CN110866168A

CN110866168A - Information recommendation method and device, terminal and server

Info

Publication number: CN110866168A
Application number: CN201810981797.6A
Authority: CN
Inventors: 张雷; 王玉顺; 金亮
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2018-08-27
Filing date: 2018-08-27
Publication date: 2020-03-06

Abstract

The embodiment of the application provides an information recommendation method, an information recommendation device, a terminal and a server. In the embodiment of the application, a first target image acquired by a first user side is determined; identifying the image content of the first target image to determine the label information corresponding to the first target image; determining first recommendation information corresponding to the label information of the first target image; sending the first recommendation information to the first user terminal; or generating second recommendation information at least comprising the first target image; and the second recommendation information is used for being sent to a second user end matched with the label information of the first target image. The technical scheme provided by the embodiment of the application improves the effectiveness and accuracy of the information.

Description

Information recommendation method and device, terminal and server

Technical Field

The embodiment of the application relates to the technical field of computer application, in particular to an information recommendation method, an information recommendation device, a terminal and a server.

Background

With the increasing improvement of the quality of life, the demands of users on tourism such as vacation and leisure are continuously increased, and the users can generally do a large number of lessons before or during traveling so as to know travel destinations to a certain extent.

With the continuous development of internet technology, people increasingly rely on obtaining relevant information from the internet, and more websites providing travel-related information, such as a web service platform providing travel services such as tourism, are provided.

However, the information provided by the network service platform is complicated, and the user can only search by means of keywords when the user is clear of his own travel purpose, or can obtain the desired related information by reading a large amount irregularly, but the user often becomes in a lost state, so that the effective and accurate information cannot be obtained from the network service platform.

Disclosure of Invention

The embodiment of the application provides an information recommendation method, an information recommendation device, a terminal and a server, and aims to solve the technical problem that effective and accurate information cannot be obtained in the prior art.

In a first aspect, an embodiment of the present application provides an information recommendation method, including:

determining a first target image acquired by a first user side;

identifying the image content of the first target image to determine the label information corresponding to the first target image;

determining first recommendation information corresponding to the label information of the first target image;

and sending the first recommendation information to the first user terminal.

In a second aspect, an embodiment of the present application provides an information recommendation method, including:

collecting a first target image;

sending the first target image to a server side, so that the server side can identify the image content of the first target image, determine the label information corresponding to the first target image, and determine first recommendation information corresponding to the label information;

acquiring the first recommendation information sent by the server;

and outputting the first recommendation information.

In a third aspect, an embodiment of the present application provides an information recommendation method, including:

determining a first target image acquired by a first user side;

generating second recommendation information including at least the first target image; and the second recommendation information is used for being sent to a second user end matched with the label information of the first target image.

In a fourth aspect, an embodiment of the present application provides an information recommendation method, including:

receiving a second recommendation request sent by a third user end;

determining a second target image of which the label information is matched with the third user side; the second target image is acquired by a fourth user end; the label information of the second target image is obtained based on the image content identification of the second target image;

determining third recommendation information including at least the second target image.

And sending the third recommendation information to the third user terminal.

In a fifth aspect, an embodiment of the present application provides an information recommendation apparatus, including:

the first image determining module is used for determining a first target image acquired by a first user side;

the first identification module is used for identifying the image content of the first target image so as to determine the label information corresponding to the first target image;

the first information determining module is used for determining first recommendation information corresponding to the label information of the first target image;

and the first information sending module is used for sending the first recommendation information to the first user terminal.

In a sixth aspect, an embodiment of the present application provides an information recommendation apparatus, including:

the image acquisition module is used for acquiring a first target image;

the image sending module is used for sending the first target image to a server so that the server can identify the image content of the first target image, determine the label information corresponding to the first target image and determine first recommendation information corresponding to the label information;

the information acquisition module is used for acquiring the first recommendation information sent by the server;

and the information output module is used for outputting the first recommendation information.

In a seventh aspect, an embodiment of the present application provides an information recommendation apparatus, including:

the second image determining module is used for determining a first target image acquired by the first user side;

the second identification module is used for identifying the image content of the first target image so as to determine the label information corresponding to the first target image;

a second information determination module for generating second recommendation information including at least the first target image; and the second recommendation information is used for being sent to a second user end matched with the label information of the first target image.

In an eighth aspect, an embodiment of the present application provides an information recommendation apparatus, including:

the request receiving module is used for receiving a second recommendation request sent by a third user end;

the third image determining module is used for determining a second target image of which the label information is matched with the third user side; the second target image is acquired by a fourth user end; the label information of the second target image is obtained based on the image content identification of the second target image;

and the third information determining module is used for determining third recommendation information at least comprising the second target image.

And the third information sending module is used for sending the third recommendation information to the third user terminal.

In a ninth aspect, an embodiment of the present application provides a server, including a processing component and a storage component;

the storage component stores one or more computer instructions; the one or more computer instructions to be invoked for execution by the processing component;

the processing component is to:

determining a first target image acquired by a first user side;

and sending the first recommendation information to the first user terminal.

In a tenth aspect, an embodiment of the present application provides a terminal, including a storage component, a display component, and a processing component; the storage component stores one or more computer program instructions; the one or more computer program instructions for invocation and execution by the processing component;

the processing component is to:

collecting a first target image;

acquiring the first recommendation information sent by the server;

and outputting the first recommendation information through the display component.

In an eleventh aspect, an embodiment of the present application provides a server, including a processing component and a storage component;

the processing component is to:

determining a first target image acquired by a first user side;

In a twelfth aspect, an embodiment of the present application provides a server, including a processing component and a storage component;

the processing component is to:

receiving a second recommendation request sent by a third user end;

And sending the third recommendation information to the third user terminal.

In the embodiment of the application, the label information corresponding to the first target image is determined by identifying the image content of the first target image acquired by the first user side, so that the corresponding first recommendation information can be determined based on the label information of the first target image, and the first user side outputs the first recommendation information. In the embodiment of the application, the user does not need to search keywords by imagination or perform traversal reading and searching, so that effective and accurate information can be obtained, and the accuracy and the effectiveness of the information are improved.

These and other aspects of the present application will be more readily apparent from the following description of the embodiments.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a flow chart illustrating a method of one embodiment of a method for information recommendation provided herein;

FIG. 2 illustrates a method flow diagram of one embodiment of a model training method provided herein;

FIG. 3 illustrates a method flow diagram of yet another embodiment of a method for information recommendation provided herein;

FIG. 4 is a schematic diagram of an interface display in a practical application according to an embodiment of the present application;

FIG. 5 is a flow chart of a method of another embodiment of a method of information recommendation provided herein;

FIG. 6 is a flow chart of a method of another embodiment of a method of information recommendation provided herein;

FIG. 7 is a schematic diagram illustrating an interaction of the information recommendation method provided by the present application in a practical application;

FIG. 8 is a schematic structural diagram illustrating an embodiment of an information recommendation device provided by the present application;

FIG. 9 is a schematic diagram illustrating an embodiment of a server provided by the present application;

FIG. 10 is a schematic structural diagram of another embodiment of an information recommendation device provided by the present application;

FIG. 11 is a schematic diagram illustrating an embodiment of a terminal provided by the present application;

FIG. 12 is a schematic structural diagram of another embodiment of an information recommendation device provided by the present application;

FIG. 13 is a schematic diagram illustrating an architecture of yet another embodiment of a server provided by the present application;

FIG. 14 is a schematic structural diagram of another embodiment of an information recommendation device provided by the present application;

fig. 15 is a schematic structural diagram of a server according to still another embodiment of the present application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.

In some of the flows described in the specification and claims of this application and in the above-described figures, a number of operations are included that occur in a particular order, but it should be clearly understood that these operations may be performed out of order or in parallel as they occur herein, the number of operations, e.g., 101, 102, etc., merely being used to distinguish between various operations, and the number itself does not represent any order of performance. Additionally, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first", "second", etc. in this document are used for distinguishing different messages, devices, modules, etc., and do not represent a sequential order, nor limit the types of "first" and "second" to be different.

The technical scheme of the embodiment of the application can be suitable for providing different travel service network service scenes, for example, providing travel service network service scenes.

As described in the background art, although a network service platform providing travel services can provide travel related information, a user can only obtain related information by searching according to keywords when the user specifies his or her travel purpose, or obtain desired related information by reading a large amount irregularly, which results in failure to obtain useful information timely and effectively.

In the embodiment of the present application, by identifying the image content of the first target image acquired by the first user, tag information corresponding to the first target image is determined, so that corresponding first recommendation information can be determined based on the tag information of the first target image, and the first user outputs the first recommendation information. The first target image can be acquired by collecting the area where the user is located or the seen object, so that the acquired first recommendation information is related to the user traveling, and the user does not need to search keywords by imagination or perform traversal reading and searching, so that effective and accurate information can be acquired.

The technical solutions in the embodiments 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 obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Fig. 1 is a flowchart of an embodiment of an information recommendation method provided in an embodiment of the present application, where a technical solution of the embodiment is executed by a server, and the method may include the following steps:

101: and determining a first target image acquired by the first user side.

The first target image can be obtained by the first user terminal through image acquisition of the first target area. The first target area may be a current location area of the user, and the like.

Therefore, optionally, the determining of the target image acquired by the first user end may be:

and determining a first target image obtained by the first user terminal performing image acquisition on the first target area where the first user terminal is located.

The first target image may be obtained by image-capturing a first target object in a first target region where the first target object is located. The first target object may be something in the first target area that is fixed for a certain time, such as a natural landscape, a landmark building, a seasonal scene, etc.

In a travel scene, the first target area may be any area seen in the user's travel process, and the like. The user can acquire the first target area through the first user end to obtain a first target image.

102: and identifying the image content of the first target image to determine the label information corresponding to the first target image.

Optionally, the image content of the first target image may be identified by using an image classification model to determine the tag information corresponding to the first target image.

The image classification model is obtained according to sample image training of preset label information. The tag information of the first target image may be used to represent the image content of the first target image.

In the embodiment of the application, in order to solve the user requirement, the image content transmitted by the first target image needs to be understood, and in a travel scene, particularly a travel scene for traveling, travel-related information that the user wants to know is usually spread around a certain sight spot or a certain landmark object, for example, sight spot introduction information, sight spot entrance ticket-related information, sight spot peripheral accommodation or catering service information, and the like. Therefore, the preset tag information of the sample image may be determined based on the image content of the sample image or the object identification of the landmark object corresponding to the sample image, and the like, so as to identify the obtained tag information of the first target image, i.e., may represent the image content of the first target image, and the like.

In a travel scene aiming at traveling, a user mainly aims at browsing scenic spots or landmark objects and the like, so that the sample image can specifically select images corresponding to different scenic spot POIs (points of Interest) or different landmark objects.

In an alternative, the image classification model may be obtained by pre-training specifically as follows:

acquiring a plurality of sample images;

setting label information of each sample image;

training to obtain an image classification model by using the image characteristics and label information of each sample image;

therefore, optionally, the identifying, by using the image classification model, the tag information corresponding to the first target image may include:

extracting image features of the first target image;

and identifying and obtaining label information corresponding to the first target image by using the image classification model based on the image characteristics of the first target image.

The image classification model may be an SVM (Support Vector Machine), CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), or other Machine learning models.

103: and determining first recommendation information corresponding to the label information of the first target image.

104: and sending the first recommendation information to the first user terminal.

After the tag information of the first target image is identified, first recommendation information corresponding to the tag information can be determined, and the first recommendation information can be sent to the first user side and output by the first user side.

The corresponding relation between different tag information and different recommendation information can be preset, so that the first recommendation information corresponding to the tag information of the first target image can be determined based on the corresponding relation.

The first recommendation information may specifically be travel related information matched with the tag information of the first target image, and the travel related information may include travel route introduction information, object introduction information of an image content representation object, and certainly may also include travel related products, such as tickets, lodging or catering services, and the like. When the tag information of the first target image indicates that the first target image is obtained by image acquisition at a certain sight spot or a certain landmark object, the travel-related product may be a sight spot ticket or a landmark object ticket, or an accommodation service or a catering service provided by a service organization around the sight spot or the landmark object.

In the embodiment, the image content can be understood through image acquisition and image identification, so that corresponding recommendation information can be obtained through acquiring the target image, a user does not need to search keywords by imagination or perform traversal reading and searching, effective and accurate information can be obtained, and especially when the first target image is acquired in the travel process, useful information related to travel can be guaranteed to be obtained.

In order to improve the information recommendation accuracy, in yet another optional embodiment, the method may further include:

acquiring first positioning information of the first user terminal;

the determining the first recommendation information corresponding to the tag information may include:

and determining first recommendation information corresponding to the label information and the first positioning information.

Since in practical applications, there may be a case where different locations have the same landscape, such as some landmark buildings, and the tag information represents the image content of the first target image, more accurate first recommendation information can be obtained by combining the first positioning information of the first user and the tag information.

For example, if the first target image is obtained by image acquisition of a landmark building "statue liberty", since both the tablespace and the new york have "statues liberty", the current position of the user can be determined by combining the first positioning information of the first user side, so that the first recommendation information of the "statue liberty" with the current position of the user can be recommended to the user, so that the information recommendation is more accurate,

In some embodiments, the first recommendation information corresponding to the tag information may be travel-related information, and the determining of the first recommendation information corresponding to the tag information may include:

and determining travel related information corresponding to the label information.

The travel related information may include travel related products and purchase prompt information; the purchase prompting information is used for prompting the user to purchase the travel related product. Accordingly, the method may further comprise:

receiving a purchase request sent by the first user terminal for the travel related product;

and processing the purchase request to finish the purchase operation of the travel related products.

The purchase request may be sent by the first user end in response to a purchase operation for the travel-related product, and the purchase prompt information may include a transaction control, and the purchase operation may be triggered by operating the transaction control.

Further, in some embodiments, the determining the first recommendation information corresponding to the tag information may include:

acquiring user characteristics;

and determining first recommendation information respectively matched with the label information of the first target image and the user characteristics.

The user features represent the user portrait and can be obtained by combining with user historical trip information statistics. The user historical travel information may refer to, for example, historical travel locations, historical browsing views, and the like.

According to the tag information of the first target image, a landmark object such as a landmark building or a POI corresponding to the first target image can be determined. Objects that can be matched from user features in conjunction with user features or landmark objects, target objects that are similar to landmark objects, and the like. Therefore, the first recommendation information may include travel recommendation information corresponding to the target object, such as related introduction information or related travel products.

As can be seen from the above description, the image classification model may be obtained by pre-training, and thus, as shown in fig. 2, an embodiment of the present application further provides a model training method, which may include the following steps:

201: a plurality of sample images are acquired.

202: label information of each sample image is set.

203: and training to obtain an image classification model by using the image characteristics of each sample image and the label information thereof.

Specifically, the image feature of each sample image may be used as an input sample, and the label information thereof is used as an output sample, and the image classification model is obtained through training.

The image classification model can be used for identifying the label information of the target image acquired by any user side.

As an alternative, the acquiring the plurality of sample images may include:

acquiring sample images corresponding to different POIs;

the setting of the label information of each sample image may include:

the label information of each sample image is set according to the image content of each sample image.

In addition, POI identifiers and the like of corresponding POIs can be set for each sample image.

Since the user may pass through different locations in the travel route during the course of his/her trip, such as sights, meeting facilities, lodging facilities, dining facilities, etc., these locations may be generally represented by POIs in the map information system. Therefore, sample images corresponding to different POIs can be obtained.

Each point of interest POI may correspond to one or more sample images, and the sample image corresponding to each point of interest POI may include an image of an area where the point of interest POI is located.

Acquiring sample images corresponding to different POIs from an image database; the image database may be provided by a web services platform.

Wherein, according to the image content of each sample image, the tag information set for each image may be set according to the object type of the object represented by the image content, such as a person, a scene, food, etc.; or the object identifier may be set according to an object identifier of an object represented by the image content, where the object represented by the image content may be a landmark object in the corresponding POI, such as a landmark building, and the like, and therefore the object identifier may be a name of the landmark building, and the like, for example, if the sample image is obtained by image capturing an eiffel tower, the tag information may be set to be "eiffel tower" and the like.

Furthermore, as yet another alternative, the acquiring a plurality of sample images may include:

acquiring sample images corresponding to different landmark objects;

the setting of the label information of each sample image may include:

and setting label information of each sample image according to the object identification of the landmark object corresponding to each sample image.

Wherein each landmark object may correspond to one or more sample images, and the sample image corresponding to each landmark object may include the landmark object.

It can be known that the sample image corresponding to each POI may include the sample image corresponding to the landmark object in the area where each POI is located.

In some embodiments, after identifying, by using the image classification model, the target label information corresponding to the first target image, the method may further include:

and taking the first target image as a sample image for training the image classification model.

Fig. 3 is a flowchart of another embodiment of an information recommendation method provided in an embodiment of the present application, which is described from the perspective of a first user, and the method may include the following steps:

301: a first target image is acquired.

Optionally, the first target image corresponding to a first target area may be acquired, where the first target area is an area where the first user terminal is currently located.

Further, a first target image may be obtained by acquiring a first target object in the first target region. The first target object may be something in the first target area that is fixed for a certain time, such as a natural landscape, a landmark building, a seasonal scene, etc.

302: and sending the first target image to a server side, so that the server side can identify the image content of the first target image, determine the label information corresponding to the first target image, and determine first recommendation information corresponding to the label information.

For determining the first recommendation information, reference may be made to the embodiment shown in fig. 1, which is not described herein again.

303: and acquiring the first recommendation information sent by the server.

304: and outputting the first recommendation information.

In practical application, if a user arrives at a first target area or sees a first target object in the first target area, and wants to acquire related information of the first target area or the first target object, the first target area or the first target object may be subjected to image acquisition by the first user end to obtain a first target image, so that the first target image is sent to a server end, the server end may identify tag information of the first target image, the tag information of the first target image may represent image content, the server end may determine first recommendation information matched with the tag information of the first target image, and the first recommendation information is related information of the first target image, that is, related information of the first target area or the first target object. The server side sends the first recommendation information to the first user side, the first user side outputs the first recommendation information, a user can obtain relevant information of the first target area or the first target object, keyword search and traversal reading search are not needed, useful information can be timely and effectively obtained, and particularly when the user does not know the first target area or the first target object, accurate and effective relevant information can be provided for the user.

Moreover, to further enhance the user experience, in some embodiments, the capturing the first target image comprises:

acquiring a first target image and displaying the first target image on an image acquisition interface;

the outputting the first recommendation information may include:

and displaying the first recommendation information on an image acquisition interface of the first target image.

By displaying the first recommendation information on the image acquisition interface, the display effect of virtual and real combination is realized, and a user can know the related information while appreciating the first target image.

For example, the first target image is obtained by image capturing a certain landmark building, the tag information of the first target image, such as the name of the landmark building, may be identified by the image classification model, and the first recommendation information may be related introduction information of the landmark building, such as the coming calendar, the year of construction, and the like.

For convenience of understanding, as shown in the schematic diagram of fig. 4, the first user terminal performs image acquisition on the landmark building 401, obtains the first target image 402, and displays the first target image in the image acquisition interface 403.

The first user side also sends the first target image 402 to the server side, so that the server side can use the image classification model to identify and obtain the label information of the server side, specifically, the label information is the name of the landmark building. Therefore, the corresponding first recommendation information 404 can be obtained based on the name of the landmark building, and the first recommendation information 404 is sent to the first user terminal.

The first user displays the first recommendation information 404 in the image capturing interface 403, where the first recommendation information 404 may include, for example, related introduction information to the landmark building, and the like, and may also include travel-related products corresponding to the landmark building, such as entrance ticket information, peripheral service organization information, and the like.

In addition, as still another embodiment, the first recommendation information may include travel-related products and purchase prompting information corresponding to the tag information.

Therefore, after the outputting the first recommendation information, the method may further include:

and responding to the purchase operation of the travel related product, and sending a purchase request to the server to complete the purchase operation of the travel related product.

The purchase prompting information may include a transaction control, and the purchase operation may be specifically triggered by operating the transaction control.

In addition, in the prior art, only when a user specifies his or her trip purpose, the user can search by means of keywords to obtain related information, or a large number of irregular readings are required to obtain desired related information, and the information obtained from the network service platform is usually obtained by pre-editing the network service platform, which may greatly differ from a real scene, so that the obtained information may not meet the trip requirement of the user.

Therefore, in order to improve more accurate information for the user, in some embodiments, after the identifying the label information corresponding to the first image by using the image classification model, the method further includes:

generating second recommendation information including at least the first target image; and the second recommendation information is used for being sent to a second user end matched with the label information.

Namely, the first target image actually acquired by the first user end is used as second recommendation information to be sent to the corresponding second user end to be recommended to other users, and the other users can obtain the real image of the real scene instead of the related information after platform beautification or processing, so that effective information can be obtained, and the accuracy of information acquisition is improved.

As shown in fig. 5, an embodiment of the present application further provides an information recommendation method, which may include the following steps:

501: and determining a first target image acquired by the first user side.

502: and identifying the image content of the first target image to determine the label information corresponding to the first target image.

The image classification model is obtained according to sample image training of preset label information.

The training process of the image classification model may refer to the embodiment shown in fig. 2, and is not described herein again.

503: generating second recommendation information including at least the first target image.

And the second recommendation information is used for being sent to a second user end matched with the label information.

In this embodiment, after determining the tag information of a first target image acquired by a first user, second recommendation information at least including the first target image is generated, so that the first target image can be pushed to a second user matched with the tag information of the first target image, and a user corresponding to the second user can view an image of a real scene, thereby ensuring the accuracy and validity of the acquired information.

In some embodiments, after the generating of the second recommendation information including at least the first target image, the method further includes:

receiving a first recommendation request sent by the second user end;

and if the label information of the first target image is matched with the second user side, sending the second recommendation information to the second user side.

The first recommendation request can be generated by the second user end in response to a request recommendation operation triggered by the user.

Optionally, the server may send a recommendation prompting message to the second user end; the second user terminal can respond to the request recommendation operation triggered by the recommendation prompt information to generate the first recommendation request.

As an optional manner, the first recommendation request may include first search information;

at present, the network service platform may provide an information search function, so that the first recommendation request is also a search request, and the first search information may refer to a search keyword.

If the label information of the first target image is matched with the second user side, sending the second recommendation information to the second user side comprises the following steps:

and if the label information of the first target image is matched with the first search information, sending the second recommendation information to the second user terminal.

The matching between the tag information and the first search information may mean that the tag information is the same as the first search information or the similarity exceeds a certain similarity threshold, and the like.

For example, the first user uploads the cherry blossom photos shot in the place a through the first user side, the server side identifies the cherry blossom photos, the tag information of the cherry blossom photos can be determined to be 'cherry blossom', the second user searches 'cherry blossom' through the second user side at the moment, the cherry blossom photos uploaded by the first user side are matched with the search keywords, and then the cherry blossom photos uploaded by the first user side can be sent to the second user side so as to be viewed by the second user side.

As another alternative, after determining the first target image acquired by the first user, the method further includes:

determining the acquisition position of the first target image;

after receiving the first search request sent by the second user terminal, the method further includes:

acquiring second positioning information of the second user terminal;

if the tag information of the first target image is matched with the first search information, sending the second recommendation information to the second user side comprises:

and if the label information of the first target image is matched with the first searching information and the acquisition position of the first target image is matched with the second positioning information, sending the second recommendation information to the second user terminal.

The acquisition position and the label information of the first target image can be stored corresponding to the first recommendation information, so that subsequent searching is facilitated.

The matching between the collection position and the second positioning information may mean that the collection position and the second positioning information belong to the same geographical area, or are separated by a distance within a preset range, or are in the same location area.

The acquisition position of the first target image may be obtained according to the positioning information of the first user, or may be obtained from the acquisition information of the first target image.

For example, the user a uploads the cherry blossom photo shot in the place a through the first user side, that is, the first target image, the server side identifies the first target image, it can be determined that the tag information is "cherry blossom", and the acquisition position is "a" place, at this time, the user B searches for "cherry blossom" through the second user side in the place B, that is, the first search information is the keyword "cherry blossom", it matches with the tag information "cherry blossom" of the first target image, and the location information of the second user side is "B place", the preset range is separated from the place B in the place a, it can be considered that the place a matches with the place B, then the cherry blossom photo uploaded by the first user side can be sent to the second user side, so that the second user side can view the cherry blossom photo.

In addition, the second recommendation information may include not only the first target image, but also travel-related information and the like matching the tag information of the first target image, and thus, in some embodiments, the generating of the second recommendation information including at least the first target image may include:

determining travel related information corresponding to the label information of the first target image;

and generating second recommendation information comprising the first target image and the travel related information.

The travel related information may include, for example, object introduction information representing an object corresponding to the image content by the tag information, or travel related information representing an object corresponding to the image content.

The travel related information may include route recommendation information when the second positioning information reaches the collection position of the first target image, entrance ticket information of the collection position of the first target image, service information such as accommodation or dining, content introduction information corresponding to the tag information of the first target image, and the like.

For example, the first target image is a cherry blossom photo taken in place a, the tag information is "cherry blossom", and the second recommendation information may include the first target image, and may also include cherry blossom related introduction information, such as flowering date, ornamental value, and the like, and may also include ticket information for visiting the cherry blossom in place a, or service information for accommodation or dining and the like in place a.

Fig. 6 is a flowchart of another embodiment of an information recommendation method provided in an embodiment of the present application, where the method may include the following steps:

601: and receiving a second recommendation request sent by a third user end.

602: and determining a second target image of which the label information is matched with the third user side.

The second target image is acquired by a fourth user end; the label information of the second target image can be obtained based on image content identification of the second target image, and specifically, can be obtained based on image classification model identification; and the image classification model is obtained according to sample image training of preset label information.

The training process of the image classification model may refer to the embodiment shown in fig. 2, and will not be repeated herein.

603: determining third recommendation information including at least the second target image.

604: and sending the third recommendation information to the third user terminal.

In this embodiment, after determining the tag information of the second target image acquired by the fourth user, third recommendation information at least including the second target image is generated, so that the second target image can be pushed to a third user matched with the tag information of the second target image, and a user corresponding to the third user can view an image of a real scene, thereby ensuring the accuracy and validity of the information acquired by the third user.

It should be noted that, in the embodiment of the present application, the third client and the fourth client may refer to any client, and the "third" and the "fourth" in the third client and the fourth client are merely for descriptive distinction, which indicates that the third client and the fourth client are two different clients.

The second recommendation request sent by the third user end may be the same as or similar to the first recommendation request sent by the second user end described above, and the "first" and the "second" in the first recommendation request and the second recommendation request are also only for descriptive distinction, and have no difference in nature, and both may refer to a recommendation request sent by any user end.

In addition, the operations of capturing and identifying the second target image may be the same as the operations of capturing and identifying the first target image described above, and the "first" and "second" in the first target image and the second target image are merely for descriptive distinction and do not represent that the two target images have a relationship such as progressive or other association, which may refer to the capturing and obtaining of any user terminal.

The second recommendation request can be generated by a third user end in response to a request recommendation operation triggered by a user.

Optionally, the server may send a recommendation prompt message to the third user end; the third user terminal can respond to the request recommendation operation triggered by the recommendation prompting information to generate the first recommendation request.

As an optional mode, the second recommendation request includes second search information;

the determining the second target image of which the tag information matches the third user side may include:

and determining a second target image of which the label information is matched with the second search information.

The second search information may be a search keyword or the like.

As another alternative, the determining of the second target image whose tag information matches the second search information may include:

acquiring third positioning information of the third user terminal;

and determining label information and the second search information, and acquiring a second target image with the position matched with the third positioning information.

The server can also determine the acquisition position of the second target image, and after the tag information of the second target image is obtained through identification, the tag information and the acquisition position can be stored in correspondence with the second target image.

In addition, the third recommendation information may include not only the second target image, but also travel-related information and the like matching the tag information of the second target image, and thus, in some embodiments, the determining of the third recommendation information including at least the second target image may include:

determining travel related information corresponding to the label information of the second target image;

and generating second recommendation information comprising the second target image and the travel related information.

The travel related information may include route recommendation information when the third positioning information reaches the collection position of the second target image, entrance ticket information of the collection position of the second target image, service information such as accommodation or dining, content introduction information corresponding to the tag information of the second target image, and the like.

In practical application, taking a travel scene for travel as an example, as shown in fig. 7, assuming that a user a 701 arrives at an area where a landmark building 702 is located, the user a performs image acquisition on the landmark building a through the user a by using the user a to the user a 703, obtains an image of the landmark building a, and sends the image to the server 704.

The server 704 recognizes the image of the landmark building a by using the image classification model, and assumes that the image classification model is obtained by training according to the sample image of the preset landmark identifier, so that the tag information of the image of the landmark building a, that is, the corresponding landmark identifier thereof, can be recognized. The server 704 can also determine the positioning information of the a client 703, thereby determining the acquisition position of the image of the landmark building a.

In an application scenario, the server 704 may determine corresponding first recommendation information, such as related introduction information of the landmark building a, entrance ticket information of the landmark building a, or service organization information around the landmark building a, according to tag information of the image of the landmark building a.

The user a 703 may output the first recommendation information, so that the user a 701 can know the landmark building a conveniently, or obtain travel-related information of the landmark building a. Because the first recommendation information is related to the landmark building A currently seen by the user A, the first recommendation information can better meet the user requirements, so that the user A can obtain effective and accurate information.

In another application scenario, the server 704 may further receive recommendation requests sent by other clients, and if the server determines a client matching the tag information of the image of the landmark building a, the server may send second recommendation information at least including the image of the landmark building a to the client.

Assuming that the information matched with the tag information of the image of the landmark building a is the B user 705, the recommendation request initiated by the B user 705 is the B user 706, and the search request initiated when the landmark building a is to be known, at this time, the server 704 can send the second recommendation information including the image of the landmark building a as a search result to the B user 705, the B user 705 outputs the second recommendation information, and the B user can view the real image of the landmark building a instead of the scene image beautified or processed by the platform, so that the B user can obtain effective and accurate information.

Fig. 8 is a schematic structural diagram of an embodiment of an information recommendation device provided in an embodiment of the present application, where the device may include:

a first image determining module 801, configured to determine a first target image acquired by a first user;

optionally, the first image determining module may specifically determine a first target image obtained by the first user terminal performing image acquisition on a first target region where the first user terminal is located or a first target object in the first target region.

A first identifying module 802, configured to identify image content of the first target image to determine tag information corresponding to the first target image.

Optionally, the image content of the first target image may be identified using an image classification model, upon determining the label information of the first target image; the image classification model is obtained according to sample image training of preset label information;

a first information determining module 803, configured to determine first recommendation information corresponding to the tag information of the first target image;

a first information sending module 804, configured to send the first recommendation information to the first user end.

In some embodiments, the apparatus may further comprise:

a first positioning obtaining module, configured to obtain first positioning information of the first user equipment;

the first information determining module is specifically configured to determine first recommendation information corresponding to both the tag information of the first target image and the first positioning information.

In some embodiments, the apparatus may further comprise:

the information generation module is used for generating second recommendation information at least comprising the first target image; and the second recommendation information is used for being sent to a second user end matched with the label information of the first target image.

In some embodiments, the first information determining module may be specifically configured to determine the travel-related information corresponding to the tag information of the first target image.

Optionally, the travel related information includes travel related products and purchase prompting information; accordingly, the apparatus may further comprise:

the transaction triggering module is used for receiving a purchase request sent by the first user end aiming at the travel related product; and processing the purchase request to finish the purchase operation of the travel related products.

In some embodiments, the first information determination module may be specifically configured to obtain a user characteristic; and determining first recommendation information respectively matched with the first target image label information and the user characteristics.

Furthermore, the apparatus may further include:

the model training module is used for acquiring a plurality of sample images;

setting label information of each sample image;

therefore, the first recognition module may be specifically configured to extract an image feature of the first target image;

and identifying and obtaining the label information of the first target image by using the image classification model based on the image characteristics of the first target image.

As an optional manner, the obtaining of the plurality of sample images by the model training module may specifically be obtaining sample images corresponding to different points of interest POI

The setting of the label information of each sample image by the model training module may specifically be setting of the label information of each sample image according to the image content of each sample image.

As another optional mode, the obtaining of the plurality of sample images by the model training module may specifically be obtaining sample images corresponding to different landmark objects;

the setting of the label information of each sample image by the model training module may specifically be setting of the label information of each sample image according to the object identifier of the landmark object corresponding to each sample image.

Furthermore, in some embodiments, the model training module may be further configured to use the first target image as a sample image for training the image classification model.

The information recommendation apparatus shown in fig. 8 may execute the information recommendation method shown in the embodiment shown in fig. 1, and the implementation principle and the technical effect are not repeated. The specific manner in which each module and unit of the information recommendation device in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail herein.

In one possible design, the information recommendation apparatus of the embodiment shown in fig. 8 may be implemented as a server, which may include a storage component 901 and a processing component 902, as shown in fig. 9;

the storage component 901 is one or more computer instructions, wherein the one or more computer instructions are for execution invoked by the processing component 902.

The processing component 902 is configured to:

determining a first target image acquired by a first user side;

and sending the first recommendation information to the first user terminal.

Among other things, the processing component 902 may include one or more processors to execute computer instructions to perform all or some of the steps of the methods described above. Of course, the processing elements may also be implemented as one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components configured to perform the above-described methods.

The storage component 901 is configured to store various types of data to support operations in the server. The memory components may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

Of course, the server may of course also comprise other components, such as input/output interfaces, communication components, etc.

An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a computer, the information recommendation method in the embodiment shown in fig. 1 may be implemented.

Fig. 10 is a schematic structural diagram of another embodiment of an information recommendation device according to an embodiment of the present application, where the information recommendation device may include:

an image acquisition module 1001 for acquiring a first target image;

an image sending module 1002, configured to send the first target image to a server, so that the server identifies image content of the first target image, to determine tag information corresponding to the first target image, and determine first recommendation information corresponding to the tag information;

an information obtaining module 1003, configured to obtain the first recommendation information sent by the server;

an information output module 1004, configured to output the first recommendation information.

In some embodiments, the image capture module may be specifically configured to capture a first target image and display the first target image on an image capture interface;

the information output module may be specifically configured to display the first recommendation information on an image capture interface of the first target image.

In some embodiments, the first recommendation information comprises travel-related products and purchase prompting information;

the apparatus may further include:

and the transaction processing module is used for responding to the purchase operation of the travel related product and sending a purchase request to the server so as to complete the purchase operation of the travel related product.

The information recommendation apparatus shown in fig. 10 may execute the information recommendation method shown in the embodiment shown in fig. 3, and the implementation principle and the technical effect are not repeated. The specific manner in which each module and unit of the information recommendation device in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail herein.

In one possible design, the information recommendation apparatus of the embodiment shown in fig. 10 may be implemented as a terminal, and as shown in fig. 11, the server may include a storage component 1101, a display component 1102, and a processing component 1103;

the storage component 1101 is one or more computer instructions, wherein the one or more computer instructions are for execution invoked by the processing component 1103.

The processing component 1103 is configured to:

collecting a first target image;

acquiring the first recommendation information sent by the server;

the first recommendation information is output via the display component 1102.

The processing component 1103 may include one or more processors executing computer instructions to perform all or part of the steps of the above-described method. Of course, the processing elements may also be implemented as one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components configured to perform the above-described methods.

The storage component 1101 is configured to store various types of data to support operations in the server. The memory components may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The display element 1102 may be an Electroluminescent (EL) element, a liquid crystal display or a microdisplay of similar construction, or a retinal direct display or similar laser scanning type display.

Of course, the terminal may of course also comprise other components, such as input/output interfaces, communication components, etc.

An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a computer, the information recommendation method in the embodiment shown in fig. 3 may be implemented.

Fig. 12 is a schematic structural diagram of another embodiment of an information recommendation device according to an embodiment of the present application, where the device may include:

a second image determining module 1201, configured to determine a first target image acquired by a first user;

a second identifying module 1202, configured to identify image content of the first target image to determine tag information corresponding to the first target image;

a second information determining module 1203, configured to generate second recommendation information including at least the first target image; and the second recommendation information is used for being sent to a second user end matched with the label information of the first target image.

Optionally, the second recognition model may specifically be configured to recognize image content of the first target image by using an image classification model to determine tag information of the first target image; the image classification model is obtained according to sample image training of preset label information.

In some embodiments, the apparatus may further comprise:

the second information sending module is used for receiving a first recommendation request sent by the second user end;

In some embodiments, the first recommendation request includes first search information;

the sending, by the second information sending module, the second recommendation information to the second user end if the tag information of the first target image is matched with the second user end may specifically be:

In some embodiments, the apparatus may further comprise:

the first position determining module is used for determining the acquisition position of the first target image;

a second positioning obtaining module, configured to obtain second positioning information of the second user end;

the sending, by the second information sending module, the second recommendation information to the second user end if the tag information of the first target image matches the first search information may specifically be:

The information recommendation apparatus shown in fig. 12 may execute the information recommendation method shown in the embodiment shown in fig. 5, and the implementation principle and the technical effect are not repeated. The specific manner in which each module and unit of the information recommendation device in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail herein.

In one possible design, the information recommendation apparatus of the embodiment shown in fig. 12 may be implemented as a terminal, as shown in fig. 13, and the server may include a storage component 1301 and a processing component 1302;

the storage component 1301 stores one or more computer instructions; the one or more computer instructions to be invoked for execution by the processing component;

the processing component 1302 is configured to:

determining a first target image acquired by a first user side;

Among other things, the processing component 1302 may include one or more processors executing computer instructions to perform all or some of the steps of the methods described above. Of course, the processing elements may also be implemented as one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components configured to perform the above-described methods.

The storage component 1301 is configured to store various types of data to support operations in the server. The memory components may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a computer, the information recommendation method in the embodiment shown in fig. 5 may be implemented.

Fig. 14 is a schematic structural diagram of another embodiment of an information recommendation device provided in an embodiment of the present application, where the information recommendation device may include:

a request receiving module 1401, configured to receive a second recommendation request sent by a third user;

a third image determining module 1402, configured to determine a second target image with tag information matching the third user side; the second target image is acquired by a fourth user end; the label information of the second target image is obtained based on the image content identification of the second target image; a third information determining module 1403, configured to determine third recommendation information at least including the second target image.

A third information sending module 1404, configured to send the third recommendation information to the third user side.

In some embodiments, the second recommendation request includes second search information;

the third information determining module is specifically configured to determine a second target image of which the tag information matches the second search information.

In some embodiments, the third information determining module may be specifically configured to obtain third positioning information of the third user end; and determining a second target image of which the label information is matched with the second search information and the acquisition position is matched with the third positioning information.

The information recommendation apparatus shown in fig. 14 may execute the information recommendation method shown in the embodiment shown in fig. 6, and the implementation principle and the technical effect are not repeated. The specific manner in which each module and unit of the information recommendation device in the above embodiments perform operations has been described in detail in the embodiments related to the method, and will not be described in detail herein.

In one possible design, the information recommendation apparatus in the embodiment shown in fig. 14 may be implemented as a terminal, as shown in fig. 15, and the server may include a storage component 1501 and a processing component 1502;

the storage component 1501 stores one or more computer instructions; the one or more computer instructions to be invoked for execution by the processing component;

the processing component 1502 is configured to:

receiving a second recommendation request sent by a third user end;

And sending the third recommendation information to the third user terminal.

Among other things, the processing component 1502 may include one or more processors executing computer instructions to perform all or some of the steps of the methods described above. Of course, the processing elements may also be implemented as one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components configured to perform the above-described methods.

The storage component 1501 is configured to store various types of data to support operations in the server. The memory components may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a computer, the information recommendation method in the embodiment shown in fig. 6 may be implemented.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. An information recommendation method, comprising:

determining a first target image acquired by a first user side;

and sending the first recommendation information to the first user terminal.

2. The method of claim 1, wherein the identifying the first target image to determine the tag information corresponding to the first target image comprises:

identifying the image content of the first target image by using an image classification model so as to determine the label information corresponding to the first target image; the image classification model is obtained according to sample image training of preset label information.

3. The method of claim 1, further comprising:

acquiring first positioning information of the first user terminal;

the determining first recommendation information corresponding to the tag information of the first target image includes:

and determining first recommendation information corresponding to the label information and the first positioning information of the first target image.

4. The method of claim 1, wherein after identifying label information for the first target image using the image classification model, the method further comprises:

5. The method of claim 1, wherein the determining first recommendation information corresponding to label information for the first target image comprises:

acquiring user characteristics;

and determining first recommendation information respectively matched with the first target image label information and the user characteristics.

6. The method of claim 1, wherein the determining first recommendation information corresponding to label information for the first target image comprises:

and determining travel related information corresponding to the label information of the first target image.

7. The method of claim 5, wherein the travel-related information comprises travel-related products and purchase prompting information;

after the sending the first recommendation information to the first user end, the method further includes:

8. The method according to claim 2, characterized in that the image classification model is obtained beforehand as follows:

acquiring a plurality of sample images;

setting label information of each sample image;

the identifying the label information of the first target image by using the image classification model comprises:

extracting image features of the first target image;

9. The method of claim 8, wherein the acquiring a plurality of sample images comprises:

acquiring sample images corresponding to different POIs;

the setting of the label information of each sample image includes:

10. The method of claim 8, wherein the acquiring a plurality of sample images comprises:

acquiring sample images corresponding to different landmark objects;

the setting of the label information of each sample image includes:

11. The method of claim 1, wherein determining the target image captured by the first user comprises:

determining a first target image obtained by a first user terminal through image acquisition on a first target area where the first user terminal is located or a first target object in the first target area.

12. The method according to claim 8 or 9, wherein after identifying the target label information corresponding to the first target image by using the image classification model, the method further comprises:

13. An information recommendation method, comprising:

collecting a first target image;

acquiring the first recommendation information sent by the server;

and outputting the first recommendation information.

14. The method of claim 13, wherein said acquiring a first target image comprises:

the outputting the first recommendation information includes:

15. The method of claim 14, wherein the first recommendation information comprises travel-related product and purchase prompting information;

after the outputting the first recommendation information, the method further comprises:

16. An information recommendation method, comprising:

determining a first target image acquired by a first user side;

17. The method of claim 16, wherein the identifying image content of the first target image to determine tag information corresponding to the first target image comprises:

18. The method of claim 16, wherein after generating the second recommendation information including at least the first target image, the method further comprises:

receiving a first recommendation request sent by the second user end;

19. The method of claim 18, wherein the first recommendation request includes first search information;

20. The method of claim 19, wherein after determining the first target image captured by the first user, the method further comprises:

determining the acquisition position of the first target image;

acquiring second positioning information of the second user terminal;

21. An information recommendation method, comprising:

receiving a second recommendation request sent by a third user end;

And sending the third recommendation information to the third user terminal.

22. The method of claim 21, wherein the second recommendation request includes second search information;

the determining the second target image of which the tag information is matched with the third user side comprises:

23. The method of claim 21, wherein the determining a second target image whose tag information matches the second search information comprises:

acquiring third positioning information of the third user terminal;

and determining a second target image of which the label information is matched with the second search information and the acquisition position is matched with the third positioning information.

24. An information recommendation apparatus, comprising:

25. An information recommendation apparatus, comprising:

the image acquisition module is used for acquiring a first target image;

26. An information recommendation apparatus, comprising:

27. An information recommendation apparatus, comprising: