A method and device for determining a person based on AR glasses, AR glasses and medium

Abstract

The present application relates to a method, device, AR glasses and medium for determining a person based on AR glasses, and belongs to the technical field of face recognition. The method includes: obtaining historical information, the historical information includes historical multimedia information and / or historical object information, the historical multimedia information is multimedia information containing historical objects, and the historical object information includes facial features of historical objects; determining candidate objects based on historical information, and controlling the display of object attribute information of candidate objects, and the object attribute information includes: name, gender, age and occupation; determining the target object based on the user's selection operation, and determining the facial features of the target object based on the historical information; based on the facial features of the target object, tracking the target object from the multimedia information shot in the current scene, and controlling the display of the target object in the multimedia information shot in the current scene in a preset manner. The present application has the effect of improving the speed of determining the target person.

Description

Technical Field

[0001] The present application relates to the technical field of face recognition, and in particular to a method and device for determining a person based on AR glasses, AR glasses, and a medium. Background Art

[0002] AR glasses are also called augmented reality glasses. AR glasses cover virtual objects directly in the user's direct field of vision through transparent glass. Users of AR glasses can observe the real world and the virtual world at the same time. With the rapid development of artificial intelligence, AR glasses are used in many occasions, such as ball games, concerts and other large-scale events.

[0003] However, in the process of implementing the present application, the inventor discovered that when using AR glasses at various large-scale event venues such as ball games and concerts, due to the large number of participants, how to use AR glasses to quickly select and determine the target person and accurately display the target person becomes a key issue. Summary of the invention

[0004] In order to increase the speed of identifying a target person, the present application provides a person identification method, device, AR glasses and medium based on AR glasses.

[0005] In a first aspect, the present application provides a method for determining a person based on AR glasses, comprising:

[0006] Acquire historical information, where the historical information includes historical multimedia information and / or historical object information, where the historical multimedia information is multimedia information containing historical objects, and the historical object information includes facial features of historical objects;

[0007] Determine candidate objects based on the historical information, and control display of object attribute information of the candidate objects, the object attribute information including: name, gender, age and occupation;

[0008] Determine a target object based on a selection operation of the user, and determine a facial feature of the target object based on the historical information;

[0009] Based on the facial features of the target object, the target object is tracked from the multimedia information shot in the current scene, and the target object is controlled to be displayed in a preset manner in the multimedia information shot in the current scene.

[0010] By adopting the above technical solution, when the user wears AR glasses in the current scene, the AR glasses obtain candidate objects from historical information and determine the target object based on the user's selection, so as to obtain the facial features of the target object from the historical information, so that the target object can be tracked and displayed in the multimedia information of the current scene based on the acquired facial features, so that the target object can be quickly selected and determined, and the target object can be accurately tracked and displayed.

[0011] In another possible implementation, the determining the candidate object based on the historical information includes:

[0012] Acquire facial features of each historical object based on the historical information;

[0013] Get the time and location information of the current scene;

[0014] Acquire specific multimedia information based on the time information and the location information, the specific multimedia information including the appearance object in the current scene, and the specific multimedia information is multimedia information uploaded by other users that matches the time information and the location information;

[0015] Acquire facial features of the subject based on the specific multimedia information;

[0016] A candidate object is determined based on the facial features of the appearance object and the facial features of the historical object, wherein the facial features of the candidate object are facial features that are consistent between the facial features of the appearance object and the facial features of the historical object.

[0017] By adopting the above technical solution, AR glasses determine to obtain specific multimedia information according to the current location information and time information, and screen the facial features of the objects appearing in the specific multimedia information with the facial features in the historical objects to obtain the facial features that are consistent with the comparison, so as to preliminarily screen and determine the candidate objects. AR glasses perform personalized screening of the candidate objects according to the changes in the scene, which is suitable for the current scene, thereby reducing the time for users to determine the target object.

[0018] In another possible implementation manner, after determining the candidate object based on the historical information, the step further includes:

[0019] Obtain object attribute information corresponding to each candidate object;

[0020] Obtaining a program list, the program list including the program sequence, the start time of each program, and the appearance object of each program;

[0021] Based on the program list, obtain object attribute information of the appearance objects corresponding to each program;

[0022] Determine the candidate object corresponding to each program based on the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object, wherein the object attribute information of the candidate object corresponding to each program is the object attribute information that is consistent between the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object;

[0023] The controlling and displaying of object attribute information of the candidate object includes:

[0024] When the start time corresponding to each program is reached, the object attribute information of the corresponding candidate objects is displayed through control.

[0025] By adopting the above technical solution, the AR glasses obtain the first multimedia information of the current scene, and then further screen the candidate objects through the first multimedia information, and compare the object attribute information of the candidate objects corresponding to each program with the object attribute information of the candidate objects, and further screen the candidate objects corresponding to each program, so as to facilitate users to re-determine the candidate objects according to the progress of the program, thereby improving the user experience of the AR glasses.

[0026] In another possible implementation, if there are at least two candidate objects, then controlling to display object attribute information of the candidate objects includes:

[0027] Determining object attribute information corresponding to each candidate object based on the facial features corresponding to each candidate object;

[0028] Obtaining the user's preference for each candidate object based on the historical information;

[0029] sorting the candidate objects according to their likeability;

[0030] According to the sorting result, the object attribute information corresponding to each candidate object is controlled to be displayed.

[0031] By adopting the above technical solution, when it is determined that there are at least two candidate objects, the object attribute information of the candidate objects is sorted and displayed according to the user's preference for each candidate object. The user will see the candidate objects with high preference first, which will increase the speed of determining the target object and thus improve the user experience.

[0032] In another possible implementation, obtaining the user's preference for each candidate object based on the historical information includes:

[0033] determining, based on the historical object information, the number of times each candidate object is determined as a target object;

[0034] Arrange each candidate object in descending order based on the number of times each candidate object is determined as a target object to obtain first sorting information;

[0035] Based on the historical multimedia information corresponding to each candidate object, respectively obtain the historical figure features corresponding to each candidate object, the historical figure features corresponding to any candidate object are the character features corresponding to any candidate object in each historical multimedia information, and the historical figure features include clothing features and hairstyle features;

[0036] Determine the number of historical figure features corresponding to each candidate object, the number of historical figure features corresponding to any candidate object is the number of different historical figure features of any candidate object in each historical multimedia information, the different historical figure features include: at least one of a clothing feature and a hairstyle feature is different;

[0037] Arrange the candidate objects in descending order based on the number of historical figure features corresponding to each of the candidate objects, so as to obtain second sorting information;

[0038] The user's preference for the candidate object is determined according to the first ranking information and the second ranking information.

[0039] By adopting the above technical solution, when the AR glasses obtain the user's preference for each candidate object through historical information, they obtain first sorting information through the number of times each candidate object is determined as the target object, and obtain second sorting information through the number of historical figure features corresponding to each candidate object, and then obtain final sorting information through the first sorting information and the second sorting information, and then reflect the user's preference for the candidate objects through the final sorting information, thereby improving the accuracy of the AR glasses in analyzing the user's preference for the candidate objects.

[0040] In another possible implementation, the user's selection operation adopts at least one of key selection, touch screen selection, gesture selection, and pupil recognition. When pupil recognition is adopted,

[0041] The determining of the target object based on the user's selection operation includes:

[0042] Obtaining display positions corresponding to the candidate objects respectively, wherein the display positions are display positions of the object attribute information in the display area;

[0043] Obtaining the user's pupil position and / or the dwell time of the user's sight at each display position;

[0044] The target object is determined based on at least one of the pupil position of the user and the dwelling time of the user's sight at each display position, and the display positions corresponding to each candidate object.

[0045] By adopting the above technical solution, after each candidate object is displayed in the display area, the AR glasses obtain the display position of each candidate object. Therefore, the AR glasses can determine the object attribute information that the user is looking at according to the correspondence between the user's pupil position and / or the user's line of sight and the display position of each candidate object, and the AR glasses can determine the target object selected by the user according to the user's pupil position and / or the residence time of the user's line of sight at the display position, thereby simplifying the steps for the user to select the target object.

[0046] In another possible implementation, the method further includes:

[0047] When the action information of the target object is detected as specific action information in the multimedia information of the current scene, a capture operation is performed to save the captured multimedia information, wherein the specific action information includes specific gesture action information and / or specific body action information of the target object.

[0048] By adopting the above technical solution, the AR glasses capture and save multimedia information when the action information of the target object is specific action information, and obtain multimedia information containing the target object according to the user's preferences, thereby meeting the user's personalized needs for using the AR glasses and improving convenience of use.

[0049] In a second aspect, the present application provides a person determination device based on AR glasses, comprising:

[0050] An acquisition module, used to acquire historical information, wherein the historical information includes historical multimedia information and / or historical object information, wherein the historical multimedia information is multimedia information containing historical objects, and the historical object information includes facial features of historical objects;

[0051] A first determination module, used to determine a candidate object based on the historical information, and control the display of object attribute information of the candidate object, wherein the object attribute information includes: name, gender, age and occupation;

[0052] A second determination module is used to determine a target object based on a selection operation of a user, and to determine a facial feature of the target object based on the historical information;

[0053] The control display module is used to track the target object from the multimedia information shot in the current scene based on the facial features of the target object, and control the display of the target object in the multimedia information shot in the current scene in a preset manner.

[0054] By adopting the above technical solution, when the user wears AR glasses in the current scene, the acquisition module acquires historical information, the first determination module determines the target object based on the user's selection, and the second determination module acquires the facial features of the target object from the historical information, thereby controlling the display module to track and display the target object in the multimedia information of the current scene based on the acquired facial features, thereby quickly selecting and determining the target object, and accurately tracking and displaying the target object.

[0055] In another possible implementation manner, when determining the candidate object based on the historical information, the first determining module is specifically configured to:

[0056] Acquire facial features of each historical object based on the historical information;

[0057] Get the time and location information of the current scene;

[0058] Acquire specific multimedia information based on the time information and the location information, the specific multimedia information including the appearance object in the current scene, and the specific multimedia information is multimedia information uploaded by other users that matches the time information and the location information;

[0059] Acquire facial features of the subject based on the specific multimedia information;

[0060] A candidate object is determined based on the facial features of the appearance object and the facial features of the historical object, wherein the facial features of the candidate object are facial features that are consistent between the facial features of the appearance object and the facial features of the historical object.

[0061] In another possible implementation manner, after determining the candidate object based on the historical information, the first determining module is specifically configured to:

[0062] Obtain object attribute information corresponding to each candidate object;

[0063] Obtaining a program list, the program list including the program sequence, the start time of each program, and the appearance object of each program;

[0064] Based on the program list, obtain object attribute information of the appearance objects corresponding to each program;

[0065] Determine the candidate object corresponding to each program based on the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object, wherein the object attribute information of the candidate object corresponding to each program is the object attribute information that is consistent between the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object;

[0066] Wherein, when controlling the display of object attribute information of the candidate object, the first determination module is specifically used to:

[0067] When the start time corresponding to each program is reached, the object attribute information of the corresponding candidate objects is displayed through control.

[0068] In another possible implementation, there are at least two candidate objects, and the first determination module, when controlling the display of object attribute information of the candidate objects, is specifically configured to:

[0069] Determining object attribute information corresponding to each candidate object based on the facial features corresponding to each candidate object;

[0070] Obtaining the user's preference for each candidate object based on the historical information;

[0071] sorting the candidate objects according to their likeability;

[0072] According to the sorting result, the object attribute information corresponding to each candidate object is controlled to be displayed.

[0073] In another possible implementation, when the first determination module obtains the user's preference for each candidate object based on the historical information, it is specifically configured to:

[0074] determining, based on the historical object information, the number of times each candidate object is determined as a target object;

[0075] Arrange each candidate object in descending order based on the number of times each candidate object is determined as a target object to obtain first sorting information;

[0076] Based on the historical multimedia information corresponding to each candidate object, respectively obtain the historical figure features corresponding to each candidate object, the historical figure features corresponding to any candidate object are the character features corresponding to any candidate object in each historical multimedia information, and the historical figure features include clothing features and hairstyle features;

[0077] Determine the number of historical figure features corresponding to each candidate object, the number of historical figure features corresponding to any candidate object is the number of different historical figure features of any candidate object in each historical multimedia information, the different historical figure features include: at least one of a clothing feature and a hairstyle feature is different;

[0078] Arrange the candidate objects in descending order based on the number of historical figure features corresponding to each of the candidate objects, so as to obtain second sorting information;

[0079] The user's preference for the candidate object is determined according to the first ranking information and the second ranking information.

[0080] In another possible implementation, the user's selection operation adopts pupil recognition, and the second determination module is specifically used to:

[0081] Obtaining display positions corresponding to the candidate objects respectively, wherein the display positions are display positions of the object attribute information in the display area;

[0082] Obtaining the user's pupil position and / or the dwell time of the user's sight at each display position;

[0083] The target object is determined based on at least one of the pupil position of the user and the dwelling time of the user's sight at each display position, and the display positions corresponding to each candidate object.

[0084] In another possible implementation, the device further includes a snapshot module, wherein:

[0085] The capture module is used to: when the action information of the target object is detected as specific action information in the multimedia information of the current scene, perform a capture operation and save the captured multimedia information, wherein the specific action information includes specific gesture action information and / or specific body action information of the target object.

[0086] In a third aspect, the present application proposes an AR glasses comprising a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any method in the first aspect.

[0087] By adopting the above technical solution, when the user wears the AR glasses in the current scene, the processor loads and executes the computer program stored in the memory, so that the AR glasses can obtain candidate objects from historical information, and the user determines the target object from the displayed candidate objects. When the user wears the AR glasses in the current scene, the AR glasses obtain historical information, determine the target object based on the user's selection, and obtain the facial features of the target object from the historical information, so that the target object can be tracked and displayed in the multimedia information of the current scene based on the acquired facial features, so that the target object can be quickly selected and determined, and the target object can be accurately tracked and displayed.

[0088] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the methods described in the first aspect.

[0089] By adopting the above technical solution, when the user wears the AR glasses in the current scene, the processor loads and executes the computer program stored in the computer-readable storage medium, and the program enables the AR glasses to obtain candidate objects from historical information, and the user determines the target object from the displayed candidate objects. When the user wears the AR glasses in the current scene, the AR glasses obtain historical information, determine the target object based on the user's selection, and obtain the facial features of the target object from the historical information, so that the target object can be tracked and displayed in the multimedia information of the current scene based on the acquired facial features, so that the target object can be quickly selected and determined, and the target object can be accurately tracked and displayed. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] Figure 1 It is a schematic diagram of the overall process of the method for determining a person based on AR glasses in an embodiment of the present application.

[0091] Figure 2 It is a structural diagram of a person determination device based on AR glasses in an embodiment of the present application.

[0092] Figure 3 It is a structural block diagram of the AR glasses in an embodiment of the present application. DETAILED DESCRIPTION

[0093] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0094] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0095] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0096] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0097] The present application provides a method for determining a person based on AR glasses, which can be performed by AR glasses. Figure 1 , including (step S101 to step S104):

[0098] Step S101: acquiring historical information, where the historical information includes historical multimedia information and / or historical object information, where the historical multimedia information is multimedia information containing historical objects, and the historical object information includes facial features of historical objects.

[0099] Users can use AR glasses in various activity venues, such as competitions or concerts. If they need to use AR glasses to watch activities and locate target persons, they can issue an activation command. When the AR glasses receive the user's activation command, they begin to determine the target object.

[0100] Among them, historical objects are objects that the user has paid attention to, historical objects include target objects that the user has determined, and historical multimedia information includes multimedia information saved by the user or automatically saved by AR glasses. Historical object information includes facial features of each person determined as a target object.

[0101] Step S102: determining candidate objects based on historical information, and controlling the display of object attributes of the candidate objects.

[0102] In an embodiment of the present application, historical information can reflect the user's viewing preference for an object. The AR glasses perform statistical processing on the historical information, determine candidate objects, and display the object attribute information of the candidate objects in the display area to facilitate the user to select the target object from the candidate objects.

[0103] Furthermore, the AR glasses can display the attribute information of the candidate objects in the form of a list in the display area, or display the attribute information of each candidate object in a grid and display the grid flatly in the display area. The present application does not specifically limit the display method.

[0104] Step S103: determining a target object based on the user's selection operation, and determining facial features of the target object based on historical information.

[0105] The user selects and determines the target object based on the attribute information of the candidate objects displayed in the display area. After the AR glasses obtain the user's selection operation information, they obtain the facial features of the target object.

[0106] Among them, the user's selection operation can be carried out by at least one of button selection, touch screen selection, gesture selection, and pupil recognition. This application does not specifically limit the selection operation method.

[0107] When the historical information only includes historical multimedia information, the AR glasses search for the historical multimedia information including the target object, and obtain the facial features of the target object through the historical multimedia information.

[0108] When the historical information includes historical multimedia information and historical object information, the AR glasses obtain the facial features of the target object in the historical multimedia information, and combine them with the facial information of the target object contained in the historical object information to obtain the final facial features of the target object, thereby improving the accuracy of the facial features of the target object.

[0109] Step S104: based on the facial features of the target object, the target object is tracked from the multimedia information captured in the current scene, and the target object is controlled to be displayed in the multimedia information captured in the current scene in a preset manner.

[0110] After the AR glasses obtain the facial features of the target object, they obtain the facial features of all objects in the multimedia information captured in the current scene, and compare the facial features of all objects with the facial features of the target object one by one. The object with consistent comparison is determined as the target object.

[0111] At this time, the AR glasses track the determined target object, and at the same time, in order to facilitate the user to view the target object, the AR glasses display the target object in a preset manner. In the embodiment of the present application, the AR glasses display the target object in a preset manner including at least one of displaying an indicator frame to select the target object, displaying an indicator arrow to indicate the target object, or magnifying and displaying the target object. It is convenient for the user to track and view the target person in the current scene.

[0112] An embodiment of the present application provides a method for determining a person based on AR glasses. The AR glasses determine candidate objects through historical information. The user selects a target object from the candidate objects according to the current scene. After the AR glasses obtain the user's selection operation, the target object's facial features are obtained according to the historical information, and the target object is tracked in the multimedia information of the current scene according to the facial features of the target object, and the target object is displayed in a preset manner.

[0113] Furthermore, the AR glasses store a lot of historical information and candidate objects, and a step is added for the user to select a target object from multiple candidate objects. In order to facilitate the user to quickly select the target object, the AR glasses determine the candidate objects in combination with the current scene. The candidate objects are determined based on the historical information, including (steps S1021 to S1025) (not shown in the figure):

[0114] Step S1021: Acquire facial features of each historical object based on historical information.

[0115] Specifically, when the AR glasses save historical multimedia information, face recognition is performed on historical objects in the historical multimedia information to obtain and save facial features of each historical object, so that the AR glasses can directly obtain the facial features of each object and simplify the calculation steps.

[0116] Step S1022: Obtain the time information and location information of the current scene.

[0117] Among them, when the AR glasses issue an activation command, the AR glasses can obtain the location information of the current scene and the current time information, and then search the Internet to obtain the name of the event held under the current location information and time information.

[0118] Step S1023: Acquire specific multimedia information based on the time information and the location information.

[0119] The specific multimedia information includes the objects that appear in the current scene, and the specific multimedia information is multimedia information uploaded by other users that matches the time information and the location information.

[0120] Specifically, after obtaining the time information and location information of the current scene, multimedia information matching the time information and location information can be obtained from the Internet based on the obtained time information. For example, if the time information of the current scene is 8:00 p.m. on November 17, 2021, and the location information is the Workers' Stadium, then videos shot and uploaded by other users at the Workers' Stadium between 7:50 p.m. on November 17, 2021 and 8:00 p.m. on November 17, 2021, are obtained from the Internet.

[0121] Among them, other users include audience members participating in the event or event officials. Therefore, the specific multimedia information may be multimedia information uploaded by audience members participating in the event, or may be posters or promotional videos sent by event officials.

[0122] Step S1024: Acquire facial features of the subject based on the specific multimedia information.

[0123] Specifically, the specific multimedia information includes the objects appearing in the current scene. The AR glasses obtain the facial features of the objects through the specific multimedia information, and determine the candidate objects according to the facial features of the objects.

[0124] Step S1025: Determine candidate objects based on the facial features of the present object and the facial features of the historical object.

[0125] The facial features of the candidate object are facial features that are consistent between the facial features of the appearance object and the facial features of the historical object.

[0126] Specifically, the facial features of historical objects are compared with the facial features of appearance objects one by one to screen out candidate objects. The screened out candidate objects all appear in the current scene, so the AR glasses do not display historical objects that do not appear, reducing the number of candidate objects and making it easier for users to quickly select target objects.

[0127] Furthermore, there is no strict execution order between step S1021 and step S1022, step S1023 and step S1024. For example, step S1021 can be executed after step S1022 or before step S1022. The embodiments of the present application do not specifically limit the execution order of the above steps, and any execution order is within the protection scope of the embodiments of the present application.

[0128] In another possible implementation of the embodiment of the present application, the AR glasses may determine the candidate object of each program through the program list of the current scene, wherein after the candidate object is determined based on the historical information, the method further includes (steps S1 to S4) (not shown in the figure):

[0129] Step S1: Obtain object attribute information of each candidate object.

[0130] Specifically, the AR glasses can obtain facial features of each candidate object in the historical information, and then obtain object attribute information of each candidate object through the Internet based on the facial features of each candidate object.

[0131] In another possible implementation, the AR glasses pre-store the object attribute information of each historical object input by the user, and the AR glasses directly obtain the object attribute information of each candidate object.

[0132] Step S2: Obtain a program list, which includes the program sequence, the start time of each program, and the appearance object of each program;

[0133] Among them, AR glasses can obtain the program list of the current scene through the Internet, and use text recognition to obtain the order of each program in the program list, the start time of each program, and the appearance objects of each program in turn.

[0134] In another implementation, the AR glasses can capture the program list of the current scene, so that the AR glasses can save the program list.

[0135] Step S3: obtaining object attribute information of the appearance objects corresponding to each program based on the program list;

[0136] Specifically, the AR glasses can obtain the object attribute information of each appearing object from the program list through text recognition, wherein the obtained object attribute information of each appearing object at least includes the name of the appearing object.

[0137] Step S4: determining the candidate object corresponding to each program based on the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object, wherein the object attribute information of the candidate object corresponding to each program is the object attribute information that is consistent with the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object;

[0138] Specifically, the attribute information of the appearance object corresponding to each program is compared with the object attribute information of the candidate object one by one. If at least the names of the two attribute information are consistent, the candidate objects with the consistent comparison are determined as the candidate objects corresponding to each program.

[0139] Among them, controlling the display of object attribute information of candidate objects includes:

[0140] When the start time corresponding to each program is reached, the object attribute information of the corresponding candidate objects is displayed through control.

[0141] Specifically, as the program progresses, the appearance objects of each program change. Before the program starts, the AR glasses display the object attribute information of the candidate objects corresponding to each program in the display area, so that the user can determine the target object corresponding to each program, thereby improving the user experience.

[0142] The embodiments of the present application do not specifically limit the execution order of the above steps, and any execution order is within the protection scope of the embodiments of the present application.

[0143] In another possible implementation, if there are at least two candidate objects, the attribute information of the candidate objects is controlled to be displayed, including: determining the object attribute information corresponding to each candidate object based on the facial features corresponding to each candidate object; obtaining the user's preference for each candidate object based on historical information; sorting each candidate object according to the preference of each candidate object; and controlling the display of the object attribute information corresponding to each candidate object according to the sorting result.

[0144] Specifically, after the AR glasses determine the candidate objects, they can obtain the object attribute information corresponding to each candidate object through the Internet search based on the facial information corresponding to each candidate object, or they can obtain the object attribute information corresponding to each candidate object from a preset database. Among them, the preset database stores the mapping relationship between the facial features of the object and the object attribute information. In the embodiment of the present application, the user can intuitively and clearly understand each candidate object through the object attribute information corresponding to each candidate object.

[0145] Among them, the user's preference for each candidate object can be obtained according to the frequency of occurrence of each candidate object in the historical information, and after the candidate objects are sorted by preference, it is convenient for the user to make personalized selection.

[0146] Furthermore, in order to obtain more accurate user preferences for each candidate object, the user preferences for each candidate object are obtained based on historical information, including (steps Sa to Sf) (not shown in the figure):

[0147] Step Sa: Determine the number of times each candidate object is determined as a target object based on the historical object information.

[0148] Specifically, after determining the target object from the historical objects, the AR glasses obtain the facial features of the target object and save the facial features of the target object. When the facial features of the saved historical objects are determined as the target objects multiple times, the facial features of the historical objects are saved together with the number of times they are determined as the target objects, that is, the AR glasses record the number of times each historical object is determined as the target object. Therefore, the AR glasses can directly determine the number of times each candidate object is determined as the target object through the historical object information.

[0149] In another possible implementation, the AR glasses save the facial features of a person determined as a target object each time. When the AR glasses determine the number of times each candidate object is determined as a target object, the facial information of the candidate object is compared one by one with the facial features of each historical object saved by the AR glasses. The number of consistent comparisons obtained is the number of times each candidate object is determined as a target object.

[0150] Step Sb: Arrange each candidate object in descending order based on the number of times each candidate object is determined as a target object to obtain first ranking information.

[0151] For example, the AR glasses determine that the candidate objects are A, B, and C, respectively, where the number of times each candidate object is determined as the target object is 1 time, 3 times, and 2 times, respectively. Then the first sorting information is B, C, and A.

[0152] Step Sc: Based on the historical multimedia information corresponding to each candidate object, the historical figure features corresponding to each candidate object are obtained respectively.

[0153] The historical figure features corresponding to any candidate object are the character features corresponding to any candidate object in each historical multimedia information, and the historical figure features include clothing features and hairstyle features.

[0154] When the AR glasses obtain and save the historical multimedia information corresponding to each historical object, they can perform image recognition on the historical multimedia information corresponding to each historical object, obtain the historical figure features corresponding to each historical object, and save them, so that when the AR glasses obtain the historical figure features corresponding to each candidate object, they can obtain them directly, reducing the calculation complexity and increasing the speed of obtaining the historical figure features corresponding to each candidate object.

[0155] In another possible implementation, after the AR glasses determine the candidate objects, the AR glasses perform image recognition on the historical multimedia information corresponding to each candidate object, and then obtain the characteristics of the historical figures corresponding to each candidate object.

[0156] Step Sd: Determine the number of historical figure features corresponding to each candidate object.

[0157] The number of historical figure features corresponding to any candidate object is the number of different historical figure features of any candidate object in each historical multimedia information, and the different historical figure features include: at least one of clothing features and hairstyle features is different.

[0158] Specifically, when the number of historical figure features of any candidate object in the historical multimedia information is large, it can be reflected that the user has viewed the candidate object through the AR glasses many times, and the corresponding preference degree of any candidate object is high.

[0159] For example, the historical figures of candidate A include:

[0160] Clothing feature 1, hair style feature 2;

[0161] Clothing feature 1, hair style feature 3;

[0162] Clothing feature 2, hair style feature 3;

[0163] Clothing features 2, hairstyle features 3.

[0164] Then the number of historical figure features corresponding to candidate object A is 3.

[0165] If the number of historical figure features corresponding to candidate object B is 4, the user's preference for candidate object B is higher than that for candidate object A.

[0166] Step Se: Arrange the candidate objects in descending order based on the number of historical figure features corresponding to each candidate object, so as to obtain second sorting information.

[0167] For example: the number of historical figure features corresponding to candidate object A is 3, the number of historical figure features corresponding to candidate object B is 4, and the number of historical figure features corresponding to candidate object C is 1, then the second sorting information is: B, A, C.

[0168] Step Sf: Determine the user's preference for the candidate object based on the first ranking information and the second ranking information.

[0169] Specifically, since the first ranking information is generated according to the number of times each candidate object is determined as the target object, the first ranking information can better reflect the user's preference for each candidate object than the content in the second ranking information. Therefore, when determining the user's preference for the candidate object based on the first ranking information and the second ranking information, the order of each candidate object in the first ranking information and the second ranking information is re-ranked according to the weight ratio to obtain the final ranking information, wherein the weight ratio of the order of the candidate object in the first ranking information is greater than the weight ratio in the second ranking information.

[0170] For example: the first sorting information: B, C, A;

[0171] Second sorting information: B, A, C;

[0172] Candidate object A: its ranking in the first ranking information is 3, and its ranking in the second ranking information is 2;

[0173] Candidate object B: its order in the first sorting information is 1, and its order in the second sorting information is 1;

[0174] Candidate object C: its ranking in the first ranking information is 2, and its ranking in the second ranking information is 3.

[0175] For example, the weight ratio of the order of candidate objects in the first sorting information is set to 60%, and the weight ratio of the order of candidate objects in the second sorting information is set to 40%, and the final sorting information B, C, A is calculated. It is determined that the user's preference for the candidate objects is B, C, A from high to low.

[0176] In another possible implementation, when the AR glasses use pupil recognition to obtain the user's selection operation, the target object is determined based on the user's selection operation, which may specifically include: obtaining the display position corresponding to each candidate object, the display position is the display position of the object attribute information in the display area; obtaining the user's pupil position and / or the residence time of the user's line of sight at each display position; determining the target object based on at least one of the user's pupil position and the residence time of the user's line of sight at each display position and the display position corresponding to each candidate object.

[0177] For the embodiment of the present application, when the AR glasses display the object attribute information corresponding to each candidate object in the display area, the human eye will sequentially look at the position where each candidate object is displayed, and then select the target object from each candidate object. The AR glasses can determine the position where the candidate object the user is looking at is displayed by obtaining the user's pupil position or the user's line of sight, and then judge the user's choice. When the user's pupil position and / or the user's line of sight stays at a certain display position for a time greater than a preset time, the candidate object displayed at the above position is determined to be the target object.

[0178] In another implementation, in order to allow the user to review the wonderful scenes in the current scene or certain actions of the target object, it also includes: when the action information of the target object is detected as specific action information in the multimedia information of the current scene, a snapshot operation is performed, and the captured multimedia information is saved, and the specific action information includes specific gesture action information and / or specific body action information of the target object.

[0179] Specifically, the AR glasses pre-store specific action information of the target object. For example, the specific action of the target object includes waving and / or looking directly into the lens of the AR glasses, and saves feature information of the specific action.

[0180] The AR glasses use the image processing module to identify the target object's action feature information in the multimedia information of the current scene, and the image analysis module determines whether the target object's action feature information is consistent with the feature information of a specific action. If they are consistent, the target object's action information is specific action information. Then, during the activity, the AR glasses capture and save multimedia information of the target object waving and / or looking directly at the lens of the AR glasses. And the captured multimedia information can be used as historical multimedia information.

[0181] The present application also provides a person recognition device based on AR glasses, referring to Figure 2 , the person recognition device 200 based on AR glasses includes:

[0182] An acquisition module 201 is used to acquire historical information, where the historical information includes historical multimedia information and / or historical object information, where the historical multimedia information is multimedia information containing historical objects, and the historical object information includes facial features of historical objects;

[0183] The first determination module 202 is used to determine the candidate object based on the historical information and control the display of the object attribute information of the candidate object, the object attribute information includes: name, gender, age and occupation;

[0184] A second determination module 203 is used to determine a target object based on a selection operation of the user, and to determine a facial feature of the target object based on historical information;

[0185] The control display module 204 is used to track the target object from the multimedia information captured in the current scene based on the facial features of the target object, and control the display of the target object in the multimedia information captured in the current scene in a preset manner.

[0186] In another possible implementation, when determining the candidate object based on the historical information, the first determining module 202 is specifically configured to:

[0187] Acquire facial features of each historical object based on historical information;

[0188] Get the time and location information of the current scene;

[0189] Acquire specific multimedia information based on time information and location information, where the specific multimedia information includes objects that appear in the current scene, and the specific multimedia information is multimedia information uploaded by other users that matches the time information and location information;

[0190] Acquire facial features of the subject based on specific multimedia information;

[0191] A candidate object is determined based on the facial features of the appearance object and the facial features of the historical object. The facial features of the candidate object are facial features that are consistent between the facial features of the appearance object and the facial features of the historical object.

[0192] In another possible implementation, after determining the candidate object based on the historical information, the first determining module 202 is specifically configured to:

[0193] Obtain object attribute information corresponding to each candidate object;

[0194] Obtaining a program list, the program list including the program sequence, the start time of each program, and the appearance object of each program;

[0195] Based on the program list, object attribute information of the appearance objects corresponding to each program is obtained;

[0196] Determine the candidate object corresponding to each program based on the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object, wherein the object attribute information of the candidate object corresponding to each program is the object attribute information that is consistent between the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object;

[0197] The first determining module 202, when controlling the display of the object attribute information of the candidate object, is specifically used to:

[0198] When the start time corresponding to each program is reached, the object attribute information of the corresponding candidate objects is displayed through control.

[0199] In another possible implementation, there are at least two candidate objects, and the first determining module 202, when controlling the display of object attribute information of the candidate objects, is specifically configured to:

[0200] Determine object attribute information corresponding to each candidate object based on the facial features corresponding to each candidate object;

[0201] Obtain the user's preference for each candidate object based on historical information;

[0202] Sort each candidate object according to its preference;

[0203] According to the sorting result, the object attribute information corresponding to each candidate object is controlled to be displayed.

[0204] In another possible implementation, when the first determining module 202 obtains the user's preference for each candidate object based on the historical information, it is specifically configured to:

[0205] determining a number of times each candidate object is determined as a target object based on the historical object information;

[0206] Arrange each candidate object in descending order based on the number of times each candidate object is determined as a target object to obtain first sorting information;

[0207] Based on the historical multimedia information corresponding to each candidate object, the historical figure features corresponding to each candidate object are obtained respectively, the historical figure features corresponding to any candidate object are the character features corresponding to any candidate object in each historical multimedia information, and the historical figure features include clothing features and hairstyle features;

[0208] Determine the number of historical figure features corresponding to each candidate object, the number of historical figure features corresponding to any candidate object is the number of different historical figure features of any candidate object in each historical multimedia information, the different historical figure features include: at least one of clothing features and hairstyle features is different;

[0209] Arrange the candidate objects in descending order based on the number of historical figure features corresponding to each candidate object, so as to obtain second sorting information;

[0210] The user's preference for the candidate object is determined according to the first ranking information and the second ranking information.

[0211] In another possible implementation, the user's selection operation adopts pupil recognition, and the second determination module 203 is specifically used to:

[0212] Obtaining the display position corresponding to each candidate object, where the display position is the display position of the object attribute information in the display area;

[0213] Obtaining the user's pupil position and / or the dwell time of the user's sight at each display position;

[0214] The target object is determined based on at least one of the user's pupil position and the dwelling time of the user's sight at each display position, and the display position corresponding to each candidate object.

[0215] In another possible implementation, the device also includes a capture module, which is used to: when the action information of the target object is detected as specific action information in the multimedia information of the current scene, perform a capture operation and save the captured multimedia information, the specific action information including specific gesture action information and / or specific limb action information of the target object.

[0216] The various variations and specific examples of the methods in the aforementioned embodiments are also applicable to the person determination device based on AR glasses in this embodiment. Through the aforementioned detailed description of the person determination method based on AR glasses, those skilled in the art can clearly understand the implementation method of the person determination device based on AR glasses in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0217] In order to better implement the above method, the present application embodiment provides an AR glasses, referring to Figure 3 , AR glasses 300 include: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the AR glasses 300 may also include a transceiver 304 and a display 305, and the display 305 is connected to the processor 301 through the bus 302. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the AR glasses 300 does not constitute a limitation on the embodiments of the present application.

[0218] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0219] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 302 may be divided into an address bus, a data bus, a control bus, etc.

[0220] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0221] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0222] The display 305 can be one of a combination of LCoS and prism, a combination of Micro OLED and free-form surface technology, a combination of LCoS / DLP and waveguide technology, and LBS and holographic reflective film.

[0223] Figure 3 The AR glasses shown are merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0224] An embodiment of the present application also provides a computer-readable storage medium, storing a computer program that can be loaded by a processor and executes a method for determining a person based on AR glasses as provided in the above embodiment. When a user wears AR glasses in a current scene, the AR glasses obtain candidate objects from historical information, and determine a target object based on user selection, so as to obtain facial features of the target object from the historical information, so that the target object can be tracked and displayed in the multimedia information of the current scene based on the acquired facial features, so that the target object can be quickly selected and determined, and the target object can be accurately tracked and displayed.

[0225] In this embodiment, the computer-readable storage medium may be a tangible device that holds and stores instructions used by the instruction execution device. The computer-readable storage medium may be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium may be a portable computer disk, a hard disk, a USB flash drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a podium random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, an optical disk, a magnetic disk, a mechanical encoding device, and any combination thereof.

[0226] The computer program in this embodiment includes program codes for executing all the aforementioned methods, and the program codes may include instructions corresponding to the steps of the methods provided in the above embodiments. The computer program can be downloaded from a computer-readable storage medium to various computing / processing devices, or downloaded to an external computer or external storage device via a network (such as the Internet, a local area network, a wide area network, and / or a wireless network). The computer program can be executed completely on the user's computer or as an independent software package.

[0227] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

[0228] In addition, it is to be understood that relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprises," "comprising," or any other variation thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements that are not explicitly listed, or elements that are inherent to such process, method, article, or device.

Claims

1. A method for determining a person based on AR glasses, characterized in that: include: Acquire historical information, where the historical information includes historical multimedia information and / or historical object information, where the historical multimedia information is multimedia information containing historical objects, and the historical object information includes facial features of historical objects; Determine candidate objects based on the historical information, and control display of object attribute information of the candidate objects, the object attribute information including: name, gender, age and occupation; Determine a target object based on a selection operation of the user, and determine a facial feature of the target object based on the historical information; Based on the facial features of the target object, the target object is tracked from the multimedia information captured in the current scene, and the target object is controlled to be displayed in a preset manner in the multimedia information captured in the current scene; The determining of the candidate object based on the historical information includes: Acquire facial features of each historical object based on the historical information; Get the time and location information of the current scene; Acquire specific multimedia information based on the time information and the location information, the specific multimedia information including the appearance object in the current scene, and the specific multimedia information is multimedia information uploaded by other users that matches the time information and the location information; Acquire facial features of the subject based on the specific multimedia information; Determine a candidate object based on the facial features of the appearance object and the facial features of the historical object, wherein the facial features of the candidate object are facial features that are consistent between the facial features of the appearance object and the facial features of the historical object; After determining the candidate object based on the historical information, the method further includes: Obtain object attribute information corresponding to each candidate object; Obtain a program list, the program list including the program sequence, the start time of each program, and the appearance object of each program; Based on the program list, object attribute information of the appearance objects corresponding to each program is obtained; wherein the object attribute information of each appearance object is obtained by character recognition of the program list, and the object attribute information of each appearance object obtained includes at least the name of the appearance object; Determine the candidate object corresponding to each program based on the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object, wherein the object attribute information of the candidate object corresponding to each program is the object attribute information that is consistent between the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object; The controlling and displaying of object attribute information of the candidate object includes: When the start time corresponding to each program is reached, the object attribute information of the corresponding candidate objects is displayed through control; If there are at least two candidate objects, Then, the object attribute information of the candidate object is controlled to be displayed, including: Determining object attribute information corresponding to each candidate object based on the facial features corresponding to each candidate object; Obtaining the user's preference for each candidate object based on the historical information; sorting the candidate objects according to their likeability; According to the sorting results, control the display of object attribute information corresponding to each candidate object; The obtaining of the user's preference for each candidate object based on the historical information includes: determining, based on the historical object information, the number of times each candidate object is determined as a target object; Arrange each candidate object in descending order based on the number of times each candidate object is determined as a target object to obtain first sorting information; Based on the historical multimedia information corresponding to each candidate object, respectively obtain the historical figure features corresponding to each candidate object, the historical figure features corresponding to any candidate object are the character features corresponding to any candidate object in each historical multimedia information, and the historical figure features include clothing features and hairstyle features; Determine the number of historical figure features corresponding to each candidate object, the number of historical figure features corresponding to any candidate object is the number of different historical figure features of any candidate object in each historical multimedia information, the different historical figure features include: at least one of a clothing feature and a hairstyle feature is different; Arrange the candidate objects in descending order based on the number of historical figure features corresponding to each of the candidate objects, so as to obtain second sorting information; Determining the user's preference for the candidate object according to the first ranking information and the second ranking information; When determining the user's preference for candidate objects based on the first sorting information and the second sorting information, the order of each candidate object in the first sorting information and the second sorting information is re-sorted according to the weight ratio to obtain final sorting information, wherein the weight ratio of the order of the candidate objects in the first sorting information is greater than the weight ratio in the second sorting information.

2. The method according to claim 1, characterized in that The user's selection operation adopts at least one of key selection, touch screen selection, gesture selection, and pupil recognition. When pupil recognition is adopted, The determining of the target object based on the user's selection operation includes: Obtaining display positions corresponding to the candidate objects respectively, wherein the display positions are display positions of the object attribute information in the display area; Obtaining the user's pupil position and / or the dwell time of the user's sight at each display position; The target object is determined based on at least one of the pupil position of the user and the dwelling time of the user's sight at each display position, and the display positions corresponding to each candidate object.

3. The method according to claim 1, characterized in that Also includes: When the action information of the target object is detected as specific action information in the multimedia information of the current scene, a capture operation is performed to save the captured multimedia information, wherein the specific action information includes specific gesture action information and / or specific body action information of the target object.

4. A person recognition device based on AR glasses, characterized in that: include: An acquisition module, configured to acquire historical information upon receiving an activation instruction from a user, wherein the historical information includes historical multimedia information and / or historical object information, wherein the historical multimedia information is multimedia information containing historical objects, and the historical object information includes facial features of historical objects; A first determination module is used to determine a candidate object and control the display of object attribute information of the candidate object, wherein the object attribute information includes: name, gender, age and occupation; A second determination module is used to determine a target object based on a selection operation of a user, and to determine a facial feature of the target object based on the historical information; A control display module, used for tracking the target object from the multimedia information shot in the current scene based on the facial features of the target object, and controlling the display of the target object in a preset manner in the multimedia information shot in the current scene; When determining the candidate object based on the historical information, the first determination module is specifically used to: Acquire facial features of each historical object based on historical information; Get the time and location information of the current scene; Acquire specific multimedia information based on time information and location information, where the specific multimedia information includes objects that appear in the current scene, and the specific multimedia information is multimedia information uploaded by other users that matches the time information and location information; Acquiring facial features of the subject based on specific multimedia information; Determine a candidate object based on the facial features of the appearance object and the facial features of the historical object, wherein the facial features of the candidate object are facial features that are consistent between the facial features of the appearance object and the facial features of the historical object; After determining the candidate object based on the historical information, the first determination module is specifically configured to: Obtain object attribute information corresponding to each candidate object; Obtain a program list, the program list including the program sequence, the start time of each program, and the appearance object of each program; Based on the program list, object attribute information of the appearance objects corresponding to each program is obtained; wherein the object attribute information of each appearance object is obtained by character recognition of the program list, and the object attribute information of each appearance object obtained includes at least the name of the appearance object; Determine the candidate object corresponding to each program based on the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object, wherein the object attribute information of the candidate object corresponding to each program is the object attribute information that is consistent between the object attribute information of the appearance object corresponding to each program and the object attribute information of the candidate object; Wherein, when controlling the display of object attribute information of the candidate object, the first determination module is specifically used to: When the start time corresponding to each program is reached, the object attribute information of the corresponding candidate objects is displayed through control; There are at least two candidate objects, and the first determining module, when controlling the display of object attribute information of the candidate objects, is specifically used to: Determine object attribute information corresponding to each candidate object based on the facial features corresponding to each candidate object; Obtain the user's preference for each candidate object based on historical information; Sort each candidate object according to its preference; According to the sorting results, control the display of object attribute information corresponding to each candidate object; When the first determining module obtains the user's preference for each candidate object based on the historical information, it is specifically used to: determining a number of times each candidate object is determined as a target object based on the historical object information; Arrange each candidate object in descending order based on the number of times each candidate object is determined as a target object to obtain first sorting information; Based on the historical multimedia information corresponding to each candidate object, the historical figure features corresponding to each candidate object are obtained respectively, the historical figure features corresponding to any candidate object are the character features corresponding to any candidate object in each historical multimedia information, and the historical figure features include clothing features and hairstyle features; Determine the number of historical figure features corresponding to each candidate object, the number of historical figure features corresponding to any candidate object is the number of different historical figure features of any candidate object in each historical multimedia information, the different historical figure features include: at least one of clothing features and hairstyle features is different; Arrange the candidate objects in descending order based on the number of historical figure features corresponding to each candidate object, so as to obtain second sorting information; Determining the user's preference for the candidate object according to the first ranking information and the second ranking information; When determining the user's preference for candidate objects based on the first sorting information and the second sorting information, the order of each candidate object in the first sorting information and the second sorting information is re-sorted according to the weight ratio to obtain final sorting information, wherein the weight ratio of the order of the candidate objects in the first sorting information is greater than the weight ratio in the second sorting information.

5. An AR glasses, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and executes any one of the methods according to claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images