Non-inductive man-machine interaction method and system fusing UWB and space sound field

Abstract

The invention discloses a non-inductive man-machine interaction method and a non-inductive man-machine interaction system fusing UWB and a space sound field, and belongs to the technical field of intelligent control. Through a trained neural network model, an original ranging value between a UWB positioning label of a user and each UWB positioning base station at present is used as an input; outputting a corresponding distance measurement error correction value between the current UWB positioning tag of the user and each UWB positioning base station, and obtaining a correction distance measurement value between the current UWB positioning tag of the user and each UWB positioning base station according to the distance measurement error correction value; and after a time difference of arrival equation set is constructed by using the corrected distance measurement value, the first coordinate data of the user is obtained by resolving through a chan algorithm, so that the accuracy of UWB positioning is improved, and the interaction instruction identification efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a seamless human-computer interaction method and system that integrates UWB and spatial sound field. Background Technology

[0002] In traditional human-computer interaction, users need to learn the language of machines, such as typing, clicking icons, swiping the screen, and even memorizing complex instructions, so that the machine can understand what the user wants to do. However, with the development of technology, most machines and devices have also achieved seamless human-computer interaction, where the machine actively senses and understands human gestures and then executes the corresponding instructions to automatically provide services. However, most existing contactless human-computer interactions require camera devices to recognize user actions, which is inefficient. Furthermore, in the interaction space, there are often situations where the camera cannot capture images, thus making it impossible to recognize user actions. Therefore, contactless human-computer interaction methods using UWB (Ultra Wide Band) technology have emerged. However, existing contactless interactions based on UWB suffer from ranging errors and inaccurate positioning, which affects the recognition of interaction commands. Summary of the Invention

[0003] To address the technical problems existing in the prior art, this invention provides a seamless human-computer interaction method that integrates UWB and spatial sound field, comprising the following steps: S1. Establish a UWB positioning coordinate system and a sound field coordinate system based on the interactive space, and perform spatial joint calibration on the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system, including the rotation matrix R1 and the translation vector T1. S2. In the interactive space, the user wears a device with a UWB positioning tag on their hand. Based on the UWB positioning coordinate system and the user's UWB positioning tag, the user's first coordinate data is calculated and obtained in real time, specifically: S21. A neural network model trained using the sequence of experimental raw ranging values ​​from the experimental UWB tag to each UWB positioning base station and the corresponding experimental ranging error correction values ​​as training samples. The model takes the raw ranging values ​​between the user's UWB positioning tag and each UWB positioning base station as input and outputs the corresponding ranging error correction values ​​between the user's UWB positioning tag and each UWB positioning base station. Based on the ranging error correction values, the corrected ranging values ​​between the user's UWB positioning tag and each UWB positioning base station are obtained. S22. Select one of the UWB positioning base stations as the reference base station, and construct a set of time difference of arrival equations using the corrected ranging values: ; This is the corrected ranging value between the user's UWB positioning tag and the i-th UWB positioning base station at time t; This is the corrected ranging value between the user's UWB positioning tag and the reference base station at time t; Let t be the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system. Let be the position coordinates of the i-th UWB positioning base station in the UWB positioning coordinate system; The reference base station's position coordinates in the UWB positioning coordinate system; S23. The user's first coordinate data, i.e., the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system, is obtained by solving the time difference of arrival equation system through the improved chan algorithm. S3. Obtain the first coordinate data sequence within the latest time period according to step S2, obtain the user's hand movement trajectory within the latest time period according to the first coordinate data sequence, and perform interactive command recognition and matching according to the hand movement trajectory. S4. Control the corresponding device to complete the interactive command action according to the matched interactive command. At the same time, transform the user's current first coordinate data into the sound field coordinate system according to the rotation matrix R1 and the translation vector T1 to obtain the corresponding second coordinate data. Control each speaker to project sound directionally to the second coordinate data through phased array beamforming technology and broadcast interactive feedback voice.

[0004] Furthermore, the UWB positioning coordinate system is specifically configured by deploying at least four UWB positioning base stations in the interaction space, with one of the UWB positioning base stations serving as the origin of the UWB positioning coordinate system. The sound field coordinate system is specifically defined by deploying multiple speakers in the interactive space, with one of the speakers serving as the origin of the sound field coordinate system.

[0005] Furthermore, the spatial joint calibration of the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system specifically involves: A calibration target is set up in the interactive space, with a reference UWB positioning tag and a reference microphone on it. The calibration target is moved sequentially to multiple preset positions in the interactive space. During this process, multiple tag coordinates P1 calculated by UWB and multiple sound source receiving coordinates P2, which are obtained by transmitting test signals through the sound field generator and receiving them through the reference microphone, are recorded. The tag coordinates and sound source receiving coordinates corresponding to the same preset position are regarded as a coordinate pair. The rotation matrix R1 and translation vector T1 between the UWB positioning coordinate system and the sound field coordinate system are solved by the least squares method, so that P2 = R1 × P1 + T1 holds for all coordinate pairs.

[0006] Furthermore, the experimental ranging error correction value is obtained through prior testing, specifically as follows: A test UWB tag is set up to move continuously in the interactive space. During this process, a bilateral bidirectional ranging protocol is used to collect the test raw flight time between the test UWB tag and each UWB positioning base station at a fixed frequency, and convert it into the corresponding test raw ranging value: ; This represents the initial experimental ranging value between the experimental UWB tag and the i-th UWB positioning base station at time t, where c is the speed of light. This represents the original flight time of the test UWB tag and the i-th UWB positioning base station at time t. Obtain the true geometric distance between the test UWB tag and the corresponding UWB positioning base station corresponding to the original ranging value of each test. Based on the original ranging value and the corresponding true geometric distance, obtain the corresponding test ranging error correction value: ; This represents the test ranging error correction value between the test UWB tag and the i-th UWB positioning base station at time t. Let t be the actual geometric distance between the experimental UWB tag and the i-th UWB positioning base station.

[0007] Furthermore, interactive command recognition and matching are performed based on the hand movement trajectory, specifically as follows: Obtain a preset interactive instruction model library, which records the trajectory movement sequence and the final trajectory imaging graphic corresponding to each interactive instruction; Project each coordinate point in the first coordinate data sequence corresponding to the hand movement trajectory onto the same plane, and smoothly connect the projected points according to the order of acquisition of the first coordinate data to obtain the first graphic. Based on the formation order of the hand movement trajectory, the corresponding matching trajectory movement order is selected from the interaction instruction model library. Then, the final image of the trajectory corresponding to the matching trajectory movement order is compared with the first image for similarity analysis. If the similarity is greater than a preset similarity threshold, the corresponding interaction instruction matches the hand movement trajectory.

[0008] Furthermore, phased array beamforming technology is used to control each loudspeaker to project sound directionally toward the second coordinate data, specifically as follows: Based on the coordinate positions of each speaker in the sound field coordinate system and the second coordinate data, the straight-line distance from each speaker to the current user is obtained; Based on the stated straight-line distance, calculate the required emission phase for each loudspeaker: ; Let f be the required emission phase for the j-th loudspeaker, f be the carrier frequency of the sound wave emitted by the loudspeaker, and cy be the speed of sound. Let j be the straight-line distance from the j-th speaker to the current user. Preset initial reference phase; Based on the required emission phase of each loudspeaker, each loudspeaker simultaneously emits sound waves that have undergone phase adjustment.

[0009] This invention also provides a seamless human-computer interaction system that integrates UWB and spatial sound field, comprising: The calibration module is used to establish a UWB positioning coordinate system and a sound field coordinate system based on the interactive space, and to perform joint spatial calibration of the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system, including the rotation matrix R1 and the translation vector T1. The calculation module, in the interactive space, uses a device with a UWB positioning tag on the user's hand to calculate and obtain the user's first coordinate data in real time based on the UWB positioning coordinate system and the user's UWB positioning tag; The instruction matching module obtains the first coordinate data sequence within the latest time period, obtains the user's hand movement trajectory within the latest time period based on the first coordinate data sequence, and performs interactive instruction recognition and matching based on the hand movement trajectory. The execution broadcast module controls the corresponding device to complete the interactive command action according to the matched interactive command. At the same time, it transforms the user's current first coordinate data into the sound field coordinate system according to the rotation matrix R1 and the translation vector T1 to obtain the corresponding second coordinate data. Through phased array beamforming technology, it controls each speaker to project sound directionally to the second coordinate data and broadcasts the interactive feedback voice.

[0010] Furthermore, the UWB positioning coordinate system is specifically configured by deploying at least four UWB positioning base stations in the interaction space, with one of the UWB positioning base stations serving as the origin of the UWB positioning coordinate system. The sound field coordinate system is specifically defined by deploying multiple speakers in the interactive space, with one of the speakers serving as the origin of the sound field coordinate system.

[0011] Furthermore, the spatial joint calibration of the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system specifically involves: A calibration target is set up in the interactive space, with a reference UWB positioning tag and a reference microphone on it. The calibration target is moved sequentially to multiple preset positions in the interactive space. During this process, multiple tag coordinates P1 calculated by UWB and multiple sound source receiving coordinates P2, which are obtained by transmitting test signals through the sound field generator and receiving them through the reference microphone, are recorded. The tag coordinates and sound source receiving coordinates corresponding to the same preset position are regarded as a coordinate pair. The rotation matrix R1 and translation vector T1 between the UWB positioning coordinate system and the sound field coordinate system are solved by the least squares method, so that P2 = R1 × P1 + T1 holds for all coordinate pairs.

[0012] Furthermore, the real-time calculation to obtain the user's first coordinate data specifically includes: S21. A neural network model trained using the sequence of experimental raw ranging values ​​from the experimental UWB tag to each UWB positioning base station and the corresponding experimental ranging error correction values ​​as training samples. The model takes the raw ranging values ​​between the user's UWB positioning tag and each UWB positioning base station as input and outputs the corresponding ranging error correction values ​​between the user's UWB positioning tag and each UWB positioning base station. Based on the ranging error correction values, the corrected ranging values ​​between the user's UWB positioning tag and each UWB positioning base station are obtained. S22. Select one of the UWB positioning base stations as the reference base station, and construct a set of time difference of arrival equations using the corrected ranging values: ; This is the corrected ranging value between the user's UWB positioning tag and the i-th UWB positioning base station at time t; This is the corrected ranging value between the user's UWB positioning tag and the reference base station at time t; Let t be the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system at time t; Let be the position coordinates of the i-th UWB positioning base station in the UWB positioning coordinate system; The reference base station's position coordinates in the UWB positioning coordinate system; S23. Solve the time difference of arrival equations using the Chan algorithm to obtain the user's first coordinate data, which is the position coordinate of the user's UWB positioning tag in the UWB positioning coordinate system.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention uses a trained neural network model to take the original ranging values ​​between the user's UWB positioning tag and each UWB positioning base station as input, and outputs the ranging error correction values ​​corresponding to the current ranging error between the user's UWB positioning tag and each UWB positioning base station. Based on the ranging error correction values, the corrected ranging values ​​between the user's UWB positioning tag and each UWB positioning base station are obtained. After constructing a set of time difference of arrival equations using the corrected ranging values, the user's first coordinate data is obtained by solving the Chan algorithm, thereby improving the accuracy of UWB positioning and thus improving the efficiency and accuracy of interactive command recognition. This invention projects each coordinate point in the first coordinate data sequence corresponding to the hand movement trajectory onto the same plane, and smoothly connects the projected points according to the order of acquisition of the first coordinate data to obtain a first graphic. This graphic is then compared with the final image of the trajectory of the corresponding interactive command in the interactive command model library for similarity. By projecting each coordinate point in the first coordinate data sequence onto the same plane to obtain the first graphic, the invention avoids directly comparing the three-dimensional graphic drawn by the user in actual space with the two-dimensional trajectory final image in the library, effectively improving the effectiveness of similarity comparison and thus improving the accuracy of command matching. Attached Figure Description

[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of a non-sensory human-computer interaction method that integrates UWB and spatial sound field according to the present invention; Figure 2 This is a structural block diagram of a non-intrusive human-computer interaction system that integrates UWB and spatial sound field according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0019] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" and "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0020] Example 1 See Figure 1 As shown, the present invention provides a seamless human-computer interaction method that integrates UWB and spatial sound field, specifically including the following steps: S1. Establish a UWB positioning coordinate system and a sound field coordinate system based on the interactive space, and perform spatial joint calibration on the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system, including the rotation matrix R1 and the translation vector T1. S2. In the interactive space, the user wears a device with a UWB positioning tag on their hand. Based on the UWB positioning coordinate system and the user's UWB positioning tag, the user's first coordinate data is calculated and obtained in real time. S3. Obtain the first coordinate data sequence within the latest time period according to step S2, obtain the user's hand movement trajectory within the latest time period according to the first coordinate data sequence, and perform interactive command recognition and matching according to the hand movement trajectory. S4. Control the corresponding device to complete the interactive command action according to the matched interactive command. At the same time, transform the user's current first coordinate data into the sound field coordinate system according to the rotation matrix R1 and the translation vector T1 to obtain the corresponding second coordinate data. Control each speaker to project sound directionally to the second coordinate data through phased array beamforming technology and broadcast interactive feedback voice.

[0021] The following provides a detailed explanation of each step: S1. Establish a UWB positioning coordinate system and a sound field coordinate system based on the interactive space, and perform spatial joint calibration of the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters: rotation matrix R1 and translation vector T1.

[0022] Specifically, the UWB positioning coordinate system is configured by deploying M UWB positioning base stations in the interaction space, where M ≥ 4, with one of the UWB positioning base stations serving as the origin of the UWB positioning coordinate system.

[0023] Specifically, the sound field coordinate system is configured by deploying multiple speakers in the interactive space, with one of the speakers serving as the origin of the sound field coordinate system.

[0024] Specifically, the UWB positioning coordinate system and the sound field coordinate system are jointly calibrated in space to obtain the transformation parameters: rotation matrix R1 and translation vector T1, specifically: A calibration target is set up in the interactive space, with a reference UWB positioning tag and a reference microphone on it. The calibration target is moved sequentially to multiple preset positions in the interactive space. During this process, multiple tag coordinates P1 calculated by UWB and multiple sound source receiving coordinates P2, which are obtained by transmitting test signals through the sound field generator and receiving them through the reference microphone, are recorded. The tag coordinates and sound source receiving coordinates corresponding to the same preset position are regarded as a coordinate pair. The rotation matrix R1 and translation vector T1 between the UWB positioning coordinate system and the sound field coordinate system are solved by the least squares method, so that P2 = R1 × P1 + T1 holds for all coordinate pairs.

[0025] S2. In the interactive space, the user wears a device with a UWB positioning tag on their hand. Based on the UWB positioning coordinate system and the user's UWB positioning tag, the user's first coordinate data is calculated and obtained in real time.

[0026] Specifically, the user wears a device with a UWB positioning tag on their hand, such as a wristband.

[0027] Specifically, the user's first coordinate data is obtained through real-time calculation, as follows: S21. A neural network model trained using the sequence of experimental raw ranging values ​​from the experimental UWB tag to each UWB positioning base station and the corresponding experimental ranging error correction values ​​as training samples. The model takes the raw ranging values ​​between the user's UWB positioning tag and each UWB positioning base station as input and outputs the corresponding ranging error correction values ​​between the user's UWB positioning tag and each UWB positioning base station. Based on the ranging error correction values, the corrected ranging values ​​between the user's UWB positioning tag and each UWB positioning base station are obtained. S22. Select one of the UWB positioning base stations as the reference base station, and construct a set of time difference of arrival equations using the corrected ranging values: ; This is the corrected ranging value between the user's UWB positioning tag and the i-th UWB positioning base station at time t; This is the corrected ranging value between the user's UWB positioning tag and the reference base station at time t; Let t be the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system at time t; Let be the position coordinates of the i-th UWB positioning base station in the UWB positioning coordinate system; The reference base station's position coordinates in the UWB positioning coordinate system; S23. The user's first coordinate data, i.e., the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system, is obtained by solving the time difference of arrival equation system using the improved chan algorithm.

[0028] In step S21, specifically, the test ranging error correction value is obtained through prior testing, specifically as follows: A test UWB tag is set up to move continuously in the interactive space. During this process, a bilateral bidirectional ranging protocol is used to collect the test raw flight time between the test UWB tag and each UWB positioning base station at a fixed frequency, and convert it into the corresponding test raw ranging value: ; This represents the initial experimental ranging value between the experimental UWB tag and the i-th UWB positioning base station at time t, where c is the speed of light. This represents the original flight time of the test UWB tag and the i-th UWB positioning base station at time t. Obtain the true geometric distance between the test UWB tag and the corresponding UWB positioning base station corresponding to the original ranging value of each test. Based on the original ranging value and the corresponding true geometric distance, obtain the corresponding test ranging error correction value: ; This represents the test ranging error correction value between the test UWB tag and the i-th UWB positioning base station at time t. Let t be the actual geometric distance between the experimental UWB tag and the i-th UWB positioning base station.

[0029] Specifically, in the neural network model, the input data is first processed by a convolutional neural network to extract local features, capturing the spatial correlation between the original ranging values ​​of different UWB positioning base stations. After convolution and pooling operations, a feature map is output. The feature map is then input into a bidirectional long short-term memory network, which includes forward LSTM and backward LSTM. This network can learn the rules of ranging value changes from both directions, thereby effectively identifying and suppressing NLOS noise and outputting a hidden state sequence. The hidden state sequence is then input into an attention layer, and after attention weighting, a context vector is obtained. Finally, the vector is input into a fully connected layer, and the ranging error correction value between the user's UWB positioning tag and each UWB positioning base station is predicted by linear regression.

[0030] In step S23, the user's first coordinate data is obtained by solving the time difference of arrival equations using the improved Chan algorithm, specifically as follows: S231. Define base station coordinate constants for The time difference of arrival equations are converted into matrix form: A is an (M-1)×3 dimensional coefficient matrix composed of the coordinate differences of UWB positioning base stations. Let be the position coordinate vector of the user's UWB positioning tag in the UWB positioning coordinate system at time t. The corrected distance measurement value at time t and base station coordinate constants The constructed (M-1)×1 dimensional observation vector: ; ; ; S232, Analyze the observation vector covariance matrix and with covariance matrix The inverse matrix is ​​used as the first weight matrix. According to the first weight matrix The first weighted least squares solution yields the following result: Minimize the target position coordinate vector , , Let t be the first estimated position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system at time t; Wherein, the covariance matrix : ; diag() is a diagonal matrix with the elements within the parentheses as the main diagonal elements. The variance of the corrected ranging value between the user's UWB positioning tag and the i-th UWB positioning base station at time t; S233, Based on the target position coordinate vector Obtain the second weight matrix : ; S234, According to the second weight matrix The second result vector is obtained by performing a second weighted least squares solution. : ; ; The coefficient matrix, The square of the user's UWB positioning tag's coordinate offset relative to the reference base station. Let be the first result vector at time t. Let t be the second estimated position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system. S235, from the second result vector The second estimated position coordinates were recovered. As the user's current primary coordinate data: ; ; ; ; like ,but ,otherwise ,for and Similarly.

[0031] S3. Obtain the first coordinate data sequence within the latest time period according to step S2, obtain the user's hand movement trajectory within the latest time period according to the first coordinate data sequence, and perform interactive command recognition and matching based on the hand movement trajectory.

[0032] Specifically, the user's hand movement trajectory in the latest time period is obtained based on the first coordinate data sequence. Specifically, the smooth trajectory sequence obtained by smoothing the first coordinate data sequence using Kalman filtering or moving average filtering is used as the user's hand movement trajectory in the latest time period.

[0033] Specifically, the interactive command recognition and matching is performed based on the hand movement trajectory, specifically as follows: Obtain a preset interactive instruction model library, which records the trajectory movement sequence and the final trajectory imaging graphic corresponding to each interactive instruction; Project each coordinate point in the first coordinate data sequence corresponding to the hand movement trajectory onto the same plane, and smoothly connect the projected points according to the order of acquisition of the first coordinate data to obtain the first graphic. Based on the formation order of the hand movement trajectory, the corresponding matching trajectory movement order is selected from the interaction instruction model library. Then, the final image of the trajectory corresponding to the matching trajectory movement order is compared with the first image for similarity analysis. If the similarity is greater than a preset similarity threshold, the corresponding interaction instruction matches the hand movement trajectory.

[0034] S4. Control the corresponding device to complete the interactive command action according to the matched interactive command. At the same time, transform the user's current first coordinate data into the sound field coordinate system according to the rotation matrix R1 and the translation vector T1 to obtain the corresponding second coordinate data. Control each speaker to project sound directionally to the second coordinate data through phased array beamforming technology and broadcast interactive feedback voice.

[0035] Specifically, phased array beamforming technology is used to control each loudspeaker to project sound directionally toward the second coordinate data, as follows: Based on the coordinate positions of each speaker in the sound field coordinate system and the second coordinate data, the straight-line distance from each speaker to the current user is obtained; Based on the stated straight-line distance, calculate the required emission phase for each loudspeaker: ; Let f be the required emission phase for the j-th loudspeaker, f be the carrier frequency of the sound wave emitted by the loudspeaker, and cy be the speed of sound. Let j be the straight-line distance from the j-th speaker to the current user. Preset initial reference phase; Based on the required emission phase of each loudspeaker, each loudspeaker simultaneously emits sound waves that have undergone phase adjustment.

[0036] Each speaker simultaneously emits phase-adjusted sound waves, which interfere as they propagate in space: at the target location, all sound waves are in phase, while in other directions, they are out of phase, canceling each other out and ultimately forming an audible sound focusing area at the user's location, where the user can clearly hear the voice feedback.

[0037] Example 2 See Figure 2 As shown, the present invention also provides a seamless human-computer interaction system integrating UWB and spatial sound field, specifically comprising: The calibration module is used to establish a UWB positioning coordinate system and a sound field coordinate system based on the interactive space, and to perform joint spatial calibration of the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system, including the rotation matrix R1 and the translation vector T1. The calculation module, in the interactive space, uses a device with a UWB positioning tag on the user's hand to calculate and obtain the user's first coordinate data in real time based on the UWB positioning coordinate system and the user's UWB positioning tag; The instruction matching module obtains the first coordinate data sequence within the latest time period, obtains the user's hand movement trajectory within the latest time period based on the first coordinate data sequence, and performs interactive instruction recognition and matching based on the hand movement trajectory. The execution broadcast module controls the corresponding device to complete the interactive command action according to the matched interactive command. At the same time, it transforms the user's current first coordinate data into the sound field coordinate system according to the rotation matrix R1 and the translation vector T1 to obtain the corresponding second coordinate data. Through phased array beamforming technology, it controls each speaker to project sound directionally to the second coordinate data and broadcasts the interactive feedback voice.

[0038] Example 3 The present invention also provides an electronic device, including: a processor, a transmitting device, an input device, an output device, and a memory. The processor may be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory may be implemented using a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), and is used to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0039] Example 4 The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, which, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0040] The beneficial effects of this invention are as follows: This invention uses a trained neural network model, taking the original ranging values ​​between the user's UWB positioning tag and each UWB positioning base station as input, and outputting the ranging error correction values ​​corresponding to the current ranging values ​​between the user's UWB positioning tag and each UWB positioning base station. Based on the ranging error correction values, the corrected ranging values ​​between the user's UWB positioning tag and each UWB positioning base station are obtained. After constructing a system of time difference of arrival equations using the corrected ranging values, the user's first coordinate data is obtained by solving the Chan algorithm, thereby improving the accuracy of UWB positioning and thus enhancing the efficiency and accuracy of interactive command recognition.

[0041] In the description of this specification, the references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0042] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0043] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A seamless human-computer interaction method integrating UWB and spatial sound field, characterized in that, Includes the following steps: S1. Establish a UWB positioning coordinate system and a sound field coordinate system based on the interactive space, and perform spatial joint calibration on the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system, including the rotation matrix R1 and the translation vector T1. S2. In the interactive space, the user wears a device with a UWB positioning tag on their hand. Based on the UWB positioning coordinate system and the user's UWB positioning tag, the user's first coordinate data is calculated and obtained in real time, specifically: S21. A neural network model trained using the sequence of experimental raw ranging values ​​from the experimental UWB tag to each UWB positioning base station and the corresponding experimental ranging error correction values ​​as training samples. The model takes the raw ranging values ​​between the user's UWB positioning tag and each UWB positioning base station as input and outputs the corresponding ranging error correction values ​​between the user's UWB positioning tag and each UWB positioning base station. Based on the ranging error correction values, the corrected ranging values ​​between the user's UWB positioning tag and each UWB positioning base station are obtained. S22. Select one of the UWB positioning base stations as the reference base station, and construct a set of time difference of arrival equations using the corrected ranging values: ； This is the corrected ranging value between the user's UWB positioning tag and the i-th UWB positioning base station at time t; This is the corrected ranging value between the user's UWB positioning tag and the reference base station at time t; Let t be the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system at time t; Let be the position coordinates of the i-th UWB positioning base station in the UWB positioning coordinate system; The reference base station's position coordinates in the UWB positioning coordinate system; S23. The user's first coordinate data, i.e., the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system, is obtained by solving the time difference of arrival equation system through the improved chan algorithm. S3. Obtain the first coordinate data sequence within the latest time period according to step S2, obtain the user's hand movement trajectory within the latest time period according to the first coordinate data sequence, and perform interactive command recognition and matching according to the hand movement trajectory. S4. Control the corresponding device to complete the interactive command action according to the matched interactive command. At the same time, transform the user's current first coordinate data into the sound field coordinate system according to the rotation matrix R1 and the translation vector T1 to obtain the corresponding second coordinate data. Control each speaker to project sound directionally to the second coordinate data through phased array beamforming technology and broadcast interactive feedback voice.

2. The seamless human-computer interaction method integrating UWB and spatial sound field according to claim 1, characterized in that, The UWB positioning coordinate system is specifically defined by deploying at least four UWB positioning base stations in the interaction space, with one of the UWB positioning base stations serving as the origin of the UWB positioning coordinate system. The sound field coordinate system is specifically defined by deploying multiple speakers in the interactive space, with one of the speakers serving as the origin of the sound field coordinate system.

3. The seamless human-computer interaction method integrating UWB and spatial sound field according to claim 1, characterized in that, The spatial joint calibration of the UWB positioning coordinate system and the sound field coordinate system yields the transformation parameters between them, specifically: A calibration target is set up in the interactive space, with a reference UWB positioning tag and a reference microphone on it. The calibration target is moved sequentially to multiple preset positions in the interactive space. During this process, multiple tag coordinates P1 calculated by UWB and multiple sound source receiving coordinates P2, which are obtained by transmitting test signals through the sound field generator and receiving them through the reference microphone, are recorded. The tag coordinates and sound source receiving coordinates corresponding to the same preset position are regarded as a coordinate pair. The rotation matrix R1 and translation vector T1 between the UWB positioning coordinate system and the sound field coordinate system are solved by the least squares method, so that P2 = R1 × P1 + T1 holds for all coordinate pairs.

4. The seamless human-computer interaction method integrating UWB and spatial sound field according to claim 1, characterized in that, The test ranging error correction value was obtained through prior testing, specifically as follows: A test UWB tag is set up to move continuously in the interactive space. During this process, a bilateral bidirectional ranging protocol is used to collect the test raw flight time between the test UWB tag and each UWB positioning base station at a fixed frequency, and convert it into the corresponding test raw ranging value: ； This represents the initial experimental ranging value between the experimental UWB tag and the i-th UWB positioning base station at time t, where c is the speed of light. This represents the original flight time of the test UWB tag and the i-th UWB positioning base station at time t. Obtain the true geometric distance between the test UWB tag and the corresponding UWB positioning base station corresponding to the original ranging value of each test. Based on the original ranging value and the corresponding true geometric distance, obtain the corresponding test ranging error correction value: ； This represents the test ranging error correction value between the test UWB tag and the i-th UWB positioning base station at time t. Let t be the actual geometric distance between the experimental UWB tag and the i-th UWB positioning base station.

5. The seamless human-computer interaction method integrating UWB and spatial sound field according to claim 1, characterized in that, The interaction command recognition and matching is performed based on the hand movement trajectory, specifically as follows: Obtain a preset interactive instruction model library, which records the trajectory movement sequence and the final trajectory imaging graphic corresponding to each interactive instruction; Project each coordinate point in the first coordinate data sequence corresponding to the hand movement trajectory onto the same plane, and smoothly connect the projected points according to the order of acquisition of the first coordinate data to obtain the first graphic. Based on the formation order of the hand movement trajectory, the corresponding matching trajectory movement order is selected from the interaction instruction model library. Then, the final image of the trajectory corresponding to the matching trajectory movement order is compared with the first image for similarity analysis. If the similarity is greater than a preset similarity threshold, the corresponding interaction instruction matches the hand movement trajectory.

6. The seamless human-computer interaction method integrating UWB and spatial sound field according to claim 1, characterized in that, The phased array beamforming technology is used to control each loudspeaker to project sound directionally toward the second coordinate data, specifically: Based on the coordinate positions of each speaker in the sound field coordinate system and the second coordinate data, the straight-line distance from each speaker to the current user is obtained; Based on the stated straight-line distance, calculate the required emission phase for each loudspeaker: ； Let f be the required emission phase for the j-th loudspeaker, f be the carrier frequency of the sound wave emitted by the loudspeaker, and cy be the speed of sound. Let j be the straight-line distance from the j-th speaker to the current user. Preset initial reference phase; Based on the required emission phase of each loudspeaker, each loudspeaker simultaneously emits sound waves that have undergone phase adjustment.

7. A seamless human-computer interaction system integrating UWB and spatial sound field, applied to the seamless human-computer interaction method integrating UWB and spatial sound field as described in any one of claims 1 to 6, characterized in that, include: The calibration module is used to establish a UWB positioning coordinate system and a sound field coordinate system based on the interactive space, and to perform joint spatial calibration of the UWB positioning coordinate system and the sound field coordinate system to obtain the transformation parameters between the UWB positioning coordinate system and the sound field coordinate system, including the rotation matrix R1 and the translation vector T1. The calculation module, in the interactive space, uses a device with a UWB positioning tag on the user's hand to calculate and obtain the user's first coordinate data in real time based on the UWB positioning coordinate system and the user's UWB positioning tag; The instruction matching module obtains the first coordinate data sequence within the latest time period, obtains the user's hand movement trajectory within the latest time period based on the first coordinate data sequence, and performs interactive instruction recognition and matching based on the hand movement trajectory. The execution broadcast module controls the corresponding device to complete the interactive command action according to the matched interactive command. At the same time, it transforms the user's current first coordinate data into the sound field coordinate system according to the rotation matrix R1 and the translation vector T1 to obtain the corresponding second coordinate data. Through phased array beamforming technology, it controls each speaker to project sound directionally to the second coordinate data and broadcasts the interactive feedback voice.

8. The seamless human-computer interaction system integrating UWB and spatial sound field according to claim 7, characterized in that, The UWB positioning coordinate system is specifically defined by deploying at least four UWB positioning base stations in the interaction space, with one of the UWB positioning base stations serving as the origin of the UWB positioning coordinate system. The sound field coordinate system is specifically defined by deploying multiple speakers in the interactive space, with one of the speakers serving as the origin of the sound field coordinate system.

9. A seamless human-computer interaction system integrating UWB and spatial sound field according to claim 7, characterized in that, The spatial joint calibration of the UWB positioning coordinate system and the sound field coordinate system yields the transformation parameters between them, specifically: A calibration target is set up in the interactive space, with a reference UWB positioning tag and a reference microphone on it. The calibration target is moved sequentially to multiple preset positions in the interactive space. During this process, multiple tag coordinates P1 calculated by UWB and multiple sound source receiving coordinates P2, which are obtained by transmitting test signals through the sound field generator and receiving them through the reference microphone, are recorded. The tag coordinates and sound source receiving coordinates corresponding to the same preset position are regarded as a coordinate pair. The rotation matrix R1 and translation vector T1 between the UWB positioning coordinate system and the sound field coordinate system are solved by the least squares method, so that P2 = R1 × P1 + T1 holds for all coordinate pairs.

10. A seamless human-computer interaction system integrating UWB and spatial sound field according to claim 7, characterized in that, The real-time calculation to obtain the user's first coordinate data specifically includes: A neural network model is trained using the sequence of experimental raw ranging values ​​from the UWB tag to each UWB positioning base station and the corresponding experimental ranging error correction values ​​as training samples. The model takes the raw ranging values ​​between the user's UWB positioning tag and each UWB positioning base station as input and outputs the corresponding ranging error correction values ​​between the user's UWB positioning tag and each UWB positioning base station. Based on the ranging error correction values, the corrected ranging values ​​between the user's UWB positioning tag and each UWB positioning base station are obtained. Select one of the UWB positioning base stations as the reference base station, and construct a set of time difference of arrival equations using the corrected ranging values: ； This is the corrected ranging value between the user's UWB positioning tag and the i-th UWB positioning base station at time t; This is the corrected ranging value between the user's UWB positioning tag and the reference base station at time t; Let t be the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system at time t; Let be the position coordinates of the i-th UWB positioning base station in the UWB positioning coordinate system; The reference base station's position coordinates in the UWB positioning coordinate system; The improved Chan algorithm is used to solve the time difference of arrival equations to obtain the user's first coordinate data, that is, the position coordinates of the user's UWB positioning tag in the UWB positioning coordinate system.

Images