CN113987326A

CN113987326A - Resource recommendation method and device, computer equipment and medium

Info

Publication number: CN113987326A
Application number: CN202111623462.5A
Authority: CN
Inventors: 何攀; 高小平; 郑秋野; 徐禄军; 王宗; 尹立岩; 徐佳
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2021-12-28
Filing date: 2021-12-28
Publication date: 2022-01-28
Anticipated expiration: 2041-12-28
Also published as: CN113987326B

Abstract

The disclosure relates to a resource recommendation method, a resource recommendation device, computer equipment and a medium, and belongs to the technical field of internet. In the embodiment of the disclosure, when an object is searched based on a target keyword in an object search page of a multimedia resource, at least one object matched with the target keyword can be triggered and displayed, the information amount displayed by the object search page is increased, and a user can trigger and obtain other objects having corresponding interactive operation behaviors with the matched object through the interactive type control by setting the interactive type control in the object search page.

Description

Resource recommendation method and device, computer equipment and medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a resource recommendation method, apparatus, computer device, and medium.

Background

At present, when recommending multimedia resources to a user, a user to be recommended of the multimedia resources needs to be determined first, and a determination method generally adopted is as follows: and selecting users related to the multimedia resources by service personnel according to experience, determining the selected users as the users to be recommended of the multimedia resources, and recommending the multimedia resources to the users to be recommended.

However, the above process relies on human determination, which reduces the efficiency and accuracy of determining the user to be recommended, and thus reduces the efficiency and accuracy of resource recommendation.

Disclosure of Invention

The present disclosure provides a resource recommendation method, apparatus, computer device, and medium, which improve the efficiency and accuracy of determining an object to be recommended, thereby improving the efficiency and accuracy of resource recommendation. The technical scheme of the present disclosure includes the following.

According to a first aspect of the embodiments of the present disclosure, there is provided a resource recommendation method, including:

in an object search page of a multimedia resource, responding to a search operation on a target keyword, and displaying at least one first object matched with the target keyword, wherein the object search page comprises at least one interaction type control, and the interaction type controls respectively correspond to a type of interaction operation behaviors;

responding to the triggering operation of the at least one interaction type control, and acquiring at least one second object of which the interaction operation behavior corresponding to the at least one first object occurs;

and recommending the multimedia resource based on the at least one first object and the at least one second object.

In the embodiment of the disclosure, when an object is searched based on a target keyword in an object search page of a multimedia resource, at least one object matched with the target keyword can be triggered and displayed, the information amount displayed by the object search page is increased, and a user can trigger and obtain other objects having corresponding interactive operation behaviors with the matched object through the interactive type control by setting the interactive type control in the object search page.

In some embodiments, presenting at least one first object matching a target keyword in response to a search operation for the target keyword comprises:

and responding to the search operation of the target keyword, and displaying at least one first object matched with the target keyword in a first display area of the object search page, wherein the first display area is used for displaying the searched object.

In the embodiment of the disclosure, the at least one first object can be visually displayed by displaying the at least one first object in the first display area, so that a service person can clearly determine that the displayed first object is an object obtained by searching, and the display effect of the first object is improved.

In some embodiments, the method further comprises:

and in response to the selection operation of any one first object in the at least one first object, displaying the selected first object in a second display area of the object search page, wherein the second display area is used for displaying the selected object.

In the embodiment of the disclosure, the selected first object can be visually displayed by displaying the selected first object in the second display area, so that the service personnel can make sure that the displayed first object is the selected object, and the display effect of the selected first object is improved.

In some embodiments, the object search page includes an import control to import at least one object of the multimedia asset determined over a historical period of time;

the method further comprises the following steps:

and importing at least one object of the multimedia resource determined in the historical time period in the object search page based on the importing control.

In the embodiment of the disclosure, by setting the import control, the business personnel can import other objects determined before through the import control by one key without consuming a long time to find the other objects determined before, so that the human-computer interaction efficiency is improved.

In some embodiments, the object search page includes a storage control, where the storage control is configured to store the selected at least one object to an object data package of the multimedia resource, and the object data package is configured to store an object to be recommended for the multimedia resource;

the method further comprises the following steps:

and responding to the triggering operation of the storage control, and storing the selected at least one object to an object data packet of the multimedia resource.

In the embodiment of the disclosure, by setting the storage control, the business personnel can rapidly store the selected object into the object data packet through the storage control, and the packing process is not required to be performed for a long time, so that the human-computer interaction efficiency is improved.

In some embodiments, the interoperation behavior comprises at least one of an attention operation behavior, a publishing resource based interoperation behavior, or a virtual space based interoperation behavior.

In the embodiment of the disclosure, various types of interactive operation behaviors are provided, and the flexibility of determining the object to be recommended is improved.

According to a second aspect of the embodiments of the present disclosure, there is provided a resource recommendation method, including:

responding to a search request for a target keyword, determining at least one first object matched with the target keyword, wherein the search request is triggered based on an object search page of a multimedia resource, the object search page comprises at least one interaction type control, and the interaction type controls respectively correspond to a type of interaction operation behaviors;

in response to an object acquisition request triggered based on the at least one interaction type control, acquiring at least one second object of which the interaction operation behavior corresponding to the at least one first object occurs;

In some embodiments, in response to a search request for a target keyword, determining at least one first object that matches the target keyword comprises any of:

in response to a search request for the target keyword, determining at least one first object matching the target keyword from target relationship data, the target relationship data representing a correspondence between an object and at least one object matching the object;

and responding to the search request of the target keyword, and selecting at least one first object matched with the target keyword from a plurality of candidate objects.

In an alternative implementation manner, the first object can be determined quickly based on the target relationship data, so that the efficiency of determining the first object is improved, and in response to a search request, the first object matched with the target keyword is determined in real time, so that the efficiency of determining the first object is ensured and the storage space is saved.

In some embodiments, selecting at least one first object from the plurality of candidate objects that matches the target keyword comprises:

respectively determining the matching degree of the candidate objects and the target keyword based on the object characteristic information of the candidate objects, wherein the matching degree represents the matching degree between the candidate objects and the target keyword;

and determining the candidate object with the matching degree meeting the matching condition as at least one first object matched with the target keyword.

In the embodiment of the disclosure, the matching degree between each candidate object and the target keyword is determined, and then the first object matched with the target keyword is determined based on the matching degree, so that the efficiency and the accuracy of determining the first object are improved.

In some embodiments, before determining the matching degrees of the candidate objects and the target keyword respectively based on the object feature information of the candidate objects, the method further includes:

and inputting the object information of the plurality of candidate objects into a feature extraction model, and extracting the object feature information of the plurality of candidate objects through the feature extraction model, wherein the feature extraction model is obtained by training based on the object information of the plurality of sample objects and the object feature information of the plurality of sample objects.

In the embodiment of the disclosure, the object feature information of each candidate object is extracted through the feature extraction model, so that the efficiency and the accuracy of extracting the object feature information are improved.

In some embodiments, the obtaining of the plurality of candidate objects comprises:

determining at least one object meeting the attention degree condition based on an object attention list of a plurality of objects, wherein the object attention list is used for recording objects which are concerned by the corresponding objects;

at least one object satisfying the attention degree condition is determined as the plurality of candidate objects.

In the embodiment of the disclosure, the objects meeting the attention degree condition are used as candidate objects, so that the subsequently determined first objects are all the objects meeting the attention degree condition, and then a large number of second objects can be determined based on the first objects, so that the data volume of the determined second objects is increased, and the resource recommendation effect is improved.

In some embodiments, the method further comprises:

and if a third object exists in the plurality of objects, deleting the third object, wherein the number of the objects concerned by the third object reaches a number threshold value.

In the embodiment of the disclosure, the effect of preprocessing the user data is achieved by filtering the users with too wide interests, unnecessary user data processing is avoided, the processing content of the server can be reduced, and the processing efficiency of the server is improved.

According to a third aspect of the embodiments of the present disclosure, there is provided a resource recommendation apparatus, including:

the search unit is configured to execute an object search page of the multimedia resource, respond to a search operation on a target keyword, and display at least one first object matched with the target keyword, wherein the object search page comprises at least one interaction type control, and the interaction type controls respectively correspond to a type of interaction operation behaviors;

the obtaining unit is configured to execute triggering operation responding to the at least one interaction type control, and obtain at least one second object of which the interaction operation behavior corresponding to the at least one first object occurs;

a recommending unit configured to perform recommending the multimedia resource based on the at least one first object and the at least one second object.

In some embodiments, the search unit is configured to perform:

In some embodiments, the apparatus further comprises:

and the showing unit is configured to execute a selection operation responding to any one first object in the at least one first object, and show the selected first object in a second showing area of the object search page, wherein the second showing area is used for showing the selected object.

the device also includes:

and the importing unit is configured to execute importing at least one object of the multimedia resource determined in the historical time period in the object search page based on the importing control.

the device also includes:

and the storage unit is configured to execute triggering operation responding to the storage control and store the selected at least one object to the object data packet of the multimedia resource.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a resource recommendation apparatus, including:

the determining unit is configured to execute a search request responding to a target keyword, determine at least one first object matched with the target keyword, wherein the search request is triggered based on an object search page of the multimedia resource, the object search page comprises at least one interaction type control, and the interaction type controls respectively correspond to a type of interactive operation behaviors;

the obtaining unit is configured to execute, in response to an object obtaining request triggered based on the at least one interaction type control, obtaining at least one second object of which the interaction operation behavior corresponding to the at least one first object occurs;

In some embodiments, the determining unit includes any one of:

a determining subunit configured to perform determining, in response to a search request for the target keyword, at least one first object matching the target keyword from target relationship data representing a correspondence between an object and at least one object matching the object;

and the selecting subunit is configured to execute the step of selecting at least one first object matched with the target keyword from a plurality of candidate objects in response to the search request of the target keyword.

In some embodiments, the selection subunit includes:

a first determining subunit configured to perform determining, based on object feature information of the plurality of candidate objects, matching degrees of the plurality of candidate objects and the target keyword, respectively, the matching degrees indicating degrees of matching between the candidate objects and the target keyword;

and the second determining subunit is configured to execute the candidate object of which the matching degree meets the matching condition, and determine the candidate object as at least one first object matched with the target keyword.

In some embodiments, the apparatus further comprises:

an extraction unit configured to perform inputting the object information of the plurality of candidate objects into a feature extraction model by which object feature information of the plurality of candidate objects is extracted, the feature extraction model being trained based on the object information of the plurality of sample objects and the object feature information of the plurality of sample objects.

In some embodiments, the obtaining unit is further configured to perform:

In some embodiments, the apparatus further comprises:

and the deleting unit is configured to delete a third object if the third object exists in the plurality of objects, wherein the number of the objects concerned by the third object reaches a number threshold value.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer apparatus including:

one or more processors;

a memory for storing the processor executable program code;

wherein the processor is configured to execute the program code to implement the resource recommendation method described above.

According to a sixth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium including: the program code in the computer readable storage medium, when executed by a processor of a computer device, enables the computer device to perform the resource recommendation method described above.

According to a seventh aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the resource recommendation method described above.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a schematic illustration of an implementation environment of a resource recommendation method, according to an example embodiment;

FIG. 2 is a flow diagram illustrating a method for resource recommendation in accordance with an exemplary embodiment;

FIG. 3 is a flow diagram illustrating a method for resource recommendation in accordance with an exemplary embodiment;

FIG. 4 is a flow diagram illustrating a method for resource recommendation in accordance with an exemplary embodiment;

FIG. 5 is a schematic diagram illustrating an object search page in accordance with an illustrative embodiment;

FIG. 6 is a schematic flow diagram illustrating a resource recommendation in accordance with an exemplary embodiment;

FIG. 7 is a block diagram illustrating a resource recommendation device in accordance with an exemplary embodiment;

FIG. 8 is a block diagram illustrating a resource recommendation device in accordance with an exemplary embodiment;

FIG. 9 is a block diagram illustrating a terminal in accordance with an exemplary embodiment;

FIG. 10 is a block diagram illustrating a server in accordance with an example embodiment.

Detailed Description

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

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

The data or information to which the present disclosure relates may be data or information that is authorized by a user or sufficiently authorized by various parties.

Fig. 1 is a schematic diagram of an implementation environment of a resource recommendation method provided in an embodiment of the present disclosure, referring to fig. 1, where the implementation environment includes: a terminal 101 and a server 102.

In some embodiments, the terminal 101 is at least one of a smartphone, a smartwatch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, a laptop portable computer, and the like. The terminal 101 has a communication function and can access a wired network or a wireless network. The terminal 101 may be generally referred to as one of a plurality of terminals, and the embodiment is only illustrated by the terminal 101. Those skilled in the art will appreciate that the number of terminals described above may be greater or fewer.

The terminal 101 is a terminal operated by a service person. In some embodiments, the terminal 101 is associated with a resource management platform, which is capable of managing multimedia resources. Among other things, multimedia assets are used to advertise products or services in a business, such as advertising videos.

In the embodiment of the present disclosure, the terminal 101 is configured to, in an object search page of a multimedia resource, respond to a search operation on a target keyword, present at least one first object matching the target keyword, respond to a trigger operation on at least one interaction type control in the object search page, obtain at least one second object having an interaction behavior corresponding to the at least one first object, and recommend the multimedia resource based on the at least one first object and the at least one second object.

In some embodiments, the server 102 is an independent physical server, or a server cluster or distributed file system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, web services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), big data and artificial intelligence platforms, and the like.

In some embodiments, the server 102 and the terminal 101 are connected directly or indirectly through wired or wireless communication, which is not limited in the embodiments of the present disclosure.

The server 102 is a background server of the resource management platform associated with the terminal 101. In the embodiment of the present disclosure, the server 102 is configured to determine, in response to a search request for a target keyword sent by the terminal 101, at least one first object matching the target keyword to trigger the terminal 101 to display the at least one first object matching the target keyword, obtain, in response to an object obtaining request sent by the terminal 101, at least one second object having an interactive operation behavior corresponding to the at least one first object, and recommend the multimedia resource based on the at least one first object and the at least one second object.

Alternatively, the number of the servers 102 may be more or less, and the embodiment of the disclosure does not limit this. Of course, the server 102 may also include other functional servers to provide more comprehensive and diverse services.

Fig. 2 is a flowchart illustrating a resource recommendation method according to an exemplary embodiment, which is performed by a terminal as shown in fig. 2 and includes the following steps.

In step 201, the terminal responds to a search operation on a target keyword in an object search page of a multimedia resource, and displays at least one first object matched with the target keyword, wherein the object search page comprises at least one interaction type control, and the interaction type controls respectively correspond to a type of interaction operation behaviors.

In step 202, the terminal responds to the triggering operation of the at least one interaction type control, and acquires at least one second object of which the interaction operation behavior corresponding to the at least one first object occurs.

In step 203, the terminal recommends the multimedia resource based on the at least one first object and the at least one second object.

According to the technical scheme provided by the embodiment of the disclosure, when an object is searched in an object search page of a multimedia resource based on a target keyword, at least one object matched with the target keyword can be triggered and displayed, the information amount displayed by the object search page is increased, and the interactive type control is arranged in the object search page, so that a user can trigger and acquire other objects which have corresponding interactive operation behaviors with the matched object through the interactive type control.

In some embodiments, the method further comprises:

the method further comprises the following steps:

FIG. 3 is a flowchart illustrating a resource recommendation method, as shown in FIG. 3, performed by a server, including the following steps, according to an example embodiment.

In step 301, in response to a search request for a target keyword, a server determines at least one first object matching the target keyword, where the search request is triggered based on an object search page of a multimedia resource, and the object search page includes at least one interaction type control, where the interaction type controls respectively correspond to a type of interaction behavior.

In step 302, the server responds to an object acquisition request triggered based on the at least one interaction type control, and acquires at least one second object of which the interaction operation behavior corresponding to the at least one first object occurs.

In step 303, the server recommends the multimedia resource based on the at least one first object and the at least one second object.

In some embodiments, the method further comprises:

Fig. 2 to fig. 3 are only basic flows of the present disclosure, and the solution provided by the present disclosure is further explained below based on a specific implementation, and fig. 4 is a flow chart of a resource recommendation method according to an exemplary embodiment, and referring to fig. 4, the method includes the following steps.

In step 401, the terminal sends a search request for a target keyword to the server in response to a search operation for the target keyword in an object search page of a multimedia resource.

In the disclosed embodiment, the multimedia resources are used for promoting products or services in a certain industry, such as promoting videos. In some embodiments, the multimedia asset is represented with an asset identity. For example, the resource identifier may be a resource name, a resource number, a resource ID (Identity number), and the like.

In some embodiments, the terminal is associated with a resource management platform, and the resource management platform has a function of managing multimedia resources. In some embodiments, the resource management platform is provided with an object search page for searching for objects matching the keyword for a subsequent resource recommendation process based on the searched objects.

Wherein the object refers to a user. The disclosed embodiments subsequently employ the first object to refer to an object that matches the target keyword. In some embodiments, the first object is an object that satisfies a degree of attention condition. The attention degree condition is used for judging whether the attention degree of the object reaches a preset degree. In an alternative embodiment, the attention condition is that the amount of attention reaches an attention amount threshold, for example, the amount of attention reaches 10 ten thousand; or, the attention degree condition is that the object carries a target tag, and the target tag is used for indicating that the attention degree of the corresponding object reaches a preset degree. For example, carrying a "greater than 10 million people focused on" tag. It should be noted that, here, only the attention condition is taken as an example that the amount of attention reaches the number threshold or carries the target tag, and in other embodiments, the attention condition can also be another preset object screening condition, which is not limited in the embodiment of the present disclosure.

In some embodiments, the search request is based on an object search page trigger of the multimedia resource. For example, the object search page includes a keyword search box, a service person inputs a target keyword in the keyword search box, the terminal acquires the input target keyword in response to an input operation in the keyword search box, and sends a search request for the target keyword to the server based on the target keyword to request a search for at least one first object matching the target keyword.

In the embodiment of the disclosure, the target keyword is used for determining an object matched with the target keyword, so as to perform a subsequent resource recommendation process based on the searched object. In some embodiments, the target keywords are keywords that are used to describe objects, illustratively, object categories such as "games, beauty make-up," and the like; in other embodiments, the target keyword is a keyword for uniquely indicating an object, for example, "object name, object account number or object ID", and the like. In the case where the target keyword is a keyword for uniquely indicating an object, the determined at least one first object matching the target keyword includes the object indicated by the target keyword and other objects matching the object.

In step 402, the server determines at least one first object matching a target keyword in response to a search request for the target keyword.

In some embodiments, the process of the server determining the at least one first object includes any one of (402A) and (402B) below.

(402A) In some embodiments, the server determines, in real-time, at least one first object matching the target keyword based on the search request for the target keyword, and the corresponding process is: the server responds to the search request of the target keyword, and selects at least one first object matched with the target keyword from a plurality of candidate objects.

In some embodiments, the server determines matching degrees of the plurality of candidate objects and the target keyword respectively based on the object feature information of the plurality of candidate objects, and determines the candidate object with the matching degree satisfying the matching condition as at least one first object matching the target keyword. Therefore, the matching degree between each candidate object and the target keyword is determined, and the first object matched with the target keyword is determined based on the matching degree, so that the efficiency and the accuracy of determining the first object are improved.

The matching degree represents a matching degree between the candidate object and the target keyword, and specifically, the matching degree represents a similarity degree between object feature information of each candidate object and keyword feature information of the target keyword. The object feature information is used for representing object features of the candidate objects, and the keyword feature information is used for representing word features of the target keywords. In some embodiments, the object feature information and the keyword feature information are both in the form of feature vectors (embedding). Illustratively, the object feature information is a 32-dimensional vector. In some embodiments, the degree of match is expressed in terms of the distance between feature vectors. For example, the distance may be any one of a cosine distance, an euclidean distance, a manhattan distance, a chebyshev distance, a chi-square distance, or a hamming distance, and the embodiment of the present disclosure does not limit which distance is selected to calculate the matching degree. It should be understood that the smaller the distance, the greater the degree of matching, and the larger the distance, the lesser the degree of matching.

In an optional implementation manner, the terminal calculates a distance between the object feature information of each candidate object and the keyword feature information based on the object feature information of the candidate objects and the keyword feature information of the target keyword, and determines the distance as a matching degree between the object feature information of the candidate objects and the keyword feature information.

The matching condition is used for judging whether the candidate objects are matched with the target keywords or not. In some embodiments, the matching condition is that the matching degree is greater than or equal to a threshold matching degree, which is a predetermined threshold, such as 80. Accordingly, (402A) may be replaced by: the server responds to the search request of the target keyword, and selects at least one first object with the matching degree larger than or equal to the threshold value of the matching degree from the candidate objects. In other embodiments, the matching condition is that the arrangement order of the matching degrees is located in the previous target digit number, and the target digit number is a preset fixed digit number, such as the previous 10 digits. Accordingly, (402A) may be replaced by: the server responds to the search request of the target keyword, and selects at least one first object with the arrangement order of the matching degree positioned in the front target digit from the plurality of candidate objects.

In the embodiment of the present disclosure, the plurality of candidate objects are a plurality of objects satisfying the attention condition. In some embodiments, the server determines the plurality of candidate objects based on a plurality of common objects, that is, a plurality of common users (for example, an object that does not satisfy the attention degree condition, and is subsequently referred to as a plurality of objects), and the corresponding process is: the server determines at least one object meeting the attention degree condition based on the object attention list of the plurality of objects, and determines the at least one object meeting the attention degree condition as the plurality of candidate objects.

Wherein the object attention list is used for recording the objects which the corresponding objects pay attention to. In some embodiments, the server obtains an object attention list of the plurality of objects from the user representation of the plurality of objects, and determines the plurality of candidate objects from the object attention list of the plurality of objects. Wherein the user representation is used to describe attribute information or behavior information of the object. In some embodiments, the user representation is provided in the form of a user representation table.

In some embodiments, if a third object exists in the plurality of objects, the third object is deleted, and the number of objects concerned by the third object reaches a number threshold. Wherein the number threshold is a predetermined fixed number, such as 500 or 1000.

Illustratively, the number of the plurality of objects is 2000 thousands, taking the object as an ordinary user as an example, and taking the candidate object as a user meeting the attention degree condition as an example, the user meeting the attention degree condition, which is concerned by the 2000 thousands of ordinary users, is randomly selected as the candidate object, so that by selecting a certain amount of user data, on the premise of ensuring that the data volume is sufficient, the processing content of the server can be reduced, thereby improving the processing efficiency of the server; meanwhile, taking the number threshold value as 500 as an example, common users with the concerned number reaching 500 are filtered, so that the filtering of users with too wide interest is realized, the effect of preprocessing the user data is achieved, unnecessary user data is avoided being processed, the processing content of the server can be reduced, and the processing efficiency of the server is improved.

In the above embodiment, the objects meeting the attention degree condition are used as candidate objects, so that the subsequently determined first objects are all the objects meeting the attention degree condition, and further a large number of second objects can be determined based on the first objects, so that the data size of the determined second objects is increased, and the resource recommendation effect is improved.

In some embodiments, the server employs a feature extraction model to extract object feature information of the plurality of candidate objects, and the corresponding process is: the server inputs the object information of the candidate objects into a characteristic extraction model, and extracts the object characteristic information of the candidate objects through the characteristic extraction model. Therefore, the object characteristic information of each candidate object is extracted through the characteristic extraction model, and the efficiency and the accuracy of extracting the object characteristic information are improved.

Wherein the object information is attribute information, behavior information, and the like of a plurality of candidate objects. In the embodiment of the present disclosure, the feature extraction model is used to extract object feature information of a plurality of candidate objects. The feature extraction model is a trained model, and in some embodiments, the feature extraction model is trained based on object information of a plurality of sample objects and object feature information of the plurality of sample objects.

In some embodiments, the server obtains object information of a plurality of sample objects and object feature information of the plurality of sample objects, and performs model training based on the object information of the plurality of sample objects and the object feature information of the plurality of sample objects to obtain the feature extraction model. Specifically, the training process of the feature extraction model comprises the following steps: in the first iteration process, respectively inputting the object information of the plurality of sample objects into an initial model to obtain a feature training result of the first iteration process; determining a loss function based on the feature training result of the first iteration process and the object feature information of the corresponding sample object, and adjusting model parameters in the initial model based on the loss function; taking the model parameters after the first iteration adjustment as model parameters of the second iteration, and then carrying out the second iteration; and repeating the iteration process for a plurality of times, in the Nth process, taking the model parameters after the N-1 th iteration adjustment as new model parameters, carrying out model training until the training meets the target conditions, and acquiring the model corresponding to the iteration process meeting the target conditions as a feature extraction model.

Wherein N is a positive integer and is greater than 1. In some embodiments, the initial model is model-trained using a target recommendation algorithm to train the feature extraction model. Optionally, the target recommendation algorithm is an item2vec algorithm. In some embodiments, the window parameter of the feature extraction model is 100. In some embodiments, the training satisfies a target condition that the number of training iterations of the initial model reaches a target number, which is a preset number of training iterations; alternatively, the training satisfies a target condition that the loss value satisfies a target threshold condition, such as a loss value less than 0.00001. The embodiments of the present disclosure do not limit the setting of the target conditions.

In the embodiment, when the first object matched with the target keyword is determined in real time in response to the search request, the efficiency of determining the first object is ensured, and meanwhile, the storage space is saved.

(402B) In some embodiments, the server determines, from the target relationship data, at least one first object matching the target keyword in response to a search request for the target keyword.

Wherein the target relationship data represents a correspondence between the object and at least one object matching the object. The object included in the target relationship data is an object that satisfies the attention degree condition.

In some embodiments, the server generates the target relationship data based on object feature information of a plurality of candidate objects before executing the present scheme, and the corresponding process is described in (1) to (4) below.

(1) The server acquires object information of the plurality of candidate objects.

In some embodiments, the server determines at least one object satisfying the attention condition based on an object attention list of the plurality of objects, determines the at least one object satisfying the attention condition as the plurality of candidate objects, and acquires object information of the plurality of candidate objects.

It should be noted that, for the determination process of the multiple candidate objects, reference is made to the content of (402A) above, and details are not repeated.

(2) The server determines object feature information of the plurality of candidate objects based on the object information of the plurality of candidate objects.

In some embodiments, the server employs a feature extraction model to extract object feature information of the plurality of candidate objects, and the corresponding process is: the server inputs the object information of the candidate objects into a characteristic extraction model, and extracts the object characteristic information of the candidate objects through the characteristic extraction model.

In some embodiments, after determining the object feature information of the plurality of candidate objects, the server generates a feature text set based on the object feature information of the plurality of candidate objects, wherein the feature text set includes the object feature information of the plurality of candidate objects.

It should be noted that, for the relevant content of the feature extraction model, reference is made to the content of (402A) above, and details are not repeated.

(3) The server determines the matching degree between any two candidate objects based on the object feature information of the plurality of candidate objects.

The matching degree between any two candidate objects represents the matching degree between any two candidate objects, and specifically, the matching degree between any two candidate objects represents the similarity degree between the object feature information of any two candidate objects. In some embodiments, the degree of match is expressed in terms of the distance between feature vectors. For example, the distance may be any one of a cosine distance, an euclidean distance, a manhattan distance, a chebyshev distance, a chi-square distance, or a hamming distance, and the embodiment of the present disclosure does not limit which distance is selected to calculate the matching degree. It should be understood that the smaller the distance, the greater the degree of matching, and the larger the distance, the lesser the degree of matching.

In some embodiments, the terminal calculates a distance between the object feature information of any two candidate objects based on the object feature information of any two candidate objects, and determines the distance as a matching degree between the object feature information of any two candidate objects.

In some embodiments, the server is associated with an ANN (Artificial Neural Network) similarity calculation interface, and the above process of determining the matching degree between any two candidate objects is performed through the ANN similarity calculation interface.

(4) The server generates the target relationship data based on each candidate object and at least one candidate object matched with each candidate object.

In some embodiments, any two candidate objects match if the matching degree between the two candidate objects satisfies the matching condition. The matching condition is used for judging whether any two candidate objects are matched or not. In some embodiments, the matching condition is that the matching degree is greater than or equal to a threshold matching degree, which is a predetermined threshold, such as 80. Accordingly, the process may be replaced with: and if the matching degree between any two candidate objects is greater than or equal to the threshold value of the matching degree, matching the any two candidate objects. In other embodiments, the matching condition is that the arrangement order of the matching degrees is located in the previous target digit number, and the target digit number is a preset fixed digit number, such as the previous 10 digits. Accordingly, the process may be replaced with: and if the arrangement sequence of the matching degrees between any two candidate objects is positioned at the front target digit, matching the any two candidate objects.

In some embodiments, after the server generates the target relationship data, the target relationship data is stored to a matching information database associated with the server. In an optional embodiment, the server imports the matching degree corresponding to each object into the matching information database based on the relationship data between the objects included in the target relationship data. In an alternative embodiment, the server updates the target relationship data stored in the matching information database every target time duration. Wherein, the target time length is a preset fixed time length, such as 1 day.

In the above embodiment, by setting the target relationship data in advance, the first object can be determined quickly based on the target relationship data, and the efficiency of determining the first object is improved.

In step 403, the server transmits at least one first object matching the target keyword to the terminal.

In step 404, the terminal receives at least one first object matching the target keyword, and displays the at least one first object matching the target keyword.

In some embodiments, the terminal presents at least one first object matched with the target keyword in a first presentation area of the object search page, and the first presentation area is used for presenting searched objects.

The first display area is a search result display area. Illustratively, fig. 5 is a schematic diagram of an object search page shown according to an exemplary embodiment, referring to fig. 5, in the object search page shown in fig. 5, a first display area is an "area 501" shown in fig. 5, and in the "area 501", at least one first object matching the target keyword is displayed. In some embodiments, in the case that the target keyword is a keyword for uniquely indicating an object, the determined at least one first object matching the target keyword includes the object indicated by the target keyword and other objects matching the object, and accordingly, the terminal displays the object indicated by the target keyword in a first display area of an object search page, and displays the other objects matching the object in response to a trigger operation on the object indicated by the target keyword. For example, referring to fig. 5, the object search page shown in fig. 5 is a page displayed after triggering the object indicated by the target keyword. The object indicated by the target keyword is also user 1, and the other objects matched with the object are also user 2, user 3, user 4, user 5, and the like.

In the above embodiment, by displaying the at least one first object in the first display area, the at least one first object can be visually displayed, so that the service person can clearly determine that the displayed first object is the searched object, and the display effect of the first object is improved.

In some embodiments, the terminal responds to the selection operation of any one of the at least one first object, displays the selected first object in a second display area of the object search page, and the second display area is used for displaying the selected object.

Wherein the second display area is a selected result display area. Illustratively, referring to fig. 5, in the object search page shown in fig. 5, the second presentation area is an "area 502" shown in fig. 5, and in the "area 502", the selected first object, such as the user 5, is presented.

In the above embodiment, the selected first object can be visually displayed by displaying the selected first object in the second display area, so that the service person can make sure that the displayed first object is the selected object, and the display effect of the selected first object is improved.

In step 405, the terminal sends an object acquisition request to the server in response to a trigger operation on at least one interactive type control in the object search page.

In some embodiments, the object search page includes at least one interaction type control, the interaction type controls respectively corresponding to a class of interaction behavior. In some embodiments, the interoperation behavior comprises at least one of an attention operation behavior, a publishing resource based interoperation behavior, or a virtual space based interoperation behavior. The publishing resource refers to a multimedia resource that an object has published, such as a published video, and accordingly, the interactive operation behavior based on the publishing resource may be a praise operation behavior, a comment operation behavior, a share operation behavior, a collection operation behavior, and the like for the video. The virtual space refers to a live broadcast room, and accordingly, the interactive operation behavior based on the virtual space can be an access operation behavior to the live broadcast room, an operation behavior of presenting a virtual gift in the live broadcast room, an operation behavior of purchasing a commodity in the live broadcast room, and the like. Therefore, various types of interactive operation behaviors are provided, and the flexibility of determining the object to be recommended is improved.

Illustratively, referring to fig. 5, in the object search page shown in fig. 5, the at least one interaction type control is a "focus control", a "video interaction control", and a "live interaction control", respectively.

The object obtaining request is used for requesting to obtain at least one second object of the interactive operation behavior corresponding to the at least one first object. The disclosed embodiments subsequently employ the second object to refer to the object that has interacted with the first object. Taking the example that the interactive operation behavior is the operation behavior of interest, the object obtaining request is used for requesting to obtain at least one second object which has the operation behavior of interest with the at least one first object. Illustratively, the second object may be an object that focuses on the first object. Taking the example that the interactive operation behavior is the interactive operation behavior based on the published resource, the object obtaining request is used for requesting to obtain at least one second object which has the interactive operation behavior based on the published resource with the at least one first object. Illustratively, the second object may be an object that favorites the publishing resource of the first object. Taking the example that the interactive operation behavior is the interactive operation behavior based on the virtual space, the object obtaining request is used for requesting to obtain at least one second object which has the interactive operation behavior based on the virtual space with the at least one first object. Illustratively, the second object may be an object that has purchased goods within a live room of the first object. It should be understood that the second object may be a normal user, i.e. a user that does not satisfy the attention condition.

In step 406, the server, in response to the object obtaining request triggered based on the at least one interaction type control, obtains at least one second object having an interaction behavior corresponding to the at least one first object.

In some embodiments, the process of the server obtaining the at least one second object comprises at least one of the following.

(406A) In some embodiments, taking the triggered interaction type control as a "focus control", and taking the interaction operation behavior as a focus operation behavior as an example, the process of the server acquiring the at least one second object is as follows: the server acquires at least one second object which has performed operation behavior of interest with the at least one first object.

(406B) In some embodiments, taking the triggered interaction type control as a "video interaction control", and taking the interaction operation behavior based on the publishing resource as an example, the process of the server acquiring the at least one second object is as follows: the server acquires at least one second object which has interacted with the at least one first object based on the publishing resource.

(406C) In some embodiments, taking the triggered interaction type control as a "live interaction control", and taking the interaction operation behavior based on the virtual space as an example, the process of the server acquiring the at least one second object is as follows: the server acquires at least one second object which has interacted with the at least one first object based on the virtual space.

In the above steps 405 to 406, based on the triggered interaction type control, the server is requested to obtain a second object having a corresponding interaction operation behavior with the first object. In some embodiments, the terminal responds to the triggering operation of one, two or three of the at least one interaction type control, and requests the server to acquire a second object which has undergone a corresponding interaction operation behavior with the first object. Illustratively, taking the triggered interaction type controls as a "focus control" and a "video interaction control" as examples, the process of the server acquiring the at least one second object is as follows: the server acquires an object which has an operation behavior related to the at least one first object, acquires an object which has an interaction behavior based on the publishing resource and has occurred with the at least one first object, and determines the acquired object as the at least one second object. Exemplarily, taking the triggered interaction type controls as a "focus control", a "video interaction control", and a "live interaction control" as examples, the process of the server acquiring the at least one second object is as follows: the server acquires an object which has performed attention operation behavior with the at least one first object, an object which has performed issue resource-based interactive operation behavior with the at least one first object, and an object which has performed virtual space-based interactive operation behavior with the at least one first object, and determines the acquired object as the at least one second object. In this way, the flexibility of determining the second object is improved.

In the above steps 404 to 406, the process of requesting the server to obtain the at least one second object having the interactive operation behavior corresponding to the at least one first object based on the at least one first object displayed by the terminal, that is, in the case that the at least one first object is selected, the process of requesting the server to obtain the at least one second object having the interactive operation behavior corresponding to the at least one first object is performed. In other embodiments, after executing step 404, the terminal, in response to the selection operation of any one of the at least one first object, executes a process of sending an object acquisition request based on the interaction type control in step 405 based on the selected first object, so as to request the server to acquire at least one second object having an interaction operation behavior corresponding to the selected first object. In this way, the flexibility of determining the second object is improved.

In step 407, the server recommends the multimedia resource based on the at least one first object and the at least one second object.

In some embodiments, the object search page includes a resource recommendation control, the service person may select an object to be recommended, based on the selected object to be recommended, a trigger operation is performed on the resource recommendation control in the object search page, and then the terminal recommends the multimedia resource to the selected object to be recommended in response to the trigger operation on the resource recommendation control.

For example, taking a scene of searching a certain user as an example, when a service person searches the user in the object search page, the service person may trigger to show a target number of other users matching the user, for example, show 10 other users matching the user, and then the service person may determine the user who has performed a critical operation behavior, a video interaction operation behavior, or a live interaction operation behavior with the users, and perform resource recommendation based on the determined user.

In some embodiments, the object search page includes an import control for importing at least one object of the multimedia asset determined during a historical period of time, and accordingly, the method further includes: and the terminal imports at least one object of the multimedia resource determined in the historical time period in the object search page based on the import control.

In an alternative embodiment, the import control is used to import at least one first object of the multimedia asset determined in the historical time period, or the import control is used to import at least one second object of the multimedia asset determined in the historical time period, or the import control is used to import at least one first object and at least one corresponding second object of the multimedia asset determined in the historical time period.

For example, referring to fig. 5, in the object search page shown in fig. 5, the import control may be the "batch import control" shown in fig. 5. In an optional embodiment, the terminal responds to the triggering operation of the import control, presents at least one object of the multimedia resource determined in the historical time period, and responds to the selection operation of any object in the at least one object to import the selected object in the object search page.

Therefore, by setting the import control, business personnel can import other objects determined before through the import control by one key without consuming longer time to search the other objects determined before, and the man-machine interaction efficiency is improved.

In some embodiments, the object search page includes a storage control, the storage control is configured to store the selected at least one object to an object data package of the multimedia resource, the object data package is configured to store an object to be recommended for the multimedia resource, and accordingly, the method further includes: and the terminal responds to the triggering operation of the storage control and stores the selected at least one object to the object data packet of the multimedia resource.

In an optional embodiment, the storage control is configured to store the selected at least one first object to the object data package of the multimedia resource, or store the selected at least one second object to the object data package of the multimedia resource, or store the selected at least one first object and the corresponding at least one second object to the object data package of the multimedia resource.

For example, referring to fig. 5, in the object search page illustrated in fig. 5, the storage control may be the "generate package control" illustrated in fig. 5.

Therefore, by arranging the storage control, business personnel can quickly store the selected object into the object data packet through the storage control, the packaging process is not required to be carried out for a long time, and the human-computer interaction efficiency is improved.

Exemplarily, fig. 6 is a schematic flow diagram illustrating resource recommendation according to an exemplary embodiment, and referring to fig. 6, the resource recommendation method provided by the embodiment of the present disclosure is provided with four processing modules, which are a data preprocessing module, a feature extraction module, a similarity calculation module and a recommendation result presentation module, respectively, where the data preprocessing module is configured to obtain an attention list of a user, and obtain a certain amount of user information from the attention list, for example, the user information is attribute information and behavior information of the user meeting an attention condition; the feature extraction module is used for carrying out model training by using a target recommendation algorithm to obtain a feature extraction model, and further extracting feature vectors of all users through the feature extraction model; the similarity calculation module is used for calculating the similarity between any two users based on the feature vectors of the users and correspondingly storing the users and the first 10 similar users of the users; and the recommendation result display module is used for displaying the top 10 similar users of any user while displaying the user based on the search operation of the user. Therefore, according to the attention list of the users, the recommendation method of the similar users is realized by using the target recommendation algorithm, the service personnel can be helped to accurately orient the user groups of the similar users, and accurate recommendation between the oriented groups and the media resources is realized.

FIG. 7 is a block diagram illustrating a resource recommendation device according to an example embodiment. Referring to fig. 7, the apparatus includes a search unit 701, an acquisition unit 702, and a recommendation unit 703:

a search unit 701 configured to execute, in an object search page of a multimedia resource, in response to a search operation on a target keyword, presenting at least one first object matching the target keyword, where the object search page includes at least one interaction type control, and the interaction type controls respectively correspond to a type of interaction operation behavior;

an obtaining unit 702, configured to perform, in response to a triggering operation on the at least one interaction type control, obtaining at least one second object for which an interaction operation behavior corresponding to the at least one first object has occurred;

a recommending unit 703 configured to perform recommending the multimedia resource based on the at least one first object and the at least one second object.

In some embodiments, the searching unit 701 is configured to perform:

In some embodiments, the apparatus further comprises:

the device also includes:

FIG. 8 is a block diagram illustrating a resource recommendation device in accordance with an example embodiment. Referring to fig. 8, the apparatus includes a determination unit 801, an acquisition unit 802, and a recommendation unit 803:

a determining unit 801 configured to perform determining, in response to a search request for a target keyword, at least one first object matching the target keyword, where the search request is triggered based on an object search page of a multimedia resource, and the object search page includes at least one interaction type control, where the interaction type controls respectively correspond to a type of interactive operation behavior;

an obtaining unit 802 configured to perform, in response to an object obtaining request triggered based on the at least one interaction type control, obtaining at least one second object having an interaction operation behavior corresponding to the at least one first object;

a recommending unit 803 configured to perform recommending the multimedia resource based on the at least one first object and the at least one second object.

In some embodiments, the determining unit 801 includes any one of:

In some embodiments, the selection subunit includes:

In some embodiments, the apparatus further comprises:

In some embodiments, the obtaining unit 802 is further configured to perform:

In some embodiments, the apparatus further comprises:

It should be noted that: in the resource recommendation apparatus provided in the foregoing embodiment, only the division of the functional modules is illustrated in the foregoing description, and in practical applications, the function allocation may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the resource recommendation device and the resource recommendation method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.

The computer device mentioned in the embodiments of the present disclosure may be provided as a terminal. Fig. 9 shows a block diagram of a terminal 900 according to an exemplary embodiment of the disclosure. The terminal 900 may be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, motion video Experts compression standard Audio Layer 3), an MP4 player (Moving Picture Experts Group Audio Layer IV, motion video Experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. Terminal 900 may also be referred to by other names such as user equipment, portable terminals, laptop terminals, desktop terminals, and the like.

In general, terminal 900 includes: a processor 901 and a memory 902.

Processor 901 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 901 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 901 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 901 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed by the display screen. In some embodiments, the processor 901 may further include an AI (Artificial Intelligence) processor for processing computing operations related to machine learning.

Memory 902 may include one or more computer-readable storage media, which may be non-transitory. The memory 902 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer readable storage medium in the memory 902 is used for storing at least one program code, which is used for being executed by the processor 901 to implement the processes executed by the terminal in the resource recommendation method provided by the method embodiments in the present disclosure.

In some embodiments, terminal 900 can also optionally include: a peripheral interface 903 and at least one peripheral. The processor 901, memory 902, and peripheral interface 903 may be connected by buses or signal lines. Various peripheral devices may be connected to the peripheral interface 903 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 904, a display screen 905, a camera assembly 906, an audio circuit 907, a positioning assembly 908, and a power supply 909.

The peripheral interface 903 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 901 and the memory 902. In some embodiments, the processor 901, memory 902, and peripheral interface 903 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 901, the memory 902 and the peripheral interface 903 may be implemented on a separate chip or circuit board, which is not limited by this embodiment.

The Radio Frequency circuit 904 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 904 communicates with communication networks and other communication devices via electromagnetic signals. The radio frequency circuit 904 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 904 comprises: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 904 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the radio frequency circuit 904 may also include NFC (Near Field Communication) related circuits, which are not limited by this disclosure.

The display screen 905 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 905 is a touch display screen, the display screen 905 also has the ability to capture touch signals on or over the surface of the display screen 905. The touch signal may be input to the processor 901 as a control signal for processing. At this point, the display 905 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, the display 905 may be one, disposed on the front panel of the terminal 900; in other embodiments, the number of the display panels 905 may be at least two, and each of the display panels is disposed on a different surface of the terminal 900 or is in a foldable design; in other embodiments, the display 905 may be a flexible display disposed on a curved surface or a folded surface of the terminal 900. Even more, the display screen 905 may be arranged in a non-rectangular irregular figure, i.e. a shaped screen. The Display panel 905 can be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and other materials.

The camera assembly 906 is used to capture images or video. Optionally, camera assembly 906 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 906 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

Audio circuit 907 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 901 for processing, or inputting the electric signals to the radio frequency circuit 904 for realizing voice communication. For stereo sound acquisition or noise reduction purposes, the microphones may be multiple and disposed at different locations of the terminal 900. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 901 or the radio frequency circuit 904 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, audio circuit 907 may also include a headphone jack.

The positioning component 908 is used to locate the current geographic Location of the terminal 900 for navigation or LBS (Location Based Service). The Positioning component 908 may be a Positioning component based on the GPS (Global Positioning System) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the european union.

Power supply 909 is used to provide power to the various components in terminal 900. The power source 909 may be alternating current, direct current, disposable or rechargeable. When power source 909 comprises a rechargeable battery, the rechargeable battery may support wired or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 900 can also include one or more sensors 910. The one or more sensors 910 include, but are not limited to: acceleration sensor 911, gyro sensor 912, pressure sensor 913, fingerprint sensor 914, optical sensor 915, and proximity sensor 916.

The acceleration sensor 911 can detect the magnitude of acceleration in three coordinate axes of the coordinate system established with the terminal 900. For example, the acceleration sensor 911 may be used to detect the components of the gravitational acceleration in three coordinate axes. The processor 901 can control the display screen 905 to display the user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 911. The acceleration sensor 911 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 912 may detect a body direction and a rotation angle of the terminal 900, and the gyro sensor 912 may cooperate with the acceleration sensor 911 to acquire a 3D motion of the user on the terminal 900. The processor 901 can implement the following functions according to the data collected by the gyro sensor 912: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

The pressure sensor 913 may be disposed on a side bezel of the terminal 900 and/or underneath the display 905. When the pressure sensor 913 is disposed on the side frame of the terminal 900, the user's holding signal of the terminal 900 may be detected, and the processor 901 performs left-right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 913. When the pressure sensor 913 is disposed at a lower layer of the display screen 905, the processor 901 controls the operability control on the UI interface according to the pressure operation of the user on the display screen 905. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 914 is used for collecting a fingerprint of the user, and the processor 901 identifies the user according to the fingerprint collected by the fingerprint sensor 914, or the fingerprint sensor 914 identifies the user according to the collected fingerprint. Upon recognizing that the user's identity is a trusted identity, processor 901 authorizes the user to perform relevant sensitive operations including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings, etc. The fingerprint sensor 914 may be disposed on the front, back, or side of the terminal 900. When a physical key or vendor Logo is provided on the terminal 900, the fingerprint sensor 914 may be integrated with the physical key or vendor Logo.

The optical sensor 915 is used to collect ambient light intensity. In one embodiment, the processor 901 may control the display brightness of the display screen 905 based on the ambient light intensity collected by the optical sensor 915. Specifically, when the ambient light intensity is high, the display brightness of the display screen 905 is increased; when the ambient light intensity is low, the display brightness of the display screen 905 is reduced. In another embodiment, the processor 901 can also dynamically adjust the shooting parameters of the camera assembly 906 according to the ambient light intensity collected by the optical sensor 915.

Proximity sensor 916, also known as a distance sensor, is typically disposed on the front panel of terminal 900. The proximity sensor 916 is used to collect the distance between the user and the front face of the terminal 900. In one embodiment, when the proximity sensor 916 detects that the distance between the user and the front face of the terminal 900 gradually decreases, the processor 901 controls the display 905 to switch from the bright screen state to the dark screen state; when the proximity sensor 916 detects that the distance between the user and the front surface of the terminal 900 gradually becomes larger, the display 905 is controlled by the processor 901 to switch from the breath screen state to the bright screen state.

Those skilled in the art will appreciate that the configuration shown in fig. 9 does not constitute a limitation of terminal 900, and may include more or fewer components than those shown, or may combine certain components, or may employ a different arrangement of components.

The computer device mentioned in the embodiments of the present disclosure may be provided as a server. Fig. 10 is a block diagram of a server according to an exemplary embodiment, where the server 1000 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 1001 and one or more memories 1002, where the one or more memories 1002 store at least one program code, and the at least one program code is loaded and executed by the one or more processors 1001 to implement the processes executed by the server in the resource recommendation method provided by the above-mentioned method embodiments. Of course, the server 1000 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 1000 may also include other components for implementing the functions of the device, which are not described herein again.

In an exemplary embodiment, a computer readable storage medium comprising program code, such as a memory 1002 comprising program code, executable by a processor 1001 of the server 1000 to perform the resource recommendation method described above is also provided. Alternatively, the computer-readable storage medium may be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact-Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program product is also provided, comprising a computer program which, when executed by a processor, implements the resource recommendation method described above.

In some embodiments, a computer program according to embodiments of the present disclosure may be deployed to be executed on one computer device or on multiple computer devices located at one site, or on multiple computer devices distributed at multiple sites and interconnected by a communication network, and the multiple computer devices distributed at the multiple sites and interconnected by the communication network may constitute a block chain system.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for resource recommendation, the method comprising:

2. The resource recommendation method according to claim 1, wherein presenting at least one first object matching a target keyword in response to a search operation on the target keyword comprises:

3. The resource recommendation method of claim 1, further comprising:

and in response to the selection operation of any one of the at least one first object, displaying the selected first object in a second display area of the object search page, wherein the second display area is used for displaying the selected object.

4. The resource recommendation method according to claim 1, wherein the object search page comprises an import control for importing at least one object of the multimedia resource determined within a historical period of time;

the method further comprises the following steps:

importing, based on the import control, at least one object of the multimedia resource determined over a historical period of time in the object search page.

5. The resource recommendation method according to claim 1, wherein the object search page includes a storage control, the storage control is configured to store the selected at least one object to an object data packet of the multimedia resource, and the object data packet is configured to store an object to be recommended for the multimedia resource;

the method further comprises the following steps:

6. A method for resource recommendation, the method comprising:

7. The resource recommendation method according to claim 6, wherein determining at least one first object matching a target keyword in response to a search request for the target keyword comprises any one of:

in response to a search request for the target keyword, determining at least one first object matched with the target keyword from target relation data, wherein the target relation data represents a corresponding relation between an object and at least one object matched with the object;

and responding to a search request of the target keyword, and selecting at least one first object matched with the target keyword from a plurality of candidate objects.

8. The resource recommendation method according to claim 7, wherein said selecting at least one first object matching the target keyword from the plurality of candidate objects comprises:

respectively determining matching degrees of the candidate objects and the target keywords based on object feature information of the candidate objects, wherein the matching degrees represent matching degrees between the candidate objects and the target keywords;

9. The resource recommendation method according to claim 8, wherein before determining the matching degrees of the candidate objects with the target keyword respectively based on the object feature information of the candidate objects, the method further comprises:

inputting the object information of the candidate objects into a feature extraction model, extracting the object feature information of the candidate objects through the feature extraction model, wherein the feature extraction model is obtained through training based on the object information of the sample objects and the object feature information of the sample objects.

10. The resource recommendation method according to any one of claims 7 to 9, wherein the obtaining of the plurality of candidate objects comprises:

determining at least one object meeting a focus condition based on an object focus list of a plurality of objects, wherein the object focus list is used for recording objects focused by the corresponding objects;

determining at least one object satisfying a degree of attention condition as the plurality of candidate objects.

11. An apparatus for resource recommendation, the apparatus comprising:

the obtaining unit is configured to execute triggering operation of the at least one interaction type control, and obtain at least one second object of which the interaction operation behavior corresponding to the at least one first object occurs;

12. The resource recommendation device according to claim 11, wherein the search unit is configured to perform:

13. The resource recommendation device of claim 11, further comprising:

and the showing unit is configured to execute a selection operation responding to any one of the at least one first object, and show the selected first object in a second showing area of the object searching page, wherein the second showing area is used for showing the selected object.

14. An apparatus for resource recommendation, the apparatus comprising:

the determining unit is configured to execute a search request responding to a target keyword, and determine at least one first object matched with the target keyword, wherein the search request is triggered based on an object search page of a multimedia resource, the object search page comprises at least one interaction type control, and the interaction type controls respectively correspond to a type of interaction operation behaviors;

an obtaining unit configured to execute, in response to an object obtaining request triggered based on the at least one interaction type control, obtaining at least one second object for which an interaction operation behavior corresponding to the at least one first object has occurred;

15. The resource recommendation device according to claim 14, wherein the determining unit comprises any one of:

a selecting subunit configured to perform, in response to a search request for the target keyword, selecting at least one first object matching the target keyword from a plurality of candidate objects.

16. A computer device, characterized in that the computer device comprises:

one or more processors;

a memory for storing the processor executable program code;

wherein the processor is configured to execute the program code to implement the resource recommendation method of any one of claims 1 to 10.

17. A computer-readable storage medium, characterized in that program code in the computer-readable storage medium, when executed by a processor of a computer device, enables the computer device to perform the resource recommendation method of any one of claims 1 to 10.