A wake-up system and method based on a smart speaker

Abstract

The present invention relates to the technical field of audio wake-up, and specifically discloses a wake-up system and method based on an intelligent audio, including the following steps: Step 1: Obtain the target wireless device distance reflecting the distance between the user and the intelligent audio by detecting the signal strength of the target wireless device worn by the user; Step 2: Based on the target wireless device distance, preset a first distance threshold and a second distance threshold, so as to evaluate the relative position relationship between the user and the intelligent audio, and accordingly determine the working state of the intelligent audio; The present invention not only improves the user experience, but also deeply considers the diversity of the user's movement state and environmental differences, and optimizes the setting of the second distance threshold through historical data analysis, ensuring that the intelligent audio can be timely awakened when the user approaches.

Description

Technical Field

[0001] The present invention relates to the technical field of audio wake-up, and specifically relates to a wake-up system and method based on a smart speaker. Background Art

[0002] With the rapid development of smart home technology, smart speakers have become an indispensable part of family life. However, the wake-up mechanisms of existing smart speakers are mostly limited to fixed voice commands or preset wake-up scenarios, lacking a keen insight into and flexible response to the dynamic changes in the user's spatial position. Specifically, when the distance between the user and the smart speaker exceeds its preset sensitive range (i.e., the second distance threshold), the speaker cannot respond immediately, and the user often has to wait for a period of time until the speaker is awakened from sleep, thus affecting the user experience. Therefore, the concept of the second distance threshold needs to be introduced, aiming to optimize the wake-up logic of the smart speaker through more refined distance perception, so as to better serve the actual needs of users. Summary of the Invention

[0003] The purpose of the present invention is to provide a wake-up system and method based on a smart speaker to solve at least one of the above-mentioned problems in the prior art.

[0004] In a first aspect, the present invention provides a wake-up method based on a smart speaker, including the following steps:

[0005] Step 1: By detecting the signal strength of the target wireless device worn by the user, obtain the target wireless device distance reflecting the distance between the user and the smart speaker;

[0006] Step 2: Based on the target wireless device distance, preset a first distance threshold and a second distance threshold, thereby evaluating the relative position relationship between the user and the smart speaker, and determining the working state of the smart speaker accordingly;

[0007] Among them, the setting process of the second distance threshold is as follows:

[0008] Preset threshold analysis points, and extract the time required for the user to reach the first distance threshold from the threshold analysis points to obtain the user walking time. Compare and analyze the user walking time with the smart speaker wake-up time. If the user walking time is equal to the smart speaker wake-up time, mark the user walking time as the wake-up preparation threshold time, and mark the threshold analysis point as the second distance threshold point. Set the distance from the second distance threshold point to the smart speaker as the second distance threshold.

[0009] In a second aspect, the present invention provides a wake-up system based on a smart speaker, and the system includes:

[0010] Distance detection module: By detecting the signal strength of the target wireless device worn by the user, the distance of the target wireless device reflecting the distance between the user and the smart speaker is obtained;

[0011] Status regulation module: Based on the distance of the target wireless device, a first distance threshold and a second distance threshold are preset, so as to evaluate the relative position relationship between the user and the smart speaker, and accordingly determine the working status of the smart speaker;

[0012] Second distance threshold setting sub-module: Preset the threshold analysis point, and extract the time required for the user to reach the first distance threshold from the threshold analysis point to obtain the user walking time. Compare and analyze the user walking time with the smart speaker wake-up time. If the user walking time is equal to the smart speaker wake-up time, mark the user walking time as the wake-up preparation threshold time, and mark the threshold analysis point as the second distance threshold point. The distance from the second distance threshold point to the smart speaker is set as the second distance threshold.

[0013] Advantages of the present invention:

[0014] By real-time monitoring the signal strength between the target wireless device worn by the user and the smart speaker, the present invention intelligently evaluates the relative position relationship between the user and the smart speaker, and dynamically adjusts the working status of the smart speaker accordingly. This not only improves the user experience, but also deeply considers the diversity of the user's moving state and environmental differences. By analyzing historical data to optimize the setting of the second distance threshold, it ensures that the smart speaker can be woken up in time when the user approaches. In particular, for the path areas that the user often walks, the present invention adopts refined path analysis and speed stability evaluation to estimate and set a more accurate wake-up preparation threshold time, further enhancing the timeliness and accuracy of the smart speaker's response. Description of the drawings

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0016] Figure 1 It is a flowchart of a wake-up method based on a smart speaker provided in Embodiment 1 of the present invention;

[0017] Figure 2 It is a schematic structural diagram of a wake-up system based on a smart speaker provided in Embodiment 2 of the present invention;

[0018] Figure 3 It is a schematic structural diagram of a wake-up device based on a smart speaker provided in Embodiment 3 of the present invention. Detailed Implementation Manner

[0019] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0020] Embodiment 1

[0021] Figure 1 The figure is a flowchart of a wake-up method based on a smart speaker provided in Embodiment 1 of the present invention. The embodiments of the present invention are applicable to a situation of waking up based on a smart speaker. The wake-up method based on a smart speaker can be executed by a wake-up system based on a smart speaker. The wake-up system based on a smart speaker can be implemented by software and / or hardware, and the wake-up system based on a smart speaker can be configured in a wake-up device based on a smart speaker. Optionally, a wake-up device based on a smart speaker can be an electronic device, and the electronic device can be a notebook, a desktop computer, a smart tablet, etc. The embodiments of the present invention do not limit this.

[0022] The wake-up method based on a smart speaker provided in the embodiments of the present invention specifically includes the following steps:

[0023] Step 1: By detecting the signal strength of the target wireless device worn by the user, obtain the distance of the target wireless device reflecting the distance between the user and the smart speaker;

[0024] In some implementation schemes, based on the signal strength detection period, extract the signal strength of the current target wireless device through the target wireless device currently worn by the user, and mark it as the signal strength value;

[0025] It should be explained that the signal strength detection period can be: 1 second, 2 seconds; the target wireless device includes but is not limited to: wireless earphones;

[0026] Through the formula: , calculate to obtain the distance d of the target wireless device, where RSSI is the signal strength value, abs() is the absolute value function, A is the signal strength threshold, and n is the environmental attenuation factor;

[0027] It should be noted that RSSI is related to the received power, with the unit of dBm, usually negative, reflecting the signal attenuation degree. In the ideal state without attenuation, RSSI = 0dBm. However, in actual situations, even when the target wireless device is very close, the RSSI is only -50dBm. During the transmission process, there is attenuation, and different RSSI values can be obtained. The relative distance can be calculated according to the conversion formula. The formula is as follows: , where d is the distance of the target wireless device, RSSI is the signal strength value, abs( ) is the absolute value function, A is the signal strength threshold (the signal strength threshold is the signal strength when the smart speaker and the target wireless device are one meter apart), and n is the environmental attenuation factor. Since the environment is different and the corresponding parameter values of the target wireless device are different, when the smart speaker is connected to different target wireless devices, each parameter in the formula needs to be calibrated according to actual needs to determine the environmental attenuation factor;

[0028] Step 2: Based on the distance of the target wireless device, preset the first distance threshold and the second distance threshold, so as to evaluate the relative position relationship between the user and the smart speaker, and determine the working state of the smart speaker accordingly;

[0029] Preset the first distance threshold and the second distance threshold, and compare and analyze the distance of the target wireless device with the first distance threshold and the second distance threshold respectively;

[0030] If the distance of the target wireless device is less than or equal to the first distance threshold, it means that the distance between the target wireless device and the smart speaker is relatively close, then a wake-up signal is generated to wake up the smart speaker, that is, the smart speaker is switched from the screen saver mode to the working mode, so that the user can perform relevant operations based on the display interface of the smart speaker;

[0031] If the distance of the target wireless device is greater than the first distance threshold and less than or equal to the second distance threshold respectively, it means that the distance between the target wireless device and the smart speaker is moderate, then the current movement state of the user is analyzed, and based on the analysis result, a wake-up signal or a sleep signal is generated;

[0032] If the distance of the target wireless device is greater than the second distance threshold, it means that the distance between the target wireless device and the smart speaker is relatively far, then a sleep signal is generated to switch the smart speaker from the working mode to the screen saver mode;

[0033] Specifically, the process of analyzing the current movement state of the user and generating a wake-up signal or a sleep signal based on the analysis result is as follows:

[0034] Based on the chronological order of the signal strength detection periods within the historical target time period, sort the distances of the target wireless device obtained in each signal strength detection period;

[0035] If the sorted values of the distances of the target wireless devices are in a decreasing state, it is determined that the current user's movement state is a approaching state, that is, a wake-up signal is generated;

[0036] If the sorted values of the distances of the target wireless devices are in an increasing state, it is determined that the current user's movement state is a moving-away state, that is, a sleep signal is generated;

[0037] It should be explained that the historical target period includes multiple signal strength detection cycles, and the historical target period can be 5 seconds, 10 seconds;

[0038] Second, specifically, the process of setting the second distance threshold is as follows:

[0039] It should be explained that when setting the second distance threshold, the time required for the user to walk from this threshold to the first distance threshold should be considered to ensure that the smart speaker has been awakened before the user reaches the closer distance (the first distance threshold), thereby improving the user experience and preventing the user from having to wait for it to wake up when approaching the smart speaker;

[0040] Based on taking the smart speaker as the origin, a three-dimensional coordinate system is established. The preset position of the user in the three-dimensional coordinate system is set as the threshold analysis point. The time required for the user to reach the first distance threshold from the threshold analysis point is extracted to obtain the user walking time. The user walking time is compared and analyzed with the smart speaker wake-up time. If the user walking time is equal to the smart speaker wake-up time, the user walking time is marked as the wake-up preparation threshold time, and the threshold analysis point is marked as the second distance threshold point. The distance from the second distance threshold point to the smart speaker is set as the second distance threshold;

[0041] It should be explained that for the threshold analysis points in different directions and positions, due to factors such as individual differences, environmental differences (such as stairs, elevators, corridors, etc.), and paths (the user may not move in a straight line when moving from the threshold analysis point to the first distance threshold) of the user's movement speed, the required walking times may vary. Therefore, the second distance threshold points in different directions and positions may not show a regular distribution, that is, the second distance threshold may be different in different directions;

[0042] Among them, the process of obtaining the wake-up preparation threshold time is as follows:

[0043] Extract the positions of each distance detection point in the historical data, and based on the positions of each distance detection point and the user's movement direction, obtain multiple historical paths;

[0044] Based on any one of the historical paths, mark the area within all the path thresholds of the historical path as the preset path area, extract the number of historical paths within the preset path area range, and calculate the ratio with the total number of all historical paths to obtain the path stability ratio;

[0045] Preset a path stability ratio threshold, and conduct a comparative analysis of the path stability ratio and the path stability ratio threshold;

[0046] If the path stability ratio is less than or equal to the path stability ratio threshold, it indicates that the preset path area corresponding to this path stability ratio is a path area that users do not often walk, and mark this preset path area as an unstable path area;

[0047] If the path stability ratio is greater than the path stability ratio threshold, it indicates that the preset path area corresponding to this path stability ratio is a path area that users often walk, and mark this preset path area as a stable path area;

[0048] First exemplarily, if the threshold analysis point is in an unstable path area, in the historical data, extract the historical path that passes through the threshold analysis point and has the shortest wake-up device time (the wake-up device time is the time used by the user from the threshold analysis point to the first distance threshold), and mark the wake-up device time of this historical path as the wake-up preparation threshold time;

[0049] Second exemplarily, if the threshold analysis point is in a stable path area, in the historical data, extract all historical paths within this stable path area, mark them as threshold analysis paths, and extract the wake-up device time of each threshold analysis path;

[0050] Evaluate the stability of the wake-up device time of each threshold analysis path, specifically:

[0051] Sort all the wake-up device times of the threshold analysis paths in ascending order of values, and extract the first quartile value and the third quartile value in the sorting to obtain the first quartile wake-up device time and the third quartile wake-up device time. Calculate the difference between the first quartile wake-up device time and the third quartile wake-up device time to obtain a stability characterization value;

[0052] Preset a stability characterization threshold, and conduct a comparative analysis of the stability characterization value and the stability characterization threshold;

[0053] If the stability characterization value is less than or equal to the stability characterization threshold, it indicates that the wake-up device times of each threshold analysis path are relatively stable, and mark the first quartile value as the wake-up preparation threshold time;

[0054] If the stability characterization value is greater than the stability characterization threshold, it indicates that the wake-up device times of each threshold analysis path are relatively unstable. Then conduct a section analysis of the stable path area to determine the walking speed stable sub-area and the walking speed unstable sub-area, so as to estimate the wake-up characterization time of this stable path area, and mark the wake-up characterization time as the wake-up preparation threshold time;

[0055] Among them, the specific process of performing road section analysis on the stable path area, determining the walking speed stable sub-areas and walking speed unstable sub-areas, and thus estimating the wake-up representation time of the stable path area and marking the wake-up representation time as the wake-up preparation threshold time is as follows:

[0056] Based on all distance detection points in the stable path area, obtain the walking sub-speeds of the distance detection points in each distance detection period;

[0057] It should be explained that the walking sub-speed is calculated based on the distance between the distance detection points of the previous detection period corresponding to this distance detection period and the distance detection points of this distance detection period, as well as the time interval from the previous detection period to this distance detection period;

[0058] Based on any one distance detection point, sort all the walking sub-speeds of the distance detection point according to the magnitude of the values, and extract the first quartile value and the third quartile value of the sorting to obtain the first quartile walking sub-speed and the third quartile walking sub-speed, and calculate the difference between the first quartile walking sub-speed and the third quartile walking sub-speed to obtain the stability coefficient;

[0059] Preset a stability coefficient threshold, and conduct a comparative analysis of the stability coefficient and the stability coefficient threshold;

[0060] If the stability coefficient is less than or equal to the stability coefficient threshold, it indicates that in the historical data, the user's walking speed at the distance detection point corresponding to this stability coefficient is relatively stable, and this distance detection point is marked as a speed stable detection point;

[0061] If the stability coefficient is greater than the stability coefficient threshold, it indicates that in the historical data, the user's walking speed at the distance detection point corresponding to this stability coefficient is relatively unstable, and this distance detection point is marked as a speed unstable detection point;

[0062] Based on all the speed stable detection points and speed unstable detection points in the stable path area, divide the stable path area to obtain several walking speed stable sub-areas and walking speed unstable sub-areas;

[0063] Extract the central path of the stable path area to obtain the central identification path, and based on each walking speed stable sub-area and walking speed unstable sub-area passed by the central identification path, obtain the wake-up representation time, and mark the wake-up representation time as the wake-up preparation threshold time;

[0064] It should be noted that the walking speed in the stable walking speed sub-region is the mean value of the first quartile walking sub-speeds of all speed stable detection points in the stable walking speed sub-region; the walking speed in the unstable walking speed sub-region is the first quartile value of the first quartile walking sub-speeds of all speed stable detection points in the unstable walking speed sub-region.

[0065] The technical solution of the embodiment of the present invention is mainly as follows: by real-time monitoring the signal strength between the target wireless device worn by the user and the smart speaker, calculating the relative distance between the user and the smart speaker, and based on this distance information, presetting a first distance threshold and a second distance threshold to intelligently evaluate the relative position relationship between the user and the smart speaker, and dynamically adjusting the working state of the smart speaker accordingly; in addition, the present invention also deeply considers the diversity of the user's movement state and environmental differences, optimizes the setting of the second distance threshold through historical data analysis, ensures that the smart speaker can be woken up in time when the user approaches, and improves the user experience. In particular, for the path area where the user often walks, the present invention adopts refined path analysis and speed stability evaluation to estimate and set a more accurate wake-up preparation threshold time, further enhancing the timeliness and accuracy of the smart speaker's response.

[0066] Embodiment 2

[0067] On the basis of Embodiment 1, please refer to Figure 2 As shown, a wake-up system based on a smart speaker according to an embodiment of the present invention includes:

[0068] Distance detection module: By detecting the signal strength of the target wireless device worn by the user, obtaining the target wireless device distance reflecting the distance between the user and the smart speaker;

[0069] State regulation module: Based on the target wireless device distance, presetting a first distance threshold and a second distance threshold, thereby evaluating the relative position relationship between the user and the smart speaker, and determining the working state of the smart speaker accordingly;

[0070] Second distance threshold setting sub-module: Presetting threshold analysis points, extracting the time required for the user to reach the first distance threshold from the threshold analysis points, obtaining the user walking time, comparing and analyzing the user walking time with the smart speaker wake-up time. If the user walking time is equal to the smart speaker wake-up time, marking the user walking time as the wake-up preparation threshold time, marking the threshold analysis point as the second distance threshold point, and setting the distance from the second distance threshold point to the smart speaker as the second distance threshold.

[0071] Embodiment 3

[0072] Refer to Figure 3, an embodiment of the present invention further provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements a wake-up method based on a smart speaker as described in any one of the above methods.

[0073] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand that

[0074] Figure 3 These are merely examples of the computer device 3 and do not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0075] The so-called processor 301 may be a central processing unit (CPU), and the processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0076] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or will be output.

[0077] Example 4

[0078] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements a wake-up method based on a smart speaker as described in any one of the above methods.

[0079] In this embodiment, if the integrated unit is implemented in the form of 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, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0080] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0081] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0082] In the embodiments disclosed in the present application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another

[0083] point is that the displayed or discussed coupling, direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0084] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0086] The above has described an embodiment of the present invention in detail, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A wake-up method based on a smart speaker, characterized in that, It includes the following steps: Step 1: Obtain the distance of the target wireless device, which reflects the distance between the user and the smart speaker, by detecting the signal strength of the target wireless device worn by the user; Step 2: Based on the distance of the target wireless device, preset a first distance threshold and a second distance threshold, so as to evaluate the relative position relationship between the user and the smart speaker, and determine the working state of the smart speaker accordingly; Among them, the setting process of the second distance threshold is as follows: Preset the threshold analysis point, and extract the time required for the user to reach the first distance threshold from the threshold analysis point to obtain the user walking time. Compare and analyze the user walking time with the smart speaker wake-up time. If the user walking time is equal to the smart speaker wake-up time, mark the user walking time as the wake-up preparation threshold time, and mark the threshold analysis point as the second distance threshold point. The distance from the second distance threshold point to the smart speaker is set as the second distance threshold; The process of obtaining the wake-up preparation threshold time is as follows: Extract the positions of each distance detection point in the historical data to obtain multiple historical paths; Preset a path area, calculate the ratio of the number of historical paths within the preset path area to the total number of all historical paths to obtain the path stability ratio; Based on the path stability ratio, mark the preset path area as an unstable path area or a stable path area; If the threshold analysis point is in the unstable path area, extract the historical path that passes through the threshold analysis point and has the shortest wake-up device time, and mark the wake-up device time of this historical path as the wake-up preparation threshold time; If the threshold analysis point is in the stable path area, extract all historical paths within this stable path area in the historical data, mark them as threshold analysis paths, and extract the wake-up device times of each threshold analysis path; Evaluate the stability of the wake-up device times of each threshold analysis path, and obtain the wake-up preparation threshold time based on the stability of the wake-up device times of each threshold analysis path.

2. The wake-up method based on a smart speaker according to claim 1, wherein, The process of presetting a first distance threshold and a second distance threshold based on the distance of the target wireless device, so as to evaluate the relative position relationship between the user and the smart speaker, and determine the working state of the smart speaker accordingly is as follows: Preset a first distance threshold and a second distance threshold, and compare and analyze the distance of the target wireless device with the first distance threshold and the second distance threshold respectively; If the distance of the target wireless device is less than or equal to the first distance threshold, generate a wake-up signal and wake up the smart speaker, that is, transfer the smart speaker from the screensaver mode to the working mode; If the distance of the target wireless device is greater than the first distance threshold and less than or equal to the second distance threshold respectively, analyze the current movement state of the user, and generate a wake-up signal or a sleep signal based on the analysis result; If the distance of the target wireless device is greater than the second distance threshold, generate a sleep signal and transfer the smart speaker from the working mode to the screensaver mode.

3. The wake-up method based on a smart speaker according to claim 2, wherein The process of analyzing the current movement state of the user and generating a wake-up signal or a sleep signal based on the analysis result is as follows: Sort the distances of the target wireless device obtained in each signal strength detection period; If the values of the distances of the sorted target wireless devices are in a decreasing state, it is determined that the current moving state of the user is a approaching state, that is, a wake-up signal is generated. If the values of the distances of the sorted target wireless devices are in an increasing state, it is determined that the current moving state of the user is a leaving state, that is, a sleep signal is generated.

4. A wake-up method based on a smart speaker according to claim 1, characterized in that The process of marking a preset path area as an unstable path area or a stable path area based on the path stability ratio is as follows: A preset path stability ratio threshold is set, and the path stability ratio is compared and analyzed with the path stability ratio threshold. If the path stability ratio is less than or equal to the path stability ratio threshold, the preset path area is marked as an unstable path area. If the path stability ratio is greater than the path stability ratio threshold, the preset path area is marked as a stable path area.

5. A wake-up method based on a smart speaker according to claim 1, characterized in that The process of evaluating the stability of the wake-up device time of each threshold analysis path and obtaining the wake-up preparation threshold time based on the stability of the wake-up device time of each threshold analysis path is as follows: The wake-up device times of all threshold analysis paths are sorted in ascending order of values, and the first quartile value and the third quartile value in the sorting are extracted to obtain the first quartile wake-up device time and the third quartile wake-up device time. The difference between the first quartile wake-up device time and the third quartile wake-up device time is calculated to obtain a stability characterization value. A preset stability characterization threshold is set, and the stability characterization value is compared and analyzed with the stability characterization threshold. If the stability characterization value is less than or equal to the stability characterization threshold, the first quartile value is marked as the wake-up preparation threshold time. If the stability characterization value is greater than the stability characterization threshold, a section analysis is performed on the stable path area to determine a walking speed stable sub-area and a walking speed unstable sub-area, so as to estimate the wake-up characterization time of the stable path area, and the wake-up characterization time is marked as the wake-up preparation threshold time.

6. The wake-up method based on a smart speaker according to claim 5, wherein The specific process of performing a section analysis on the stable path area to determine a walking speed stable sub-area and a walking speed unstable sub-area, so as to estimate the wake-up characterization time of the stable path area and marking the wake-up characterization time as the wake-up preparation threshold time is as follows: Based on all distance detection points in the stable path area, the walking sub-speeds of the distance detection points in each distance detection period are obtained. Based on any one distance detection point, all the walking sub-speeds of the distance detection point are sorted according to the magnitude of the values, and the first quartile value and the third quartile value in the sorting are extracted to obtain the first quartile walking sub-speed and the third quartile walking sub-speed. The difference between the first quartile walking sub-speed and the third quartile walking sub-speed is calculated to obtain a stability coefficient. Based on the stability coefficient, it is evaluated whether the walking speed of the user at the distance detection point corresponding to the stability coefficient is stable, so as to mark the distance detection point as a speed stable detection point or a speed unstable detection point. Based on all the speed stable detection points and speed unstable detection points in the stable path area, the wake-up characterization time is obtained, and the wake-up characterization time is marked as the wake-up preparation threshold time.

7. The wake-up method based on a smart speaker according to claim 6, wherein The process of evaluating whether the walking speed of the user at the distance detection point corresponding to the stability coefficient is stable based on the stability coefficient, so as to mark the distance detection point as a speed stable detection point or a speed unstable detection point is as follows: Preset a stability coefficient threshold, and compare and analyze the stability coefficient with the stability coefficient threshold; If the stability coefficient is less than or equal to the stability coefficient threshold, mark this distance detection point as a speed stability detection point; If the stability coefficient is greater than the stability coefficient threshold, mark this distance detection point as a speed instability detection point.

8. A wake-up method based on a smart speaker according to claim 6, wherein The process of obtaining the wake-up representation time based on all speed stability detection points and speed instability detection points in the stable path area and marking the wake-up representation time as the wake-up preparation threshold time is as follows: Based on all speed stability detection points and speed instability detection points in the stable path area, divide the stable path area into several sub-areas with stable walking speed and sub-areas with unstable walking speed; Extract the central path of the stable path area to obtain the central identification path, and based on each sub-area with stable walking speed and sub-area with unstable walking speed passed by the central identification path, obtain the wake-up representation time and mark the wake-up representation time as the wake-up preparation threshold time.

9. A wake-up system based on a smart speaker, characterized in that, The system is used to execute the method described in any one of the above claims 1-8. The system includes: Distance detection module: By detecting the signal strength of the target wireless device worn by the user, obtain the target wireless device distance reflecting the distance between the user and the smart speaker; Status regulation module: Based on the target wireless device distance, preset a first distance threshold and a second distance threshold, so as to evaluate the relative position relationship between the user and the smart speaker, and determine the working state of the smart speaker accordingly; Second distance threshold setting sub-module: Preset a threshold analysis point, extract the time required for the user to reach the first distance threshold from the threshold analysis point to obtain the user walking time, compare and analyze the user walking time with the smart speaker wake-up time. If the user walking time is equal to the smart speaker wake-up time, mark the user walking time as the wake-up preparation threshold time, and mark this threshold analysis point as the second distance threshold point. The distance from the second distance threshold point to the smart speaker is set as the second distance threshold; The process of obtaining the wake-up preparation threshold time is as follows: Extract the positions of each distance detection point in the historical data to obtain multiple historical paths; Preset a path area, calculate the ratio of the number of historical paths within the preset path area to the total number of all historical paths to obtain the path stability ratio; Based on the path stability ratio, mark the preset path area as an unstable path area or a stable path area; If the threshold analysis point is in the unstable path area, extract the historical path with the shortest wake-up device time passing through the threshold analysis point, and mark the wake-up device time of this historical path as the wake-up preparation threshold time; If the threshold analysis point is in the stable path area, in the historical data, extract all historical paths within this stable path area, mark them as threshold analysis paths, and extract the wake-up device time of each threshold analysis path; Evaluate the stability of the wake-up device time of each threshold analysis path, and based on the stability of the wake-up device time of each threshold analysis path, obtain the wake-up preparation threshold time.

Images