Natural interaction virtual scene generation system and method

Abstract

The invention discloses a natural interaction virtual scene generation system and method, and relates to the technical field of data processing, and the system comprises an initial preference setting module, a virtual scene configuration module, a sensing data acquisition module, an interaction instruction processing module and an interaction instruction feedback module. According to the method, the initial preference interaction data of the user and the personal body shape data of the user are collected in advance, the personalized behavior preset parameters of the interaction instructions of the user are generated through analysis and processing, and the personalized virtual scene is configured, so that personal habits and body characteristics of the user can be better matched, interaction in the virtual environment is more natural and comfortable, and the user experience is improved. And meanwhile, the identification accuracy of the interaction instruction of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a natural interactive virtual scene generation system and method. Background Art

[0002] Traditional interaction methods (such as keyboard and mouse) may not be intuitive enough, while natural interaction systems can interact through gestures and other methods, which are more in line with human natural behavior habits. By generating realistic virtual scenes, users can get a more immersive experience.

[0003] The prior art, such as the invention patent with announcement number: CN106445176B, is a human-computer interaction system and interaction method based on virtual reality technology. The human-computer interaction system includes: a virtual reality head display device, a controller and a somatosensory recognition device. When the user needs to interact with the virtual world, the somatosensory recognition device will capture the user's somatosensory data information and output the somatosensory data information to the controller. The controller converts the acquired somatosensory data set information into a user motion data processing signal, outputs it to the virtual reality head display device, controls the motion model in the virtual scene displayed by the virtual reality head display device to move synchronously, and completes the human-computer interaction.

[0004] The prior art, such as the invention patent with announcement number: CN106502426B, is a virtual character control device and a virtual reality interactive system, the device includes a signal input device and a direction controller for setting on the abdomen of the character; the direction controller includes a first central contact and a direction contact, the first central contact is used to contact the direction contact according to the change of the abdomen caused by the movement of the character, and generate a direction displacement signal for controlling the virtual character to move synchronously with the character; the signal input device is connected to the direction controller, and is used to send the direction displacement signal to the carrier terminal of the virtual character. By collecting the behavior actions of real players and the body changes corresponding to special actions, the corresponding signals are formed through the virtual character control device, thereby controlling the virtual character, so that the virtual character can achieve the action state synchronized with the real player.

[0005] Based on the above scheme, it can be seen that the existing technology often focuses on identifying the user's interactive behavior by analyzing the signals or somatosensory data generated when the user interacts. However, in actual applications, different users may generate different data when interacting, and personalized interactive feedback is required for different users. At the same time, users may perform non-interactive command actions in virtual scenes, and these non-interactive command actions are easily misidentified in actual applications, thereby reducing the user's experience. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a natural interactive virtual scene generation system and method and system. To achieve the above objectives, the present invention is implemented through the following technical solutions: A natural interactive virtual scene generation system and method, comprising:

[0007] An initial preference setting module is used to collect the user's initial preference interaction data and the user's personal body shape data in the virtual scene through the natural interaction platform, analyze and process to generate the user's initial interaction preference feature value and personalized body shape feature value, and analyze and process the initial behavior parameters of each interaction instruction stored in the natural interaction platform to generate the personalized behavior preset parameters of each interaction instruction of the user;

[0008] A virtual scene configuration module, based on the user's personalized body shape feature value, processes the user's personalized virtual scene configuration parameters and generates the user's personalized virtual scene;

[0009] The sensor data acquisition module is used to collect the real-time motion data of the user in the personalized virtual scene through the motion capture sensor, filter out the effective real-time motion data of the user in the personalized virtual scene, and send the effective real-time motion data to the interactive instruction processing module;

[0010] The interactive instruction processing module is used to compare the effective real-time action data of the user in the personalized virtual scene with the personalized behavior preset parameters of each interactive instruction of the user to generate matching values ​​between the effective real-time data and each interactive instruction, and screen the interactive instruction corresponding to the highest matching value as the effective interactive instruction of the user;

[0011] The interaction instruction feedback module is used to receive the user's effective interaction instruction, index the interaction feedback data corresponding to the effective interaction instruction preset by the natural interaction platform, and provide interaction feedback to the user.

[0012] As a preferred technical solution, the natural interaction platform is used to collect the user's initial preference interaction data and the user's personal body shape data in the virtual scene. The specific process is as follows:

[0013] The user logs in to the natural interaction platform through a personal account. If the user is using the natural interaction platform for the first time, the user's personal body data, including the user's height, shoulder width and arm length, is collected. The user's joint feature nodes are anchored based on the user's personal body data, and the user is guided to perform trial matching. The user is guided to try out various interaction commands. After the trial matching is completed, the user's initial preference interaction data is counted, including user interaction sensitivity, average duration of each interaction command, interaction position deviation value of each interaction command and success rate of each interaction command.

[0014] If the user has used the natural interaction platform multiple times, the user's personal body data and historical preference interaction data are extracted from the natural interaction platform. The historical preference interaction data includes historical action sensitivity, average duration of historical interaction instructions, interaction position deviation value of historical interaction instructions, and success rate of historical interaction instructions, and are recorded as the user's initial preference interaction data this time.

[0015] As a preferred technical solution, the initial behavior parameters of each interaction instruction stored in the natural interaction platform are analyzed and processed with the user's initial interaction preference feature value to generate personalized behavior preset parameters for each interaction instruction of the user, specifically including:

[0016] Based on the user's initial preference interaction data, analyzing and processing to generate the user's initial interaction preference feature value, wherein the user's initial interaction preference feature value is used to comprehensively characterize the user's interaction preference;

[0017] Based on the user's personal body shape data, analyzing and processing to generate the user's personalized body shape feature value, the user's personalized body shape feature value is used to characterize the user's body shape feature;

[0018] Extracting an initial behavior parameter standard value set and an initial behavior parameter allowable error value set of each interaction instruction from the natural interaction platform, wherein the initial behavior parameter standard value set includes: a displacement standard value of each joint feature node of each interaction instruction action, an action duration standard value of each joint feature node of each interaction instruction action, an action speed standard value of each joint feature node of each interaction instruction action, and a direction vector standard value of each joint feature node of each interaction instruction action;

[0019] The set of initial behavior parameter allowable error values ​​includes the allowable error value of displacement of each joint feature node of each interactive instruction action, the allowable error value of action duration of each joint feature node of each interactive instruction action, the allowable error value of action speed of each joint feature node of each interactive instruction action, and the allowable error value of direction vector angle of each joint feature node of each interactive instruction action;

[0020] Based on the initial interaction preference feature value of the user, the initial behavior parameter standard value set of each interaction instruction is adjusted, and the processed initial behavior parameter standard value set of each interaction instruction is recorded as the personalized preset behavior parameter of each interaction instruction action of the user;

[0021] The personalized preset behavior parameters of each interactive instruction action of the user include personalized preset values ​​of displacement of each joint feature node of each interactive instruction action, personalized preset values ​​of action duration of each joint feature node of each interactive instruction action, personalized preset values ​​of action speed of each joint feature node of each interactive instruction action, and personalized preset values ​​of direction vector of each joint feature node of each interactive instruction action.

[0022] As a preferred technical solution, the processing based on the personalized body shape feature value of the user to obtain the personalized virtual scene configuration parameters of the user and generate the personalized virtual scene of the user specifically includes:

[0023] Based on the personalized body feature values ​​of the user, mapping and matching are performed with personalized virtual scene configuration parameters corresponding to each personalized body feature value interval pre-stored in the natural interaction platform to obtain the personalized virtual scene configuration parameters of the user, wherein the personalized virtual scene configuration parameters include personalized graphics rendering parameters and physical simulation parameters. The virtual scene is configured based on the personalized virtual scene configuration parameters of the user, and the virtual scene is recorded as a personalized virtual scene.

[0024] As a preferred technical solution, the method of collecting the real-time motion data of the user in the personalized virtual scene by the motion capture sensor, screening out the effective real-time motion data of the user in the personalized virtual scene, and sending the effective real-time motion data to the interactive instruction processing module specifically includes:

[0025] Based on the spatial position coordinates of the user's joint feature nodes, the real-time action data of the user's joint feature nodes in the personalized virtual scene are obtained;

[0026] When the coordinates of each joint feature node of the user enter the command recognition range preset by the personalized virtual scene, the real-time action data of each joint feature node is counted and sent to the interactive command processing module as effective real-time action data.

[0027] As a preferred technical solution, the effective real-time action data of the user in the personalized virtual scene is compared with the personalized behavior preset parameters of each interaction instruction of the user to generate a matching value of the effective real-time data and each interaction instruction, specifically including:

[0028] Based on the effective real-time action data of each joint feature node of the user in the personalized virtual scene, including the action time of each joint feature node, the action speed of each joint feature node, the action direction vector of each joint feature node and the action displacement of each joint feature node, the data are compared with the personalized behavior preset parameters of each interaction instruction of the user to generate the matching value of the effective real-time data and each interaction instruction.

[0029] As a preferred technical solution, the screening obtains the interaction instruction corresponding to the highest matching value as the user's valid interaction instruction, specifically including:

[0030] The matching values ​​of the effective real-time data and each interaction instruction are sorted in descending order, and the interaction instruction corresponding to the interaction instruction matching value that ranks first is selected as the effective interaction instruction of the user.

[0031] As a preferred technical solution, the specific processing process of generating the matching value of the effective real-time data and each interactive instruction is as follows:

[0032] ;

[0033] in, To effectively conduct real-time behavioral data and The matching value of the interactive instruction, Provide users with personalized virtual scenes The displacement of the joint feature node, Provide users with personalized virtual scenes The action duration of each joint feature node, Provide users with personalized virtual scenes The action speed of the joint feature node, Provide users with personalized virtual scenes The direction vector of the joint feature node, For the The interactive command The displacement of each joint feature node is personalized preset value. For the The interactive command Personalized preset value of action duration of each joint feature node, For the The interactive command The action speed of each joint feature node is personalized and preset. For the The interactive command The direction vector of each joint feature node is personalized preset value. For the The interactive command The displacement tolerance of each joint feature node is: For the The interactive command The allowable error value of the action duration of the joint feature node, For the The interactive command The permissible error value of the motion speed of the joint feature node is: For the The interactive command The allowable error value of the direction vector angle of the joint feature node, is the number of the interactive instruction, , is the total number of interactive instructions, is the joint feature node number, , is the total number of joint feature nodes, Range is .

[0034] As a preferred technical solution, a personalized behavior preset parameter update module is also included, specifically including:

[0035] After the feedback is completed, obtain the user's interactive feedback evaluation information;

[0036] Obtaining a user's interactive feedback result based on the interactive feedback evaluation information, wherein the user's interactive feedback result includes correct interactive feedback and incorrect interactive feedback;

[0037] The interactive feedback results of this time are entered into the natural interaction platform as historical interaction data storage, and the user's personalized behavior preset parameters are updated based on the historical interaction data.

[0038] The present invention also provides a method for generating a natural interactive virtual scene, comprising:

[0039] S1, used to collect the user's initial preference interaction data and the user's personal body shape data in the virtual scene through the natural interaction platform, analyze and process to generate the user's initial interaction preference feature value and personalized body shape feature value, and analyze and process to generate the personalized behavior preset parameters of each interaction instruction of the user based on the initial behavior parameters of each interaction instruction stored in the natural interaction platform;

[0040] S2. Based on the personalized body shape feature value of the user, obtain the personalized virtual scene configuration parameters of the user and generate the personalized virtual scene of the user;

[0041] S3, used to collect real-time motion data of the user in the personalized virtual scene through a motion capture sensor, filter out effective real-time motion data of the user in the personalized virtual scene, and send the effective real-time motion data to the interactive instruction processing module;

[0042] S4, used to compare the effective real-time action data of the user in the personalized virtual scene with the personalized behavior preset parameters of each interaction instruction of the user to generate matching values ​​of the effective real-time data and each interaction instruction, and screen the interaction instruction corresponding to the highest matching value as the effective interaction instruction of the user;

[0043] S5, used to receive a valid interaction instruction from a user, and index interaction feedback data corresponding to the valid interaction instruction preset by the natural interaction platform, and provide interaction feedback to the user.

[0044] Compared with the prior art, the embodiments of the present invention have at least the following beneficial effects:

[0045] (1) The present invention provides a natural interactive virtual scene generation system and method. By collecting the user's initial preference interaction data and the user's personal body shape data in advance, analyzing and processing to generate personalized behavior preset parameters for each user's interaction instructions, the system can better match the user's personal habits and physical characteristics, making the interaction in the virtual environment more natural and comfortable.

[0046] (2) The present invention obtains the user's personalized virtual scene configuration parameters based on the user's personalized body shape feature value and generates the user's personalized virtual scene. The size, proportion and layout of the elements in the scene are adjusted according to the user's body shape features, so that the virtual scene is more in line with the user's actual feelings. The user's operation and interaction in the virtual scene are more natural, reducing the sense of difference with the real world. It also reduces erroneous operations and interaction difficulties.

[0047] (3) The present invention collects the real-time motion data of the user in the personalized virtual scene through the motion capture sensor, screens out the effective real-time motion data of the user in the personalized virtual scene, reduces the user's accidental touches in the personalized virtual scene, reduces the computing power burden of the system, and increases the recognition accuracy of the user's interactive instructions.

[0048] Of course, any product implementing the present invention does not necessarily need to achieve all of the above advantages at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the system module of the present invention.

[0050] Figure 2 It is a schematic diagram of the method flow of the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] See also Figure 1 As shown, an embodiment of the present invention provides a natural interactive virtual scene generation system, including:

[0053] The initial preference setting module is used to collect the user's initial preference interaction data and the user's personal body data in the virtual scene through the natural interaction platform, analyze and process to generate the user's initial interaction preference feature value and personalized body feature value, and analyze and process the initial behavior parameters of each interaction instruction stored in the natural interaction platform to generate the personalized behavior preset parameters of each interaction instruction of the user.

[0054] The specific process of collecting the user's initial preference interaction data and the user's personal body shape data in the virtual scene through the natural interaction platform is as follows:

[0055] The user logs in to the natural interaction platform through a personal account. If the user is using the natural interaction platform for the first time, the user's personal body data, including the user's height, shoulder width and arm length, is collected through a questionnaire. The user's joint feature nodes are anchored based on the user's personal body data, and the user is guided to perform trial matching. The user is guided to try out various interaction commands. After the trial matching is completed, the user's initial preference interaction data is counted, including user interaction sensitivity, average duration of each interaction command, interaction position deviation value of each interaction command and success rate of each interaction command.

[0056] The specific process of anchoring the user's joint feature nodes based on the user's personal body shape data is as follows:

[0057] The average body model data, including average height, average shoulder width and average arm length, is retrieved from the natural interaction platform. Based on the user's personal body data, the model data, including height, shoulder width and arm length, is dynamically adjusted. Based on the adjusted body model, the position of the feature nodes of each joint of the user is anchored.

[0058] It should be explained that user interaction sensitivity refers to the reaction speed of users when they are guided to interact. It is used to evaluate the reaction speed of users when they interact.

[0059] The average duration of each interactive instruction refers to the average time required for users to complete each interactive instruction.

[0060] The interaction position deviation value of each interaction instruction refers to the difference between the actual interaction position and the expected interaction position when the user executes each interaction instruction. It is used to evaluate the accuracy of each interaction instruction, adjust the position of each interaction instruction, reduce the position deviation, and improve the interaction accuracy.

[0061] The success rate of each interactive command refers to the percentage of users who successfully execute each interactive command. It is used to measure the effectiveness of each interactive command and identify which commands users encounter difficulties with, so as to improve the interactive commands in a targeted manner.

[0062] If the user has used the natural interaction platform multiple times, the user's personal body data and historical preference interaction data are extracted from the natural interaction platform. The historical preference interaction data includes historical action sensitivity, average duration of historical interaction instructions, interaction position deviation value of historical interaction instructions, and success rate of historical interaction instructions, and are recorded as the user's initial preference interaction data this time.

[0063] An interaction verification value set of each interaction instruction is extracted from the natural interaction platform, including an interaction sensitivity verification value, a standard duration of each interaction instruction, an interaction position deviation value verification value of each interaction instruction, and a success rate verification value of each interaction instruction.

[0064] The initial behavior parameters of each interaction instruction stored in the natural interaction platform are analyzed and processed with the initial interaction preference feature value of the user to generate personalized behavior preset parameters of each interaction instruction of the user, specifically including:

[0065] Based on the user's initial preference interaction data, analysis and processing are performed to generate the user's initial interaction preference feature value, where the user's initial interaction preference feature value is used to comprehensively characterize the user's interaction preference.

[0066] The analysis process generates the user's initial interaction preference feature value, and the specific processing method is as follows:

[0067] ;

[0068] in, is the user's initial interaction preference feature value, For user The interaction sensitivity of each interactive command, For user The average duration of interaction instructions, For user The interaction position deviation value of the interaction instruction, For user The success rate of interactive commands, is the interaction sensitivity check value, For the The standard duration of an interactive instruction, For the The interactive position deviation check value of the interactive instruction, For the The success rate check value of the interactive command, is the number of the interactive instruction, , is the total number of interactive instructions.

[0069] Based on the user's personal body shape data, the user's personalized body shape feature value is generated through analysis and processing, and the user's personalized body shape feature value is used to characterize the user's body shape feature.

[0070] The average height, average shoulder width, and average arm length corresponding to the user's gender are extracted from the natural interaction platform.

[0071] The analysis process generates the user's personalized body shape feature value, and the specific processing conditions are:

[0072] ;

[0073] in, is the user's personalized body shape feature value, is the user's height, is the user's shoulder width, is the user's arm length, is the average height, is the average shoulder width, is the average arm length. The softplus function is a built-in function in Pytnon. .

[0074] A set of standard initial behavior parameter values ​​and a set of allowable error values ​​of initial behavior parameters for each interaction instruction are extracted from the natural interaction platform, wherein the set of standard initial behavior parameter values ​​includes: standard displacement values ​​of each joint feature node of each interaction instruction action, standard action duration values ​​of each joint feature node of each interaction instruction action, standard action speed values ​​of each joint feature node of each interaction instruction action, and standard direction vector angle values ​​of each joint feature node of each interaction instruction action.

[0075] The standard value of the displacement of each joint feature node of each interactive instruction action refers to the distance that each joint feature node is expected to move when executing a specific interactive instruction.

[0076] The standard value of the action duration of each joint feature node of each interactive instruction action refers to the time required for each joint feature node to complete the expected displacement when executing each interactive instruction.

[0077] The standard value of the action speed of each joint feature node of each interactive instruction action refers to the expected movement speed of each joint feature node when executing each interactive instruction.

[0078] The standard value of the direction vector angle of each joint feature node of each interactive instruction action refers to the direction in which each joint feature node moves when executing each interactive instruction.

[0079] The set of initial behavior parameter allowable error values ​​includes the allowable error value of displacement of each joint feature node of each interactive instruction action, the allowable error value of action duration of each joint feature node of each interactive instruction action, the allowable error value of action speed of each joint feature node of each interactive instruction action, and the allowable error value of direction vector angle of each joint feature node of each interactive instruction action;

[0080] Based on the initial interaction preference feature value of the user, the initial behavior parameter standard value set of each interaction instruction is adjusted, and the processed initial behavior parameter standard value set of each interaction instruction is recorded as the personalized preset behavior parameter of each interaction instruction action of the user;

[0081] The initial behavior parameter standard value set for adjusting each interaction instruction specifically includes:

[0082] Based on the user's initial interaction preference characteristic value, a mapping match is performed with the standard adjustment value of the initial behavior parameters of each interaction instruction corresponding to each initial interaction preference characteristic value interval pre-existing in the natural interaction platform to obtain the standard adjustment value of the initial behavior parameters of each interaction instruction, and the standard value of the initial behavior parameters of each interaction instruction is adjusted based on the standard adjustment value of the initial behavior parameters of each interaction instruction.

[0083] The standard adjustment values ​​of the initial behavior parameters of each interactive instruction include the standard adjustment value of the displacement of each joint feature node of each interactive instruction action, the standard adjustment value of the action duration, the standard adjustment value of the action speed and the standard adjustment value of the direction vector angle.

[0084] For example, if the standard adjustment value of the displacement of a joint feature node of a certain interactive command action is -2, then the standard adjustment value of the displacement of the joint feature node of the interactive command action is reduced by 2 units. In another embodiment of the invention, 1 unit is 10 centimeters.

[0085] The personalized preset behavior parameters of each interactive instruction action of the user include personalized preset values ​​of displacement of each joint feature node of each interactive instruction action, personalized preset values ​​of action duration of each joint feature node of each interactive instruction action, personalized preset values ​​of action speed of each joint feature node of each interactive instruction action, and personalized preset values ​​of direction vector of each joint feature node of each interactive instruction action.

[0086] The virtual scene configuration module processes the user's personalized virtual scene configuration parameters based on the user's personalized body shape feature value and generates the user's personalized virtual scene.

[0087] The process of obtaining the user's personalized virtual scene configuration parameters based on the user's personalized body shape feature value and generating the user's personalized virtual scene specifically includes:

[0088] Based on the personalized body feature values ​​of the user, mapping and matching are performed with the personalized virtual scene configuration parameters corresponding to each personalized body feature value interval pre-stored in the natural interaction platform to obtain the personalized virtual scene configuration parameters of the user, wherein the personalized virtual scene configuration parameters include personalized graphics rendering parameters and physical simulation parameters. Based on the personalized virtual scene configuration parameters of the user, the rendering engine is adjusted to perform virtual scene configuration, and the virtual scene is recorded as a personalized virtual scene.

[0089] Personalized graphics rendering parameters determine the visual effects of the virtual scene, including resolution, shadow effect parameters, lighting simulation parameters, anti-aliasing parameters, and post-processing effect parameters (such as depth of field, motion blur, and glow).

[0090] Physics simulation parameters determine how objects in the virtual scene interact and move according to the laws of physics, including gravity parameters, collision parameters, rigid body dynamics parameters, and fluid dynamics parameters.

[0091] The sensor data acquisition module is used to collect the real-time motion data of the user in the personalized virtual scene through the motion capture sensor, filter out the effective real-time motion data of the user in the personalized virtual scene, and send the effective real-time motion data to the interactive instruction processing module.

[0092] The method of collecting the real-time motion data of the user in the personalized virtual scene by the motion capture sensor, filtering out the effective real-time motion data of the user in the personalized virtual scene, and sending the effective real-time motion data to the interactive instruction processing module specifically includes:

[0093] After the personalized virtual scene is configured, a three-dimensional rectangular coordinate system is established with the center point of the user's standing position as the center of the circle;

[0094] The preset command recognition area of ​​the personalized virtual scene is extracted from the natural interaction platform. When the user's joint feature nodes enter the command recognition area, the real-time spatial position coordinates of the user's joint feature nodes are obtained by scanning sensors.

[0095] Based on the real-time spatial position coordinates of each joint feature node of the user, the real-time action data of each joint feature node of the user in the personalized virtual scene is obtained;

[0096] When the coordinates of each joint feature node of the user enter the command recognition area preset in the personalized virtual scene, the real-time action data of each joint feature node is counted and sent to the interactive command processing module as effective real-time action data.

[0097] The interactive instruction processing module is used to compare the user's effective real-time action data in the personalized virtual scene with the personalized behavior preset parameters of each interactive instruction of the user to generate matching values ​​between the effective real-time data and each interactive instruction, and screen out the interactive instruction corresponding to the highest matching value as the user's effective interactive instruction.

[0098] The step of comparing the effective real-time action data of the user in the personalized virtual scene with the personalized behavior preset parameters of each interaction instruction of the user to generate a matching value between the effective real-time data and each interaction instruction specifically includes:

[0099] Based on the effective real-time action data of each joint feature node of the user in the personalized virtual scene, including the action time of each joint feature node, the action speed of each joint feature node, the action direction vector of each joint feature node and the action displacement of each joint feature node, the data are compared with the personalized behavior preset parameters of each interaction instruction of the user to generate the matching value of the effective real-time data and each interaction instruction.

[0100] The specific process of generating the matching value of the effective real-time data and each interactive instruction is as follows:

[0101] ;

[0102] in, To effectively conduct real-time behavioral data and The matching value of the interactive instruction, Provide users with personalized virtual scenes The displacement of the joint feature node, Provide users with personalized virtual scenes The action duration of each joint feature node, Provide users with personalized virtual scenes The action speed of the joint feature node, Provide users with personalized virtual scenes The direction vector of the joint feature node, For the The interactive command The displacement of each joint feature node is personalized preset value. For the The interactive command Personalized preset value of action duration of each joint feature node, For the The interactive command The action speed of each joint feature node is personalized and preset. For the The interactive command The direction vector of each joint feature node is personalized preset value. For the The interactive command The displacement tolerance of the joint feature nodes is: For the The interactive command The allowable error value of the action duration of the joint feature node, For the The interactive command The permissible error value of the motion speed of each joint feature node, For the The interactive command The allowable error value of the direction vector angle of the joint feature node, is the number of the interactive instruction, , is the total number of interactive instructions, is the joint feature node number, , is the total number of joint feature nodes, Range is .

[0103] The interaction instruction corresponding to the highest matching value is screened as the user's valid interaction instruction, which specifically includes:

[0104] The matching values ​​of the effective real-time data and each interaction instruction are sorted in descending order, and the interaction instruction corresponding to the first interaction instruction matching value is selected as the effective interaction instruction of the user.

[0105] The interaction instruction feedback module is used to receive the user's effective interaction instruction, index the interaction feedback data corresponding to the effective interaction instruction preset by the natural interaction platform, and provide interaction feedback to the user.

[0106] The interactive feedback data corresponding to the effective interactive instruction, in another embodiment of the invention, for example, after accepting the user's "click to start CPR simulation training" interactive instruction, indexes the interactive feedback data of "click to start CPR simulation training" to start the CPR simulation training timing.

[0107] In addition, the present invention also includes a personalized behavior preset parameter update module, specifically including:

[0108] After the feedback is completed, the user's interactive feedback evaluation information is obtained, including real-time evaluation information and natural interaction platform questionnaire evaluation information.

[0109] The user's interaction feedback result is obtained based on the interaction feedback evaluation information processing, and the user's interaction feedback result includes correct interaction feedback and incorrect interaction feedback.

[0110] The interactive feedback results of this time are entered into the natural interaction platform as historical interaction data storage, and the user's personalized behavior preset parameters are updated based on the historical interaction data.

[0111] In this embodiment, the present invention further provides a method for generating a natural interactive virtual scene, comprising:

[0112] S1, used to collect the user's initial preference interaction data and the user's personal body shape data in the virtual scene through the natural interaction platform, analyze and process to generate the user's initial interaction preference feature value and personalized body shape feature value, and analyze and process to generate the personalized behavior preset parameters of each interaction instruction of the user based on the initial behavior parameters of each interaction instruction stored in the natural interaction platform;

[0113] S2. Based on the personalized body shape feature value of the user, obtain the personalized virtual scene configuration parameters of the user and generate the personalized virtual scene of the user;

[0114] S3, used to collect real-time motion data of the user in the personalized virtual scene through a motion capture sensor, filter out effective real-time motion data of the user in the personalized virtual scene, and send the effective real-time motion data to the interactive instruction processing module;

[0115] S4, used to compare the effective real-time action data of the user in the personalized virtual scene with the personalized behavior preset parameters of each interaction instruction of the user to generate matching values ​​of the effective real-time data and each interaction instruction, and screen the interaction instruction corresponding to the highest matching value as the effective interaction instruction of the user;

[0116] S5, used to receive a valid interaction instruction from a user, and index interaction feedback data corresponding to the valid interaction instruction preset by the natural interaction platform, and provide interaction feedback to the user.

[0117] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0118] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. As long as they do not deviate from the structure of the present invention or exceed the scope defined by the present invention, they should all belong to the protection scope of the present invention.

Claims

1. A natural interactive virtual scene generation system, characterized in that: include: An initial preference setting module is used to collect the user's initial preference interaction data and the user's personal body shape data in the virtual scene through the natural interaction platform, analyze and process to generate the user's initial interaction preference feature value and personalized body shape feature value, and analyze and process the initial behavior parameters of each interaction instruction stored in the natural interaction platform to generate the personalized behavior preset parameters of each interaction instruction of the user; A virtual scene configuration module, based on the user's personalized body shape feature value, processes the user's personalized virtual scene configuration parameters and generates the user's personalized virtual scene; The sensor data acquisition module is used to collect the real-time motion data of the user in the personalized virtual scene through the motion capture sensor, filter out the effective real-time motion data of the user in the personalized virtual scene, and send the effective real-time motion data to the interactive instruction processing module; The interactive instruction processing module is used to compare the effective real-time action data of the user in the personalized virtual scene with the personalized behavior preset parameters of each interactive instruction of the user to generate matching values ​​between the effective real-time data and each interactive instruction, and screen the interactive instruction corresponding to the highest matching value as the effective interactive instruction of the user; The interaction instruction feedback module is used to receive the user's effective interaction instruction, index the interaction feedback data corresponding to the effective interaction instruction preset by the natural interaction platform, and provide interaction feedback to the user.

2. A natural interactive virtual scene generation system according to claim 1, characterized in that: The specific process of collecting the user's initial preference interaction data and the user's personal body shape data in the virtual scene through the natural interaction platform is as follows: The user logs in to the natural interaction platform through a personal account. If the user is using the natural interaction platform for the first time, the user's personal body data, including the user's height, shoulder width and arm length, is collected. The user's joint feature nodes are anchored based on the user's personal body data, and the user is guided to perform trial matching. The user is guided to try out various interaction commands. After the trial matching is completed, the user's initial preference interaction data is counted, including user interaction sensitivity, average duration of each interaction command, interaction position deviation value of each interaction command and success rate of each interaction command. If the user has used the natural interaction platform multiple times, the user's personal body data and historical preference interaction data are extracted from the natural interaction platform. The historical preference interaction data includes historical action sensitivity, average duration of historical interaction instructions, interaction position deviation value of historical interaction instructions, and success rate of historical interaction instructions, and are recorded as the user's initial preference interaction data this time.

3. A natural interactive virtual scene generation system according to claim 1, characterized in that: The initial behavior parameters of each interaction instruction stored in the natural interaction platform are analyzed and processed with the initial interaction preference feature value of the user to generate personalized behavior preset parameters of each interaction instruction of the user, specifically including: Based on the user's initial preference interaction data, analyzing and processing to generate the user's initial interaction preference feature value, wherein the user's initial interaction preference feature value is used to comprehensively characterize the user's interaction preference; Based on the user's personal body shape data, analyzing and processing to generate the user's personalized body shape feature value, the user's personalized body shape feature value is used to characterize the user's body shape feature; Extracting an initial behavior parameter standard value set and an initial behavior parameter allowable error value set of each interaction instruction from the natural interaction platform, wherein the initial behavior parameter standard value set includes: a displacement standard value of each joint feature node of each interaction instruction action, an action duration standard value of each joint feature node of each interaction instruction action, an action speed standard value of each joint feature node of each interaction instruction action, and a direction vector standard value of each joint feature node of each interaction instruction action; The set of initial behavior parameter allowable error values ​​includes the allowable error value of displacement of each joint feature node of each interactive instruction action, the allowable error value of action duration of each joint feature node of each interactive instruction action, the allowable error value of action speed of each joint feature node of each interactive instruction action, and the allowable error value of direction vector angle of each joint feature node of each interactive instruction action; Based on the initial interaction preference feature value of the user, the initial behavior parameter standard value set of each interaction instruction is adjusted, and the processed initial behavior parameter standard value set of each interaction instruction is recorded as the personalized preset behavior parameter of each interaction instruction action of the user; The personalized preset behavior parameters of each interactive instruction action of the user include personalized preset values ​​of displacement of each joint feature node of each interactive instruction action, personalized preset values ​​of action duration of each joint feature node of each interactive instruction action, personalized preset values ​​of action speed of each joint feature node of each interactive instruction action, and personalized preset values ​​of direction vector of each joint feature node of each interactive instruction action.

4. A natural interactive virtual scene generation system according to claim 3, characterized in that: The process of obtaining the personalized virtual scene configuration parameters of the user based on the personalized body shape feature value of the user and generating the personalized virtual scene of the user specifically includes: Based on the personalized body feature values ​​of the user, mapping and matching are performed with personalized virtual scene configuration parameters corresponding to each personalized body feature value interval pre-stored in the natural interaction platform to obtain the personalized virtual scene configuration parameters of the user, wherein the personalized virtual scene configuration parameters include personalized graphics rendering parameters and physical simulation parameters. The virtual scene is configured based on the personalized virtual scene configuration parameters of the user, and the virtual scene is recorded as a personalized virtual scene.

5. A natural interactive virtual scene generation system according to claim 4, characterized in that: The method of collecting the real-time motion data of the user in the personalized virtual scene by the motion capture sensor, filtering out the effective real-time motion data of the user in the personalized virtual scene, and sending the effective real-time motion data to the interactive instruction processing module specifically includes: Based on the spatial position coordinates of each joint feature node of the user, the real-time action data of each joint feature node of the user in the personalized virtual scene is obtained; When the coordinates of each joint feature node of the user enter the command recognition range preset by the personalized virtual scene, the real-time action data of each joint feature node is counted and sent to the interactive command processing module as effective real-time action data.

6. A natural interactive virtual scene generation system according to claim 4, characterized in that: The step of comparing the effective real-time action data of the user in the personalized virtual scene with the personalized behavior preset parameters of each interaction instruction of the user to generate a matching value between the effective real-time data and each interaction instruction specifically includes: Based on the effective real-time action data of each joint feature node of the user in the personalized virtual scene, including the action time of each joint feature node, the action speed of each joint feature node, the action direction vector of each joint feature node and the action displacement of each joint feature node, the data are compared with the personalized behavior preset parameters of each interaction instruction of the user to generate the matching value of the effective real-time data and each interaction instruction.

7. A natural interactive virtual scene generation system according to claim 3, characterized in that: The screening obtains the interaction instruction corresponding to the highest matching value as the user's valid interaction instruction, specifically including: The matching values ​​of the effective real-time data and each interaction instruction are sorted in descending order, and the interaction instruction corresponding to the interaction instruction matching value that ranks first is selected as the effective interaction instruction of the user.

8. A natural interactive virtual scene generation system according to claim 6, characterized in that: The specific process of generating the matching value of the effective real-time data and each interactive instruction is as follows: ； in, To effectively conduct real-time behavioral data and The matching value of the interactive instruction, Provide users with personalized virtual scenes The displacement of the joint feature node, Provide users with personalized virtual scenes The action duration of each joint feature node, Provide users with personalized virtual scenes The action speed of the joint feature node, Provide users with personalized virtual scenes The direction vector of the joint feature node, For the The interactive command The displacement of each joint feature node is personalized preset value. For the The interactive command Personalized preset value of action duration of each joint feature node, For the The interactive command The action speed of each joint feature node is personalized and preset. For the The interactive command The direction vector of each joint feature node is personalized preset value. For the The interactive command The displacement tolerance of the joint feature nodes is: For the The first interactive command The allowable error value of the action duration of the joint feature node, For the The first interactive command The permissible error value of the motion speed of each joint feature node, For the The first interactive command The allowable error value of the direction vector angle of the joint feature node, is the number of the interactive instruction, , is the total number of interactive instructions, Number the joint feature nodes. , is the total number of joint feature nodes, Range is .

9. A natural interactive virtual scene generation system according to claim 1, characterized in that: It also includes a personalized preset parameter update module, including: After the feedback is completed, obtain the user's interactive feedback evaluation information; Obtaining a user's interactive feedback result based on the interactive feedback evaluation information, wherein the user's interactive feedback result includes correct interactive feedback and incorrect interactive feedback; The interactive feedback results of this time are entered into the natural interaction platform as historical interaction data storage, and the user's personalized behavior preset parameters are updated based on the historical interaction data.

10. A method for generating a natural interactive virtual scene, characterized in that: include: S1, used to collect the user's initial preference interaction data and the user's personal body shape data in the virtual scene through the natural interaction platform, analyze and process to generate the user's initial interaction preference feature value and personalized body shape feature value, and analyze and process to generate the personalized behavior preset parameters of each interaction instruction of the user based on the initial behavior parameters of each interaction instruction stored in the natural interaction platform; S2. Based on the personalized body shape feature value of the user, obtain the personalized virtual scene configuration parameters of the user and generate the personalized virtual scene of the user; S3, used to collect real-time motion data of the user in the personalized virtual scene through a motion capture sensor, filter out effective real-time motion data of the user in the personalized virtual scene, and send the effective real-time motion data to the interactive instruction processing module; S4, used to compare the effective real-time action data of the user in the personalized virtual scene with the personalized behavior preset parameters of each interaction instruction of the user to generate matching values ​​of the effective real-time data and each interaction instruction, and screen the interaction instruction corresponding to the highest matching value as the effective interaction instruction of the user; S5, used to receive a valid interaction instruction from a user, and index interaction feedback data corresponding to the valid interaction instruction preset by the natural interaction platform, and provide interaction feedback to the user.

Images