WO2021073328A1 - 视频搜索的方法及装置、终端和存储介质 - Google Patents

视频搜索的方法及装置、终端和存储介质 Download PDF

Info

Publication number
WO2021073328A1
WO2021073328A1 PCT/CN2020/114799 CN2020114799W WO2021073328A1 WO 2021073328 A1 WO2021073328 A1 WO 2021073328A1 CN 2020114799 W CN2020114799 W CN 2020114799W WO 2021073328 A1 WO2021073328 A1 WO 2021073328A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
searched
video image
result
page
Prior art date
Application number
PCT/CN2020/114799
Other languages
English (en)
French (fr)
Inventor
王子昂
张永华
王晓露
Original Assignee
北京字节跳动网络技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京字节跳动网络技术有限公司 filed Critical 北京字节跳动网络技术有限公司
Priority to JP2022522608A priority Critical patent/JP7488333B2/ja
Publication of WO2021073328A1 publication Critical patent/WO2021073328A1/zh
Priority to US17/722,334 priority patent/US11630861B2/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73Querying
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73Querying
    • G06F16/738Presentation of query results

Definitions

  • the present disclosure relates to the field of computer technology, and in particular to a method and device, terminal and storage medium for video search.
  • the current image recognition technology is to transfer the photo to the server after taking a picture, and then the server will identify and search the objects or people in the picture, and then return the search results to the sender. For the time being, there is no implementation scheme for searching based on video.
  • the present disclosure provides a video search method and device, terminal and storage medium.
  • the present disclosure adopts the following technical solutions.
  • the present disclosure provides a video search method, including:
  • the first recommendation result corresponding to the first target to be searched is acquired, and the first recommendation result is displayed on a search result page.
  • the present disclosure provides a video search device, including:
  • the receiving module is used to receive the first event generated when the first control is triggered;
  • the acquiring module is used to acquire the current video image frame played in the video playback page when the first event is triggered, the first target to be searched located by the second control in the current video image frame, and the first target to be searched.
  • the display module is used to display the first recommendation result on the search result page.
  • the present disclosure provides a terminal, including: at least one memory and at least one processor;
  • the memory is used to store program code
  • the processor is used to call the program code stored in the memory to execute the above method.
  • the present disclosure provides a storage medium, the storage medium is used to store program code, and the program code is used to execute the above-mentioned method.
  • the video search method provided by the present disclosure can classify and recognize video image frames according to the selected current video content.
  • the recognized content includes people and objects displayed in all video images, and can also be people and objects within a selected area.
  • the embodiments of the present disclosure can facilitate the user to obtain the commodity and character information in the video.
  • Fig. 1 is a flowchart of a video search method according to an embodiment of the present disclosure.
  • Fig. 2 is a schematic diagram of a video image frame being played on a video playback page of an embodiment of the present disclosure.
  • Fig. 3 is a schematic diagram of a first control transformed into a second control in an embodiment of the present disclosure.
  • Fig. 4 is a schematic diagram of a search result page of an embodiment of the present disclosure.
  • Fig. 5 is a schematic diagram of a search result page according to another embodiment of the present disclosure.
  • Fig. 6 is a schematic diagram of a search result page according to still another embodiment of the present disclosure.
  • FIG. 7 is a schematic diagram of replacing the target to be searched in an embodiment of the present disclosure.
  • Fig. 8 is a schematic structural diagram of a video search device according to an embodiment of the present disclosure.
  • FIG. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.
  • FIG. 1 is a flowchart of a video search method according to an embodiment of the present disclosure, which includes the following steps.
  • S100 In the video playback page, receive a first event generated when a first control is triggered.
  • FIG. 2 is a schematic diagram of a video image frame being played on a video playback page of an embodiment of the present disclosure.
  • the embodiment of the present disclosure may include the first control as the startup path, for example, it may be a frame selection button or a picture recognition button on the running terminal of the program.
  • the difference between the frame selection button and the image recognition button is that clicking the image recognition button can send the automatic recognition instruction information, that is, automatically select the information that is considered valid in a frame; and the frame selection button can be a frame of the image selected by the user Part of the information.
  • the acquisition instruction may be issued by clicking the first control as shown in FIG.
  • the first control shown is presented in the form of a circular icon.
  • the first control may also appear in other forms, and is not limited to the form of a circle or an icon.
  • the first event may include that the first control is activated to display in a manner such as a shape change; it may also include, for example, lowering the brightness of the display area other than the first control for display; of course, the above example is only used as
  • the embodiments of the present disclosure may also include other methods for activating the display, and are not limited to those described in the previous example.
  • the playback is stopped, the playback of the video file can be stopped, and the corresponding acquired video image frame is determined.
  • the time stamp of the video playback at the moment of the trigger point is recorded, and the video image frame in the corresponding video file is determined according to the time stamp.
  • the second control may include at least one of a floating frame or a floating point.
  • the second control includes a floating box and a floating point;
  • the first target to be searched may include a first target and a second target.
  • the first target positioned by the floating frame and the second target positioned by the floating point in the current video image frame can be respectively obtained;
  • the display position of the first target in the current video image frame and the position of the second target The display position in the current video image frame; and the floating frame is displayed at the display position of the first object in the current video image frame, and the floating point is displayed at the display position of the second object in the current video image frame.
  • FIG. 3 is a schematic diagram of the first control transformed into the second control in the embodiment of the present disclosure.
  • box A and point B are the first target to be searched.
  • the first control can become, for example, a rectangle with rounded corners, and at the same time become larger and move in the direction of A, finally forming a rounded corner for positioning the A target Rectangular floating frame.
  • the video image frame can also be divided into a background part and a main part, and then the display parameters corresponding to the floating frame can be obtained, which can include the position information and size information of the floating frame, and specifically can include the upper left corner of the floating frame.
  • the first pixel is in the X coordinate of the video image frame
  • the first pixel in the upper left corner of the floating frame is in the Y coordinate of the video image frame
  • the length and width of the floating frame etc.
  • the floating frame can be positioned according to the position information and size determined on the video image frame by the above four display parameters.
  • the floating frame can be represented by the display start coordinates and the frame length and width, and the limited area of the floating frame can be set.
  • the floating frame of this embodiment may also be an irregular shape identified by the boundary, or determine the initial position and stroke path of the floating frame, and obtain the change relative to the change of the abscissa x Function f(x) and so on.
  • the embodiment of the present disclosure may not only include one target to be searched, but the first target to be searched may include A and B at the same time; further, the embodiment of the present disclosure does not limit the number of the first target to be searched, more or less
  • the first target to be searched for should also be included in the protection scope of the embodiments of the present disclosure; and the second control may not be limited to the form of a floating box or a floating point, and other reasonable forms of the second control can be considered as a simple replacement of the above-mentioned embodiment.
  • S400 Acquire a first recommendation result corresponding to the first target to be searched, and display the first recommendation result on a search result page.
  • the embodiment of the present disclosure may receive a second event generated by the second control being triggered; and in response to the second event, evoke a search result page; wherein the search result page at least partially covers the current video image frame and obscures the second event.
  • Two controls The first result to be recommended corresponding to the first target and the second result to be recommended corresponding to the second target are respectively obtained; the first tag used to identify the first target and the first recommended result are correspondingly displayed in the first search result page Within a region; and correspondingly displaying the second label for identifying the second target and the second recommendation result in the second region in the search result page.
  • the embodiment of the present disclosure may include the step of searching the first recommendation result corresponding to the second control when the second control is triggered, and calling out the search result page for displaying the first recommendation result.
  • the search result page can be partially or completely covered on the video image frame.
  • the related search results of people and objects can be displayed separately, or displayed in tab pages.
  • FIG. 4 is a schematic diagram of a search result page of an embodiment of the present disclosure.
  • the search result page shown in FIG. 4 includes the first result to be recommended corresponding to the first target A and the second result to be recommended corresponding to the second target B displayed in columns.
  • the first target A is a product, and the upper part of the search result page is the same or similar results corresponding to the product A; the second target B is a person, and the lower part of the search result page is a related video result corresponding to the person B.
  • the embodiment of the present disclosure may further include a first tag a for identifying the first target A and a second tag b for identifying the second target B.
  • the search result page may include, for example, one horizontal column and multiple vertical columns. Wherein, the horizontal column can display tags corresponding to different targets in the video, that is, corresponding to the commodities/persons in sequence.
  • the first label a when the first result to be recommended corresponding to the first target A is displayed, the first label a can be slightly enlarged as an identification; and when the second result to be recommended corresponding to the second target B is switched to display, the first result can be restored.
  • the vertical columns may respectively correspond to the horizontal columns, and each vertical column may respectively display other videos a related to the character A, and the same and similar items b of the product B in a vertical direction.
  • the horizontal column can be a fixed column or a scrolling column.
  • each label When there are not many recognition targets, each label can be arranged horizontally; when there are many recognition targets, it can be selectively displayed in a horizontal scroll mode.
  • vertical products/videos can also be arranged in a vertical scroll bar.
  • the character videos can be sorted, for example, by the click-through rate; and the product category can be arranged according to the similarity with the target product as described above, for example.
  • other permutation logic may also be used, as long as a reasonable result is obtained.
  • the first results to be recommended may be presented in two columns as shown in the figure, or arranged in other arrangements. The embodiment of the present disclosure does not limit the arrangement of the results.
  • the order of arrangement for example, can be based on the similarity score, as a basis for sorting multiple search results, and results with high similarity can be ranked first.
  • Other factors that affect rankings may also include, for example, video playback volume, etc., which are not limited here.
  • the first target to be searched may also include valid targets and invalid targets.
  • all the video image frames in the video played on the video playback page can also be obtained; and the effective target in each video image frame can be obtained to obtain a global result; among them, the effective target includes characters, commodities, and items in the At least one; an invalid target is a target result other than a valid target.
  • the embodiments of the present disclosure may classify the first target to be searched by sieving targets by models such as multi-path detection models, which may specifically be commodity detection models, face detection models, and article detection models. Among them, the model may include, for example, facial feature information, product feature information, and so on. Then divide the first target to be searched into at least one category.
  • the first target to be searched is a valid target, obtain the first recommended result corresponding to the valid target, and display the first recommended result on the search result page; if the first target to be searched is an invalid target, display None on the search results page Results; or if the first target to be searched is a valid target, obtain the first recommended result corresponding to the valid target, and sequentially display the first recommended result and the global results other than the first recommended result in the search results page; such as the first The target to be searched is an invalid target, and the global result is displayed on the search result page.
  • the acquisition of the first recommendation result in the embodiment of the present disclosure may include online acquisition and offline acquisition.
  • the first recommendation result may be data stored on the server or locally, such as item introduction, purchase link, or person-related video, or other related information.
  • the returned result can be the recognized area coordinates and the recognized effective target. If the server does not have the relevant cache of the video file, the server can perform online recognition in real time, compare features with the products in the server, for example, the products in the product library, and then return the same or similar product results; if the relevant content is identified as a person, it can be extracted For example, the face information is used to search for other videos containing the image or name of the person by video feature.
  • the relevant results can be transmitted through the client interface.
  • the client for example, a program installed on a mobile phone
  • it can also directly call its own product library according to the recognition result; further, an external link can also be set in the own product library, which can be accessed through the external link.
  • the link jumps to, for example, applets, other apps, or web pages.
  • the offline acquisition method includes acquiring the result of the current video image frame and returning the global search result at the same time. Among them, the online acquisition method may not be able to obtain effective results, that is, the product or character information cannot be recognized. Therefore, the user interface displays the prompt information as shown in FIG. 5.
  • FIG. 6 is a schematic diagram of a search result page according to still another embodiment of the present disclosure. In Figure 6, after the current results a and b, one of the global results c is also provided.
  • this embodiment can also set tags, which can not only help classification, but also serve as a basis for de-duplication, such as comparing the results of the same tag in the global results to determine whether they belong to the same item/person, or similar items / Similar people.
  • the former can return only one result as the result of deduplication; the latter can be classified into one category if it is similar.
  • the present disclosure may also include the step of re-determining the target to be searched.
  • the search result page is moved to the edge of the current video image frame and part of the search result page is hidden to display the second control. Detect whether the first display position of the second control is changed, if it changes, obtain the second display position of the second control; determine the corresponding second target to be searched according to the second display position; obtain the second target to be searched Corresponding second recommendation result; and then evoke the search result page, and replace the first recommendation result in the search result page with the second recommendation result.
  • FIG. 7 is a schematic diagram of changing the target to be searched in an embodiment of the present disclosure.
  • the search result page is partially hidden under the current video image frame.
  • the search result page can also be folded in other ways, which is not limited here. Move the position of the floating frame from A to G, and/or move the position of the floating point from B to H, thereby obtaining the second target to be searched.
  • the step of obtaining and displaying the second recommendation result from the second target to be searched may refer to the step of obtaining and displaying the first recommendation result from the first target to be searched, which will not be repeated here.
  • the embodiments of the present disclosure may also include a risk control model, which may specifically be a shielding mechanism provided with filtering features.
  • a risk control model which may specifically be a shielding mechanism provided with filtering features.
  • the filtering criteria can be violent shots, exposed images, or masking when the recognized facial features involve privacy. More specifically, it can be that the face detection model only includes the celebrity atlas, and when the detection result is related to the face When the detection model does not match, the filter feature is added, and the result is neither detection nor search, so personal privacy can be protected.
  • the filtering criteria of the embodiments of the present disclosure are not limited to the above, and any reasonable filtering evaluation criteria can be included in the embodiments of the present disclosure.
  • the video search method provided by the embodiments of the present disclosure can be used for online detection or offline detection.
  • the detection and search results can be linked with the commodity library, which can help merchants better arrange consumption stock and consumption increase, and optimize product structure.
  • the video server it can also play a role as a hot guide and a flow guide, so that content providers can arrange content services more reasonably.
  • a content ranking strategy can be established based on the returned results, and a rule generator can be automatically established based on, for example, the amount of likes and content quality.
  • an embodiment of the present disclosure also provides a video search device 10, which may include a receiving module 30, an acquiring module 50, and a display module 70.
  • the receiving module 30 can be used to receive the first event generated when the first control is triggered.
  • the acquiring module 50 can be used to acquire the current video image frame played in the video playback page when the first event is triggered, the first target to be searched located by the second control in the current video image frame, and the first target to be searched in the current video image.
  • the display module 70 can be used to display the first recommendation result on the search result page.
  • the relevant part can refer to the part of the description of the method embodiment.
  • the device embodiments described above are merely illustrative, and the modules described as separate modules may or may not be separate. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement it without creative work.
  • the visual detection and search method and device of the present disclosure have been described based on the embodiments and application examples.
  • the present disclosure also provides a terminal and storage medium, which are described below.
  • FIG. 9 shows a schematic structural diagram of an electronic device (such as a terminal device or a server) 800 suitable for implementing the embodiments of the present disclosure.
  • Terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 9 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device 800 may include a processing device (such as a central processing unit, a graphics processor, etc.) 801, which can be loaded into a random access device according to a program stored in a read-only memory (ROM) 802 or loaded from a storage device 808.
  • the program in the memory (RAM) 803 executes various appropriate actions and processing.
  • various programs and data required for the operation of the electronic device 800 are also stored.
  • the processing device 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804.
  • An input/output (I/O) interface 805 is also connected to the bus 804.
  • the following devices can be connected to the I/O interface 805: including input devices 806 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, vibration An output device 807 such as a device; a storage device 808 such as a magnetic tape, a hard disk, etc.; and a communication device 809.
  • the communication device 809 may allow the electronic device 800 to perform wireless or wired communication with other devices to exchange data.
  • FIG. 3 shows an electronic device 800 having various devices, it should be understood that it is not required to implement or have all of the illustrated devices. It may alternatively be implemented or provided with more or fewer devices.
  • an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device 809, or installed from the storage device 808, or installed from the ROM 802.
  • the processing device 801 the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.
  • the aforementioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium.
  • the computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device .
  • the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.
  • the client and server can communicate with any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium.
  • Communication e.g., communication network
  • Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), the Internet (for example, the Internet), and end-to-end networks (for example, ad hoc end-to-end networks), as well as any currently known or future research and development network of.
  • the above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.
  • the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, the electronic device is caused to execute the aforementioned method of the present disclosure.
  • the computer program code used to perform the operations of the present disclosure may be written in one or more programming languages or a combination thereof.
  • the above-mentioned programming languages include object-oriented programming languages—such as Java, Smalltalk, C++, and also conventional Procedural programming language-such as "C" language or similar programming language.
  • the program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).
  • LAN local area network
  • WAN wide area network
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions.
  • the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.
  • the units involved in the embodiments described in the present disclosure can be implemented in software or hardware. Among them, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.
  • exemplary types of hardware logic components include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.
  • FPGA Field Programmable Gate Array
  • ASIC Application Specific Integrated Circuit
  • ASSP Application Specific Standard Product
  • SOC System on Chip
  • CPLD Complex Programmable Logical device
  • a machine-readable medium may be a tangible medium, which may contain or store a program for use by the instruction execution system, apparatus, or device or in combination with the instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • the machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing.
  • machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage device or any suitable combination of the above.
  • a video search method including:
  • the first recommendation result corresponding to the first target to be searched is acquired, and the first recommendation result is displayed on a search result page.
  • the second control includes at least one of a floating frame or a floating point.
  • the first target to be searched includes a first target and a second target
  • the second control includes a floating frame and a floating point
  • the first to-be-searched target positioned by the second control in the current video image frame and the first display position of the first to-be-searched target in the current video image frame are acquired, in the first display position
  • the step of displaying the second control includes:
  • the floating frame is displayed at the display position of the first target in the current video image frame, and the floating point is displayed at the display position of the second target in the current video image frame.
  • a method characterized in that the first recommendation result corresponding to the first target to be searched is obtained, and the first recommendation result is displayed in the search result.
  • the steps on the page include:
  • a second label for identifying the second target and the second recommendation result are correspondingly displayed in the second area of the search result page.
  • the first target to be searched includes a valid target and an invalid target
  • the method further includes:
  • the effective target is at least one of a character, a commodity, and an article; the invalid target is a target result other than the effective target.
  • a method characterized in that the first recommendation result corresponding to the first target to be searched is obtained, and the first recommendation result is displayed in the search result.
  • the steps on the page also include:
  • the first target to be searched is a valid target
  • the first recommended result corresponding to the valid target is acquired, and the first recommended result is displayed on the search result page; as in the first to be searched
  • the target is an invalid target, and no results are displayed on the search results page; or
  • the first recommendation result corresponding to the valid target is acquired, and the first recommendation result and the global result other than the first recommendation result are displayed in sequence In the search result page; if the first target to be searched is an invalid target, the global result is displayed in the search result page.
  • a method characterized in that the first recommendation result corresponding to the first target to be searched is acquired, and the first recommendation result is displayed in the search Before the results page, it also includes:
  • the search result page at least partially covers the current video image frame and obscures the second control.
  • a method characterized in that the first recommendation result corresponding to the first target to be searched is acquired, and the first recommendation result is displayed in the search After the steps in the result page, it also includes:
  • a method characterized in that the method further includes:
  • search result page is aroused, and the first recommendation result in the search result page is replaced with the second recommendation result.
  • a video search device including:
  • the receiving module is used to receive the first event generated when the first control is triggered;
  • the acquiring module is used to acquire the current video image frame played in the video playback page when the first event is triggered, the first target to be searched located by the second control in the current video image frame, and the first target to be searched.
  • the display module is used to display the first recommendation result on the search result page.
  • a terminal including: at least one memory and at least one processor;
  • the at least one memory is used to store program code
  • the at least one processor is used to call the program code stored in the at least one memory to execute the method described in any one of the above items.
  • a storage medium is provided, the storage medium is used to store program code, and the program code is used to execute the above-mentioned method.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Library & Information Science (AREA)
  • User Interface Of Digital Computer (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本公开提供视频搜索的方法及装置、终端和存储介质。视频搜索的方法包括:在视频播放页面中,接收第一控件被触发产生的第一事件;响应所述第一事件,获取所述第一事件被触发时所述视频播放页面中所播放的当前视频图像帧;获取所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置,在所述第一显示位置显示所述第二控件;及获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中。本公开的视频搜索方法能够根据识别出视频中出现的人和物,解决分类问题,并搜索相似结果,方便用户获取视频中的商品及人物相关信息。

Description

视频搜索的方法及装置、终端和存储介质
相关申请的交叉引用
本申请要求于2019年10月17日提交的,申请号为201910990463.X、发明名称为“视频搜索的方法及装置、终端和存储介质”的中国专利申请的优先权,该申请的全文通过引用结合在本申请中。
技术领域
本公开涉及计算机技术领域,尤其涉及一种视频搜索的方法及装置、终端和存储介质。
背景技术
目前的识图技术是在拍照之后,将照片传输给服务器,然后由服务器对图片中的物品或人进行识别和搜索,再将搜索结果返回给发送端。暂时还没有一种基于视频进行搜索的实现方案。
发明内容
为解决现有问题,本公开提供一种视频搜索的方法及装置、终端和存储介质。
本公开采用以下的技术方案。
在一些实施例中,本公开提供一种视频搜索的方法,包括:
在视频播放页面中,接收第一控件被触发产生的第一事件;
响应所述第一事件,获取所述第一事件被触发时所述视频播放页面中所播放的当前视频图像帧;
获取所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置,在所述第一显示位置显示所述第二控件;及
获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中。
在一些实施例中,本公开提供一种视频搜索的装置,包括:
接收模块,用于接收第一控件被触发产生的第一事件;
获取模块,用于获取所述第一事件被触发时视频播放页面中所播放的当前视频图像帧、所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置、和所述第一待搜索目标对应的第一推荐结果;及
显示模块,用于将所述第一推荐结果显示在搜索结果页面中。
在一些实施例中,本公开提供一种终端,包括:至少一个存储器和至少一个处理器;
其中,存储器用于存储程序代码,处理器用于调用所述存储器所存储的程序代码执行上述的方法。
在一些实施例中,本公开提供一种存储介质,所述存储介质用于存储程序代码,所述程序代码用于执行上述的方法。
本公开提供的视频搜索方法能够根据选定当前视频内容,对视频图像帧进行分类识别,识别的内容包括全部视频图像中显示的人和物,也可以是选定区域范围内的人和物,本公开实施例能够方便用户获取视频中的商品及人物信息。
附图说明
结合附图并参考以下具体实施方式,本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中,相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的,元件和元素不一定按照比例绘制。
图1是本公开实施例的视频搜索方法的流程图。
图2是本公开实施例的视频播放页面播放到一视频图像帧的示意图。
图3是本公开实施例的第一控件转化为第二控件的示意图。
图4是本公开实施例的搜索结果页面的示意图。
图5是本公开另一实施例的搜索结果页面的示意图。
图6是本公开再一实施例的搜索结果页面的示意图。
图7是本公开实施例更换待搜索目标的示意图。
图8是本公开实施例的视频搜索装置的结构示意图。
图9是本公开实施例的电子设备的结构示意图。
具体实施方式
下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例,然而应当理解的是,本公开可以通过各种形式来实现,而且不应该被解释为限于这里阐述的实施例,相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是,本公开的附图及实施例仅用于示例性作用,并非用于限制本公开的保护范围。
应当理解,本公开的方法实施方式中记载的各个步骤可以按和/或并行执行。此外,方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。
本文使用的术语“包括”及其变形是开放性包括,即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”;术语“另一实施例”表示“至少一个另外的实施例”;术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。
需要注意,本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分,并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。
需要注意,本公开中提及的“一个”的修饰是示意性而非限制性的,本领域技术人员应当理解,除非在上下文另有明确指出,否则应该理解为“一个或多个”。
本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的,而并不是用于对这些消息或信息的范围进行限制。
以下将结合附图,对本申请实施例提供的方案进行详细描述。
如图1所示,图1是本公开实施例的视频搜索方法的流程图,包括如下步骤。
S100,在视频播放页面中,接收第一控件被触发产生的第一事件。
如图2所示,图2是本公开实施例的视频播放页面播放到一视频图像帧的示意图。具体地,本公开实施例可以包括第一控件作为启动路径,例如可以是程序在运行终端上的框选按钮或识图按钮。框选按钮与识图按钮的区别在于,点击识图按钮可以发送自动识别指令信息,即自动选中一帧中被认为有效的信息;而框选按钮可以是用户选定出的一帧图像中的一部分信息。更具体地,在视频播放到某一帧时,用户发出获取指令,在本公开实施例中,可以是通过点击如图2中所示的第一控件发出获取指令;可以理解,即使图2所示的第一控件以圆形图标的形式呈现,在本公开其它实施例中,第一控件也可以其它形式出现,而不限于圆形或图标的形式。相应地,第一事件可以包括第一控件被激活而以例如形状改变的方式进行展示;还可包括例如将除第一控件以外的显示区域的亮度调低进行展示;当然,以上示例仅用作举例说明,本公开实施例还可包括其它激活展示的方法,而不仅限于前例所述。
S200,响应所述第一事件,获取所述第一事件被触发时所述视频播放页面中所播放的当前视频图像帧。
在本公开实施例中,典型地例如可以是获取视频文件播放中的视频图像帧。具体地,根据用户发出的指令信息,例如触发第一控件而产生的控件形变或者亮度变化而停止播放,视频文件的播放可以中止,进而确定相应获取到的视频图像帧。再例如,记录触发点时刻的视频播放的时间戳,再根据时间戳确定对应视频文件中的视频图像帧。
S300,获取所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置,在所述第一显示位置显示所述第二控件。
其中,第二控件可包括浮动框或浮动点中的至少一个。具体在本公开实施例中,第二控件包括浮动框和浮动点;第一待搜索目标可包 括第一目标和第二目标。本实施例具体可分别获取当前视频图像帧中的由浮动框定位的第一目标和由浮动点定位的第二目标;获取第一目标在当前视频图像帧中的显示位置,以及第二目标在当前视频图像帧中的显示位置;及在第一目标在当前视频图像帧中的显示位置显示所述浮动框,和在第二目标在当前视频图像帧中的显示位置显示浮动点。更具体地,本公开实施例可通过触发第一控件唤出第二控件,第二控件可用于定位第一待搜索目标及其位置;或者,第二控件可以由第一控件转化而来。如图3所示,图3是本公开实施例的第一控件转化为第二控件的示意图。图中A框和B点为第一待搜索目标,当触发第一控件后,第一控件可以变为例如圆角矩形,并同时变大且向A方向移动,最终形成定位A目标的圆角矩形状的浮动框。在本公开实施例中,还可以将视频图像帧分为背景部分和主体部分,再获取浮动框对应的显示参数,其可以包括浮动框的位置信息和大小信息,具体可包括浮动框左上角的第一个像素在视频图像帧的X坐标、浮动框左上角的第一个像素在视频图像帧上的Y坐标、浮动框的长度和宽度等。可以再根据上述四个显示参数在视频图像帧上确定的位置信息和大小对浮动框进行定位。浮动框可以由显示起始坐标和框长度及宽度来表示,设定浮动框的限定区域。此外,除上述规则形状浮动框以外,本实施例的浮动框也可以是例如边界识别出的不规则形状,或确定浮动框的初始位置及划动路径,获取相对于横坐标x变化而变化的函数f(x)等。此外,本公开实施例可不仅包含一个待搜索目标,第一待搜索目标可以同时包括A和B;更进一步地,本公开实施例不限制第一待搜索目标的个数,更多或更少的第一待搜索目标也应包含在本公开实施例的保护范围内;且第二控件可不限于浮动框或浮动点的形式,其它合理形式的第二控件可认为是上述实施例的简单替换。
S400,获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中。
具体地,本公开实施例可接收第二控件被触发产生的第二事件;及响应于第二事件,唤起搜索结果页面;其中,搜索结果页面至少部分地覆盖于当前视频图像帧上并遮挡第二控件。分别获取第一目标对 应的第一待推荐结果和第二目标对应的第二待推荐结果;将用于标识第一目标的第一标签和第一推荐结果对应地显示在搜索结果页面中的第一区域内;及将用于标识第二目标的第二标签和第二推荐结果对应地显示在搜索结果页面中的第二区域内。更具体地,本公开实施例可包括第二控件被触发产生的对第二控件对应的第一推荐结果进行搜索的步骤,并呼出搜索结果页面,用于显示第一推荐结果。其中,搜索结果页面可部分地或全部覆盖于视频图像帧上。在本公开实施例中,一帧视频图像中有可能既识别出物品、又识别出人物。此时,人物和物品的相关搜索结果既可以分别显示,也可以分标签页进行显示。如图4所示,图4是本公开实施例的搜索结果页面的示意图。图4所示的搜索结果页面包括分栏显示的第一目标A对应的第一待推荐结果和第二目标B对应的第二待推荐结果。例如,第一目标A为商品,搜索结果页面的上部为对应商品A的同款或相似款结果;第二目标B为人物,搜索结果页面的下部为对应人物B的相关视频结果。本公开实施例还可包括用于标识第一目标A的第一标签a和用于标识第二目标B的第二标签b。搜索结果页面例如可以包括一个横栏与多个纵栏。其中,横栏可以显示视频中对应不同目标的标签,即依次分别对应所述商品/人物。如图所示,当显示第一目标A对应的第一待推荐结果时,可稍放大第一标签a作为标识;而切换显示第二目标B对应的第二待推荐结果时,可还原第一标签a的大小并放大第二标签b。,可以理解,在本公开其它实施例中,也可以采用其它对应形式,在此不做限定。相应地,纵栏可分别对应于横栏,每个纵栏可分别以垂直向显示例如与人物A相关的其它视频a、及商品B的同款与类似款b。横栏可以是固定栏或者滚动栏,当识别目标不多时,可横向排列各个标签;当识别目标较多时,可以横向滚动方式进行选择性展示。同理,纵向商品/视频也可以是以纵向滚动条的方式排列。而排列的顺序,人物视频可以例如点击率进行排序;而商品类例如可以如前所述地依据与目标商品的相似度进行排列。当然,在本公开实施例中,也可采用其它排列逻辑,只要获得合理结果即可。第一待推荐结果可以如图所示的两纵列的方式呈现,或其他排布方式排列,本公开实施例不对结果的排 布方式设限。而排布的次序,例如可以是根据相似度得分,作为多搜索结果排序的依据,相似度高的结果可以优先排名。其它影响排名的因素还可以包括例如视频播放量等,在此不做限定。
此外,第一待搜索目标还可以包括有效目标和无效目标。在本公开实施例还可获取视频播放页面所播放的视频中的全部视频图像帧;及获取每一视频图像帧中的有效目标,得到全局结果;其中,有效目标包括人物、商品和物品中的至少一种;无效目标为除有效目标以外的目标结果。具体地,本公开实施例可以通过模型例如多路检测模型筛分目标,具体可以是商品检测模型、人脸检测模型和物品检测模型等,对第一待搜索目标进行分类。其中,模型可以包括例如人脸特征信息、商品特征信息等。再将第一待搜索目标分为至少其中一类。如第一待搜索目标为有效目标,获取有效目标对应的第一推荐结果,并将第一推荐结果显示在搜索结果页面中;如第一待搜索目标为无效目标,在搜索结果页面中显示无结果;或如第一待搜索目标为有效目标,获取有效目标对应的第一推荐结果,依次将第一推荐结果和除第一推荐结果之外的全局结果显示在搜索结果页面中;如第一待搜索目标为无效目标,将全局结果显示在搜索结果页面中。
具体地,本公开实施例的第一推荐结果的获取可包括在线获取和离线获取两种方式。更具体地,第一推荐结果可以是储存在服务器或本地的数据,例如物品介绍、购买链接,或者人物相关视频,或其它相关信息等。返回的结果可以是识别的区域坐标及识别出的其中的有效目标。如服务器没有该视频文件的相关缓存时,服务器可实时进行在线识别,与服务器中的例如产品库中的商品进行特征比对,再返回相同或相似产品结果;如相关内容识别为人物,可以提取例如人脸信息进行视频特征查找其它含有该人物的图像或名字的视频。如搜索过程在服务器上进行,则相关结果可以通过客户端接口进行传送。特别地,如果客户端例如手机上安装的程序应用自建有商品库,也可以根据识别结果直接调取自有商品库;进一步,在自有商品库中还可设置外部链接,可通过该外部链接跳转至例如小程序、其它app或网页等。离线获取方式包括获取当前视频图像帧的结果的同时,还返回全局搜 索结果。其中,在线获取方式可能不能获得有效结果,即不能识别出商品或人物信息,因此,用户界面显示如图5所示的提示信息。在可获取离线缓存结果的情况下,用户不仅能够获取当前视频图像帧的搜索结果,还可获得全局结果;这样,即使当前视频图像帧不能识别出有效结果,用户仍可以获得全局结果。特别注意的是,在同时返回当前结果和全局结果时,可优先排布当前结果,全局结果可排布在后以提供给用户更多选择。如图6所示,图6是本公开再一实施例的搜索结果页面的示意图。在图6中,在当前结果a和b之后,还提供全局结果之一c。优选地,本实施例还可以设置标签,标签不仅可以有助于分类,还可以作为去重的依据,例如对比全局结果中相同标签的结果,判断是否属于同一物品/同一个人,或是相似物品/相似的人。前者可以只返回一个结果,作为去重的结果;后者如是相似物品,可归为一类。
本公开还可以包括重新确定待搜索目标的步骤。在一实施例中,移动搜索结果页面至当前视频图像帧的边缘并隐藏部分搜索结果页面,以显示第二控件。检测第二控件所在的第一显示位置是否发生变化,如果发生变化,获取第二控件的第二显示位置;根据所述第二显示位置确定对应的第二待搜索目标;获取第二待搜索目标对应的第二推荐结果;及再唤起搜索结果页面,将搜索结果页面中的第一推荐结果更换为第二推荐结果。
具体地,如图7所示,图7是本公开实施例更换待搜索目标的示意图。在本实施例中,搜索结果页面被部分地隐藏在当前视频图像帧的下方,在本公开其它实施例中,搜索结果页面也可以其它方式收起,在此不做限制。将浮动框的位置由A移动至G,和/或将浮动点的位置由B移动至H,由此获得第二待搜索目标。由第二待搜索目标获得第二推荐结果并显示的步骤可参考由第一待搜索目标获得第一推荐结果并显示的步骤,这里不再赘述。
特别地,本公开实施例还可以包括风控模型,具体可以是设置有过滤特征的屏蔽机制。例如,识别出的待搜索目标包括预先设定的过滤特征,那么可以选择拦截这个识别结果并且不发出搜索匹配指令, 起到过滤作用。其中,过滤的标准可以是暴力镜头、暴露画面,也可以是当识别出的人脸特征涉及隐私时予以屏蔽,更具体地可以是人脸检测模型只包括名人图谱,而当检测结果与人脸检测模型不符时加入过滤特征,结果为既不检测也不搜索,因而可以保护个人隐私。当然,本公开实施例的过滤标准不局限于以上所述,任何合理的过滤评判标准都可包含在本公开实施例中。
本公开实施例提供的视频搜索方法可用于在线检测或离线检测。对于商品服务端,可以将检测与搜索结果与商品库联系起来,可以帮助商家更好地安排消费存量与消费增量,优化产品结构。对于视频服务端,也可以起到热度指引与引流导向作用,以便内容供应商更合理地安排内容服务。其它方面还可以根据返回结果建立内容排序策略,根据例如点赞量、内容质量等自动建立规则生成器等。
如图8所示,本公开实施例还提供一种视频搜索的装置10,可包括接收模块30、获取模块50及显示模块70。其中,接收模块30可用于接收第一控件被触发产生的第一事件。获取模块50可用于获取第一事件被触发时视频播放页面中所播放的当前视频图像帧、当前视频图像帧中由第二控件定位的第一待搜索目标及第一待搜索目标在当前视频图像帧中的第一显示位置、和第一待搜索目标对应的第一推荐结果。显示模块70可用于将第一推荐结果显示在搜索结果页面中。
对于装置的实施例而言,由于其基本对应于方法实施例,所以相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的,其中所述作为分离模块说明的模块可以是或者也可以不是分开的。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性劳动的情况下,即可以理解并实施。
以上,基于实施例和应用例说明了本公开的视觉检测与搜索方法及装置。此外,本公开还提供一种终端及存储介质,以下说明这些终端和存储介质。
下面参考图9,其示出了适于用来实现本公开实施例的电子设备(例如终端设备或服务器)800的结构示意图。本公开实施例中的终 端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图9示出的电子设备仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。
如图9所示,电子设备800可以包括处理装置(例如中央处理器、图形处理器等)801,其可以根据存储在只读存储器(ROM)802中的程序或者从存储装置808加载到随机访问存储器(RAM)803中的程序而执行各种适当的动作和处理。在RAM803中,还存储有电子设备800操作所需的各种程序和数据。处理装置801、ROM 802以及RAM 803通过总线804彼此相连。输入/输出(I/O)接口805也连接至总线804。
通常,以下装置可以连接至I/O接口805:包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置806;包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置807;包括例如磁带、硬盘等的存储装置808;以及通信装置809。通信装置809可以允许电子设备800与其他设备进行无线或有线通信以交换数据。虽然图3示出了具有各种装置的电子设备800,但是应理解的是,并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。
特别地,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信装置809从网络上被下载和安装,或者从存储装置808被安装,或者从ROM 802被安装。在该计算机程序被处理装置801执行时,执行本公开实施例的方法中限定的上述功能。
需要说明的是,本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红 外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本公开中,计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质,该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:电线、光缆、RF(射频)等等,或者上述的任意合适的组合。
在一些实施方式中,客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol,超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信,并且可以与任意形式或介质的数字数据通信(例如,通信网络)互连。通信网络的示例包括局域网(“LAN”),广域网(“WAN”),网际网(例如,互联网)以及端对端网络(例如,ad hoc端对端网络),以及任何当前已知或未来研发的网络。
上述计算机可读介质可以是上述电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
上述计算机可读介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备执行上述的本公开的方法。
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码,上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++,还包括常规的过程式程序设计 语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图,图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如,非限制性地,可以使用的示范类型的硬件逻辑部件包括:现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本公开的上下文中,机器可读介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁 性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
根据本公开的一个或多个实施例,提供了一种视频搜索的方法,包括:
在视频播放页面中,接收第一控件被触发产生的第一事件;
响应所述第一事件,获取所述第一事件被触发时所述视频播放页面中所播放的当前视频图像帧;
获取所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置,在所述第一显示位置显示所述第二控件;及
获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,所述第二控件包括浮动框或浮动点中的至少一个。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,所述第一待搜索目标包括第一目标和第二目标,所述第二控件包括浮动框和浮动点;
其中,获取所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置,在所述第一显示位置显示所述第二控件的步骤包括:
分别获取所述当前视频图像帧中的由所述浮动框定位的所述第一目标和由所述浮动点定位的所述第二目标;
获取所述第一目标在所述当前视频图像帧中的显示位置,以及所述第二目标在所述当前视频图像帧中的显示位置;及
在所述第一目标在所述当前视频图像帧中的显示位置显示所述浮动框,在所述第二目标在所述当前视频图像帧中的显示位置显示所述 浮动点。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,所述获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中的步骤包括:
分别获取所述第一目标对应的第一待推荐结果和所述第二目标对应的第二待推荐结果;
将用于标识所述第一目标的第一标签和所述第一推荐结果对应地显示在所述搜索结果页面中的第一区域内;及
将用于标识所述第二目标的第二标签和所述第二推荐结果对应地显示在所述搜索结果页面中的第二区域内。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,所述第一待搜索目标包括有效目标和无效目标;
其中,所述方法还包括:
获取所述视频播放页面所播放的视频中的全部视频图像帧;及
获取每一所述视频图像帧中的所述有效目标,得到全局结果;
其中,所述有效目标为人物、商品和物品中的至少一种;所述无效目标为除所述有效目标以外的目标结果。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,所述获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中的步骤还包括:
如所述第一待搜索目标为有效目标,获取所述有效目标对应的所述第一推荐结果,并将所述第一推荐结果显示在所述搜索结果页面中;如所述第一待搜索目标为无效目标,在所述搜索结果页面中显示无结果;或
如所述第一待搜索目标为有效目标,获取所述有效目标对应的所述第一推荐结果,依次将所述第一推荐结果和除所述第一推荐结果之外的所述全局结果显示在所述搜索结果页面中;如所述第一待搜索目标为无效目标,将所述全局结果显示在所述搜索结果页面中。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,在所述获取所述第一待搜索目标对应的第一推荐结果,并将所述第一 推荐结果显示在搜索结果页面中之前,还包括:
接收所述第二控件被触发产生的第二事件;及
响应于所述第二事件,唤起所述搜索结果页面;
其中,所述搜索结果页面至少部分地覆盖于所述当前视频图像帧上并遮挡所述第二控件。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,在所述获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中的步骤之后,还包括:
移动所述搜索结果页面至所述当前视频图像帧的边缘并隐藏部分所述搜索结果页面,以显示所述第二控件。
根据本公开的一个或多个实施例,提供了一种方法,其特征在于,所述方法还包括:
检测所述第二控件所在的所述第一显示位置是否发生变化,如果发生变化,获取所述第二控件的第二显示位置;
根据所述第二显示位置确定对应的第二待搜索目标;
获取所述第二待搜索目标对应的第二推荐结果;及
再唤起所述搜索结果页面,将所述搜索结果页面中的所述第一推荐结果更换为所述第二推荐结果。
根据本公开的一个或多个实施例,提供了一种视频搜索的装置,包括:
接收模块,用于接收第一控件被触发产生的第一事件;
获取模块,用于获取所述第一事件被触发时视频播放页面中所播放的当前视频图像帧、所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置、和所述第一待搜索目标对应的第一推荐结果;及
显示模块,用于将所述第一推荐结果显示在搜索结果页面中。
根据本公开的一个或多个实施例,提供了一种终端,包括:至少一个存储器和至少一个处理器;
其中,所述至少一个存储器用于存储程序代码,所述至少一个处理器用于调用所述至少一个存储器所存储的程序代码执行上述中任一 项所述的方法。
根据本公开的一个或多个实施例,提供了一种存储介质,所述存储介质用于存储程序代码,所述程序代码用于执行上述的方法。
以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解,本公开中所涉及的公开范围,并不限于上述技术特征的特定组合而成的技术方案,同时也应涵盖在不脱离上述公开构思的情况下,由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外,虽然采用特定次序描绘了各操作,但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下,多任务和并行处理可能是有利的。同样地,虽然在上面论述中包含了若干具体实现细节,但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地,在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题,但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反,上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。

Claims (12)

  1. 一种视频搜索的方法,包括:
    在视频播放页面中,接收第一控件被触发产生的第一事件;
    响应所述第一事件,获取所述第一事件被触发时所述视频播放页面中所播放的当前视频图像帧;
    获取所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置,在所述第一显示位置显示所述第二控件;及
    获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中。
  2. 根据权利要求1所述的方法,其特征在于,所述第二控件包括浮动框或浮动点中的至少一个。
  3. 根据权利要求2所述的方法,其特征在于,所述第一待搜索目标包括第一目标和第二目标,所述第二控件包括浮动框和浮动点;
    其中,获取所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置,在所述第一显示位置显示所述第二控件的步骤包括:
    分别获取所述当前视频图像帧中的由所述浮动框定位的所述第一目标和由所述浮动点定位的所述第二目标;
    获取所述第一目标在所述当前视频图像帧中的显示位置,以及所述第二目标在所述当前视频图像帧中的显示位置;及
    在所述第一目标在所述当前视频图像帧中的显示位置显示所述浮动框,在所述第二目标在所述当前视频图像帧中的显示位置显示所述浮动点。
  4. 根据权利要求3所述的方法,其特征在于,所述获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中的步骤包括:
    分别获取所述第一目标对应的第一待推荐结果和所述第二目标对应的第二待推荐结果;
    将用于标识所述第一目标的第一标签和所述第一推荐结果对应地显示在所述搜索结果页面中的第一区域内;及
    将用于标识所述第二目标的第二标签和所述第二推荐结果对应地显示在所述搜索结果页面中的第二区域内。
  5. 根据权利要求1所述的方法,其特征在于,所述第一待搜索目标包括有效目标和无效目标;
    其中,所述方法还包括:
    获取所述视频播放页面所播放的视频中的全部视频图像帧;及
    获取每一所述视频图像帧中的所述有效目标,得到全局结果;
    其中,所述有效目标为人物、商品和物品中的至少一种;所述无效目标为除所述有效目标以外的目标结果。
  6. 根据权利要求5所述的方法,其特征在于,所述获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中的步骤还包括:
    如所述第一待搜索目标为有效目标,获取所述有效目标对应的所述第一推荐结果,并将所述第一推荐结果显示在所述搜索结果页面中;如所述第一待搜索目标为无效目标,在所述搜索结果页面中显示无结果;或
    如所述第一待搜索目标为有效目标,获取所述有效目标对应的所述第一推荐结果,依次将所述第一推荐结果和除所述第一推荐结果之外的所述全局结果显示在所述搜索结果页面中;如所述第一待搜索目标为无效目标,将所述全局结果显示在所述搜索结果页面中。
  7. 根据权利要求1所述的方法,其特征在于,在所述获取所述第一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中之前,还包括:
    接收所述第二控件被触发产生的第二事件;及
    响应于所述第二事件,唤起所述搜索结果页面;
    其中,所述搜索结果页面至少部分地覆盖于所述当前视频图像帧上并遮挡所述第二控件。
  8. 根据权利要求7所述的方法,其特征在于,在所述获取所述第 一待搜索目标对应的第一推荐结果,并将所述第一推荐结果显示在搜索结果页面中的步骤之后,还包括:
    移动所述搜索结果页面至所述当前视频图像帧的边缘并隐藏部分所述搜索结果页面,以显示所述第二控件。
  9. 根据权利要求8所述的方法,其特征在于,所述方法还包括:
    检测所述第二控件所在的所述第一显示位置是否发生变化,如果发生变化,获取所述第二控件的第二显示位置;
    根据所述第二显示位置确定对应的第二待搜索目标;
    获取所述第二待搜索目标对应的第二推荐结果;及
    再唤起所述搜索结果页面,将所述搜索结果页面中的所述第一推荐结果更换为所述第二推荐结果。
  10. 一种视频搜索的装置,包括:
    接收模块,用于接收第一控件被触发产生的第一事件;
    获取模块,用于获取所述第一事件被触发时视频播放页面中所播放的当前视频图像帧、所述当前视频图像帧中由第二控件定位的第一待搜索目标及所述第一待搜索目标在所述当前视频图像帧中的第一显示位置、和所述第一待搜索目标对应的第一推荐结果;及
    显示模块,用于将所述第一推荐结果显示在搜索结果页面中。
  11. 一种终端,包括:
    至少一个存储器和至少一个处理器;
    其中,所述至少一个存储器用于存储程序代码,所述至少一个处理器用于调用所述至少一个存储器所存储的程序代码执行权利要求1至9中任一项所述的方法。
  12. 一种存储介质,所述存储介质用于存储程序代码,所述程序代码用于执行权利要求1至9中任一项所述的方法。
PCT/CN2020/114799 2019-10-17 2020-09-11 视频搜索的方法及装置、终端和存储介质 WO2021073328A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022522608A JP7488333B2 (ja) 2019-10-17 2020-09-11 ビデオ検索方法、装置、端末、及び記憶媒体
US17/722,334 US11630861B2 (en) 2019-10-17 2022-04-16 Method and apparatus for video searching, terminal and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910990463.X 2019-10-17
CN201910990463.XA CN110704684B (zh) 2019-10-17 2019-10-17 视频搜索的方法及装置、终端和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/722,334 Continuation US11630861B2 (en) 2019-10-17 2022-04-16 Method and apparatus for video searching, terminal and storage medium

Publications (1)

Publication Number Publication Date
WO2021073328A1 true WO2021073328A1 (zh) 2021-04-22

Family

ID=69200515

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/114799 WO2021073328A1 (zh) 2019-10-17 2020-09-11 视频搜索的方法及装置、终端和存储介质

Country Status (4)

Country Link
US (1) US11630861B2 (zh)
JP (1) JP7488333B2 (zh)
CN (1) CN110704684B (zh)
WO (1) WO2021073328A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023134407A1 (zh) * 2022-01-17 2023-07-20 北京字跳网络技术有限公司 内容搜索方法、装置、设备及介质

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110704684B (zh) * 2019-10-17 2022-08-09 北京字节跳动网络技术有限公司 视频搜索的方法及装置、终端和存储介质
CN112199522B (zh) * 2020-08-27 2023-07-25 深圳一块互动网络技术有限公司 互动实现方法、终端、服务端、计算机设备及存储介质
CN115225945A (zh) * 2021-04-20 2022-10-21 北京字节跳动网络技术有限公司 对象展示方法、装置、电子设备及计算机可读存储介质
CN113343005A (zh) * 2021-05-17 2021-09-03 北京百度网讯科技有限公司 搜索方法、装置、电子设备以及可读存储介质
CN113535031A (zh) * 2021-08-03 2021-10-22 北京字跳网络技术有限公司 页面显示方法、装置、设备及介质
CN113589991A (zh) * 2021-08-13 2021-11-02 北京字跳网络技术有限公司 一种文本输入方法、装置、电子设备和存储介质
CN115878844A (zh) * 2021-09-27 2023-03-31 北京有竹居网络技术有限公司 基于视频的信息展示方法及装置、电子设备和存储介质
CN115878838A (zh) * 2021-09-27 2023-03-31 北京有竹居网络技术有限公司 基于视频的信息展示方法、装置、电子设备及存储介质
CN114443897A (zh) * 2022-02-10 2022-05-06 北京字跳网络技术有限公司 一种视频推荐方法、装置、电子设备和存储介质
CN114786062A (zh) * 2022-03-07 2022-07-22 维沃移动通信有限公司 信息推荐方法、装置和电子设备
CN114780790A (zh) * 2022-05-05 2022-07-22 北京字节跳动网络技术有限公司 内容搜索方法、装置、设备和存储介质
CN114969524A (zh) * 2022-05-24 2022-08-30 北京字节跳动网络技术有限公司 信息搜索方法、装置、设备及介质
CN115665498A (zh) * 2022-10-27 2023-01-31 北京字跳网络技术有限公司 一种视频处理方法、装置、设备及存储介质
CN116471429B (zh) * 2023-06-20 2023-08-25 上海云梯信息科技有限公司 基于行为反馈的图像信息推送方法及实时视频传输系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112129A (zh) * 2014-06-25 2014-10-22 小米科技有限责任公司 图像识别方法及装置
CN105095483A (zh) * 2015-08-14 2015-11-25 北京铭嘉实咨询有限公司 图片码识别方法和系统
CN109388725A (zh) * 2018-10-30 2019-02-26 百度在线网络技术(北京)有限公司 通过视频内容进行搜索的方法及装置
CN110704684A (zh) * 2019-10-17 2020-01-17 北京字节跳动网络技术有限公司 视频搜索的方法及装置、终端和存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2756073B2 (ja) * 1993-04-06 1998-05-25 株式会社富士通ソーシアルサイエンスラボラトリ データ検索方法
JP3093987B2 (ja) * 1997-03-07 2000-10-03 日立ソフトウエアエンジニアリング株式会社 部分動画像関連情報検索方法及びシステム
JP2004054435A (ja) 2002-07-17 2004-02-19 Toshiba Corp ハイパーメディア情報提示方法、ハイパーメディア情報提示プログラムおよびハイパーメディア情報提示装置
US20070250775A1 (en) * 2006-04-19 2007-10-25 Peter Joseph Marsico Methods, systems, and computer program products for providing hyperlinked video
US8239359B2 (en) 2008-09-23 2012-08-07 Disney Enterprises, Inc. System and method for visual search in a video media player
KR101727316B1 (ko) * 2010-10-08 2017-04-17 삼성전자 주식회사 비디오 재생장치 및 그 위치탐색방법
US8854474B2 (en) * 2011-03-08 2014-10-07 Nice Systems Ltd. System and method for quick object verification
US20140178041A1 (en) * 2012-12-26 2014-06-26 Balakesan P. Thevar Content-sensitive media playback
CN106776957A (zh) * 2016-12-05 2017-05-31 乐视控股(北京)有限公司 内容搜索方法、装置及电子设备
KR20180091285A (ko) * 2017-02-06 2018-08-16 삼성전자주식회사 동영상 관련 서비스 표시 방법, 저장 매체 및 이를 위한 전자 장치
CN107657011A (zh) * 2017-09-25 2018-02-02 小草数语(北京)科技有限公司 视频内容搜索方法、装置及其设备
CN110121093A (zh) * 2018-02-06 2019-08-13 优酷网络技术(北京)有限公司 视频中目标对象的搜索方法及装置
WO2019182583A1 (en) * 2018-03-21 2019-09-26 Rovi Guides, Inc. Systems and methods for presenting auxiliary video relating to an object a user is interested in when the user returns to a frame of a video in which the object is depicted
CN109218750B (zh) * 2018-10-30 2022-01-04 百度在线网络技术(北京)有限公司 视频内容检索的方法、装置、存储介质和终端设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104112129A (zh) * 2014-06-25 2014-10-22 小米科技有限责任公司 图像识别方法及装置
CN105095483A (zh) * 2015-08-14 2015-11-25 北京铭嘉实咨询有限公司 图片码识别方法和系统
CN109388725A (zh) * 2018-10-30 2019-02-26 百度在线网络技术(北京)有限公司 通过视频内容进行搜索的方法及装置
CN110704684A (zh) * 2019-10-17 2020-01-17 北京字节跳动网络技术有限公司 视频搜索的方法及装置、终端和存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023134407A1 (zh) * 2022-01-17 2023-07-20 北京字跳网络技术有限公司 内容搜索方法、装置、设备及介质

Also Published As

Publication number Publication date
CN110704684A (zh) 2020-01-17
US20220237227A1 (en) 2022-07-28
JP7488333B2 (ja) 2024-05-21
JP2022553174A (ja) 2022-12-22
CN110704684B (zh) 2022-08-09
US11630861B2 (en) 2023-04-18

Similar Documents

Publication Publication Date Title
WO2021073328A1 (zh) 视频搜索的方法及装置、终端和存储介质
US10474233B2 (en) Enabling augmented reality using eye gaze tracking
EP2983077B1 (en) Display control device, display control method, and display control program
KR102173123B1 (ko) 전자장치에서 이미지 내의 특정 객체를 인식하기 위한 방법 및 장치
CN109740085B (zh) 一种页面内容的展示方法、装置、设备及存储介质
CN105320403B (zh) 用于提供内容的方法和装置
CN108920515B (zh) 网页显示过程的信息推荐方法、装置、设备及存储介质
CN110020140A (zh) 推荐内容显示方法、装置及系统
CA3102222C (en) Method, device, terminal equipment and storage medium of sharing personal information
EP2596421A2 (en) Fisheye-based presentation of information for mobile devices
WO2020200146A1 (zh) 页面信息处理方法、装置及电子设备
US20150186491A1 (en) Personalized electronic magazine
WO2020259522A1 (zh) 一种内容查找方法、相关设备及计算机可读存储介质
WO2018004200A1 (en) Electronic device and information providing method thereof
WO2023071491A1 (zh) 百科信息确定方法、显示方法、装置、设备和介质
US9619519B1 (en) Determining user interest from non-explicit cues
JP2008146492A (ja) 情報提供装置、情報提供方法、及びコンピュータプログラム
CN106507177A (zh) 用于生成弹幕的方法和装置
WO2024001578A1 (zh) 书籍信息处理方法、装置、设备和存储介质
CN111581554A (zh) 一种信息推荐方法及装置
KR20130128800A (ko) 미디어 기기에서의 콘텐츠 정렬 방법 및 장치와 그 방법에 대한 프로그램 소스를 저장한 기록 매체
CN112202958B (zh) 截图方法、装置及电子设备
CN107145314B (zh) 一种显示处理方法和装置、一种用于显示处理的装置
CN110825909A (zh) 视频图像的识别方法、装置、服务器、终端和存储介质
CN115086774B (zh) 资源显示方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20876926

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022522608

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 05.08.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 20876926

Country of ref document: EP

Kind code of ref document: A1