Method and system for managing location information and computer readable storage medium
By using machine learning models on the server side to determine and update the provision of location information, the performance degradation caused by the exchange of user location data in virtual space is solved, achieving more efficient data transmission and system optimization.
Patent Information
- Application Number
- CN202411517088.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-05-22
- Filing Date
- 2024-10-29
- Publication Date
- 2025-11-25
AI Technical Summary
When a large number of users enter the same virtual space, the continuous exchange of user location data in existing technologies leads to performance degradation and latency issues for both servers and client devices.
The server uses a machine learning model to determine whether to provide location information to the client device, and updates the model based on feedback messages to avoid unnecessary data transmission.
It improves system performance and efficiency, reduces unnecessary data transmission, and optimizes user location management in virtual space.
Smart Images
Figure CN121013049A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to a mechanism for managing information, and more particularly to a method, system, and computer-readable storage medium for managing location information. Background Technology
[0002] When a large number of users enter the same virtual space (e.g., a virtual reality (VR) world), a large amount of user location data needs to be continuously exchanged. This amount of data directly affects the performance of the server and the user's client device, leading to slower operation and potentially causing latency issues. Summary of the Invention
[0003] In view of this, the present invention provides a method, system, and computer-readable storage medium for managing location information, which can be used to solve the above-mentioned technical problems.
[0004] This invention provides a method for managing location information, comprising: receiving first location information from a first client device by a server; determining, using a machine learning model, whether to provide the first location information to a second client device; in response to determining that the first location information should be provided to the second client device, sending the first location information to the second client device by the server; and in response to determining that a feedback message corresponding to the first location information has been received from the second client device, updating the machine learning model based on the feedback message.
[0005] This invention provides a system for managing location information, including a server. The server is configured to perform the following actions: receiving first location information from a first client device; using a machine learning model to determine whether to provide the first location information to a second client device; in response to determining that the first location information should be provided to the second client device, sending the first location information to the second client device; and in response to determining that a feedback message corresponding to the first location information has been received from the second client device, updating the machine learning model based on the feedback message.
[0006] This invention provides a computer-readable storage medium containing an executable computer program loaded by a server to perform the following steps: receiving first location information from a first client device; using a machine learning model to determine whether to provide the first location information to a second client device; in response to determining that the first location information should be provided to the second client device, sending the first location information to the second client device; and in response to determining that a feedback message corresponding to the first location information has been received from the second client device, updating the machine learning model based on the feedback message. Attached Figure Description
[0007] Figure 1 This is a schematic diagram of a system for managing location information based on an embodiment of the present invention.
[0008] Figure 2 This is a flowchart illustrating a method for managing location information according to an embodiment of the present invention.
[0009] Figure 3 This is a flowchart illustrating the operation performed by the second client device in response to the first location information, according to an embodiment of the present invention. Detailed Implementation
[0010] Please refer to Figure 1 , Figure 1 This is a schematic diagram of a system for managing location information based on an embodiment of the present invention.
[0011] In this embodiment, system 10 includes server 100 and client devices 11-1N (where N is a positive integer greater than 1). In various embodiments, server 100 and / or client devices 11-1N can be any smart device / computer device. In other embodiments, the mechanisms described in this invention can also be executed by multiple servers, but are not limited thereto.
[0012] In some embodiments, client devices 11-1N may be host devices (e.g., head-mounted displays (HMDs)) capable of providing visual content for a corresponding user to view reality services, but the invention is not limited thereto. In some embodiments, the reality service may be augmented reality (AR) service, VR service, mixed reality (MR) service, or extended reality (XR) service, and the corresponding visual content may be AR / VR / MR / XR content, but the invention is not limited thereto.
[0013] In this embodiment, server 100 includes storage circuitry 102 and processor 104. Storage circuitry 102 is one or a combination of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk, or any other similar device, and it records multiple modules and / or program code executable by processor 104.
[0014] Processor 104 may be coupled to storage circuitry 102, and processor 104 may be, for example, a general-purpose processor, a special-purpose processor, a conventional processor, a digital signal processor (DSP), one or more microprocessors associated with a DSP core, a controller, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) circuit, any other type of integrated circuit (IC), a state machine, and the like.
[0015] In some embodiments, each client device 11-1N may have the same structure as the server 100, but the present invention is not limited thereto.
[0016] In embodiments of the present invention, client devices 11-1N can exchange their respective location information through server 100. For example, when client device 11 determines its location information P1 (e.g., coordinates and / or orientation) in at least one environment (e.g., client devices 11-1N may be located in the same environment or distributed in different environments) through a tracking mechanism (e.g., inside-out tracking and / or outside-in tracking), client device 11 can send the location information P1 to server 100, and server 100 can send the location information P1 to, for example, client device 12 and / or other client devices, but the present invention is not limited thereto.
[0017] In one embodiment, after the client device 12 receives the location information P1, the client device 12 can perform related subsequent operations accordingly.
[0018] For better understanding, client devices 11 to 1N will be assumed to be immersed in the same virtual world (e.g., the same VR world) within the same environment (e.g., a venue, room, or other similar space). In this case, visual content (e.g., VR content) rendered by one client device can be associated with another client device.
[0019] For example, if client device 11 is located in front of client device 12 in the environment (e.g., client device 11 is within the field of view (FOV) of client device 12), the visual content rendered by client device 12 may need to present / display a virtual avatar corresponding to client device 11.
[0020] For example, if client device 12 is located behind client device 11 in the environment (e.g., client device 12 is not in the field of view of client device 11), then the visual content rendered by client device 11 may not need to present / display the virtual avatar corresponding to client device 12.
[0021] Additionally, if there is an obstacle between client device 11 and client device 12, causing client device 11 to be outside the field of view of client device 12 (e.g., client device 11 is obscured from the view of client device 12), then the visual content rendered by client device 12 may not need to present / display the virtual avatar corresponding to client device 11, but the present invention is not limited thereto.
[0022] However, in the conventional approach, even though client device 11 (and / or its associated virtual avatar) may not need to be presented in the visual content of client device 12 in some scenarios (i.e., client device 12 does not need location information P1), server 100 still provides location information P1 to client device 12, which results in unnecessary data transmission.
[0023] Similarly, in cases where other client devices do not require location information P1, more unnecessary data transmission will occur.
[0024] Therefore, embodiments of the present invention provide solutions to the above problems, and the relevant descriptions will be provided below.
[0025] In this embodiment of the invention, the processor 104 can access the modules and / or program code stored in the storage circuit 102 to implement the method for managing location information provided by the present invention, which will be further discussed below.
[0026] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a method for managing location information according to an embodiment of the present invention. The method of this embodiment can be derived from… Figure 1 The server 100 in the middle is executed, and the following will be supplemented with Figure 1 Component description Figure 2 Details of each step.
[0027] In step S210, processor 104 receives first location information from the first client device. In step S220, processor 104 uses a machine learning model to determine whether to provide the first location information to the second client device.
[0028] For better understanding, the first client device and the second client device considered below will be assumed to be (but not limited to) client device 11 and client device 12, respectively. Under this assumption, the first location information may be location information P1, but the present invention is not limited thereto.
[0029] In other words, the processor 104 can use a machine learning model to determine whether to provide the location information P1 to the client device 12, instead of directly providing the location information P1 to the client device 12.
[0030] In embodiments of the present invention, the machine learning model may be, for example, a reinforcement learning model, which may be updated / trained based on feedback messages from one or more of the client devices 11-1N.
[0031] In one embodiment, if the processor 104 determines that a feedback message from a client device (e.g., client device 12) is a positive feedback message, this may indicate that the decision made by the machine learning model is acceptable to the client device. In this case, the processor 104 may update the machine learning model for the purpose of behavioral reinforcement. That is, since the decision made by the machine learning model is acceptable to the client device, the processor 104 may update the machine learning model to reinforce this behavior, but the invention is not limited thereto.
[0032] In some embodiments, positive feedback messages may also be understood as reward messages, but the present invention is not limited thereto.
[0033] On the other hand, if the processor 104 determines that the feedback message from a client device is a negative feedback message, this indicates that the decision made by the machine learning model may be unacceptable for that client device. In this case, the processor 104 may update the machine learning model, but the invention is not limited thereto.
[0034] In some embodiments, negative feedback messages may also be understood as punishment messages, but the present invention is not limited thereto.
[0035] In one embodiment, in step S220, the processor 104 may obtain environmental information related to the current environment of client devices 11 and 12. In this embodiment, the environmental information may include at least the device posture (e.g., coordinates and / or orientation) of client devices 11 and 12 (and / or other client devices), the virtual avatars corresponding to the first client device and the second client device, and / or the configuration of environmental objects (e.g., the appearance / size / position of virtual objects in the virtual world and / or physical objects in the environment), but the present invention is not limited thereto.
[0036] In some embodiments, environmental information may be understood as scene information associated with the (virtual) scene in which client devices 11 and 12 (and / or other client devices) are immersed, and this scene information may include information about objects in the scene (e.g., appearance / size / location).
[0037] After obtaining environmental information, the processor 104 can input the environmental information into a machine learning model, wherein the machine learning model can provide a judgment result indicating whether to provide location information P1 to the client device 12 in response to the environmental information.
[0038] In other words, the machine learning model can determine whether to provide location information P1 to the client device 12 based on environmental information.
[0039] In one embodiment, in response to a determination to provide first location information (e.g., location information P1) to a second client device, processor 104 may execute step S230 to send the first location information to the second client device.
[0040] For example, if the machine learning model determines that location information P1 should be provided to the client device 12, the processor 104 may transmit the location information P1 to the client device 12 accordingly.
[0041] On the other hand, in response to determining that the first location information (e.g., location information P1) will not be provided to the second client device, the processor 104 may execute step S250 to not send the first location information to the second client device.
[0042] For example, if the machine learning model determines that location information P1 should not be provided to the client device 12, the processor 104 may accordingly not send location information P1 to the client device 12, but the present invention is not limited thereto.
[0043] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the operation performed by the second client device in response to the first location information, according to an embodiment of the present invention.
[0044] In step S310, the second client device (e.g., client device 12) receives first location information (e.g., location information P1) from the server 100.
[0045] In step S320, the second client device determines whether the second client device needs the first location information and configures the feedback message M1 accordingly.
[0046] In one embodiment, the second client device can determine whether it needs the first location information. In response to determining that the second client device needs the first location information, the second client device can configure feedback message M1 as a positive feedback message. Conversely, in response to determining that the second client device does not need the first location information, the second client device can configure feedback message M1 as a negative feedback message.
[0047] In step S330, the second client device sends a feedback message M1 to the server 100.
[0048] In one embodiment, the second client device can perform the determination in step S320 by determining, based on the first location information, whether it is necessary to render a virtual avatar corresponding to the first client device (e.g., client device 11) in the visual content of the second client device.
[0049] For example, the second client device may execute a culling algorithm based on the first location information. In various embodiments, the culling algorithm may include one or more of occlusion culling, frustum culling, and other culling algorithms to determine whether the virtual avatar corresponding to the first client device is visible to the second client device, but the invention is not limited thereto.
[0050] In one embodiment, in response to the determination result of the culling algorithm indicating that the virtual avatar corresponding to the first client device is not obscured by the second client device, it means that when the user of the second client device is experiencing the virtual world, the virtual character corresponding to the first client device is visible to that user. In this case, the second client device can determine that the virtual avatar corresponding to the first client device needs to be rendered in the visual content of the second client device.
[0051] On the other hand, in response to the judgment result of the elimination algorithm indicating that the virtual avatar corresponding to the first client device has been occluded for the second client device, this means that when the user of the second client device is experiencing the virtual world, the virtual character corresponding to the first client device is not visible to that user. In this case, the second client device can determine that it does not need to render the virtual avatar corresponding to the first client device in the visual content of the second client device, but the present invention is not limited thereto.
[0052] For details on the elimination algorithm, please refer to relevant literature, which will not be elaborated here.
[0053] In one embodiment, in response to determining that the virtual avatar corresponding to the first client device needs to be rendered in the visual content of the second client device, the second client device may determine that the second client device needs the first location information, and the second client device may send a feedback message M1 as a positive feedback message. On the other hand, in response to determining that the virtual avatar corresponding to the first client device does not need to be rendered in the visual content of the second client device, the second client device may determine that the second client device does not need the first location information, and the second client device may send a feedback message M1 as a negative feedback message, but is not limited to this.
[0054] In one embodiment, after the second client device completes step S330, the processor 104 may execute accordingly. Figure 2Step S240 in the process.
[0055] Please refer to this again. Figure 2 In step S240, in response to determining that a feedback message M1 corresponding to the first location information (e.g., location information P1) has been received from the second client device (e.g., client device 12), the processor 104 updates the machine learning model based on the feedback message M1.
[0056] In one embodiment, in response to determining that feedback message M1 is a positive feedback message, processor 104 may update the machine learning model to reinforce this behavior.
[0057] More specifically, since the positive feedback message can be understood as the second client device indeed needing the first location information (i.e., the machine learning model made the correct judgment), the processor 104 can update the machine learning model to enhance this behavior, but the invention is not limited thereto.
[0058] On the other hand, in response to determining that the feedback message M1 is a negative feedback message, the processor 104 can train a machine learning model based on the negative feedback message and the aforementioned environmental information.
[0059] More specifically, since the negative feedback message can be interpreted as the second client device not needing the first location information (i.e., the machine learning model made an incorrect judgment), the processor 104 can use the aforementioned environmental information as training data for the machine learning model. In this case, the machine learning model can be trained to provide the location information P1 of the client device 11 to the client device 12 when the environmental information indicates certain specific information about the environment.
[0060] Based on this, the updated machine learning model can more appropriately / intelligently determine whether to provide the location information of one of the client devices 11-1N to the other client device 11-1N, but the present invention is not limited thereto.
[0061] The present invention further provides a computer-readable storage medium for performing the above-described method for managing location information. The computer-readable storage medium comprises a plurality of program instructions (e.g., setup program instructions and deployment program instructions) contained herein. These program instructions can be loaded into and executed by server 100 to perform the above-described method for managing location information and the functions of server 100.
[0062] In summary, the embodiments of the present invention provide a technical solution that allows a server to use a machine learning model to determine whether to provide the location information of one client device to another. This avoids unnecessary data transmission, thereby improving the performance and efficiency of the entire system.
[0063] Although the present invention has been disclosed above with reference to embodiments, it is not intended to limit the present invention. Those skilled in the art can make some modifications and refinements without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope defined in the appended claims.
Claims
1. A method for managing location information, characterized in that, include: The server receives the first location information from the first client device; The server uses a machine learning model to determine whether to provide the first location information to the second client device; In response to the determination to provide the first location information to the second client device, the server sends the first location information to the second client device; as well as In response to determining that a feedback message corresponding to the first location information has been received from the second client device, the server updates the machine learning model based on the feedback message.
2. The method according to claim 1, comprising: The server obtains environmental information associated with at least one environment currently in which the first client device and the second client device, or the virtual avatars corresponding to the first client device and the second client device, are located; The server inputs the environmental information into the machine learning model, wherein the machine learning model responds to the environmental information by providing a judgment result indicating whether to provide the first location information to the second client device.
3. The method according to claim 2, wherein the environmental information includes the device posture of the first client device and the second client device or the virtual avatar corresponding to the first client device and the second client device, and the configuration of environmental objects within the at least one environment.
4. The method according to claim 1, wherein the machine learning model includes a reinforcement learning model, and updating the machine learning model based on the feedback message includes: In response to determining that the feedback message includes a negative feedback message, the server trains the machine learning model based on the negative feedback message and environmental information associated with at least one environment in which the virtual avatars corresponding to the first client device and the second client device or the first client device and the second client device are currently located.
5. The method according to claim 4, wherein updating the machine learning model based on the feedback message further comprises: In response to the determination that the feedback message includes a positive feedback message, the server updates the machine learning model for the purpose of behavior reinforcement.
6. The method according to claim 1, further comprising: The second client device receives the first location information from the server; The second client device determines whether it needs the first location information and configures the feedback message accordingly. The second client device sends the feedback message to the server.
7. The method according to claim 6, further comprising: In response to the determination that the second client device needs the first location information, the second client device configures the feedback message as a positive feedback message; In response to the determination that the second client device does not need the first location information, the second client device configures the feedback message as a negative feedback message.
8. The method of claim 6, comprising: The second client device determines, based on the first location information, whether it is necessary to render the virtual avatar corresponding to the first client device in the visual content of the second client device; In response to the determination that the virtual avatar corresponding to the first client device needs to be rendered in the visual content of the second client device, the second client device determines that the second client device needs the first location information; In response to the determination that it is not necessary to render the virtual avatar corresponding to the first client device in the visual content of the second client device, the second client device determines that it does not need the first location information.
9. The method according to claim 8, wherein determining whether to render the virtual avatar corresponding to the first client device in the visual content of the second client device based on the first location information comprises: The second client device executes the elimination algorithm based on the first location information; In response to the determination result of the culling algorithm indicating that the virtual avatar corresponding to the first client device is not obscured by the second client device, the second client device determines that the virtual avatar corresponding to the first client device needs to be rendered in the visual content of the second client device; In response to the determination result of the culling algorithm indicating that the virtual avatar corresponding to the first client device has been occluded for the second client device, the second client device determines that the virtual avatar corresponding to the first client device does not need to be rendered in the visual content of the second client device.
10. The method according to claim 1, further comprising: In response to the determination that the first location information should not be provided to the second client device, the server does not send the first location information to the second client device.
11. A system for managing location information, characterized in that, include: The server is configured to perform: Receive first location information from the first client device; Use a machine learning model to determine whether to provide the first location information to the second client device; In response to the determination to provide the first location information to the second client device, the first location information is sent to the second client device; as well as In response to determining that a feedback message corresponding to the first location information has been received from the second client device, the machine learning model is updated based on the feedback message.
12. The system of claim 11, wherein the server performs: Obtain environmental information associated with at least one environment where the virtual avatars corresponding to the first client device and the second client device, or the first client device and the second client device, are currently located; The environmental information is input into the machine learning model, wherein the machine learning model responds to the environmental information by providing a judgment result indicating whether to provide the first location information to the second client device.
13. The system of claim 12, wherein the environmental information includes the device posture of the first client device and the second client device or the virtual avatar corresponding to the first client device and the second client device, and the configuration of environmental objects within the at least one environment.
14. The system of claim 11, wherein the machine learning model comprises a reinforcement learning model, and the server performs: In response to determining that the feedback message includes a negative feedback message, the machine learning model is trained based on the negative feedback message and environmental information associated with at least one environment in which the virtual avatars corresponding to the first client device and the second client device or the first client device and the second client device are currently located.
15. The system according to claim 14, wherein, The server further performs: In response to the determination that the feedback message includes a positive feedback message, the machine learning model is updated for the purpose of behavioral reinforcement.
16. The system of claim 11, further comprising: The second client device is configured to execute: Receive the first location information from the server; Determine whether the second client device needs the first location information, and configure the feedback message accordingly; Send the feedback message to the server.
17. The system of claim 16, wherein the second client device further performs: In response to the determination that the second client device needs the first location information, the second client device configures the feedback message as a positive feedback message; In response to the determination that the second client device does not need the first location information, the second client device configures the feedback message as a negative feedback message.
18. The system of claim 16, wherein the second client device performs: Based on the first location information, determine whether it is necessary to render the virtual avatar corresponding to the first client device in the visual content of the second client device; In response to the determination that the virtual avatar corresponding to the first client device needs to be rendered in the visual content of the second client device, it is determined that the second client device needs the first location information; In response to the determination that it is not necessary to render the virtual avatar corresponding to the first client device in the visual content of the second client device, it is determined that the second client device does not need the first location information.
19. The system of claim 16, wherein the second client device performs: Execute the elimination algorithm based on the first location information; In response to the determination result of the culling algorithm indicating that the virtual avatar corresponding to the first client device is not obscured by the second client device, it is determined that the virtual avatar corresponding to the first client device needs to be rendered in the visual content of the second client device; In response to the determination result of the culling algorithm indicating that the virtual avatar corresponding to the first client device has been occluded for the second client device, it is determined that the virtual avatar corresponding to the first client device does not need to be rendered in the visual content of the second client device.
20. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains an executable computer program, which is loaded by the server to perform the following steps: Receive first location information from the first client device; Use a machine learning model to determine whether to provide the first location information to the second client device; In response to the determination to provide the first location information to the second client device, the first location information is sent to the second client device; as well as In response to determining that a feedback message corresponding to the first location information has been received from the second client device, the machine learning model is updated based on the feedback message.