WO2021169793A1 - Method and apparatus for acquiring target object and storage medium - Google Patents

Abstract

The present disclosure relates to a method and apparatus for acquiring a target object, and a storage medium. The method comprises: insofar as it is detected that a first user account plays back a first multimedia resource, acquiring a preferred object of the first user account; according to the preferred object of the first user account, identifying a resource image of the first multimedia resource; determining a target object comprised in the resource image; acquiring object source information of the target object; generating an object acquisition inlet for acquiring the target object; and displaying the object acquisition inlet in an interface region corresponding to the target object for the first user account to acquire the target object by means of the object acquisition inlet. In the method and apparatus for acquiring the target object, the electronic device, and the storage medium provided by the present disclosure, a target object may be determined according to the preference of a user who automatically recognizes and plays back a multimedia resource, and the object acquisition inlet of the target object is displayed.

Description

Method, device and storage medium for acquiring target object

Cross-references to related applications

This application claims the priority of Chinese Patent Application No. 202010130110.5 filed in China on February 28, 2020, the entire content of which is incorporated herein by reference.

Technical field

The present disclosure relates to the field of image processing technology, and in particular, to a method, device, and storage medium for acquiring a target object.

Background technique

In the related art, during the process of the user playing the multimedia resource, the object acquisition portal can be displayed, so that the user can obtain the target object in the multimedia resource through the object acquisition portal. For example, display the purchase link corresponding to the product in the video, so that the user can purchase the corresponding product through the purchase link.

In the related art, in the process of playing the same multimedia resource by different users, the object acquisition entry of the same target object is displayed.

Summary of the invention

The present disclosure provides a method, device and storage medium for obtaining a target object, and the technical solutions of the present disclosure are as follows:

According to a first aspect of the embodiments of the present disclosure, there is provided a method for obtaining a target object, the method comprising: in a case where it is detected that a first user account is playing a first multimedia resource, obtaining information about the first user account Preference object; according to the preference object of the first user account, identify the resource image of the first multimedia resource, determine the target object included in the resource image; obtain the object source information of the target object, Generate an object acquisition portal for acquiring the target object, and display the object acquisition portal in an interface area corresponding to the target object, for the first user account to obtain the target through the object acquisition portal Object.

According to a second aspect of the embodiments of the present disclosure, there is provided a method for obtaining a target object, the method comprising: receiving an obtaining request to obtain a preference object of a first user account; and according to the preference object of the first user account, The resource image of the first multimedia resource is identified, the target object included in the resource image is determined; the object source information of the target object is acquired, the object acquisition entry for acquiring the target object is generated, and the The object acquisition portal is sent to the first user account to display the object acquisition portal in an interface area corresponding to the target object, for the first user account to obtain the object acquisition portal through the object acquisition portal target.

According to a third aspect of the embodiments of the present disclosure, there is provided an apparatus for acquiring a target object, the apparatus comprising: a first acquiring module configured to, when it is detected that a first user account is playing a first multimedia resource, Acquire the preference object of the first user account; a first determining module is configured to identify the resource image of the first multimedia resource according to the preference object of the first user account, and determine the resource image The first generation module is configured to obtain the object source information of the target object, generate an object acquisition entry for obtaining the target object, and display the object acquisition entry in the target object The interface area corresponding to the object is used by the first user account to obtain the entry through the object to obtain the target object.

According to a fourth aspect of the embodiments of the present disclosure, there is provided an apparatus for acquiring a target object, the apparatus including: a second acquisition module configured to receive an acquisition request to acquire a preference object of a first user account; and a second determination module , Configured to identify the resource image of the first multimedia resource according to the preference object of the first user account, and determine the target object included in the resource image; the second generation module is configured to obtain The object source information of the target object generates an object acquisition entry for acquiring the target object, and sends the object acquisition entry to the first user account to display the object acquisition entry in the The interface area corresponding to the target object is used by the first user account to obtain the target object through the object acquisition portal.

According to a fifth aspect of the embodiments of the present disclosure, there is provided a terminal device, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement The method for obtaining the target object as described in the first aspect above.

According to a sixth aspect of the embodiments of the present disclosure, there is provided a server, including: a processor; a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement The method for obtaining the target object described in the second aspect above.

According to a seventh aspect of the embodiments of the present disclosure, a system for acquiring a target object includes: the terminal device according to the fifth aspect; and the server according to the sixth aspect.

According to an eighth aspect of the embodiments of the present disclosure, a storage medium is provided, and instructions in the storage medium are executed by a processor of an electronic device, so that the electronic device can execute the acquisition of a target object as described in the first aspect or the second aspect Methods.

According to a ninth aspect of the embodiments of the present disclosure, a computer program product is provided, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, and the program instructions are executed by a computer , Causing the computer to execute the method for acquiring the target object as described in the first aspect or the second aspect.

The embodiment of the present disclosure provides a method, device, and storage medium for acquiring a target object. In the case of detecting that the first user account is playing the first multimedia resource, the preference object of the first user account is acquired, according to the first user account. The preference object of the user account identifies the resource image of the first multimedia resource, determines the target object included in the resource image; obtains the object source information of the target object, generates an object acquisition entry for acquiring the target object, and combines the object The acquisition entry is displayed in the interface area corresponding to the target object, for the first user account to acquire the target object through the object acquisition entry, the target object can be determined according to the preference of the user who automatically recognizes the multimedia resource, and the object acquisition of the corresponding target object is displayed Entrance.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure.

Description of the drawings

The drawings herein are incorporated into the specification and constitute a part of the specification, show embodiments conforming to the disclosure, and together with the specification are used to explain the principle of the disclosure, and do not constitute an improper limitation of the disclosure.

FIG. 1 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

Figures 2a-2b show schematic diagrams of resource images of multimedia resources.

FIG. 3 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

FIG. 4 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

FIG. 5 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

FIG. 6 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

FIG. 7 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

FIG. 8 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

FIG. 9 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

FIG. 10 shows another schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure.

Fig. 11 is a block diagram showing a device for acquiring a target object according to an exemplary embodiment.

Fig. 12 is a block diagram showing a device for acquiring a target object according to an exemplary embodiment.

Fig. 13 is a block diagram of a terminal device for implementing a method for acquiring a target object shown in an exemplary embodiment.

Fig. 14 is a block diagram of a server for implementing a method for acquiring a target object shown in an exemplary embodiment.

Detailed ways

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

It should be noted that the terms “first”, “second”, etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of the present disclosure described herein can be implemented in a sequence other than those illustrated or described herein. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

FIG. 1 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S12, in a case where it is detected that the first user account is playing the first multimedia resource, a preference object of the first user account is acquired.

When it is detected that the first user account, such as viewers, fans, etc., is playing the first multimedia resource, the preference object of the first user account can be acquired. There may be at least one preference object of the first user account, and the at least one preference object may constitute a preference object set. In this step, the terminal device may obtain the preference object of the first user account, or the terminal device may send an obtaining request to the server, so that the server obtains the preference object of the first user account. Generally, the processing capacity and memory of the terminal device are lower than that of the server, and the server may obtain the preference object of the first user account, so as to reduce the data processing pressure of the terminal device.

In step S14, the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target object included in the resource image is determined.

Figure 2a shows a schematic diagram of a first multimedia resource. As shown in the figure, the resource image of the first multimedia resource is identified according to the preference object of the first user account, and the resource image is determined The target objects included, for example, include: strawberries.

In step S16, the object source information of the target object is acquired, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in the interface area corresponding to the target object for the The first user account obtains the target object through the object acquisition portal.

The target object may be a commodity, and the object acquisition entry for obtaining the target object may be a payment link for purchasing the commodity; for example, a payment link for purchasing the strawberry shown in FIG. 2a. Figure 2a only takes the target object as a physical product as an example, but it does not mean that the target object must be a physical product. The target object can also be a virtual product, such as an application (Application, App). The object acquisition entry for obtaining the target object It may be a download function for downloading the App; the target object may be a membership in the App, and the object acquisition entry for obtaining the target object may be a subscription function for subscribing to the membership.

Thus, a method for obtaining a target object provided by an embodiment of the present disclosure is to obtain the preference object of the first user account when it is detected that the first user account is playing the first multimedia resource; according to the first user account The preferred object of the first multimedia resource is identified, the target object included in the resource image is determined; the object source information of the target object is obtained, the object acquisition entry for acquiring the target object is generated, and the object The acquisition portal is displayed in the interface area corresponding to the target object, for the first user account to acquire the portal through the object to acquire the target object, and the target object can be determined according to the preference of the user who automatically recognizes the multimedia resource, and the object corresponding to the target object is displayed Get the entrance.

In addition, in a method for obtaining a target object provided by an embodiment of the present disclosure, by sending an obtaining request to a server so that the server obtains the preference object of the first user account, the server may obtain the preference of the first user account. Object to reduce the data processing pressure of terminal equipment.

FIG. 3 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S32, when it is detected that the first user account is playing the first multimedia resource, a preference object of the first user account is acquired.

In step S34, the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target object included in the resource image is determined.

The foregoing steps can be described similarly to steps S12 and S14 in the embodiment of FIG. 1, and repetitive parts are not repeated here.

In step S36, a preset object source information set of the multimedia resource is obtained, wherein the preset object source information set includes: object source information corresponding to each object included in the multimedia resource, from the In the preset source information set, the object source information of the target object is obtained.

In an implementation manner, before step S36, it may further include: in a case where the second multimedia resource uploaded by the second user is acquired, identifying the resource image of the second multimedia resource, and determining For each object included in the resource image, an object source information configuration interface is displayed for each object, so as to receive an operation from a second user to configure the object source information corresponding to each object; according to the object corresponding to each object Source information, generating the preset source information set. Among them, the second user is, for example, an anchor who sells merchandise. In the case that the second multimedia resource uploaded by the second user is acquired, the image recognition model can be called or the image segmentation algorithm can be used to identify the resource image of the second multimedia resource, and determine that the resource image is Every object included.

The object source information configuration interface is displayed for each object. The object and object source information configuration interface can be a one-to-one relationship, that is, an object corresponds to an object source information configuration interface, or a many-to-one relationship, that is, multiple objects Corresponding to an object source information configuration interface, so that the second user can configure the source information of multiple objects through one configuration interface. According to the object source information corresponding to each object, the preset source information set is generated, and the preset source information set includes: object source information corresponding to each object included in the multimedia resource.

Optionally, the second multimedia resource can be the same as the first multimedia resource. For example, both the second multimedia resource and the first multimedia resource can be as shown in FIG. The photograph is taken as a multimedia resource and uploaded. In this step, the preset source information set is generated. When the fan plays the multimedia resource, the target object is determined according to the fan’s preference, and all the information is obtained from the preset source information set. Describe the object source information of the target object. Specifically, the anchor can photograph the fruits sold in the live broadcast room into multimedia resources as shown in Figure 2a. In this step, each object included in the resource image, such as strawberries and cherries, is determined, and the object corresponding to each object is configured. Source information, that is, payment links used to purchase strawberries and cherries, respectively, generates the preset source information set. When a fan plays the video shown in Figure 2a, if the target object determined according to the fan’s preference object is a strawberry, a payment link for purchasing strawberries is obtained from the preset source information set, and a payment link used to obtain the target is generated. The object of the object gets the entry.

Optionally, the second multimedia resource may be different from the first multimedia resource, where the first multimedia resource may be, for example, as shown in FIG. 2a, and FIG. 2b shows a schematic diagram of the second multimedia resource. For example, the host can shoot all the commodities sold in the live broadcast room as a second multimedia resource and upload it, as shown in Figure 2b. In this step, each product included in the video can be automatically identified and determined, and the object source information configuration interface is displayed for each product to receive the operation of the anchor to configure the product source information corresponding to each product; the object corresponding to the product The source information constitutes a preset source information collection.

Through the second multimedia resource shown in Figure 2b, the source information set can be preset to include fruits such as strawberries, cherries, apples, bananas, watermelons, etc. Therefore, the anchor can configure a multimedia resource to be sold in the live broadcast room. The source information of all the products of, facilitate the operation of the second user, and improve the efficiency of publishing the target object. Based on this, the anchor can respectively display different target objects through different first multimedia resources. In the case where the fan plays the first multimedia resource as shown in Fig. 2a, all of them can be obtained from the preset source information set. Describe the object source information of the target object.

In another implementation manner, before step S26, it may further include: in the case of acquiring the second multimedia resource uploaded by the second user, identifying the resource image of the second multimedia resource, and determining Each object included in the resource image; search for each object in a preset object source database to obtain the object source information corresponding to each object; according to the object corresponding to each object Source information, generating the preset source information set. The second user is, for example, an anchor who sells merchandise. In the case that the second multimedia resource uploaded by the second user is acquired, the image recognition model can be called or the image segmentation algorithm can be used to identify the resource image of the second multimedia resource, and determine that the resource image is Every object included. And based on this, in a preset object source database, search for each object to obtain the object source information corresponding to each object; generate the preview according to the object source information corresponding to each object The source information set is set, and the preset source information set does not need to be generated through the configuration operation of the second user. For example, an anchor can use a certain platform, website, and online store as a preset object source database. For example, in the case of an anchor promoting an App, the anchor can search for the App in the App store and obtain the download link of the App. There is no need for the host to perform configuration operations. For example, in the case of an anchor selling a product, the product can be searched for on a shopping website and the purchase link of the purchased product can be obtained without the configuration operation of the second user to generate the preset source information set.

In step S38, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in an interface area corresponding to the target object for the first user account to acquire the entry through the object To obtain the target object.

Therefore, a method for obtaining a target object provided by an embodiment of the present disclosure is to obtain a preference object of the first user account when it is detected that the first user account is playing the first multimedia resource; The preference object of the first user account identifies the resource image of the first multimedia resource, and determines the target object included in the resource image; obtains the object source information of the target object, and generates information for obtaining the The object acquisition entrance of the target object, and the object acquisition entrance is displayed in the interface area corresponding to the target object for the first user account to obtain the target object through the object acquisition entrance, which can be automatically identified according to The preference of the user who plays the multimedia resource determines the target object, and displays the object acquisition portal of the target object to meet the individualized object acquisition needs of different users.

In addition, an embodiment of the present disclosure provides a method for obtaining a target object by obtaining a preset object source information set of the multimedia resource, wherein the preset object source information set includes: The object source information corresponding to each object; the object source information of the target object is obtained from the preset source information set, and the object source information of the target object can be obtained accurately and efficiently, thereby improving the accuracy of obtaining the target object Degree and efficiency.

In addition, an embodiment of the present disclosure provides a method for obtaining a target object, by obtaining the second multimedia resource uploaded by the second user before the obtaining the preset object source information set of the multimedia resource Next, the resource image of the second multimedia resource is identified, and each object included in the resource image is determined; an object source information configuration interface is displayed for each object to receive operations from the second user. Configuring object source information corresponding to each object; generating the preset source information set according to the object source information corresponding to each object, enabling the second user to conveniently and efficiently configure the object source information corresponding to each object.

In addition, an embodiment of the present disclosure provides a method for acquiring a target object, which recognizes the resource image of the second multimedia resource when the second multimedia resource uploaded by the second user is acquired, Determine each object included in the resource image; search for each object in a preset object source database to obtain the object source information corresponding to each object; The object source information generates the preset source information set, which can automatically generate the preset source information set without the second user's configuration operation.

FIG. 4 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S42, when it is detected that the first user account is playing the first multimedia resource, the preference object of the first user account is acquired.

In step S44, the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target object included in the resource image is determined.

The foregoing steps can be described similarly to steps S12 and S14 in the embodiment of FIG. 1, and repetitive parts are not repeated here.

In step S46, a search is performed on the target object in a preset object source database, and the object source information corresponding to the target object is obtained.

For example, a certain platform, website, and online store can be used as a preset object source database. For example, the App can be searched in an App store and the download link of the App can be obtained without the host performing configuration operations. For example, in the case of an anchor selling a product, you can search for the product on a shopping website and obtain the purchase link of the purchased product without the anchor performing the operation of configuring the object source information. After the target object is determined, it is in the preset object source database Search in, so as to obtain the object source information corresponding to the target object.

In step S48, an object acquisition portal for acquiring the target object is generated, and the object acquisition portal is displayed in an interface area corresponding to the target object for the first user account to acquire the entrance through the object To obtain the target object.

Therefore, a method for obtaining a target object provided by an embodiment of the present disclosure is to obtain a preference object of the first user account when it is detected that the first user account is playing the first multimedia resource; The preference object of the first user account identifies the resource image of the first multimedia resource, and determines the target object included in the resource image; obtains the object source information of the target object, and generates information for obtaining the The object acquisition entrance of the target object, and the object acquisition entrance is displayed in the interface area corresponding to the target object for the first user account to obtain the target object through the object acquisition entrance, which can be automatically identified according to The preference of the user who plays the multimedia resource determines the target object, and displays the object acquisition portal of the target object to meet the individualized object acquisition needs of different users.

In addition, in a method for obtaining a target object provided by an embodiment of the present disclosure, by searching for the target object in a preset object source database to obtain the object source information corresponding to the target object, the host does not need to configure it. The operation of the object source information is to search in the preset object source database after the target object is determined, so as to obtain the object source information corresponding to the target object.

FIG. 5 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S52, when it is detected that the first user account is playing the first multimedia resource, the preference object of the first user account is acquired.

This step can adopt a description similar to step S12 in the embodiment of FIG. 1, and repetitive parts are not described here.

In step S541, at least one frame of the resource image of the first multimedia resource is used as the input of the preset image recognition model.

In a possible implementation manner, the preset image recognition model is obtained by taking a plurality of images containing the object as a sample set, and using a preset type of machine learning algorithm to train the sample set. In other words, before this step, a method for obtaining a target object provided by an embodiment of the present disclosure may further include: taking multiple multimedia resources containing objects as sample sets, for example, taking multiple multimedia resources containing various commodities as samples Set; train the sample set by a preset type of machine learning algorithm to obtain the preset multimedia resource recognition model, so that in this step, at least one frame of the resource image of the first multimedia resource As the input of the preset multimedia resource recognition model.

In step S542, when at least one frame of the resource image of the first multimedia resource contains at least one candidate object, the output of the preset image recognition model is the description information of the at least one candidate object, The description information of the candidate object includes: the name of the candidate object.

Among them, the candidate object may be associated with the object source information. For example, the candidate object may be a commodity, and the corresponding object source information may be a payment link for purchasing the commodity; the candidate object may be an App, and the corresponding object source information may be downloading the App The download link of; the candidate object can be the membership in the App, and the corresponding object source information can be the subscription link to subscribe to the membership, etc. An object that cannot be associated with the source information of the object does not belong to the candidate object described in the embodiment of the present disclosure.

With reference to FIG. 2a again, in step S541, FIG. 2a may be used as the input of the preset multimedia resource recognition model. In Figure 2a, the sun and people cannot be associated with the source information of the object, so they are not candidates. Strawberries and cherries can be associated with object source information and belong to candidate objects. In this step, when the first multimedia resource contains two candidate objects (strawberry, cherry), the output of the preset multimedia resource recognition model is the description of the two candidate objects (strawberry, cherry) information. Conversely, when at least one frame of the first multimedia resource does not contain a candidate object, the output of the preset multimedia resource identification model is 0 or an error message.

In step S543, the candidate object corresponding to the preference object of the first user account is determined as the target object.

For example, if strawberry is a candidate object corresponding to the preference object of the first user account, then strawberry is determined as the target object; if strawberry and cherry are both candidate objects corresponding to the preference object of the first user account, then strawberry And Cherry are both identified as the target object.

In an implementation manner, the candidate object that is the same as the object classification of the preference object may be determined as the target object. For example, if the preference object of the first user account is strawberry, which belongs to the fruit category, and the candidate objects are strawberries, cherries, and both strawberries and cherries belong to the fruit category, then both strawberries and cherries are determined as the target objects. As a result, as many target objects as possible can be recommended to the user.

In another implementation manner, the candidate object that is the same as the preference object may also be determined as the target object. For example, if the preference object of the first user account is strawberry and the candidate objects are strawberries and cherries, then strawberry is determined as the target object, and cherries are not as the target object. As a result, the accuracy of recommending the target object can be improved.

In step S56, the object source information of the target object is acquired, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in an interface area corresponding to the target object for the The first user account obtains the target object through the object acquisition portal.

This step can be described as similar to step S16 in the embodiment of FIG. 1, steps S36-S38 in the embodiment of FIG. 3, or steps S46-S48 in the embodiment of FIG. In the case that only strawberries are determined as the target object, only the object source information of the target object may be obtained, and the object source information of the cherry is no longer obtained.

In addition, in an implementation manner, the description information of the candidate object may further include: a target position of the candidate object in the resource image of the first multimedia resource. Wherein, the target position can be represented by the coordinates of the candidate object in the first multimedia resource, or can be represented by other ways that the candidate object can be located in the first multimedia resource, for example, by its relative to a predetermined The relative position of the reference object is expressed, such as the relative position relative to the multimedia resource center.

The target object is one or more of the candidate objects. According to the description information of the candidate object, the description information of the target object can be determined, that is, the target position of the target object can be determined. The acquisition entrance of the object is displayed in the interface area corresponding to the target position. For example, it may be displayed near the target location, for example, it may be displayed 1 cm below the target location to facilitate the user's operation of obtaining the target object.

Therefore, a method for obtaining a target object provided by an embodiment of the present disclosure is to obtain a preference object of the first user account when it is detected that the first user account is playing the first multimedia resource; The preference object of the first user account identifies the resource image of the first multimedia resource, and determines the target object included in the resource image; obtains the object source information of the target object, and generates information for obtaining the The object acquisition entrance of the target object, and the object acquisition entrance is displayed in the interface area corresponding to the target object for the first user account to obtain the target object through the object acquisition entrance, which can be automatically identified according to The preference of the user who plays the multimedia resource determines the target object, and displays the object acquisition portal of the target object to meet the individualized object acquisition needs of different users.

The embodiment of the present disclosure provides a method for obtaining a target object, by using at least one frame of the resource image of the first multimedia resource as the input of a preset image recognition model; in at least one frame of the first multimedia resource When the resource image of the resource contains at least one candidate object, the output of the preset image recognition model is the description information of the at least one candidate object, and the description information of the candidate object includes: the name of the candidate object; The candidate object corresponding to the preference object of the first user account is determined as the target object, and the target object corresponding to the preference object of the first user account can be determined through a preset image recognition model, thereby automatically, accurately and accurately. Efficiently recommend different target objects for different users to meet the individualized object acquisition needs of different users.

In addition, an embodiment of the present disclosure provides a method for acquiring a target object. The preset image recognition model uses a plurality of images containing the object as a sample set, and uses a preset type of machine learning algorithm to analyze the The sample set obtained by training can automatically, efficiently and accurately identify the target object in the first multimedia resource based on the pre-trained preset multimedia resource recognition model.

FIG. 6 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S62, when it is detected that the first user account is playing the first multimedia resource, the preference object of the first user account is acquired.

This step can adopt a description similar to step S12 in the embodiment of FIG. 1, and repetitive parts are not described here.

In step S641, at least one object region included in at least one frame of the resource image of the first multimedia resource is determined.

As shown in FIG. 2c, the resource image of the first multimedia resource can be determined. The four object areas included in FIG. 2a are area A, area B, area C, and area D, respectively. Optionally, the area and shape of each region may be the same or different, and the distribution may be uniform or uneven. In an implementation manner, the area, shape, and distribution of each region can be determined according to the area, shape, and distribution of objects appearing in it.

In step S642, the at least one object area is classified to determine the candidate objects contained in the at least one object area, and the description information of the candidate object is determined, and the description information of the candidate object includes: the candidate The name of the object.

For example, the object area is classified to determine that area A contains the object sun, area B contains the object strawberry, area C contains the object cherry, and area D contains the object person. Among them, the candidate object may be associated with the object source information. For example, the candidate object may be a commodity, and the corresponding object source information may be a payment link for purchasing the commodity; the candidate object may be an App, and the corresponding object source information may be downloading the App The download link of; the candidate object can be the membership in the App, and the corresponding object source information can be the subscription link to subscribe to the membership, etc. An object that cannot be associated with the source information of the object does not belong to the candidate object described in the embodiment of the present disclosure. In Figure 2a, the sun and people cannot be associated with the source information of the object, so they are not candidates. Strawberries and cherries can be associated with object source information and belong to candidate objects.

In step S643, the candidate object corresponding to the preference object of the first user account is determined as the target object.

This step can be described in the same way as step S543 in the embodiment of FIG. 5, and will not be repeated here.

In step S66, the object source information of the target object is acquired, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in the interface area corresponding to the target object for the The first user account obtains the target object through the object acquisition portal.

This step can be described similarly to step S16 in the embodiment of FIG. 1, steps S36-S38 in the embodiment of FIG. 3, steps S46-S48 in the embodiment of FIG. 4, or step S56 in the embodiment of FIG.

Therefore, a method for obtaining a target object provided by an embodiment of the present disclosure is to obtain a preference object of the first user account when it is detected that the first user account is playing the first multimedia resource; The preference object of the first user account identifies the resource image of the first multimedia resource, and determines the target object included in the resource image; obtains the object source information of the target object, and generates information for obtaining the The object acquisition entrance of the target object, and the object acquisition entrance is displayed in the interface area corresponding to the target object for the first user account to obtain the target object through the object acquisition entrance, which can be automatically identified according to The preference of the user who plays the multimedia resource determines the target object, and displays the object acquisition portal of the target object to meet the individualized object acquisition needs of different users.

An embodiment of the present disclosure provides a method for obtaining a target object, by determining at least one object area contained in at least one frame of the resource image of the first multimedia resource; classifying the at least one object area to determine the Describe the candidate objects contained in at least one object area, and determine the description information of the candidate object. The description information of the candidate object includes: the name of the candidate object; The candidate object is determined as the target object, thereby automatically, accurately, and efficiently recommending different target objects for different users to meet the individualized object acquisition needs of different users.

FIG. 7 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S721, when it is detected that the first user account is playing the first multimedia resource, each object corresponding to the target operation behavior of the first user account is scored.

Wherein, the target operation behavior of the first user account is the operation behavior performed on each object by the first user account within a preset time period, which may include query, browsing, payment, and download performed on each object. , Subscription and other operations.

In an implementation manner, the weights of the target operation behaviors may be respectively set in advance. In this step, the weight of each target operation behavior is obtained, the number of operations performed by the second user on each object of each target operation behavior is obtained, and the operations are performed on each object according to the weight and the number of operations. score. For example, the weights obtained for query, browsing, and payment are a1, a2, and a3, respectively. For a commodity object A, the user performs the query, browsing, and payment n1, n2, and n3 times, then the score N _A corresponding to the object A is (n1*a1+n2*a2+n3*a3) points. For a certain commodity object B, the user makes n4, n5, and n6 times of query, browsing, and payment, and the score NB corresponding to object _B is (n4*a1+n5*a2+n6*a3) points, which can be accurate Each object is scored accordingly. Further, the weight of the target operation behavior may be determined according to the attributes of the target operation behavior. For example, the weight of the payment and purchase behavior may be greater than the query and browsing behavior, and the weight of the download and subscription behavior may be greater than the query and browsing behavior.

In step S722, the object whose score meets the preset score condition is determined as the preferred object of the first user account.

For example, an object with a score greater than a preset score threshold or a score ranked in the top N is determined as a preference object of the first user account. At least one preference object of the first user account may constitute a set of preference objects of the first user account, whereby the preference object of the first user account can be obtained, and the target object can be determined based on the user's preference.

In step S74, the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target object included in the resource image is determined.

This step can use the description similar to step S14 in the embodiment of FIG. 1, step S34 in the embodiment of FIG. 3, step S44 in the embodiment of FIG. 4, steps S541-S543 in the embodiment of FIG. 5, or steps S641-S643 in the embodiment of FIG. Part of it will not be repeated here.

In step S76, the object source information of the target object is acquired, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in the interface area corresponding to the target object for the The first user account obtains the target object through the object acquisition portal.

This step can be described similarly to step S16 in the embodiment of FIG. 1, steps S36-S38 in the embodiment of FIG. 3, steps S46-S48 in the embodiment of FIG. 4, or step S56 in the embodiment of FIG.

Therefore, a method for obtaining a target object provided by an embodiment of the present disclosure is to obtain a preference object of the first user account when it is detected that the first user account is playing the first multimedia resource; The preference object of the first user account identifies the resource image of the first multimedia resource, and determines the target object included in the resource image; obtains the object source information of the target object, and generates information for obtaining the The object acquisition entrance of the target object, and the object acquisition entrance is displayed in the interface area corresponding to the target object for the first user account to obtain the target object through the object acquisition entrance, which can be automatically identified according to The preference of the user who plays the multimedia resource determines the target object, and displays the object acquisition portal of the target object to meet the individualized object acquisition needs of different users.

The embodiment of the present disclosure provides a method for obtaining a target object by scoring each object corresponding to the target operation behavior of the first user account, wherein the target operation behavior of the first user account is at a preset time In the paragraph, the operation behavior performed by the first user account on each object; the object whose score meets the preset score condition is determined as the preferred object of the first user account, and the information of the first user account can be obtained Preference the object, thereby determining the target object based on the user's preference.

FIG. 8 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S821, when it is detected that the first user account is playing the first multimedia resource, a similar user similar to the first user account is determined according to the portrait of the first user account.

Optionally, this step may be performed in the case that the first user account is a new user account and the previous operation behavior of the first user account cannot be obtained. The portrait of the first user account may be obtained through the identity information of the first user account, for example, it may include: gender, age, occupation, hobbies, and so on. The identity information of the first user account may be collected through the input of the first user. The portrait of the similar user has a higher similarity with the portrait of the first user, for example, higher than a preset similarity threshold.

In step S822, the preference object of the similar user is determined as the preference object of the first user account.

In an implementation manner, similar users are old users, then the preference objects of similar users can be determined based on the method of steps S721-S722 in the embodiment of FIG. 7, which will not be repeated here. Moreover, in this step, the preference objects of the similar users are determined as the preference objects of the first user account. As a result, it is possible to accurately identify and meet the needs of users, especially new users, and improve the accuracy of recommending target objects.

In an implementation manner, in the case where there are multiple similar users determined in step S821, multiple preference objects of the multiple similar users may be deduplicated, and the deduplicated preference objects may be processed, Determined as the preferred object of the first user account. As a result, it is avoided that repeated target objects are recommended due to repeated preference objects.

In step S84, the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target object included in the resource image is determined.

This step can use the description similar to step S14 in the embodiment of FIG. 1, step S34 in the embodiment of FIG. 3, step S44 in the embodiment of FIG. 4, steps S541-S543 in the embodiment of FIG. 5, or steps S641-S643 in the embodiment of FIG. Part of it will not be repeated here.

In step S86, the object source information of the target object is acquired, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in the interface area corresponding to the target object for the The first user account obtains the target object through the object acquisition portal.

This step can be described similarly to step S16 in the embodiment of FIG. 1, steps S36-S38 in the embodiment of FIG. 3, steps S46-S48 in the embodiment of FIG. 4, or step S56 in the embodiment of FIG.

Therefore, a method for obtaining a target object provided by an embodiment of the present disclosure is to obtain a preference object of the first user account when it is detected that the first user account is playing the first multimedia resource; The preference object of the first user account identifies the resource image of the first multimedia resource, and determines the target object included in the resource image; obtains the object source information of the target object, and generates information for obtaining the The object acquisition entrance of the target object, and the object acquisition entrance is displayed in the interface area corresponding to the target object for the first user account to obtain the target object through the object acquisition entrance, which can be automatically identified according to The preference of the user who plays the multimedia resource determines the target object, and displays the object acquisition portal of the target object to meet the individualized object acquisition needs of different users.

The embodiment of the present disclosure provides a method for obtaining a target object, by determining a similar user similar to the first user account according to the portrait of the first user account; determining the preference object of the similar user as the The preference objects of the first user account can accurately identify and meet the needs of users, especially new users, and improve the accuracy of recommending target objects.

FIG. 9 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a terminal device. In other words, the method can be executed by software or hardware installed in the terminal device. As shown in the figure, the method may include the following steps.

In step S92, when it is detected that the first user account is playing the first multimedia resource, the preference object of the first user account is acquired.

In step S94, the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target object included in the resource image is determined.

In step S96, the object source information of the target object is acquired, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in an interface area corresponding to the target object for the The first user account obtains the target object through the object acquisition portal.

The foregoing steps S92-S96 may adopt the descriptions of the corresponding steps in the embodiments of Figs. 1 to 8, which will not be repeated here.

In step S98, an operation for acquiring the target object performed by the first user account through the object acquisition portal is received.

Wherein, the operation of obtaining the target object may include at least one of payment, download, and subscription. As a result, the process from stimulating the user's needs through the first multimedia resource to achieving the acquisition of the target object forms a complete closed transaction loop, and the process of achieving the target function is complete, efficient, and accurate.

FIG. 10 shows a schematic flowchart of a method for acquiring a target object provided by an embodiment of the present disclosure, and the method may be executed by a server. In other words, the method can be executed by software or hardware installed on the server. As shown in the figure, the method may include the following steps.

In step S102, an acquisition request is received to acquire a preference object of the first user account.

In a case where it is detected that the first user account is playing the first multimedia resource, the terminal device may send an acquisition request to the server, and the server receives the acquisition request and acquires the preference object of the first user account. Generally, the processing capacity and memory of the terminal device are lower than that of the server, and the server may obtain the preference object of the first user account, so as to reduce the data processing pressure of the terminal device. The specific steps for the server to obtain the preference object of the first user account may adopt the descriptions of the corresponding steps in the embodiments of FIG. 1 to FIG. 8, which will not be repeated here.

In step S104, the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target object included in the resource image is determined.

In step S106, the object source information of the target object is acquired, an object acquisition entry for acquiring the target object is generated, and the object acquisition entry is displayed in the interface area corresponding to the target object for the The first user account obtains the target object through the object acquisition portal.

The foregoing steps S104 and S106 can adopt the descriptions of the corresponding steps in the embodiments of FIG. 1 to FIG. 9 and achieve the same or corresponding effects, which will not be repeated here.

Therefore, in a method for obtaining a target object provided by an embodiment of the present disclosure, an obtaining request is received through a server to obtain a preference object of a first user account; according to the preference object of the first user account, the first user account is The resource image of the media resource is identified, the target object included in the resource image is determined; the object source information of the target object is acquired, the object acquisition entry for acquiring the target object is generated, and the object acquisition entry Displayed in the interface area corresponding to the target object, for the first user account to obtain the entry through the object to obtain the target object, the target object can be determined according to the preference of the user who automatically recognizes the multimedia resource, and the target is displayed The object acquisition portal of the object meets the personalized object acquisition needs of different users, and can reduce the data processing pressure of the terminal device.

Fig. 11 is a block diagram showing a device for acquiring a target object according to an exemplary embodiment. Referring to FIG. 11, the apparatus may be a terminal device or applied to a terminal device. The device 1100 includes a first acquiring module 1101, a first determining module 1102, and a first generating module 1103.

The first obtaining module 1101 is configured to obtain a preference object of the first user account when it is detected that the first user account is playing the first multimedia resource. The first determining module 1102 is configured to identify the resource image of the first multimedia resource according to the preference object of the first user account, and determine the target object included in the resource image. The first generation module 1103 is configured to obtain the object source information of the target object, generate an object acquisition entry for acquiring the target object, and display the object acquisition entry in an interface area corresponding to the target object , For the first user account to obtain the target object through the object acquisition portal.

In an implementation manner, the first obtaining module 1101 is configured to obtain a preset object source information set of the multimedia resource, wherein the preset object source information set includes: the multimedia resource includes Object source information corresponding to each object in; Obtain the object source information of the target object from the preset source information set.

In an implementation manner, the first acquiring module 1101 is configured to identify the resource image of the second multimedia resource in the case of acquiring the second multimedia resource uploaded by the second user , Determine each object included in the resource image; display an object source information configuration interface for each object to receive an operation from a second user to configure the object source information corresponding to each object; The corresponding object source information generates the preset source information set.

In an implementation manner, the first acquiring module 1101 is configured to identify the resource image of the second multimedia resource in the case of acquiring the second multimedia resource uploaded by the second user , Determine each object included in the resource image; search for each object in a preset object source database to obtain the object source information corresponding to each object; The source information of the object is generated, and the preset source information set is generated.

In an implementation manner, the first obtaining module 1101 is configured to search for the target object in a preset object source database, and obtain the object source information corresponding to the target object.

In an implementation manner, the first determining module 1102 is configured to use at least one frame of the resource image of the first multimedia resource as the input of the preset image recognition model; When the resource image of the multimedia resource contains at least one object, the output of the preset image recognition model is the description information of the at least one candidate object, and the description information of the candidate object includes: Name; the candidate object corresponding to the preference object of the first user account is determined as the target object. In an implementation manner, the preset image recognition model is obtained by taking a plurality of images containing the object as a sample set, and training the sample set using a preset type of machine learning algorithm.

In an implementation manner, the first determining module 1102 is configured to determine at least one object area included in at least one frame of the resource image of the first multimedia resource; and classify the at least one object area To determine the candidate object contained in the at least one object area, and determine the description information of the candidate object. The description information of the candidate object includes: the name of the candidate object; The candidate object corresponding to the object is determined as the target object.

In an implementation manner, the first determining module 1102 is configured to determine the candidate object that is the same as the object classification of the preference object as the target object; or, it will be the same as the preference object The candidate object of is determined to be the target object.

In an implementation manner, the first obtaining module 1101 is configured to score each object corresponding to the target operation behavior of the first user account, wherein the target operation behavior of the first user account is The operation behavior performed by the first user account on each object within a preset time period; the object whose score meets the preset score condition is determined as the preferred object of the first user account.

In an implementation manner, the first obtaining module 1101 is configured to obtain the weight of each target operation behavior; obtain the number of operations performed on each object by the first user account for each target operation behavior; The weight and the number of operations are weighted and summed to obtain the score of each object.

In one implementation, the first acquisition module 1101 is configured to determine similar users similar to the first user account according to the portrait of the first user account; and compare the preference objects of the similar users to Determined as a preference object of the first user account.

In an implementation manner, the first obtaining module 1101 is further configured to perform deduplication processing on the preference objects followed by the plurality of similar users when there are multiple similar users; The processed preference objects of the plurality of similar users are determined as preference objects of the first user account.

In an implementation manner, the first generating module 1103 is configured to determine the description information of the target object according to the description information of the candidate object, wherein the description information of the candidate object further includes: The target position of the candidate object in the resource image of the first multimedia resource; displaying the object acquisition entry in the interface area corresponding to the target position.

In an implementation manner, the first generation module 1103 is further configured to receive an operation for acquiring the target object performed by the first user account through the object acquisition portal.

In an implementation manner, the first obtaining module 1101 is configured to send an obtaining request to the server so that the server obtains the preference object of the first user account.

Regarding the device in the foregoing embodiment, the specific manner in which each module performs the operation and the technical effect achieved by it have been described in detail in the embodiment of the method, and no detailed description will be given here.

Fig. 12 is a block diagram showing a device for acquiring a target object according to an exemplary embodiment. Referring to FIG. 12, the device may be a server or an application server. The device 1200 includes: a second acquiring module 1201, a second determining module 1202, and a second generating module 1203.

The second obtaining module 1201 is configured to receive an obtaining request to obtain the preference object of the first user account. The second determining module 1202 is configured to identify the resource image of the first multimedia resource according to the preferred object of the first user account, and determine the target object included in the resource image. The second generating module 1203 is configured to obtain the object source information of the target object, generate an object acquisition entry for obtaining the target object, and send the object acquisition entry to the first user account to send The object acquisition portal is displayed in an interface area corresponding to the target object, for the first user account to obtain the target object through the object acquisition portal.

In an implementation manner, the second generating module 1203 is configured to obtain a preset object source information set of the multimedia resource, wherein the preset object source information set includes: the multimedia resource includes Object source information corresponding to each object in; Obtain the object source information of the target object from the preset source information set.

In an implementation manner, the second generating module 1203 is further configured to perform a process on the resource image of the second multimedia resource when the second multimedia resource uploaded by the second user is acquired. Identify and determine each object included in the resource image; display an object source information configuration interface for each object to receive an operation from a second user to configure the object source information corresponding to each object; The object source information corresponding to the object generates the preset source information set.

In an implementation manner, the second generating module 1203 is further configured to perform a process on the resource image of the second multimedia resource when the second multimedia resource uploaded by the second user is acquired. Identify and determine each object included in the resource image; search for each object in a preset object source database to obtain the object source information corresponding to each object; The corresponding object source information generates the preset source information set.

In an implementation manner, the second generating module 1203 is further configured to search for the target object in a preset object source database to obtain object source information corresponding to the target object.

In an implementation manner, the second determining module 1202 is configured to use at least one frame of the resource image of the first multimedia resource as the input of the preset image recognition model; When the resource image of the multimedia resource contains at least one object, the output of the preset image recognition model is the description information of the at least one candidate object, and the description information of the candidate object includes: Name; the candidate object corresponding to the preference object of the first user account is determined as the target object.

In an implementation manner, the preset image recognition model is obtained by taking a plurality of images containing the object as a sample set, and training the sample set using a preset type of machine learning algorithm.

In an implementation manner, the second determining module 1202 is configured to determine at least one object area included in at least one frame of the resource image of the first multimedia resource; and classify the at least one object area To determine the candidate object contained in the at least one object area, and determine the description information of the candidate object. The description information of the candidate object includes: the name of the candidate object; The candidate object corresponding to the object is determined as the target object.

In an implementation manner, the second determining module 1202 is configured to determine the candidate object that is the same as the object classification of the preference object as the target object; or, it will be the same as the preference object The candidate object of is determined to be the target object.

In an implementation manner, the second acquisition module 1201 is configured to score each object corresponding to the target operation behavior of the first user account, wherein the target operation behavior of the first user account is The operation behavior performed by the first user account on each object within a preset time period; the object whose score meets the preset score condition is determined as the preferred object of the first user account.

In an implementation manner, the second obtaining module 1201 is configured to obtain the weight of each target operation behavior; obtain the number of operations performed on each object by the first user account for each target operation behavior; The weight and the number of operations are weighted and summed to obtain the score of each object.

In one implementation, the second acquisition module 1201 is configured to determine similar users similar to the first user account according to the portrait of the first user account; and compare the preference objects of the similar users to Determined as a preference object of the first user account.

In an implementation manner, the second obtaining module 1201 is further configured to perform deduplication processing on the preference objects followed by the multiple similar users when there are multiple similar users; The processed preference objects of the plurality of similar users are determined as preference objects of the first user account.

In an implementation manner, the second generating module 1203 is configured to determine the description information of the target object according to the description information of the candidate object, wherein the description information of the candidate object further includes: The target position of the candidate object in the resource image of the first multimedia resource; sending the object acquisition portal to the first user account to display the object acquisition portal on the corresponding target object Interface area.

In an implementation manner, the second generating module 1203 is further configured to receive a request for obtaining the target object, wherein the request for obtaining the target object is based on the approval of the first user account The object is generated by obtaining the operation performed by the entry.

Fig. 13 is a block diagram of a terminal device 1300 for implementing a method for acquiring a target object shown in an exemplary embodiment. The terminal device 1300 includes a processor 1301 and a memory 1302 for storing instructions executable by the processor 1301. Wherein, the processor 1301 is configured to execute the instructions to implement the method for acquiring the target object in the embodiments of FIGS. 1-9 of the present disclosure. In practical applications, the terminal device 1300 may also include a network interface 1303, an I/O controller 1304, a mass storage device 1305, and a bus 1306 for connecting them.

In an exemplary embodiment, a storage medium including instructions is also provided, such as a memory 1302 including instructions. The foregoing instructions can be executed by the processor 1301 of the terminal device 1300 to achieve the acquisition target in the embodiments of FIGS. 1-9 of the present disclosure. Object method. Alternatively, the storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage Equipment, etc.

In an exemplary embodiment, a computer program product is also provided, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, and the program instructions are executed by a computer, The computer is allowed to implement the method for obtaining the target object in the embodiments of FIGS. 1-9 of the present disclosure, and achieve the same technical effect.

Fig. 14 is a block diagram of a server 1400 for implementing a method for acquiring a target object shown in an exemplary embodiment. The server 1400 includes a processor 1401 and a memory 1402 for storing instructions executable by the processor 1401. Wherein, the processor 1401 is configured to execute the instructions to implement the method for acquiring the target object in the embodiment of FIG. 10 of the present disclosure. In practical applications, the server 1400 may also include a network interface 1403, an I/O controller 1404, a mass storage device 1405, and a bus 1406 for connecting them.

In an exemplary embodiment, there is also provided a storage medium including instructions, such as a memory 1402 including instructions. The foregoing instructions can be executed by the processor 1401 of the server 1400 to implement the method for obtaining a target object in the embodiment of FIG. 10 of the present disclosure. .

Alternatively, the storage medium may be a non-transitory computer-readable storage medium, for example, the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage Equipment, etc.

In an exemplary embodiment, a computer program product is also provided, the computer program product includes a computer program stored on a computer-readable storage medium, the computer program includes program instructions, and the program instructions are executed by a computer, The computer is allowed to implement the method for obtaining the target object in the embodiment of FIG. 10 of the present disclosure, and achieve the same technical effect.

Those skilled in the art will easily think of other embodiments of the present disclosure after considering the specification and practicing the application disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field that are not disclosed in the present disclosure. . The description and the embodiments are to be regarded as exemplary only, and the true scope and spirit of the present disclosure are pointed out by the following claims.

It should be understood that the present disclosure is not limited to the precise structure that has been described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure is only limited by the appended claims.

Claims (67)

1. A method for obtaining a target object, characterized in that the method includes:

   In a case where it is detected that the first user account is playing the first multimedia resource, acquiring the preference object of the first user account;

   Identifying the resource image of the first multimedia resource according to the preference object of the first user account, and determining the target object included in the resource image;

   Obtain the object source information of the target object, generate an object acquisition entry for acquiring the target object, and display the object acquisition entry in the interface area corresponding to the target object for the first user account to pass The object acquisition portal is used to acquire the target object.
2. The method of claim 1, wherein the step of obtaining the object source information of the target object comprises:

   Acquiring a preset object source information set of the multimedia resource, where the preset object source information set includes: object source information corresponding to each object included in the multimedia resource;

   Obtain the object source information of the target object from the preset source information set.
3. The method according to claim 2, wherein the method further comprises:

   In the case of acquiring the second multimedia resource uploaded by the second user, identify the resource image of the second multimedia resource, and determine each object included in the resource image;

   Displaying an object source information configuration interface for each object to receive an operation from a second user to configure the object source information corresponding to each object;

   According to the object source information corresponding to each object, the preset source information set is generated.
4. The method according to claim 2, wherein the method further comprises:

   In the case of acquiring the second multimedia resource uploaded by the second user, identify the resource image of the second multimedia resource, and determine each object included in the resource image;

   Search for each object in a preset object source database to obtain object source information corresponding to each object;

   According to the object source information corresponding to each object, the preset source information set is generated.
5. The method of claim 1, wherein the step of obtaining the object source information of the target object comprises:

   In a preset object source database, search for the target object to obtain object source information corresponding to the target object.
6. The method of claim 1, wherein the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target included in the resource image is determined Object steps, including:

   Using at least one frame of the resource image of the first multimedia resource as an input of a preset image recognition model;

   In the case that at least one frame of the resource image of the first multimedia resource contains at least one candidate object, the output of the preset image recognition model is the description information of the at least one candidate object, and the The description information includes: the name of the candidate object;

   The candidate object corresponding to the preference object of the first user account is determined as the target object.
7. The method of claim 6, wherein the preset image recognition model uses a plurality of images containing the object as a sample set, and uses a preset type of machine learning algorithm to train the sample set owned.
8. The method of claim 1, wherein the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target included in the resource image is determined Object steps, including:

   Determining at least one object area included in at least one frame of the resource image of the first multimedia resource;

   Classify the at least one object area to determine the candidate objects contained in the at least one object area, and determine the description information of the candidate object, where the description information of the candidate object includes: the name of the candidate object;

   The candidate object corresponding to the preference object of the first user account is determined as the target object.
9. The method according to claim 6 or 8, wherein the determining the candidate object corresponding to the preference object of the first user account as the target object comprises:

   Determining the candidate object that is the same as the object classification of the preference object as the target object;

   or,

   The candidate object that is the same as the preference object is determined as the target object.
10. The method according to claim 1, wherein the step of obtaining the preference object of the first user account comprises:

    Score each object corresponding to the target operation behavior of the first user account, where the target operation behavior of the first user account is that within a preset time period, the first user account performs ’S operating behavior;

    The object whose score meets the preset score condition is determined as the preferred object of the first user account.
11. The method of claim 10, wherein the step of scoring each object corresponding to the target operation behavior of the first user account comprises:

    Obtaining the weight of each target operation behavior;

    Acquiring the number of operations performed on each object by the first user account for each of the target operation behaviors;

    Perform a weighted summation on the weight and the number of operations to obtain the score of each object.
12. The method according to claim 1, wherein the step of obtaining the preference object of the first user account comprises:

    Determining similar users similar to the first user account according to the portrait of the first user account;

    The preference object of the similar users is determined as the preference object of the first user account.
13. The method of claim 12, wherein the method further comprises:

    In the case where there are multiple similar users, de-duplication processing is performed on the preference objects concerned by the multiple similar users;

    The preference objects of the plurality of similar users after the deduplication processing are determined as the preference objects of the first user account.
14. The method according to claim 6 or 8, wherein the step of displaying the object acquisition portal in an interface area corresponding to the target object comprises:

    Determine the description information of the target object according to the description information of the candidate object, wherein the description information of the candidate object further includes: the target position of the candidate object in the resource image of the first multimedia resource ；

    The object acquisition portal is displayed in an interface area corresponding to the target position.
15. The method of claim 1, wherein the method further comprises:

    An operation for acquiring the target object performed by the first user account through the object acquisition portal is received.
16. The method according to claim 1, wherein the step of obtaining the preference object of the first user account comprises:

    Sending an acquisition request to the server to enable the server to acquire the preference object of the first user account.
17. A method for obtaining a target object, characterized in that the method includes:

    Receiving an acquisition request to acquire the preference object of the first user account;

    Identifying the resource image of the first multimedia resource according to the preference object of the first user account, and determining the target object included in the resource image;

    Obtain the object source information of the target object, generate an object acquisition portal for acquiring the target object, and send the object acquisition portal to the first user account to display the object acquisition portal in the The interface area corresponding to the target object is used by the first user account to obtain the target object through the object acquisition portal.
18. The method according to claim 17, wherein the step of obtaining the object source information of the target object comprises:

    Acquiring a preset object source information set of the multimedia resource, where the preset object source information set includes: object source information corresponding to each object included in the multimedia resource;

    Obtain the object source information of the target object from the preset source information set.
19. The method of claim 18, wherein the method further comprises:

    In the case of acquiring the second multimedia resource uploaded by the second user, identify the resource image of the second multimedia resource, and determine each object included in the resource image;

    Displaying an object source information configuration interface for each object to receive an operation from a second user to configure the object source information corresponding to each object;

    According to the object source information corresponding to each object, the preset source information set is generated.
20. The method of claim 18, wherein the method further comprises:

    In the case of acquiring the second multimedia resource uploaded by the second user, identify the resource image of the second multimedia resource, and determine each object included in the resource image;

    Search for each object in a preset object source database to obtain object source information corresponding to each object;

    According to the object source information corresponding to each object, the preset source information set is generated.
21. The method according to claim 17, wherein the step of obtaining the object source information of the target object comprises:

    In a preset object source database, search for the target object to obtain object source information corresponding to the target object.
22. The method according to claim 17, wherein the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target included in the resource image is determined Object steps, including:

    Using at least one frame of the resource image of the first multimedia resource as an input of a preset image recognition model;

    In the case where at least one frame of the resource image of the first multimedia resource contains at least one object, the output of the preset image recognition model is the description information of the at least one candidate object, and the description of the candidate object The information includes: the name of the candidate object;

    The candidate object corresponding to the preference object of the first user account is determined as the target object.
23. The method of claim 22, wherein the preset image recognition model uses a plurality of images containing the object as a sample set, and uses a preset type of machine learning algorithm to train the sample set owned.
24. The method according to claim 17, wherein the resource image of the first multimedia resource is identified according to the preferred object of the first user account, and the target included in the resource image is determined Object steps, including:

    Determining at least one object area included in at least one frame of the resource image of the first multimedia resource;

    Classify the at least one object area to determine the candidate objects contained in the at least one object area, and determine the description information of the candidate object, where the description information of the candidate object includes: the name of the candidate object;

    The candidate object corresponding to the preference object of the first user account is determined as the target object.
25. The method according to claim 22 or 24, wherein the determining the candidate object corresponding to the preference object of the first user account as the target object comprises:

    Determining the candidate object that is the same as the object classification of the preference object as the target object;

    or,

    The candidate object that is the same as the preference object is determined as the target object.
26. The method according to claim 17, wherein the step of obtaining the preference object of the first user account comprises:

    Score each object corresponding to the target operation behavior of the first user account, where the target operation behavior of the first user account is that within a preset time period, the first user account performs ’S operating behavior;

    The object whose score meets the preset score condition is determined as the preferred object of the first user account.
27. The method of claim 26, wherein the step of scoring each object corresponding to the target operation behavior of the first user account comprises:

    Obtaining the weight of each target operation behavior;

    Acquiring the number of operations performed on each object by the first user account for each of the target operation behaviors;

    Perform a weighted summation on the weight and the number of operations to obtain the score of each object.
28. The method according to claim 17, wherein the step of obtaining the preference object of the first user account comprises:

    Determining similar users similar to the first user account according to the portrait of the first user account;

    The preference object of the similar users is determined as the preference object of the first user account.
29. The method of claim 28, wherein the method further comprises:

    In the case where there are multiple similar users, de-duplication processing is performed on the preference objects concerned by the multiple similar users;

    The preference objects of the plurality of similar users after the deduplication processing are determined as the preference objects of the first user account.
30. The method according to claim 22 or 24, wherein the object acquisition portal is sent to the first user account to display the object acquisition portal in an interface area corresponding to the target object The steps include:

    Determine the description information of the target object according to the description information of the candidate object, wherein the description information of the candidate object further includes: the target position of the candidate object in the resource image of the first multimedia resource ；

    The object acquisition portal is sent to the first user account to display the object acquisition portal in an interface area corresponding to the target object.
31. The method of claim 17, wherein the method further comprises:

    A request for acquiring the target object is received, wherein the request for acquiring the target object is generated based on an operation performed by the first user account through the object acquisition portal.
32. A device for acquiring a target object, characterized in that the device comprises:

    The first obtaining module is configured to obtain the preference object of the first user account when it is detected that the first user account is playing the first multimedia resource;

    The first determining module is configured to identify the resource image of the first multimedia resource according to the preference object of the first user account, and determine the target object included in the resource image;

    The first generating module is configured to obtain the object source information of the target object, generate an object acquisition entry for obtaining the target object, and display the object acquisition entry in an interface area corresponding to the target object, For the first user account to obtain the target object through the object acquisition portal.
33. The device according to claim 32, wherein the first obtaining module is configured to obtain a preset object source information set of the multimedia resource, wherein the preset object source information set includes: Object source information corresponding to each object included in the multimedia resource; and obtain the object source information of the target object from the preset source information set.
34. The apparatus according to claim 33, wherein the first obtaining module is configured to perform a check on the second multimedia resource when the second multimedia resource uploaded by the second user is obtained. To identify each object included in the resource image; display an object source information configuration interface for each object to receive the operation of the second user to configure the object source information corresponding to each object; The object source information corresponding to each object generates the preset source information set.
35. The apparatus according to claim 33, wherein the first obtaining module is configured to perform a check on the second multimedia resource when the second multimedia resource uploaded by the second user is obtained. To identify each object included in the resource image; search for each object in a preset object source database to obtain the object source information corresponding to each object; The object source information corresponding to each object is described, and the preset source information set is generated.
36. The device according to claim 32, wherein the first obtaining module is configured to search for the target object in a preset object source database to obtain object source information corresponding to the target object .
37. The device of claim 32, wherein the first determining module is configured to use at least one frame of the resource image of the first multimedia resource as an input of a preset image recognition model; In the case that the resource image of the first multimedia resource contains at least one object, the output of the preset image recognition model is the description information of the at least one candidate object, and the description information of the candidate object includes: The name of the candidate object; the candidate object corresponding to the preference object of the first user account is determined as the target object.
38. The device of claim 37, wherein the preset image recognition model uses a plurality of images containing the object as a sample set, and uses a preset type of machine learning algorithm to train the sample set owned.
39. The device of claim 32, wherein the first determining module is configured to determine at least one object region included in at least one frame of the resource image of the first multimedia resource; One object area is classified to determine the candidate objects contained in the at least one object area, and the description information of the candidate object is determined. The description information of the candidate object includes: the name of the candidate object; A candidate object corresponding to a preference object of a user account is determined as the target object.
40. The device according to claim 37 or 39, wherein the first determining module is configured to determine the candidate object that is the same as the object classification of the preference object as the target object;

    or,

    The candidate object that is the same as the preference object is determined as the target object.
41. The device according to claim 32, wherein the first obtaining module is configured to score each object corresponding to the target operation behavior of the first user account, wherein the first user account The target operation behavior is the operation behavior performed by the first user account on each object within a preset time period;

    The object whose score meets the preset score condition is determined as the preferred object of the first user account.
42. The device according to claim 41, wherein the first obtaining module is configured to obtain the weight of each of the target operation behaviors; obtain the first user account to perform each of the target operation behaviors on each object The number of operations; the weight and the number of operations are weighted and summed to obtain the score of each object.
43. The apparatus according to claim 32, wherein the first obtaining module is configured to determine similar users similar to the first user account according to the portrait of the first user account; The user's preference object is determined to be the preference object of the first user account.
44. The device according to claim 43, wherein the first acquiring module is further configured to de-duplicate preference objects followed by the multiple similar users when there are multiple similar users deal with;

    The preference objects of the plurality of similar users after the deduplication processing are determined as the preference objects of the first user account.
45. The device according to claim 37 or 39, wherein the first generating module is configured to determine the description information of the target object according to the description information of the candidate object, wherein the The description information also includes: the target position of the candidate object in the resource image of the first multimedia resource;

    The object acquisition portal is displayed in an interface area corresponding to the target position.
46. The apparatus according to claim 32, wherein the first generating module is further configured to receive an operation for obtaining the target object performed by the first user account through the object obtaining portal.
47. The apparatus according to claim 32, wherein the first obtaining module is configured to send an obtaining request to a server so that the server obtains the preference object of the first user account.
48. A device for acquiring a target object, characterized in that the device comprises:

    The second obtaining module is configured to receive the obtaining request to obtain the preference object of the first user account;

    The second determining module is configured to identify the resource image of the first multimedia resource according to the preference object of the first user account, and determine the target object included in the resource image;

    The second generation module is configured to obtain the object source information of the target object, generate an object acquisition entry for obtaining the target object, and send the object acquisition entry to the first user account to transfer all The object acquisition portal is displayed in an interface area corresponding to the target object, for the first user account to obtain the target object through the object acquisition portal.
49. The device of claim 48, wherein the second generating module is configured to obtain a preset object source information set of the multimedia resource, wherein the preset object source information set includes: The object source information corresponding to each object included in the multimedia resource;

    Obtain the object source information of the target object from the preset source information set.
50. The apparatus according to claim 49, wherein the second generating module is further configured to perform a response to the second multimedia resource when the second multimedia resource uploaded by the second user is acquired. The resource image of the resource is identified, and each object included in the resource image is determined;

    Displaying an object source information configuration interface for each object to receive an operation from a second user to configure the object source information corresponding to each object;

    According to the object source information corresponding to each object, the preset source information set is generated.
51. The apparatus according to claim 49, wherein the second generating module is further configured to perform a response to the second multimedia resource when the second multimedia resource uploaded by the second user is acquired. The resource image of the resource is identified, and each object included in the resource image is determined;

    Search for each object in a preset object source database to obtain object source information corresponding to each object;

    According to the object source information corresponding to each object, the preset source information set is generated.
52. The device according to claim 48, wherein the second generating module is further configured to search for the target object in a preset object source database to obtain the object source corresponding to the target object information.
53. The device of claim 48, wherein the second determining module is configured to use at least one frame of the resource image of the first multimedia resource as an input of a preset image recognition model;

    In the case where at least one frame of the resource image of the first multimedia resource contains at least one object, the output of the preset image recognition model is the description information of the at least one candidate object, and the description of the candidate object The information includes: the name of the candidate object;

    The candidate object corresponding to the preference object of the first user account is determined as the target object.
54. The device of claim 53, wherein the preset image recognition model uses a plurality of images containing the object as a sample set, and uses a preset type of machine learning algorithm to train the sample set owned.
55. The device of claim 48, wherein the second determining module is configured to determine at least one object area included in at least one frame of the resource image of the first multimedia resource;

    Classify the at least one object area to determine the candidate objects contained in the at least one object area, and determine the description information of the candidate object, where the description information of the candidate object includes: the name of the candidate object;

    The candidate object corresponding to the preference object of the first user account is determined as the target object.
56. The apparatus according to claim 53 or 55, wherein the second determining module is configured to determine the candidate object that is the same as the object classification of the preference object as the target object;

    or,

    The candidate object that is the same as the preference object is determined as the target object.
57. The device according to claim 48, wherein the second acquisition module is configured to score each object corresponding to the target operation behavior of the first user account, wherein The target operation behavior is the operation behavior performed by the first user account on each object within a preset time period;

    The object whose score meets the preset score condition is determined as the preferred object of the first user account.
58. The device according to claim 57, wherein the second obtaining module is configured to obtain the weight of each of the target operation behaviors;

    Acquiring the number of operations performed on each object by the first user account for each of the target operation behaviors;

    Perform a weighted summation on the weight and the number of operations to obtain the score of each object.
59. The device of claim 48, wherein the second acquisition module is configured to determine similar users similar to the first user account based on the portrait of the first user account;

    The preference object of the similar users is determined as the preference object of the first user account.
60. The apparatus according to claim 59, wherein the second acquiring module is further configured to: after determining the preference object of the similar user as the preference object of the first user account, the In the case that there are multiple similar users, de-duplication processing is performed on the preference objects concerned by the multiple similar users;

    The preference objects of the plurality of similar users after the deduplication processing are determined as the preference objects of the first user account.
61. The device according to claim 58 or 60, wherein the second generating module is configured to determine the description information of the target object according to the description information of the candidate object, wherein the The description information also includes: the target position of the candidate object in the resource image of the first multimedia resource;

    The object acquisition portal is sent to the first user account to display the object acquisition portal in an interface area corresponding to the target object.
62. The apparatus of claim 48, wherein the second generating module is further configured to receive a request for obtaining the target object, wherein the request for obtaining the target object is based on the The first user account is generated by the operation performed by the object acquisition portal.
63. A terminal device, characterized in that it comprises:

    processor;

    A memory for storing executable instructions of the processor;

    Wherein, the processor is configured to execute the instruction to implement the method for obtaining a target object according to any one of claims 1 to 16.
64. A server, characterized in that it comprises:

    processor;

    A memory for storing executable instructions of the processor;

    Wherein, the processor is configured to execute the instruction to implement the method for obtaining a target object according to any one of claims 17 to 31.
65. A system for acquiring a target object, characterized in that the system includes:

    The terminal device according to claim 63;

    The server according to claim 64.
66. A storage medium, where instructions in the storage medium are executed by a processor of an electronic device, so that the electronic device can execute the method for obtaining a target object according to any one of claims 1 to 16; or execute the method as claimed in claim 17. The method for obtaining a target object described in any one of to 31.
67. A computer program product, characterized in that the computer program product runs on a computer, so that the computer executes the method for obtaining a target object according to any one of claims 1 to 16; or executes the method as claimed in claim 17. The method for obtaining a target object described in any one of to 31.

Images