list, combined with the corresponding scene information, perform data link; according to the data list and data link, establish a mapping data table.

Optionally, the processor 210 executing the program data is also used to implement the following method: acquiring current scene information, including: acquiring current time information; based on the current scene information, from a pre-established mapping data table, acquiring the current The target video data type matching the scene information includes: obtaining the target video data type matching the current time information from a pre-established mapping data table based on the current time information.

Optionally, the processor 210 executing the program data is also used to implement the following method: acquiring current scene information, including: acquiring current location information; based on the current scene information, from a pre-established mapping data table, acquiring the current The target video data type matching the scene information includes: obtaining the target video data type matching the current position information from a pre-established mapping data table based on the current position information.

Optionally, the processor 210 executing the program data is also used to implement the following method: acquiring current scene information, including: acquiring current environment parameter information; based on the current scene information, from a pre-established mapping data table, acquiring the current The target video data type matched by the scene information includes: obtaining the target video data type matched by the current environmental parameter information from a pre-established mapping data table based on the current environmental parameter information.

Optionally, the program data executed by the processor 210 is also used to implement the following method: push message according to the tags of the target video data category, including: extracting keywords after analyzing the tags of the target video data category; expanding keywords Get the push message and push the message.

Optionally, the program data executed by the processor 210 is also used to implement the following method: obtaining multiple video files in a video database, including: obtaining multiple video files in the local video library of the client and/or multiple network caches Video files.

Optionally, the processor 210 executing program data is also used to implement the following method: before acquiring multiple video files in the client's local video library and/or multiple video files cached on the network, the method further includes: acquiring and reading local The permission of the video library and/or the permission to read online records.

Optionally, the execution of the program data by the processor 210 is also used to implement the following method: before acquiring the current scene information, the method further includes: acquiring the permission to push messages.

Optionally, the program data executed by the processor 210 is also used to implement the following method: acquiring the authority to perform message push includes: acquiring a notification that the user enables the message push function, or acquiring a notification that the message push function is enabled by default.

Optionally, the processor 210 executing the program data is also used to implement the following method: before performing message push according to the tag of the target video data category, the method includes: obtaining the current message push strategy of the client; wherein, the current message push strategy includes: At least one of push cycle, push frequency, push scenario, and push tag.

Optionally, the program data executed by the processor 210 is also used to implement the following method: obtaining the current message push strategy of the client, including: using the message pushing strategy selected or edited by the user as the message pushing strategy, or using the default message pushing strategy as the message pushing strategy. Message push strategy.

Optionally, the processor 210 executing the program data is also used to implement the following method: before pushing the message according to the tag of the target video data category, the method includes: judging whether the pushing condition is reached according to the current message pushing strategy; if so, executing according to The tag of the target video data type, the step of pushing the message.

Optionally, the execution of the program data by the processor 210 is also used to implement the following method: if not, then return to continue the step of obtaining current scene information.

Optionally, the program data executed by the processor 210 is also used to implement the following method: obtaining current scene information, including: obtaining at least two of the current time information, the current location information, the current environmental parameters, and the current video file. As the current scene information.

Optionally, the program data executed by the processor 210 is also used to implement the following method: acquiring current scene information includes: acquiring a current video file; performing frame division processing on the current video file to obtain multiple current video frames; Input each current video frame to the trained deep learning network to output the corresponding label as the current scene information; among them, the current video file refers to the video file and/or network stored in the local video library at the preset time Cached video files.

In this embodiment, the terminal device 200 may specifically be a mobile phone, a computer, a server, etc., or may be a wearable device. The wearable device 100 may specifically be a smart watch, smart glasses, smart bracelet, clothing, etc.

Please refer to FIG. 7, which is a schematic diagram of an embodiment of a computer storage medium provided by the present application.

In this embodiment, the computer storage medium 300 is used to store program data 310. When the program data 310 is executed by the processor, it is used to implement the following method: obtain current scene information; based on the current scene information, from a pre-established mapping In the data table, obtain the target video data category that matches the current scene information; among them, the mapping data table is established by classifying the video files in the video database according to preset tags and associating the scene information; according to the target video data The label of the class, for message push.

It can be understood that the computing storage medium 300 in this embodiment can be applied to the above-mentioned terminal device 200, and the specific implementation steps can be referred to the above-mentioned embodiment, which is not repeated here.

In the several implementation manners provided in this application, it should be understood that the disclosed method, device, and system may be implemented in other ways. For example, the methods, devices, and system implementations described above are only illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other divisions, such as multiple units or Components can be combined or integrated into another system, or some features can be omitted or not implemented.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of this embodiment.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit in the other embodiments described above is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes. .

This application obtains the current scene information, and based on the current scene information, obtains the target video data type matching the current scene information from the pre-established mapping data table, so as to push the message according to the tag of the target video data type , Since the mapping data table is established by classifying the video files in the video database according to preset tags and associating scene information, the pushed messages are not only associated with the current scene information, but also based on historical video files and their scenes. Information, so that the pushed messages are based on the user’s past behaviors and meet the needs of the current scene, that is, the pushed messages are personalized and practical, so it can provide users with personalized message pushes and improve the message push accuracy.

The above are only implementations of this application, and do not limit the scope of this application. Any equivalent structure or equivalent process transformation made using the content of the description and drawings of this application, or directly or indirectly applied to other related technical fields, The same reasoning is included in the scope of patent protection of this application.

Claims

A method for pushing messages based on video data, characterized in that the method includes:

Get current scene information;

Based on the current scene information, obtain the target video data class matching the current scene information from a pre-established mapping data table; wherein, the mapping data table is based on a preset label to the video database Categorized the video files and establish the associated scene information;

Push messages according to the tags of the target video data category.
The method according to claim 1, wherein the method further comprises:

Acquiring multiple video files in the video database;

Classify the video files in the video database according to the preset tags;

Acquiring scene information of each of the video files;

The mapping table is established according to the classification of the multiple video files and the corresponding scene information.
The method of claim 2, wherein:

The classifying the video files in the video database according to the preset tags includes:

Performing framing processing on the video file in the video database to obtain multiple video frames;

Input each of the video frames to a trained deep learning network to output a corresponding label; wherein, the deep learning network is obtained based on supervised learning training on the video frame with a pre-established correspondence relationship and the preset label of;

Analyze the video files in the video database according to the output corresponding tags, and classify and generate a data list.
The method of claim 3, wherein:

Establishing the mapping table according to the classifications of the multiple video files and corresponding scene information:

Based on the data list, in combination with the corresponding scene information, data link is performed;

According to the data list and the data link, the mapping data table is established.
The method of claim 1, wherein:

The acquiring current scene information includes:

Get current time information;

The acquiring, based on the current scene information, from a pre-established mapping data table, the target video data category that matches the current scene information includes:

Based on the current time information, a target video data category that matches the current time information is obtained from a pre-established mapping data table.
The method of claim 1, wherein:

The acquiring current scene information includes:

Get current location information;

The acquiring, based on the current scene information, from a pre-established mapping data table, the target video data category that matches the current scene information includes:

Based on the current location information, obtain the target video data category that matches the current location information from a pre-established mapping data table.
The method of claim 1, wherein:

The acquiring current scene information includes:

Obtain current environmental parameter information;

The acquiring, based on the current scene information, from a pre-established mapping data table, the target video data category that matches the current scene information includes:

Based on the current environmental parameter information, obtain the target video data class that matches the current environmental parameter information from a pre-established mapping data table.
The method of claim 1, wherein:

The performing message push according to the tag of the target video data category includes:

After analyzing the tags of the target video data category, keywords are extracted;

Expand the keyword to obtain a push message and push the message.
The method of claim 2, wherein:

The obtaining multiple video files in the video database includes:

Obtain multiple video files in the local video library of the client and/or multiple video files cached on the network.
The method of claim 2, wherein:

Before the acquiring multiple video files in the local video library of the client and/or multiple video files cached on the network, the method further includes:

Obtain the permission to read the local video library and/or the permission to read online records.
The method of claim 1, wherein:

Before acquiring the current scene information, the method further includes:

Obtain the permission to push messages.
The method of claim 11, wherein:

The obtaining permission to push messages includes:

Obtain the notification that the user has enabled the message push function, or

Get the notification that the message push function is enabled by default.
The method of claim 1, wherein:

Before the message push is performed according to the tag of the target video data category, the method includes:

Get the current message push strategy of the client;

Wherein, the current message push strategy includes: at least one of a push cycle, a push frequency, a push scenario, and a push tag.
The method of claim 13, wherein:

The obtaining the current message push strategy of the client includes:

Use the message push strategy selected or edited by the user as the message push strategy, or

Use the default message push strategy as the message push strategy.
The method of claim 14, wherein:

Before performing message push according to the tag of the target video data category, the method includes:

Judging whether the pushing condition is reached according to the current message pushing strategy;

If yes, execute the step of pushing the message according to the tag of the target video data category.
The method according to claim 8, wherein the method further comprises:

If not, return to continue the step of obtaining the current scene information.
The method of claim 1, wherein:

The acquiring current scene information includes:

Get the current video file;

Perform framing processing on the current video file to obtain multiple current video frames;

Input each of the current video frames to the trained deep learning network to output corresponding labels as current scene information;

Among them, the current video file refers to a video file stored in a local video library at a preset time and/or a video file cached on the network.
The method of claim 1, wherein:

The acquiring current scene information includes:

At least two of the current time information, the current location information, the current environment parameter, and the current video file are acquired as the current scene information.
A terminal device, characterized in that the terminal device includes a processor and a memory electrically connected to the processor, the memory is used to store program data, and the processor is used to execute the program data to implement The method of any one of claims 1-18.
A computer storage medium, wherein the computer storage medium is used to store program data, and the program data is used to implement the method according to any one of claims 1-18 when the program data is executed by a processor.