CN113434717A

CN113434717A - Content recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN113434717A
Application number: CN202010199374.6A
Authority: CN
Inventors: 赵安; 于超; 王云路
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2020-03-20
Filing date: 2020-03-20
Publication date: 2021-09-24
Also published as: WO2021185184A1

Abstract

The embodiment of the application provides a content recommendation method, a content recommendation device, electronic equipment and a storage medium, and relates to the field of terminal artificial intelligence, wherein in the method, feature tag mining is carried out on a first target content set to obtain a feature tag and a feature tag type of each target content; classifying the feature labels to obtain a first feature label set; responding to the received second feature tag set, and matching the second feature tag set with the first feature tag set to obtain a third feature tag set; and inquiring the first target content set according to the third characteristic tag set to obtain a second target content set, and recommending and displaying the second target content set, so that a more effective content intelligent recommendation mode is provided, the content sharing efficiency of both parties can be improved, the content sharing accuracy is improved, and the user experience is improved.

Description

Content recommendation method and device, electronic equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of Artificial Intelligence (AI) of terminals, in particular to a content recommendation method, a content recommendation device, an electronic device and a storage medium.

Background

With the popularization of intelligent terminals, people are used to take pictures and share pictures by using cameras on the intelligent terminals; the smart terminal accumulates a large amount of images and videos. Simple picture sharing has not met the social needs of people, so more and more social software is beginning to be designed around picture sharing.

At present, in the face of massive pictures, picture social software generally provides a recommendation function, one is to automatically arrange the pictures of a user and generate a theme album for sharing the pictures; the other is to recommend pictures which are interested by the other party according to the browsing history of the other party; and thirdly, recommending friends to the user according to the similarity of the two picture sets. According to the mode, the current recommendation function only considers one aspect, and the common interests of the sharing parties cannot be combined, so that the recommended content is not required by the sharing parties, and the content sharing efficiency is low.

Disclosure of Invention

The embodiment of the application provides a content recommendation method and device and electronic equipment, and further provides a computer-readable storage medium, so that an efficient content intelligent recommendation mode is provided, feature tags of contents of both sharing parties can be mined, matching is performed according to the feature tags of the contents of both sharing parties, and matched contents are recommended after being screened, so that the content sharing accuracy can be improved, and the user experience is improved.

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

mining the feature labels of the first target content set to obtain the feature labels and the feature label types of each target content; wherein the first set of target content comprises a plurality of target content;

specifically, the first target content may be a picture set, a video set, or a combination set of a picture and a video; mining the feature tags of the first target content set to obtain the feature tags of each picture or each video segment; the feature tag is used to label one or more features of each picture or each video, which may include time, place, people, activities, and the like.

Classifying the feature labels to obtain a first feature label set, wherein the first feature label set comprises one or more feature label types, each feature label type comprises one or more feature labels, and each feature label corresponds to one or more target contents;

specifically, multiple pictures or multiple videos may correspond to the same feature tag, so that all pictures and videos may be clustered, and the pictures or videos belonging to the same feature tag are classified into one feature tag.

Sending a content sharing request, and waiting for receiving a second feature tag set, wherein the second feature tag set comprises one or more feature tag types, and each feature tag type comprises one or more feature tags;

specifically, content sharing may be initiated actively, that is, a content sharing request may be sent, a receiver of the content sharing request is another party to be shared, and after sending the content sharing request, a second feature tag set of the other party may be waited for;

responding to the received second feature label set, and matching the second feature label set with the first feature label set to obtain a third feature label set, wherein the third feature label set comprises one or more feature labels;

in particular, the third feature set may also include one or more feature labels, which may be an intersection of the second feature label set and the first feature label set.

And querying in the first target content set according to the third characteristic label set to obtain a second target content set, and recommending and displaying the second target content set.

Specifically, the second target content set may include a picture, a video, or a combination of a picture and a video, and after the second target content set is obtained, the second target content set may be displayed on a display screen of the mobile terminal.

In the content recommendation method, feature tag mining is performed on the first target content, the mined tag is matched with the feature tag of the receiver, and the target content corresponding to the matched feature tag is recommended, so that a content recommendation mode is provided, the content sharing accuracy can be improved, and the user experience is improved.

In one possible implementation manner, the mining the feature tag of the first target content set to obtain the feature tag and the feature tag type of each target content includes:

performing feature tag mining on the first target content set according to one or more target features to obtain a feature tag and a feature tag type of each target content, wherein each feature tag comprises at least one target feature;

specifically, the target feature may include time, place, person, activity, and the like.

And counting according to the feature tag of each target content to obtain the first recommendation strength of the feature tag.

Specifically, the frequency of occurrence of each feature tag in the first target content set may be counted, for example, each picture or video corresponds to one feature tag, when any feature tag is counted, all pictures and videos including the feature tag may be counted to obtain a statistical number, and then the statistical number is compared with the total number of pictures and videos in the first target content set to calculate a proportion, which is the frequency (first recommendation strength) of the feature tag, so that experience and interest of the user may be counted more accurately.

In one possible implementation manner, after the performing statistics according to the feature tag of each target content and obtaining the first recommendation strength of the feature tag, the method further includes:

and obtaining a second recommendation strength of the feature tag, and calculating according to the second recommendation strength and the first recommendation strength to obtain a third recommendation strength of the feature tag.

Specifically, the popularity of the feature tag, that is, the second recommendation strength, may be obtained, where the second recommendation strength may be given by statistical data in the cloud, for example, the number of all users including the feature tag is counted in the cloud to obtain a statistical number, the statistical number is compared with the number of users, and an Inverse Document Frequency (IDF) value is calculated, where the IDF value is the second recommendation strength, and then the second recommendation strength and the first recommendation strength may be combined and calculated to obtain a third recommendation strength, where the combining calculation may be addition or multiplication, and thus, experience and interest of the users may be more accurately counted.

In one possible implementation manner, the matching the second feature tag set with the first feature tag set to obtain a third feature tag set includes:

matching the second characteristic label set with the first characteristic label set to obtain matched characteristic labels;

and screening the matched feature tags according to the third recommended strength to obtain a third feature tag set.

Specifically, the filtering may be to sort the feature tags according to the third recommendation strength, and then select N feature tags that are ranked first to obtain a third feature tag set, where the N value may be preset. The method comprises the steps of sorting according to different feature tag types, and then screening the first N feature tags under different feature tag types, so that recommended content is simply and clearly displayed, the content recommendation efficiency is improved, and the user experience is improved.

In a possible implementation manner, the querying in the first target content set according to the third feature tag set to obtain a second target content set includes:

and sequentially performing traversal query in the first target content set according to each feature tag in the third feature tag set to obtain all target content corresponding to the feature tag.

In one possible implementation manner, the recommending and displaying the second target content set includes;

classifying and displaying all target contents obtained by query according to the label types;

and adding a corresponding target annotation according to each tag type.

Specifically, the target annotation may be a sentence or a short caption, and the target annotation may correspond to the feature tag type, for example, assuming that the feature tag type is "location", the target annotation may be: "you have all gone" can let the user more directly perceivedly know both sides' common experience and interest from this, promotes user experience.

In one possible implementation manner, after the recommending and displaying the second target content set, the method further includes;

and transmitting the third feature label set.

In one possible implementation manner, after the feature tag mining is performed on the first target content set to obtain a first feature tag set, the method further includes;

and responding to the received content sharing request, and sending the first feature tag set.

In a second aspect, an embodiment of the present application provides a content recommendation apparatus, including:

the mining module is used for mining the feature tags of the first target content set to obtain the feature tags and the feature tag types of each target content; wherein the first set of target content comprises a plurality of target content;

a classification module, configured to classify the feature labels to obtain a first feature label set, where the first feature label set includes one or more feature label types, each feature label type includes one or more feature labels, and each feature label corresponds to one or more target contents;

the request module is used for sending a content sharing request and waiting for receiving a second feature tag set, wherein the second feature tag set comprises one or more feature tag types, and each feature tag type comprises one or more feature tags;

the matching module is used for responding to the received second feature tag set, matching the second feature tag set with the first feature tag set to obtain a third feature tag set, wherein the third feature tag set comprises one or more feature tags;

and the recommending module is used for inquiring in the first target content set according to the third characteristic label set to obtain a second target content set and recommending and displaying the second target content set.

In one possible implementation manner, the mining module includes:

the mining submodule is used for mining the feature tags of the first target content set according to one or more target features to obtain the feature tags and the feature tag types of each target content, wherein each feature tag comprises at least one target feature;

and the counting submodule is used for carrying out statistics according to the characteristic label of each target content to obtain the first recommendation strength of the characteristic label.

In one possible implementation manner, the mining module further includes:

and the enhancement submodule is used for acquiring the second recommended strength of the feature tag, and calculating according to the second recommended strength and the first recommended strength to obtain the third recommended strength of the feature tag.

In one possible implementation manner, the matching module includes:

the matching submodule is used for matching the second characteristic label set with the first characteristic label set to obtain matched characteristic labels;

and the screening submodule is used for screening the matched feature tags according to the third recommended strength to obtain a third feature tag set.

In one possible implementation manner, the recommending module is further configured to perform traversal query in the first target content set according to each feature tag in the third feature tag set in sequence, and obtain all target content corresponding to the feature tag.

In one possible implementation manner, the recommendation module includes:

the classification submodule is used for classifying and displaying all the target contents obtained by inquiry according to the label types;

and the annotation submodule is used for adding corresponding target annotations according to each tag type.

In one possible implementation manner, the apparatus further includes:

and the first sending module is used for sending the third feature tag set.

In one possible implementation manner, the apparatus further includes:

and the second sending module is used for responding to the received content sharing request and sending the first feature tag set.

In a third aspect, an embodiment of the present application provides an electronic device, including:

a display screen; one or more processors; a memory; a plurality of application programs; and one or more computer programs, wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions which, when executed by the apparatus, cause the apparatus to perform the steps of:

and inquiring in the first target content set according to the third characteristic label set to obtain a second target content set, and recommending and displaying the second target content set.

In one possible implementation manner, when executed by the apparatus, the instruction causes the apparatus to perform feature tag mining on a first target content set, and the step of obtaining a feature tag and a feature tag type of each target content includes:

In one possible implementation manner, when executed by the apparatus, the instructions cause the apparatus to perform, after the step of performing statistics according to the feature tag of each target content and obtaining the first recommendation strength of the feature tag, the following steps of:

In one possible implementation manner, when executed by the device, the instruction causes the device to perform matching between the second feature tag set and the first feature tag set, and the step of obtaining a third feature tag set includes:

In one possible implementation manner, when executed by the apparatus, the instructions cause the apparatus to perform a query in the first target content set according to the third feature tag set, and the step of obtaining the second target content set includes:

In one possible implementation manner, the instructions, when executed by the apparatus, cause the apparatus to perform the step of performing recommended display of the second target content set, including:

and adding a corresponding target annotation according to each tag type.

In one possible implementation manner, when executed by the apparatus, the instructions cause the apparatus to perform the following steps after performing the step of recommending and displaying the second target content set:

and transmitting the third feature label set.

In one possible implementation manner, when executed by the apparatus, the instruction causes the apparatus to perform feature tag mining on the first target content set, and after the step of obtaining the first feature tag set, the following steps are further performed:

It should be understood that the second to third aspects of the present application are consistent with the technical solution of the first aspect of the present application, and the beneficial effects obtained by the aspects and the corresponding possible implementation are similar, and are not described again.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon a computer program, which, when run on a computer, causes the computer to perform the method according to the first aspect.

In a fifth aspect, embodiments of the present application provide a computer program, which, when executed by a computer, is configured to perform the method of the first aspect.

In a possible design, the program of the fifth aspect may be stored in whole or in part on a storage medium packaged with the processor, or in part or in whole on a memory not packaged with the processor.

Drawings

FIG. 1 is a flow chart of an embodiment of a content recommendation method of the present application;

FIG. 2 is a schematic view of a first feature tag set of the present application;

FIG. 3A is a flowchart of an embodiment of information interaction between two mobile terminals according to the present application;

FIG. 3B is a flowchart illustrating another embodiment of information interaction between two mobile terminals according to the present application;

FIG. 4 is a schematic diagram of a content recommendation display interface according to the present application;

FIG. 5 is a schematic structural diagram of an embodiment of a content recommendation device according to the present application;

FIG. 6 is a schematic structural diagram of another embodiment of a content recommendation device of the present application;

FIG. 7 is a schematic structural diagram of a content recommendation device according to another embodiment of the present application;

FIG. 8 is a schematic structural diagram of a content recommendation device according to another embodiment of the present application;

FIG. 9 is a schematic diagram of an embodiment of an electronic device of the present application;

fig. 10 is a schematic structural diagram of the system of the present application.

Detailed Description

The terminology used in the description of the embodiments section of the present application is for the purpose of describing particular embodiments of the present application only and is not intended to be limiting of the present application.

In the existing implementation scheme, the picture similarity of the sharing parties is compared or the related content is recommended according to the historical behavior of the user, and the common experience and interest of the sharing parties are not combined, so that the recommended content is irrelevant to the sharing parties, the sharing efficiency is reduced, and the user experience is reduced.

Therefore, the content recommendation method provided by the embodiment of the application can effectively analyze the common experience and interest of both parties, improve the content recommendation efficiency and improve the user experience.

Fig. 1 is a flowchart of an embodiment of a content recommendation method according to the present application, and as shown in fig. 1, the content recommendation method may include:

step 101, performing feature tag mining on the first target content set to obtain a feature tag and a feature tag type of each target content.

Specifically, the target content may be a picture or a video, where the picture or the video may be from a local gallery of the mobile terminal, or the picture and the video of the cloud gallery may be downloaded to the local gallery of the mobile terminal; the first target content set may be all pictures and videos in the mobile terminal, or may be part of the pictures and videos, which is not limited in this embodiment of the present application.

The feature tag mining can be performed on all target contents in the mobile terminal, wherein the feature tag mining can be performed according to target features, and the target features can include time, places, entities, activities, faces and the like; when feature tag mining is performed on any one picture, the picture corresponds to one feature tag, the feature tag at least comprises one target feature, for example, if one picture corresponds to one time, the picture comprises one time feature tag; a picture may also correspond to a time and a place, and the picture contains a composite tag of time + place.

In a specific implementation, time and place can be extracted from metadata in a picture or a video, wherein the time can be a specific day (holiday) extracted according to the shooting time, such as a christmas day, a valentine day and the like, and the time can be null if the time is not a special day such as the holiday; the place can be a symbolic place screened out according to the shooting place, such as West lake, Tiananmen and the like, and if the picture does not contain the symbolic place, the place can be empty; entities and activities can be extracted from pictures and videos through image recognition algorithms, wherein the entities can include any object, such as cats, gourmets and the like, and a plurality of entities can be extracted from one picture; the activity may include any scene, such as riding a horse, attending a wedding, etc., and the activity may first extract the pose of the entity and the person in the picture through a convolutional neural network, and then map the combination of the entity and the pose to the activity or the scene; the human face can be processed by a human face recognition algorithm, and the human face feature vector in the picture or the video can be extracted by the human face recognition algorithm.

After mining the feature tags of all pictures and videos in the mobile terminal, all the pictures and videos will include corresponding feature tag types and feature tags, for example, if one picture includes one cat, the tag type of the picture is an entity, and the feature tag is a cat.

It should be understood that since the number of pictures and videos in the mobile terminal is large, for the same feature tag, the same feature tag may correspond to multiple target objects, that is, multiple target objects belong to the same feature tag, for example, if there are multiple pictures of cats in the mobile terminal, the feature tags of the multiple pictures are all cats.

And 102, classifying the feature labels to obtain a first feature label set.

Specifically, after the feature tag of each picture or video is obtained, the feature tags of the picture or video may be classified, since multiple pictures may correspond to the same feature tag, if each picture is recorded, the calculation amount is too large, and therefore, for pictures belonging to the same feature tag, merging is performed, that is, only the feature tag type and the feature tag are recorded, and finally, a first feature tag set is obtained, as shown in fig. 2, after classification, the first feature tag set includes one or more tag types, each tag type includes one or more feature tags, each feature tag may map one or more pictures or videos, and each picture or video may correspond to different feature tags.

Further, the significance of the feature tag can be calculated to obtain a first recommendation strength, and the first recommendation strength can be used for evaluating the recommendation degree of the picture or the video; in a specific implementation, the frequency of the feature tag may be counted, for example, if the total number of pictures and videos in the mobile terminal is N, and the number of pictures and videos including the feature tag is m, the first recommendation strength of the tag is m/N.

Further, when calculating the degree of saliency of the feature label, the degree of popularity of the feature label may be combined to obtain the second recommendation strength. Since the smaller the population the more prominent the feature tag may be, i.e., the significance of the feature tag may be enhanced, for example, two people who like lizards should be more significant than two people who like dogs, so that the common interests of the two people can be more accurately mined and recommended. In specific implementation, the enhancement factor may be obtained in advance, and the enhancement factor may be obtained by statistics of a large number of users through a cloud, where the statistics may be obtained by calculating Inverse Document Frequency (IDF), and a weighting coefficient may also be configured, that is, the enhancement factor of each tag is reweighed. The embodiments of the present application do not limit this. After the enhancement factor is obtained, the enhancement factor may be multiplied by the first recommended strength, or may be added to the first recommended strength to obtain a second recommended strength, which is not limited in the embodiment of the present application.

Step 103, sending a content sharing request, and waiting for receiving a second feature tag set; and responding to the received second feature label set, and matching the second feature label set with the first feature label set to obtain a third feature label set.

Specifically, if the current mobile terminal desires to share content with the target mobile terminal, a content sharing request may be initiated, where the content sharing request is used to request to receive the second feature tag set; when the target mobile terminal receives the content sharing request, the second feature tag set may be sent to the current mobile terminal according to the request.

It should be understood that, for any mobile terminal, after mining the feature tags of the picture and video of the mobile terminal, a corresponding feature tag set is generated, and therefore, the first feature tag set of the current mobile terminal and the second feature tag set of the target mobile terminal are equivalent concepts, that is, for any mobile terminal, after receiving a sharing request, the first feature tag set of the mobile terminal is sent, and for the receiving party, the receiving party already has the first feature tag set, so that the second feature tag set is received; with reference to fig. 3A and 3B, there are two mobile terminals, namely, a mobile terminal a and a mobile terminal B, respectively, where if the mobile terminal a is an initiator of a content sharing request and the mobile terminal B is a receiver of the content sharing request, the mobile terminal a includes a first feature tag set and receives a second feature tag set from the mobile terminal B; if the mobile terminal B is the initiator of the content sharing request and the mobile terminal a is the receiver of the content sharing request, the mobile terminal B includes the first feature tag set and receives the second feature tag set from the mobile terminal a.

After receiving the second feature tag set, because the second feature tag set includes feature tags as with the first feature tag set, the feature tags in the second feature tag set can be matched with the feature tags in the first feature tag set, so as to obtain a third feature tag set, where the third feature tag set includes matched feature tags.

Optionally, in the matching process, matching may be performed according to the feature tag types between the second feature tag set and the first feature tag set, and after the feature tag types are matched, matching of the feature tag under each feature tag type is performed, so that a matched feature tag is found; the feature labels in the second feature label set and the feature labels in the first feature label set may also be directly matched, that is, an intersection between the second feature label set and the first feature label set is found, so as to find out the matched feature labels.

Furthermore, after the matched feature tags are found, the matched feature tags can be screened, and as many matched feature tags are possible, the matched feature tags can be prioritized first, screened according to the priority, and output, so that the recommendation efficiency is improved; in particular implementations, since each feature tag has a corresponding degree of significance (first recommendation strength or second recommendation strength), the feature tags can be ranked according to the degree of significance.

Optionally, during sorting, the feature tags under each feature tag type may be sorted according to the feature tag types, and the sorted feature tags are extracted, for example, a target value N is set, and the feature tags of N before the ranking are extracted, so that N feature tags under each feature tag type are obtained, which may effectively avoid a large amount of recommended content, avoid causing a large amount of redundant operations, and also improve user experience.

Further, when sorting is performed according to the significance (the first recommendation intensity or the second recommendation intensity) of the feature tags, the sorting may be performed according to the comprehensive significance of the feature tags between the second feature tag set and the first feature tag set, and when the sorting is specifically implemented, a third recommendation intensity may be obtained by adding or multiplying the first recommendation intensity or the second recommendation intensity of the two, and after the third recommendation intensity is obtained, the matched feature tags may be sorted according to the third recommendation intensity; taking a single feature tag as an example, the feature tag a in the first feature tag set is matched with the feature tag B in the second feature tag set, the second recommendation strength of the feature tag a is 40, and the second recommendation strength of the feature tag B is 50, then the third recommendation strength of the feature tag may be 40 × 50; taking the composite label as an example, the composite feature label (a1, a2) in the first feature label set matches with the feature label (B1, B2) in the second feature label set, the second recommended intensity of feature label a1 is 40, the second recommended intensity of feature label a2 is 50, the second recommended intensity of feature label B1 is 20, and the second recommended intensity of feature label B2 is 30, so that the third recommended intensity of the composite feature label may be 40 × 20+50 × 30.

And 104, inquiring in the first target content set according to the third characteristic label set to obtain a second target content set, and recommending and displaying the second target content set.

Specifically, the third feature tag set includes one or more matched feature tags, so that a query can be performed in the first target content set according to the matched feature tags to obtain pictures or videos corresponding to the matched feature tags, that is, the second target content set, and the pictures and videos (the second target content set) are displayed.

Further, in the process of displaying the second target content set, the second target content set may be displayed in a classified manner, so that the user can more clearly know the common interests or experiences of the two sharing parties, the classification manner may be according to the type of the feature tag, or may be in other forms, which is not limited in the embodiment of the present application.

Further, after the second target content set is classified, a note may be added to each classification, which may be preset according to different classifications, for example, a sentence or a short text, and a brief description is performed on the classification, as shown in fig. 4, the final recommended display effect diagram 400 is shown, and the display effect diagram 400 may include target content 410, feature tags 420 and target notes 430.

In the embodiment, matching is performed according to the content feature tags of the sharing parties, and the matched content is selected and recommended, so that a more efficient content recommendation method is provided, the content recommendation efficiency of the sharing parties can be improved, the common experience and interest of the sharing parties can be more accurately extracted, and the user experience is improved.

In one possible implementation manner, after step 104, the method may further include:

and transmitting the third feature label set.

Specifically, the initiator of the current content sharing has already queried the corresponding target content according to the third feature tag set and performed recommendation display, so that the initiator can send the third feature tag set to the receiver of the current sharing request, as shown in fig. 3A, so that the receiver also performs corresponding query to obtain the corresponding target content after receiving the third feature tag set, and performs recommendation display, thereby implementing sharing of the contents of both parties, enhancing understanding of each other, and improving user experience. The final recommendation display effect at the receiving side can also be shown in fig. 4.

Fig. 5 is a schematic structural diagram of an embodiment of a content recommendation device according to the present application, and as shown in fig. 5, the content recommendation device 50 may include: a mining module 51, a classification module 52, a request module 53, a matching module 54 and a recommendation module 55; it should be understood that the content recommendation device 50 may correspond to the electronic apparatus 900 shown in fig. 9.

The mining module 51 is configured to perform feature tag mining on the first target content set to obtain a feature tag and a feature tag type of each target content; wherein the first set of target content comprises a plurality of target content;

a classifying module 52, configured to classify the feature labels to obtain a first feature label set, where the first feature label set includes one or more feature label types, each feature label type includes one or more feature labels, and each feature label corresponds to one or more target contents;

a request module 53, configured to send a content sharing request and wait for receiving a second feature tag set, where the second feature tag set includes one or more feature tag types, and each feature tag type includes one or more feature tags;

a matching module 54, configured to, in response to the received second feature tag set, match the second feature tag set with the first feature tag set to obtain a third feature tag set, where the third feature tag set includes one or more feature tags;

and the recommending module 55 is configured to query the first target content set according to the third feature tag set to obtain a second target content set, and recommend and display the second target content set.

In one possible implementation manner, the mining module 51 may include: a mining submodule 511 and a statistics submodule 512;

a mining submodule 511, configured to perform feature tag mining on the first target content set according to one or more target features, to obtain a feature tag and a feature tag type of each target content, where each feature tag includes at least one target feature;

the statistics submodule 512 is configured to perform statistics according to the feature tag of each target content to obtain a first recommendation strength of the feature tag.

In one possible implementation manner, the mining module 51 may further include: an enhancer module 513;

and the enhancer module 513 is configured to obtain a second recommendation strength of the feature tag, and calculate according to the second recommendation strength and the first recommendation strength to obtain a third recommendation strength of the feature tag.

In one possible implementation manner, the matching module 54 may include: a matching submodule 541 and a screening submodule 542;

a matching submodule 541, configured to match the second feature tag set with the first feature tag set, so as to obtain a matched feature tag;

and the screening submodule 542 is configured to screen the matched feature tags according to the third recommended strength, so as to obtain a third feature tag set.

In one possible implementation manner, the recommending module 55 is further configured to perform traversal query in the first target content set according to each feature tag in the third feature tag set in sequence, so as to obtain all target content corresponding to the feature tag.

The content recommendation device provided in the embodiment shown in fig. 5 may be used to implement the technical solutions of the method embodiments shown in fig. 1 to fig. 4 of the present application, and the implementation principles and technical effects thereof may be further referred to in the related description of the method embodiments.

Fig. 6 is a schematic structural diagram of another embodiment of a content recommendation device of the present application, which is different from the content recommendation device 50 shown in fig. 5 in that, in the content recommendation device 60 shown in fig. 6, a recommendation module 55 may include: a classification sub-module 551 and an annotation sub-module 552;

the classification submodule 551 is configured to classify and display all target contents obtained through query according to the tag types;

the annotation sub-module 552 is configured to add a corresponding target annotation according to each tag type.

The content recommendation device 60 provided in the embodiment shown in fig. 6 may be used to implement the technical solutions of the method embodiments shown in fig. 1 to fig. 4 of the present application, and the implementation principles and technical effects thereof may be further referred to in the related description of the method embodiments.

Fig. 7 is a schematic configuration diagram of another embodiment of a content recommendation device according to the present application, which is different from the content recommendation device 50 shown in fig. 5 in that the content recommendation device 70 shown in fig. 7 may further include: a first transmission module 71;

the first sending module 71 is configured to send the third feature tag set.

The content recommendation device 70 provided in the embodiment shown in fig. 7 may be used to implement the technical solutions of the method embodiments shown in fig. 1 to fig. 4 of the present application, and the implementation principles and technical effects thereof may be further referred to in the related description of the method embodiments.

Fig. 8 is a schematic configuration diagram of another embodiment of a content recommendation device according to the present application, which is different from the content recommendation device 50 shown in fig. 5 in that the content recommendation device 80 shown in fig. 8 may further include: a second transmitting module 81;

the second sending module 81 is configured to send the first feature tag set in response to the received content sharing request.

The content recommendation apparatus 80 provided in the embodiment shown in fig. 8 can be used to implement the technical solutions of the method embodiments shown in fig. 1 to fig. 4 of the present application, and the implementation principles and technical effects thereof can be further referred to the related descriptions in the method embodiments.

It should be understood that the division of the modules of the content recommendation device shown in fig. 5 to 8 is merely a logical division, and the actual implementation may be wholly or partially integrated into one physical entity or physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling by the processing element in software, and part of the modules can be realized in the form of hardware. For example, the detection module may be a separate processing element, or may be integrated into a chip of the electronic device. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.

For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), one or more microprocessors (DSPs), one or more Field Programmable Gate Arrays (FPGAs), etc. For another example, these modules may be integrated together and implemented in the form of a System-On-a-Chip (SOC).

Fig. 9 is a schematic structural diagram of an embodiment of an electronic device of the present application, and as shown in fig. 9, the electronic device may include: a display screen; one or more processors; a memory; a plurality of application programs; and one or more computer programs.

The display screen may include a display screen of a mobile terminal; the electronic equipment can be a mobile terminal (mobile phone), an intelligent screen and the like.

Wherein the one or more computer programs are stored in the memory, the one or more computer programs comprising instructions which, when executed by the apparatus, cause the apparatus to perform the steps of:

In one possible implementation manner, when the instruction is executed by the device, the device performs the following steps after performing the step of performing statistics according to the feature tag of each target content and obtaining the first recommendation strength of the feature tag:

In a possible implementation manner, when executed by the device, the instruction causes the device to perform matching between the second feature tag set and the first feature tag set, and obtain a third feature tag set, where the step includes:

In a possible implementation manner, when executed by the device, the instruction causes the device to perform querying in the first target content set according to the third feature tag set, and the step of obtaining the second target content set includes:

In one possible implementation manner, when executed by the device, the instruction causes the device to perform the step of displaying the second target content set in a recommended manner, where the step includes:

and adding a corresponding target annotation according to each tag type.

In one possible implementation manner, when the instruction is executed by the device, the device performs the following steps after performing the step of recommending and displaying the second target content set:

and transmitting the third feature label set.

In one possible implementation manner, when the instruction is executed by the device, the device performs feature tag mining on the first target content set, and after the step of obtaining the first feature tag set, the following steps are further performed:

The electronic device shown in fig. 9 may be a terminal device or a circuit device built in the terminal device. The apparatus may be used to perform the functions/steps of the methods provided by the embodiments of fig. 1-4 of the present application.

As shown in fig. 9, the electronic device 900 includes a processor 910 and a transceiver 920. Optionally, the electronic device 900 may also include a memory 930. The processor 910, the transceiver 920 and the memory 930 may communicate with each other via internal connection paths to transmit control and/or data signals, the memory 930 may be used for storing a computer program, and the processor 910 may be used for calling and running the computer program from the memory 930.

The memory 930 may be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a Random Access Memory (RAM), or other types of dynamic storage devices that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disc storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, etc.

Optionally, the electronic device 900 may further include an antenna 940 for transmitting and receiving wireless signals output by the transceiver 920.

The processor 910 and the memory 930 may be combined into a single processing device, or more generally, separate components, and the processor 910 is configured to execute the program code stored in the memory 930 to implement the functions described above. In particular implementations, the memory 930 may be integrated with the processor 910 or may be separate from the processor 910.

In addition, to further enhance the functionality of the electronic device 900, the electronic device 900 may further include one or more of an input unit 960, a display unit 970, an audio circuit 980, a camera 990, or the like. The display unit 970 may include a display screen, among others.

Optionally, the electronic device 900 may further include a power supply 950 for supplying power to various devices or circuits in the terminal device.

It should be understood that the electronic device 900 shown in fig. 9 is capable of implementing the processes of the methods provided by the embodiments shown in fig. 1-4 of the present application. The operations and/or functions of the respective modules in the electronic device 900 are respectively for implementing the corresponding flows in the above-described method embodiments. For details, reference may be made to the description of the method embodiment shown in fig. 1 to 4 of the present application, and a detailed description is appropriately omitted herein to avoid redundancy.

It should be understood that the processor 910 in the electronic device 900 shown in fig. 9 may be a system on chip SOC, and the processor 910 may include a Central Processing Unit (CPU), and may further include other types of processors, such as: an image Processing Unit (hereinafter, referred to as GPU), and the like.

In summary, various portions of the processors or processing units within the processor 910 may cooperate to implement the foregoing method flows, and corresponding software programs for the various portions of the processors or processing units may be stored in the memory 930.

The present application further provides an electronic device, where the device includes a storage medium and a central processing unit, the storage medium may be a non-volatile storage medium, a computer executable program is stored in the storage medium, and the central processing unit is connected to the non-volatile storage medium and executes the computer executable program to implement the method provided in the embodiment shown in fig. 1 to fig. 4 of the present application.

Fig. 10 is a schematic diagram of a system architecture 1000 according to an embodiment of the present application. The system architecture is used for realizing the method provided in the above method embodiment.

The processing center 1010 is configured to obtain target content in the storage control center 1020 and mine feature tags of the target content.

The processing center 1010 is further configured to classify the feature labels of the target content to obtain a first feature label set.

In one possible implementation, the processing center 1010 is further configured to calculate a first recommended strength of the feature label.

In one possible implementation, the processing center 1010 is further configured to receive a second recommendation strength of the feature tag from the communication control center 1030.

In one possible implementation manner, the processing center 1010 is further configured to calculate the first recommendation strength and the second recommendation strength to obtain a third recommendation strength.

In one possible implementation manner, the processing center 1010 is further configured to generate a sharing request and instruct the communication control center 1030 to transmit the sharing request.

In one possible implementation manner, the processing center 1010 is further configured to receive a sharing request from the communication control center 1030, and instruct the communication control center 1030 to send the first feature tag set according to the sharing request.

The processing center 1010 is further configured to receive a second set of feature tags from the communications control center 1030.

The processing center 1010 is further configured to obtain a third feature tag set according to matching between the second feature tag set and the first feature tag set.

In one possible implementation, the processing center 1010 is further configured to instruct the communication control center 1030 to transmit the third feature tag set.

The processing center 1010 is further configured to perform a query in the first target content set according to the third feature tag set to obtain a second target content set.

In one possible implementation, the processing center 1010 is further configured to classify the second target content set and add a target annotation.

The processing center 1010 is further configured to instruct the display center 1040 to display the second set of target content.

The storage control center 1020 is used to store the target content.

The storage control center 1020 is further configured to send the target content to the processing center according to the instruction of the processing center 1010, and mine the feature tag of the target content.

The storage control center 1020 is further configured to send the corresponding target content to the display center 1040 for displaying according to the instruction of the processing center 1010.

The communication control center 1030 is configured to send the sharing request generated by the processing center 1010 to other mobile terminals.

In one possible implementation manner, the communication control center 1030 is further configured to receive a sharing request of another mobile terminal.

In one possible implementation, the communication control center 1030 is further configured to transmit the first feature tag set according to an instruction of the processing center 1010.

In one possible implementation, the communication control center 1030 is further configured to transmit a third feature tag set according to the indication of the processing center 1010.

In one possible implementation manner, the communication control center 1030 is further configured to receive a second recommendation strength of the feature tag sent by the server.

In one possible implementation manner, the communication control center 1030 is further configured to receive pictures and videos stored on the server, and send the pictures and videos to the storage control center 1020.

The display center 1040 is used for displaying the target content according to the instruction of the processing center 1010.

In the above embodiments, the processors may include, for example, a CPU, a DSP, a microcontroller, or a digital Signal processor, and may further include a GPU, an embedded Neural Network Processor (NPU), and an Image Signal Processing (ISP), and the processors may further include necessary hardware accelerators or logic Processing hardware circuits, such as an ASIC, or one or more integrated circuits for controlling the execution of the program according to the technical solution of the present application. Further, the processor may have the functionality to operate one or more software programs, which may be stored in the storage medium.

An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is enabled to execute the method provided by the embodiment shown in fig. 1 to 4 of the present application.

Embodiments of the present application further provide a computer program product, which includes a computer program and when the computer program runs on a computer, the computer executes the method provided in the embodiments shown in fig. 1 to 4 of the present application.

In the embodiments of the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" describes the association relationship of the associated objects, and means that there may be three relationships, for example, a and/or B, and may mean that a exists alone, a and B exist simultaneously, and B exists alone. Wherein A and B can be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c may represent: a, b, c, a and b, a and c, b and c or a and b and c, wherein a, b and c can be single or multiple.

Those of ordinary skill in the art will appreciate that the various elements and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

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.

In the several embodiments provided in the present application, any function, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above description is only for the specific embodiments of the present application, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present disclosure, and all the changes or substitutions should be covered by the protection scope of the present application. The protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A content recommendation method, comprising:

2. The method of claim 1, wherein the feature tag mining for the first set of target content to obtain the feature tag and the feature tag type of each target content comprises:

3. The method according to claim 2, wherein after the obtaining the first recommendation strength of the feature tag according to the statistics of the feature tag of each target content, further comprises:

4. The method of claim 3, wherein matching the second set of feature labels with the first set of feature labels to obtain a third set of feature labels comprises:

5. The method of claim 1, wherein the querying in the first target content set according to the third feature tag set to obtain a second target content set comprises:

6. The method of claim 5, wherein said displaying the second set of target content as a recommendation comprises;

and adding a corresponding target annotation according to each tag type.

7. The method of claim 1, further comprising, after said displaying the second set of target content for recommendation;

and transmitting the third feature label set.

8. The method of claim 1, further comprising, after said feature tag mining the first target set of content to obtain a first set of feature tags;

9. A content recommendation apparatus characterized by comprising:

10. The apparatus of claim 9, wherein the excavation module comprises:

11. The apparatus of claim 10, wherein the excavation module further comprises:

12. The apparatus of claim 11, wherein the matching module comprises:

13. The apparatus of claim 9, wherein the recommending module is further configured to perform a traversal query in the first target content set according to each feature tag in the third feature tag set in sequence, and obtain all target content corresponding to the feature tags.

14. The apparatus of claim 13, wherein the recommendation module comprises:

15. The apparatus of claim 9, further comprising:

and the first sending module is used for sending the third feature tag set.

16. The apparatus of claim 9, further comprising:

17. An electronic device, comprising:

18. The electronic device of claim 17, wherein the instructions, when executed by the device, cause the device to perform feature tag mining on a first set of target content, the step of obtaining a feature tag and a feature tag type for each target content comprising:

19. The electronic device of claim 18, wherein the instructions, when executed by the device, cause the device to perform the following steps after the step of obtaining the first recommendation strength of the feature tag by performing statistics according to the feature tag of each target content:

20. The electronic device of claim 19, wherein the instructions, when executed by the device, cause the device to perform matching the second set of feature tags with the first set of feature tags, resulting in a third set of feature tags comprising:

21. The electronic device of claim 17, wherein the instructions, when executed by the device, cause the device to perform the step of querying the first set of target content according to the third set of feature tags, resulting in a second set of target content comprising:

22. The electronic device of claim 21, wherein the instructions, when executed by the device, cause the device to perform the step of displaying the second set of target content as a recommendation comprises:

and adding a corresponding target annotation according to each tag type.

23. The electronic device of claim 17, wherein the instructions, when executed by the device, cause the device to perform the step of displaying the second set of target content as a recommendation, further comprising:

and transmitting the third feature label set.

24. The electronic device of claim 17, wherein the instructions, when executed by the device, cause the device to perform feature tag mining on a first target set of content, the step of obtaining a first set of feature tags being followed by the step of:

25. A computer-readable storage medium, in which a computer program is stored which, when run on a computer, causes the computer to carry out the method according to any one of claims 1 to 8.