Individualized consciousness rehabilitation interactive training method based on virtual scene intelligent generation

Abstract

Embodiments of the present disclosure disclose an individualized consciousness rehabilitation interaction training method based on virtual scene intelligent generation. A specific embodiment of the system includes: initializing meta-object information, object attribute information and relationship network to generate meta-object target information, object attribute target information and target relationship network; based on the object attribute target information and the target relationship network, generating target object space information corresponding to the meta-object target information; performing collision detection on the target object space information to generate scene required object information; storing the scene required object information into a preset scene graph; determining the scene required object information as the meta-object target information, repeating the above steps until the iteration convergence condition is met, and obtaining a target scene graph. The embodiment provides a programmed virtual scene consistent with common sense, thereby providing effective consciousness rehabilitation training for patients.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, specifically to a method and apparatus for individualized consciousness rehabilitation interactive training based on intelligent generation of virtual scenes. Background Technology

[0002] Traumatic brain injury is often accompanied by a loss of consciousness and perception. During rehabilitation, patients need to be exposed to realistic scenarios that align with common sense, and their consciousness is trained through recognizing and interacting with objects within these scenarios. Currently, consciousness rehabilitation training often requires the creation of realistic scenarios in rehabilitation centers or the use of VR (Virtual Reality). However, when using these methods for consciousness rehabilitation training, the following technical problems frequently arise:

[0003] First, setting up real-life scenarios in rehabilitation centers is often costly. Real-life training models are subject to many time and space constraints, making them inflexible. Furthermore, doctors sometimes conduct targeted training on dangerous items in daily life, which can lead to certain safety hazards for patients when they engage in real-life practical training.

[0004] Secondly, most current VR scenes are manually modeled, resulting in a lack of scene variability, low automation, and a lack of data support based on common-sense object relationship networks and knowledge graphs. Consequently, the constructed scenes are difficult to align with common sense. Furthermore, existing automated modeling processes cannot perform semantic interaction relationship reasoning, making it difficult to meet the needs of consciousness rehabilitation. Summary of the Invention

[0005] The content section of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the subsequent detailed description section. This content section is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions. Some embodiments of this disclosure propose a personalized consciousness rehabilitation interactive training method and apparatus based on intelligent virtual scene generation to address one or more of the technical problems mentioned in the background section above.

[0006] In a first aspect, some embodiments of this disclosure provide a personalized consciousness rehabilitation interactive training method based on intelligent generation of virtual scenes. The system includes: initializing meta-object information, object attribute information, and relationship networks to generate meta-object target information, object attribute target information, and target relationship networks; generating target object spatial information corresponding to the meta-object target information based on the object attribute target information and the target relationship networks; performing collision detection on the target object spatial information to generate object information required for the scene; storing the object information required for the scene in a preset scene graph; determining the object information required for the scene as the meta-object target information, repeating the above steps until the iterative convergence condition is met to obtain a target scene graph, wherein the target scene graph includes: a set of object information required for the scene and a target object relationship network required for the scene.

[0007] Secondly, some embodiments of this disclosure provide a personalized consciousness rehabilitation interactive training device based on intelligent generation of virtual scenes. The device includes: an initialization processing unit configured to initialize meta-object information, object attribute information, and a relationship network to generate meta-object target information, object attribute target information, and a target relationship network; a generation unit configured to generate target object spatial information corresponding to the meta-object target information based on the object attribute target information and the target relationship network; a collision detection unit configured to perform collision detection on the target object spatial information to generate object information required for the scene; a storage unit configured to store the object information required for the scene in a preset scene graph; and a determination unit configured to determine the object information required for the scene as the meta-object target information, repeat the above steps until the iterative convergence condition is met to obtain a target scene graph, wherein the target scene graph includes: a set of object information required for the scene and a relationship network of object relationships required for the scene.

[0008] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0010] The above-described embodiments of this disclosure have the following beneficial effects: A personalized consciousness rehabilitation interactive training method based on intelligent virtual scene generation, as described in some embodiments of this disclosure, provides a procedural virtual scene that conforms to common sense, thereby providing patients with effective consciousness rehabilitation training. Specifically, the reasons for certain safety hazards when patients conduct real-scene practical training are that the construction of real-scene facilities in rehabilitation centers is often costly, the real-scene training mode is subject to many time and space constraints, is inflexible, and doctors sometimes conduct targeted training on dangerous items in daily life, creating certain safety hazards for patients during real-scene practical training. The reason why the constructed virtual scene is difficult to conform to common sense is that most current VR scenes are manually modeled, resulting in a lack of scene variability, low automation, and a lack of object relationship networks and knowledge graphs based on common sense as data support, making it difficult for the constructed scene to conform to common sense. At the same time, existing automated modeling processes cannot perform semantic interaction relationship reasoning, making it difficult to meet the needs of consciousness rehabilitation. Based on this, some embodiments of this disclosure provide a personalized consciousness rehabilitation interactive training method based on intelligent virtual scene generation. First, meta-object information, object attribute information, and relationship networks are initialized to generate meta-object target information, object attribute target information, and target relationship networks. The meta-object information, object attribute information, and relationship networks are randomly determined to make the subsequently generated virtual scene more variable. Second, based on the aforementioned object attribute target information and target relationship networks, target object spatial information corresponding to the aforementioned meta-object target information is generated. Target object spatial information is generated using a relationship network representing common sense, making the generated target object spatial information more consistent with common sense. Then, collision detection is performed on the aforementioned target object spatial information to generate the object information required for the scene. It is ensured that there are no collisions between objects in the scene graph or between objects and boundaries. Next, the aforementioned object information required for the scene is stored in a preset scene graph. Finally, the aforementioned object information required for the scene is determined as the aforementioned meta-object target information, and the above steps are repeated until the iterative convergence condition is met to obtain a target scene graph, wherein the aforementioned target scene graph includes: a set of object information required for the scene and a relationship network of object relationships required for the scene. This method uses virtual scenes to prevent safety hazards for patients during rehabilitation training. Furthermore, it addresses the current issue that most virtual scenes are modeled manually, resulting in a lack of scene variability, low automation, and a lack of data support based on common-sense object relationship networks and knowledge graphs, making it difficult for the constructed scenes to align with common-sense realities. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0012] Figure 1 This is a schematic diagram of an application scenario of an individualized consciousness rehabilitation interactive training method based on intelligent virtual scene generation, which is one of the embodiments of this disclosure.

[0013] Figure 2 This is a flowchart of some embodiments of a personalized consciousness rehabilitation interactive training method based on intelligent generation of virtual scenes according to the present disclosure;

[0014] Figure 3 This is a schematic diagram of the structure of some embodiments of a personalized consciousness rehabilitation interactive training device based on intelligent generation of virtual scenes according to the present disclosure;

[0015] Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure;

[0016] Figure 5 This is a schematic diagram of the training process corresponding to a preset training operation scenario of another embodiment of a personalized consciousness rehabilitation interactive training method based on intelligent generation of virtual scene according to the present disclosure.

[0017] Figure 6 These are screenshots illustrating the operation of a system according to some embodiments of an individualized consciousness rehabilitation interactive training method based on intelligent virtual scene generation, as disclosed herein. Detailed Implementation

[0018] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0019] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0020] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0021] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0022] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0023] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0024] Figure 1 This is a schematic diagram illustrating an application scenario of an individualized consciousness rehabilitation interactive training method based on intelligent virtual scene generation, according to some embodiments of this disclosure.

[0025] exist Figure 1 In the application scenario, firstly, the computing device 101 can initialize the meta-object information 102, object attribute information 103, and relationship network 104 to generate meta-object target information 105, object attribute target information 106, and target relationship network 107; based on the above object attribute target information 106 and the above target relationship network 107, the target object spatial information 108 corresponding to the above meta-object target information 105 is generated; collision detection is performed on the above target object spatial information 108 to generate the object information 109 required for the scene; the above object information 109 required for the scene is stored in a preset scene graph; the above object information 109 required for the scene is determined as the above meta-object target information 105, and the above steps are repeated until the iterative convergence condition is met to obtain the target scene graph 110, wherein the above target scene graph 110 includes: the set of object information required for the scene and the object relationship network required for the scene.

[0026] It should be noted that the aforementioned computing device 101 can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed within the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0027] It should be understood that Figure 1 The number of computing devices shown is merely illustrative. Any number of computing devices can be used depending on implementation needs.

[0028] Continue to refer to Figure 2The flowchart 200 illustrates some embodiments of a personalized consciousness rehabilitation interactive training method based on intelligent virtual scene generation according to this disclosure. This personalized consciousness rehabilitation interactive training method based on intelligent virtual scene generation includes the following steps:

[0029] Step 201: Initialize the meta-object information, object attribute information, and relationship network to generate meta-object target information, object attribute target information, and target relationship network.

[0030] In some embodiments, the implementer of the personalized consciousness rehabilitation interactive training method based on virtual scene intelligent generation (e.g., Figure 1 The computing device 101 shown can initialize meta-object information, object attribute information, and relationship networks to generate meta-object target information, object attribute target information, and target relationship networks. The aforementioned meta-object information refers to the initial scene objects in the scene graph. The aforementioned meta-object information can be a "floor". The aforementioned object attribute information can be the object information required for the entire scene graph, and the aforementioned object attribute information may include, but is not limited to, at least one of the following: object identifier, object type, object quantity, object mutual exclusion relationship, and object space occupation information. The aforementioned relationship network is the constraint information between the target object and the meta-object.

[0031] The constraint information mentioned above may include, but is not limited to, at least one of the following: distance, position (relative rotation of two objects), orientation, local coordinate system of the target object, local coordinate system of the meta-object, centroid of the target object relative to the centroid of the meta-object, bounding box of the target object relative to the bounding box of the meta-object, object type, instance reference, scene boundaries (e.g., left boundary, right boundary, top boundary, bottom boundary), constraint ratio between the target object and the meta-object (the constraint ratio ranges from [0,1]), control the degree to which the target object and the meta-object are constrained, control the ratio of the distance between the rotation axis of the target object and the meta-object and the centroid of the two objects (the rotation axis is located on the line connecting the centroids of the two objects), and sampling curve.

[0032] For distance, the horizontal axis of the above sampling curve represents the distance between the two objects, and the vertical axis represents the relative velocity between the two objects. For position (relative rotation of the two objects), the horizontal axis of the above sampling curve represents the angle from the origin to the other object relative to the object's orientation within the specified reference coordinate system, i.e., the angle of the (0,1) vector (clockwise is defined as positive, the unit is deg, and the value range is [-180, 180]). The vertical axis of the above sampling curve represents the rotational speed of the object around the rotation axis in the reference coordinate system. The angle (clockwise is defined as positive, the unit is deg / s, and the value range is [-180, 180]) is the angle between the object and the orientation of the original object in the local coordinate system of the above sampling curve (clockwise is defined as positive, the unit is deg, and the value range is [-180, 180]). The vertical axis is the rotational speed of the orientation of the original object (clockwise is defined as positive, the unit is deg / s, and the value range is [-180, 180]).

[0033] Step 202: Based on the above object attribute target information and the above target relationship network, generate the target object spatial information corresponding to the above meta-object target information.

[0034] In some embodiments, the aforementioned execution entity (e.g. Figure 1 The computing device 101 shown can generate target object spatial information corresponding to the above-mentioned meta-object target information in various ways, based on the above-mentioned object attribute target information and the above-mentioned target relationship network.

[0035] In some optional implementations of certain embodiments, the execution entity generates target object spatial information corresponding to the meta-object target information based on the object attribute target information and the target relationship network, which can be achieved through the following steps:

[0036] The first step is to select the scene object identifier corresponding to the above object attribute target information based on the above meta-object target information.

[0037] The aforementioned executing entity can query a preset scene object database and, based on the object attribute target information, select the scene object identifier corresponding to the aforementioned meta-object target information. The preset scene object database stores the object attribute information and relationship network required for scene information generation. Simultaneously, the preset scene object database also stores patient information and usage preferences.

[0038] The second step is to determine the spatial information of the target objects corresponding to the object identifiers in the above-mentioned scene based on the target relationship network.

[0039] The aforementioned executing entity can determine the spatial information of the target object corresponding to the aforementioned scene object identifier by querying a preset scene object database and based on the aforementioned target relationship network. The aforementioned target object spatial information may include, but is not limited to, at least one of the following: target object position information and target object turning angle.

[0040] Step 203: Perform collision detection on the spatial information of the target object to generate the object information required for the scene.

[0041] In some embodiments, the aforementioned execution entity may utilize a 2-D boundary collision detection algorithm to perform collision detection on the spatial information of the target object in order to generate the object information required for the scene.

[0042] In some optional implementations of certain embodiments, the execution entity performs collision detection on the spatial information of the target object to generate the object information required for the scene, which can be achieved through the following steps:

[0043] The first step is to perform collision detection on the spatial information of the target object and the information of the meta-object to generate the first detection feedback information.

[0044] Specifically, the aforementioned executing entity can utilize the OBB (Oriented Bounding Box) algorithm to perform collision detection on the spatial information of the target object and the meta-object information to generate first detection feedback information. This first detection feedback information may include: first check passed and first check failed.

[0045] The second step involves performing secondary collision detection on the spatial information of the target object and the preset boundary information to generate second detection feedback information.

[0046] The aforementioned execution entity can also use the AABB (axis-aligned bounding box) algorithm to perform secondary collision detection on the spatial information of the target object and the preset boundary information to generate second detection feedback information. The aforementioned first detection feedback information may include: second check passed and second check failed.

[0047] The third step is to determine the target object spatial information as the object information required for the scene in response to the determination that both the first detection feedback information and the second detection feedback information have passed the detection.

[0048] Fourth step: In response to the determination that the first detection feedback information and the second detection feedback information have failed the detection, the spatial information of the target object is adjusted according to a preset step size to generate the adjusted spatial information of the target object.

[0049] The preset step size can be 0.01.

[0050] Fifth step: In response to determining that the adjusted target object spatial information meets the preset convergence condition, the adjusted target object spatial information is determined as the object information required for the above scene.

[0051] The aforementioned preset convergence condition can be that the adjusted target object spatial information is the preset object spatial information.

[0052] As an example, the above preset object spatial information could be ["1.2,2.5",45 degrees].

[0053] Step 204: Store the object information required for the above scene into the preset scene map.

[0054] In some embodiments, the execution entity may store the object information required for the scenario in a preset scene diagram. The preset scene diagram is the original scene diagram.

[0055] Step 205: Determine the object information required for the above scene as the above meta-object target information, repeat the above steps until the iterative convergence condition is met, and obtain the target scene map.

[0056] In some embodiments, the execution entity may determine the object information required by the scene as the meta-object target information, repeat the above steps until the iterative convergence condition is met, and obtain the target scene graph. The iterative convergence condition may be that the number of repetitions reaches a convergence threshold. The target scene graph includes: a set of object information required by the scene and a network of object relationships required by the scene.

[0057] As an example, the above convergence threshold could be 50 times.

[0058] Optionally, the aforementioned execution entity can first, based on a preset training operation scenario, prompt the target user to perform operations on the target scene required object information in the set of scene required object information included in the aforementioned target scene graph to generate the scene required object information after the operation. The training process diagram corresponding to the aforementioned preset training operation scenario can be as follows: Figure 5 As shown. Secondly, the aforementioned executing entity can control the target device to provide prompts based on the object information required in the scene after the above operations and the aforementioned relationship network.

[0059] As an example, screenshots of the above system during operation are as follows: Figure 6 As shown.

[0060] The above-described embodiments of this disclosure have the following beneficial effects: A personalized consciousness rehabilitation interactive training method based on intelligent virtual scene generation, as described in some embodiments of this disclosure, provides a procedural virtual scene that conforms to common sense, thereby providing patients with effective consciousness rehabilitation training. Specifically, the reasons for certain safety hazards when patients conduct real-scene practical training are that the construction of real-scene facilities in rehabilitation centers is often costly, the real-scene training mode is subject to many time and space constraints, is inflexible, and doctors sometimes conduct targeted training on dangerous items in daily life, creating certain safety hazards for patients during real-scene practical training. The reason why the constructed virtual scene is difficult to conform to common sense is that most current VR scenes are manually modeled, resulting in a lack of scene variability, low automation, and a lack of object relationship networks and knowledge graphs based on common sense as data support, making it difficult for the constructed scene to conform to common sense. At the same time, existing automated modeling processes cannot perform semantic interaction relationship reasoning, making it difficult to meet the needs of consciousness rehabilitation. Based on this, some embodiments of this disclosure provide a personalized consciousness rehabilitation interactive training method based on intelligent virtual scene generation. First, meta-object information, object attribute information, and relationship networks are initialized to generate meta-object target information, object attribute target information, and target relationship networks. The meta-object information, object attribute information, and relationship networks are randomly determined to make the subsequently generated virtual scene more variable. Second, based on the aforementioned object attribute target information and target relationship networks, target object spatial information corresponding to the aforementioned meta-object target information is generated. Target object spatial information is generated using a relationship network representing common sense, making the generated target object spatial information more consistent with common sense. Then, collision detection is performed on the aforementioned target object spatial information to generate the object information required for the scene. It is ensured that there are no collisions between objects in the scene graph or between objects and boundaries. Next, the aforementioned object information required for the scene is stored in a preset scene graph. Finally, the aforementioned object information required for the scene is determined as the aforementioned meta-object target information, and the above steps are repeated until the iterative convergence condition is met to obtain a target scene graph, wherein the aforementioned target scene graph includes: a set of object information required for the scene and a relationship network of object relationships required for the scene. This method uses virtual scenes to prevent safety hazards for patients during rehabilitation training. Furthermore, it addresses the current issue that most virtual scenes are modeled manually, resulting in a lack of scene variability, low automation, and a lack of data support based on common-sense object relationship networks and knowledge graphs, making it difficult for the constructed scenes to align with common-sense realities.

[0061] Further reference Figure 3 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a personalized consciousness rehabilitation interactive training device based on intelligent generation of virtual scenes. These device embodiments are similar to... Figure 2Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0062] like Figure 3 As shown, some embodiments of the personalized consciousness rehabilitation interactive training device 300 based on virtual scene intelligent generation include: an initialization processing unit 301, a generation unit 302, a collision detection unit 303, a storage unit 304, and a determination unit 305. The initialization processing unit 301 is configured to initialize meta-object information, object attribute information, and a relationship network to generate meta-object target information, object attribute target information, and a target relationship network. The generation unit 302 is configured to generate target object spatial information corresponding to the meta-object target information based on the object attribute target information and the target relationship network. The collision detection unit 303 is configured to perform collision detection on the target object spatial information to generate object information required for the scene. The storage unit 304 is configured to store the object information required for the scene in a preset scene graph. The determination unit 305 is configured to determine the object information required for the scene as the meta-object target information, repeat the above steps until the iterative convergence condition is met to obtain a target scene graph, wherein the target scene graph includes: a set of object information required for the scene and a set of object relationship networks required for the scene.

[0063] It is understandable that the units described in the device 300 are related to the reference. Figure 2 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method also apply to the device 300 and the units contained therein, and will not be repeated here.

[0064] The following is for reference. Figure 4 It illustrates electronic devices suitable for implementing some embodiments of this disclosure (e.g., Figure 1 A schematic diagram of the structure of the computing device 101)400. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0065] like Figure 4 As shown, electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. RAM 403 also stores various programs and data required for the operation of electronic device 400. Processing device 401, ROM 402, and RAM 403 are interconnected via bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0066] Typically, the following devices can be connected to I / O interface 405: input devices 404 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 4 Each box shown can represent a device or multiple devices as needed.

[0067] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from storage device 408, or installed from ROM 402. When the computer program is executed by processing device 401, it performs the functions defined above in the methods of some embodiments of this disclosure.

[0068] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0069] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0070] The aforementioned computer-readable medium may be included in the aforementioned device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: initialize meta-object information, object attribute information, and relationship networks to generate meta-object target information, object attribute target information, and target relationship networks; generate target object spatial information corresponding to the meta-object target information based on the object attribute target information and the target relationship network; perform collision detection on the target object spatial information to generate object information required for the scene; store the object information required for the scene in a preset scene graph; determine the object information required for the scene as the meta-object target information, and repeat the above steps until the iterative convergence condition is met to obtain a target scene graph, wherein the target scene graph includes: a set of object information required for the scene and a scene-required object relationship network.

[0071] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0073] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor may be described as including an initialization processing unit, a generation unit, a collision detection unit, a storage unit, and a determination unit. The names of these units do not necessarily limit the specific unit itself; for example, the initialization processing unit may also be described as "a unit that performs initialization processing on meta-object information, object attribute information, and relationship networks to generate meta-object target information, object attribute target information, and target relationship networks."

[0074] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0075] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A personalized consciousness rehabilitation interactive training method based on intelligent generation of virtual scenes, comprising: The meta-object information, object attribute information, and relationship network are initialized to generate meta-object target information, object attribute target information, and target relationship network. The meta-object information consists of initial scene objects in the scene graph, and the object attribute information consists of object information required for the entire scene graph. The object attribute information includes at least one of the following: object identifier, object type, object quantity, object mutual exclusion relationship, and object space occupation information. The relationship network consists of constraint information between the target object and the meta-object. Based on the object attribute target information and the target relationship network, target object spatial information corresponding to the meta-object target information is generated; The collision detection of the target object spatial information to generate the object information required for the scene includes: performing collision detection on the target object spatial information and the meta-object information to generate first detection feedback information; and performing secondary collision detection on the target object spatial information and preset boundary information to generate second detection feedback information. Store the object information required for the scene into a preset scene map; The object information required for the scene is determined as the meta-object target information. The above steps are repeated until the iterative convergence condition is met to obtain the target scene graph. The target scene graph includes: a set of object information required for the scene and a network of object relationships required for the scene. The iterative convergence condition is that the number of repetitions reaches a convergence threshold.

2. The method according to claim 1, wherein, The method further includes: Based on a preset training operation scenario, the target user is prompted to perform operations on the target scene required object information in the set of scene required object information included in the target scene graph to generate the scene required object information after the operation. Based on the object information required for the scene after the operation and the relationship network, the target device is controlled to provide prompts.

3. The method according to claim 2, wherein, The step of generating target object spatial information corresponding to the meta-object target information based on the object attribute target information and the target relationship network includes: Based on the object attribute target information, select the scene object identifier corresponding to the meta-object target information; Based on the target relationship network, the spatial information of the target object corresponding to the scene object identifier is determined.

4. The method according to claim 3, wherein, The step of performing collision detection on the spatial information of the target object to generate the object information required for the scene also includes: In response to determining that both the first detection feedback information and the second detection feedback information have passed the detection, the spatial information of the target object is determined as the object information required by the scene; In response to determining that the first detection feedback information and the second detection feedback information have failed the detection, the target object spatial information is adjusted according to a preset step size to generate adjusted target object spatial information.

5. The method according to claim 4, wherein, The step of performing collision detection on the spatial information of the target object to generate the object information required for the scene also includes: In response to determining that the adjusted target object spatial information satisfies a preset convergence condition, the adjusted target object spatial information is determined as the object information required by the scene.

6. A personalized consciousness rehabilitation interactive training device based on intelligent virtual scene generation, comprising: An initialization processing unit is configured to perform initialization processing on meta-object information, object attribute information, and relationship network to generate meta-object target information, object attribute target information, and target relationship network. The meta-object information consists of initial scene objects in the scene graph, and the object attribute information consists of object information required for the entire scene graph. The object attribute information includes at least one of the following: object identifier, object type, object quantity, object mutual exclusion relationship, and object space occupation information. The relationship network consists of constraint information between target objects and meta-objects. The generation unit is configured to generate target object spatial information corresponding to the meta-object target information based on the object attribute target information and the target relationship network. The collision detection unit is configured to perform collision detection on the spatial information of the target object to generate object information required for the scene, including: performing collision detection on the spatial information of the target object and the meta-object information to generate first detection feedback information; and performing secondary collision detection on the spatial information of the target object and preset boundary information to generate second detection feedback information. The storage unit is configured to store the object information required by the scene into a preset scene diagram; The determining unit is configured to determine the object information required by the scene as the meta-object target information, repeat the above steps until the iterative convergence condition is met to obtain the target scene graph, wherein the target scene graph includes: a set of object information required by the scene and a network of object relationships required by the scene, and the iterative convergence condition is that the number of repetitions reaches a convergence threshold.

7. An electronic device, comprising: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

Images