Pointing selection method and device based on spatial perception positioning, equipment and medium

Abstract

The invention discloses a direction selection method and device based on spatial perception positioning, equipment and a medium. The method comprises the following steps: acquiring a current area and a specific position of a user; when the pointing information of the user is detected, a pointing axis is determined according to the pointing information, and a virtual elliptic cone area with an axial angle is constructed around the pointing axis; obtaining an object set covered by the virtual elliptic cone region in the region where the user is located, and determining priorities of all objects in the object set; and pushing subscription information corresponding to the object with the highest priority in the object set to the user, and / or selecting a target object from the object set according to an instruction given by the user and executing corresponding operation. The invention provides a sensing technology for user position and user pointing selection so as to accurately identify the operation intention and the target object of the user, thereby realizing more intuitive operation execution and simplifying instruction input. The method is of great significance in promoting highly intelligent development in the fields of industry, smart home and the like.

Description

Technical Field

[0001] The present invention relates to the field of perception and positioning technology, and in particular to a direction selection method, device, equipment and medium based on space perception and positioning. Background Art

[0002] In application scenarios such as industry and smart home, when the system can obtain the current position of the operator, and even know the operator's operation intention and its target at the same time, the execution of the corresponding operation will be more intuitive and the instructions will be simpler. For example, in the industrial field, in a certain modeled warehouse area, the identified and located workers can easily "subscribe to the task information of the current area"; the workers only need to point their fingers from a distance and issue the command "what is in this box (i.e. the target object)" to provide the system with sufficient information for query. Similarly, in the field of smart home, in a certain modeled room, the identified and located members can directly issue the command "open the curtains", and the home system will open the curtains of the corresponding room; members can point their fingers from a distance and give the command "turn on this light", and the home system can accurately turn on the lamps pointed by the members. Therefore, the development of an accurate and adaptable pointing selection recognition technology is of great significance to promoting the highly intelligent development of fields such as industry and smart home. Summary of the invention

[0003] The purpose of the present invention is to provide a direction selection method, device, equipment and medium based on spatial perception positioning, aiming to solve the problem of inaccurate direction selection recognition in the prior art.

[0004] In a first aspect, an embodiment of the present invention provides a direction selection method based on space perception positioning, including: Get the user's current area and specific location; When the user's pointing information is detected, a pointing axis is determined according to the pointing information and a virtual elliptical cone area with an axis angle is constructed around the pointing axis; Obtaining a collection of objects covered by the virtual elliptical cone area in the area where the user is located, and determining the priorities of all objects in the collection of objects; Pushing subscription information corresponding to the object with the highest priority in the object collection to the user, and / or selecting a target object from the object collection according to an instruction given by the user and performing a corresponding operation.

[0005] In a second aspect, an embodiment of the present invention provides a direction selection device based on space perception positioning, including: Position location unit, used to obtain the user's current area and specific location; A pointing area acquisition unit, configured to, when the pointing information of the user is detected, determine the pointing axis according to the pointing information and construct a virtual elliptical cone area with an axis angle around the pointing axis; A pointing object acquisition unit, used to acquire a collection of objects covered by the virtual elliptical cone area in the area where the user is located, and determine the priority of all objects in the collection of objects; The pointing object selection unit is used to push the subscription information corresponding to the object with the highest priority in the object collection to the user, and / or select the target object from the object collection according to the instruction given by the user and perform the corresponding operation.

[0006] In a third aspect, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the pointing selection method based on spatial perception positioning described in the first aspect is implemented.

[0007] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the pointing selection method based on spatial perception positioning described in the first aspect above.

[0008] The beneficial effects of the embodiments of the present invention are: Providing the perception technology of user position and user direction selection to accurately identify the user's operation intention and target object, thereby achieving more intuitive operation execution and simplifying command input. It is of great significance to promote the highly intelligent development of industries and smart homes. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 A schematic diagram of a flow chart of a direction selection method provided by an embodiment of the present invention; Figure 2 A schematic diagram of a sub-process (implementation method 1) of step S102 provided in an embodiment of the present invention; Figure 3 A schematic diagram of the process after step S102 provided in an embodiment of the present invention; Figure 4 A schematic diagram of a sub-process (implementation method 2) of step S102 provided in an embodiment of the present invention; Figure 5 A schematic diagram of a sub-flow chart of step S103 provided in an embodiment of the present invention; Figure 6 A schematic diagram of a sub-process of step S104 provided in an embodiment of the present invention; Figure 7 A schematic block diagram of a pointing selection device provided by an embodiment of the present invention; Figure 8 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0013] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.

[0014] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0015] See also Figure 1 , Figure 1 A schematic diagram of a flow chart of a direction selection method based on spatial perception positioning provided by an embodiment of the present invention; like Figure 1 As shown, the method includes steps S101-S104.

[0016] S101, obtaining the user's current area and specific location; In this step, the area and specific location of the user can be obtained through a positioning device (such as a head-mounted device) with a positioning function (including a gyroscope and camera for positioning) carried by the user; the area and specific location of the user can also be obtained through a positioning device carried by the user with a gesture and eye tracking function, and through fixed camera equipment installed in each area.

[0017] S102, when the user's pointing information is detected, determining a pointing axis according to the pointing information and constructing a virtual elliptical cone area with an axis angle around the pointing axis; In this step, the pointing information refers to the directional indication provided by the user. By analyzing this pointing information, a pointing axis is determined, and then a virtual elliptical cone area is constructed outward around this pointing axis. The virtual elliptical cone area has a certain axis angle and is used to define the spatial range where the user may intend to interact. This design aims to improve the flexibility and accuracy of the interaction, allowing users to select or operate specific objects or areas through simple pointing actions.

[0018] S103, obtaining a collection of objects covered by the virtual elliptical cone area in the area where the user is located, and determining the priority of all objects in the collection of objects; In this step, the higher the priority of an object, the more likely it is that the user may intend to interact with the target object. The system will give priority to high-priority objects as the focus of interaction to improve the accuracy of the interaction.

[0019] S104: Pushing subscription information corresponding to the object with the highest priority in the object collection to the user, and / or, selecting a target object from the object collection according to an instruction given by the user and performing a corresponding operation; In this step, the subscription information corresponding to the object can be pre-set to automatically push the subscription information corresponding to the object with the highest priority to the user when no instruction is given by the user; and when the user gives an instruction, the target object that the user intends to interact with is selected based on the information of the instruction to execute the corresponding operation of the instruction.

[0020] In this embodiment, the solution of steps S101-S104 provides a technology for sensing the user's position and the user's pointing selection, so as to accurately identify the user's operation intention and the target object, thereby achieving more intuitive operation execution and simplifying command input. This is of great significance for promoting the highly intelligent development of industries and smart homes.

[0021] In some specific application scenarios, such as in the industrial field, when workers are identified and located in a modeled warehouse area, they can more conveniently "subscribe to the task information of the current area"; workers only need to point their fingers from a distance, supplemented by the command "what's in this box", to provide the system with sufficient information for query. Similarly, in the field of smart homes, when members are identified and located in a modeled room, they can directly issue the command "open the curtains", and the home system will automatically open the curtains in the corresponding room. In addition, members can point their fingers from a distance, supplemented by the command "turn on this light", and the home system can accurately turn on the lamps pointed by the members.

[0022] In one embodiment, the user location positioning in step S101 requires modeling in advance, which generally refers to positioning and recording each object in the area in the industry. Some immovable objects (such as pillars) can be used for positioning anchor points and correction, and operable objects (such as goods) can be selected for operation after the user provides coordinates; in the field of smart homes, mobile phone cameras are generally used to scan and build models for each room in the home, and by adding operable objects (such as smart furniture) to the room model, objects can be directly operated in the model.

[0023] In one embodiment, there are two ways of detecting the area and position of the user in step S101: active detection and passive detection.

[0024] In the first type of active detection, as long as the user is in the modeled area, the user's location and specific position are determined in real time through the positioning device carried by the user; the positioning of fixed camera equipment in the area is an alternative solution. When using fixed cameras, other personnel positioning methods are required to identify the located individuals; the algorithm monitors the position of each positioning device at regular intervals and subscribes to notifications of positioning changes, so there will be a certain delay. Active detection mainly realizes non-precise positioning. By dividing a large area into multiple small areas (for example, in industry, it can be divided according to work areas, and in home environments, it can be divided according to rooms), active detection is used to determine the area where the operator is located. The following three functions can be mainly realized.

[0025] Function 1: Automatically push high-priority information. For example, when a worker is in a specific work area, he or she will automatically subscribe to the alarm information in this work area, and the alarm will be automatically pushed when it occurs.

[0026] Function 2: As an auxiliary positioning tool for other functions. For example, when family members need to operate certain unique objects or objects with significantly different priorities in a specific room (such as there are multiple devices in the room, but the priorities are obviously different; for example, in a room with a main light, the main light obviously has a higher priority when the "turn on the light" operation is performed), there is no need to provide additional location information in the command. In addition, this function can also be combined with command information as a source of secondary priority information (that is, if a conflict occurs, the command information shall prevail): for example, when a family member issues an "open the curtains" command in the bedroom, the system should open the corresponding curtains in the bedroom according to the priority of the curtains; and when a family member issues a "turn on the living room ceiling light" command in the bedroom, the system will determine the living room as the room to be operated based on the priority, rather than the current bedroom.

[0027] Function 3: As a switching signal for preloading regional models, accurate positioning usually relies on high-precision modeling or obtaining relevant information about the area in advance to speed up the positioning process. Once it is confirmed that the user has entered a specific area, the positioning device (such as a head-mounted device) can be notified to load the model of the corresponding area, thereby speeding up the response speed of subsequent triggering detection functions.

[0028] In the second passive detection method, when the user directly makes a request or a user behavior trigger is detected, the area and specific location of the user are obtained (the acquisition method is the same as the active detection method), and then various action information of the user is obtained, such as head posture, finger movements, eye movements, etc., to provide analysis basis for subsequent pointing selection.

[0029] There are two implementation methods for constructing a virtual elliptical cone region in step S102 of the present invention.

[0030] In the first embodiment, Figure 2 As shown, step S102 may include: S201, when a pointing point triggered by a user is detected, identifying the coordinates of the pointing point of the user; S202, taking the line connecting the user's head coordinates and the pointing point coordinates as the pointing axis; S203: construct a virtual elliptical cone area with an axis angle around the pointing axis, wherein the axis angle in the horizontal direction is greater than the axis angle in the vertical direction.

[0031] In this embodiment, the pointing point triggered by the user can be the pointing information obtained by finger triggering (such as detecting the pointing action of the user's finger), and a ray starting from the head coordinates and passing through the pointing point coordinates (i.e., the fingertip coordinates) is made as the pointing axis, and a virtual elliptical cone area with an axis angle is constructed around the pointing axis. Among them, in order to accurately simulate the line of sight of the human eye, the axis angle in the horizontal direction is set to be greater than the axis angle in the vertical direction. This is because the field of view of the human eye in the horizontal direction is inherently greater than the field of view in the vertical direction, and it is also considered that when the user performs a pointing operation, he usually moves within a certain range in the horizontal direction, while the range of movement in the vertical direction is relatively small. Therefore, the axis angle in the horizontal direction is set to be greater than the axis angle in the vertical direction, which will be closer to the actual operation habits of the user. Such a design not only improves the accuracy of the pointing selection, but also makes the user's operation experience more natural and smooth.

[0032] In this embodiment, the size of the axis angle can be adjusted, and the relative distance between the head coordinates and the pointing point coordinates is negatively correlated with the axis angle, that is, the larger the relative distance between the head coordinates and the pointing point coordinates, the smaller the axis angle; this is to take into account the error caused by positioning accuracy, because the remote positioning range is a virtual elliptical cone area made by the line connecting the head and the fingertips. When the fingertips are positioned, the closer the distance between the fingertips and the head is, the greater the error in the distant projection will be under the same error accuracy. Therefore, when the fingertip coordinates are far away from the head coordinates, the misjudgment area caused by errors will be reduced, and the axis angle can be reduced. The specific standard depends on the device and the user, and needs to be calibrated during actual use. The preferred initial reference values ​​are: 1-3° in the up and down direction and 3-10° in the left and right direction; the distance between the reference finger and the head is 80-40cm (negative correlation), and these parameters can be processed linearly.

[0033] Further, such as Figure 3 As shown, after step S201, the following steps are also included: S301, obtaining three Euler angles of the user's head posture; S302, determining whether the user's finger is within the preset range of the center of the three Euler angles; if so, proceeding to step S303; if not, jumping to step S304; S303, taking the line connecting the coordinates of the user's head and the coordinates of the fingertips as the pointing axis; S304: Determine that the triggered finger action is a false alarm action and ignore it.

[0034] In steps S301-S304, the three Euler angles of the head posture can be identified by a positioning device or a fixed camera; the role of the three Euler angles is to determine whether there is a false alarm in the user's finger action, because in human habits, when consciously using fingers to point, the head will cooperate to turn to see the fingers in a certain area, and this angle usually does not exceed 20 degrees up and down, so the preset range can be set to within plus or minus 20 degrees of the center of the three Euler angles. When it is detected that the three Euler angles of the user's head posture and the fingertip position relationship meet this condition, we believe that the user is consciously using the finger to perform a pointing operation. At this time, the system will calculate the pointing axis based on the head coordinates and the fingertip coordinates for subsequent interactive logic processing. If the relationship between the head Euler angle and the finger position does not meet the preset conditions, that is, the head posture and the finger action are not coordinated, then the system will ignore the finger action to avoid the occurrence of misoperation. This design is intended to improve the accuracy and fluency of user interaction and ensure that the user's intention can be correctly identified and executed.

[0035] In the second embodiment, if Figure 4 As shown, step S102 includes: S401, when a pointing angle triggered by binocular gaze of the user is detected, taking the central axis of the pointing angle as the pointing axis; S402: construct a virtual elliptical cone area with an axis angle around the pointing axis, wherein the axis angle in the horizontal direction is greater than the axis angle in the vertical direction.

[0036] In this embodiment, eye tracking technology (glasses with eye tracking function) can be used to sense the movement trajectory of the user's eyes, so as to capture the user's pointing intention. When the user's line of sight is stably staring, the gaze point is used as the starting point for triggering the pointing action. At this time, the eye tracking technology can accurately track the gaze position of the user's eyes, and then determine the central axis of the pointing angle as the pointing axis. Among them, the axis angle size of step S402 can refer to the setting method of embodiment 1. After determining the axis angle, a virtual elliptical cone area can be constructed around the pointing axis.

[0037] In one embodiment, if Figure 5 As shown, step S103 includes: S501, obtaining a non-blocking cross section formed by the intersection or boundary intersection of the virtual elliptical cone area and the object in the area where the user is located; S502, obtaining all objects whose mutually non-occluding cross sections cover the area where the user is located, and constructing an object collection; S503: Taking the center of the mutually non-occluded cross-section or the coordinates of the user's head as the priority starting point, the closer the object is to the priority starting point, the higher the priority is.

[0038] In this embodiment, in the mutually non-occluded cross-section obtained by step S501, there may be multiple cross-section fragments due to the intersection of multiple objects or boundaries. When a cross-section fragment is partially obscured by other cross-section fragments and cannot be directly perceived by the virtual elliptical cone area (that is, the user's field of view cannot directly see it), only the unobstructed area is considered. When a cross-section fragment is completely obscured by other cross-section fragments and cannot be directly perceived by the virtual elliptical cone area, this cross-section fragment is ignored.

[0039] In this embodiment, through step S502 to step S503, all objects covered by mutually non-occluding cross sections are constructed into an object collection, and the priority of each object is set to provide a basis for subsequent direction selection.

[0040] In one embodiment, if Figure 6 As shown, step S104 includes: S601, when no instruction given by the user is received, push the subscription information corresponding to the object with the highest priority in the object collection to the user; S602: When receiving an instruction given by the user, obtain the object information and / or position information in the instruction, confirm the target object in the object collection according to the object information and / or position information, and perform corresponding operations according to the operation requirements for the target object in the instruction.

[0041] In this embodiment, step S601 is a case where no instruction given by the user is received. The subscription information corresponding to the object with the highest priority (i.e., the target object) can be pushed to the user (such as the user's operation interface); for example, when the user confirms through the above embodiment that the target object selected by the user is a commodity, the subscription information related to the commodity is pushed to the user's head-mounted device or handheld device operation interface.

[0042] In this embodiment, step S602 is the case where an instruction given by the user is received. The objects in the object collection need to be sorted according to the information in the instruction. For example, when the user stares at a column but says "what's in this cargo box", the cargo box with the highest priority (i.e., the target object) should be found in the object collection for operation. When the instruction contains relative position information, the highest priority item in the object collection is taken as the starting point, and selection is made in the area according to the relative position: for example, when the user stares at a cargo box but says "what's behind this cargo box", the object closest to the worker that is blocked by this cargo box (i.e., the target object) should be selected. When the instruction contains absolute position information, the priority in the instruction is higher: for example, when the worker stares at a cargo box but says "where is the nearest forklift (i.e., the target object)", it is not necessary to consider whether the item is in the object collection when processing the instruction.

[0043] The embodiment of the present invention further provides a device for selecting a direction based on spatial perception and positioning, and the device for selecting a direction based on spatial perception and positioning is used to execute any embodiment of the method for selecting a direction based on spatial perception and positioning. Figure 7 , Figure 7 It is a schematic block diagram of a pointing selection device based on space perception positioning provided by an embodiment of the present invention.

[0044] like Figure 7 As shown, the pointing selection device 700 based on space perception positioning includes: a position positioning unit 701, a pointing area acquisition unit 702, a pointing object acquisition unit 703 and a pointing object selection unit 704.

[0045] Position location unit 701, used to obtain the area and specific location of the user; The pointing area acquisition unit 702 is used to determine the pointing axis according to the pointing information and construct a virtual elliptical cone area with an axis angle around the pointing axis when the pointing information of the user is detected; The pointing object acquisition unit 703 is used to acquire a collection of objects covered by the virtual elliptical cone area in the area where the user is located, and determine the priority of all objects in the collection of objects; The pointing object selection unit 704 is used to push the subscription information corresponding to the object with the highest priority in the object collection to the user, and / or select the target object from the object collection according to the instruction given by the user and perform the corresponding operation.

[0046] The device provides a technology to perceive the user's position and direction selection, so as to accurately identify the user's operation intention and target object, thereby achieving more intuitive operation execution and simplifying command input. It is of great significance to promote the highly intelligent development of industries and smart homes.

[0047] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0048] The above-mentioned direction selection device based on spatial perception positioning can be implemented in the form of a computer program, and the computer program can be used in a computer system such as Figure 8 Runs on the computer device shown.

[0049] See also Figure 8 , Figure 8 800 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 800 is a server, which can be an independent server or a server cluster composed of multiple servers.

[0050] See also Figure 8 The computer device 800 includes a processor 802 , a memory and a network interface 805 connected via a system bus 801 , wherein the memory may include a non-volatile storage medium 803 and an internal memory 804 .

[0051] The non-volatile storage medium 803 may store an operating system 8031 ​​and a computer program 8032. When the computer program 8032 is executed, the processor 802 may execute a direction selection method based on spatial perception positioning.

[0052] The processor 802 is used to provide computing and control capabilities and support the operation of the entire computer device 800.

[0053] The internal memory 804 provides an environment for the operation of the computer program 8032 in the non-volatile storage medium 803. When the computer program 8032 is executed by the processor 802, the processor 802 can execute a pointing selection method based on spatial perception positioning.

[0054] The network interface 805 is used for network communication, such as providing data information transmission, etc. Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 800 to which the solution of the present invention is applied. The specific computer device 800 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0055] Those skilled in the art will understand that Figure 8 The embodiments of the computer device shown in the figure do not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such embodiments, the structure and function of the memory and the processor are the same as those of the embodiment of the present invention. Figure 8 The embodiments shown are consistent and will not be described again here.

[0056] It should be understood that in the embodiment of the present invention, the processor 802 may be a central processing unit (CPU), and the processor 802 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0057] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the pointing selection method based on spatial perception positioning of the embodiment of the present invention is implemented.

[0058] The storage medium is a physical, non-transient storage medium, for example, it can be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk, etc., which can store program codes.

[0059] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0060] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A direction selection method based on spatial perception positioning, characterized in that: include: Get the user's current area and specific location; When the user's pointing information is detected, a pointing axis is determined according to the pointing information and a virtual elliptical cone area with an axis angle is constructed around the pointing axis; Obtaining a collection of objects covered by the virtual elliptical cone area in the area where the user is located, and determining the priorities of all objects in the collection of objects; Pushing subscription information corresponding to the object with the highest priority in the object collection to the user, and / or selecting a target object from the object collection according to an instruction given by the user and performing a corresponding operation.

2. The method for direction selection based on spatial perception positioning according to claim 1, characterized in that: The obtaining of the current region and specific location of the user includes: Obtain the user's current area and specific location through a positioning device with positioning function carried by the user; or The user's current area and specific location are obtained through the camera equipment installed in each area.

3. The method for direction selection based on spatial perception positioning according to claim 1, characterized in that: When the user's pointing information is detected, a pointing axis is determined according to the pointing information and a virtual elliptical cone area with an axis angle is constructed around the pointing axis, including: When a pointing point triggered by a user is detected, the coordinates of the pointing point of the user are identified; The line connecting the user's head coordinates and the pointing point coordinates is used as the pointing axis; A virtual elliptical cone area with an axis angle is constructed around the pointing axis, wherein the axis angle in the horizontal direction is greater than the axis angle in the vertical direction.

4. The method for direction selection based on spatial perception positioning according to claim 3, characterized in that: After the step of identifying the coordinates of the user's pointing point when the pointing point triggered by the user is detected, the method further includes: Get the three Euler angles of the user's head posture; Determine whether the user's finger is within the preset range of the center of the three Euler angles; If yes, the line connecting the user's head coordinates and the fingertip coordinates is used as the pointing axis; If not, the triggered finger action is determined to be a false alarm action and ignored.

5. The method for direction selection based on spatial perception positioning according to claim 1, characterized in that: When the user's pointing information is detected, a pointing axis is determined according to the pointing information and a virtual elliptical cone area with an axis angle is constructed around the pointing axis, including: When a pointing angle triggered by the user's binocular gaze is detected, the central axis of the pointing angle is used as the pointing axis; A virtual elliptical cone area with an axis angle is constructed around the pointing axis, wherein the axis angle in the horizontal direction is greater than the axis angle in the vertical direction.

6. The method for direction selection based on spatial perception positioning according to claim 1, characterized in that: The obtaining of a collection of objects covered by the virtual elliptical cone area in the area where the user is located, and determining the priorities of all objects in the collection of objects includes: Obtaining a mutually non-blocking cross section formed by the intersection or boundary intersection of the virtual elliptical cone area and an object in the area where the user is located; Acquire all objects covered by the mutually non-occluding cross-sections on the area where the user is located, and construct an object collection; The center of the mutually non-occluded cross section or the coordinates of the user's head is taken as the priority starting point, and the closer the object is to the priority starting point, the higher the priority is.

7. The method for direction selection based on spatial perception positioning according to claim 1, characterized in that: The pushing of subscription information corresponding to the object with the highest priority in the object collection to the user, and / or, selecting a target object from the object collection and performing a corresponding operation according to an instruction given by the user, includes: When no instruction given by the user is received, the subscription information corresponding to the object with the highest priority in the object collection is pushed to the user; When receiving an instruction given by the user, the object information and / or position information in the instruction is obtained, the target object in the object collection is confirmed according to the object information and / or position information, and the corresponding operation is performed according to the operation requirements for the target object in the instruction.

8. A pointing selection device based on spatial perception and positioning, characterized in that: include: Position location unit, used to obtain the user's current area and specific location; A pointing area acquisition unit, configured to, when the pointing information of the user is detected, determine the pointing axis according to the pointing information and construct a virtual elliptical cone area with an axis angle around the pointing axis; A pointing object acquisition unit, used to acquire a collection of objects covered by the virtual elliptical cone area in the area where the user is located, and determine the priority of all objects in the collection of objects; The pointing object selection unit is used to push the subscription information corresponding to the object with the highest priority in the object collection to the user, and / or select the target object from the object collection according to the instruction given by the user and perform the corresponding operation.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the direction selection method based on spatial perception positioning as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to perform the direction selection method based on spatial perception positioning as described in any one of claims 1 to 7.

Images