A VR-based Somatosensory Sleeve

Abstract

The somatosensory sleeve based on VR provided by the embodiments of the present invention can, based on the exploration of somatosensory simulation requirements from multiple angles of somatosensory simulation requirements, identify the target somatosensory simulation requirements of the first VR content somatosensory control instruction. Among them, the target somatosensory simulation requirements can serve as the somatosensory simulation requirements that can realize the function positioning of the somatosensory sleeve, and can support the function positioning of the somatosensory sleeve for the target somatosensory simulation requirements corresponding to the first VR content somatosensory control instruction. In this way, under the condition of the basic VR content somatosensory control instruction, through the function positioning process of the somatosensory sleeve for the target somatosensory simulation requirements, it is possible to identify as many VR content somatosensory control instructions for somatosensory simulation requirements from different somatosensory simulation requirement angles as possible, thereby realizing the all-round somatosensory simulation of the somatosensory sleeve and improving the fidelity of the somatosensory sleeve.

Description

Technical Field

[0001] The present invention relates to the field of VR technology, and particularly to a somatosensory sleeve based on VR. Background Art

[0002] At present, users' pursuit of VR content with increasingly high playable real effects is no longer limited to a single VR headset or VR controller. There is also a need for real feedback effects on the body. As an upgraded VR wearable device, the somatosensory sleeve can bring different somatosensory feedback from VR headsets or VR controllers. However, in actual applications, how to achieve a full-range somatosensory simulation of the somatosensory sleeve to improve its fidelity is a difficult point that needs to be overcome at present. Summary of the Invention

[0003] To improve the technical problems existing in the related art, the present invention provides a somatosensory sleeve based on VR.

[0004] In a first aspect, an embodiment of the present invention provides a somatosensory sleeve based on VR, including: a control instruction acquisition module for acquiring a first VR content somatosensory control instruction; a primary demand mining module for performing somatosensory simulation demand mining processing on the first VR content somatosensory control instruction from each somatosensory simulation demand angle among multiple somatosensory simulation demand angles to obtain multiple pending somatosensory simulation demands of the first VR content somatosensory control instruction; and an advanced demand mining module for mining a target somatosensory simulation demand of the first VR content somatosensory control instruction through the multiple pending somatosensory simulation demands of the first VR content somatosensory control instruction, where the target somatosensory simulation demand is used to realize the function positioning of the somatosensory sleeve.

[0005] Applied to the embodiment of the present invention, based on the somatosensory simulation demand mining from multiple somatosensory simulation demand angles, the target somatosensory simulation demand of the first VR content somatosensory control instruction can be mined. Among them, the target somatosensory simulation demand can be used as the somatosensory simulation demand that can realize the function positioning of the somatosensory sleeve, and can support the function positioning of the somatosensory sleeve for the target somatosensory simulation demand corresponding to the first VR content somatosensory control instruction. In this way, under the condition of the basic VR content somatosensory control instruction, through the function positioning processing of the target somatosensory simulation demand of the somatosensory sleeve, it is possible to mine as rich as possible the VR content somatosensory control instructions of different somatosensory simulation demands from different angles, so as to realize the full-range somatosensory simulation of the somatosensory sleeve and improve the fidelity of the somatosensory sleeve.

[0006] For some possible embodiments, the somatosensory sleeve further includes: a function positioning module for performing function positioning of the somatosensory sleeve on the target somatosensory simulation demand of the first VR content somatosensory control instruction to obtain a second VR content somatosensory control instruction after the function positioning of the somatosensory sleeve.

[0007] Applied to the embodiments of the present invention, the functional positioning of the somatosensory sleeve for the target somatosensory simulation requirement can be processed. The somatosensory simulation requirement of the second VR content somatosensory control instruction after the functional positioning of the somatosensory sleeve can be a target somatosensory simulation requirement different from that of the first VR content somatosensory control instruction, so as to facilitate the excavation of VR content somatosensory control instructions with richer somatosensory simulation requirements from different somatosensory simulation requirement perspectives.

[0008] For some possible embodiments, the obtaining of the first VR content somatosensory control instruction includes: obtaining the attention variable in the hidden network layer of the lightweight neural network; and obtaining the first VR content somatosensory control instruction by means of the lightweight neural network and the attention variable in the lightweight neural network.

[0009] Applied to the embodiments of the present invention, the first VR content somatosensory control instruction can be obtained based on the lightweight neural network and the attention variable, so as to subsequently determine or excavate the target somatosensory simulation requirement of the first VR content somatosensory control instruction through the connection between the attention variable and the first VR content somatosensory control instruction.

[0010] For some possible embodiments, the obtaining of the attention variable in the hidden network layer of the lightweight neural network includes: obtaining the third VR content somatosensory control instruction and parsing to obtain the instruction description of the third VR content somatosensory control instruction; and migrating and transforming the parsed instruction description onto the hidden network layer as the attention variable in the hidden network layer of the lightweight neural network.

[0011] Applied to the embodiments of the present invention, in the case where the somatosensory sleeve function positioning needs to be performed on the third VR content somatosensory control instruction, the attention variable can be obtained by migrating and transforming the instruction description of the third VR content somatosensory control instruction onto the hidden network layer. In this way, the acquisition of the VR content somatosensory control instruction and the excavation processing of the somatosensory simulation requirement can be performed, so as to realize the determination and excavation of the target somatosensory simulation requirement.

[0012] For some possible embodiments, the first somatosensory simulation requirement angle among the multiple somatosensory simulation requirement angles corresponds to a first somatosensory simulation requirement classification network; the first somatosensory simulation requirement angle is one of the multiple somatosensory simulation requirement angles; the performing of the somatosensory simulation requirement excavation processing on the first VR content somatosensory control instruction from each somatosensory simulation requirement angle among the multiple somatosensory simulation requirement angles to obtain multiple pending somatosensory simulation requirements of the first VR content somatosensory control instruction includes: by means of the first somatosensory simulation requirement classification network, performing the somatosensory simulation requirement excavation processing on the first VR content somatosensory control instruction from the first somatosensory simulation requirement angle to obtain the pending somatosensory simulation requirement of the first VR content somatosensory control instruction from the first somatosensory simulation requirement angle.

[0013] Applied to the embodiments of the present invention, for various somatosensory simulation demand angles, the pending somatosensory simulation demands of the VR content somatosensory control instructions can be mined respectively by means of the somatosensory simulation demand classification network corresponding to each somatosensory simulation demand angle.

[0014] For some possible embodiments, the first pending somatosensory simulation demand among the multiple pending somatosensory simulation demands corresponds to the attention variable in the hidden network layer of the lightweight neural network. The lightweight neural network and the attention variable are used to obtain the first VR content somatosensory control instruction, and the first pending somatosensory simulation demand is one of the multiple pending somatosensory simulation demands. Mining the target somatosensory simulation demand of the first VR content somatosensory control instruction through the multiple pending somatosensory simulation demands of the first VR content somatosensory control instruction includes: modifying the attention variable through the first pending somatosensory simulation demand to obtain a modified attention variable; obtaining a second VR content somatosensory control instruction by means of the modified attention variable and the lightweight neural network, and mining the second pending somatosensory simulation demand of the second VR content somatosensory control instruction; determining the updated evaluation of the first pending somatosensory simulation demand through the difference index between the first pending somatosensory simulation demand and the second pending somatosensory simulation demand; after obtaining the updated evaluations corresponding to the multiple pending somatosensory simulation demands respectively, extracting the target somatosensory simulation demand whose updated evaluation meets the specified requirements from the multiple pending somatosensory simulation demands through the updated evaluations corresponding to the multiple pending somatosensory simulation demands.

[0015] Applied to the embodiments of the present invention, the updated evaluation of the somatosensory simulation demand of the VR content somatosensory control instruction can be obtained based on the modification analysis of the attention variable before and after, and then the target somatosensory simulation demand that can be mined can be determined.

[0016] For some possible embodiments, modifying the attention variable through the first pending somatosensory simulation demand to obtain a modified attention variable includes: mining the somatosensory simulation demand label of the first pending somatosensory simulation demand on the hidden network layer; modifying the attention variable through the somatosensory simulation demand label to obtain a modified attention variable.

[0017] Applied to the embodiments of the present invention, the attention variable can be modified based on the somatosensory simulation demand label to analyze the somatosensory simulation demand label in the hidden network layer.

[0018] For some possible embodiments, determining an updated evaluation of the first to-be-determined somatosensory simulation requirement based on the difference index between the first to-be-determined somatosensory simulation requirement and the second to-be-determined somatosensory simulation requirement includes: obtaining a credibility coefficient of the first to-be-determined somatosensory simulation requirement and a credibility coefficient of the second to-be-determined somatosensory simulation requirement; determining the updated evaluation of the first to-be-determined somatosensory simulation requirement based on the quantitative comparison result of the credibility coefficient of the first to-be-determined somatosensory simulation requirement and the credibility coefficient of the second to-be-determined somatosensory simulation requirement.

[0019] Applied to the embodiments of the present invention, the updated evaluation of the somatosensory simulation requirement can be identified through the quantitative comparison result of the credibility coefficients of the front and back somatosensory simulation requirements.

[0020] For some possible embodiments, mining the somatosensory simulation requirement label of the first to-be-determined somatosensory simulation requirement on the hidden network layer includes: mining the somatosensory simulation requirement label of the first to-be-determined somatosensory simulation requirement on the hidden network layer by means of a pre-configured label parsing strategy, where the pre-configured label parsing strategy is configured by means of positive examples and negative examples of the first somatosensory simulation requirement angle corresponding to the first to-be-determined somatosensory simulation requirement.

[0021] Applied to the embodiments of the present invention, the pre-configured label parsing strategy can be used to mine the somatosensory simulation requirement label, and the somatosensory simulation requirement label of a specific somatosensory simulation requirement can be efficiently determined.

[0022] For some possible embodiments, mining the target somatosensory simulation requirement of the first VR content somatosensory control instruction based on multiple to-be-determined somatosensory simulation requirements of the first VR content somatosensory control instruction includes: extracting the target somatosensory simulation requirement from the multiple to-be-determined somatosensory simulation requirements based on the updated evaluations corresponding to the multiple to-be-determined somatosensory simulation requirements, where the updated evaluation reflects the difference between the VR content somatosensory control instruction obtained after modifying the attention variable in the lightweight neural network and the VR content somatosensory control instruction obtained before modifying the attention variable in the lightweight neural network for the corresponding to-be-determined somatosensory simulation requirement, and the lightweight neural network is used to obtain the VR content somatosensory control instruction through the attention variable.

[0023] Applied to the embodiments of the present invention, as many and different VR content somatosensory control instructions as possible can be mined, thereby ensuring the fidelity of the somatosensory sleeve. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present invention, and are used together with the specification to explain the principles of the present invention.

[0025] Figure 1It is a schematic diagram of modules of a VR-based somatosensory sleeve provided by an embodiment of the present invention.

[0026] Figure 2 It is a schematic diagram of the method flow corresponding to the functional modules of a VR-based somatosensory sleeve provided by an embodiment of the present invention. Detailed implementation manners

[0027] Here, exemplary embodiments will be described in detail, and examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence.

[0029] Please refer to Figure 1 , which shows a VR-based somatosensory sleeve, and the somatosensory sleeve may include the following functional modules.

[0030] A control instruction acquisition module 11, configured to acquire a first VR content somatosensory control instruction.

[0031] In some possible embodiments, acquiring the first VR content somatosensory control instruction includes: acquiring an attention variable in a hidden network layer of a lightweight neural network; and obtaining the first VR content somatosensory control instruction by means of the lightweight neural network and the attention variable in the lightweight neural network.

[0032] In some other possible embodiments, acquiring the attention variable in the hidden network layer of the lightweight neural network includes: acquiring a third VR content somatosensory control instruction and parsing to obtain an instruction description of the third VR content somatosensory control instruction; and migrating and transforming the parsed instruction description onto the hidden network layer as the attention variable in the hidden network layer of the lightweight neural network.

[0033] A primary requirement mining module 12, configured to perform somatosensory simulation requirement mining processing on the first VR content somatosensory control instruction from each of multiple somatosensory simulation requirement perspectives, to obtain multiple pending somatosensory simulation requirements of the first VR content somatosensory control instruction.

[0034] In some other possible embodiments, a first somatosensory simulation demand classification network corresponds to a first somatosensory simulation demand angle among the multiple somatosensory simulation demand angles; the first somatosensory simulation demand angle is one of the multiple somatosensory simulation demand angles. Based on this, performing somatosensory simulation demand mining processing on the first VR content somatosensory control instruction for each somatosensory simulation demand angle among the multiple somatosensory simulation demand angles to obtain multiple pending somatosensory simulation demands of the first VR content somatosensory control instruction, including: by means of the first somatosensory simulation demand classification network, performing somatosensory simulation demand mining processing on the first VR content somatosensory control instruction for the first somatosensory simulation demand angle to obtain the pending somatosensory simulation demand of the first VR content somatosensory control instruction for the first somatosensory simulation demand angle.

[0035] The advanced demand mining module 13 is configured to mine the target somatosensory simulation demand of the first VR content somatosensory control instruction through the multiple pending somatosensory simulation demands of the first VR content somatosensory control instruction, wherein the target somatosensory simulation demand is used to implement the function positioning of the somatosensory sleeve.

[0036] In some possible embodiments, the mining of the target somatosensory simulation demand of the first VR content somatosensory control instruction through the multiple pending somatosensory simulation demands of the first VR content somatosensory control instruction includes: extracting the target somatosensory simulation demand from the multiple pending somatosensory simulation demands through the updated evaluations respectively corresponding to the multiple pending somatosensory simulation demands, where the updated evaluation reflects the difference in the VR content somatosensory control instruction obtained after the attention variable of the lightweight neural network is modified compared to the VR content somatosensory control instruction obtained before the attention variable of the lightweight neural network is modified, and the lightweight neural network is used to obtain the VR content somatosensory control instruction through the attention variable.

[0037] In some other possible embodiments, the first undetermined somatosensory simulation requirement among the multiple undetermined somatosensory simulation requirements corresponds to an attention variable in the hidden network layer of the lightweight neural network. The lightweight neural network and the attention variable are used to obtain the first VR content somatosensory control instruction, and the first undetermined somatosensory simulation requirement is one of the multiple undetermined somatosensory simulation requirements. Based on this, extracting the target somatosensory simulation requirement from the multiple undetermined somatosensory simulation requirements through the update evaluations respectively corresponding to the multiple undetermined somatosensory simulation requirements includes: modifying the attention variable through the first undetermined somatosensory simulation requirement to obtain a modified attention variable; using the modified attention variable and the lightweight neural network to obtain a second VR content somatosensory control instruction and mining the second undetermined somatosensory simulation requirement of the second VR content somatosensory control instruction; determining the update evaluation of the first undetermined somatosensory simulation requirement through the difference index between the first undetermined somatosensory simulation requirement and the second undetermined somatosensory simulation requirement; after obtaining the update evaluations respectively corresponding to the multiple undetermined somatosensory simulation requirements, extracting the target somatosensory simulation requirement whose update evaluation meets the specified requirements from the multiple undetermined somatosensory simulation requirements through the update evaluations respectively corresponding to the multiple undetermined somatosensory simulation requirements.

[0038] Based on the above, modifying the attention variable through the first undetermined somatosensory simulation requirement to obtain a modified attention variable includes: mining the somatosensory simulation requirement label of the first undetermined somatosensory simulation requirement on the hidden network layer; modifying the attention variable through the somatosensory simulation requirement label to obtain a modified attention variable.

[0039] Based on the above, determining the update evaluation of the first undetermined somatosensory simulation requirement through the difference index between the first undetermined somatosensory simulation requirement and the second undetermined somatosensory simulation requirement includes: obtaining the credibility coefficient of the first undetermined somatosensory simulation requirement and the credibility coefficient of the second undetermined somatosensory simulation requirement; determining the update evaluation of the first undetermined somatosensory simulation requirement through the quantitative comparison result of the credibility coefficient of the first undetermined somatosensory simulation requirement and the credibility coefficient of the second undetermined somatosensory simulation requirement.

[0040] Based on the above, mining the somatosensory simulation requirement label of the first undetermined somatosensory simulation requirement on the hidden network layer includes: mining the somatosensory simulation requirement label of the first undetermined somatosensory simulation requirement on the hidden network layer by means of a pre-configured label parsing strategy, where the pre-configured label parsing strategy is configured by means of positive examples and negative examples of the first somatosensory simulation requirement angle corresponding to the first undetermined somatosensory simulation requirement.

[0041] Based on the above content, please continue to refer to Figure 1 The somatosensory sleeve further includes a function positioning module 14, which is used to perform somatosensory sleeve function positioning on the target somatosensory simulation requirements of the first VR content somatosensory control instruction, and obtain a second VR content somatosensory control instruction after somatosensory sleeve function positioning.

[0042] Combined with the above content, the embodiments of the present invention also disclose the related principles and structural introductions of the somatosensory sleeve, which may include the following exemplary content.

[0043] The somatosensory sleeve of the embodiment of the present invention can be a lightweight intelligent wearable device, which can realize the combination of VR virtual reality technology and the somatosensory sleeve through relevant Bluetooth communication technologies. It simulates the state feedback and positioning of the prop simulator in the VR content scene.

[0044] The somatosensory sleeve of the present invention can be composed of a control system, a pressure feedback device, a motion feedback device, a thermal feedback device, and a mobile power supply device.

[0045] For some examples, in VR content, a VR all-in-one machine or a PC sends different control instructions to the control system on the somatosensory sleeve through Bluetooth according to the content. The control system analyzes the received instructions, and the control system will control and start the corresponding devices on the somatosensory sleeve according to the instructions. At the same time, the control system will also feedback the operating state of the somatosensory sleeve device through Bluetooth to achieve interaction in the content.

[0046] For other examples, in VR content, the somatosensory sleeve is simulated as some props in the content. The somatosensory sleeve communicates with a VR all-in-one machine or a PC through Bluetooth. The VR all-in-one machine or the PC sends instructions to the somatosensory sleeve according to the content, and then the somatosensory sleeve control system receives the instructions and controls the pressure feedback device, the motion feedback device, and the thermal feedback device, etc. according to the instructions.

[0047] For example, the pressure feedback device controls the air pump motor on the somatosensory sleeve to work through the control system, realizes the inflation and deflation of the airbag wrapped around the arm, and simulates the sense of pressure applied to the user's arm in the content scene.

[0048] Further, the thermal feedback device controls the heating element on the somatosensory sleeve to generate heat through the control system, and at the same time, the sleeve has a temperature detection function, which can realize the actual temperature displayed by the prop in the content scene, as well as the thermal sensation and authenticity given to the user's arm.

[0049] In addition, the motion feedback device controls the motion motor on the somatosensory sleeve through the control system to simulate the vibration sensation feedback to the user's arm in the content scene. The mobile power supply device is responsible for powering the devices on the somatosensory sleeve to achieve portable wearing.

[0050] Based on the same inventive concept described above, please refer to Figure 2 , which shows a schematic diagram of the method flow corresponding to the functional modules of a VR-based somatosensory sleeve, including the following steps.

[0051] S21. Obtain a first VR content somatosensory control instruction.

[0052] S22. Perform somatosensory simulation requirement mining processing on each somatosensory simulation requirement angle among multiple somatosensory simulation requirement angles of the first VR content somatosensory control instruction to obtain multiple pending somatosensory simulation requirements of the first VR content somatosensory control instruction.

[0053] S23. Mine the target somatosensory simulation requirement of the first VR content somatosensory control instruction through the multiple pending somatosensory simulation requirements of the first VR content somatosensory control instruction, where the target somatosensory simulation requirement is used to implement the functional positioning of the somatosensory sleeve.

[0054] Applied to the embodiments of the present invention, based on the somatosensory simulation requirement mining on multiple somatosensory simulation requirement angles, the target somatosensory simulation requirement of the first VR content somatosensory control instruction can be mined. Among them, the target somatosensory simulation requirement can be used as the somatosensory simulation requirement that can achieve the functional positioning of the somatosensory sleeve, and it can support the functional positioning of the somatosensory sleeve for the target somatosensory simulation requirement corresponding to the first VR content somatosensory control instruction. In this way, under the condition of the basic VR content somatosensory control instruction, through the functional positioning process of the somatosensory sleeve for the target somatosensory simulation requirement, it is possible to mine as rich as possible the VR content somatosensory control instructions of different somatosensory simulation requirement angles, so as to realize the all-round somatosensory simulation of the somatosensory sleeve and improve the fidelity of the somatosensory sleeve.

[0055] Furthermore, a readable storage medium is also provided, on which a program is stored, and when the program is executed by a processor, the above method is implemented.

[0056] In several embodiments provided by the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0057] In addition, the functional modules in various embodiments of the present invention can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0058] If the described functions are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs, etc., which can store program codes. It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, method, article, or device including the element.

[0059] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A VR-based somatosensory sleeve, characterized in that, the somatosensory sleeve includes: a control instruction acquisition module for acquiring a first VR game somatosensory control instruction; a primary demand mining module for performing somatosensory simulation demand mining processing on the first VR game somatosensory control instruction from each somatosensory simulation demand angle among a plurality of somatosensory simulation demand angles to obtain a plurality of pending somatosensory simulation demands of the first VR game somatosensory control instruction; an advanced demand mining module for mining a target somatosensory simulation demand of the first VR game somatosensory control instruction through the plurality of pending somatosensory simulation demands of the first VR game somatosensory control instruction, wherein the target somatosensory simulation demand is used to realize the functional positioning of the somatosensory sleeve; The mining of the target somatosensory simulation demand of the first VR game somatosensory control instruction through the plurality of pending somatosensory simulation demands of the first VR game somatosensory control instruction includes: extracting the target somatosensory simulation demand from the plurality of pending somatosensory simulation demands through the update evaluations respectively corresponding to the plurality of pending somatosensory simulation demands, where the update evaluation reflects the difference in the VR game somatosensory control instruction obtained after modifying the attention variable in the lightweight neural network compared to the VR game somatosensory control instruction obtained before modifying the attention variable in the lightweight neural network, and the lightweight neural network is used to obtain the VR game somatosensory control instruction through the attention variable; a first somatosensory simulation demand classification network corresponds to a first somatosensory simulation demand angle among the plurality of somatosensory simulation demand angles; the first somatosensory simulation demand angle is one of the plurality of somatosensory simulation demand angles; The performing of somatosensory simulation demand mining processing on the first VR game somatosensory control instruction from each somatosensory simulation demand angle among the plurality of somatosensory simulation demand angles to obtain a plurality of pending somatosensory simulation demands of the first VR game somatosensory control instruction includes: by means of the first somatosensory simulation demand classification network, performing somatosensory simulation demand mining processing on the first VR game somatosensory control instruction from the first somatosensory simulation demand angle to obtain a pending somatosensory simulation demand of the first VR game somatosensory control instruction from the first somatosensory simulation demand angle; a first pending somatosensory simulation demand among the plurality of pending somatosensory simulation demands corresponds to an attention variable in a hidden network layer of a lightweight neural network, the lightweight neural network and the attention variable are used to obtain the first VR game somatosensory control instruction, and the first pending somatosensory simulation demand is one of the plurality of pending somatosensory simulation demands; the extracting of the target somatosensory simulation demand from the plurality of pending somatosensory simulation demands through the update evaluations respectively corresponding to the plurality of pending somatosensory simulation demands includes: modifying the attention variable through the first pending somatosensory simulation demand to obtain a modified attention variable; by means of the modified attention variable and the lightweight neural network, obtaining a second VR game somatosensory control instruction and mining a second pending somatosensory simulation demand of the second VR game somatosensory control instruction; Determine the updated evaluation of the first to-be-determined somatosensory simulation requirement based on the difference index between the first to-be-determined somatosensory simulation requirement and the second to-be-determined somatosensory simulation requirement; After obtaining the updated evaluations corresponding to the various to-be-determined somatosensory simulation requirements respectively, extract the target somatosensory simulation requirements whose updated evaluations meet the specified requirements from the various to-be-determined somatosensory simulation requirements based on the updated evaluations corresponding to the various to-be-determined somatosensory simulation requirements respectively.

2. The somatosensory sleeve according to claim 1, wherein, the somatosensory sleeve further includes: a function positioning module, configured to perform somatosensory sleeve function positioning on the target somatosensory simulation requirement of the first VR game somatosensory control instruction to obtain a second VR game somatosensory control instruction after somatosensory sleeve function positioning.

3. The somatosensory sleeve according to claim 1, wherein, the obtaining of the first VR game somatosensory control instruction includes: acquiring an attention variable in a hidden network layer of a lightweight neural network; obtaining a first VR game somatosensory control instruction by means of the lightweight neural network and the attention variable in the lightweight neural network.

4. The somatosensory sleeve according to claim 3, wherein, the acquiring of the attention variable in the hidden network layer of the lightweight neural network includes: acquiring a third VR game somatosensory control instruction and parsing to obtain an instruction description of the third VR game somatosensory control instruction; transforming and migrating the parsed instruction description onto the hidden network layer as the attention variable in the hidden network layer of the lightweight neural network.

5. The somatosensory sleeve according to claim 1, wherein, the modifying of the attention variable by means of the first to-be-determined somatosensory simulation requirement to obtain a modified attention variable includes: mining a somatosensory simulation requirement label of the first to-be-determined somatosensory simulation requirement on the hidden network layer; modifying the attention variable by means of the somatosensory simulation requirement label to obtain a modified attention variable.

6. The somatosensory sleeve according to claim 1, wherein, the determining of the updated evaluation of the first to-be-determined somatosensory simulation requirement based on the difference index between the first to-be-determined somatosensory simulation requirement and the second to-be-determined somatosensory simulation requirement includes: acquiring a credibility coefficient of the first to-be-determined somatosensory simulation requirement and a credibility coefficient of the second to-be-determined somatosensory simulation requirement; determining the updated evaluation of the first to-be-determined somatosensory simulation requirement based on the quantitative comparison result of the credibility coefficient of the first to-be-determined somatosensory simulation requirement and the credibility coefficient of the second to-be-determined somatosensory simulation requirement.

7. The somatosensory sleeve according to claim 5, wherein, the mining of the somatosensory simulation requirement label of the first to-be-determined somatosensory simulation requirement on the hidden network layer includes: mining the somatosensory simulation requirement label of the first to-be-determined somatosensory simulation requirement on the hidden network layer by means of a pre-configured label parsing strategy, wherein the pre-configured label parsing strategy is configured by means of positive examples and negative examples of the first somatosensory simulation requirement angle corresponding to the first to-be-determined somatosensory simulation requirement.

Images