Object recognition method, apparatus, device, storage medium, and program product

Abstract

This application relates to an object recognition method, apparatus, device, storage medium, and program product. The method includes: displaying a target page showing a dynamic video frame; receiving a touch operation based on the video frame; determining a selected target object in the video frame based on the touch operation; and outputting recognition information for the target object. This method can improve the intelligence of human-computer interaction.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular to an object recognition method, apparatus, device, storage medium, and program product. Background Technology

[0002] With the development of artificial intelligence technology, more and more electronic devices can identify and analyze objects in images and output information about related items in the images to users.

[0003] However, traditional technologies still suffer from insufficient intelligence in human-computer interaction. Summary of the Invention

[0004] Therefore, it is necessary to provide an object recognition method, device, equipment, storage medium, and program product that can improve the intelligence of human-computer interaction in response to the above-mentioned technical problems.

[0005] In a first aspect, this application provides an object recognition method, the method comprising:

[0006] Display the target page, which shows a dynamic video; receive touch operations based on the video, determine the selected target object in the video based on the touch operations, and output the recognition information of the target object.

[0007] Secondly, this application also provides an object recognition device, which includes:

[0008] The display module is used to display the target page, which shows dynamic video footage;

[0009] The determination module is used to receive touch operations based on the video screen and determine the selected target object in the video screen based on the touch operations.

[0010] The output module is used to output the identification information of the target object.

[0011] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps described in the first aspect above.

[0012] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps described in the first aspect above.

[0013] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps described in the first aspect above.

[0014] The aforementioned object recognition method, apparatus, device, storage medium, and program product, by displaying a target page with a dynamic video frame, receiving touch operations based on the video frame, determining the selected target object in the video frame based on the touch operation, and then outputting recognition information for the target object, can achieve the purpose of receiving the user's recognition intent based on a dynamic video frame and outputting recognition information based on the user's recognition intent. Compared with the existing technology that only supports receiving the user's recognition intent based on a static image, this can greatly improve the intelligence of human-computer interaction and simplify the operation steps of object recognition. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating an object recognition method in one embodiment;

[0017] Figure 2 This is a flowchart illustrating the process of displaying information after receiving a touch operation in one embodiment.

[0018] Figure 3 This is a flowchart illustrating the target screen frame in one embodiment;

[0019] Figure 4 This is a schematic diagram of the target page in one embodiment;

[0020] Figure 5 This is a schematic diagram of the touch operation process in one embodiment;

[0021] Figure 6 This is a schematic diagram illustrating the target display effect and recognition information in one embodiment;

[0022] Figure 7 This is a structural block diagram of an object recognition device in one embodiment;

[0023] Figure 8 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0025] With the development of electronic and artificial intelligence technologies, more and more electronic devices can support the recognition of objects in images and output relevant recognition information.

[0026] For example, many smartphone manufacturers have developed AI assistants. When users need to identify objects, they can activate the AI ​​assistant, which will then identify the objects in the image and output relevant identification information.

[0027] In related technologies, electronic devices generally only support the recognition of objects in static images. The relevant process may include, for example, the user activating an artificial intelligence assistant when there is a need for object recognition, and then the user using a camera device to take an image to obtain a static image, and then using the artificial intelligence assistant to recognize the objects in the static image.

[0028] When a user needs to identify multiple objects, they first need to take a picture of one object to obtain a static image of that object. Then, an AI assistant is used to identify the object in the static image and obtain its identification information. After viewing the identification information, the user can exit the current identification process and proceed to the next one. In the next identification process, the user needs to take a picture of another object to obtain a static image of that object, and then use the AI ​​assistant to identify the object in the static image, and so on. The user needs to repeat the above identification process multiple times to meet the identification needs of multiple objects. Moreover, each identification process requires the steps of taking a picture and outputting identification information, which is cumbersome and has poor human-computer interaction intelligence.

[0029] In view of this, embodiments of this application provide an object recognition method, apparatus, device, storage medium, and program product. In this object recognition method, a target page displaying dynamic video footage can be shown. Then, a touch operation is received based on the video footage, and the selected target object in the video footage is determined according to the touch operation. Finally, recognition information for the target object is output. This achieves the goal of receiving the user's recognition intent based on dynamic video footage and outputting recognition information accordingly. Compared to existing technologies that only support receiving the user's recognition intent based on static images, this greatly improves the intelligence of human-computer interaction and simplifies the operation steps of object recognition.

[0030] In one exemplary embodiment, such as Figure 1As shown, an object recognition method is provided. Taking the application of this method to an electronic device as an example, the electronic device can be a laptop, smartphone, tablet, IoT device, or portable wearable device, etc. The IoT device can be a smart speaker, smart TV, smart air conditioner, smart in-vehicle device, projector, etc., and the portable wearable device can be a smartwatch, smart bracelet, head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. Figure 1 As shown, the object recognition method may include the following steps:

[0031] Step 101: Display the target page.

[0032] The target page displays dynamic video footage. In one optional embodiment of this application, the dynamic video footage includes a viewfinder image captured in real time by the camera device of an electronic device.

[0033] In optional embodiments of this application, the target page may be a page provided by an AI assistant, a page provided by a video playback application, or a viewfinder page provided by a camera application, etc. This application does not specifically limit it in this regard.

[0034] In an optional embodiment of this application, the target page may be displayed in response to a target triggering operation.

[0035] Taking the target page as an example of a page provided by an AI assistant, electronic devices can provide an entry point for the AI ​​assistant. This entry point could be an AI assistant application icon on the desktop, a physical button, or a voice activation entry point. Through this entry point, the AI ​​assistant can be opened, and the target page provided by the AI ​​assistant can be displayed.

[0036] For example, the target trigger operation is that the user inputs a voice wake-up command to activate the target page through the voice wake-up entry. In this way, the electronic device can receive the voice wake-up command, and in response to the voice wake-up command, open the artificial intelligence assistant and display the target page provided by the artificial intelligence assistant.

[0037] In one possible implementation, during the display of the target page provided by the AI ​​assistant, the AI ​​assistant can invoke a camera device and control the camera device to enter viewfinder mode. In viewfinder mode, the camera device can capture a real-time view and display this viewfinder image on the target page. It is understood that the real-time viewfinder image displayed on the target page is a dynamic video feed.

[0038] In another possible implementation, the AI ​​assistant can provide a video selection entry and / or a video upload entry. Through these entry points, the AI ​​application can retrieve a target video already present on the electronic device and display it on the target page. Similarly, the target video displayed on the target page is a dynamic video frame.

[0039] Taking a video playback application as an example, the target page can provide a video playback page. This video playback page can be the target page in this embodiment of the application. The video playback page can be opened based on a target-triggered operation, and the local video or streaming video played on the video playback page is the dynamic video image displayed on the target page.

[0040] In one possible implementation, the video playback application can have a built-in artificial intelligence module, which can be used to implement subsequent technical solutions. For example, during video playback, the AI ​​module is activated, receives touch operations based on the target page provided by the video playback application, uses the AI ​​module to determine the selected target object in the video frame of the target page, and outputs recognition information for the target object.

[0041] In another possible implementation, while the video playback page is being displayed, the user can open the AI ​​assistant in the background through an entry point (such as a voice activation entry point) and then perform subsequent steps based on the AI ​​assistant running in the background.

[0042] Taking a target page provided by a camera application as an example, the camera application can provide a viewfinder page. This viewfinder page can be the target page in this embodiment. In this case, the image captured by the camera device and displayed on the viewfinder page is a dynamic video image.

[0043] In one possible implementation, during the display of the viewfinder page, the user can open the AI ​​assistant in the background through an entry point (such as a voice activation entry point) and implement subsequent steps based on the AI ​​assistant running in the background.

[0044] Step 102: Receive touch operation based on video screen, and determine the selected target object in the video screen based on the touch operation.

[0045] During the dynamic display of video footage, the video frame may include at least one object. Optionally, the object in the video frame may be an animal, plant, item, etc., and this application does not specifically limit this.

[0046] Electronic devices receive touch operations based on video feeds, with the touch location corresponding to a target object. For example, if the video feed includes multiple objects, the user performs a touch operation within the touch area corresponding to the display area of ​​the target object on the target page. The electronic device extracts an image from the touch location of the touch operation and determines the target object based on that image.

[0047] Optionally, the target object can be a single object.

[0048] Optionally, the selected object is highlighted on the target page so that the user can determine whether the object identified by the electronic device is the object the user wants to select.

[0049] Step 103: Output the identification information for the target object.

[0050] In one possible implementation, the identification information for the target object is output on the target page. This allows the user to view both the target object and the identification information simultaneously.

[0051] In another possible implementation, a subpage is displayed on the target page, and the identification information for the target object is output on the subpage. Optionally, the subpage may completely or partially cover the target page.

[0052] In an optional embodiment of this application, the electronic device can determine the object information of the selected target object, obtain the identification information of the target object based on the object information, and output the identification information.

[0053] In one alternative implementation, the process of obtaining the identification information of the target object can be as follows: the electronic device calls a search engine in the background, inputs the object information into the search engine, and obtains the identification information of the target object returned by the search engine.

[0054] In another alternative implementation, the electronic device has a pre-installed object information database, and the identification information of the target object is retrieved from the object information database based on the object information.

[0055] Optionally, the identification information of the target object may be at least one type of information related to the target object. For example, if the target object is an animal, the identification information may include the target object's name, aliases, physical characteristics, habitat, habits, distribution range, etc., though not all examples are provided here. As another example, if the target object is a plant, the identification information may include the target object's name, species, morphological characteristics, reproductive methods, ecological value, etc., though not all examples are provided here.

[0056] The object recognition method provided in this embodiment displays a target page with dynamic video footage, receives touch operations based on the video footage, determines the selected target object in the video footage based on the touch operations, and then outputs recognition information for the target object. In this way, it can realize the purpose of receiving the user's recognition intention based on dynamic video footage and outputting recognition information based on the user's recognition intention. Compared with the existing technology that only supports receiving the user's recognition intention based on static images, it can greatly improve the intelligence of human-computer interaction and simplify the operation steps of object recognition.

[0057] Please refer to Figure 2 In an optional embodiment of this application, an optional technical process is provided for displaying an input after receiving a touch operation, such as... Figure 2 As shown, the technical process includes the following steps:

[0058] Step 201: After receiving a touch operation, display the target frame from the multiple frames included in the video.

[0059] The video feed is dynamic; upon receiving a touch input, a static target frame can be displayed. Optionally, the target frame can be displayed on the target page.

[0060] In one possible implementation, the electronic device determines the touch moment of receiving the touch operation, and determines the image displayed at the touch moment as the target image frame based on the touch moment.

[0061] In another possible implementation, the electronic device determines the touch moment of receiving the touch operation, acquires multiple first-frame images displayed before the touch moment, acquires a second-frame image displayed at the touch moment, and acquires multiple third-frame images displayed after the touch moment. Based on each of the first, second, and third-frame images, a target image frame is determined. For example, the first, second, and third-frame images are merged to determine the target image frame. Another example is selecting the image frame with the highest resolution from the first, second, and third-frame images as the target image frame. It is understood that the target object is included in the video frame both before and after the touch moment.

[0062] Step 202: Display the target object in the target frame with the target display effect, which is different from the display effect of other areas in the target frame.

[0063] As mentioned above, the target object can be highlighted. In this embodiment, the target object is highlighted on the target page by displaying it with a target display effect, allowing the user to check whether the target object identified by the electronic device is the object selected by the user.

[0064] In an optional embodiment of this application, the electronic device determines the target object from the target screen frame based on the touch position of the touch operation, and then displays the target object with the target display effect.

[0065] In one possible implementation, the electronic device identifies the edge lines of the target object and displays those edge lines with a target display effect, thereby highlighting the target object. For example, the edge lines of the target object are displayed as a preset highlight color.

[0066] In another possible implementation, the electronic device determines the target area where the target object is located and displays that target area with a target display effect. For example, in the target area where the target object is located in the target frame, a preset color image is overlaid with a preset transparency to highlight the target object.

[0067] It is understandable that other display effects can be used to display the target object, so that the display effect of the target is different from the display effect of other areas in the target image frame. However, this is not fully demonstrated here.

[0068] In this embodiment, by determining the target frame, the electronic device can accurately identify the target object from the target frame and flexibly display the target object in the target frame with the target display effect. Furthermore, by displaying the target object with the target display effect, the user can promptly determine whether the target object determined by the electronic device is the target object the user wants to select, improving the intelligence of human-computer interaction and ensuring that the user's recognition needs are met.

[0069] In an optional embodiment of this application, the target page includes a first exit control; after detecting a trigger operation on the first exit control, the video screen continues to be displayed, and the output of identification information for the target object stops.

[0070] For example, in one possible use case, if a user determines, based on the target display effect, that the target object identified by the electronic device based on the touch operation is not the object the user intends to select, or if the user needs to change the object to be selected, the user can perform a trigger operation on the first exit control. Upon detecting the trigger operation on the first exit control, the electronic device stops outputting the identification information for the target object.

[0071] In another possible use case, if the output target identification information is not the identification information that the user needs to see, the user can also perform a trigger operation on the first exit control.

[0072] Optionally, during the display of the target page, the first exit control remains continuously displayed in the first position on the target page. Alternatively, when the target object is displayed in the target frame with the target display effect, the first exit control is invoked and displayed in the first position on the target page. Or, during the output of recognition information for the target object, the first exit control is invoked and displayed in the first position on the target page.

[0073] In this embodiment of the application, by providing a first exit control, the user's flexibility in viewing the information displayed on the target page is improved. Furthermore, when the user needs to reselect the target object or determines that the recognition information needs to be re-output, the triggering operation based on the first exit control efficiently responds to the user's needs and accurately meets the user's recognition intent.

[0074] Please refer to Figure 3 In an optional embodiment of this application, an optional technical process for displaying target image frames is provided, such as... Figure 3 As shown, the technical process includes the following steps:

[0075] Step 301: Enlarge the target frame.

[0076] Step 302: Display the target area in the magnified target image frame. The target area includes the target object.

[0077] In one alternative implementation, the entire target frame can be magnified.

[0078] In another optional implementation, the target area containing the target object in the target frame can be magnified to display the target area in the magnified target frame.

[0079] Correspondingly, the target object can be displayed in the target area with a target display effect.

[0080] It is understandable that the target object in the magnified image of the target area displayed by the electronic device is larger than the target object in the target frame.

[0081] In this embodiment, the target area containing the target object is displayed after the target image frame is magnified, so that the user can perform touch operation based on the target area. Since the target object is magnified, the user can select the target object more accurately, thereby improving the accuracy of the electronic device in recognizing the target object and the intelligence of human-computer interaction.

[0082] In optional embodiments of this application, two optional technical methods for outputting identification information for the target object are provided, wherein:

[0083] The first technical approach includes: performing identification processing on the target object, obtaining identification information based on the results of the identification processing, and outputting it.

[0084] The recognition and processing result is the object information identified above.

[0085] In one possible implementation, an image of the target object can be extracted and input into a search engine so that the search engine can identify and process the image of the target object and obtain relevant object information as identification information.

[0086] In another possible implementation, the target image frame is input into a search engine, which then identifies the objects within the frame and obtains the identification result determined by the search engine. If the target image frame contains multiple objects, the identification result may include object information for each object. Therefore, the object information of the target object can be extracted from the identification result as identification information and output.

[0087] In another possible implementation, the image of the target object is identified to determine its name. For example, an object recognition model deployed in an electronic device can be invoked. The image of the target object is input into the object recognition model, and the name of the target object is output by the model. The name of the target object is then input into a search engine, which processes the name to identify the target object and obtains related object information as identification information.

[0088] The second technical approach includes: acquiring auxiliary identification information, performing identification processing on the target object based on the auxiliary identification information, and acquiring and outputting identification information based on the results of the identification processing.

[0089] In an optional embodiment of this application, the auxiliary identification information is input by the user based on an artificial intelligence assistant.

[0090] In an optional embodiment of this application, the auxiliary identification information is generated during the display of the target page, or the auxiliary identification information is generated historically.

[0091] In optional embodiments of this application, the auxiliary recognition information may be speech-type information, text-type information, etc., and is not specifically limited here.

[0092] The auxiliary identification information is used to indicate to the user the object type information required for the target object. No specific limitation is made regarding the target type here.

[0093] For example, taking an animal as the target object, the auxiliary identification information could be something like "Please determine the name and habits of the target object." The electronic device could then determine the name and habits of the target object as identification information and output it. One possible implementation involves using a search engine to determine all object information for the target object and extracting its name and habits as identification information. Another possible implementation involves inputting an image of the target object, its "name" field, and its "habits" field into a search engine, and using its output information as identification information.

[0094] This application provides multiple methods for acquiring identification information, enhancing the flexibility of electronic devices in obtaining target object identification information. Furthermore, combining auxiliary identification information can further increase the matching degree between the output identification information and the user's identification needs, thereby improving the intelligence of human-computer interaction.

[0095] In optional embodiments of this application, two optional technical methods for obtaining auxiliary identification information are provided, wherein:

[0096] The first technical approach includes receiving voice information within a preset time period before or after a touch operation is detected, and using the voice information as auxiliary recognition information.

[0097] In other words, users can input voice information into electronic devices within a preset time before or after touch operation.

[0098] For example, during the display of a target page, the user inputs voice information using an AI assistant. The electronic device acquires and recognizes this voice information to obtain auxiliary recognition information. For instance, the electronic device can convert the voice information into text, and then use the converted text as auxiliary recognition information.

[0099] The second technical approach includes: obtaining the user's historical intent and preference information, and using the historical intent and preference information as auxiliary identification information.

[0100] Among them, historical intent preference information can characterize the object information of the target type that the user needs to view during the historical display process of the target page.

[0101] Optionally, historical intent preference information is the user input during the display of the target page's history.

[0102] In this way, the system can output the target type of object information that the user needs to view without requiring the user to repeatedly input their intention and preference information, thereby reducing the complexity of the target object recognition information and improving the intelligence of human-computer interaction.

[0103] The third technical approach includes: the target page also includes input controls, and the text information output by the user is received based on the output controls, and the text information is used as auxiliary recognition information.

[0104] In this application embodiment, multiple methods are provided to obtain auxiliary identification information, thereby improving the flexibility of electronic devices in obtaining auxiliary identification information and improving the accuracy of the output identification information.

[0105] In an optional embodiment of this application, the target page includes a second exit control; upon detecting a triggering operation on the second exit control, the target page is exited.

[0106] In one possible implementation, the target page is exited to stop displaying video footage and identification information for the target object.

[0107] In another possible implementation, the target page is exited to stop displaying the video feed, and the identification information for the target object is output on a new page.

[0108] In this way, the user's need to exit the target page can be obtained in a timely manner through the second exit control.

[0109] To make the technical solutions provided in this application easier for readers to understand, the embodiments of this application will be described below in conjunction with... Figure 4 , Figure 5 as well as Figure 6 A brief description of the object recognition method provided in the embodiments of this application is given below.

[0110] Based on the voice activation entry point of the AI ​​assistant, the system receives the user's voice wake-up command, responds to the command, opens the AI ​​assistant, displays the target page provided by the AI ​​assistant, and invokes the electronic device's camera to capture a real-time view, displaying this dynamic view as a video feed on the target page. For example, Figure 4 As shown, the target page displays a dynamic video, a first exit control, a second exit control, and a recognition reminder message. Figure 4 The dynamic video footage includes "flowers" and "insects"; the recognition alert message is "Xiao Bu is listening and sensing the scene," used to remind the user that a target object in the video footage can be identified based on the target page. Based on the user's touch input in the video footage, the selected target object in the video footage is determined according to the touch input, such as... Figure 5 As shown, the selected target is the "insect" in the video frame. Upon receiving a touch operation, the system can display the target frame from multiple frames in the video, zoom in on the target frame, and display the target area containing the target object within the zoomed-in frame, such as... Figure 5As shown, the "insect" is magnified. The target object is displayed in the target frame with a target display effect that differs from the display effects of other areas in the target frame. Furthermore, the target object undergoes identification processing, and identification information is obtained and output based on the results of the identification processing. Figure 6 As shown, the target object, "insect," is highlighted with deepened lines, and identification information for the target object can be output on the target page. Optionally, the display position of this identification information does not overlap with the display position of the target object. Optionally, during the target object identification process, auxiliary identification information is acquired, the target object is identified based on the auxiliary identification information, and identification information is acquired and output based on the result of the identification process. Specifically, after detecting a trigger operation for the first exit control, the video screen continues to be displayed, and the output of identification information for the target object stops. After detecting a trigger operation for the second exit control, the target page exits.

[0111] In this embodiment of the application, combined with Figure 4 , Figure 5 as well as Figure 6 As can be seen, the electronic device displays a dynamic video during the process of showing the target page. When the user sees the main subject of the screen where they want to ask a question, they can directly perform a touch operation on the target object based on the video screen to complete the accurate input of intent. The identified target object will be segmented and understood by the model in a timely manner, and the selected target object will be highlighted for the user to view. At the same time, the identification information of the target object is provided, realizing the functions of instant questioning, reducing the interaction process and improving the recognition efficiency, thus enhancing the intelligence of human-computer interaction.

[0112] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0113] Based on the same inventive concept, this application also provides an object recognition device for implementing the object recognition method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more object recognition device embodiments provided below can be found in the limitations of the object recognition method described above, and will not be repeated here.

[0114] In one exemplary embodiment, such as Figure 7 As shown, an object recognition device 700 is provided, including: a display module 701, a determination module 702 and an output module 703.

[0115] The display module 701 is used to display the target page, which displays dynamic video footage.

[0116] The determination module 702 is used to receive touch operations based on the video screen and determine the selected target object in the video screen based on the touch operations.

[0117] Output module 703 is used to output identification information for the target object.

[0118] In some embodiments, dynamic video footage includes a viewfinder image captured in real time by the camera device of an electronic device.

[0119] In some embodiments, the display module 701 is further configured to: after receiving a touch operation, display a target frame from the multiple frames included in the video frame; display a target object in the target frame with a target display effect, wherein the target display effect is different from the display effect of other areas in the target frame.

[0120] In some embodiments, the display module 701 is further configured to: magnify the target image frame; and display the target area in the magnified target image frame, wherein the target area includes the target object.

[0121] In some embodiments, the display module 701 is further configured to: continue displaying the video image after detecting a trigger operation on the first exit control, and the output module 703 is further configured to stop outputting the identification information of the target object.

[0122] In some embodiments, the output module 703 is specifically used to perform identification processing on the target object, obtain identification information based on the result of the identification processing, and output it; or, obtain auxiliary identification information, perform identification processing on the target object based on the auxiliary identification information, obtain identification information based on the result of the identification processing, and output it.

[0123] In some embodiments, the output module 703 specifically includes at least one of the following: receiving voice information within a preset time period before or after a touch operation is detected, and using the voice information as auxiliary recognition information; obtaining the user's historical intent preference information, and using the historical intent preference information as auxiliary recognition information.

[0124] Each module in the aforementioned object recognition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independent of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the operations corresponding to each module.

[0125] In one exemplary embodiment, an electronic device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, this electronic device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements an object recognition method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the electronic device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the electronic device, or external keyboards, touchpads, or mice, etc.

[0126] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0127] In one exemplary embodiment, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0128] Display the target page, which shows a dynamic video; receive touch operations based on the video, determine the selected target object in the video based on the touch operations, and output the recognition information of the target object.

[0129] In one embodiment, the dynamic video footage includes a viewfinder image captured in real time by the camera device of an electronic device.

[0130] In one embodiment, when the processor executes the computer program, it further performs the following steps: after receiving a touch operation, it displays a target frame from the multiple frames included in the video frame; and displays a target object in the target frame with a target display effect that is different from the display effect of other areas in the target frame.

[0131] In one embodiment, when the processor executes the computer program, it further performs the following steps: magnifying the target image frame; displaying the target region in the magnified target image frame, the target region including the target object.

[0132] In one embodiment, the target page includes a first exit control; when the processor executes the computer program, it further performs the following steps: after detecting a trigger operation on the first exit control, it continues to display the video screen and stops outputting identification information for the target object.

[0133] In one embodiment, when the processor executes the computer program, it further performs the following steps: performing identification processing on the target object, obtaining identification information based on the result of the identification processing, and outputting it; or, obtaining auxiliary identification information, performing identification processing on the target object based on the auxiliary identification information, obtaining identification information based on the result of the identification processing, and outputting it.

[0134] In one embodiment, when the processor executes the computer program, it further performs at least one of the following steps: receiving voice information within a preset time period before or after a touch operation is detected, and using the voice information as auxiliary recognition information; obtaining the user's historical intent preference information, and using the historical intent preference information as auxiliary recognition information.

[0135] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0136] Display the target page, which shows a dynamic video; receive touch operations based on the video, determine the selected target object in the video based on the touch operations, and output the recognition information of the target object.

[0137] In one embodiment, the dynamic video footage includes a viewfinder image captured in real time by the camera device of an electronic device.

[0138] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: after receiving a touch operation, it displays a target frame from the multiple frames included in the video frame; and displays a target object in the target frame with a target display effect that is different from the display effect of other areas in the target frame.

[0139] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: magnifying the target image frame; displaying the target region in the magnified target image frame, the target region including the target object.

[0140] In one embodiment, the target page includes a first exit control; when the computer program is executed by the processor, it further performs the following steps: after detecting a trigger operation on the first exit control, it continues to display the video screen and stops outputting identification information for the target object.

[0141] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: performing identification processing on the target object, obtaining identification information based on the result of the identification processing and outputting it; or, obtaining auxiliary identification information, performing identification processing on the target object based on the auxiliary identification information, obtaining identification information based on the result of the identification processing and outputting it.

[0142] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: receiving voice information within a preset time period before or after a touch operation is detected, and using the voice information as auxiliary recognition information; obtaining the user's historical intent preference information, and using the historical intent preference information as auxiliary recognition information.

[0143] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0144] Display the target page, which shows a dynamic video; receive touch operations based on the video, determine the selected target object in the video based on the touch operations, and output the recognition information of the target object.

[0145] In one embodiment, the dynamic video footage includes a viewfinder image captured in real time by the camera device of an electronic device.

[0146] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: after receiving a touch operation, it displays a target frame from the multiple frames included in the video frame; and displays a target object in the target frame with a target display effect that is different from the display effect of other areas in the target frame.

[0147] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: magnifying the target image frame; displaying the target region in the magnified target image frame, the target region including the target object.

[0148] In one embodiment, the target page includes a first exit control; when the computer program is executed by the processor, it further performs the following steps: after detecting a trigger operation on the first exit control, it continues to display the video screen and stops outputting identification information for the target object.

[0149] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: performing identification processing on the target object, obtaining identification information based on the result of the identification processing and outputting it; or, obtaining auxiliary identification information, performing identification processing on the target object based on the auxiliary identification information, obtaining identification information based on the result of the identification processing and outputting it.

[0150] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: receiving voice information within a preset time period before or after a touch operation is detected, and using the voice information as auxiliary recognition information; obtaining the user's historical intent preference information, and using the historical intent preference information as auxiliary recognition information.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0152] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0153] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0154] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An object recognition method, characterized in that, The method includes: Display the target page, which shows dynamic video footage; Based on the video frame, a touch operation is received, and the selected target object in the video frame is determined according to the touch operation; Output the identification information for the target object.

2. The method according to claim 1, characterized in that, The dynamic video footage includes real-time views captured by the camera device of the electronic device.

3. The method according to claim 1, characterized in that, The method further includes: Upon receiving the touch operation, the target frame from the multiple frames included in the video is displayed; The target object is displayed in the target frame with a target display effect, which is different from the display effect of other areas in the target frame.

4. The method according to claim 3, characterized in that, The target frame among the multiple frames of the video screen being displayed includes: The target image frame is magnified; The target area is displayed in the magnified target image frame, and the target area includes the target object.

5. The method according to claim 3, characterized in that, The target page includes a first exit control; the method further includes: After detecting a trigger operation on the first exit control, the video screen continues to be displayed, and the output of identification information for the target object stops.

6. The method according to any one of claims 1 to 5, characterized in that, The output includes identification information for the target object, including: The target object is identified, and the identification information is obtained and output based on the result of the identification process; or, Obtain auxiliary identification information, perform identification processing on the target object based on the auxiliary identification information, and obtain and output the identification information based on the result of the identification processing.

7. The method according to claim 6, characterized in that, The acquisition of auxiliary identification information includes at least one of the following: Within a preset time period before or after the detection of the touch operation, voice information is received and used as the auxiliary recognition information; Obtain the user's historical intent preference information and use the historical intent preference information as the auxiliary identification information.

8. An object recognition device, characterized in that, The device includes: The display module is used to display the target page, which displays dynamic video footage; The determination module is used to receive touch operations based on the video frame and determine the selected target object in the video frame according to the touch operations; The output module is used to output identification information for the target object.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images