CN112699274A - Object searching method and device and computer storage medium - Google Patents
Object searching method and device and computer storage medium Download PDFInfo
- Publication number
- CN112699274A CN112699274A CN202011560437.2A CN202011560437A CN112699274A CN 112699274 A CN112699274 A CN 112699274A CN 202011560437 A CN202011560437 A CN 202011560437A CN 112699274 A CN112699274 A CN 112699274A
- Authority
- CN
- China
- Prior art keywords
- target
- video frame
- search
- search instruction
- triggered
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/738—Presentation of query results
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for searching an object, and a computer storage medium. The method and the device for searching the target object in the live broadcast video interface have the advantages that in response to a search instruction triggered by a target account, recommendation information of the target object corresponding to the search instruction is displayed on the live broadcast video interface; the target object is searched from the candidate object set according to a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame; the target video frame is a video frame displayed in a live video interface within a preset time length after the target account triggers the search instruction, so that the object can be quickly and flexibly searched.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method and an apparatus for searching an object, and a computer storage medium.
Background
With the development of network technology, live webcasting has stepped into the era of national live webcasting, and the content and live webcasting form of live webcasting are more and more diversified. Through the live broadcast mode, the information in different fields such as education, public welfare, E-commerce and the like is shared, the user can know the real-time information in different fields only by logging in a platform account, the processes of manually searching and screening the information by the user are reduced, and the purpose of quickly sharing the information can be realized. However, when a user watches the live broadcast of the anchor broadcast in the live broadcast room at present, if a certain article in the live broadcast room needs to be searched, the user can only manually search the article in the live broadcast room by other platforms after screenshot, and the searching method is too complicated in flow.
Disclosure of Invention
The embodiment of the disclosure provides an object searching method, an object searching device and a computer storage medium, which can realize fast and flexible object searching.
According to a first aspect of the embodiments of the present disclosure, there is provided an object search method, applied to a client, including:
responding to a search instruction triggered by a target account, and displaying recommendation information of a target object corresponding to the search instruction on the live video interface;
the target object is searched from a candidate object set according to a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame; the target video frame is a video frame displayed in the live video interface within a preset time length after the target account triggers the search instruction.
An optional implementation manner is that, before the selecting operation is a touch operation triggered by the target account in the target video frame and the live video interface displays recommendation information of a target object corresponding to the search instruction, the method further includes:
after the search instruction triggered by the target account is detected, detecting touch operation in the live video interface; and detecting a touch operation triggered by the target account in the target video frame displayed in the live video interface.
In an optional embodiment, the search instruction is triggered by the target account through a search view; or
The search instruction is triggered by the target account through a voice command; or
The search instruction is triggered by the target account through a preset gesture.
In an optional embodiment, the recommendation information of the target object includes at least one of description information and a link address of the target object; and the link address is the address of the webpage containing the description information of the target object.
An optional implementation manner is that, in response to a search instruction triggered by a target account, the method for displaying recommendation information of a target object corresponding to the search instruction on the live video interface includes:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
according to the position information, determining a reference object which needs to be referred to for object search from the target video frame, and identifying attribute information of the reference object;
sending the attribute information of the reference object to a server so that the server searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on the live video interface.
An optional implementation manner is that, in response to a search instruction triggered by a target account, the method for displaying recommendation information of a target object corresponding to the search instruction on the live video interface includes:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
sending the target video frame and the position information corresponding to the search instruction to a server, so that the server determines a reference object to be referred to for object search from the target video frame according to the position information, and searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on the live video interface.
According to a second aspect of the embodiments of the present disclosure, there is provided an object search method applied to a server, including:
determining attribute information of a reference object; the reference object is an object to be referenced for object search determined from the target video frame according to the target video frame corresponding to the search instruction and the position information corresponding to the selection operation triggered by the target account in the target video frame; the search instruction is an instruction triggered by the target account through a client; the target video frame is a video frame displayed in a live broadcast video interface within a preset time length after the target account triggers the search instruction;
searching a target object from a candidate object set according to the attribute information of the reference object;
and sending the recommendation information of the target object to a client so that the client displays the recommendation information of the target object in the live video interface.
An optional implementation manner is that the determining of the attribute information of the reference object includes:
receiving attribute information of the reference object sent by the client; the attribute information of the reference object is obtained by the client side through determining and identifying the reference object from the target video frame according to the position information; or
And receiving a target video frame and position information sent by the client, determining a reference object from the target video frame according to the position information, and identifying attribute information of the reference object.
In an optional embodiment, the recommendation information of the target object includes at least one of description information and a link address of the target object; and the link address is the address of the webpage containing the description information of the target object.
According to a third aspect of the embodiments of the present disclosure, there is provided an object search apparatus including:
the detection unit is configured to execute a search instruction triggered by the detection target account;
the display unit is configured to execute a search instruction triggered by a target account, and display recommendation information of a target object corresponding to the search instruction on the live video interface;
the target object is searched from a candidate object set according to a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame; the target video frame is a video frame displayed in the live video interface within a preset time length after the target account triggers the search instruction.
In an optional embodiment, the selecting operation is a touch operation triggered by the target account in the target video frame, and the presenting unit is configured to perform:
after the search instruction triggered by the target account is detected, detecting touch operation in the live video interface; and detecting a touch operation triggered by the target account in the target video frame displayed in the live video interface.
In an optional embodiment, the search instruction is triggered by the target account through a search view; or
The search instruction is triggered by the target account through a voice command; or
The search instruction is triggered by the target account through a preset gesture.
In an optional embodiment, the recommendation information of the target object includes at least one of description information and a link address of the target object; and the link address is the address of the webpage containing the description information of the target object.
In an optional embodiment, the presentation unit is configured to perform:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
according to the position information, determining a reference object which needs to be referred to for object search from the target video frame, and identifying attribute information of the reference object;
sending the attribute information of the reference object to a server so that the server searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on the live video interface.
In an optional embodiment, the presentation unit is configured to perform:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
sending the target video frame and the position information corresponding to the search instruction to a server, so that the server determines a reference object to be referred to for object search from the target video frame according to the position information, and searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on the live video interface.
According to a fourth aspect of the embodiments of the present disclosure, there is provided an object search apparatus including:
a determination unit configured to perform determination of attribute information of a reference object; the reference object is an object to be referenced for object search determined from the target video frame according to the target video frame corresponding to the search instruction and the position information corresponding to the selection operation triggered by the target account in the target video frame; the search instruction is an instruction triggered by the target account through a client; the target video frame is a video frame displayed in a live broadcast video interface within a preset time length after the target account triggers the search instruction;
a searching unit configured to perform a search for a target object from a set of candidate objects according to attribute information of the reference object;
and the sending unit is configured to send the recommendation information of the target object to the client so that the client displays the recommendation information of the target object in the live video interface.
In an optional embodiment, the determining unit is configured to perform:
receiving attribute information of the reference object sent by the client; the attribute information of the reference object is obtained by the client side through determining and identifying the reference object from the target video frame according to the position information; or
And receiving a target video frame and position information sent by the client, determining a reference object from the target video frame according to the position information, and identifying attribute information of the reference object.
In an optional embodiment, the recommendation information of the target object includes at least one of description information and a link address of the target object; and the link address is the address of the webpage containing the description information of the target object.
According to a fifth aspect of the embodiments of the present disclosure, there is provided an object search apparatus including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the object search method of the first aspect.
According to a sixth aspect of the embodiments of the present disclosure, there is provided an object search apparatus including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the object search method according to the second aspect.
According to a seventh aspect of embodiments of the present disclosure, there is provided a storage medium having instructions that, when executed by a processor of an object search apparatus, enable the object search apparatus to perform the object search method according to the first aspect.
According to an eighth aspect of embodiments of the present disclosure, there is provided a storage medium having instructions that, when executed by a processor of an object search apparatus, enable the object search apparatus to perform the object search method according to the second aspect.
According to a ninth aspect of the embodiments of the present disclosure, there is provided a computer program product which, when run on an electronic device, causes the electronic device to perform a method implementing the above aspects of the embodiments of the present disclosure and any possible design to which the aspects relate.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
according to the embodiment of the invention, the user can automatically search the target object from the candidate object set by triggering the search instruction in the live video interface and triggering the selection operation in the target video frame corresponding to the search instruction, and the recommendation information of the target object is displayed in the live video interface. In the process of watching the live broadcast, if a user needs to search for an article related to the live broadcast video, the user does not need to exit the current live broadcast interface and go to other platforms to manually search for a target object, so that the target object needing to be searched can be quickly searched, and a flexible object searching mode is provided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
FIG. 1 is a schematic diagram illustrating an object search system in accordance with an exemplary embodiment;
FIG. 2 is a schematic diagram of a live video interface of a target account, shown in accordance with an exemplary embodiment;
FIG. 3 is a diagram illustrating a live video interface with a user touch in a target account, according to an example embodiment;
FIG. 4 is a diagram illustrating a live video interface showing recommendation information for a target object, according to an illustrative embodiment;
FIG. 5 is a schematic diagram of a live video interface of a target account, shown in accordance with an exemplary embodiment;
FIG. 6 is a diagram illustrating a user gesture in a live video interface of a target account, according to an illustrative embodiment;
FIG. 7 is a flow diagram illustrating client-server interaction in a method for object searching, according to an exemplary embodiment;
FIG. 8 is a flow diagram illustrating client-server interaction in a method for object searching, according to an exemplary embodiment;
FIG. 9 is a flow diagram illustrating a method of object searching in accordance with an exemplary embodiment;
FIG. 10 is a block diagram illustrating an object search apparatus in accordance with an exemplary embodiment;
FIG. 11 is a block diagram illustrating an object search apparatus 1100 in accordance with an exemplary embodiment;
FIG. 12 is a block diagram illustrating an object search apparatus in accordance with an exemplary embodiment;
fig. 13 is a block diagram illustrating an object search apparatus 1300 according to an exemplary embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Hereinafter, some terms in the embodiments of the present disclosure are explained to facilitate understanding by those skilled in the art.
(1) The term "plurality" in the embodiments of the present disclosure means two or more, and other terms are similar thereto.
(2) "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
(3) A server serving the terminal, the contents of the service such as providing resources to the terminal, storing terminal data; the server is corresponding to the application program installed on the terminal and is matched with the application program on the terminal to run.
(4) The client may refer to an APP (Application) of a software class, or may refer to a terminal device. The system is provided with a visual display interface and can interact with a user; is corresponding to the server, and provides local service for the client. For software applications, except some applications that are only run locally, the software applications are generally installed on a common client terminal and need to be run in cooperation with a server terminal. After the internet has developed, more common applications include e-mail clients for e-mail receiving and sending, and instant messaging clients. For such applications, a corresponding server and a corresponding service program are required in the network to provide corresponding services, such as database services, configuration parameter services, and the like, so that a specific communication connection needs to be established between the client terminal and the server terminal to ensure the normal operation of the application program.
In the related technology, when a user watches the live broadcast of a main broadcast in a live broadcast room, if a certain article in the live broadcast room needs to be searched, the user can only perform manual search by capturing the image of the article in the live broadcast room and then going to other platforms, and the searching mode flow is too complicated.
In view of the above, fig. 1 is a schematic diagram illustrating an object search system according to an exemplary embodiment, and as shown in fig. 1, the system includes a live client 10 and a server 20.
The live broadcast client 10 responds to a search instruction triggered by a target account, wherein a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame are determined according to the search instruction, a reference object to be referred to for object search is determined from the target video frame according to the position information, attribute information of the reference object is identified, and the attribute information of the reference object is sent to the server 20; the server 20 searches out a target object from the candidate object set according to the attribute information of the reference object, and sends recommendation information of the target object to the live broadcast client 10; the live client 10 displays recommendation information of the target object in a live video interface.
Or, the live broadcast client 10 responds to a search instruction triggered by the target account through the live broadcast video interface, wherein a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame are determined according to the search instruction, and the target video frame and the position information corresponding to the search instruction are sent to the server 20; the server 20 determines a reference object to be referred to for object search from the target video frame according to the position information, identifies attribute information of the reference object, searches a target object from the candidate object set according to the attribute information of the reference object, and sends recommendation information of the target object to the live broadcast client 10; the live client 10 displays recommendation information of the target object in a live video interface.
Because the embodiment of the disclosure can respond to the search instruction triggered by the target account, and then the recommendation information of the target object corresponding to the search instruction is displayed on the live video interface, when a user watches the live video, if the user needs to search for an article related to the live video, the user does not need to exit the current live video interface and go to other platforms to manually search for the target object, so that the target object needing to be searched can be quickly searched.
An embodiment of the present disclosure provides an object search method, which is applied to a client, and specifically includes:
and responding to a search instruction triggered by the target account, and displaying recommendation information of the target object corresponding to the search instruction on a live video interface.
The target object is searched from the candidate object set according to a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame; the target video frame is a video frame displayed in a live video interface within a preset time length after the target account triggers the search instruction.
In some embodiments, the target account may trigger a selection operation in the target video frame by:
In this way, a touch operation triggered by the target account in the target video frame is taken as a selection operation; and the position information corresponding to the selection operation is touch position information of touch operation triggered by the target account in the target video frame.
Exemplarily, as shown in fig. 2, a schematic diagram of a live video interface of a target account is shown, and a client detects a touch operation in the live video interface; for example, as shown in fig. 3, a schematic view of a live video interface where a user performs a touch operation is shown, where a position in which the touch operation is displayed in fig. 3 is located in a jacket of a main broadcast in the live video interface, and a target object is the jacket; and the client responds to a search instruction triggered by the target account through the live video interface and searches out the target object from the candidate object set according to the position information of the touch operation, and the recommendation information of the target object is displayed on the live video interface. As shown in fig. 4, which shows a schematic view of a live video interface showing recommendation information of a target object, the recommendation information of a purchase jacket is displayed beside a main-play jacket in fig. 4.
Mode 2, the target account triggers an air-break operation in the target video frame.
In this way, the blank operation triggered by the target account in the target video frame is taken as the selection operation; and the position information corresponding to the selection operation is the position information corresponding to the space operation triggered by the target account in the target video frame.
For example, the user of the target account may trigger an air-break operation in the air on a terminal screen displaying a live video, where the air-break operation may be a single click, a double click, or a preset gesture.
In some embodiments, the recommendation information of the target object includes at least one of description information of the target object, a link address; the link address is the address of the webpage containing the description information of the target object.
For example, when the target object is the overcoat in the above example, the description information of the target object may include: the material of the outer sleeve and the composition of the material; the link address may be a web page address for purchasing the jacket, and here, a plurality of link addresses may be included so that the user has more choices.
The following describes a manner in which the target account triggers a search instruction and a selection operation, taking the selection operation as a touch operation as an example:
after a search instruction triggered by a target account is detected, detecting touch operation in a live video interface; and after detecting that the target account triggers touch operation in a target video frame displayed in the live video interface, displaying recommendation information of a target object corresponding to the search instruction on the live video interface.
Exemplarily, as shown in fig. 5, a schematic view of a live video interface of a target account is shown, when a client detects that a target account triggers a search instruction of "search for the same money" in the live video interface, a search function of "search for the same money" is started, then a touch operation in the live video interface is detected, if a touch operation triggered in the live video interface is detected, such as the position information of the touch operation shown in fig. 3, a target object is searched from a candidate object set according to the position information of the touch operation, and recommendation information of the target object is displayed in the live video interface.
The search instruction of the embodiment of the present disclosure may be triggered in the following manner:
the method comprises the following steps that 1, a search instruction is triggered by a target account through a search view;
the mode 2, the search instruction is triggered by the target account through a voice command mode;
mode 3, the search instruction is triggered by the target account through a preset gesture.
Here, when the search instruction is a case where the target account is triggered by the search view, the search instruction is triggered by triggering the search view of "search for the same money" as shown in fig. 5; when the search instruction is a case that the target account is triggered by means of a voice command, a voice button of 'what to say …', as shown in fig. 5, triggers the search instruction by triggering a voice button of 'what to say …'; when the search instruction is triggered by the target account through a preset gesture, as shown in fig. 6, two fingers trigger the live video interface according to the preset gesture, and the search instruction is triggered, where the preset gesture may be one or more of gestures such as a downward stroke, an upward stroke, a leftward stroke, and a rightward stroke of the two fingers at the same time, and a specific gesture is not limited herein and may be adjusted according to an actual application scenario.
Optionally, in an embodiment of the present disclosure, as shown in fig. 7, an interaction flowchart of a client and a server in an object search method shown in an embodiment is shown, and the specific steps are as follows:
s701, the live broadcast client responds to a search instruction triggered by a target account, and determines a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame.
For example, as shown in fig. 3, when the selection operation is a touch operation triggered by a target account in a target video frame, the position of the touch operation is displayed in a jacket of a main broadcast in a live video interface, after the client responds to a search instruction triggered by the target account, it is determined that the current live video interface in fig. 3 is the target video frame, and the touch position information is position information of the current live video interface touched by a hand in fig. 3.
S702, the live broadcast client determines a reference object to be referred to for object search from the target video frame according to the position information, and identifies the attribute information of the reference object.
When identifying the attribute information of the reference object, an optional implementation manner is that the position information and the target video frame are input into the trained identification model, and the attribute information of the reference object output by the trained identification model is obtained;
in implementation, the trained recognition model can perform target detection on a target video frame to detect an object in the target video frame; wherein, the object in the target video frame can be all objects except the background, such as people, animals, plants, buildings, etc. in the target video frame; alternatively, for example, when the target video frame is a video frame including a person, the object in the target video frame may be an object such as a head, a jacket, trousers, or shoes.
Selecting a reference object selected by a user from the objects detected in the target video frame by the trained recognition model according to the position information;
after the reference object in the target video frame is determined, the trained recognition model further recognizes the reference object to obtain the attribute information of the reference object.
In an optional implementation manner, the recognition model in the embodiment of the present disclosure includes an object detection network and an information recognition network; the object detection network is used for selecting a reference object selected by a user from the objects detected in the target video frame according to the position information; the information identification network is used for identifying the reference object to obtain attribute information of the reference object;
the object detection network may be a convolutional neural network, and the information identification network may be a fully-connected network.
Illustratively, the selection operation is a touch operation triggered by the target account in the target video frame, and when the area of an item is small, the touch position information in the target video frame may be touched by the item and other items, at this time, the touch position information in the target video frame may correspond to a plurality of items, and when the area of the item is large, the touch position information in the target video frame may correspond to only one item. For example, the touch position information in the target video frame shown in fig. 3 corresponds to the outer casing.
The embodiment of the disclosure can obtain the recognition model through the following training modes:
acquiring a training sample set, wherein the training sample set comprises a plurality of groups of training samples, each group of training samples comprises a sample video frame, sample position information and pre-labeled attribute information of a sample object corresponding to the sample position information in the sample video frame;
acquiring a plurality of groups of training samples from a training sample set, respectively inputting the training samples into a recognition model, and acquiring output attribute information corresponding to each group of training samples; and determining a sample loss value according to the output attribute information and the attribute information of the pre-labeled sample object, and adjusting the model parameters of the recognition model according to the sample loss value until the determined sample loss value is within a preset range to obtain the trained recognition model.
Exemplarily, as shown in fig. 3, the reference object is a coat, and the attribute information of the reference object may be a lady, a chant, a geometric stitching pattern.
And S703, the live broadcast client sends the attribute information of the reference object to the server.
S704, the server searches out the target object from the candidate object set according to the attribute information of the reference object.
When searching for the target object from the candidate object set according to the attribute information of the reference object, an optional implementation manner is to calculate a similarity between the attribute information of the reference object and the attribute information of each candidate object in the candidate object set, and determine that the similarity is higher than a preset threshold as the target object.
Exemplarily, the attribute information of the reference object is a lady, a long and geometric stitching pattern, and after comparing the attribute information of each candidate object in the candidate object set, the similarity between the attribute information of the candidate object 1 and the attribute information of the reference object is 70%, the similarity between the attribute information of the candidate object 2 and the attribute information of the reference object is 90%, and the preset threshold is 80%, then the candidate object 2 is determined as the target object.
S705, the server sends recommendation information of the target object to the live client.
And S706, after receiving the recommendation information of the target object returned by the server, the live broadcast client displays the recommendation information of the target object corresponding to the search instruction on a live broadcast video interface.
Specifically, the server determines recommendation information of the target object according to the target object and the preset relationship. The preset relationship is a mapping relationship between the object and the recommendation information of the object.
In the object searching method provided by this embodiment, first, in response to a search instruction triggered by a target account, a target video frame corresponding to the search instruction and location information corresponding to a selection operation triggered by the target account in the target video frame are determined; and then according to the position information, determining a reference object which needs to be referred to for object search from the target video frame, identifying attribute information of the reference object, sending the attribute information of the reference object to the server, so that the server searches out the target object from the candidate object set according to the attribute information of the reference object, and finally displaying recommendation information of the target object corresponding to the search instruction on a live video interface after receiving the recommendation information of the target object returned by the server. By the object searching method provided by the embodiment, the target account can timely and accurately acquire the recommendation information of the target object in the live video interface.
Optionally, in an embodiment of the present disclosure, as shown in fig. 8, an interaction flowchart of a client and a server in an object search method shown in an embodiment is shown, and the specific steps include:
s801, the live broadcast client responds to a search instruction triggered by a target account, and determines a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame.
S802, the live broadcast client sends a target video frame corresponding to the search instruction and position information corresponding to the selection operation triggered by the target account in the target video frame to the server.
And S803, the server determines a reference object which needs to be referred to for object search from the target video frame according to the position information, and searches the target object from the candidate object set according to the attribute information of the reference object.
S804, the server sends recommendation information of the target object to the live client.
And S805, after receiving the recommendation information of the target object returned by the server, the live broadcast client displays the recommendation information of the target object corresponding to the search instruction on a live broadcast video interface.
Here, the detailed implementation of steps S801 to S805 may refer to steps S701 to S706, which are not described herein again. Optionally, in an embodiment of the present disclosure, as shown in fig. 9, a flowchart of an object search method shown in an embodiment is shown, and is applied to a server, where the specific steps include:
s901, determines attribute information of the reference object.
The reference object is an object to be referred to for object search determined from the target video frame according to the target video frame corresponding to the search instruction and the position information corresponding to the selection operation triggered by the target account in the target video frame; the search instruction is an instruction triggered by the target account through the client; the target video frame is a video frame displayed in a live video interface within a preset time length after the target account triggers the search instruction.
Here, the attribute information of the reference object may be determined by any one of the following manners:
receiving attribute information of a reference object sent by a client in a first mode; the attribute information of the reference object is obtained by the client through determining and identifying the reference object from the target video frame according to the position information.
And secondly, receiving the target video frame and the position information sent by the client, determining the reference object from the target video frame according to the position information, and identifying the attribute information of the reference object.
S902, searching out the target object from the candidate object set according to the attribute information of the reference object.
And S903, sending the recommendation information of the target object to the client so that the client displays the recommendation information of the target object in a live video interface.
Specifically, the recommendation information of the target object includes at least one of description information and a link address of the target object; the link address is the address of the webpage containing the description information of the target object.
For example, when the target object is the overcoat in the above example, the description information of the target object may include: the material of the outer sleeve and the composition of the material; the link address may be a web page address for purchasing the jacket, and here, a plurality of link addresses may be included so that the user has more choices.
Fig. 10 is a block diagram illustrating an object search apparatus according to an exemplary embodiment. Referring to fig. 10, the apparatus includes: detection unit 1001, show unit 1002.
A detection unit 1001 configured to execute a search instruction to detect a target account trigger;
the display unit 1002 is configured to execute a search instruction triggered by a target account, and display recommendation information of a target object corresponding to the search instruction on a live video interface;
the target object is searched from the candidate object set according to a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame; the target video frame is a video frame displayed in a live video interface within a preset time length after the target account triggers the search instruction.
In an optional embodiment, the selecting operation is a touch operation triggered by the target account in the target video frame, and the presenting unit 1002 is configured to perform:
after a search instruction triggered by a target account is detected, detecting touch operation in a live video interface; and detecting a touch operation triggered by the target account in a target video frame displayed in the live video interface.
In an optional embodiment, the search instruction is triggered by the target account through a search view; or
The search instruction is triggered by the target account through a voice command; or
The search instruction is triggered by the target account through a preset gesture.
In an optional embodiment, the recommendation information of the target object includes at least one of description information and a link address of the target object; the link address is the address of the webpage containing the description information of the target object.
In an alternative embodiment, the presentation unit 1002 is configured to perform:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
according to the position information, determining a reference object to be referred to for object search from the target video frame, and identifying attribute information of the reference object;
sending the attribute information of the reference object to a server so that the server searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on a live video interface.
In an alternative embodiment, the presentation unit 1002 is configured to perform:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
sending the target video frame and the position information corresponding to the search instruction to a server so that the server determines a reference object to be referred to for object search from the target video frame according to the position information and searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on a live video interface.
With regard to the object search apparatus in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 11 is a block diagram illustrating an object search apparatus 1100 according to an exemplary embodiment, including:
a processor 1101 and a memory 1102 for storing instructions executable by the processor 1101;
wherein the processor 1101 is configured to execute the instructions to implement the object search method as in the above embodiments.
In an exemplary embodiment, there is also provided a computer storage medium comprising instructions, such as a memory 1102 comprising instructions, executable by a processor 1101 of an object search apparatus 1100 to perform the object search method described above. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is further provided, which, when run on an electronic device, causes the electronic device to execute any possible object search method that implements the auxiliary client side mentioned above in the embodiments of the present disclosure.
Based on the same inventive concept, the embodiment of the present disclosure further provides an object search apparatus, and as the apparatus corresponds to a server in the object search system of the embodiment of the present disclosure, and the principle of the apparatus to solve the problem is similar to the method, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not repeated.
Fig. 12 is a block diagram illustrating an object search apparatus according to an exemplary embodiment. Referring to fig. 12, the apparatus includes: a determination unit 1201, a search unit 1202, and a transmission unit 1203.
A determining unit 1201 configured to perform determining attribute information of a reference object; the reference object is an object to be referred to for object search determined from the target video frame according to the target video frame corresponding to the search instruction and the position information corresponding to the selection operation triggered by the target account in the target video frame; the search instruction is an instruction triggered by the target account through the client; the target video frame is a video frame displayed in a live broadcast video interface within a preset time length after the target account triggers the search instruction;
a search unit 1202 configured to perform a search for a target object from the candidate object set according to the attribute information of the reference object;
a sending unit 1203 configured to execute sending the recommendation information of the target object to the client, so that the client presents the recommendation information of the target object in the live video interface.
In an optional embodiment, the determining unit 1201 is configured to perform:
receiving attribute information of a reference object sent by a client; the attribute information of the reference object is obtained by the client side through determining and identifying the reference object from the target video frame according to the position information; or
And receiving the target video frame and the position information sent by the client, determining a reference object from the target video frame according to the position information, and identifying the attribute information of the reference object.
In an optional embodiment, the recommendation information of the target object includes at least one of description information and a link address of the target object; the link address is the address of the webpage containing the description information of the target object.
Fig. 13 is a block diagram illustrating an object search apparatus 1300 according to an exemplary embodiment, including:
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 object search method as in the above embodiments.
In an exemplary embodiment, there is also provided a computer storage medium comprising instructions, such as a memory 1302 comprising instructions, executable by the processor 1301 of the object search apparatus 1300 to perform the object search method described above. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is further provided, which, when run on an electronic device, causes the electronic device to execute any possible object search method that implements the auxiliary client side mentioned above in the embodiments of the present disclosure.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. An object searching method is applied to a client and comprises the following steps:
responding to a search instruction triggered by a target account, and displaying recommendation information of a target object corresponding to the search instruction on the live video interface;
the target object is searched from a candidate object set according to a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame; the target video frame is a video frame displayed in the live video interface within a preset time length after the target account triggers the search instruction.
2. The method of claim 1, wherein the selection operation is a touch operation triggered by the target account in the target video frame; before the live video interface displays the recommendation information of the target object corresponding to the search instruction, the method further includes:
after the search instruction triggered by the target account is detected, detecting touch operation in the live video interface; and detecting a touch operation triggered by the target account in the target video frame displayed in the live video interface.
3. The method of claim 1, wherein the presenting, in response to a search instruction triggered by a target account, recommendation information of a target object corresponding to the search instruction on the live video interface comprises:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
according to the position information, determining a reference object which needs to be referred to for object search from the target video frame, and identifying attribute information of the reference object;
sending the attribute information of the reference object to a server so that the server searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on the live video interface.
4. The method of claim 1, wherein the presenting, in response to a search instruction triggered by a target account, recommendation information of a target object corresponding to the search instruction on the live video interface comprises:
responding to a search instruction triggered by a target account, and determining a target video frame corresponding to the search instruction and position information corresponding to a selection operation triggered by the target account in the target video frame;
sending the target video frame and the position information corresponding to the search instruction to a server, so that the server determines a reference object to be referred to for object search from the target video frame according to the position information, and searches a target object from the candidate object set according to the attribute information of the reference object;
and after receiving the recommendation information of the target object returned by the server, displaying the recommendation information of the target object corresponding to the search instruction on the live video interface.
5. An object searching method is applied to a server and comprises the following steps:
determining attribute information of a reference object; the reference object is an object to be referenced for object search determined from the target video frame according to the target video frame corresponding to the search instruction and the position information corresponding to the selection operation triggered by the target account in the target video frame; the search instruction is an instruction triggered by the target account through a client; the target video frame is a video frame displayed in a live broadcast video interface within a preset time length after the target account triggers the search instruction;
searching a target object from a candidate object set according to the attribute information of the reference object;
and sending the recommendation information of the target object to a client so that the client displays the recommendation information of the target object in the live video interface.
6. An object search apparatus, comprising:
the detection unit is configured to execute a search instruction triggered by the detection target account;
the display unit is configured to execute a search instruction triggered by a target account, and display recommendation information of a target object corresponding to the search instruction on the live video interface;
the target object is searched from a candidate object set according to a target video frame corresponding to the search instruction and position information corresponding to selection operation triggered by the target account in the target video frame; the target video frame is a video frame displayed in the live video interface within a preset time length after the target account triggers the search instruction.
7. An object search apparatus, comprising:
a determination unit configured to perform determination of attribute information of a reference object; the reference object is an object to be referenced for object search determined from the target video frame according to the target video frame corresponding to the search instruction and the position information corresponding to the selection operation triggered by the target account in the target video frame; the search instruction is an instruction triggered by the target account through a client; the target video frame is a video frame displayed in a live broadcast video interface within a preset time length after the target account triggers the search instruction;
a searching unit configured to perform a search for a target object from a set of candidate objects according to attribute information of the reference object;
and the sending unit is configured to send the recommendation information of the target object to the client so that the client displays the recommendation information of the target object in the live video interface.
8. An object search apparatus, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the object search method of any one of claims 1 to 4.
9. An object search apparatus, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the object search method of claim 5.
10. A computer storage medium, wherein instructions in the computer storage medium, when executed by a processor of an object search apparatus, enable the object search apparatus to perform the object search method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011560437.2A CN112699274A (en) | 2020-12-25 | 2020-12-25 | Object searching method and device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011560437.2A CN112699274A (en) | 2020-12-25 | 2020-12-25 | Object searching method and device and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112699274A true CN112699274A (en) | 2021-04-23 |
Family
ID=75510409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011560437.2A Pending CN112699274A (en) | 2020-12-25 | 2020-12-25 | Object searching method and device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112699274A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016153865A1 (en) * | 2015-03-25 | 2016-09-29 | Thomson Licensing | Method and apparatus for providing content recommendation |
| CN109344299A (en) * | 2018-11-12 | 2019-02-15 | 考拉征信服务有限公司 | Object search method, apparatus, electronic equipment and computer readable storage medium |
| CN110121093A (en) * | 2018-02-06 | 2019-08-13 | 优酷网络技术（北京）有限公司 | The searching method and device of target object in video |
| CN110225387A (en) * | 2019-05-20 | 2019-09-10 | 北京奇艺世纪科技有限公司 | A kind of information search method, device and electronic equipment |
| CN111198961A (en) * | 2018-11-16 | 2020-05-26 | 北京京东尚科信息技术有限公司 | Commodity searching method and device and server |
-
2020
- 2020-12-25 CN CN202011560437.2A patent/CN112699274A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016153865A1 (en) * | 2015-03-25 | 2016-09-29 | Thomson Licensing | Method and apparatus for providing content recommendation |
| CN110121093A (en) * | 2018-02-06 | 2019-08-13 | 优酷网络技术（北京）有限公司 | The searching method and device of target object in video |
| CN109344299A (en) * | 2018-11-12 | 2019-02-15 | 考拉征信服务有限公司 | Object search method, apparatus, electronic equipment and computer readable storage medium |
| CN111198961A (en) * | 2018-11-16 | 2020-05-26 | 北京京东尚科信息技术有限公司 | Commodity searching method and device and server |
| CN110225387A (en) * | 2019-05-20 | 2019-09-10 | 北京奇艺世纪科技有限公司 | A kind of information search method, device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110362714B (en) | Video content searching method and device | |
| US20190102952A1 (en) | Identifying augmented reality visuals influencing user behavior in virtual-commerce environments | |
| CN110716645A (en) | Augmented reality data presentation method and device, electronic equipment and storage medium | |
| CN112104899A (en) | Information recommendation method and device in live broadcast, electronic equipment and storage medium | |
| CN106598998B (en) | Information acquisition method and information acquisition device | |
| US20200342320A1 (en) | Non-binary gender filter | |
| KR102340228B1 (en) | Message service providing method for message service linking search service and message server and user device for performing the method | |
| US20170270506A1 (en) | Display terminal-based data processing method | |
| JP2003271084A (en) | Apparatus and method for providing information | |
| KR102246109B1 (en) | Product recommendation system and method based on consumer preference | |
| CN110431514A (en) | System and method for context driven intelligence | |
| KR20190065197A (en) | Method for creating web documents and Apparatus thereof | |
| CN112632349B (en) | Exhibition area indication method and device, electronic equipment and storage medium | |
| US20180276731A1 (en) | System and Method for Automated Product Recommendations | |
| CN110998507B (en) | Electronic device and method for providing search results | |
| CN111199443A (en) | Commodity information processing method, commodity information processing device and computer-readable storage medium | |
| CN114816180A (en) | Content browsing guiding method and device, electronic equipment and storage medium | |
| EP3800561A1 (en) | Electronic device and control method for electronic device | |
| CN104965633B (en) | A kind of method and apparatus that service jumps | |
| CN112699274A (en) | Object searching method and device and computer storage medium | |
| US20210366172A1 (en) | Commodity guiding method, electronic device and storage medium | |
| KR20160029603A (en) | Apparatus, system, method, program for providing searching service | |
| CN113129112A (en) | Article recommendation method and device and electronic equipment | |
| KR20220150140A (en) | Pagetalk-based multi-user e-commerce platform providing device and method by simultaneous connection | |
| US20240152211A1 (en) | Touchless engagement system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |