A smart home touch panel and a smart home touch system

Abstract

The application relates to the touch control field and discloses a smart home touch control panel and a smart home touch control system, namely the smart home touch control panel comprises a touch film, a touch gesture recognition module and a home material panel, wherein the home material panel is attached to the touch film. In this way, human touch gesture information can be collected, the purpose of controlling associated smart home equipment based on the human touch gesture information is achieved, the home material panel is attached to the touch film, the appearance can be consistent with the wall surface to be embedded or other building surface, the form of the smart home touch control panel can be no longer limited to a 86 type installation box, but can be integrated with the wall surface or other building surface, the overall aesthetic property of the home decoration effect is guaranteed, and the smart home touch control panel is convenient for practical application and popularization.

Description

Technical Field

[0001] This invention belongs to the field of touch technology, specifically relating to a smart home touch panel and a smart home touch system. Background Technology

[0002] As people's living standards continue to improve, smart homes are becoming increasingly common. Smart appliances, in particular, are home appliances that incorporate microprocessors, sensor technology, and network communication technology. They automatically sense the status of the living space, the appliance itself, and its service status, and can automatically control and receive control commands from the user inside or remotely. Furthermore, as a component of a smart home system, smart appliances can interconnect with other appliances, home devices, and facilities to form a unified system and realize smart home functionality. Traditional smart home devices, however, rely on 86-type mounting boxes for their control panels. These boxes are embedded in walls or other building surfaces, resulting in a limited design and adding an extra layer of visual clutter, which can negatively impact the overall aesthetics of the home. Summary of the Invention

[0003] To address the limitations of traditional control panels, such as being confined to the 86-type mounting box, having a relatively simple form factor, and affecting the overall aesthetics of home decoration, this invention aims to provide a novel smart home touch panel and smart home touch system. This system enables control of associated smart home devices based on human touch gestures, while also allowing the smart home touch panel to be integrated into walls or other building surfaces, thus ensuring the overall aesthetic appeal of the home decoration.

[0004] In a first aspect, the present invention provides a smart home touch panel, comprising a touch film, a touch gesture recognition module, and a home material panel, wherein the home material panel is attached to the touch film;

[0005] The touch film is used to sense touch signals generated by hand gestures on the home furnishing material panel;

[0006] The touch gesture recognition module is communicatively connected to the touch film and is used to recognize touch gestures based on touch signals received from the touch film.

[0007] Based on the above invention, not only can human touch gesture information be collected to achieve the purpose of controlling associated smart home devices based on the human touch gesture information, but also, since the home material panel is attached to the touch film, it can maintain a consistent appearance with the wall or other building surface to be embedded. Therefore, the form of the smart home touch panel is no longer limited to the 86-type mounting box, but can be integrated with the wall or other building surface, ensuring the overall aesthetics of the home decoration effect and facilitating practical application and promotion.

[0008] In one possible design, a Universal Asynchronous Receiver / Transmitter (UART) serial port module is also included, which is used to output the touch gesture recognition results.

[0009] In one possible design, the touch film is either a resistive touch film or a capacitive touch film.

[0010] In one possible design, the home material panel is made of leather, wood, PP, PVC, PET, or ARM materials.

[0011] In one possible design, the function of recognizing a touch gesture based on a touch signal received from the touch membrane includes:

[0012] After receiving the first touch signal collected by the touch film, the corresponding first touch point coordinate sequence is obtained by parsing the first touch signal. The first touch signal is presented in the form of a data stream in the time domain, and the first touch point coordinate sequence contains N two-dimensional coordinates of touch points, where N is a natural number greater than 2.

[0013] Based on the first touch point coordinate sequence, a corresponding first slope sequence is obtained, wherein the first slope sequence contains N-1 first slopes, and each of the N-1 first slopes corresponds one-to-one with each pair of adjacent two touch point two-dimensional coordinates in the N touch point two-dimensional coordinates, and each first slope is calculated based on the corresponding adjacent two touch point two-dimensional coordinates.

[0014] For each slope sequence template stored in the template library, the Dynamic Time Warping (DTW) algorithm is used to calculate the corresponding DTW similarity distance with the first slope sequence, wherein the slope sequence template has a corresponding relationship with known touch gestures;

[0015] Among all the calculated DTW similarity distances, the shortest DTW similarity distance is determined;

[0016] Based on the shortest DTW similarity distance, the corresponding known touch gesture is found, and this known touch gesture is used as the touch gesture recognition result.

[0017] Based on the aforementioned possible designs, after receiving the touch signal collected by the touch film, the corresponding slope sequence is first obtained. Then, using DTW similarity distance as a distance metric, template matching is performed between this slope sequence and the slope sequence templates of each known touch gesture. Finally, based on the template matching results, the known touch gesture corresponding to the shortest DTW similarity distance is found, and this known touch gesture is identified as the touch gesture recognition result. This not only ensures the sensitivity of touch gesture recognition and reduces or eliminates the adverse effects of home furnishing material panels adhering to the touch film on recognition sensitivity, but also only requires the deployment of the Dynamic Time Warping (DTW) algorithm and the slope sequence templates of each known touch gesture in the touch gesture recognition module, greatly reducing the demand for computing and storage resources. This allows smart home touch panels to quickly and accurately obtain human touch gesture information, facilitating real-time control of associated smart home devices. Furthermore, when the touch gesture recognition scheme needs to recognize a new touch gesture, it only needs to add the corresponding slope sequence template of that gesture, demonstrating strong scalability and further facilitating practical application and promotion.

[0018] In one possible design, before calculating the corresponding DTW similarity distance with the first slope sequence using the Dynamic Time Warping (DTW) algorithm for each slope sequence template stored in the template library, the following steps are also included:

[0019] For a known touch gesture, a second touch signal is acquired by the touch membrane during the corresponding gesture swiping process, wherein the second touch signal is presented in the form of a data stream in the time domain;

[0020] Based on the second touch signal, the corresponding second touch point coordinate sequence is obtained by parsing, wherein the second touch point coordinate sequence contains M two-dimensional coordinates of touch points, where M is a natural number greater than 2;

[0021] Based on the second touch point coordinate sequence, a corresponding second slope sequence is obtained, wherein the second slope sequence contains M-1 second slopes, each of the M-1 second slopes corresponds one-to-one with each pair of adjacent two touch point two-dimensional coordinates in the M touch point two-dimensional coordinates, and each second slope is calculated based on the corresponding adjacent two touch point two-dimensional coordinates;

[0022] Cluster analysis with DTW similarity distance as the distance metric and a cluster size of S is performed on multiple second slope sequences to obtain clustering results of S clusters, where S is a natural number greater than 2;

[0023] For each cluster in the S cluster, the corresponding cluster center is calculated based on the corresponding clustering result, and the corresponding calculation result is stored in the template library as a slope sequence template corresponding to a certain known touch gesture.

[0024] In one possible design, for each cluster in the S-cluster, the corresponding cluster center is calculated based on the corresponding clustering result, including: for each cluster in the S-cluster, the average sequence of the corresponding clustering result is calculated using the Dynamic Time Warping Centroid Average (DBA) algorithm to obtain the corresponding cluster center.

[0025] In one possible design, based on the shortest DTW similarity distance, the corresponding known touch gesture is found, and this known touch gesture is used as the touch gesture recognition result, including:

[0026] Determine whether the shortest DTW similarity distance is greater than a preset distance threshold;

[0027] If so, the touch gesture recognition result is determined to be a recognition failure message; otherwise, a known touch gesture corresponding to the shortest DTW similarity distance is found, and the known touch gesture is used as the touch gesture recognition result, and the gesture code corresponding to the known touch gesture is output.

[0028] In one possible design, based on the shortest DTW similarity distance, the corresponding known touch gesture is found, and this known touch gesture is used as the touch gesture recognition result, including:

[0029] Find the known touch gesture corresponding to the shortest DTW similarity distance, and determine whether the shortest DTW similarity distance is greater than a preset distance threshold of the known touch gesture. If not, take the known touch gesture as the touch gesture recognition result and output the gesture code corresponding to the known touch gesture.

[0030] In a second aspect, the present invention provides a smart home touch control system, including a scene controller, a WiFi communication module, and a smart home touch control panel as described in the first aspect or any possible design in the first aspect.

[0031] The scene controller is communicatively connected to the smart home touch panel and is used to generate a corresponding execution request message based on the touch gesture recognition result received from the smart home touch panel after receiving the touch gesture recognition result.

[0032] The WiFi communication module is communicatively connected to the scene controller and is used to wirelessly transmit the execution request message to the smart home device or the cloud server so that the smart home device or the cloud server can respond to the execution request message. Attached Figure Description

[0033] 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, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a schematic diagram of the principle structure of the smart home touch panel provided by the present invention.

[0035] Figure 2 This is a schematic diagram of the process for recognizing touch gestures in a smart home touch panel provided by the present invention.

[0036] Figure 3 These are comparative examples of Euclidean distance matching and DTW distance matching provided by the present invention, wherein (a) shows the Euclidean distance matching method and (b) shows the DTW distance matching method.

[0037] Figure 4 This is an example diagram of cluster analysis using DTW similarity distance as a distance metric, provided by the present invention.

[0038] Figure 5 This is a schematic diagram of the application structure of the smart home touch control system provided by the present invention. Detailed Implementation

[0039] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. It should be noted that while the description of these embodiments is intended to aid in understanding the invention, it does not constitute a limitation thereof. The specific structural and functional details disclosed herein are only for describing exemplary embodiments of the invention. However, the invention can be embodied in many alternative forms and should not be construed as being limited to the embodiments described herein.

[0040] It should be understood that although the terms "first" and "second", etc., may be used herein to describe various objects, these objects should not be limited by these terms. These terms are only used to distinguish one object from another. For example, the first object may be referred to as the second object, and similarly, the second object may be referred to as the first object, without departing from the scope of the exemplary embodiments of the invention.

[0041] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, or A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone or A and B exist simultaneously. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0042] like Figure 1 As shown, the smart home touch panel provided in the first aspect of this embodiment includes a touch film, a touch gesture recognition module, and a home material panel, wherein the home material panel is attached to the touch film; the touch film is used to sense touch signals generated by hand gestures on the home material panel; the touch gesture recognition module is communicatively connected to the touch film and is used to recognize touch gestures based on touch signals received from the touch film.

[0043] like Figure 1 As shown, in the specific structure of the smart home touch panel, on the one hand, since the touch film can sense the touch signal generated by the gesture sliding on the home material panel, and the touch gesture recognition module can identify the touch gesture based on the touch signal, such as obtaining the gesture code, the smart home touch panel can collect human touch gesture information by the gesture sliding on the home material panel, thereby achieving the purpose of controlling associated smart home devices based on the human touch gesture information; on the other hand, since the home material panel is attached to the touch film, it can maintain a consistent appearance with the wall or other building surface to be embedded, thus making the form of the smart home touch panel no longer limited to the 86-type mounting box, but can be integrated with the wall or other building surface, ensuring the overall aesthetics of the home decoration effect, and facilitating practical application and promotion.

[0044] Specifically, the smart home touch panel also includes, but is not limited to, a Universal Asynchronous Receiver / Transmitter (UART) serial port module that is communicatively connected to the touch gesture recognition module, wherein the UART serial port module is used to output the touch gesture recognition results. For example... Figure 1 As shown, the design of the UART (Universal Asynchronous Receiver / Transmitter) serial port module can output touch gesture recognition results, such as gesture codes, to facilitate interaction with linked smart home devices or other intermediate node devices.

[0045] Specifically, the touch film can be, but is not limited to, a resistive touch film or a capacitive touch film. More specifically, when the touch film is a resistive touch film, based on the resistive touch principle, to ensure the touch film can sense the touch signal, the furniture material panel needs to have a certain degree of softness and thickness; for example, the furniture material panel is made of leather and has a thickness of 0.5mm. When the touch film is a capacitive touch film, based on the capacitive touch principle, considering that the capacitive sensing range of the capacitive touch film is not just the surface layer, but extends to an area of ​​approximately two centimeters around the film, similarly, to ensure the touch film can sense the touch signal, the furniture material panel needs to be made of a non-electromagnetic shielding material and have a certain thickness; for example, the furniture material panel is made of wood and has a thickness of 0.5mm. In detail, the home furnishing material panel can be made of, but is not limited to, leather, wood, PP (Polypropylene), PVC (Polyvinyl chloride), PET (Polyethylene Terephthalate), or ARM (an existing synthetic material named ARM, generally composed of silicone, PET, and other materials). Furthermore, the touch film and the touch gesture recognition module can also be embedded in wall panels or other building panels (i.e., as the home furnishing material panel) to obtain the smart home touch panel.

[0046] Therefore, based on the aforementioned detailed description of the smart home touch panel, not only can it collect human touch gesture information to achieve the purpose of controlling associated smart home devices based on this human touch gesture information, but also, since the home material panel is attached to the touch film, it can maintain a consistent appearance with the wall or other building surface to be embedded. Thus, the form of the smart home touch panel is no longer limited to the 86-type mounting box, but can be integrated with the wall or other building surface, ensuring the overall aesthetics of the home decoration effect and facilitating practical application and promotion.

[0047] Based on the aforementioned first aspect of the technical solution, this embodiment also provides a possible design for how to specifically identify touch gestures, namely, the method for identifying touch gestures based on touch signals received from the touch membrane, such as... Figure 2 As shown, it includes, but is not limited to, the following steps S1 to S5.

[0048] S1. After receiving the first touch signal collected by the touch film, the corresponding first touch point coordinate sequence is obtained by parsing the first touch signal. The first touch signal is presented in the form of a data stream in the time domain, and the first touch point coordinate sequence contains N two-dimensional coordinates of touch points, where N is a natural number greater than 2.

[0049] In step S1, the first touch signal is the touch signal generated after a certain gesture swipe operation is performed on the home material panel. Therefore, it is presented in the form of a data stream in the time domain, and the corresponding first touch point coordinate sequence can be obtained by parsing the first touch signal based on the conventional resistive / capacitive touch principle.

[0050] S2. Based on the first touch point coordinate sequence, obtain the corresponding first slope sequence, wherein the first slope sequence contains N-1 first slopes, each of the N-1 first slopes corresponds one-to-one with each pair of adjacent two touch point two-dimensional coordinates in the N touch point two-dimensional coordinates, and each first slope is calculated based on the corresponding adjacent two touch point two-dimensional coordinates.

[0051] In step S2, the first slope is the slope of the line segment based on the two-dimensional coordinates of the corresponding two adjacent touch points, so the calculation result can be obtained through conventional calculation methods.

[0052] S3. For each slope sequence template stored in the template library, the Dynamic Time Warping (DTW) algorithm is used to calculate the corresponding DTW similarity distance with the first slope sequence, wherein the slope sequence template has a corresponding relationship with known touch gestures.

[0053] In step S3, the template library is used to pre-store all slope sequence templates corresponding to the known touch gestures. These slope sequence templates serve as a set of sliding trajectory feature sequences for the corresponding known touch gestures. They can be obtained in advance, but are not limited to, based on multiple slope sequences corresponding to the known touch gestures, through clustering analysis using DTW (Dynamic Time Wrapping) similarity distance as the distance metric. Considering that a single slope sequence template is unlikely to be universal, the correspondence between the slope sequence templates and the known touch gestures is preferably a many-to-one relationship, meaning that each known touch gesture can correspond to multiple different slope sequence templates, such as three. The known touch gestures can include, but are not limited to, swipe-up gestures, swipe-down gestures, W-shaped gestures, and / or O-shaped gestures.

[0054] In step S3, the Dynamic Time Warping (DTW) algorithm is an existing method for measuring the similarity between two time series of different lengths (e.g., sequences containing multiple slopes). It has wide applications, primarily in template matching, such as isolated word speech recognition (i.e., identifying whether two speech segments represent the same word), gesture recognition, data mining, and information retrieval. The basic idea of ​​the DTW algorithm is to select an alignment method between points in two sequences that minimizes the sum of differences between all aligned points. Figure 3 A comparative example of Euclidean distance matching and DTW distance matching is given. Euclidean distance aligns points sequentially, thus only handling sequences of equal length. DTW, on the other hand, offers more flexible alignment, allowing for "stretching," "moving," and / or "compressing" to match sequences as closely as possible. The stability of DTW similarity distance has been verified both domestically and internationally, and therefore can be used as a criterion for determining whether the slope sequence template matches the first slope sequence: a shorter DTW similarity distance indicates a higher degree of matching, and vice versa.

[0055] S4. Among all the calculated DTW similarity distances, determine the shortest DTW similarity distance.

[0056] S5. Based on the shortest DTW similarity distance, find the corresponding known touch gesture and use the known touch gesture as the touch gesture recognition result.

[0057] In step S5, the slope sequence template corresponding to the shortest DTW similarity distance is the template that best matches the first slope sequence. Since the slope sequence template corresponds to known touch gestures, it is easy to find the known touch gesture corresponding to the shortest DTW similarity distance and determine this known touch gesture as the gesture recognition result. Optimally, to improve the accuracy of the recognition method, a threshold comparison method can be introduced in step S5. That is, based on the shortest DTW similarity distance, the corresponding known touch gesture is found, and this known touch gesture is used as the touch gesture recognition result, including but not limited to the following steps S51-S52.

[0058] S51. Determine whether the shortest DTW similarity distance is greater than a preset distance threshold.

[0059] S52. If yes, then determine the touch gesture recognition result as recognition failure information; otherwise, find the known touch gesture corresponding to the shortest DTW similarity distance, and use the known touch gesture as the touch gesture recognition result, and output the gesture code corresponding to the known touch gesture.

[0060] In step S51, if the shortest DTW similarity distance is determined to be greater than the preset distance threshold, it is considered that the similarity / matching degree between the first slope sequence and all slope sequence templates is not high, and the known touch gesture corresponding to the shortest DTW similarity distance cannot be determined as the touch gesture recognition result. At this time, the touch gesture recognition result needs to be determined as recognition failure information so as to be output as a recognition result.

[0061] Therefore, based on the touch gesture recognition scheme described in steps S1 to S5 above, after receiving the touch signal collected by the touch film, the corresponding slope sequence is first processed. Then, using DTW similarity distance as a distance metric, template matching is performed between this slope sequence and the slope sequence templates of each known touch gesture. Finally, based on the template matching results, the known touch gesture corresponding to the shortest DTW similarity distance is found, and this known touch gesture is determined as the touch gesture recognition result. This not only ensures the sensitivity of touch gesture recognition and reduces or eliminates the adverse effects of home material panels being attached to the touch film on recognition sensitivity, but also only requires the deployment of the Dynamic Time Warping (DTW) algorithm and the slope sequence templates of each known touch gesture in the touch gesture recognition module, greatly reducing the demand for computing and storage resources. This allows smart home touch panels to quickly and accurately obtain human touch gesture information, facilitating real-time control of associated smart home devices. Furthermore, when the touch gesture recognition scheme needs to recognize a new touch gesture, it only needs to add the corresponding slope sequence template of that gesture, which has strong scalability and further facilitates practical application and promotion.

[0062] Based on the aforementioned possible design one technical solution, this embodiment also provides a possible design two for how to obtain multiple slope sequence templates of known touch gestures. That is, before calculating the corresponding dynamic time warping (DTW) similarity distance with the first slope sequence for each slope sequence template stored in the template library, the following steps S301 to S305 are included, but are not limited to.

[0063] S301. For a known touch gesture, acquire a second touch signal collected by the touch film during the corresponding gesture swiping process, wherein the second touch signal is presented in the form of a data stream in the time domain.

[0064] In step 301, the second touch signal is the touch signal generated after a sliding operation corresponding to a known touch gesture is performed on the home furnishing material panel, and therefore it is presented as a data stream in the time domain. Furthermore, to enrich the sample size for subsequent cluster analysis, the aforementioned sliding operation can be performed multiple times on the home furnishing material panel to obtain multiple second touch signals.

[0065] S302. Based on the second touch signal, the corresponding second touch point coordinate sequence is parsed, wherein the second touch point coordinate sequence contains M two-dimensional coordinates of touch points, and M is a natural number greater than 2.

[0066] In step S302, the corresponding second touch point coordinate sequence can also be obtained by parsing the second touch signal based on the conventional resistive / capacitive touch principle.

[0067] S303. Based on the second touch point coordinate sequence, obtain the corresponding second slope sequence, wherein the second slope sequence contains M-1 second slopes, each of the M-1 second slopes corresponds one-to-one with each pair of adjacent two touch point two-dimensional coordinates in the M touch point two-dimensional coordinates, and each second slope is calculated based on the corresponding adjacent two touch point two-dimensional coordinates.

[0068] In step S303, the second slope is the slope of the line segment based on the two-dimensional coordinates of the corresponding two adjacent touch points, so the calculation result can also be obtained through conventional calculation methods.

[0069] S304. Perform cluster analysis on multiple second slope sequences with DTW similarity distance as the distance metric and a cluster number of S, to obtain the clustering result of S clusters, where S is a natural number greater than 2.

[0070] In step S304, the cluster analysis may, but is not limited to, using existing K-means clustering algorithms, such as... Figure 4 As shown. Additionally, S can be 3 for example.

[0071] S305. For each cluster in the S cluster, calculate the corresponding cluster center according to the corresponding clustering result, and store the corresponding calculation result as a slope sequence template corresponding to a certain known touch gesture in the template library.

[0072] In step S305, specifically, for each cluster in the S cluster, the corresponding cluster center is calculated based on the corresponding clustering result, including but not limited to: for each cluster in the S cluster, the Dynamic Time Warping Barycenter Averaging (DTW) algorithm is used to calculate the average sequence of the corresponding clustering result to obtain the corresponding cluster center. The DBA (DTW Barycenter Averaging) algorithm is a centroid averaging based on DTW, which is also an averaging method consistent with dynamic time warping. It is also an iterative process. Each iteration will execute the following two steps: (1) Calculate the DTW similarity distance between each individual time series and the temporary average sequence to be refined, and find the relationship between the coordinates of the average sequence and the coordinates of the time series set; (2) Update each coordinate of the average sequence to the mean (centroid) of the associated coordinates, and continue to execute the previous step (1).

[0073] Therefore, based on the possible design two described in steps S301 to S305 above, multiple slope sequences corresponding to known touch gestures can be obtained in advance, and multiple slope sequence templates can be obtained through cluster analysis using DTW similarity distance as the distance metric, so as to ensure the accuracy of subsequent touch gesture recognition results.

[0074] Based on the aforementioned possible design one, this embodiment also provides another possible design three that introduces threshold comparison in the post-processing stage. Specifically, based on the shortest DTW similarity distance, a corresponding known touch gesture is found, and this known touch gesture is used as the touch gesture recognition result. This includes, but is not limited to: finding a known touch gesture corresponding to the shortest DTW similarity distance, and determining whether the shortest DTW similarity distance is greater than a preset distance threshold for the known touch gesture. If not, the known touch gesture is used as the touch gesture recognition result, and the gesture code corresponding to the known touch gesture is output. Since the slope data amplitude range of different touch gestures is different, different thresholds can be set for different touch gestures, and different threshold comparisons can be performed to further improve recognition accuracy. Furthermore, if it is determined that the shortest DTW similarity distance is greater than the preset distance threshold for the known touch gesture, the shortest DTW similarity distance corresponding to another known touch gesture can be determined from all calculated DTW similarity distances, and then the threshold comparison is performed again. If it is still not possible to determine a known touch gesture, the touch gesture recognition result can be determined as recognition failure information.

[0075] Therefore, based on the aforementioned possible design three, different thresholds can be set for different touch gestures, and different threshold comparisons can be performed to further improve recognition accuracy.

[0076] like Figure 5As shown, the second aspect of this embodiment provides a smart home touch control system based on the first aspect or any possible design of the smart home touch panel, including a scene controller, a WiFi communication module, and the smart home touch panel as described in the first aspect or any possible design of the first aspect; the scene controller is communicatively connected to the smart home touch panel and is used to generate a corresponding execution request message based on the touch gesture recognition result received from the smart home touch panel after receiving the touch gesture recognition result; the WiFi communication module is communicatively connected to the scene controller and is used to wirelessly transmit the execution request message to a smart home device or a cloud server so that the smart home device or the cloud server can respond to the execution request message.

[0077] In the specific structure of the smart home touch control system, the scene controller is an existing controller. The specific way in which it generates the corresponding execution request message based on the touch gesture recognition result can be, but is not limited to, generating an execution request message for executing the corresponding smart home device action based on a preset mapping relationship between various touch gestures and various smart home device actions. The scene controller can be, but is not limited to, implemented using a single-chip microcomputer of model CA51F3 and its peripheral circuits. The WiFi communication module may, but is not limited to, use a low-power embedded Wi-Fi module of model WR3, which is a low-power embedded Wi-Fi module developed by Tuya Smart. It consists of a highly integrated wireless radio frequency chip RTL8710BN and an external flash chip. It has a built-in Wi-Fi network protocol stack and rich library functions, and also includes low-power ARMCM4F, WLAN MAC and 1T1R WLAN. The maximum main frequency is 125MHz. It has 256K SRAM, 2Mbyte flash and rich peripheral resources. Since it is an RTOS (Real Time Operating System) platform, it integrates all Wi-Fi MAC and TCP / IP protocol function libraries. Therefore, users can develop embedded Wi-Fi products that meet their own needs based on these. This allows the control device in this embodiment to use the Tuya system platform to control smart home devices through devices such as smartphone APP / Tuya series control panels (i.e., as external devices). Furthermore, the specific manner in which the cloud server responds to the execution request message may include, but is not limited to, performing conventional message processing after receiving the execution request message and then sending it to the controlled smart home device (e.g., Figure 5 The smart home device (such as smart home device A or smart home device B) sends corresponding control commands to achieve remote control; while the smart home device can also directly respond to the execution request message (as a control command) to achieve local control.

[0078] The working process, working details and technical effects of the aforementioned smart home touch system provided in the second aspect of this embodiment can be found in the first aspect or any possible design of the smart home touch panel described in the first aspect, and will not be repeated here.

[0079] Finally, it should be noted that this invention is not limited to the optional embodiments described above, and anyone can derive other various forms of products under the guidance of this invention. The specific embodiments described above should not be construed as limiting the scope of protection of this invention, which should be determined by the claims, and the specification can be used to interpret the claims.

Claims

1. A smart home touch panel, characterized in that, It includes a touch film, a touch gesture recognition module, and a home furnishing material panel, wherein the home furnishing material panel is attached to the touch film; The touch film is used to sense touch signals generated by hand gestures on the home furnishing material panel; The touch gesture recognition module is communicatively connected to the touch film and is used to recognize touch gestures based on touch signals received from the touch film, including the following steps: After receiving the first touch signal collected by the touch film, the corresponding first touch point coordinate sequence is obtained by parsing the first touch signal. The first touch signal is presented in the form of a data stream in the time domain, and the first touch point coordinate sequence contains N two-dimensional coordinates of touch points, where N is a natural number greater than 2. Based on the first touch point coordinate sequence, a corresponding first slope sequence is obtained, wherein the first slope sequence contains N-1 first slopes, and each of the N-1 first slopes corresponds one-to-one with each pair of adjacent two touch point two-dimensional coordinates in the N touch point two-dimensional coordinates, and each first slope is calculated based on the corresponding adjacent two touch point two-dimensional coordinates. For each slope sequence template stored in the template library, the Dynamic Time Warping (DTW) algorithm is used to calculate the corresponding DTW similarity distance with the first slope sequence, wherein the slope sequence template has a corresponding relationship with known touch gestures; Among all the calculated DTW similarity distances, the shortest DTW similarity distance is determined; Based on the shortest DTW similarity distance, the corresponding known touch gesture is found, and the known touch gesture is used as the touch gesture recognition result. Specifically, this includes: determining whether the shortest DTW similarity distance is greater than a preset distance threshold; if so, the touch gesture recognition result is determined to be recognition failure information; otherwise, the known touch gesture corresponding to the shortest DTW similarity distance is found, and the known touch gesture is used as the touch gesture recognition result, and the gesture code corresponding to the known touch gesture is output. Before calculating the corresponding DTW similarity distance with the first slope sequence for each slope sequence template stored in the template library using the Dynamic Time Warping (DTW) algorithm, the method further includes: for a known touch gesture, acquiring a second touch signal collected by the touch membrane during the corresponding gesture swiping process, wherein the second touch signal is presented as a data stream in the time domain; parsing the second touch signal to obtain the corresponding second touch point coordinate sequence, wherein the second touch point coordinate sequence contains M two-dimensional coordinates of touch points, where M is a natural number greater than 2; obtaining the corresponding second slope sequence based on the second touch point coordinate sequence, wherein... The second slope sequence contains M-1 second slopes, each of which corresponds one-to-one with each pair of adjacent two-dimensional coordinates of the M touch points. Each second slope is calculated based on the corresponding two-dimensional coordinates of the adjacent two touch points. Cluster analysis with DTW similarity distance as the distance metric and a cluster size of S is performed on the multiple second slope sequences to obtain S clusters, where S is a natural number greater than 2. For each cluster in the S clusters, the corresponding cluster center is calculated based on the corresponding clustering result, and the corresponding calculation result is stored in the template library as a slope sequence template corresponding to a certain known touch gesture.

2. The smart home touch panel as described in claim 1, characterized in that, It also includes a Universal Asynchronous Receiver / Transmitter (UART) serial port module that is connected to the touch gesture recognition module, wherein the UART serial port module is used to output the touch gesture recognition results.

3. The smart home touch panel as described in claim 1, characterized in that, The touch film is either a resistive touch film or a capacitive touch film.

4. The smart home touch panel as described in claim 1, characterized in that, The home furnishing material panels are made of leather, wood, PP, PVC, PET, or ARM materials.

5. The smart home touch panel as described in claim 1, characterized in that, For each cluster in the S-cluster, the corresponding cluster center is calculated based on the corresponding clustering result, including: for each cluster in the S-cluster, the average sequence of the corresponding clustering result is calculated using the Dynamic Time Warping Centroid Average (DBA) algorithm to obtain the corresponding cluster center.

6. A smart home touch control system, characterized in that, It includes a scene controller, a WiFi communication module, and a smart home touch panel as described in any one of claims 1 to 5; The scene controller is communicatively connected to the smart home touch panel and is used to generate a corresponding execution request message based on the touch gesture recognition result received from the smart home touch panel after receiving the touch gesture recognition result. The WiFi communication module is communicatively connected to the scene controller and is used to wirelessly transmit the execution request message to the smart home device or the cloud server so that the smart home device or the cloud server can respond to the execution request message.

Images