CN117290584A

CN117290584A - Video recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN117290584A
Application number: CN202210690727.1A
Authority: CN
Inventors: 吴佳宇
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2022-06-17
Filing date: 2022-06-17
Publication date: 2023-12-26

Abstract

The application relates to the technical field of computers, in particular to the field of maps, and provides a video recommendation method, a video recommendation device, electronic equipment and a storage medium for accurately recommending videos. The method comprises the following steps: presenting a navigation interface, and in response to a destination input operation for the navigation interface, presenting a destination-related target navigation route in the navigation interface, and displaying a recommended video for the target navigation route, the recommended video being a video resource related to a location point in the target navigation route; responding to the selected operation for the target video in the recommended video, and presenting a corresponding video playing interface; in the video playing interface, the target video is played from the associated time point of the target video, wherein the associated time point is the playing position of the video frame in the target video, which is related to the position point corresponding to the target video. The method and the device can be combined with object map navigation to accurately recommend video resources related to the target navigation route.

Description

Video recommendation method and device, electronic equipment and storage medium

Technical Field

The application relates to the technical field of computers, in particular to the field of maps, and provides a video recommendation method, a video recommendation device, electronic equipment and a storage medium.

Background

With the rapid development of internet technology, more and more Applications (APP) have been developed, such as chat APP, shopping APP, game APP, map APP, video APP, and short video APP. The object can watch various video resources such as film and television works at any time and any place through an internet channel, and of course, some actual viewing places such as a scenic spot, a school, a logo building and the like are also involved in the video resources.

However, since video resources are very abundant, not all video resources are watched by the subject, and in real life, the connection between these video resources and the relevant actual viewing places is not well known, so that after the subject finishes a certain place, it is often caused to find that a certain movie works are viewed at the place, but the subject does not pay attention at that time, and thus the situation that a scene related to the place cannot be combined and the like occurs.

Aiming at the problems, the object can search through a webpage to check the view finding place of some famous movies, in the mode, the object is required to input search keywords in a search box by itself, and the search results obtained through keyword matching are not accurate enough; the object can also search related videos through shooting countries to which the film and television works belong, in this way, the country is taken as the searching granularity, the searching range is wider, the searched video resources refer to the film and television works shot by the country selected by the object, for example, the country selected by the object is the country A, the searching result is the video resources shot by the country A, for example, films and television dramas shot by the country A, however, the film and television works are shot by the country A, the actual view finding area in shooting is not necessarily the country A, and the searching result is not accurate enough.

Disclosure of Invention

The embodiment of the application provides a video recommendation method, a video recommendation device, electronic equipment and a storage medium, which are used for accurately recommending videos.

The video recommendation method provided by the embodiment of the application comprises the following steps:

presenting a navigation interface, and in response to a destination input operation for the navigation interface, presenting a destination-related target navigation route in the navigation interface, and presenting at least one recommended video for the target navigation route, each recommended video being a video resource related to a location point in the target navigation route;

responding to the selected operation for the target video in the at least one recommended video, and presenting a corresponding video playing interface;

in the video playing interface, starting from the associated time point of the target video, playing the target video, wherein the associated time point is as follows: and video frames related to the position points corresponding to the target video are played at the playing positions in the target video.

receiving a navigation request aiming at a destination, and generating a destination-related target navigation route;

In a preset video resource set, determining video resources related to position points in the target navigation route as recommended videos, and returning the target navigation route and at least one recommended video to terminal equipment so that the terminal equipment presents the target navigation route in a navigation interface and displays the at least one recommended video;

receiving a playing request aiming at a target video in at least one recommended video, returning an associated time point of the target video to the terminal equipment so as to enable the terminal equipment to present a corresponding video playing interface, and playing the target video in the video playing interface from the associated time point, wherein the associated time point is as follows: and video frames related to the position points corresponding to the target video are played at the playing positions in the target video.

The video recommendation device provided in the embodiment of the application includes:

a first response unit, configured to present a navigation interface, and in response to a destination input operation for the navigation interface, present a destination-related target navigation route in the navigation interface, and present at least one recommended video for the target navigation route, each recommended video being a video resource related to a location point in the target navigation route;

The second response unit is used for responding to the selected operation of the target video in the at least one recommended video and presenting a corresponding video playing interface;

the second response unit is further configured to play, in the video playing interface, the target video from an associated time point of the target video, where the associated time point is: and video frames related to the position points corresponding to the target video are played at the playing positions in the target video.

Optionally, the location point corresponding to each recommended video includes: at least one of the destination and an intermediate location;

wherein, the intermediate place is: other waypoints in the target navigation route than the destination.

Optionally, the second response unit is specifically configured to:

presenting a destination-related target navigation route in a map area of the navigation interface, and displaying at least one recommended video for the target navigation route in a video recommendation area of the navigation interface; or alternatively

And presenting a destination-related target navigation route in the navigation interface, and displaying a recommended video corresponding to a relevant position point in the target navigation route.

Optionally, the video recommendation area includes a plurality of recommended videos; the second response unit is specifically configured to:

and displaying the corresponding recommended video according to the priority of the position point corresponding to each recommended video.

wherein the destination has a higher priority than the intermediate location; the intermediate location is: other waypoints in the target navigation route than the destination.

Optionally, the second response unit is specifically configured to:

presenting the video playing interface in a partial area in the navigation interface; or alternatively

And displaying the navigation interface and the video playing interface in a split screen mode.

Optionally, the navigation interface further comprises at least one candidate navigation route related to the destination; the apparatus further comprises:

and the third response unit is used for responding to the selection operation of the target object on the at least one candidate navigation route, switching the navigation route aiming at the target object from the target navigation route to the selected candidate navigation route, and updating the at least one recommended video displayed in the navigation interface according to the position point in the selected candidate navigation route.

Optionally, the second response unit is specifically configured to:

and respectively displaying the video covers of the recommended videos and the corresponding video detail information on the navigation interface.

Optionally, the second response unit is further configured to:

for one recommended video, if the recommended video comprises a plurality of sub-videos, displaying the identification of the corresponding target sub-video at the associated position of the one recommended video in the navigation interface;

the target sub-video is a sub-video related to a position point in the target navigation route in the plurality of sub-videos.

Optionally, the apparatus further includes:

and the information prompt unit is used for presenting related video prompt information in the navigation interface according to the current position of the target object in the running process of the target object so as to instruct the target object to view the recommended video related to the current position.

Another video recommendation device provided in an embodiment of the present application includes:

a first receiving unit, configured to receive a navigation request for a destination, and generate a destination-related target navigation route;

the screening unit is used for determining video resources related to position points in the target navigation route as recommended videos in a preset video resource set, and returning the target navigation route and at least one recommended video to the terminal equipment so that the terminal equipment presents the target navigation route in a navigation interface and displays the at least one recommended video;

The second receiving unit is configured to receive a play request for a target video in the at least one recommended video, return an associated time point of the target video to the terminal device, so that the terminal device presents a corresponding video play interface, and play the target video in the video play interface from the associated time point, where the associated time point is: and video frames related to the position points corresponding to the target video are played at the playing positions in the target video.

Optionally, the screening unit is specifically configured to:

acquiring each position point related to the target navigation route, and for each position point, respectively executing the following operations:

for a location point, respectively acquiring distances between the location point and street view points respectively associated with each video resource in the video resource set; the street scenery points respectively associated with each video resource are as follows: determining a place corresponding to a street view image corresponding to a scene image in a video resource based on an association relation between pre-constructed map street view information and video scene information;

And selecting video resources with the corresponding distance within a preset distance range as recommended videos corresponding to the position points.

Optionally, the filtering unit is further configured to construct an association relationship between each map street view information and the video scene information by:

aiming at a street view image of a street view point and a scene image in a video resource, acquiring the association degree of the street view image and the scene image;

if the association degree is higher than a preset threshold value, establishing association between map street view information formed by the street view image and the street view point and video scene information formed by the scene image and the video resource.

Optionally, the screening unit is specifically configured to:

respectively inputting the street view image and the scene image into a trained target association model;

based on the target association model, semantic analysis is carried out on the street view image and the scene image respectively, and street view semantic value information and street view semantic key information corresponding to the street view image and scene semantic query information corresponding to the scene image are obtained;

and after the street view semantic value information, the street view semantic key information and the scene semantic query information are decoded, mapping to obtain the association degree of the street view image and the scene image.

Optionally, the apparatus further includes:

the model training unit is used for training to obtain the target association model by the following modes:

acquiring a training sample set, wherein each training sample in the training sample set comprises a sample street view image corresponding to a sample street view point, and a positive sample scene image and a negative sample scene image corresponding to the sample street view image;

performing cyclic iterative training on the association model to be trained according to the training sample set, and outputting the target association model; wherein, in a loop iteration process, the following operations are performed:

inputting the selected training samples into the correlation model to be trained, and respectively obtaining a first prediction correlation degree between the sample street view image and the positive sample scene image and a second prediction correlation degree between the sample street view image and the negative sample scene image;

and carrying out parameter adjustment on the association model to be trained by adopting a loss function constructed based on the first prediction association degree and the second prediction association degree.

The electronic device provided by the embodiment of the application comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to execute the steps of any video recommendation method.

Embodiments of the present application provide a computer readable storage medium comprising a computer program for causing an electronic device to perform the steps of any one of the video recommendation methods described above when the computer program is run on the electronic device.

Embodiments of the present application provide a computer program product comprising a computer program stored in a computer readable storage medium; when the processor of the electronic device reads the computer program from the computer readable storage medium, the processor executes the computer program, so that the electronic device performs the steps of any one of the video recommendation methods described above.

The beneficial effects of the application are as follows:

the embodiment of the application provides a video recommendation method, a video recommendation device, electronic equipment and a storage medium. According to the method, a target navigation route can be generated by combining a destination input by an object in a navigation interface, and more accurate video recommendation is performed on the object by combining video resources related to position points in the target navigation route. In addition, in the method, the recommendation of the related video resources can be triggered only by inputting the destination, and the automatic playing of the position point related video clips can be directly realized when a certain target video is selected.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:

fig. 1 is an alternative schematic diagram of an application scenario in an embodiment of the present application;

FIG. 2 is a flowchart illustrating an implementation of a video recommendation method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a navigation interface in an embodiment of the present application;

FIG. 4 is a schematic diagram of another navigation interface in an embodiment of the present application;

FIG. 5 is a diagram illustrating a navigation and video recommendation interface according to an embodiment of the present application

FIG. 6 is a schematic diagram of another navigation and video recommendation interface in an embodiment of the present application;

fig. 7 is a schematic diagram of a video playing interface according to an embodiment of the present application;

FIG. 8A is a schematic diagram of a navigation and video playback interface according to an embodiment of the present application;

FIG. 8B is a schematic diagram of another navigation and video playback interface according to an embodiment of the present application;

FIG. 9 is a schematic diagram of a target sub-video identifier in an embodiment of the present application;

FIG. 10 is a schematic diagram of details of a corresponding location point of a recommended video according to an embodiment of the present application;

FIG. 11 is a schematic diagram of a navigation and video recommendation interface after route switching in an embodiment of the present application;

fig. 12 is a schematic diagram of a video prompt message in an embodiment of the present application;

FIG. 13 is a flowchart illustrating another implementation of a video recommendation method according to an embodiment of the present application;

FIG. 14 is a schematic structural diagram of a target association model according to an embodiment of the present application;

FIG. 15 is a flowchart of a training method of a target association model according to an embodiment of the present application;

fig. 16 is a flowchart of interaction between a terminal device and a server in an embodiment of the present application;

fig. 17 is a schematic diagram of a composition structure of a video recommendation device in an embodiment of the present application;

fig. 18 is a schematic diagram of a composition structure of another video recommendation device according to an embodiment of the present application;

fig. 19 is a schematic diagram of a hardware composition structure of an electronic device to which the embodiments of the present application are applied;

Fig. 20 is a schematic diagram of a hardware composition structure of another electronic device to which the embodiments of the present application are applied.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the technical solutions of the present application, but not all embodiments. All other embodiments, which can be made by a person of ordinary skill in the art without any inventive effort, based on the embodiments described in the present application are intended to be within the scope of the technical solutions of the present application.

Some of the concepts involved in the embodiments of the present application are described below.

Navigation route: is software, equipment, etc. that can provide navigation functions, such as navigation software, etc., that plans a generated travel route based on the current location (or input departure point) and destination of an object (e.g., a user). In general, one or more routes (such as the route with the shortest distance, the least time consumption, and the less traffic light) may be planned and generated, for example, for the same trip, the target navigation route in the embodiment of the present application may be a navigation route that is recommended by default for the trip or a navigation route that is selected by the subject by himself, and the candidate navigation route refers to other routes for the trip in addition to the target navigation route.

Navigation interface: an object-oriented interface with electronic map navigation and video recommendation functions. The navigation interface in the embodiment of the application not only displays the related navigation route when the object inputs the destination, but also further displays the recommended video (such as film and television works) related to the position point in the navigation route.

Recommending video: in the present application, the related video resources acquired by the object according to the position points in the route planned by the destination input by the object in the map navigation scene are included in the video frames related to the corresponding position points or the video frames related to the vicinity of the corresponding position points.

Location points and street view points: the location point is related to the navigation route, and may be a destination, or may be other along-way points (may be simply referred to as intermediate points) in the navigation route other than the destination. In the embodiment of the application, the destination related video can be independently recommended to the object, the middle place related video can be independently recommended to the object, and the destination and the middle place related video can be simultaneously recommended to the object. The street scenery spot refers to an actual street scenery address (irrelevant to navigation) in the electronic map, and a plurality of real scenery images, which can be called street scenery images, can be acquired at a specific street scenery address.

Street view image and scene image: is an image of two different types (different sides) in the embodiments of the present application. The street view image refers to an image on the map side, specifically, one street view image may be an actual real view image collected at a certain address in the electronic map, specifically, a plurality of street view images with different time and angles may be collected at one address; scene images are video frame images in a video asset and may also be referred to as video scene images or film and television scene images.

Video detail information: refers to some specific information about a video asset including, but not limited to, video title, duration, genre, language, origin, director, introduction, score, etc.

Video prompt information: the method refers to information for prompting the object according to the real-time position of the object in the running process of the object, and the information is used for prompting that the object passes through certain places, and can browse related film and television works, punch cards, take photos and the like.

The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification, it being understood that the preferred embodiments described herein are for illustration and explanation only, and are not intended to limit the present application, and embodiments and features of embodiments of the present application may be combined with each other without conflict.

Fig. 1 is a schematic view of an application scenario in an embodiment of the present application. The application scenario diagram includes two terminal devices 110 and a server 120.

In the embodiment of the present application, the terminal device 110 includes, but is not limited to, a mobile phone, a tablet computer, a notebook computer, a desktop computer, an electronic book reader, an intelligent voice interaction device, an intelligent home appliance, a vehicle-mounted terminal, an aircraft, and the like; the terminal device may be provided with a client having various functions, such as a client having map navigation and video correlation, where the client may be software (e.g. browser, map APP, video APP, short video APP, etc.), web page, applet, etc., and the server 120 may be a server corresponding to the software or web page, applet, etc., or a server dedicated to map navigation and video recommendation, which is not particularly limited in this application. The server 120 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, a content delivery network (Content Delivery Network, CDN), basic cloud computing services such as big data and an artificial intelligence platform.

It should be noted that, the video recommendation method in the embodiments of the present application may be performed by an electronic device, which may be the terminal device 110 or the server 120, that is, the method may be performed by the terminal device 110 or the server 120 alone, or may be performed by both the terminal device 110 and the server 120 together. For example, when the terminal device 110 and the server 120 jointly execute, the object may open a map application, trigger a navigation function, the terminal device 110 may present a navigation interface to the object, further, the object may input a destination at the navigation interface, the terminal device may send a navigation request for the destination to the server 120 in response to a destination input operation for the navigation interface, the server 120 generates a destination-related target navigation route, determines a video resource related to a location point in the target navigation route as a recommended video, returns the target navigation route and the recommended video to the terminal device 110, and further, the terminal device 110 presents the destination-related target navigation route in the navigation interface and displays the recommended video for the target navigation route.

When the object wants to browse the interesting videos, the target videos can be selected from the recommended videos, the terminal equipment 110 responds to the selection operation of the target videos in at least one recommended video, the server 120 is found to play requests of the target videos, the server returns the associated time points of the target videos to the terminal equipment, the map application of the terminal equipment 110 presents corresponding video playing interfaces by calling the video application, and in the video playing interfaces, the target videos are automatically played from the associated time points of the target videos.

In addition, the embodiment of the application can be applied to various scenes, including not only the map navigation scenes listed above, but also scenes such as cloud technology, artificial intelligence, intelligent traffic, driving assistance and the like. For example, the object can be used in vehicle-mounted video software, a vehicle-mounted navigation system is utilized for navigation, and the video works related to the destination are automatically recommended for the object to select and watch, so that the travel interestingness and the operation convenience are improved, the object obtains good navigation and video viewing object experience in the travel, and finally the satisfaction degree of vehicle-mounted application is improved.

In an alternative embodiment, the terminal device 110 and the server 120 may communicate via a communication network.

In an alternative embodiment, the communication network is a wired network or a wireless network.

It should be noted that, the embodiment shown in fig. 1 is merely an example, and the number of terminal devices and servers is not limited in practice, and is not specifically limited in the embodiment of the present application.

In the embodiment of the present application, when the number of servers is plural, plural servers may be configured as a blockchain, and the servers are nodes on the blockchain; the video recommendation method disclosed in the embodiments of the present application, wherein various related data related to video recommendation may be stored on a blockchain, for example, an identifier of each video resource, video detail information, an association relationship between map street view information and video scene information, and so on.

The video recommendation method provided in the exemplary embodiments of the present application will be described below with reference to the accompanying drawings in conjunction with the application scenario described above, and it should be noted that the application scenario described above is only shown for the convenience of understanding the spirit and principles of the present application, and embodiments of the present application are not limited in any way in this respect.

Referring to fig. 2, a flowchart of an implementation of a video recommendation method provided in an embodiment of the present application is shown, taking an implementation subject as a terminal device (e.g. a vehicle-mounted terminal) as an example, and the specific implementation process of the method is as follows S21-S23:

s21: the terminal device presents a navigation interface, responds to a destination input operation for the navigation interface, presents a destination-related target navigation route in the navigation interface, and displays at least one recommended video for the target navigation route.

Wherein each recommended video is a video asset associated with a location point in the target navigation route.

Optionally, the location point corresponding to each recommended video includes: at least one of a destination and an intermediate location; wherein the intermediate location is other along locations in the target navigation route than the destination.

For example, the starting point in the target navigation route is the A site, the ending point is the B site, and the route is a plurality of intermediate sites, including: c-site, D-site, E-site, etc.

The recommended video may be a video asset associated with any one or more of location B, location C, location D, location E, etc. Wherein, related refers to that the street view of the location point is related to a scene in the video resource, e.g. the video resource is framed at or near the location point, or the scenery in the video resource has a reference, imitates the street view of the location point or near the location point, etc.

In general, the intermediate location may be selected randomly, or may be a preferential selectable marker building, a scenic spot, a video shooting base, etc., which is not particularly limited herein.

The video resource in the embodiment of the application may be movie works such as movies, television shows, and may also be short videos. The following is mainly exemplified as a movie work.

Taking a terminal device as an in-vehicle terminal as an example, the client installed on the in-vehicle terminal may include, but is not limited to: chat APP, shopping APP, game APP, map APP, video APP, short video APP, which may be collectively referred to as a car set application.

In the embodiment of the application, the navigation interface can be presented by or call software with navigation function, such as map APP. For example, the object opens a vehicle application (such as a map APP) installed on the vehicle-mounted terminal, and after entering the navigation module, presents a navigation interface as shown in fig. 3, in which the object can navigate by inputting a destination at a dashed box S30. The starting point defaults to the current position of the object, and can be edited by the object and input again.

Specifically, when the object opens the application of the vehicle, the object enters the navigation module and then enters the destination for navigation, and the navigation interface can be updated, and two situations exist:

in case one, the destination or other navigation along-way places are not recorded near the relevant video resources (film works) which can be searched, and the navigation mode is directly entered.

In this manner, the terminal device responds to the destination input operation for the navigation interface, sends a navigation request to the server, generates a relevant navigation route by the server and returns the navigation route to the terminal device for presentation, as shown in fig. 4.

The current position of the object is the site A (X city X1 building), and the destination of the input of the object is the site B (X city X2 wetland park).

In the second case, if a record is near the destination or other navigation along-way places, the relevant video resources can be searched, and a navigation scheme and a video recommendation scheme based on the position information are generated for the object.

Specifically, as described in step S21, the navigation interface is updated based on the destination input by the object, and the target navigation route and the related recommended video are presented in the navigation interface.

In view of the fact that the updated navigation interface has two functions of navigation and video recommendation in the present application, the interface may also be referred to as a navigation and video recommendation interface, and in particular, the interface has many presentation forms:

An alternative display mode is: and presenting the destination-related target navigation route in a map area of the navigation interface, and presenting at least one recommended video for the target navigation route in a video recommendation area of the navigation interface.

That is, the display of the target navigation route and the recommended video is regional (also can be understood as split screen), for example, after the object inputs the destination, the interface shown in fig. 5 may be presented, which is a schematic diagram of a navigation and video recommendation interface in the embodiment of the present application, where the current position of the object is a location a (X city X1 building), the destination of the object inputs is a location B (X city X2 wetland park), and the target navigation route is marked with "start" and "end", that is, a start point and an end point, as shown in the map area in fig. 5. In the map area, navigation of the target navigation route can be performed.

In addition, after 4 recommended videos are displayed in the video recommendation area as shown in fig. 5, for example, the object searches for the destination x2 wetland park, the server will preferably match the viewfinder to include the x2 wetland park and the video works along the way: dishonest xx, xx brother of the 2 nd season, diet xx9999, tianx Fuchuxx and the like, and makes recommended display on a page for the selection of a subject.

Alternatively, in the case where the video recommendation area contains a plurality of recommended videos, the presentation order between the recommended videos may be determined according to the priority:

specifically, according to the priority of the position point corresponding to each recommended video, displaying the corresponding recommended video.

In general, each recommended video corresponds to one location point or a plurality of location points, and if one recommended video includes a plurality of location points, the priority of the location point corresponding to the recommended video defaults to the highest priority corresponding to the location point corresponding to the recommended video.

For example, a recommended video corresponds to a location point B and a location point C, where the priority corresponding to the location point B is 1, the priority corresponding to the location point C is 2, and the highest priority is 1.

Optionally, the priority of the destination is higher than the priority of the intermediate place, that is, the display order of the recommended video corresponding to the destination is earlier than the display order of the recommended video corresponding to the intermediate place.

As shown in fig. 5, the location point corresponding to the "dishonest xx" is the destination: site B, corresponding location points of "xx brother No. 2 season", diet xx9999 ", and" Tianx. Fuchuxx "are intermediate sites respectively: site C, site D, site E. Thus, the display order of the dishonest xx is the forefront, and for the middle places of the same level (referring to the same priority), the display orders of the corresponding film and television works of xx brother 2 nd season, diet xx9999, and Tianx-Fuchun xx can be further ordered according to the play amount, the score, the heat, the preference of the object (such as the object prefers to smile, entertainment video, or the object prefers to act and suspense video), etc., which are not particularly limited herein.

In the embodiment, the target navigation route and the recommended videos are displayed in the partitioned mode, object partition viewing is facilitated, the navigation function and the video recommending function are not affected, in addition, the recommended videos are ordered by combining priority, play quantity, scoring, heat and object preference, and object selection is facilitated.

Another alternative display mode is: and presenting a destination-related target navigation route in the navigation interface, and displaying a recommended video corresponding to the position point at the position point related to the target navigation route.

In this way, the display of the target navigation route and the recommended video are fused together, for example, after the object inputs the destination, the interface shown in fig. 6 may be presented, which is a schematic diagram of another navigation and video recommendation interface in the embodiment of the present application, where the target navigation route is the same as fig. 5, and the display position of the recommended video is related to the target navigation route, and the recommended video is "dishonest xx", xx brother 2 nd season "and" diet xx9999 ", where the location points corresponding to the three recommended videos are respectively: and (3) respectively clicking out the point B (destination), the point C and the point D at the corresponding positions on the target navigation route, and displaying the corresponding recommended video.

In the above embodiment, the target navigation route and the recommended videos are displayed in a fusion manner, so that the object can clearly understand the relationship between the videos and the location points, and can intuitively understand which videos are related to the destination and which videos are related to the intermediate places, the specific positions of the intermediate places in the route, and the like, and the object selection is facilitated.

Optionally, in order to facilitate the object to quickly understand these recommended videos, when displaying the recommended videos in the navigation and video recommendation interface, an optional display manner is: the video covers of the recommended videos and the corresponding video detail information are respectively displayed, so that the object can browse and click the interested videos for watching according to the covers of the recommended videos, the video detail information and the like.

Wherein the cover may be a poster or the like, the video details include, but are not limited to, video title, duration, genre, language, place of origin, director, introduction, score, etc.

As shown in fig. 5 and 6, taking the example of "dishonest xx", the video belongs to the film type, the language is mandarin, and the director is: von xx, the principal manifestations are pueraria x, sulx.

In this embodiment of the present application, after recommending a recommended video related to a location point on a target navigation route to an object, a video clip related to the location point may also be automatically played according to the selection of the object, where the specific process is as follows:

S22: and the terminal equipment responds to the selected operation aiming at the target video in at least one recommended video, and presents a corresponding video playing interface.

S23: and the terminal equipment starts to play the target video from the associated time point of the target video in the video playing interface.

Wherein, the associated time point is: video frames associated with the location point corresponding to the target video, play locations in the target video.

Based on the embodiment, the object can trigger the recommendation of the related video resources only by inputting the destination, and the automatic playing of the position point related video clips can be directly realized when a certain target video is selected. In addition, by combining the video resources related to the position points in the target navigation route, more accurate video recommendation is performed on the object, so that when the object is going to a certain place for visit, the object can know more information of the related position points on the target navigation route in advance, and the connection between the video resources and the corresponding actual view finding place is enhanced.

Specifically, in the embodiment of the present application, the object may select a recommended video of interest (i.e., a target video) from one or more recommended videos displayed in the navigation interface, and after the object selects the target video, the video playing interface may be presented, and play may be started directly from a portion where a location point (destination or middle location) corresponding to the target video appears in the video.

As shown in fig. 7, when the object selects "dishonest xx" for viewing, the video playing interface shown in fig. 7 may be presented, and playing starts from the position point (B location) corresponding to "dishonest xx". As can be seen from fig. 7, the relevant time points of the "dishonest xx" are 45:52, and the overall length of the video is 2:05:15.

Optionally, in step S22, various manners of presenting the corresponding video playing interface may be adopted, for example, when the object selects the target video, the navigation interface in step S21 is directly switched to the video playing interface, and the relevant clip is automatically played on the video playing interface.

Or, a video playing interface is presented in a partial area of the navigation interface, as shown in fig. 8A, which is a schematic diagram of a navigation and video playing interface in the embodiment of the present application, the video playing interface is presented in a form of a floating layer (or popup window, etc.) in a lower right corner of the navigation interface, relevant segments are automatically played in the video playing interface, and the object can drag the floating layer to move the position of the video playing interface so as to avoid shielding the display of effective information, etc., in addition, the object can click to trigger the interface to jump, separately present the video playing interface, and switch from the small window display to the large window display, etc.

Or, the navigation interface and the video playing interface may be displayed in a split screen manner, as shown in fig. 8B, which is a schematic diagram of another navigation and video playing interface in the embodiment of the present application, and the navigation interface and the video playing interface may be displayed in a split screen manner on a screen of the terminal device. The split screen refers to dividing the screen into a plurality of interfaces, and simultaneously opening two or more programs or tasks, so that the two or more programs or tasks can be simultaneously and respectively operated without affecting the respective functions. As shown in fig. 8B, the navigation task and the video playback task do not affect each other.

It should be noted that the above-listed modes of presenting the video playing interfaces are merely examples, and any mode of presenting the video playing interfaces may be applied to the embodiments of the present application, and is not specifically limited herein.

In addition, it should be noted that, in the embodiment of the present application, not only the navigation function but also the video function can be implemented, and the process may relate to the same application having both functions on the terminal device, or may relate to a map application having the navigation function alone and a video application having the video function alone, for example, the video application provides an interface for the map application, and after the object clicks to select the target video, the video application may be skipped from the map application.

In addition, when the navigation and video recommendation interfaces shown in fig. 5, 6 and the like are displayed, the map application calls a video application interface, the process map application can communicate with the video application, for example, the associated information of video resources and position points can be stored in the video application, the map application can transmit the position information of the position points in the target navigation route to the video application when calling the video application, and if the related information of the recommended video returned by the video application is obtained, the jack displays the corresponding navigation and video recommendation interface; of course, the information may also be stored in a server corresponding to the video application, or a server dedicated to storing the information, and the like, and the repetition is not repeated.

In the embodiment of the present application, the above-listed recommended video display is simply a simple description of the display sequence, the display content, and the like, and the following is a supplementary description of some other possible display modes in the embodiment of the present application:

considering that the types of recommended videos are very numerous, in general, video resources such as variety, drama, etc. may include a plurality of sub-videos, for example, a variety is divided into 12 periods, i.e., 12 sub-videos, and a drama includes 24 episodes, i.e., 24 sub-videos. For such video resources including multiple sub-videos, not all the sub-videos are related to the position points in the target navigation route, in this way, when the recommended video is displayed, related prompts can be performed, so that the object can be quickly selected, and the operation complexity of the object is reduced:

In an optional implementation manner, when a recommended video is displayed in a navigation interface, if the recommended video includes a plurality of sub-videos, the identifier of the corresponding target sub-video can be displayed at the associated position of the recommended video for any recommended video; the target sub-video is a sub-video related to a position point in the target navigation route in the plurality of sub-videos.

As shown in fig. 9, which is a schematic diagram of a target sub-video identifier in the embodiment of the present application, where the third and fourth phases in the synthetic process of xx brother season 2 are related to the location point in the target navigation route, the identifier shown by the dashed box S91 may be displayed, and the target sub-video, that is, the 3 rd and 4 th phases of the synthetic process, may also be regarded as a video playing entry, and when the object wants to use the 3 rd target sub-video as the target video, it is enough to click on the 3 rd phase in S91, and when the object wants to use the 4 th target sub-video as the target video, it is enough to click on the 4 th phase in S91.

In addition, in order to facilitate the object to know the position of each recommended video in the target navigation route, the associated position of each recommended video may also display the corresponding position point and longitude and latitude information in the video recommendation area, as shown in fig. 10, which is a schematic diagram of details of the position point corresponding to the recommended video in the embodiment of the present application, where the position point corresponding to the "dishonest xx" is: and B, the location, longitude and latitude information is as follows: the relative positions of the longitude a1 and the latitude b1 and the 'dishonest xx' are shown in the section S92 of a dotted line frame; the corresponding position points of the ' xx brother ' No. 2 season ' are as follows: c, the location, longitude and latitude information is: longitude a2 and latitude b2; the corresponding location points of diet xx9999 are: d, the location, longitude and latitude information is: longitude a3 and latitude b3; the corresponding position points of the 'Tianx-Fuchun xx' are: e, the location, longitude and latitude information is: longitude a4, latitude b4.

In the above embodiment, the associated position of each recommended video also displays the specific coordinates (longitude and latitude information) of the corresponding position point, so that the object is convenient to select, and the object can also realize finer positioning navigation based on the coordinates, so as to refine the navigation points.

Further, considering that in general, there may be one or more routes from one location to another location, i.e. after the object inputs the destination, one or more routes (such as the route with the shortest distance, the least time consumption, and less traffic light) may be planned to be generated, for the same trip, the target navigation route in the embodiment of the present application may be a navigation route recommended by default for the trip or a navigation route selected by the object by itself, and the candidate navigation route refers to other routes for the trip besides the target navigation route.

In an alternative implementation manner, the navigation interface further comprises at least one candidate navigation route related to the destination, the object can select a switching route, the terminal device responds to the selection operation of the target object on the at least one candidate navigation route, the navigation route of the target object is switched from the target navigation route to the selected candidate navigation route, and at least one recommended video displayed in the navigation interface is updated according to the position point in the selected candidate navigation route.

Fig. 11 is a schematic diagram of a navigation and video recommendation interface after route switching in the embodiment of the present application, where an original target navigation route is shown in fig. 4, and the distance is short, the time is 40 minutes, the whole distance is 13.6 km, and 22 traffic lights, and the switched target navigation route is: in the second scheme, 44 minutes are consumed, 15.1 km and 30 traffic lights are all needed, as shown in fig. 11, correspondingly, under the condition of switching the target navigation route, the middle location of the route is changed, so that the recommended video displayed on the right side can be updated accordingly, wherein the destination is unchanged, so that the recommended video "dishonest xx" corresponding to the location B is unchanged, and the recommended video related to the middle location is updated as follows: you Mild xx, bye xx, xx refuel.

In the embodiment, the recommended videos can be updated rapidly through the switching of the target navigation route, so that the object can conveniently select a preferred route according to the recommended videos, or select the video according to the route, and the like, complex operation is not needed, and the experience and the rich interactivity of the object can be effectively enhanced.

Optionally, the present application may further recommend through real-time global positioning system (Global Positioning System, GPS) information, specifically, in the driving process of the target object, according to the current position of the target object, relevant video prompt information is presented in the navigation interface, so as to instruct the target object to view the recommended video related to the current position.

As shown in fig. 12, a schematic diagram of a video prompt message in this embodiment of the present application is shown, before a subject travels to a location D (or travels to a location near the location D), the message prompt message "about to arrive at a location c—xx sibling … for viewing more information and viewing a video clip, welcome to punch a card and take a picture" is presented, so as to remind the subject that the subject "xx sibling" has been shot at a location C in the X-th stage, etc., want to know more information and view a video clip, welcome to punch a card at the location C and obtain the same photo gesture of the star, etc. For another example, when the user arrives at the D site, the prompt "arrives at the D site-diet xx9999 views the view to know more information, can watch video clips, welcome to punch cards and take photos" and the like.

In the above embodiment, by combining the real-time position information of the object, the related video recommendation and reminding can be performed on the object in real time, so that the situation that a certain movie work is found in a certain place after the object goes to the place is reduced, and therefore, the situation that the scene related to the place cannot be combined with the scene is generated.

The above is mainly described in detail by the terminal device side and the server side is described in detail below:

Referring to fig. 13, a flowchart of another implementation of a video recommendation method according to an embodiment of the present application is shown, taking an execution subject as a server as an example, and the implementation process of the method is as follows:

s131: the server receives a navigation request for a destination and generates a destination-related target navigation route.

S132: and the server takes the video resources related to the position points in the target navigation route in the preset video resource set as recommended videos, and returns the target navigation route and at least one recommended video to the terminal equipment.

Furthermore, the terminal device presents the target navigation route in the navigation interface and at least one recommended video, as shown in fig. 5, fig. 6, etc., and the repetition is not repeated.

In this embodiment of the present application, the terminal device may send the navigation request to the server in response to the destination input operation of the target object for the navigation interface, so that the server generates, in combination with the start point and the end point, a destination-related navigation route, including the target navigation route, and may further include at least one candidate navigation route.

Specifically, a map side server generates a navigation scheme, selects a plurality of addresses according to the navigation scheme, searches a pre-constructed street view-movie scene association database for whether associated movie works are contained, and if no relevant video resource (movie works) is searched in the database, directly returns a navigation route (at least including a target navigation route and possibly further including candidate navigation routes) to a terminal device according to the above, so as to enter a navigation mode. If relevant video resources can be searched in the database, the navigation route and the relevant video resources (i.e. recommended videos) can be returned to the terminal equipment so that the terminal equipment can display the video resources.

In the above embodiment, the system (including the terminal device and the server) in the embodiment of the present application may automatically recommend the destination to the object and the movie works related to the along-way location of the planned route, so as to implement video recommendation of the view-finding location, so that when the object is going to a certain place for visiting, the object may know more information of the relevant location point on the target navigation route in advance, and the connection between the video resource and the corresponding actual view-finding location is enhanced.

Besides the above functions, the system in the embodiment of the present application may automatically jump to a destination and play a segment related to a route location of a planned route, which specifically includes the following steps:

s133: and the server receives a playing request aiming at the target video in at least one recommended video, and returns the associated time point of the target video to the terminal equipment.

And further, enabling the terminal equipment to present a corresponding video playing interface, and playing the target video from the associated time point in the video playing interface. Wherein, the associated time point is: video frames associated with the location point corresponding to the target video, play locations in the target video.

Based on the embodiment, when the object selects a certain target video, the terminal equipment can directly realize the automatic playing of the video clips related to the position points based on the associated time points fed back by the server.

In this embodiment of the present application, in a video frame related to a location point corresponding to a target video, a playing position in the target video may be manually marked, or the playing position may also be determined by comparing an image analysis result of each frame of a recommended video with a picture of a corresponding location point in combination with an image analysis technology, so as to locate a segment shot at the corresponding location point, which is not specifically limited herein.

It should be noted that, the above-listed system automatically recommends a destination to an object and a movie work related to a waypoint of a planned route, and automatically jumps to the destination and plays a clip related to the waypoint of the planned route, both of which need to be related to a map-side street view image and a video-side scene image based on an image-related technology, and the scene-related technology may output a degree of association coefficient γe [0,1] of the map-side street view image and the video scene image (which may also be referred to as a movie scene image), where the larger the coefficient value, the more likely the street view image and the video scene image come from the same place, which may be referred to herein simply as an image-based street view-movie scene-related technology, which will be described in detail below.

Based on the street view-movie scene association technology, the construction of a street view-movie scene association database can be completed.

Specifically, the database is constructed by calculating the association degree of the street view image on the map side and the video image on the video side in advance, so that the client on the terminal equipment side can be conveniently used later, for each street view image, the video represented by the video image meeting a certain association degree threshold is taken as the video recommendation under the street view address, and meanwhile, the play position of the video image in the video is recorded, so that a foundation is provided for subsequent automatic jump.

The following describes the construction process of the street view-movie scene association database in detail:

firstly, for the street view-movie scene association technology in the embodiment of the present application, the street view-movie scene association technology may be implemented based on a deep learning technology, and based on this, the present application proposes a target association model to implement the association of the street view-movie scene.

Fig. 14 is a schematic structural diagram of an object association model according to an embodiment of the present application. The model is a visual transformation (Vision Transformer, viT) network (is a visual model) comprising N coding modules (Transformer Encoder, transform coding) and N decoding modules (Transformer Decoder, transform decoding). Where x N is a superposition of consecutive specified modules, e.g. Transformer Encoder x N, it is representative of N such encoders, where n=6 represents: the final output Key (Key), value (Value) to Transformer Decoder, transformer Decoder x N are also similar principles, and the repetition is not repeated.

The upper part of fig. 14 is a transducer encoding part, and the lower part is a transducer decoding part. The Multi-Head Attention section is a Multi-Head Attention section composed of a plurality of Self-Attention mechanisms (Self-Attention), and it can be seen that the encoding section contains one Multi-Head Attention and the decoding section contains two Multi-Head Attention (one of which is Masked). The Multi-Head addition is followed by a join & normalize (Add & Norm) layer, where Add represents residual join (Residual Connection) to prevent network degradation and Norm represents hierarchical normalization (Layer Normalization) to normalize the activation values of each layer.

Optionally, when the association degree of the street view image and the scene image is obtained by combining the target association model, the specific process is as follows:

as shown in fig. 14, the street view image and the scene image are respectively input into a trained target association model;

specifically, the model is input into a plurality of street view images (namely, street view images in a map database in fig. 14) and movie scene images to be queried (namely, images to be queried, which are derived from a certain movie and play segment) under a designated address, semantic analysis is performed on the street view images based on Transformer Encoder in a target association model Vision Transformer, street view semantic value information and street view semantic key information corresponding to the street view images can be obtained, semantic analysis is performed on the (video) scene images based on Transformer Decoder in the target association model Vision Transformer, and scene semantic query information corresponding to the scene images is obtained.

The street view image firstly passes through Transformer Encoder in a Vision Transformer network to form street view semantic Value information (Value) and street view semantic Key information (Key) representing street view semantics, and the scene image to be queried passes through the first half part of Transformer Decoder in the Vision Transformer network (Output embedded Output Embedding to the first Add & Nor) to form scene semantic Query information (Query) representing film and television scene semantics; then, the street view semantic Value information Value, the street view semantic Key information Key and the scene semantic Query information Query are sent into the second half part (from the second Multi-Head attribute to the third Add & Norm) of Transformer Decoder, the street view semantic Value information, the street view semantic Key information and the scene semantic Query information are subjected to related processing, and then are subjected to Linear transformation (Linear) and an activation function (Sigmoid) to be mapped to obtain the association degree gamma epsilon [0,1] of the street view image and the scene image.

An alternative embodiment may train to obtain a target association model according to the flowchart shown in fig. 15, taking a server as an execution body as an example, including the following steps S151-S152:

s151: the server constructs a training sample set;

in the embodiment of the application, to realize training of the target association model, a street view-video scene association data set needs to be constructed as a training sample set, so that a large number of street view images need to be collected and manually marked in association with the video scene images.

Specifically, a video scene image may be collected first, and several street view images may be photographed in a view of the video scene image to perform (manual) association pairing, so as to divide training samples, where each training sample may include a sample street view image corresponding to a sample street view point, a positive sample scene image (a video scene image of the association pairing) and several negative sample scene images (uncorrelated video scene images) corresponding to the sample street view image.

S152: and the server carries out cyclic iterative training on the correlation model to be trained according to the training sample set, and outputs a target correlation model.

Wherein, in a loop iteration process, the following operations are performed:

s1521: the server inputs the selected training samples into a correlation model to be trained, and respectively obtains a first prediction correlation degree between the sample street view image and the positive sample scene image and a second prediction correlation degree between the sample street view image and the negative sample scene image;

specifically, the process may refer to the relevant content corresponding to fig. 14, the sample street view image is similar to the street view image in the map database in fig. 14, the sample scene image (positive sample scene image, negative sample scene image) is similar to the image to be queried, and the repetition is not repeated.

S1522: and the server adopts a loss function constructed based on the first prediction relevance and the second prediction relevance to carry out parameter adjustment on the association model to be trained.

After the data set is built, when training, a plurality of street view images under one address and images from a plurality of film and television works can be used for calculating losses (one of the street view images is a film and television scene image of the association pair, and the other is an uncorrelated image), and binary cross entropy losses (BCE) can be used for losses.

After model training is completed based on the mode, a target association model is obtained, the model can be used for predicting the association degree of the appointed street view and the appointed video scene, if the association degree is larger than a certain value, the video scene and the street view are considered to be associated with each other, and accordingly, the street view-video scene association database is constructed.

An alternative implementation manner is that the association relation between each map street view information and video scene information is constructed by the following modes:

firstly, aiming at a street view image of a street view point and a scene image in a video resource, acquiring the association degree of the street view image and the scene image;

and further, analyzing the association degree, and if the association degree is higher than a preset threshold value, establishing an association relationship between map street view information formed by the street view image and one street view point and video scene information formed by the scene image and one video resource.

Specifically, based on the aforementioned street view-video scene association technology, associating the map-side street view data with the video-side video data as follows:

map side- > scene address (i.e. street view point) - > street view image < = > movie scene image < -movie work (i.e. video resource) < -video side.

When the association is successful (the association degree is greater than a preset threshold), the pairing relation between the scene address and the movie works can be obtained, so as to construct a street view-movie scene association database, specifically, the scene address can enable position information (such as longitude and latitude information), the movie works information comprises movie works id, corresponding scene playing positions, movie works content details and the like, and the database can relate to the following two tables:

table one: position-movie work table; and (II) table: a film and television work detail table.

It should be noted that these two tables may be combined into one, which is not specifically limited herein.

The content of the table one comprises position information of a place, film and television work IDs of corresponding positions and time points of the corresponding positions in the video: wherein the location information may store GPS information (longitude, latitude), and the video location information is in minutes. The following is a list of location-movie works listed in the examples of the present application:

List of position-film and television works

Id	Longitude and latitude	Latitude of latitude	Film and television work id	Video location
					1	120.068285	30.268804	xxxxx01	38
2	120.068278	30.269362	xxxxx02	52
					…	…	…	…	…

As shown in the above table, id of a first column of the table indicates a unique identification of a corresponding row of data in the table, e.g., id is 1, which indicates a set of data: video position 38 corresponding to video resource with film and television work id of xxxxx01 (namely, associated time point is video 38 minutes), longitude of associated street point is 120.068285, latitude is 30.268804; a set of data with Id of 2 represents: video position 52 corresponding to video asset with film and television work id of xxxxx02 (namely, the associated time point is 52 minutes of video), and the longitude of the associated street point is 120.068278, and the latitude is 30.269362, ….

The contents of the table two include the movie work ID and detailed information (i.e., video detail information) of the corresponding movie work.

Watch two film and television works detail list

Film and television work id

Title of the book

Duration of time

Director

Poster map

Introduction to the invention

Scoring of

xxxxx01

Dishonest xx

126

Kudzuvine root, radix Puerariae, and flos Puerariae Lobatae

Xxx

8.3

xxxxx02

xx brothers

84

Bag x, king x

Xxx

0

…

As shown in the above table, in combination with the table two, the video resource with the id of xxxxx01 is titled as dishonest xx, the duration is 126, the director is kudzu x, shux, the poster graph Xxx, the brief introduction Xxx, and the score is 8.3; video assets with film and television work id of xxxxx02 are named as xx brothers, the duration is 84, the main director is package x, king x, poster graph Xxx, introduction Xxx and scores of 0 and ….

Specifically, after the streetscape-movie scene association database is built, the associated movie works and video scenes can be queried in the database according to the appointed streetscape, specifically: the client initiates destination navigation on the map side, the map side returns a potential navigation line, a plurality of street view addresses can be found in the map side according to the navigation line, video scene association data are queried in the street view-video scene association database, and if the video works are queried, a result is returned to the client and then presented to the object.

Similarly, since the playing position of the movie works associated with the current street view is recorded in the street view-movie scene association database, if the associated movie works are queried, the playing position is returned, and then the movie works are displayed to the object at the client.

In combination with the above, when inquiring the related data of the movie and television scene in the related database of the street view and movie and television scene, an optional implementation manner is as follows:

acquiring each position point related to the target navigation route, so as to respectively execute the following operations for each position point:

for a position point, respectively acquiring the distance between the position point and each video resource associated street view point in the video resource set; the street scenery points respectively associated with each video resource are as follows: a location corresponding to a street view image corresponding to a scene image in a video resource is determined based on a correlation relationship between pre-constructed map street view information and video scene information (i.e., the street view-movie scene correlation database enumerated above); and selecting video resources with the corresponding distance within a preset distance range as recommended videos corresponding to the position points.

In the embodiment of the application, the corresponding distance is represented in the preset distance range to obtain the position point or the related film and television works near the position point. Specifically, the searching process needs to search the table one according to the longitude and latitude information of the destination, and specifically the calculation scheme is as follows:

comparing the longitude and latitude data of the position point with the longitude and latitude data of the street scenic spot associated with each video resource in the database, thereby screening out a film and television work id list near the position point; and then inquiring the detailed information of the video from the second table according to the id list, and further returning the navigation information and the detailed information of the video to the terminal equipment (such as a vehicle-mounted terminal).

The specific calculation rule for comparing the longitude and latitude data of the position point with the longitude and latitude data of the street scenic spot is as follows:

the longitude and latitude information of the two points P1 and P2 is recorded as follows: the location point P1 (long 1, lat 1), the street view point P2 (long 2, lat 2) associated with the video resource, the distance between P1 and P2 is:

where a represents the difference in altitude of two points and b represents the difference in longitude of two points:

a＝lat1-lat2；

b＝long1-long2；

r represents the radius of the earth, r= 6378.137;

if dis is within the preset distance range, if dis is smaller than a certain distance threshold (e.g. 1000 meters), the video resource can be used as the recommended video corresponding to the position point.

Further, after receiving the video information of the target video selected by the object, the server returns to the vehicle-mounted terminal through the second lookup table, specifically, the playing time (namely, the associated time point), and the vehicle-mounted terminal plays from the associated time point.

The following details from the point of view of interaction of the terminal device with the server:

fig. 16 is a flowchart of interaction between a terminal device and a server according to an embodiment of the present application. The specific implementation flow of the method is as follows:

first, the object serves as a terminal device initiator, after starting a journey, a destination is input in a navigation module, an instruction (i.e., a navigation request) is sent to a server, and a navigation scheme is generated by a map side server.

Further, the server selects a plurality of location points (including a destination and a destination) according to the navigation scheme, searches the database (i.e., the aforementioned street view-video scene association database) for the destination and the destination-related video works:

if no related film and television works exist, directly returning to the navigation scheme and ending the flow;

and if the related film and television works exist, returning the navigation scheme and the recommended video based on the position point to the terminal equipment.

After receiving the video recommendation, the object browses and clicks the interested video (namely the target video), sends an instruction (namely a playing request) to the server, searches detailed video information according to the video id and returns detailed information and associated time points after receiving the selection of the object, and the terminal equipment directly starts playing from the located associated time points and ends the flow.

In the related art, the video and navigation of the vehicle are two independent functional modules, and when the object needs to go to a certain place, for example, when the object wants to know the related movie works of the destination in advance, the object needs to manually surf the internet to search and then go to the video application to watch, and the object needs to manually search for the segments of the related content in the video. In the application, when the object performs GPS navigation, the movie work recommendation related to the destination and the along-way location is automatically generated, and the movie work recommendation can be directly positioned to the related segment for playing. The video recommendation scheme based on the GPS location can improve the driving experience and the video watching experience of the object, improves the interestingness of the object journey, simultaneously meets the concept of the intelligent vehicle-mounted terminal, and maximally plays the convenience of the intelligent screen of the vehicle-mounted terminal, so that the object obtains good object experience, and promotes the association between navigation and video.

Based on the same inventive concept, the embodiment of the application also provides a video recommendation device. As shown in fig. 17, which is a schematic structural diagram of the video recommendation device 1700, may include:

a first response unit 1701, configured to present a navigation interface, and in response to a destination input operation for the navigation interface, present a destination-related target navigation route in the navigation interface, and present at least one recommended video for the target navigation route, each recommended video being a video resource related to a location point in the target navigation route;

A second response unit 1702, configured to respond to a selection operation for a target video in at least one recommended video, and present a corresponding video playing interface;

the second response unit 1702 is further configured to play, in the video playing interface, the target video from an associated time point of the target video, where the associated time point is: video frames associated with the location point corresponding to the target video, play locations in the target video.

Optionally, the location point corresponding to each recommended video includes: at least one of a destination and an intermediate location;

Optionally, the second response unit 1702 is specifically configured to:

presenting a destination-related target navigation route in a map area of a navigation interface, and displaying at least one recommended video for the target navigation route in a video recommendation area of the navigation interface; or alternatively

And presenting a destination-related target navigation route in the navigation interface, and displaying a recommended video corresponding to the position point at the position point related to the target navigation route.

Optionally, the video recommendation area includes a plurality of recommended videos; the second response unit 1702 is specifically configured to:

wherein the destination has a higher priority than the intermediate location; the intermediate sites are: other waypoints in the target navigation route than the destination.

Optionally, the second response unit 1702 is specifically configured to:

presenting a video playing interface in a partial area in the navigation interface; or alternatively

And the split screen displays a navigation interface and a video playing interface.

and a third response unit 1703, configured to switch the navigation route for the target object from the target navigation route to the selected candidate navigation route in response to the selection operation of the target object for the at least one candidate navigation route, and update at least one recommended video displayed in the navigation interface according to the location point in the selected candidate navigation route.

Optionally, the second response unit 1702 is specifically configured to:

Optionally, the second response unit 1702 is further configured to:

Optionally, the apparatus further comprises:

the information prompt unit 1704 is configured to present relevant video prompt information in the navigation interface according to the current position of the target object during the driving process of the target object, so as to instruct the target object to view the recommended video related to the current position.

Based on the same inventive concept, the embodiment of the application also provides a video recommendation device. As shown in fig. 18, which is a schematic structural diagram of the video recommendation device 1800, may include:

a first receiving unit 1801, configured to receive a navigation request for a destination, and generate a destination-related target navigation route;

the screening unit 1802 is configured to take, as a recommended video, a video resource related to a location point in the target navigation route in a preset video resource set, and return the target navigation route and at least one recommended video to the terminal device, so that the terminal device presents the target navigation route in the navigation interface and at least one recommended video;

The second receiving unit 1803 is configured to receive a play request for a target video in at least one recommended video, return an associated time point of the target video to the terminal device, so that the terminal device presents a corresponding video play interface, and play the target video in the video play interface from the associated time point, where the associated time point is: video frames associated with the location point corresponding to the target video, play locations in the target video.

Optionally, the screening unit 1802 is specifically configured to:

for a position point, respectively acquiring the distance between the position point and each video resource in the video resource set and each associated street view point; the street scenery points respectively associated with each video resource are as follows: determining a place corresponding to a street view image corresponding to a scene image in a video resource based on a correlation between pre-constructed map street view information and video scene information;

And selecting video resources with corresponding distances within a preset distance range as recommended videos corresponding to the position points.

Optionally, the filtering unit 1802 is further configured to construct an association relationship between each map street view information and video scene information by:

if the association degree is higher than a preset threshold value, establishing an association relationship between map street view information formed by the street view image and one street view point and video scene information formed by the scene image and one video resource.

Optionally, the screening unit 1802 is specifically configured to:

respectively inputting a street view image and a scene image into a trained target association model;

Optionally, the apparatus further comprises:

model training unit 1804 is configured to train to obtain a target association model by:

performing cyclic iterative training on the association model to be trained according to the training sample set, and outputting a target association model; wherein, in a loop iteration process, the following operations are performed:

inputting the selected training samples into a correlation model to be trained, and respectively obtaining a first prediction correlation degree between the sample street view image and the positive sample scene image and a second prediction correlation degree between the sample street view image and the negative sample scene image;

According to the method, a target navigation route can be generated by combining a destination input by an object in a navigation interface, and more accurate video recommendation is performed on the object by combining video resources related to position points in the target navigation route. In addition, in the method, the recommendation of the related video resources can be triggered only by inputting the destination, and the automatic playing of the position point related video clips can be directly realized when a certain target video is selected.

For convenience of description, the above parts are described as being functionally divided into modules (or units) respectively. Of course, the functions of each module (or unit) may be implemented in the same piece or pieces of software or hardware when implementing the present application.

Having described the video recommendation method and apparatus of exemplary embodiments of the present application, next, an electronic device according to another exemplary embodiment of the present application is described.

Those skilled in the art will appreciate that the various aspects of the present application may be implemented as a system, method, or program product. Accordingly, aspects of the present application may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.

The embodiment of the application also provides electronic equipment based on the same inventive concept as the embodiment of the method. In one embodiment, the electronic device may be a server, such as server 120 shown in FIG. 1. In this embodiment, the electronic device may be configured as shown in fig. 19, including a memory 1901, a communication module 1903, and one or more processors 1902.

A memory 1901 for storing computer programs for execution by the processor 1902. The memory 1901 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, programs required for running an instant communication function, and the like; the storage data area can store various instant messaging information, operation instruction sets and the like.

The memory 1901 may be a volatile memory (RAM) such as a random-access memory (RAM); the memory 1901 may also be a nonvolatile memory (non-volatile memory), such as a read-only memory, a flash memory (flash memory), a hard disk (HDD) or a Solid State Drive (SSD); or memory 1901, is any other medium that can be used to carry or store a desired computer program in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 1901 may be a combination of the above memories.

The processor 1902 may include one or more central processing units (central processing unit, CPU) or digital processing units, or the like. A processor 1902 for implementing the video recommendation method described above when invoking a computer program stored in a memory 1901.

The communication module 1903 is used for communicating with a terminal device and other servers.

The specific connection medium between the memory 1901, the communication module 1903, and the processor 1902 is not limited in the embodiments of the present application. In the embodiment of the present application, the memory 1901 and the processor 1902 are connected by a bus 1904 in fig. 19, and the bus 1904 is depicted by a thick line in fig. 19, and the connection manner between other components is merely illustrative and not limited thereto. The bus 1904 may be divided into an address bus, a data bus, a control bus, and the like. For ease of description, only one thick line is depicted in fig. 19, but only one bus or one type of bus is not depicted.

The memory 1901 stores therein a computer storage medium having stored therein computer executable instructions for implementing the video recommendation method of the embodiments of the present application. The processor 1902 is configured to perform the video recommendation method described above, as shown in fig. 13.

In another embodiment, the electronic device may also be other electronic devices, such as terminal device 110 shown in fig. 1. In this embodiment, the structure of the electronic device may include, as shown in fig. 20: communication assembly 2010, memory 2020, display unit 2030, camera 2040, sensor 2050, audio circuit 2060, bluetooth module 2070, processor 2080 and the like.

The communication component 2010 is for communicating with a server. In some embodiments, a circuit wireless fidelity (Wireless Fidelity, wiFi) module may be included, where the WiFi module belongs to a short-range wireless transmission technology, and the electronic device may help the object to send and receive information through the WiFi module.

Memory 2020 may be used for storing software programs and data. The processor 2080 executes various functions and data processing of the terminal device 110 by executing software programs or data stored in the memory 2020. The memory 2020 may include high-speed random access memory and may also include non-volatile memory such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Memory 2020 stores an operating system that enables terminal device 110 to operate. The memory 2020 may store an operating system and various application programs, and may also store a computer program for executing the video recommendation method according to the embodiment of the present application.

The display unit 2030 may also be used to display information input by an object or information provided to the object and a graphical user interface (graphical user interface, GUI) of various menus of the terminal apparatus 110. Specifically, the display unit 2030 may include a display screen 2032 provided on the front surface of the terminal apparatus 110. The display 2032 may be configured in the form of a liquid crystal display, light emitting diodes, or the like. The display unit 2030 may be used for displaying a navigation interface, a video playback interface, and the like in the embodiments of the application.

The display unit 2030 may also be used for receiving input numeric or character information, generating signal inputs related to object settings and function control of the terminal apparatus 110, and in particular, the display unit 2030 may include a touch screen 2031 provided on the front surface of the terminal apparatus 110, and may collect touch operations on or near the object, such as clicking buttons, dragging scroll boxes, and the like.

The touch screen 2031 may be covered on the display screen 2032, or the touch screen 2031 and the display screen 2032 may be integrated to implement input and output functions of the terminal device 110, and after integration, the touch screen may be simply referred to as a touch screen. The display unit 2030 may display an application program and corresponding operation steps in this application.

The camera 2040 may be used to capture still images, and the subject may post images captured by the camera 2040 through an application. The camera 2040 may be one or a plurality of cameras. The object generates an optical image through the lens and projects the optical image onto the photosensitive element. The photosensitive element may be a charge coupled device (charge coupled device, CCD) or a Complementary Metal Oxide Semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, which is then transferred to the processor 2080 for conversion into a digital image signal.

The terminal device may also include at least one sensor 2050, such as an acceleration sensor 2051, a distance sensor 2052, a fingerprint sensor 2053, a temperature sensor 2054. The terminal device may also be configured with other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, light sensors, motion sensors, and the like.

The audio circuitry 2060, speaker 2061, microphone 2062 may provide an audio interface between the subject and the terminal device 110. The audio circuit 2060 may transmit the received electrical signal converted from audio data to the speaker 2061, and be converted into a sound signal by the speaker 2061 to be output. The terminal device 110 may also be configured with a volume button for adjusting the volume of the sound signal. On the other hand, the microphone 2062 converts the collected sound signal into an electrical signal, receives it by the audio circuit 2060 and converts it into audio data, which is then output to the communication component 2010 for transmission to, for example, another terminal device 110, or to the memory 2020 for further processing.

The bluetooth module 2070 is used for exchanging information with other bluetooth devices having a bluetooth module through a bluetooth protocol. For example, the terminal device may establish a bluetooth connection with a wearable electronic device (e.g., a smart watch) that also has a bluetooth module through the bluetooth module 2070, so as to perform data interaction.

The processor 2080 is a control center of the terminal device, and connects various parts of the entire terminal using various interfaces and lines, and performs various functions of the terminal device and processes data by running or executing software programs stored in the memory 2020, and calling data stored in the memory 2020. In some embodiments, the processor 2080 may include one or more processing units; the processor 2080 may also integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., and a baseband processor that primarily handles wireless communications. It will be appreciated that the baseband processor described above may not be integrated into the processor 2080. The processor 2080 may run an operating system, an application, a user interface display, a touch response, and a video recommendation method according to an embodiment of the present application. In addition, the processor 2080 is coupled to the display unit 2030.

It should be noted that, in the specific embodiment of the present application, the object data related to video recommendation and the like is referred to, and when the above embodiments of the present application are applied to specific products or technologies, the object permission or consent needs to be obtained, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related countries and regions.

In some possible embodiments, aspects of the video recommendation method provided herein may also be implemented in the form of a program product comprising a computer program for causing an electronic device to perform the steps of the video recommendation method according to the various exemplary embodiments of the present application described herein above when the program product is run on the electronic device, e.g. the electronic device may perform the steps as shown in fig. 2 or 13.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The program product of embodiments of the present application may employ a portable compact disc read only memory (CD-ROM) and comprise a computer program and may be run on an electronic device. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with a command execution system, apparatus, or device.

The readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave in which a readable computer program is embodied. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with a command execution system, apparatus, or device.

A computer program embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

Computer programs for performing the operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer program may execute entirely on the consumer electronic device, partly on the consumer electronic device, as a stand-alone software package, partly on the consumer electronic device and partly on the remote electronic device or entirely on the remote electronic device. In the case of remote electronic devices, the remote electronic device may be connected to the consumer electronic device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external electronic device (e.g., connected through the internet using an internet service provider).

It should be noted that although several units or sub-units of the apparatus are mentioned in the above detailed description, such a division is merely exemplary and not mandatory. Indeed, the features and functions of two or more of the elements described above may be embodied in one element in accordance with embodiments of the present application. Conversely, the features and functions of one unit described above may be further divided into a plurality of units to be embodied.

Furthermore, although the operations of the methods of the present application are depicted in the drawings in a particular order, this is not required to or suggested that these operations must be performed in this particular order or that all of the illustrated operations must be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having a computer-usable computer program embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program commands may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the commands executed by the processor of the computer or other programmable data processing apparatus produce means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program commands may also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the commands stored in the computer readable memory produce an article of manufacture including command means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.

Claims

1. A video recommendation method, the method comprising:

2. The method of claim 1, wherein each recommended video corresponding location point comprises: at least one of the destination and an intermediate location;

3. The method of claim 1, wherein presenting a destination-related target navigation route in the navigation interface and presenting at least one recommended video for the target navigation route comprises:

4. The method of claim 3, wherein the video recommendation area comprises a plurality of recommended videos; the displaying at least one recommended video for the target navigation route in the video recommendation area of the navigation interface comprises:

5. The method of claim 4, wherein each recommended video corresponding location point comprises: at least one of the destination and an intermediate location;

6. The method of claim 1, wherein presenting the respective video playback interface comprises:

7. The method of claim 1, wherein the navigation interface further comprises at least one candidate navigation route associated with the destination; the method further comprises the steps of:

and responding to the selection operation of a target object on the at least one candidate navigation route, switching the navigation route aiming at the target object from the target navigation route to a selected candidate navigation route, and updating the at least one recommended video displayed in the navigation interface according to the position point in the selected candidate navigation route.

8. The method of claim 1, wherein the presenting at least one recommended video for the target navigation route comprises:

9. The method of claim 1, wherein presenting at least one recommended video for the target navigation route at the navigation interface further comprises:

10. The method of any one of claims 1-9, wherein the method further comprises:

and in the running process of the target object, presenting related video prompt information in the navigation interface according to the current position of the target object so as to instruct the target object to view the recommended video related to the current position.

11. A video recommendation method, the method comprising:

Taking video resources related to position points in the target navigation route in a preset video resource set as recommended videos, and returning the target navigation route and at least one recommended video to terminal equipment so that the terminal equipment presents the target navigation route in a navigation interface and displays the at least one recommended video;

12. The method of claim 11, wherein each recommended video corresponding location point comprises: at least one of the destination and an intermediate location;

13. The method of claim 11, wherein the taking the video resources related to the location point in the target navigation route in the preset video resource set as recommended video includes:

14. The method of claim 13, wherein the association between each map street view information and video scene information is constructed by:

15. The method of claim 14, wherein the obtaining the degree of association of the street view image with the scene image comprises:

16. The method of claim 15, wherein the target association model is trained by:

17. A video recommendation device, comprising:

18. A video recommendation device, comprising:

19. An electronic device comprising a processor and a memory, wherein the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 16.

20. A computer readable storage medium, characterized in that it comprises a computer program for causing an electronic device to perform the steps of the method of any one of claims 1-16 when said computer program is run on the electronic device.

21. A computer program product comprising a computer program, the computer program being stored on a computer readable storage medium; when the computer program is read from the computer readable storage medium by a processor of an electronic device, the processor executes the computer program, causing the electronic device to perform the steps of the method of any one of claims 1-16.